PEFT
TensorBoard
Safetensors
llama
alignment-handbook
trl
sft
Generated from Trainer
lillian039's picture
Model save
10aa50f verified
raw
history blame
101 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.9982608695652173,
"eval_steps": 500,
"global_step": 574,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0036036036036036037,
"grad_norm": 0.1164047870616515,
"learning_rate": 3.5714285714285714e-06,
"loss": 0.1263,
"step": 1
},
{
"epoch": 0.007207207207207207,
"grad_norm": 0.1627219461416066,
"learning_rate": 7.142857142857143e-06,
"loss": 0.1446,
"step": 2
},
{
"epoch": 0.010810810810810811,
"grad_norm": 0.1157756817304506,
"learning_rate": 1.0714285714285714e-05,
"loss": 0.1441,
"step": 3
},
{
"epoch": 0.014414414414414415,
"grad_norm": 0.14566785288918435,
"learning_rate": 1.4285714285714285e-05,
"loss": 0.1466,
"step": 4
},
{
"epoch": 0.018018018018018018,
"grad_norm": 0.13068033224281192,
"learning_rate": 1.785714285714286e-05,
"loss": 0.1342,
"step": 5
},
{
"epoch": 0.021621621621621623,
"grad_norm": 0.15128910055561917,
"learning_rate": 2.1428571428571428e-05,
"loss": 0.1263,
"step": 6
},
{
"epoch": 0.025225225225225224,
"grad_norm": 0.12625301643275005,
"learning_rate": 2.5e-05,
"loss": 0.1306,
"step": 7
},
{
"epoch": 0.02882882882882883,
"grad_norm": 0.1341542973939784,
"learning_rate": 2.857142857142857e-05,
"loss": 0.1132,
"step": 8
},
{
"epoch": 0.032432432432432434,
"grad_norm": 0.09503727827074428,
"learning_rate": 3.2142857142857144e-05,
"loss": 0.0921,
"step": 9
},
{
"epoch": 0.036036036036036036,
"grad_norm": 0.13724411508071346,
"learning_rate": 3.571428571428572e-05,
"loss": 0.123,
"step": 10
},
{
"epoch": 0.03963963963963964,
"grad_norm": 0.1249162520121657,
"learning_rate": 3.928571428571429e-05,
"loss": 0.1183,
"step": 11
},
{
"epoch": 0.043243243243243246,
"grad_norm": 0.14002577339626954,
"learning_rate": 4.2857142857142856e-05,
"loss": 0.1297,
"step": 12
},
{
"epoch": 0.04684684684684685,
"grad_norm": 0.12032689516166056,
"learning_rate": 4.642857142857143e-05,
"loss": 0.1144,
"step": 13
},
{
"epoch": 0.05045045045045045,
"grad_norm": 0.11822508923100593,
"learning_rate": 5e-05,
"loss": 0.127,
"step": 14
},
{
"epoch": 0.05405405405405406,
"grad_norm": 0.12626847998511856,
"learning_rate": 5.3571428571428575e-05,
"loss": 0.1246,
"step": 15
},
{
"epoch": 0.05765765765765766,
"grad_norm": 0.1394135180306787,
"learning_rate": 5.714285714285714e-05,
"loss": 0.1249,
"step": 16
},
{
"epoch": 0.06126126126126126,
"grad_norm": 0.1486627737985617,
"learning_rate": 6.0714285714285715e-05,
"loss": 0.1156,
"step": 17
},
{
"epoch": 0.06486486486486487,
"grad_norm": 0.08348858837628631,
"learning_rate": 6.428571428571429e-05,
"loss": 0.0972,
"step": 18
},
{
"epoch": 0.06846846846846846,
"grad_norm": 0.19888777350730014,
"learning_rate": 6.785714285714286e-05,
"loss": 0.146,
"step": 19
},
{
"epoch": 0.07207207207207207,
"grad_norm": 0.12757635434343284,
"learning_rate": 7.142857142857143e-05,
"loss": 0.109,
"step": 20
},
{
"epoch": 0.07567567567567568,
"grad_norm": 0.17261365946211904,
"learning_rate": 7.500000000000001e-05,
"loss": 0.139,
"step": 21
},
{
"epoch": 0.07927927927927927,
"grad_norm": 0.19568066543467844,
"learning_rate": 7.857142857142858e-05,
"loss": 0.1366,
"step": 22
},
{
"epoch": 0.08288288288288288,
"grad_norm": 0.20224174296046235,
"learning_rate": 8.214285714285714e-05,
"loss": 0.1437,
"step": 23
},
{
"epoch": 0.08648648648648649,
"grad_norm": 0.24075864691751864,
"learning_rate": 8.571428571428571e-05,
"loss": 0.16,
"step": 24
},
{
"epoch": 0.09009009009009009,
"grad_norm": 0.1506076228406242,
"learning_rate": 8.92857142857143e-05,
"loss": 0.1074,
"step": 25
},
{
"epoch": 0.0936936936936937,
"grad_norm": 0.16087708567600026,
"learning_rate": 9.285714285714286e-05,
"loss": 0.1071,
"step": 26
},
{
"epoch": 0.0972972972972973,
"grad_norm": 0.15632293632911032,
"learning_rate": 9.642857142857143e-05,
"loss": 0.115,
"step": 27
},
{
"epoch": 0.1009009009009009,
"grad_norm": 0.15351274455794925,
"learning_rate": 0.0001,
"loss": 0.1083,
"step": 28
},
{
"epoch": 0.1045045045045045,
"grad_norm": 0.17410060629498864,
"learning_rate": 0.00010357142857142859,
"loss": 0.1143,
"step": 29
},
{
"epoch": 0.10810810810810811,
"grad_norm": 0.11003201267949979,
"learning_rate": 0.00010714285714285715,
"loss": 0.0822,
"step": 30
},
{
"epoch": 0.11171171171171171,
"grad_norm": 0.14850855070731758,
"learning_rate": 0.00011071428571428572,
"loss": 0.1422,
"step": 31
},
{
"epoch": 0.11531531531531532,
"grad_norm": 0.11574892051893418,
"learning_rate": 0.00011428571428571428,
"loss": 0.0917,
"step": 32
},
{
"epoch": 0.11891891891891893,
"grad_norm": 0.12172342587299105,
"learning_rate": 0.00011785714285714287,
"loss": 0.1125,
"step": 33
},
{
"epoch": 0.12252252252252252,
"grad_norm": 0.10233939138594608,
"learning_rate": 0.00012142857142857143,
"loss": 0.0916,
"step": 34
},
{
"epoch": 0.12612612612612611,
"grad_norm": 0.1277262526433454,
"learning_rate": 0.000125,
"loss": 0.1168,
"step": 35
},
{
"epoch": 0.12972972972972974,
"grad_norm": 0.1510932624260595,
"learning_rate": 0.00012857142857142858,
"loss": 0.1366,
"step": 36
},
{
"epoch": 0.13333333333333333,
"grad_norm": 0.1381015918157766,
"learning_rate": 0.00013214285714285715,
"loss": 0.1112,
"step": 37
},
{
"epoch": 0.13693693693693693,
"grad_norm": 0.12744142332679428,
"learning_rate": 0.00013571428571428572,
"loss": 0.1169,
"step": 38
},
{
"epoch": 0.14054054054054055,
"grad_norm": 0.12605036861900049,
"learning_rate": 0.0001392857142857143,
"loss": 0.1265,
"step": 39
},
{
"epoch": 0.14414414414414414,
"grad_norm": 0.09494597572244792,
"learning_rate": 0.00014285714285714287,
"loss": 0.0856,
"step": 40
},
{
"epoch": 0.14774774774774774,
"grad_norm": 0.11563858827548382,
"learning_rate": 0.00014642857142857141,
"loss": 0.091,
"step": 41
},
{
"epoch": 0.15135135135135136,
"grad_norm": 0.10978464408087514,
"learning_rate": 0.00015000000000000001,
"loss": 0.0934,
"step": 42
},
{
"epoch": 0.15495495495495495,
"grad_norm": 0.14748905325763195,
"learning_rate": 0.0001535714285714286,
"loss": 0.1042,
"step": 43
},
{
"epoch": 0.15855855855855855,
"grad_norm": 0.15028736539177057,
"learning_rate": 0.00015714285714285716,
"loss": 0.1232,
"step": 44
},
{
"epoch": 0.16216216216216217,
"grad_norm": 0.16834971174993532,
"learning_rate": 0.00016071428571428573,
"loss": 0.1388,
"step": 45
},
{
"epoch": 0.16576576576576577,
"grad_norm": 0.1364758084150375,
"learning_rate": 0.00016428571428571428,
"loss": 0.1245,
"step": 46
},
{
"epoch": 0.16936936936936936,
"grad_norm": 0.1906244918264085,
"learning_rate": 0.00016785714285714288,
"loss": 0.1419,
"step": 47
},
{
"epoch": 0.17297297297297298,
"grad_norm": 0.15582113106280285,
"learning_rate": 0.00017142857142857143,
"loss": 0.1284,
"step": 48
},
{
"epoch": 0.17657657657657658,
"grad_norm": 0.1653708513472312,
"learning_rate": 0.000175,
"loss": 0.1265,
"step": 49
},
{
"epoch": 0.18018018018018017,
"grad_norm": 0.11080370021143991,
"learning_rate": 0.0001785714285714286,
"loss": 0.1136,
"step": 50
},
{
"epoch": 0.1837837837837838,
"grad_norm": 0.14497196744014715,
"learning_rate": 0.00018214285714285714,
"loss": 0.1336,
"step": 51
},
{
"epoch": 0.1873873873873874,
"grad_norm": 0.11471991362976224,
"learning_rate": 0.00018571428571428572,
"loss": 0.1009,
"step": 52
},
{
"epoch": 0.19099099099099098,
"grad_norm": 0.1518492774928798,
"learning_rate": 0.0001892857142857143,
"loss": 0.1445,
"step": 53
},
{
"epoch": 0.1945945945945946,
"grad_norm": 0.15638927885876117,
"learning_rate": 0.00019285714285714286,
"loss": 0.1095,
"step": 54
},
{
"epoch": 0.1981981981981982,
"grad_norm": 0.12245693248057901,
"learning_rate": 0.00019642857142857144,
"loss": 0.099,
"step": 55
},
{
"epoch": 0.2018018018018018,
"grad_norm": 0.13146029758520172,
"learning_rate": 0.0002,
"loss": 0.1215,
"step": 56
},
{
"epoch": 0.20540540540540542,
"grad_norm": 0.1449923810118862,
"learning_rate": 0.00019999801019909556,
"loss": 0.1376,
"step": 57
},
{
"epoch": 0.209009009009009,
"grad_norm": 0.12275432649506118,
"learning_rate": 0.0001999920408755684,
"loss": 0.111,
"step": 58
},
{
"epoch": 0.2126126126126126,
"grad_norm": 0.13294914056261917,
"learning_rate": 0.00019998209226697376,
"loss": 0.1184,
"step": 59
},
{
"epoch": 0.21621621621621623,
"grad_norm": 0.11587311682416103,
"learning_rate": 0.00019996816476922677,
"loss": 0.1029,
"step": 60
},
{
"epoch": 0.21981981981981982,
"grad_norm": 0.211706197616785,
"learning_rate": 0.00019995025893658627,
"loss": 0.1323,
"step": 61
},
{
"epoch": 0.22342342342342342,
"grad_norm": 0.135734632583536,
"learning_rate": 0.00019992837548163316,
"loss": 0.1073,
"step": 62
},
{
"epoch": 0.22702702702702704,
"grad_norm": 0.1916821730614324,
"learning_rate": 0.00019990251527524178,
"loss": 0.1287,
"step": 63
},
{
"epoch": 0.23063063063063063,
"grad_norm": 0.1696786518231171,
"learning_rate": 0.00019987267934654538,
"loss": 0.1467,
"step": 64
},
{
"epoch": 0.23423423423423423,
"grad_norm": 0.1556597769170162,
"learning_rate": 0.00019983886888289514,
"loss": 0.1074,
"step": 65
},
{
"epoch": 0.23783783783783785,
"grad_norm": 0.11435037299616506,
"learning_rate": 0.00019980108522981284,
"loss": 0.1054,
"step": 66
},
{
"epoch": 0.24144144144144145,
"grad_norm": 0.1377527772698083,
"learning_rate": 0.00019975932989093747,
"loss": 0.1167,
"step": 67
},
{
"epoch": 0.24504504504504504,
"grad_norm": 0.13089085083126692,
"learning_rate": 0.00019971360452796522,
"loss": 0.1268,
"step": 68
},
{
"epoch": 0.24864864864864866,
"grad_norm": 0.1461221542311374,
"learning_rate": 0.00019966391096058346,
"loss": 0.1353,
"step": 69
},
{
"epoch": 0.25225225225225223,
"grad_norm": 0.10972604571483792,
"learning_rate": 0.0001996102511663983,
"loss": 0.0839,
"step": 70
},
{
"epoch": 0.25585585585585585,
"grad_norm": 0.14694411558687645,
"learning_rate": 0.0001995526272808559,
"loss": 0.1266,
