3315 lines
93 KiB
JSON
3315 lines
93 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 3.0,
|
|
"eval_steps": 500,
|
|
"global_step": 1644,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"epoch": 0.00913033553983109,
|
|
"grad_norm": 0.6315373182296753,
|
|
"learning_rate": 4.999926966182812e-05,
|
|
"loss": 1.469,
|
|
"num_input_tokens_seen": 31168,
|
|
"step": 5,
|
|
"train_runtime": 37.3694,
|
|
"train_tokens_per_second": 834.051
|
|
},
|
|
{
|
|
"epoch": 0.01826067107966218,
|
|
"grad_norm": 0.6748600006103516,
|
|
"learning_rate": 4.999630273613799e-05,
|
|
"loss": 1.5127,
|
|
"num_input_tokens_seen": 58992,
|
|
"step": 10,
|
|
"train_runtime": 70.3152,
|
|
"train_tokens_per_second": 838.965
|
|
},
|
|
{
|
|
"epoch": 0.027391006619493265,
|
|
"grad_norm": 0.8578517436981201,
|
|
"learning_rate": 4.999105384744215e-05,
|
|
"loss": 1.44,
|
|
"num_input_tokens_seen": 87296,
|
|
"step": 15,
|
|
"train_runtime": 103.3591,
|
|
"train_tokens_per_second": 844.59
|
|
},
|
|
{
|
|
"epoch": 0.03652134215932436,
|
|
"grad_norm": 0.6677753329277039,
|
|
"learning_rate": 4.998352347492226e-05,
|
|
"loss": 1.4987,
|
|
"num_input_tokens_seen": 114656,
|
|
"step": 20,
|
|
"train_runtime": 136.0501,
|
|
"train_tokens_per_second": 842.748
|
|
},
|
|
{
|
|
"epoch": 0.045651677699155443,
|
|
"grad_norm": 0.6610105037689209,
|
|
"learning_rate": 4.9973712306041256e-05,
|
|
"loss": 1.4058,
|
|
"num_input_tokens_seen": 143584,
|
|
"step": 25,
|
|
"train_runtime": 169.3921,
|
|
"train_tokens_per_second": 847.643
|
|
},
|
|
{
|
|
"epoch": 0.05478201323898653,
|
|
"grad_norm": 0.7272489666938782,
|
|
"learning_rate": 4.996162123648058e-05,
|
|
"loss": 1.4049,
|
|
"num_input_tokens_seen": 172224,
|
|
"step": 30,
|
|
"train_runtime": 202.5177,
|
|
"train_tokens_per_second": 850.415
|
|
},
|
|
{
|
|
"epoch": 0.06391234877881762,
|
|
"grad_norm": 0.6470730900764465,
|
|
"learning_rate": 4.99472513700584e-05,
|
|
"loss": 1.4239,
|
|
"num_input_tokens_seen": 200272,
|
|
"step": 35,
|
|
"train_runtime": 235.4246,
|
|
"train_tokens_per_second": 850.684
|
|
},
|
|
{
|
|
"epoch": 0.07304268431864872,
|
|
"grad_norm": 0.6487858295440674,
|
|
"learning_rate": 4.993060401862888e-05,
|
|
"loss": 1.389,
|
|
"num_input_tokens_seen": 227552,
|
|
"step": 40,
|
|
"train_runtime": 267.9205,
|
|
"train_tokens_per_second": 849.327
|
|
},
|
|
{
|
|
"epoch": 0.0821730198584798,
|
|
"grad_norm": 0.81675785779953,
|
|
"learning_rate": 4.9911680701962384e-05,
|
|
"loss": 1.3187,
|
|
"num_input_tokens_seen": 256320,
|
|
"step": 45,
|
|
"train_runtime": 301.0567,
|
|
"train_tokens_per_second": 851.401
|
|
},
|
|
{
|
|
"epoch": 0.09130335539831089,
|
|
"grad_norm": 0.590348482131958,
|
|
"learning_rate": 4.989048314760674e-05,
|
|
"loss": 1.31,
|
|
"num_input_tokens_seen": 287184,
|
|
"step": 50,
|
|
"train_runtime": 335.1262,
|
|
"train_tokens_per_second": 856.943
|
|
},
|
|
{
|
|
"epoch": 0.10043369093814197,
|
|
"grad_norm": 0.6573392748832703,
|
|
"learning_rate": 4.9867013290729535e-05,
|
|
"loss": 1.3295,
|
|
"num_input_tokens_seen": 314864,
|
|
"step": 55,
|
|
"train_runtime": 367.7602,
|
|
"train_tokens_per_second": 856.167
|
|
},
|
|
{
|
|
"epoch": 0.10956402647797306,