"step": 71
},
{
"epoch": 0.2594594594594595,
"grad_norm": 0.2623900472581046,
"learning_rate": 0.00019949104159715743,
"loss": 0.1192,
"step": 72
},
{
"epoch": 0.26306306306306304,
"grad_norm": 0.14253202316127417,
"learning_rate": 0.0001994254965661679,
"loss": 0.1268,
"step": 73
},
{
"epoch": 0.26666666666666666,
"grad_norm": 0.22775504622269988,
"learning_rate": 0.0001993559947963185,
"loss": 0.1624,
"step": 74
},
{
"epoch": 0.2702702702702703,
"grad_norm": 0.18974052313619846,
"learning_rate": 0.00019928253905350296,
"loss": 0.1656,
"step": 75
},
{
"epoch": 0.27387387387387385,
"grad_norm": 0.18281811162027828,
"learning_rate": 0.00019920513226096733,
"loss": 0.1512,
"step": 76
},
{
"epoch": 0.2774774774774775,
"grad_norm": 0.15981121539784604,
"learning_rate": 0.00019912377749919374,
"loss": 0.1414,
"step": 77
},
{
"epoch": 0.2810810810810811,
"grad_norm": 0.11107015310290616,
"learning_rate": 0.00019903847800577777,
"loss": 0.0732,
"step": 78
},
{
"epoch": 0.28468468468468466,
"grad_norm": 0.11807284847655806,
"learning_rate": 0.00019894923717529955,
"loss": 0.1158,
"step": 79
},
{
"epoch": 0.2882882882882883,
"grad_norm": 0.1674132871400004,
"learning_rate": 0.00019885605855918885,
"loss": 0.1363,
"step": 80
},
{
"epoch": 0.2918918918918919,
"grad_norm": 0.09521837972620555,
"learning_rate": 0.00019875894586558355,
"loss": 0.0761,
"step": 81
},
{
"epoch": 0.2954954954954955,
"grad_norm": 0.13313059706266978,
"learning_rate": 0.00019865790295918212,
"loss": 0.114,
"step": 82
},
{
"epoch": 0.2990990990990991,
"grad_norm": 0.15752991450823575,
"learning_rate": 0.00019855293386108992,
"loss": 0.1143,
"step": 83
},
{
"epoch": 0.3027027027027027,
"grad_norm": 0.11681361221271575,
"learning_rate": 0.0001984440427486591,
"loss": 0.0955,
"step": 84
},
{
"epoch": 0.3063063063063063,
"grad_norm": 0.1435158350817726,
"learning_rate": 0.00019833123395532226,
"loss": 0.1292,
"step": 85
},
{
"epoch": 0.3099099099099099,
"grad_norm": 0.1174821097766054,
"learning_rate": 0.00019821451197042026,
"loss": 0.119,
"step": 86
},
{
"epoch": 0.31351351351351353,
"grad_norm": 0.14421204301690782,
"learning_rate": 0.00019809388143902332,
"loss": 0.1313,
"step": 87
},
{
"epoch": 0.3171171171171171,
"grad_norm": 0.13517965622709482,
"learning_rate": 0.0001979693471617462,
"loss": 0.1297,
"step": 88
},
{
"epoch": 0.3207207207207207,
"grad_norm": 0.17145867539050777,
"learning_rate": 0.00019784091409455728,
"loss": 0.1359,
"step": 89
},
{
"epoch": 0.32432432432432434,
"grad_norm": 0.11953352813577937,
"learning_rate": 0.00019770858734858126,
"loss": 0.0878,
"step": 90
},
{
"epoch": 0.3279279279279279,
"grad_norm": 0.13673174823647213,
"learning_rate": 0.00019757237218989563,
"loss": 0.1265,
"step": 91
},
{
"epoch": 0.33153153153153153,
"grad_norm": 0.16490479257041854,
"learning_rate": 0.00019743227403932134,
"loss": 0.1393,
"step": 92
},
{
"epoch": 0.33513513513513515,
"grad_norm": 0.12343228690652325,
"learning_rate": 0.000197288298472207,
"loss": 0.1174,
"step": 93
},
{
"epoch": 0.3387387387387387,
"grad_norm": 0.16745916159569352,
"learning_rate": 0.00019714045121820676,
"loss": 0.1235,
"step": 94
},
{
"epoch": 0.34234234234234234,
"grad_norm": 0.16922526895888806,
"learning_rate": 0.00019698873816105273,
"loss": 0.0975,
"step": 95
},
{
"epoch": 0.34594594594594597,
"grad_norm": 0.129484224418453,
"learning_rate": 0.00019683316533832042,
"loss": 0.0928,
"step": 96
},
{
"epoch": 0.34954954954954953,
"grad_norm": 0.1514002748369919,
"learning_rate": 0.0001966737389411887,
"loss": 0.1341,
"step": 97
},
{
"epoch": 0.35315315315315315,
"grad_norm": 0.11053077601153272,
"learning_rate": 0.00019651046531419332,
"loss": 0.09,
"step": 98
},
{
"epoch": 0.3567567567567568,
"grad_norm": 0.11955256535981768,
"learning_rate": 0.00019634335095497458,
"loss": 0.0978,
"step": 99
},
{
"epoch": 0.36036036036036034,
"grad_norm": 0.12318848470518083,
"learning_rate": 0.0001961724025140185,
"loss": 0.1123,
"step": 100
},
{
"epoch": 0.36396396396396397,
"grad_norm": 0.19878288570661823,
"learning_rate": 0.0001959976267943923,
"loss": 0.1449,
"step": 101
},
{
"epoch": 0.3675675675675676,
"grad_norm": 0.11498348089609609,
"learning_rate": 0.0001958190307514737,
"loss": 0.101,
"step": 102
},
{
"epoch": 0.37117117117117115,
"grad_norm": 0.12807480490548945,
"learning_rate": 0.00019563662149267406,
"loss": 0.1115,
"step": 103
},
{
"epoch": 0.3747747747747748,
"grad_norm": 0.1537951698344796,
"learning_rate": 0.0001954504062771555,
"loss": 0.1099,
"step": 104
},
{
"epoch": 0.3783783783783784,
"grad_norm": 0.13376774584465406,
"learning_rate": 0.0001952603925155422,
"loss": 0.0945,
"step": 105
},
{
"epoch": 0.38198198198198197,
"grad_norm": 0.11095795904499461,
"learning_rate": 0.0001950665877696252,
"loss": 0.1001,
"step": 106
},
{
"epoch": 0.3855855855855856,
"grad_norm": 0.1176293890483276,
"learning_rate": 0.00019486899975206166,
"loss": 0.1114,
"step": 107
},
{
"epoch": 0.3891891891891892,
"grad_norm": 0.16600471258328028,
"learning_rate": 0.0001946676363260679,
"loss": 0.1565,
"step": 108
},
{
"epoch": 0.3927927927927928,
"grad_norm": 0.12969105825015786,
"learning_rate": 0.0001944625055051065,
"loss": 0.0942,
"step": 109
},
{
"epoch": 0.3963963963963964,
"grad_norm": 0.1260399594140325,
"learning_rate": 0.00019425361545256727,
"loss": 0.1151,
"step": 110
},
{
"epoch": 0.4,
"grad_norm": 0.12141152738985596,
"learning_rate": 0.00019404097448144257,
"loss": 0.0953,
"step": 111
},
{
"epoch": 0.4036036036036036,
"grad_norm": 0.16522441528864815,
"learning_rate": 0.00019382459105399632,
"loss": 0.1483,
"step": 112
},
{
"epoch": 0.4072072072072072,
"grad_norm": 0.16464941562962845,
"learning_rate": 0.00019360447378142728,
"loss": 0.1145,
"step": 113
},
{
"epoch": 0.41081081081081083,
"grad_norm": 0.1301041115410939,
"learning_rate": 0.00019338063142352644,
"loss": 0.109,
"step": 114
},
{
"epoch": 0.4144144144144144,
"grad_norm": 0.15394069789981274,
"learning_rate": 0.00019315307288832835,
"loss": 0.1484,
"step": 115
},
{
"epoch": 0.418018018018018,
"grad_norm": 0.1337025315682798,
"learning_rate": 0.00019292180723175654,
"loss": 0.1083,
"step": 116
},
{
"epoch": 0.42162162162162165,
"grad_norm": 0.11697191221298965,
"learning_rate": 0.00019268684365726326,
"loss": 0.1104,
"step": 117
},
{
"epoch": 0.4252252252252252,
"grad_norm": 0.14885108765057334,
"learning_rate": 0.00019244819151546322,
"loss": 0.1349,
"step": 118
},
{
"epoch": 0.42882882882882883,
"grad_norm": 0.16748465670739565,
"learning_rate": 0.00019220586030376134,
"loss": 0.1375,
"step": 119
},
{
"epoch": 0.43243243243243246,
"grad_norm": 0.16065529576883042,
"learning_rate": 0.00019195985966597494,
"loss": 0.1158,
"step": 120
},
{
"epoch": 0.436036036036036,
"grad_norm": 0.14710431466862364,
"learning_rate": 0.0001917101993919498,
"loss": 0.1123,
"step": 121
},
{
"epoch": 0.43963963963963965,
"grad_norm": 0.1535583565878682,
"learning_rate": 0.00019145688941717075,
"loss": 0.1244,
"step": 122
},
{
"epoch": 0.44324324324324327,
"grad_norm": 0.15887496082691002,
"learning_rate": 0.00019119993982236606,
"loss": 0.1099,
"step": 123
},
{
"epoch": 0.44684684684684683,
"grad_norm": 0.17132720394894463,
"learning_rate": 0.00019093936083310653,
"loss": 0.1366,
"step": 124
},
{
"epoch": 0.45045045045045046,
"grad_norm": 0.1304195997449305,
"learning_rate": 0.00019067516281939825,
"loss": 0.1042,
"step": 125
},
{
"epoch": 0.4540540540540541,
"grad_norm": 0.13720183539624425,
"learning_rate": 0.00019040735629527027,
"loss": 0.0939,
"step": 126
},
{
"epoch": 0.45765765765765765,
"grad_norm": 0.1878348429175824,
"learning_rate": 0.00019013595191835574,
"loss": 0.1421,
"step": 127
},
{
"epoch": 0.46126126126126127,
"grad_norm": 0.15221296411188612,
"learning_rate": 0.00018986096048946824,
"loss": 0.1207,
"step": 128
},
{
"epoch": 0.4648648648648649,
"grad_norm": 0.12530318604533355,
"learning_rate": 0.0001895823929521716,
"loss": 0.1101,
"step": 129
},
{
"epoch": 0.46846846846846846,
"grad_norm": 0.11753990553496706,
"learning_rate": 0.0001893002603923446,
"loss": 0.0814,
"step": 130
},
{
"epoch": 0.4720720720720721,
"grad_norm": 0.15143122574748422,
"learning_rate": 0.00018901457403773967,
"loss": 0.1259,
"step": 131
},
{
"epoch": 0.4756756756756757,
"grad_norm": 0.12436714806981373,
"learning_rate": 0.00018872534525753615,
"loss": 0.1148,
"step": 132
},
{
"epoch": 0.47927927927927927,
"grad_norm": 0.13100199539485474,
"learning_rate": 0.00018843258556188787,
"loss": 0.1189,
"step": 133
},
{
"epoch": 0.4828828828828829,
"grad_norm": 0.1667053146851425,
"learning_rate": 0.00018813630660146488,
"loss": 0.1494,
"step": 134
},
{
"epoch": 0.4864864864864865,
"grad_norm": 0.09073673518826318,
"learning_rate": 0.00018783652016699014,
"loss": 0.0799,
"step": 135
},
{
"epoch": 0.4900900900900901,
"grad_norm": 0.13343062211829884,
"learning_rate": 0.0001875332381887699,
"loss": 0.1241,
"step": 136
},
{
"epoch": 0.4936936936936937,
"grad_norm": 0.12750970397329575,
"learning_rate": 0.0001872264727362194,
"loss": 0.1386,
"step": 137
},
{
"epoch": 0.4972972972972973,
"grad_norm": 0.10441877909622974,
"learning_rate": 0.00018691623601738199,
"loss": 0.0888,
"step": 138
},
{
"epoch": 0.5009009009009009,
"grad_norm": 0.14478179850573814,
"learning_rate": 0.00018660254037844388,
"loss": 0.1056,
"step": 139
},
{
"epoch": 0.5045045045045045,
"grad_norm": 0.13712755003139512,
"learning_rate": 0.00018628539830324229,
"loss": 0.1489,
"step": 140
},
{
"epoch": 0.5081081081081081,
"grad_norm": 0.12379021926600628,
"learning_rate": 0.000185964822412769,
"loss": 0.1071,
"step": 141
},
{
"epoch": 0.5117117117117117,
"grad_norm": 0.12266406139545731,
"learning_rate": 0.00018564082546466805,
"loss": 0.1141,
"step": 142
},
{
"epoch": 0.5153153153153153,
"grad_norm": 0.09332411107267007,
"learning_rate": 0.00018531342035272766,
"loss": 0.0876,
"step": 143
},
{
"epoch": 0.518918918918919,
"grad_norm": 0.12722229275266542,
"learning_rate": 0.00018498262010636774,
"loss": 0.123,
"step": 144
},
{
"epoch": 0.5225225225225225,
"grad_norm": 0.1934624210241968,
"learning_rate": 0.00018464843789012085,
"loss": 0.1891,
"step": 145
},
{
"epoch": 0.5261261261261261,
"grad_norm": 0.1202206919464269,
"learning_rate": 0.00018431088700310844,
"loss": 0.1157,
"step": 146
},
{
"epoch": 0.5297297297297298,
"grad_norm": 0.11855534138749764,
"learning_rate": 0.0001839699808785118,
"loss": 0.1126,
"step": 147
},
{
"epoch": 0.5333333333333333,
"grad_norm": 0.10719514027165045,
"learning_rate": 0.00018362573308303718,
"loss": 0.0907,
"step": 148
},
{
"epoch": 0.5369369369369369,
"grad_norm": 0.11210467216409752,
"learning_rate": 0.00018327815731637612,
"loss": 0.1007,
"step": 149
},
{
"epoch": 0.5405405405405406,
"grad_norm": 0.12526617885340885,
"learning_rate": 0.00018292726741066007,
"loss": 0.1049,
"step": 150
},
{
"epoch": 0.5441441441441441,
"grad_norm": 0.1477303393799172,
"learning_rate": 0.00018257307732991008,
"loss": 0.1516,
"step": 151
},
{
"epoch": 0.5477477477477477,
"grad_norm": 0.14857702506705278,
"learning_rate": 0.00018221560116948103,
"loss": 0.1453,
"step": 152
},
{
"epoch": 0.5513513513513514,
"grad_norm": 0.14008518634545825,
"learning_rate": 0.0001818548531555006,
"loss": 0.1297,
"step": 153
},
{
"epoch": 0.554954954954955,
"grad_norm": 0.12658212522638404,
"learning_rate": 0.0001814908476443034,
"loss": 0.1155,
"step": 154
},
{
"epoch": 0.5585585585585585,
"grad_norm": 0.149670716923037,
"learning_rate": 0.00018112359912185924,
"loss": 0.1211,
"step": 155
},
{
"epoch": 0.5621621621621622,
"grad_norm": 0.11342605203968036,
"learning_rate": 0.000180753122203197,
"loss": 0.0899,
"step": 156
},
{
"epoch": 0.5657657657657658,
"grad_norm": 0.15888593819383173,
"learning_rate": 0.00018037943163182283,
"loss": 0.1445,
"step": 157
},
{
"epoch": 0.5693693693693693,
"grad_norm": 0.12437893978089608,
"learning_rate": 0.00018000254227913348,
"loss": 0.1152,
"step": 158
},
{
"epoch": 0.572972972972973,
"grad_norm": 0.11638937373238138,
"learning_rate": 0.0001796224691438244,
"loss": 0.1123,
"step": 159
},
{
"epoch": 0.5765765765765766,
"grad_norm": 0.14812854362945038,
"learning_rate": 0.00017923922735129302,
"loss": 0.1263,
"step": 160
},
{
"epoch": 0.5801801801801801,
"grad_norm": 0.10770071386782099,
"learning_rate": 0.0001788528321530366,
"loss": 0.0955,
"step": 161
},
{
"epoch": 0.5837837837837838,
"grad_norm": 0.1870539683925041,
"learning_rate": 0.00017846329892604547,
"loss": 0.1124,
"step": 162
},
{
"epoch": 0.5873873873873874,
"grad_norm": 0.1560374478952629,
"learning_rate": 0.00017807064317219094,
"loss": 0.122,
"step": 163
},
{
"epoch": 0.590990990990991,
"grad_norm": 0.14789972168680796,
"learning_rate": 0.00017767488051760857,
"loss": 0.0955,
"step": 164
},
{
"epoch": 0.5945945945945946,
"grad_norm": 0.17954009944461283,
"learning_rate": 0.00017727602671207605,
"loss": 0.1326,
"step": 165
},
{
"epoch": 0.5981981981981982,
"grad_norm": 0.12473531577026101,
"learning_rate": 0.00017687409762838664,
"loss": 0.139,
"step": 166
},
{
"epoch": 0.6018018018018018,
"grad_norm": 0.18890214448118112,
"learning_rate": 0.00017646910926171747,
"loss": 0.158,
"step": 167
},
{
"epoch": 0.6054054054054054,
"grad_norm": 0.1158510197827391,
"learning_rate": 0.00017606107772899287,
"loss": 0.124,
"step": 168
},
{
"epoch": 0.609009009009009,
"grad_norm": 0.1513359972404607,
"learning_rate": 0.00017565001926824313,
"loss": 0.1535,
"step": 169
},
{
"epoch": 0.6126126126126126,
"grad_norm": 0.11561240472832256,
"learning_rate": 0.00017523595023795813,
"loss": 0.097,
"step": 170
},
{
"epoch": 0.6162162162162163,
"grad_norm": 0.14453378759822266,
"learning_rate": 0.00017481888711643655,
"loss": 0.1369,
"step": 171
},
{
"epoch": 0.6198198198198198,
"grad_norm": 0.10823698221755142,
"learning_rate": 0.00017439884650112989,
"loss": 0.0854,
"step": 172
},
{
"epoch": 0.6234234234234234,
"grad_norm": 0.16461158555393735,
"learning_rate": 0.0001739758451079821,
"loss": 0.1327,
"step": 173
},
{
"epoch": 0.6270270270270271,
"grad_norm": 0.13330810816894179,
"learning_rate": 0.00017354989977076422,
"loss": 0.0988,
"step": 174
},
{
"epoch": 0.6306306306306306,
"grad_norm": 0.1603897957937655,
"learning_rate": 0.00017312102744040467,
"loss": 0.1517,
"step": 175
},
{
"epoch": 0.6342342342342342,
"grad_norm": 0.1387499574229483,
"learning_rate": 0.00017268924518431438,
"loss": 0.1159,
"step": 176
},
{
"epoch": 0.6378378378378379,
"grad_norm": 0.15123399261590567,
"learning_rate": 0.0001722545701857079,
"loss": 0.135,
"step": 177
},
{
"epoch": 0.6414414414414414,
"grad_norm": 0.201686818845506,
"learning_rate": 0.0001718170197429193,
"loss": 0.1601,
"step": 178
},
{
"epoch": 0.645045045045045,
"grad_norm": 0.16050791333444517,
"learning_rate": 0.0001713766112687139,
"loss": 0.1376,
"step": 179
},
{
"epoch": 0.6486486486486487,
"grad_norm": 0.13004224853328716,
"learning_rate": 0.00017093336228959536,
"loss": 0.1191,
"step": 180
},
{
"epoch": 0.6522522522522523,
"grad_norm": 0.10061992398695434,
"learning_rate": 0.000170487290445108,
"loss": 0.0958,
"step": 181
},
{
"epoch": 0.6558558558558558,
"grad_norm": 0.09779721051938423,
"learning_rate": 0.0001700384134871351,
"loss": 0.098,
"step": 182
},
{
"epoch": 0.6594594594594595,
"grad_norm": 0.12862092154540355,
"learning_rate": 0.0001695867492791921,
"loss": 0.1083,
"step": 183
},
{
"epoch": 0.6630630630630631,
"grad_norm": 0.13476322854527875,
"learning_rate": 0.00016913231579571608,
"loss": 0.1466,
"step": 184
},
{
"epoch": 0.6666666666666666,
"grad_norm": 0.09595530640274692,
"learning_rate": 0.00016867513112135013,
"loss": 0.0842,
"step": 185
},
{
"epoch": 0.6702702702702703,
"grad_norm": 0.15679543098949758,
"learning_rate": 0.00016821521345022377,
"loss": 0.1338,
"step": 186
},
{
"epoch": 0.6738738738738739,
"grad_norm": 0.14388550615027906,
"learning_rate": 0.00016775258108522908,
"loss": 0.1125,
"step": 187
},
{
"epoch": 0.6774774774774774,
"grad_norm": 0.14073204006731552,
"learning_rate": 0.0001672872524372919,
"loss": 0.139,
"step": 188
},
{
"epoch": 0.6810810810810811,
"grad_norm": 0.09327785295917886,
"learning_rate": 0.00016681924602463962,
"loss": 0.0876,
"step": 189
},
{
"epoch": 0.6846846846846847,
"grad_norm": 0.0966354577674113,
"learning_rate": 0.00016634858047206378,
"loss": 0.0817,
"step": 190
},
{
"epoch": 0.6882882882882883,
"grad_norm": 0.1298212529485729,
"learning_rate": 0.00016587527451017938,
"loss": 0.1248,
"step": 191
},
{
"epoch": 0.6918918918918919,
"grad_norm": 0.15190505228456444,
"learning_rate": 0.00016539934697467894,
"loss": 0.1346,
"step": 192
},
{
"epoch": 0.6954954954954955,
"grad_norm": 0.12074435445615049,
"learning_rate": 0.0001649208168055833,
"loss": 0.1218,
"step": 193
},
{
"epoch": 0.6990990990990991,
"grad_norm": 0.11339361129121636,
"learning_rate": 0.0001644397030464877,
"loss": 0.0945,
"step": 194
},
{
"epoch": 0.7027027027027027,
"grad_norm": 0.1480633681266718,
"learning_rate": 0.00016395602484380406,
"loss": 0.143,
"step": 195
},
{
"epoch": 0.7063063063063063,
"grad_norm": 0.13202765755871132,
"learning_rate": 0.0001634698014459988,
"loss": 0.1256,
"step": 196
},
{
"epoch": 0.7099099099099099,
"grad_norm": 0.10905065599283695,
"learning_rate": 0.00016298105220282713,
"loss": 0.1024,
"step": 197
},
{
"epoch": 0.7135135135135136,
"grad_norm": 0.10616436723037755,
"learning_rate": 0.00016248979656456275,
"loss": 0.1066,
"step": 198
},
{
"epoch": 0.7171171171171171,
"grad_norm": 0.1063733952868901,
"learning_rate": 0.0001619960540812239,
"loss": 0.1065,
"step": 199
},
{
"epoch": 0.7207207207207207,
"grad_norm": 0.1648449550913926,
"learning_rate": 0.00016149984440179537,
"loss": 0.1416,
"step": 200
},
{
"epoch": 0.7243243243243244,
"grad_norm": 0.14504142427358913,
"learning_rate": 0.00016100118727344659,
"loss": 0.1323,
"step": 201
},
{
"epoch": 0.7279279279279279,
"grad_norm": 0.15511743070098452,
"learning_rate": 0.00016050010254074564,
"loss": 0.1259,
"step": 202
},
{
"epoch": 0.7315315315315315,
"grad_norm": 0.12280785450706579,
"learning_rate": 0.00015999661014486956,
"loss": 0.1165,
"step": 203
},
{
"epoch": 0.7351351351351352,
"grad_norm": 0.13888404263902684,
"learning_rate": 0.00015949073012281093,
"loss": 0.1047,
"step": 204
},
{
"epoch": 0.7387387387387387,
"grad_norm": 0.10651036692593711,
"learning_rate": 0.00015898248260658016,
"loss": 0.1181,
"step": 205
},
{
"epoch": 0.7423423423423423,
"grad_norm": 0.10861974936989245,
"learning_rate": 0.0001584718878224047,
"loss": 0.1064,
"step": 206
},
{
"epoch": 0.745945945945946,
"grad_norm": 0.10231866176721904,
"learning_rate": 0.00015795896608992378,
"loss": 0.0988,
"step": 207
},
{
"epoch": 0.7495495495495496,
"grad_norm": 0.15024568241023914,
"learning_rate": 0.00015744373782137992,
"loss": 0.1489,
"step": 208
},
{
"epoch": 0.7531531531531531,
"grad_norm": 0.12371588452286458,
"learning_rate": 0.00015692622352080662,
"loss": 0.116,
"step": 209
},
{
"epoch": 0.7567567567567568,
"grad_norm": 0.11392721432010788,
"learning_rate": 0.00015640644378321235,
"loss": 0.1015,
"step": 210
},
{
"epoch": 0.7603603603603604,
"grad_norm": 0.11201427932233406,
"learning_rate": 0.00015588441929376097,
"loss": 0.0863,
"step": 211
},
{
"epoch": 0.7639639639639639,
"grad_norm": 0.159849063390471,
"learning_rate": 0.00015536017082694846,
"loss": 0.1651,
"step": 212
},
{
"epoch": 0.7675675675675676,
"grad_norm": 0.13935698141384686,
"learning_rate": 0.00015483371924577635,
"loss": 0.1262,
"step": 213
},
{
"epoch": 0.7711711711711712,
"grad_norm": 0.15388913192797118,
"learning_rate": 0.00015430508550092124,
"loss": 0.1602,
"step": 214
},
{
"epoch": 0.7747747747747747,
"grad_norm": 0.11744911276482749,
"learning_rate": 0.00015377429062990122,
"loss": 0.1082,
"step": 215
},
{
"epoch": 0.7783783783783784,
"grad_norm": 0.14669529425537173,
"learning_rate": 0.00015324135575623857,