|
|
"grad_norm": 0.7032639980316162,
|
|
"learning_rate": 4.984127327394146e-05,
|
|
"loss": 1.2718,
|
|
"num_input_tokens_seen": 342912,
|
|
"step": 60,
|
|
"train_runtime": 400.5266,
|
|
"train_tokens_per_second": 856.153
|
|
},
|
|
{
|
|
"epoch": 0.11869436201780416,
|
|
"grad_norm": 0.789444088935852,
|
|
"learning_rate": 4.981326544710065e-05,
|
|
"loss": 1.2547,
|
|
"num_input_tokens_seen": 370064,
|
|
"step": 65,
|
|
"train_runtime": 432.9005,
|
|
"train_tokens_per_second": 854.848
|
|
},
|
|
{
|
|
"epoch": 0.12782469755763523,
|
|
"grad_norm": 0.7282975316047668,
|
|
"learning_rate": 4.978299236709826e-05,
|
|
"loss": 1.302,
|
|
"num_input_tokens_seen": 399584,
|
|
"step": 70,
|
|
"train_runtime": 466.4409,
|
|
"train_tokens_per_second": 856.666
|
|
},
|
|
{
|
|
"epoch": 0.13695503309746634,
|
|
"grad_norm": 0.7695715427398682,
|
|
"learning_rate": 4.975045679762496e-05,
|
|
"loss": 1.2328,
|
|
"num_input_tokens_seen": 430528,
|
|
"step": 75,
|
|
"train_runtime": 500.4187,
|
|
"train_tokens_per_second": 860.336
|
|
},
|
|
{
|
|
"epoch": 0.14608536863729743,
|
|
"grad_norm": 0.6912102699279785,
|
|
"learning_rate": 4.9715661708918624e-05,
|
|
"loss": 1.296,
|
|
"num_input_tokens_seen": 460080,
|
|
"step": 80,
|
|
"train_runtime": 533.9121,
|
|
"train_tokens_per_second": 861.715
|
|
},
|
|
{
|
|
"epoch": 0.15521570417712852,
|
|
"grad_norm": 0.7808125615119934,
|
|
"learning_rate": 4.9678610277493275e-05,
|
|
"loss": 1.3248,
|
|
"num_input_tokens_seen": 488176,
|
|
"step": 85,
|
|
"train_runtime": 566.9429,
|
|
"train_tokens_per_second": 861.067
|
|
},
|
|
{
|
|
"epoch": 0.1643460397169596,
|
|
"grad_norm": 0.8161223530769348,
|
|
"learning_rate": 4.9639305885848975e-05,
|
|
"loss": 1.207,
|
|
"num_input_tokens_seen": 516896,
|
|
"step": 90,
|
|
"train_runtime": 600.1453,
|
|
"train_tokens_per_second": 861.285
|
|
},
|
|
{
|
|
"epoch": 0.1734763752567907,
|
|
"grad_norm": 0.7836668491363525,
|
|
"learning_rate": 4.959775212216308e-05,
|
|
"loss": 1.2342,
|
|
"num_input_tokens_seen": 547440,
|
|
"step": 95,
|
|
"train_runtime": 634.2069,
|
|
"train_tokens_per_second": 863.188
|
|
},
|
|
{
|
|
"epoch": 0.18260671079662177,
|
|
"grad_norm": 0.7432403564453125,
|
|
"learning_rate": 4.955395277996268e-05,
|
|
"loss": 1.1931,
|
|
"num_input_tokens_seen": 577088,
|
|
"step": 100,
|
|
"train_runtime": 667.769,
|
|
"train_tokens_per_second": 864.203
|
|
},
|
|
{
|
|
"epoch": 0.19173704633645286,
|
|
"grad_norm": 0.7105097770690918,
|
|
"learning_rate": 4.9507911857778256e-05,
|
|
"loss": 1.2122,
|
|
"num_input_tokens_seen": 606976,
|
|
"step": 105,
|
|
"train_runtime": 702.605,
|
|
"train_tokens_per_second": 863.894
|
|
},
|
|
{
|
|
"epoch": 0.20086738187628395,
|
|
"grad_norm": 0.9018083810806274,
|
|
"learning_rate": 4.9459633558778684e-05,
|
|
"loss": 1.2973,
|
|
"num_input_tokens_seen": 634416,
|
|
"step": 110,
|
|
"train_runtime": 735.186,
|
|
"train_tokens_per_second": 862.933
|
|
},
|
|
{
|
|
"epoch": 0.20999771741611503,
|
|
"grad_norm": 0.878520131111145,
|
|
"learning_rate": 4.940912229038745e-05,
|
|
"loss": 1.2483,
|
|
"num_input_tokens_seen": 660192,
|
|
"step": 115,
|
|
"train_runtime": 767.1492,
|
|
"train_tokens_per_second": 860.578