"loss": 0.1329,
"step": 216
},
{
"epoch": 0.781981981981982,
"grad_norm": 0.09725689202217797,
"learning_rate": 0.00015270630208861916,
"loss": 0.1001,
"step": 217
},
{
"epoch": 0.7855855855855856,
"grad_norm": 0.09066648478601479,
"learning_rate": 0.00015216915092004847,
"loss": 0.1005,
"step": 218
},
{
"epoch": 0.7891891891891892,
"grad_norm": 0.10556590806339675,
"learning_rate": 0.00015162992362700406,
"loss": 0.104,
"step": 219
},
{
"epoch": 0.7927927927927928,
"grad_norm": 0.10568504388848617,
"learning_rate": 0.00015108864166858506,
"loss": 0.1079,
"step": 220
},
{
"epoch": 0.7963963963963964,
"grad_norm": 0.13168798693648778,
"learning_rate": 0.0001505453265856581,
"loss": 0.1319,
"step": 221
},
{
"epoch": 0.8,
"grad_norm": 0.11471998852906086,
"learning_rate": 0.00015000000000000001,
"loss": 0.1181,
"step": 222
},
{
"epoch": 0.8036036036036036,
"grad_norm": 0.11715811264986671,
"learning_rate": 0.00014945268361343748,
"loss": 0.1053,
"step": 223
},
{
"epoch": 0.8072072072072072,
"grad_norm": 0.10491568472945026,
"learning_rate": 0.00014890339920698334,
"loss": 0.0931,
"step": 224
},
{
"epoch": 0.8108108108108109,
"grad_norm": 0.1381588520705617,
"learning_rate": 0.00014835216863996975,
"loss": 0.1417,
"step": 225
},
{
"epoch": 0.8144144144144144,
"grad_norm": 0.15507649891779268,
"learning_rate": 0.0001477990138491783,
"loss": 0.1418,
"step": 226
},
{
"epoch": 0.818018018018018,
"grad_norm": 0.11750139732263555,
"learning_rate": 0.0001472439568479671,
"loss": 0.1207,
"step": 227
},
{
"epoch": 0.8216216216216217,
"grad_norm": 0.12736893690378323,
"learning_rate": 0.00014668701972539458,
"loss": 0.1277,
"step": 228
},
{
"epoch": 0.8252252252252252,
"grad_norm": 0.11333975714941213,
"learning_rate": 0.00014612822464534059,
"loss": 0.1113,
"step": 229
},
{
"epoch": 0.8288288288288288,
"grad_norm": 0.11811846805876995,
"learning_rate": 0.00014556759384562416,
"loss": 0.1174,
"step": 230
},
{
"epoch": 0.8324324324324325,
"grad_norm": 0.12819157247369997,
"learning_rate": 0.00014500514963711883,
"loss": 0.1143,
"step": 231
},
{
"epoch": 0.836036036036036,
"grad_norm": 0.11727175144557134,
"learning_rate": 0.0001444409144028644,
"loss": 0.1153,
"step": 232
},
{
"epoch": 0.8396396396396396,
"grad_norm": 0.13457703292067713,
"learning_rate": 0.00014387491059717652,
"loss": 0.1199,
"step": 233
},
{
"epoch": 0.8432432432432433,
"grad_norm": 0.11901299124274167,
"learning_rate": 0.00014330716074475286,
"loss": 0.1147,
"step": 234
},
{
"epoch": 0.8468468468468469,
"grad_norm": 0.10353994887251415,
"learning_rate": 0.00014273768743977685,
"loss": 0.1026,
"step": 235
},
{
"epoch": 0.8504504504504504,
"grad_norm": 0.10419191980690304,
"learning_rate": 0.0001421665133450184,
"loss": 0.1063,
"step": 236
},
{
"epoch": 0.8540540540540541,
"grad_norm": 0.12748698891225302,
"learning_rate": 0.00014159366119093214,
"loss": 0.1079,
"step": 237
},
{
"epoch": 0.8576576576576577,
"grad_norm": 0.16200721887310557,
"learning_rate": 0.00014101915377475274,
"loss": 0.1152,
"step": 238
},
{
"epoch": 0.8612612612612612,
"grad_norm": 0.15795975577284813,
"learning_rate": 0.0001404430139595877,
"loss": 0.1542,
"step": 239
},
{
"epoch": 0.8648648648648649,
"grad_norm": 0.14933463930244448,
"learning_rate": 0.0001398652646735076,
"loss": 0.1236,
"step": 240
},
{
"epoch": 0.8684684684684685,
"grad_norm": 0.16198753222835588,
"learning_rate": 0.0001392859289086334,
"loss": 0.1375,
"step": 241
},
{
"epoch": 0.872072072072072,
"grad_norm": 0.13433467388254222,
"learning_rate": 0.00013870502972022173,
"loss": 0.1323,
"step": 242
},
{
"epoch": 0.8756756756756757,
"grad_norm": 0.12593674925296103,
"learning_rate": 0.00013812259022574717,
"loss": 0.1216,
"step": 243
},
{
"epoch": 0.8792792792792793,
"grad_norm": 0.13013719230493928,
"learning_rate": 0.00013753863360398241,
"loss": 0.1247,
"step": 244
},
{
"epoch": 0.8828828828828829,
"grad_norm": 0.11799267349520824,
"learning_rate": 0.0001369531830940757,
"loss": 0.1086,
"step": 245
},
{
"epoch": 0.8864864864864865,
"grad_norm": 0.08312084262618047,
"learning_rate": 0.00013636626199462615,
"loss": 0.0813,
"step": 246
},
{
"epoch": 0.8900900900900901,
"grad_norm": 0.1338651554767216,
"learning_rate": 0.00013577789366275644,
"loss": 0.137,
"step": 247
},
{
"epoch": 0.8936936936936937,
"grad_norm": 0.10150227632820087,
"learning_rate": 0.0001351881015131833,
"loss": 0.0975,
"step": 248
},
{
"epoch": 0.8972972972972973,
"grad_norm": 0.10189929428402296,
"learning_rate": 0.00013459690901728588,
"loss": 0.0923,
"step": 249
},
{
"epoch": 0.9009009009009009,
"grad_norm": 0.1408210936693087,
"learning_rate": 0.00013400433970217135,
"loss": 0.1378,
"step": 250
},
{
"epoch": 0.9045045045045045,
"grad_norm": 0.11765895193363322,
"learning_rate": 0.000133410417149739,
"loss": 0.1096,
"step": 251
},
{
"epoch": 0.9081081081081082,
"grad_norm": 0.1413792560787727,
"learning_rate": 0.00013281516499574135,
"loss": 0.1401,
"step": 252
},
{
"epoch": 0.9117117117117117,
"grad_norm": 0.08054406846656884,
"learning_rate": 0.00013221860692884396,
"loss": 0.0835,
"step": 253
},
{
"epoch": 0.9153153153153153,
"grad_norm": 0.12127761773938303,
"learning_rate": 0.0001316207666896824,
"loss": 0.118,
"step": 254
},
{
"epoch": 0.918918918918919,
"grad_norm": 0.10139113989817501,
"learning_rate": 0.00013102166806991768,
"loss": 0.0966,
"step": 255
},
{
"epoch": 0.9225225225225225,
"grad_norm": 0.10511129293269068,
"learning_rate": 0.00013042133491128935,
"loss": 0.0846,
"step": 256
},
{
"epoch": 0.9261261261261261,
"grad_norm": 0.13928639672942275,
"learning_rate": 0.00012981979110466654,
"loss": 0.1106,
"step": 257
},
{
"epoch": 0.9297297297297298,
"grad_norm": 0.1575504268549112,
"learning_rate": 0.00012921706058909756,
"loss": 0.1022,
"step": 258
},
{
"epoch": 0.9333333333333333,
"grad_norm": 0.09456528837585412,
"learning_rate": 0.00012861316735085686,
"loss": 0.0943,
"step": 259
},
{
"epoch": 0.9369369369369369,
"grad_norm": 0.11421875251828266,
"learning_rate": 0.00012800813542249072,
"loss": 0.0988,
"step": 260
},
{
"epoch": 0.9405405405405406,
"grad_norm": 0.11985070545179864,
"learning_rate": 0.00012740198888186064,
"loss": 0.1238,
"step": 261
},
{
"epoch": 0.9441441441441442,
"grad_norm": 0.09679571111756961,
"learning_rate": 0.00012679475185118535,
"loss": 0.1063,
"step": 262
},
{
"epoch": 0.9477477477477477,
"grad_norm": 0.09782919038732428,
"learning_rate": 0.0001261864484960807,
"loss": 0.1039,
"step": 263
},
{
"epoch": 0.9513513513513514,
"grad_norm": 0.17653628828090737,
"learning_rate": 0.00012557710302459803,
"loss": 0.1354,
"step": 264
},
{
"epoch": 0.954954954954955,
"grad_norm": 0.1409157686607275,
"learning_rate": 0.00012496673968626068,
"loss": 0.1181,
"step": 265
},
{
"epoch": 0.9585585585585585,
"grad_norm": 0.16396955244736236,
"learning_rate": 0.0001243553827710992,
"loss": 0.1352,
"step": 266
},
{
"epoch": 0.9621621621621622,
"grad_norm": 0.11706567681214818,
"learning_rate": 0.0001237430566086844,
"loss": 0.1103,
"step": 267
},
{
"epoch": 0.9657657657657658,
"grad_norm": 0.11951814155751256,
"learning_rate": 0.00012312978556715932,
"loss": 0.1182,
"step": 268
},
{
"epoch": 0.9693693693693693,
"grad_norm": 0.1098976660754676,
"learning_rate": 0.00012251559405226941,
"loss": 0.0981,
"step": 269
},
{
"epoch": 0.972972972972973,
"grad_norm": 0.13497038508376635,
"learning_rate": 0.00012190050650639131,
"loss": 0.139,
"step": 270
},
{
"epoch": 0.9765765765765766,
"grad_norm": 0.10505221561748224,
"learning_rate": 0.00012128454740756014,
"loss": 0.0968,
"step": 271
},
{
"epoch": 0.9801801801801802,
"grad_norm": 0.09400827669331373,
"learning_rate": 0.00012066774126849529,
"loss": 0.091,
"step": 272
},
{
"epoch": 0.9837837837837838,
"grad_norm": 0.13553635299634834,
"learning_rate": 0.00012005011263562513,
"loss": 0.1269,
"step": 273
},
{
"epoch": 0.9873873873873874,
"grad_norm": 0.12708467697016343,
"learning_rate": 0.00011943168608810978,
"loss": 0.1393,
"step": 274
},
{
"epoch": 0.990990990990991,
"grad_norm": 0.12975117728566488,
"learning_rate": 0.00011881248623686338,
"loss": 0.1305,
"step": 275
},
{
"epoch": 0.9945945945945946,
"grad_norm": 0.13065574753229398,
"learning_rate": 0.00011819253772357442,
"loss": 0.1236,
"step": 276
},
{
"epoch": 0.9981981981981982,
"grad_norm": 0.11060359555949814,
"learning_rate": 0.00011757186521972512,
"loss": 0.1018,
"step": 277
},
{
"epoch": 0.9981981981981982,
"eval_loss": 0.12383058667182922,
"eval_runtime": 52.8086,
"eval_samples_per_second": 4.431,
"eval_steps_per_second": 0.568,
"step": 277
},
{
"epoch": 1.0018018018018018,
"grad_norm": 0.11956545731254414,
"learning_rate": 0.00011695049342560968,
"loss": 0.0926,
"step": 278
},
{
"epoch": 1.0054054054054054,
"grad_norm": 0.07533035620811855,
"learning_rate": 0.00011632844706935124,
"loss": 0.0797,
"step": 279
},
{
"epoch": 1.009009009009009,
"grad_norm": 0.07020760288792346,
"learning_rate": 0.00011570575090591791,
"loss": 0.0607,
"step": 280
},
{
"epoch": 1.0126126126126127,
"grad_norm": 0.07819045444088978,
"learning_rate": 0.00011508242971613741,
"loss": 0.0735,
"step": 281
},
{
"epoch": 1.0162162162162163,
"grad_norm": 0.10053168911518578,
"learning_rate": 0.0001144585083057111,
"loss": 0.0835,
"step": 282
},
{
"epoch": 1.0198198198198198,
"grad_norm": 0.10526070984024917,
"learning_rate": 0.0001138340115042267,
"loss": 0.0951,
"step": 283
},
{
"epoch": 1.0234234234234234,
"grad_norm": 0.09945638649949284,
"learning_rate": 0.00011320896416417026,
"loss": 0.0767,
"step": 284
},
{
"epoch": 1.027027027027027,
"grad_norm": 0.07761913145188672,
"learning_rate": 0.00011258339115993696,
"loss": 0.0683,
"step": 285
},
{
"epoch": 1.0306306306306305,
"grad_norm": 0.09704735378738133,
"learning_rate": 0.0001119573173868415,
"loss": 0.0743,
"step": 286
},
{
"epoch": 1.0342342342342343,
"grad_norm": 0.07516525486775329,
"learning_rate": 0.000111330767760127,
"loss": 0.055,
"step": 287
},
{
"epoch": 1.037837837837838,
"grad_norm": 0.12817568478073565,
"learning_rate": 0.00011070376721397373,
"loss": 0.0812,
"step": 288
},
{
"epoch": 1.0414414414414415,
"grad_norm": 0.14184653764167465,
"learning_rate": 0.00011007634070050684,
"loss": 0.1011,
"step": 289
},
{
"epoch": 1.045045045045045,
"grad_norm": 0.12176639431416836,
"learning_rate": 0.00010944851318880314,
"loss": 0.0658,
"step": 290
},
{
"epoch": 1.0486486486486486,
"grad_norm": 0.12307205920891376,
"learning_rate": 0.00010882030966389766,
"loss": 0.0681,
"step": 291
},
{
"epoch": 1.0522522522522522,
"grad_norm": 0.10538765068004156,
"learning_rate": 0.00010819175512578926,
"loss": 0.0641,
"step": 292
},
{
"epoch": 1.055855855855856,
"grad_norm": 0.1835426273917669,
"learning_rate": 0.00010756287458844569,
"loss": 0.0741,
"step": 293
},
{
"epoch": 1.0594594594594595,
"grad_norm": 0.15004556066173333,
"learning_rate": 0.00010693369307880816,
"loss": 0.0697,
"step": 294
},
{
"epoch": 1.063063063063063,
"grad_norm": 0.17087142751095086,
"learning_rate": 0.00010630423563579551,
"loss": 0.0908,
"step": 295
},
{
"epoch": 1.0666666666666667,
"grad_norm": 0.11365528787847244,
"learning_rate": 0.00010567452730930743,
"loss": 0.0618,
"step": 296
},
{
"epoch": 1.0702702702702702,
"grad_norm": 0.1164578811980725,
"learning_rate": 0.00010504459315922788,
"loss": 0.0622,
"step": 297
},
{
"epoch": 1.0738738738738738,
"grad_norm": 0.188496193123827,
"learning_rate": 0.00010441445825442772,
"loss": 0.1077,
"step": 298
},
{
"epoch": 1.0774774774774776,
"grad_norm": 0.10295065488210545,
"learning_rate": 0.00010378414767176705,
"loss": 0.0735,
"step": 299
},
{
"epoch": 1.0810810810810811,
"grad_norm": 0.15374433915948252,
"learning_rate": 0.00010315368649509716,
"loss": 0.085,
"step": 300
},
{
"epoch": 1.0846846846846847,
"grad_norm": 0.09815844567459187,
"learning_rate": 0.00010252309981426244,
"loss": 0.054,
"step": 301
},
{
"epoch": 1.0882882882882883,
"grad_norm": 0.09380489686860213,
"learning_rate": 0.0001018924127241019,
"loss": 0.058,
"step": 302
},
{
"epoch": 1.0918918918918918,
"grad_norm": 0.1284280573750672,
"learning_rate": 0.00010126165032345038,
"loss": 0.0769,
"step": 303
},
{
"epoch": 1.0954954954954954,
"grad_norm": 0.1229186112985099,
"learning_rate": 0.00010063083771413975,
"loss": 0.0859,
"step": 304
},
{
"epoch": 1.0990990990990992,
"grad_norm": 0.09913923706830541,
"learning_rate": 0.0001,
"loss": 0.077,
"step": 305
},
{
"epoch": 1.1027027027027028,
"grad_norm": 0.10294321295155191,
"learning_rate": 9.936916228586028e-05,
"loss": 0.0756,
"step": 306
},
{
"epoch": 1.1063063063063063,
"grad_norm": 0.09262673197538004,
"learning_rate": 9.873834967654964e-05,
"loss": 0.0583,
"step": 307
},
{
"epoch": 1.10990990990991,
"grad_norm": 0.09476725567348886,
"learning_rate": 9.810758727589813e-05,
"loss": 0.0659,
"step": 308
},
{
"epoch": 1.1135135135135135,
"grad_norm": 0.10386525977756432,
"learning_rate": 9.747690018573757e-05,
"loss": 0.0604,
"step": 309
},
{
"epoch": 1.117117117117117,
"grad_norm": 0.1368700701066548,
"learning_rate": 9.684631350490287e-05,
"loss": 0.0728,
"step": 310
},
{
"epoch": 1.1207207207207208,
"grad_norm": 0.1432741421446136,
"learning_rate": 9.621585232823298e-05,
"loss": 0.0922,
"step": 311
},
{
"epoch": 1.1243243243243244,
"grad_norm": 0.11931342929926518,
"learning_rate": 9.55855417455723e-05,
"loss": 0.0763,
"step": 312
},
{
"epoch": 1.127927927927928,
"grad_norm": 0.10803701150902781,
"learning_rate": 9.495540684077216e-05,
"loss": 0.0661,
"step": 313
},
{
"epoch": 1.1315315315315315,
"grad_norm": 0.12884484782558658,
"learning_rate": 9.432547269069261e-05,
"loss": 0.0606,
"step": 314
},
{
"epoch": 1.135135135135135,
"grad_norm": 0.1344643405568192,
"learning_rate": 9.36957643642045e-05,
"loss": 0.0779,
"step": 315
},
{
"epoch": 1.1387387387387387,
"grad_norm": 0.12760304961299287,
"learning_rate": 9.306630692119182e-05,
"loss": 0.0603,
"step": 316
},
{
"epoch": 1.1423423423423422,
"grad_norm": 0.11600505233354397,
"learning_rate": 9.243712541155436e-05,
"loss": 0.0731,
"step": 317
},
{
"epoch": 1.145945945945946,
"grad_norm": 0.12470577794958661,
"learning_rate": 9.180824487421077e-05,
"loss": 0.0712,
"step": 318
},
{
"epoch": 1.1495495495495496,
"grad_norm": 0.1612422337136671,
"learning_rate": 9.117969033610236e-05,
"loss": 0.0683,
"step": 319
},
{
"epoch": 1.1531531531531531,
"grad_norm": 0.14102273355899492,
"learning_rate": 9.055148681119688e-05,
"loss": 0.0674,
"step": 320
},
{
"epoch": 1.1567567567567567,
"grad_norm": 0.14126790004481535,
"learning_rate": 8.992365929949319e-05,
"loss": 0.0812,
"step": 321
},
{
"epoch": 1.1603603603603603,
"grad_norm": 0.15229918606873402,
"learning_rate": 8.929623278602627e-05,
"loss": 0.0701,
"step": 322
},
{
"epoch": 1.163963963963964,
"grad_norm": 0.15483466842409133,
"learning_rate": 8.866923223987302e-05,
"loss": 0.0736,
"step": 323
},
{
"epoch": 1.1675675675675676,
"grad_norm": 0.14180233144913557,
"learning_rate": 8.80426826131585e-05,
"loss": 0.0783,
"step": 324
},
{
"epoch": 1.1711711711711712,
"grad_norm": 0.13636974208873606,
"learning_rate": 8.741660884006303e-05,
"loss": 0.0694,
"step": 325
},
{
"epoch": 1.1747747747747748,
"grad_norm": 0.09259441173399019,
"learning_rate": 8.679103583582979e-05,
"loss": 0.0524,
"step": 326
},
{
"epoch": 1.1783783783783783,
"grad_norm": 0.13715824142259708,
"learning_rate": 8.616598849577333e-05,
"loss": 0.08,
"step": 327
},
{
"epoch": 1.181981981981982,
"grad_norm": 0.12376655099748206,
"learning_rate": 8.554149169428894e-05,
"loss": 0.0784,
"step": 328
},
{
"epoch": 1.1855855855855855,
"grad_norm": 0.09319112288968635,
"learning_rate": 8.491757028386263e-05,
"loss": 0.0586,
"step": 329
},
{
"epoch": 1.1891891891891893,
"grad_norm": 0.10475390780150441,
"learning_rate": 8.429424909408214e-05,
"loss": 0.0563,
"step": 330
},
{
"epoch": 1.1927927927927928,
"grad_norm": 0.138568291584437,
"learning_rate": 8.367155293064878e-05,
"loss": 0.0894,
"step": 331
},
{
"epoch": 1.1963963963963964,
"grad_norm": 0.10228738965627485,
"learning_rate": 8.304950657439033e-05,
"loss": 0.0571,
"step": 332
},
{
"epoch": 1.2,
"grad_norm": 0.09804366197069557,
"learning_rate": 8.242813478027492e-05,
"loss": 0.0632,
"step": 333
},
{
"epoch": 1.2036036036036035,
"grad_norm": 0.09408876005476795,
"learning_rate": 8.180746227642562e-05,
"loss": 0.0553,
"step": 334
},
{
"epoch": 1.2072072072072073,
"grad_norm": 0.13733518876900813,
"learning_rate": 8.118751376313664e-05,
"loss": 0.074,
"step": 335
},
{
"epoch": 1.2108108108108109,
"grad_norm": 0.11537452385210425,
"learning_rate": 8.056831391189023e-05,
"loss": 0.0686,
"step": 336
},
{
"epoch": 1.2144144144144144,
"grad_norm": 0.1072867298305809,
"learning_rate": 7.99498873643749e-05,
"loss": 0.0628,
"step": 337
},
{
"epoch": 1.218018018018018,
"grad_norm": 0.10612605300014923,
"learning_rate": 7.93322587315047e-05,
"loss": 0.0678,
"step": 338
},
{
"epoch": 1.2216216216216216,
"grad_norm": 0.09775413101898157,
"learning_rate": 7.87154525924399e-05,
"loss": 0.0577,
"step": 339
},
{
"epoch": 1.2252252252252251,
"grad_norm": 0.11955490707565056,
"learning_rate": 7.809949349360872e-05,
"loss": 0.0576,
"step": 340
},
{
"epoch": 1.2288288288288287,
"grad_norm": 0.10380886011793584,
"learning_rate": 7.74844059477306e-05,
"loss": 0.0603,
"step": 341
},
{
"epoch": 1.2324324324324325,
"grad_norm": 0.13589511087320075,
"learning_rate": 7.687021443284071e-05,
"loss": 0.0773,
"step": 342
},
{
"epoch": 1.236036036036036,
"grad_norm": 0.1167184661521862,
"learning_rate": 7.625694339131564e-05,
"loss": 0.0677,
"step": 343
},
{
"epoch": 1.2396396396396396,
"grad_norm": 0.12624459810290067,
"learning_rate": 7.564461722890081e-05,
"loss": 0.0802,
"step": 344
},
{
"epoch": 1.2432432432432432,
"grad_norm": 0.12261184267145957,
"learning_rate": 7.503326031373931e-05,
"loss": 0.0649,
"step": 345
},
{
"epoch": 1.2468468468468468,
"grad_norm": 0.16140905294131228,
"learning_rate": 7.442289697540201e-05,
"loss": 0.0648,
"step": 346
},
{
"epoch": 1.2504504504504506,
"grad_norm": 0.1369989260957558,
"learning_rate": 7.381355150391933e-05,
"loss": 0.074,
"step": 347
},
{
"epoch": 1.2540540540540541,
"grad_norm": 0.10405503701690619,
"learning_rate": 7.32052481488147e-05,
"loss": 0.0683,
"step": 348
},
{
"epoch": 1.2576576576576577,
"grad_norm": 0.11234589174920957,
"learning_rate": 7.25980111181394e-05,
"loss": 0.0643,
"step": 349
},
{
"epoch": 1.2612612612612613,
"grad_norm": 0.09321884974416474,
"learning_rate": 7.19918645775093e-05,
"loss": 0.0571,
"step": 350
},
{
"epoch": 1.2648648648648648,
"grad_norm": 0.12641606453495435,
"learning_rate": 7.138683264914314e-05,
"loss": 0.0702,
"step": 351
},
{
"epoch": 1.2684684684684684,
"grad_norm": 0.09916971519672783,
"learning_rate": 7.078293941090249e-05,
"loss": 0.0669,
"step": 352
},
{
"epoch": 1.272072072072072,
"grad_norm": 0.11635429968669815,
"learning_rate": 7.018020889533348e-05,
"loss": 0.071,
"step": 353
},
{
"epoch": 1.2756756756756757,
"grad_norm": 0.1634329754196539,
"learning_rate": 6.957866508871068e-05,
"loss": 0.0956,
"step": 354
},
{
"epoch": 1.2792792792792793,
"grad_norm": 0.10617306865400682,
"learning_rate": 6.897833193008231e-05,
"loss": 0.0601,
"step": 355
},
{
"epoch": 1.2828828828828829,
"grad_norm": 0.09334802201378282,
"learning_rate": 6.83792333103176e-05,
"loss": 0.0633,
"step": 356
},
{
"epoch": 1.2864864864864864,
"grad_norm": 0.09803158330755328,
"learning_rate": 6.77813930711561e-05,
"loss": 0.059,
"step": 357
},
{
"epoch": 1.29009009009009,
"grad_norm": 0.1431245474215182,
"learning_rate": 6.718483500425867e-05,
"loss": 0.0942,
"step": 358
},
{
"epoch": 1.2936936936936938,
"grad_norm": 0.093782557814536,
"learning_rate": 6.658958285026102e-05,
"loss": 0.0606,
"step": 359
},
{
"epoch": 1.2972972972972974,
"grad_norm": 0.11393416329015467,
"learning_rate": 6.599566029782863e-05,
"loss": 0.0717,