|
|
},
|
|
{
|
|
"epoch": 0.21912805295594612,
|
|
"grad_norm": 0.7927104234695435,
|
|
"learning_rate": 4.9356382663880366e-05,
|
|
"loss": 1.1153,
|
|
"num_input_tokens_seen": 687936,
|
|
"step": 120,
|
|
"train_runtime": 799.9406,
|
|
"train_tokens_per_second": 859.984
|
|
},
|
|
{
|
|
"epoch": 0.22825838849577723,
|
|
"grad_norm": 0.9102480411529541,
|
|
"learning_rate": 4.930141949396454e-05,
|
|
"loss": 1.2269,
|
|
"num_input_tokens_seen": 716960,
|
|
"step": 125,
|
|
"train_runtime": 833.2659,
|
|
"train_tokens_per_second": 860.422
|
|
},
|
|
{
|
|
"epoch": 0.23738872403560832,
|
|
"grad_norm": 0.9657291173934937,
|
|
"learning_rate": 4.9244237798338866e-05,
|
|
"loss": 1.1324,
|
|
"num_input_tokens_seen": 744976,
|
|
"step": 130,
|
|
"train_runtime": 866.1684,
|
|
"train_tokens_per_second": 860.082
|
|
},
|
|
{
|
|
"epoch": 0.2465190595754394,
|
|
"grad_norm": 0.9540858268737793,
|
|
"learning_rate": 4.918484279723592e-05,
|
|
"loss": 1.1818,
|
|
"num_input_tokens_seen": 772176,
|
|
"step": 135,
|
|
"train_runtime": 898.6975,
|
|
"train_tokens_per_second": 859.217
|
|
},
|
|
{
|
|
"epoch": 0.25564939511527046,
|
|
"grad_norm": 0.9128895998001099,
|
|
"learning_rate": 4.9123239912945423e-05,
|
|
"loss": 1.1243,
|
|
"num_input_tokens_seen": 804528,
|
|
"step": 140,
|
|
"train_runtime": 933.4596,
|
|
"train_tokens_per_second": 861.878
|
|
},
|
|
{
|
|
"epoch": 0.2647797306551016,
|
|
"grad_norm": 0.896022379398346,
|
|
"learning_rate": 4.9059434769319205e-05,
|
|
"loss": 1.2134,
|
|
"num_input_tokens_seen": 831056,
|
|
"step": 145,
|
|
"train_runtime": 965.6266,
|
|
"train_tokens_per_second": 860.639
|
|
},
|
|
{
|
|
"epoch": 0.2739100661949327,
|
|
"grad_norm": 0.8580520153045654,
|
|
"learning_rate": 4.899343319125781e-05,
|
|
"loss": 1.0775,
|
|
"num_input_tokens_seen": 862416,
|
|
"step": 150,
|
|
"train_runtime": 999.9056,
|
|
"train_tokens_per_second": 862.497
|
|
},
|
|
{
|
|
"epoch": 0.28304040173476375,
|
|
"grad_norm": 0.9435716867446899,
|
|
"learning_rate": 4.892524120417872e-05,
|
|
"loss": 1.2069,
|
|
"num_input_tokens_seen": 889264,
|
|
"step": 155,
|
|
"train_runtime": 1032.1039,
|
|
"train_tokens_per_second": 861.603
|
|
},
|
|
{
|
|
"epoch": 0.29217073727459486,
|
|
"grad_norm": 0.9432860016822815,
|
|
"learning_rate": 4.8854865033466275e-05,
|
|
"loss": 1.1649,
|
|
"num_input_tokens_seen": 917104,
|
|
"step": 160,
|
|
"train_runtime": 1064.7569,
|
|
"train_tokens_per_second": 861.327
|
|
},
|
|
{
|
|
"epoch": 0.3013010728144259,
|
|
"grad_norm": 0.780659019947052,
|
|
"learning_rate": 4.878231110390337e-05,
|
|
"loss": 1.1495,
|
|
"num_input_tokens_seen": 947280,
|
|
"step": 165,
|
|
"train_runtime": 1098.5348,
|
|
"train_tokens_per_second": 862.312
|
|
},
|
|
{
|
|
"epoch": 0.31043140835425703,
|
|
"grad_norm": 1.0290687084197998,
|
|
"learning_rate": 4.870758603908489e-05,
|
|
"loss": 1.1231,
|
|
"num_input_tokens_seen": 978704,
|
|
"step": 170,
|
|
"train_runtime": 1132.7604,
|
|
"train_tokens_per_second": 863.999
|
|
},
|
|
{
|
|
"epoch": 0.3195617438940881,
|
|
"grad_norm": 0.8476850390434265,
|
|
"learning_rate": 4.863069666081307e-05,
|
|
"loss": 1.0885,
|
|
"num_input_tokens_seen": 1005904,