"step": 360
},
{
"epoch": 1.300900900900901,
"grad_norm": 0.13923517110417213,
"learning_rate": 6.540309098271416e-05,
"loss": 0.0702,
"step": 361
},
{
"epoch": 1.3045045045045045,
"grad_norm": 0.11247902438190675,
"learning_rate": 6.48118984868167e-05,
"loss": 0.0671,
"step": 362
},
{
"epoch": 1.308108108108108,
"grad_norm": 0.08843201816576483,
"learning_rate": 6.42221063372436e-05,
"loss": 0.0528,
"step": 363
},
{
"epoch": 1.3117117117117116,
"grad_norm": 0.09716724428964281,
"learning_rate": 6.363373800537387e-05,
"loss": 0.064,
"step": 364
},
{
"epoch": 1.3153153153153152,
"grad_norm": 0.15158524613568697,
"learning_rate": 6.304681690592431e-05,
"loss": 0.0704,
"step": 365
},
{
"epoch": 1.318918918918919,
"grad_norm": 0.16465157701305033,
"learning_rate": 6.246136639601764e-05,
"loss": 0.0834,
"step": 366
},
{
"epoch": 1.3225225225225226,
"grad_norm": 0.12163370539770614,
"learning_rate": 6.187740977425285e-05,
"loss": 0.0734,
"step": 367
},
{
"epoch": 1.3261261261261261,
"grad_norm": 0.10264467748684972,
"learning_rate": 6.129497027977829e-05,
"loss": 0.0688,
"step": 368
},
{
"epoch": 1.3297297297297297,
"grad_norm": 0.0908877614772114,
"learning_rate": 6.071407109136662e-05,
"loss": 0.056,
"step": 369
},
{
"epoch": 1.3333333333333333,
"grad_norm": 0.13375636202891336,
"learning_rate": 6.0134735326492456e-05,
"loss": 0.0775,
"step": 370
},
{
"epoch": 1.336936936936937,
"grad_norm": 0.11306366286295132,
"learning_rate": 5.955698604041231e-05,
"loss": 0.0609,
"step": 371
},
{
"epoch": 1.3405405405405406,
"grad_norm": 0.1273835553046169,
"learning_rate": 5.8980846225247286e-05,
"loss": 0.0653,
"step": 372
},
{
"epoch": 1.3441441441441442,
"grad_norm": 0.10437088258018255,
"learning_rate": 5.8406338809067874e-05,
"loss": 0.0639,
"step": 373
},
{
"epoch": 1.3477477477477477,
"grad_norm": 0.10184725937214306,
"learning_rate": 5.7833486654981606e-05,
"loss": 0.0531,
"step": 374
},
{
"epoch": 1.3513513513513513,
"grad_norm": 0.1439045913318642,
"learning_rate": 5.726231256022316e-05,
"loss": 0.0756,
"step": 375
},
{
"epoch": 1.3549549549549549,
"grad_norm": 0.1161759648717375,
"learning_rate": 5.669283925524715e-05,
"loss": 0.0564,
"step": 376
},
{
"epoch": 1.3585585585585584,
"grad_norm": 0.14605792072752058,
"learning_rate": 5.6125089402823485e-05,
"loss": 0.0676,
"step": 377
},
{
"epoch": 1.3621621621621622,
"grad_norm": 0.11801235296837954,
"learning_rate": 5.555908559713561e-05,
"loss": 0.0922,
"step": 378
},
{
"epoch": 1.3657657657657658,
"grad_norm": 0.0986919703756885,
"learning_rate": 5.4994850362881214e-05,
"loss": 0.0624,
"step": 379
},
{
"epoch": 1.3693693693693694,
"grad_norm": 0.10287784532358656,
"learning_rate": 5.443240615437586e-05,
"loss": 0.0692,
"step": 380
},
{
"epoch": 1.372972972972973,
"grad_norm": 0.1340740211739596,
"learning_rate": 5.387177535465945e-05,
"loss": 0.0835,
"step": 381
},
{
"epoch": 1.3765765765765765,
"grad_norm": 0.138304807951036,
"learning_rate": 5.331298027460539e-05,
"loss": 0.0749,
"step": 382
},
{
"epoch": 1.3801801801801803,
"grad_norm": 0.11145520456541595,
"learning_rate": 5.275604315203293e-05,
"loss": 0.062,
"step": 383
},
{
"epoch": 1.3837837837837839,
"grad_norm": 0.09247928908715367,
"learning_rate": 5.2200986150821696e-05,
"loss": 0.0571,
"step": 384
},
{
"epoch": 1.3873873873873874,
"grad_norm": 0.1101460184702829,
"learning_rate": 5.164783136003027e-05,
"loss": 0.076,
"step": 385
},
{
"epoch": 1.390990990990991,
"grad_norm": 0.09455088802615286,
"learning_rate": 5.109660079301668e-05,
"loss": 0.0708,
"step": 386
},
{
"epoch": 1.3945945945945946,
"grad_norm": 0.12915569506877214,
"learning_rate": 5.0547316386562507e-05,
"loss": 0.0683,
"step": 387
},
{
"epoch": 1.3981981981981981,
"grad_norm": 0.14298967602118384,
"learning_rate": 5.000000000000002e-05,
"loss": 0.0802,
"step": 388
},
{
"epoch": 1.4018018018018017,
"grad_norm": 0.13870069410611544,
"learning_rate": 4.945467341434195e-05,
"loss": 0.0849,
"step": 389
},
{
"epoch": 1.4054054054054055,
"grad_norm": 0.1542562430256231,
"learning_rate": 4.891135833141495e-05,
"loss": 0.0875,
"step": 390
},
{
"epoch": 1.409009009009009,
"grad_norm": 0.11965550746042822,
"learning_rate": 4.837007637299595e-05,
"loss": 0.0599,
"step": 391
},
{
"epoch": 1.4126126126126126,
"grad_norm": 0.13624840902702007,
"learning_rate": 4.783084907995156e-05,
"loss": 0.0805,
"step": 392
},
{
"epoch": 1.4162162162162162,
"grad_norm": 0.0916114816428032,
"learning_rate": 4.729369791138085e-05,
"loss": 0.0523,
"step": 393
},
{
"epoch": 1.4198198198198198,
"grad_norm": 0.10008527767691701,
"learning_rate": 4.675864424376146e-05,
"loss": 0.0623,
"step": 394
},
{
"epoch": 1.4234234234234235,
"grad_norm": 0.1329413030801314,
"learning_rate": 4.622570937009879e-05,
"loss": 0.0768,
"step": 395
},
{
"epoch": 1.427027027027027,
"grad_norm": 0.09990109338082896,
"learning_rate": 4.569491449907878e-05,
"loss": 0.0624,
"step": 396
},
{
"epoch": 1.4306306306306307,
"grad_norm": 0.10994747606781914,
"learning_rate": 4.5166280754223676e-05,
"loss": 0.0554,
"step": 397
},
{
"epoch": 1.4342342342342342,
"grad_norm": 0.11716673038318011,
"learning_rate": 4.4639829173051554e-05,
"loss": 0.0487,
"step": 398
},
{
"epoch": 1.4378378378378378,
"grad_norm": 0.14740947528399398,
"learning_rate": 4.411558070623907e-05,
"loss": 0.0705,
"step": 399
},
{
"epoch": 1.4414414414414414,
"grad_norm": 0.10905802122912368,
"learning_rate": 4.359355621678764e-05,
"loss": 0.0669,
"step": 400
},
{
"epoch": 1.445045045045045,
"grad_norm": 0.1372304462996132,
"learning_rate": 4.307377647919343e-05,
"loss": 0.0754,
"step": 401
},
{
"epoch": 1.4486486486486487,
"grad_norm": 0.1220267603792114,
"learning_rate": 4.255626217862013e-05,
"loss": 0.061,
"step": 402
},
{
"epoch": 1.4522522522522523,
"grad_norm": 0.10857496168656595,
"learning_rate": 4.204103391007623e-05,
"loss": 0.0666,
"step": 403
},
{
"epoch": 1.4558558558558559,
"grad_norm": 0.12862098370827468,
"learning_rate": 4.152811217759529e-05,
"loss": 0.0702,
"step": 404
},
{
"epoch": 1.4594594594594594,
"grad_norm": 0.12121566089700932,
"learning_rate": 4.1017517393419826e-05,
"loss": 0.0701,
"step": 405
},
{
"epoch": 1.463063063063063,
"grad_norm": 0.12880561806718493,
"learning_rate": 4.0509269877189106e-05,
"loss": 0.0855,
"step": 406
},
{
"epoch": 1.4666666666666668,
"grad_norm": 0.1103245174300563,
"learning_rate": 4.000338985513046e-05,
"loss": 0.0645,
"step": 407
},
{
"epoch": 1.4702702702702704,
"grad_norm": 0.11471559496567096,
"learning_rate": 3.9499897459254375e-05,
"loss": 0.069,
"step": 408
},
{
"epoch": 1.473873873873874,
"grad_norm": 0.1068585326163203,
"learning_rate": 3.899881272655342e-05,
"loss": 0.0584,
"step": 409
},
{
"epoch": 1.4774774774774775,
"grad_norm": 0.12180507516800447,
"learning_rate": 3.8500155598204644e-05,
"loss": 0.0767,
"step": 410
},
{
"epoch": 1.481081081081081,
"grad_norm": 0.10787694069789268,
"learning_rate": 3.8003945918776143e-05,
"loss": 0.0652,
"step": 411
},
{
"epoch": 1.4846846846846846,
"grad_norm": 0.11726705088810202,
"learning_rate": 3.75102034354373e-05,
"loss": 0.0629,
"step": 412
},
{
"epoch": 1.4882882882882882,
"grad_norm": 0.10762739211432558,
"learning_rate": 3.701894779717286e-05,
"loss": 0.0555,
"step": 413
},
{
"epoch": 1.491891891891892,
"grad_norm": 0.09308134521067353,
"learning_rate": 3.653019855400123e-05,
"loss": 0.0564,
"step": 414
},
{
"epoch": 1.4954954954954955,
"grad_norm": 0.1524049565519016,
"learning_rate": 3.6043975156195987e-05,
"loss": 0.0809,
"step": 415
},
{
"epoch": 1.499099099099099,
"grad_norm": 0.13279511071977756,
"learning_rate": 3.5560296953512295e-05,
"loss": 0.069,
"step": 416
},
{
"epoch": 1.5027027027027027,
"grad_norm": 0.13286192000673344,
"learning_rate": 3.507918319441672e-05,
"loss": 0.0748,
"step": 417
},
{
"epoch": 1.5063063063063065,
"grad_norm": 0.17493415887546465,
"learning_rate": 3.460065302532108e-05,
"loss": 0.0828,
"step": 418
},
{
"epoch": 1.50990990990991,
"grad_norm": 0.11057059837297634,
"learning_rate": 3.4124725489820645e-05,
"loss": 0.063,
"step": 419
},
{
"epoch": 1.5135135135135136,
"grad_norm": 0.12735355112497881,
"learning_rate": 3.365141952793622e-05,
"loss": 0.0732,
"step": 420
},
{
"epoch": 1.5171171171171172,
"grad_norm": 0.1632337270590702,
"learning_rate": 3.3180753975360415e-05,
"loss": 0.0775,
"step": 421
},
{
"epoch": 1.5207207207207207,
"grad_norm": 0.14697481590979153,
"learning_rate": 3.2712747562708115e-05,
"loss": 0.0863,
"step": 422
},
{
"epoch": 1.5243243243243243,
"grad_norm": 0.1660001616377742,
"learning_rate": 3.224741891477095e-05,
"loss": 0.082,
"step": 423
},
{
"epoch": 1.5279279279279279,
"grad_norm": 0.13048897912831442,
"learning_rate": 3.178478654977624e-05,
"loss": 0.0794,
"step": 424
},
{
"epoch": 1.5315315315315314,
"grad_norm": 0.11489435507746414,
"learning_rate": 3.132486887864992e-05,
"loss": 0.0694,
"step": 425
},
{
"epoch": 1.535135135135135,
"grad_norm": 0.07639223925814809,
"learning_rate": 3.086768420428392e-05,
"loss": 0.0413,
"step": 426
},
{
"epoch": 1.5387387387387388,
"grad_norm": 0.11453408038112112,
"learning_rate": 3.0413250720807883e-05,
"loss": 0.0658,
"step": 427
},
{
"epoch": 1.5423423423423424,
"grad_norm": 0.1667771876584119,
"learning_rate": 2.9961586512864947e-05,
"loss": 0.0798,
"step": 428
},
{
"epoch": 1.545945945945946,
"grad_norm": 0.11714414917895159,
"learning_rate": 2.9512709554892003e-05,
"loss": 0.0693,
"step": 429
},
{
"epoch": 1.5495495495495497,
"grad_norm": 0.1229110888950789,
"learning_rate": 2.9066637710404675e-05,
"loss": 0.0747,
"step": 430
},
{
"epoch": 1.5531531531531533,
"grad_norm": 0.1759221433787884,
"learning_rate": 2.8623388731286093e-05,
"loss": 0.0795,
"step": 431
},
{
"epoch": 1.5567567567567568,
"grad_norm": 0.09594983270629338,
"learning_rate": 2.818298025708075e-05,
"loss": 0.059,
"step": 432
},
{
"epoch": 1.5603603603603604,
"grad_norm": 0.090367685537466,
"learning_rate": 2.7745429814292145e-05,
"loss": 0.0531,
"step": 433
},
{
"epoch": 1.563963963963964,
"grad_norm": 0.13195671170326462,
"learning_rate": 2.7310754815685624e-05,
"loss": 0.075,
"step": 434
},
{
"epoch": 1.5675675675675675,
"grad_norm": 0.09101802024714302,
"learning_rate": 2.687897255959536e-05,
"loss": 0.0541,
"step": 435
},
{
"epoch": 1.571171171171171,
"grad_norm": 0.12030212380166792,
"learning_rate": 2.6450100229235795e-05,
"loss": 0.0739,
"step": 436
},
{
"epoch": 1.5747747747747747,
"grad_norm": 0.09282633668248956,
"learning_rate": 2.6024154892017937e-05,
"loss": 0.0585,
"step": 437
},
{
"epoch": 1.5783783783783782,
"grad_norm": 0.1437367048181832,
"learning_rate": 2.5601153498870134e-05,
"loss": 0.0744,
"step": 438
},
{
"epoch": 1.581981981981982,
"grad_norm": 0.12980503831327814,
"learning_rate": 2.518111288356345e-05,
"loss": 0.0741,
"step": 439
},
{
"epoch": 1.5855855855855856,
"grad_norm": 0.12335416962202174,
"learning_rate": 2.4764049762041874e-05,
"loss": 0.072,
"step": 440
},
{
"epoch": 1.5891891891891892,
"grad_norm": 0.10492372446642,
"learning_rate": 2.4349980731756894e-05,
"loss": 0.0716,
"step": 441
},
{
"epoch": 1.592792792792793,
"grad_norm": 0.14899587708147966,
"learning_rate": 2.3938922271007147e-05,
"loss": 0.0925,
"step": 442
},
{
"epoch": 1.5963963963963965,
"grad_norm": 0.13084935137363646,
"learning_rate": 2.353089073828255e-05,
"loss": 0.0823,
"step": 443
},
{
"epoch": 1.6,
"grad_norm": 0.13030296264089844,
"learning_rate": 2.312590237161335e-05,
"loss": 0.0725,
"step": 444
},
{
"epoch": 1.6036036036036037,
"grad_norm": 0.09700200874554347,
"learning_rate": 2.2723973287923962e-05,
"loss": 0.0664,
"step": 445
},
{
"epoch": 1.6072072072072072,
"grad_norm": 0.10633986810502474,
"learning_rate": 2.2325119482391467e-05,
"loss": 0.0679,
"step": 446
},
{
"epoch": 1.6108108108108108,
"grad_norm": 0.11142544471141212,
"learning_rate": 2.1929356827809057e-05,
"loss": 0.0614,
"step": 447
},
{
"epoch": 1.6144144144144144,
"grad_norm": 0.09250950825140586,
"learning_rate": 2.1536701073954558e-05,
"loss": 0.0588,
"step": 448
},
{
"epoch": 1.618018018018018,
"grad_norm": 0.1332480809778604,
"learning_rate": 2.1147167846963422e-05,
"loss": 0.0803,
"step": 449
},
{
"epoch": 1.6216216216216215,
"grad_norm": 0.14121311299673173,
"learning_rate": 2.0760772648707016e-05,
"loss": 0.0947,
"step": 450
},
{
"epoch": 1.6252252252252253,
"grad_norm": 0.10826628920408898,
"learning_rate": 2.037753085617563e-05,
"loss": 0.0704,
"step": 451
},
{
"epoch": 1.6288288288288288,
"grad_norm": 0.08498951848877008,
"learning_rate": 1.999745772086655e-05,
"loss": 0.0416,
"step": 452
},
{
"epoch": 1.6324324324324324,
"grad_norm": 0.15866638731251254,
"learning_rate": 1.9620568368177184e-05,
"loss": 0.0836,
"step": 453
},
{
"epoch": 1.6360360360360362,
"grad_norm": 0.11879058663162903,
"learning_rate": 1.924687779680302e-05,
"loss": 0.0721,
"step": 454
},
{
"epoch": 1.6396396396396398,
"grad_norm": 0.16212624210699175,
"learning_rate": 1.8876400878140775e-05,
"loss": 0.0788,
"step": 455
},
{
"epoch": 1.6432432432432433,
"grad_norm": 0.1205599470750737,
"learning_rate": 1.8509152355696623e-05,
"loss": 0.0891,
"step": 456
},
{
"epoch": 1.646846846846847,
"grad_norm": 0.10723522883909493,
"learning_rate": 1.8145146844499383e-05,
"loss": 0.0702,
"step": 457
},
{
"epoch": 1.6504504504504505,
"grad_norm": 0.10243191710751155,
"learning_rate": 1.7784398830519e-05,
"loss": 0.0558,
"step": 458
},
{
"epoch": 1.654054054054054,
"grad_norm": 0.08896982101996669,
"learning_rate": 1.742692267008996e-05,
"loss": 0.0603,
"step": 459
},
{
"epoch": 1.6576576576576576,
"grad_norm": 0.13618088732046185,
"learning_rate": 1.7072732589339955e-05,
"loss": 0.0744,
"step": 460
},
{
"epoch": 1.6612612612612612,
"grad_norm": 0.14798363521421304,
"learning_rate": 1.672184268362391e-05,
"loss": 0.0875,
"step": 461
},
{
"epoch": 1.6648648648648647,
"grad_norm": 0.10230547180028401,
"learning_rate": 1.6374266916962832e-05,
"loss": 0.0497,
"step": 462
},
{
"epoch": 1.6684684684684683,
"grad_norm": 0.10092039325506573,
"learning_rate": 1.6030019121488227e-05,
"loss": 0.0611,
"step": 463
},
{
"epoch": 1.672072072072072,
"grad_norm": 0.10528958039623297,
"learning_rate": 1.5689112996891576e-05,
"loss": 0.0719,
"step": 464
},
{
"epoch": 1.6756756756756757,
"grad_norm": 0.1357872146845403,
"learning_rate": 1.535156210987917e-05,
"loss": 0.0792,
"step": 465
},
{
"epoch": 1.6792792792792792,
"grad_norm": 0.16092347024456755,
"learning_rate": 1.5017379893632255e-05,
"loss": 0.0984,
"step": 466
},
{
"epoch": 1.682882882882883,
"grad_norm": 0.152681018425233,
"learning_rate": 1.4686579647272336e-05,
"loss": 0.0665,
"step": 467
},
{
"epoch": 1.6864864864864866,
"grad_norm": 0.10940364333158531,
"learning_rate": 1.4359174535331999e-05,
"loss": 0.0678,
"step": 468
},
{
"epoch": 1.6900900900900901,
"grad_norm": 0.10224571124448578,
"learning_rate": 1.4035177587230996e-05,
"loss": 0.0681,
"step": 469
},
{
"epoch": 1.6936936936936937,
"grad_norm": 0.1117508851307017,
"learning_rate": 1.3714601696757712e-05,
"loss": 0.0705,
"step": 470
},
{
"epoch": 1.6972972972972973,
"grad_norm": 0.11380708386619733,
"learning_rate": 1.339745962155613e-05,
"loss": 0.0787,
"step": 471
},
{
"epoch": 1.7009009009009008,
"grad_norm": 0.13014691697383945,
"learning_rate": 1.3083763982618025e-05,
"loss": 0.0746,
"step": 472
},
{
"epoch": 1.7045045045045044,
"grad_norm": 0.14178781462677711,
"learning_rate": 1.2773527263780626e-05,
"loss": 0.0802,
"step": 473
},
{
"epoch": 1.708108108108108,
"grad_norm": 0.13903277880623008,
"learning_rate": 1.2466761811230098e-05,
"loss": 0.0727,
"step": 474
},
{
"epoch": 1.7117117117117115,
"grad_norm": 0.14354542440047877,
"learning_rate": 1.2163479833009894e-05,
"loss": 0.0698,
"step": 475
},
{
"epoch": 1.7153153153153153,
"grad_norm": 0.12299158086851347,
"learning_rate": 1.1863693398535114e-05,
"loss": 0.0659,
"step": 476
},
{
"epoch": 1.718918918918919,
"grad_norm": 0.09882489616646957,
"learning_rate": 1.1567414438112156e-05,
"loss": 0.0626,
"step": 477
},
{
"epoch": 1.7225225225225225,
"grad_norm": 0.11570669617801674,
"learning_rate": 1.1274654742463841e-05,
"loss": 0.0646,
"step": 478
},
{
"epoch": 1.7261261261261263,
"grad_norm": 0.09504741769642676,
"learning_rate": 1.0985425962260343e-05,
"loss": 0.0587,
"step": 479
},
{
"epoch": 1.7297297297297298,
"grad_norm": 0.12981804877027894,
"learning_rate": 1.0699739607655435e-05,
"loss": 0.0646,
"step": 480
},
{
"epoch": 1.7333333333333334,
"grad_norm": 0.10868480851483209,
"learning_rate": 1.0417607047828426e-05,
"loss": 0.0671,
"step": 481
},
{
"epoch": 1.736936936936937,
"grad_norm": 0.13696903097667856,
"learning_rate": 1.01390395105318e-05,
"loss": 0.0786,
"step": 482
},
{
"epoch": 1.7405405405405405,
"grad_norm": 0.1157828731078967,
"learning_rate": 9.864048081644261e-06,
"loss": 0.0714,
"step": 483
},
{
"epoch": 1.744144144144144,
"grad_norm": 0.08900480095300936,
"learning_rate": 9.592643704729753e-06,
"loss": 0.0544,
"step": 484
},
{
"epoch": 1.7477477477477477,
"grad_norm": 0.10882498606926169,
"learning_rate": 9.324837180601741e-06,
"loss": 0.0645,
"step": 485
},
{
"epoch": 1.7513513513513512,
"grad_norm": 0.1879024889958637,
"learning_rate": 9.060639166893493e-06,
"loss": 0.0682,
"step": 486
},
{
"epoch": 1.7549549549549548,
"grad_norm": 0.1072698067292599,
"learning_rate": 8.80006017763395e-06,
"loss": 0.0558,
"step": 487
},
{
"epoch": 1.7585585585585586,
"grad_norm": 0.1177990807822665,
"learning_rate": 8.543110582829272e-06,
"loss": 0.0592,
"step": 488
},
{
"epoch": 1.7621621621621621,
"grad_norm": 0.1144052781708329,
"learning_rate": 8.289800608050202e-06,
"loss": 0.0685,
"step": 489
},
{
"epoch": 1.7657657657657657,
"grad_norm": 0.13290723111377578,
"learning_rate": 8.040140334025082e-06,
"loss": 0.0787,
"step": 490
},
{
"epoch": 1.7693693693693695,
"grad_norm": 0.14325581569648474,
"learning_rate": 7.794139696238645e-06,
"loss": 0.0767,
"step": 491
},
{
"epoch": 1.772972972972973,
"grad_norm": 0.13940373462189817,
"learning_rate": 7.551808484536782e-06,
"loss": 0.0713,
"step": 492
},
{
"epoch": 1.7765765765765766,
"grad_norm": 0.13465478912453277,
"learning_rate": 7.313156342736738e-06,
"loss": 0.0838,
"step": 493
},
{
"epoch": 1.7801801801801802,
"grad_norm": 0.10122791673864097,
"learning_rate": 7.078192768243486e-06,
"loss": 0.0577,
"step": 494
},
{
"epoch": 1.7837837837837838,
"grad_norm": 0.1571652297573745,
"learning_rate": 6.846927111671686e-06,
"loss": 0.0905,
"step": 495
},
{
"epoch": 1.7873873873873873,
"grad_norm": 0.12718467808306833,
"learning_rate": 6.61936857647355e-06,
"loss": 0.0566,
"step": 496
},
{
"epoch": 1.790990990990991,
"grad_norm": 0.15255418113431185,
"learning_rate": 6.395526218572723e-06,
"loss": 0.0646,
"step": 497
},
{
"epoch": 1.7945945945945945,
"grad_norm": 0.13721542773233897,
"learning_rate": 6.175408946003703e-06,
"loss": 0.0752,
"step": 498
},
{
"epoch": 1.798198198198198,
"grad_norm": 0.11503986327868332,
"learning_rate": 5.959025518557437e-06,
"loss": 0.0753,
"step": 499
},
{
"epoch": 1.8018018018018018,
"grad_norm": 0.09966839333280018,
"learning_rate": 5.746384547432737e-06,
"loss": 0.0658,
"step": 500
},
{
"epoch": 1.8054054054054054,
"grad_norm": 0.13097929394232063,
"learning_rate": 5.5374944948935135e-06,
"loss": 0.0647,
"step": 501
},
{
"epoch": 1.809009009009009,
"grad_norm": 0.11916565098885482,
"learning_rate": 5.332363673932106e-06,
"loss": 0.0683,
"step": 502
},
{
"epoch": 1.8126126126126128,
"grad_norm": 0.14740354567299807,
"learning_rate": 5.131000247938367e-06,
"loss": 0.0855,
"step": 503
},
{
"epoch": 1.8162162162162163,
"grad_norm": 0.12344512852482942,
"learning_rate": 4.933412230374812e-06,
"loss": 0.0689,
"step": 504
},
{
"epoch": 1.8198198198198199,
"grad_norm": 0.15079351397270196,
"learning_rate": 4.7396074844577975e-06,
"loss": 0.0865,
"step": 505
},
{
"epoch": 1.8234234234234235,
"grad_norm": 0.13387613481208308,
"learning_rate": 4.549593722844492e-06,
"loss": 0.0761,
"step": 506
},
{
"epoch": 1.827027027027027,
"grad_norm": 0.07611010028345803,
"learning_rate": 4.363378507325955e-06,
"loss": 0.0431,
"step": 507
},
{
"epoch": 1.8306306306306306,
"grad_norm": 0.13798397287470085,
"learning_rate": 4.180969248526334e-06,
"loss": 0.0806,
"step": 508
},
{
"epoch": 1.8342342342342342,
"grad_norm": 0.17673529491591075,
"learning_rate": 4.002373205607723e-06,
"loss": 0.0974,
"step": 509
},
{
"epoch": 1.8378378378378377,
"grad_norm": 0.09469787111672756,
"learning_rate": 3.827597485981527e-06,
"loss": 0.0592,
"step": 510
},
{
"epoch": 1.8414414414414413,
"grad_norm": 0.10244301409759372,
"learning_rate": 3.6566490450254286e-06,
"loss": 0.0629,
"step": 511
},
{
"epoch": 1.845045045045045,
"grad_norm": 0.09239653678543874,
"learning_rate": 3.4895346858066724e-06,
"loss": 0.0637,
"step": 512
},
{
"epoch": 1.8486486486486486,
"grad_norm": 0.136056185401784,
"learning_rate": 3.3262610588113307e-06,
"loss": 0.0784,
"step": 513
},
{
"epoch": 1.8522522522522522,
"grad_norm": 0.12238600483310333,
"learning_rate": 3.1668346616795963e-06,
"loss": 0.0703,
"step": 514
},
{
"epoch": 1.855855855855856,
"grad_norm": 0.15777844339693373,
"learning_rate": 3.011261838947277e-06,
"loss": 0.0861,
"step": 515
},
{
"epoch": 1.8594594594594596,
"grad_norm": 0.149256801647933,
"learning_rate": 2.859548781793242e-06,
"loss": 0.0816,
"step": 516
},
{
"epoch": 1.8630630630630631,
"grad_norm": 0.1158625228168308,
"learning_rate": 2.711701527793031e-06,
"loss": 0.0757,
"step": 517
},
{
"epoch": 1.8666666666666667,
"grad_norm": 0.127467190710186,
"learning_rate": 2.5677259606786684e-06,
"loss": 0.0718,
"step": 518
},
{
"epoch": 1.8702702702702703,
"grad_norm": 0.11178985379767997,
"learning_rate": 2.4276278101044046e-06,
"loss": 0.0729,
"step": 519
},
{
"epoch": 1.8738738738738738,
"grad_norm": 0.13318873038147186,
"learning_rate": 2.291412651418778e-06,
"loss": 0.0874,
"step": 520
},
{
"epoch": 1.8774774774774774,
"grad_norm": 0.11095794613520046,
"learning_rate": 2.159085905442737e-06,
"loss": 0.0632,
"step": 521
},
{
"epoch": 1.881081081081081,
"grad_norm": 0.13466988936312552,
"learning_rate": 2.03065283825381e-06,
"loss": 0.0696,
"step": 522
},
{
"epoch": 1.8846846846846845,
"grad_norm": 0.1501784745699571,
"learning_rate": 1.9061185609766995e-06,
"loss": 0.0781,
"step": 523
},
{
"epoch": 1.8882882882882883,
"grad_norm": 0.12439813775960844,
"learning_rate": 1.7854880295797405e-06,
"loss": 0.0778,
"step": 524
},
{
"epoch": 1.8918918918918919,
"grad_norm": 0.10543026463333441,
"learning_rate": 1.6687660446777277e-06,
"loss": 0.0658,
"step": 525
},
{
"epoch": 1.8954954954954955,
"grad_norm": 0.1493387910647338,
"learning_rate": 1.5559572513409338e-06,
"loss": 0.0733,
"step": 526
},
{
"epoch": 1.8990990990990992,
"grad_norm": 0.11530728589499968,
"learning_rate": 1.4470661389100804e-06,
"loss": 0.066,
"step": 527
},
{
"epoch": 1.9027027027027028,
"grad_norm": 0.0937287880770091,
"learning_rate": 1.3420970408178913e-06,
"loss": 0.0508,
"step": 528
},
{
"epoch": 1.9063063063063064,
"grad_norm": 0.1140049075150384,
"learning_rate": 1.241054134416464e-06,
"loss": 0.0722,
"step": 529
},
{
"epoch": 1.90990990990991,
"grad_norm": 0.10812439212587106,
"learning_rate": 1.143941440811147e-06,
"loss": 0.0607,
"step": 530
},
{
"epoch": 1.9135135135135135,
"grad_norm": 0.10082812889823659,
"learning_rate": 1.0507628247004465e-06,
"loss": 0.0611,
"step": 531
},
{
"epoch": 1.917117117117117,
"grad_norm": 0.1646769037018901,
"learning_rate": 9.615219942222474e-07,
"loss": 0.0907,
"step": 532
},
{
"epoch": 1.9207207207207206,
"grad_norm": 0.13342387053057897,
"learning_rate": 8.762225008062674e-07,
"loss": 0.0705,
"step": 533
},
{
"epoch": 1.9243243243243242,
"grad_norm": 0.10099025782756708,
"learning_rate": 7.948677390326786e-07,
"loss": 0.0594,
"step": 534
},
{
"epoch": 1.9279279279279278,
"grad_norm": 0.10984097417427825,
"learning_rate": 7.174609464970505e-07,
"loss": 0.064,
"step": 535
},
{
"epoch": 1.9315315315315316,
"grad_norm": 0.09250058769796181,
"learning_rate": 6.440052036815081e-07,
"loss": 0.0488,
"step": 536
},
{
"epoch": 1.9351351351351351,
"grad_norm": 0.11346138285376553,
"learning_rate": 5.745034338321187e-07,
"loss": 0.0709,
"step": 537
},
{
"epoch": 1.9387387387387387,
"grad_norm": 0.12145882785931153,
"learning_rate": 5.089584028425743e-07,
"loss": 0.0628,
"step": 538
},
{
"epoch": 1.9423423423423425,
"grad_norm": 0.09764192386128882,
"learning_rate": 4.4737271914411236e-07,
"loss": 0.0581,
"step": 539
},
{
"epoch": 1.945945945945946,
"grad_norm": 0.11336911485782475,
"learning_rate": 3.8974883360169966e-07,
"loss": 0.0652,
"step": 540
},
{
"epoch": 1.9495495495495496,
"grad_norm": 0.1197688852133187,
"learning_rate": 3.360890394165539e-07,
"loss": 0.0797,
"step": 541
},
{
"epoch": 1.9531531531531532,
"grad_norm": 0.12068524258623581,
"learning_rate": 2.86395472034795e-07,
"loss": 0.0796,
"step": 542
},
{
"epoch": 1.9567567567567568,
"grad_norm": 0.10022614951335301,
"learning_rate": 2.4067010906254626e-07,
"loss": 0.0651,
"step": 543
},
{
"epoch": 1.9603603603603603,
"grad_norm": 0.1030646452744324,
"learning_rate": 1.989147701871641e-07,
"loss": 0.0536,
"step": 544
},
{
"epoch": 1.9639639639639639,
"grad_norm": 0.07714530191454869,
"learning_rate": 1.611311171048735e-07,
"loss": 0.0494,
"step": 545
},
{
"epoch": 1.9675675675675675,
"grad_norm": 0.1157905922358179,
"learning_rate": 1.2732065345462118e-07,
"loss": 0.075,
"step": 546
},
{
"epoch": 1.971171171171171,
"grad_norm": 0.07486976400470267,
"learning_rate": 9.748472475823444e-08,
"loss": 0.0454,
"step": 547
},
{
"epoch": 1.9747747747747748,
"grad_norm": 0.09262953733370366,
"learning_rate": 7.162451836685291e-08,
"loss": 0.0556,
"step": 548
},
{
"epoch": 1.9783783783783784,
"grad_norm": 0.11616787129919331,
"learning_rate": 4.974106341374407e-08,
"loss": 0.0767,
"step": 549
},
{
"epoch": 1.981981981981982,
"grad_norm": 0.11058833058189024,
"learning_rate": 3.183523077324724e-08,
"loss": 0.0618,
"step": 550
},
{
"epoch": 1.9855855855855857,
"grad_norm": 0.10561626473162405,
"learning_rate": 1.7907733026223394e-08,
"loss": 0.0719,
"step": 551
},
{
"epoch": 1.9891891891891893,
"grad_norm": 0.1403058364172833,
"learning_rate": 7.959124431622389e-09,
"loss": 0.092,
"step": 552
},
{
"epoch": 1.9927927927927929,
"grad_norm": 0.1326365804299446,
"learning_rate": 1.989800904445005e-09,
"loss": 0.0678,
"step": 553
},
{
"epoch": 1.9963963963963964,
"grad_norm": 0.14065192361832085,
"learning_rate": 0.0,
"loss": 0.0822,
"step": 554
},
{
"epoch": 1.9963963963963964,
"eval_loss": 0.13327383995056152,
"eval_runtime": 50.2794,
"eval_samples_per_second": 4.654,
"eval_steps_per_second": 0.597,
"step": 554
},
{
"epoch": 1.9321739130434783,
"grad_norm": 0.2707502844732912,
"learning_rate": 6.683334509453465e-07,
"loss": 0.1107,
"step": 555
},
{
"epoch": 1.9356521739130435,
"grad_norm": 0.3664545335936956,
"learning_rate": 5.999024760054095e-07,
"loss": 0.1484,
"step": 556
},
{
"epoch": 1.9391304347826086,
"grad_norm": 0.2879184291998937,
"learning_rate": 5.351560625760254e-07,
"loss": 0.1073,
"step": 557
},
{
"epoch": 1.942608695652174,
"grad_norm": 0.32527132334089365,
"learning_rate": 4.7409661067642217e-07,
"loss": 0.1341,
"step": 558
},
{
"epoch": 1.9460869565217391,
"grad_norm": 0.27961707371818556,
"learning_rate": 4.167263836575286e-07,
"loss": 0.0999,
"step": 559
},
{
"epoch": 1.9495652173913043,
"grad_norm": 0.2705336974198295,
"learning_rate": 3.630475081181861e-07,
"loss": 0.0858,
"step": 560
},
{
"epoch": 1.9530434782608697,
"grad_norm": 0.2630558680757462,
"learning_rate": 3.1306197382624526e-07,
"loss": 0.1232,
"step": 561
},
{
"epoch": 1.9565217391304348,
"grad_norm": 0.2875514596758492,
"learning_rate": 2.667716336448356e-07,
"loss": 0.1385,
"step": 562
},
{
"epoch": 1.96,
"grad_norm": 0.3682978167407908,
"learning_rate": 2.2417820346367635e-07,
"loss": 0.1103,
"step": 563
},
{
"epoch": 1.9634782608695653,
"grad_norm": 0.26822875711798694,
"learning_rate": 1.8528326213548274e-07,
"loss": 0.1138,
"step": 564
},
{
"epoch": 1.9669565217391303,
"grad_norm": 0.2418187498704634,
"learning_rate": 1.50088251417424e-07,
"loss": 0.1105,
"step": 565
},
{
"epoch": 1.9704347826086956,
"grad_norm": 0.3401484224136178,
"learning_rate": 1.1859447591769934e-07,
"loss": 0.1377,
"step": 566
},
{
"epoch": 1.973913043478261,
"grad_norm": 0.23339563722483295,
"learning_rate": 9.080310304716567e-08,
"loss": 0.1081,
"step": 567
},
{
"epoch": 1.977391304347826,
"grad_norm": 0.33523600802230064,
"learning_rate": 6.671516297606095e-08,
"loss": 0.1395,
"step": 568
},
{
"epoch": 1.9808695652173913,
"grad_norm": 0.22230937288937844,
"learning_rate": 4.6331548595845984e-08,
"loss": 0.0859,
"step": 569
},
{
"epoch": 1.9843478260869565,
"grad_norm": 0.37789798217710224,
"learning_rate": 2.965301548606414e-08,
"loss": 0.1846,
"step": 570
},
{
"epoch": 1.9878260869565216,
"grad_norm": 0.29502175807159936,
"learning_rate": 1.6680181886352676e-08,
"loss": 0.1208,
"step": 571
},
{
"epoch": 1.991304347826087,
"grad_norm": 0.3456726449106421,
"learning_rate": 7.413528673549941e-09,
"loss": 0.1142,
"step": 572
},
{
"epoch": 1.9947826086956522,
"grad_norm": 0.34376689538870997,
"learning_rate": 1.8533993438318852e-09,
"loss": 0.1442,
"step": 573
},
{
"epoch": 1.9982608695652173,
"grad_norm": 0.3072940536392916,
"learning_rate": 0.0,
"loss": 0.1067,
"step": 574
},
{
"epoch": 1.9982608695652173,
"step": 574,
"total_flos": 466200922914816.0,
"train_loss": 0.0,
"train_runtime": 1.1199,
"train_samples_per_second": 8208.056,
"train_steps_per_second": 512.557
}
],
"logging_steps": 1,
"max_steps": 574,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"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": 466200922914816.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}