|
|
"step": 175,
|
|
"train_runtime": 1165.1167,
|
|
"train_tokens_per_second": 863.35
|
|
},
|
|
{
|
|
"epoch": 0.3286920794339192,
|
|
"grad_norm": 0.8470911383628845,
|
|
"learning_rate": 4.855164998847466e-05,
|
|
"loss": 1.1022,
|
|
"num_input_tokens_seen": 1034624,
|
|
"step": 180,
|
|
"train_runtime": 1198.278,
|
|
"train_tokens_per_second": 863.426
|
|
},
|
|
{
|
|
"epoch": 0.33782241497375026,
|
|
"grad_norm": 1.0513180494308472,
|
|
"learning_rate": 4.8470453238400195e-05,
|
|
"loss": 1.1223,
|
|
"num_input_tokens_seen": 1059280,
|
|
"step": 185,
|
|
"train_runtime": 1229.5356,
|
|
"train_tokens_per_second": 861.529
|
|
},
|
|
{
|
|
"epoch": 0.3469527505135814,
|
|
"grad_norm": 0.9217162132263184,
|
|
"learning_rate": 4.8387113823205096e-05,
|
|
"loss": 1.0287,
|
|
"num_input_tokens_seen": 1088960,
|
|
"step": 190,
|
|
"train_runtime": 1263.0899,
|
|
"train_tokens_per_second": 862.14
|
|
},
|
|
{
|
|
"epoch": 0.3560830860534125,
|
|
"grad_norm": 1.0153199434280396,
|
|
"learning_rate": 4.8301639351113065e-05,
|
|
"loss": 1.1138,
|
|
"num_input_tokens_seen": 1113712,
|
|
"step": 195,
|
|
"train_runtime": 1294.2756,
|
|
"train_tokens_per_second": 860.491
|
|
},
|
|
{
|
|
"epoch": 0.36521342159324355,
|
|
"grad_norm": 1.2406193017959595,
|
|
"learning_rate": 4.821403762526143e-05,
|
|
"loss": 1.1149,
|
|
"num_input_tokens_seen": 1141696,
|
|
"step": 200,
|
|
"train_runtime": 1326.999,
|
|
"train_tokens_per_second": 860.359
|
|
},
|
|
{
|
|
"epoch": 0.37434375713307466,
|
|
"grad_norm": 0.9366787075996399,
|
|
"learning_rate": 4.812431664298883e-05,
|
|
"loss": 1.1954,
|
|
"num_input_tokens_seen": 1172000,
|
|
"step": 205,
|
|
"train_runtime": 1362.1116,
|
|
"train_tokens_per_second": 860.429
|
|
},
|
|
{
|
|
"epoch": 0.3834740926729057,
|
|
"grad_norm": 0.8975793123245239,
|
|
"learning_rate": 4.803248459510511e-05,
|
|
"loss": 1.0426,
|
|
"num_input_tokens_seen": 1201136,
|
|
"step": 210,
|
|
"train_runtime": 1395.3356,
|
|
"train_tokens_per_second": 860.822
|
|
},
|
|
{
|
|
"epoch": 0.39260442821273683,
|
|
"grad_norm": 0.9986598491668701,
|
|
"learning_rate": 4.7938549865143544e-05,
|
|
"loss": 1.2254,
|
|
"num_input_tokens_seen": 1227792,
|
|
"step": 215,
|
|
"train_runtime": 1427.5362,
|
|
"train_tokens_per_second": 860.078
|
|
},
|
|
{
|
|
"epoch": 0.4017347637525679,
|
|
"grad_norm": 0.9591779112815857,
|
|
"learning_rate": 4.7842521028595526e-05,
|
|
"loss": 1.0323,
|
|
"num_input_tokens_seen": 1258240,
|
|
"step": 220,
|
|
"train_runtime": 1461.4996,
|
|
"train_tokens_per_second": 860.924
|
|
},
|
|
{
|
|
"epoch": 0.410865099292399,
|
|
"grad_norm": 1.1904876232147217,
|
|
"learning_rate": 4.7744406852127653e-05,
|
|
"loss": 0.9971,
|
|
"num_input_tokens_seen": 1289744,
|
|
"step": 225,
|
|
"train_runtime": 1495.7355,
|
|
"train_tokens_per_second": 862.281
|
|
},
|
|
{
|
|
"epoch": 0.41999543483223006,
|
|
"grad_norm": 1.1294660568237305,
|
|
"learning_rate": 4.764421629278144e-05,
|
|
"loss": 1.0328,
|
|
"num_input_tokens_seen": 1315040,
|
|
"step": 230,
|
|
"train_runtime": 1527.2934,
|
|
"train_tokens_per_second": 861.026
|
|
},
|
|
{
|
|
"epoch": 0.4291257703720612,
|
|
"grad_norm": 1.2325509786605835,
|
|
"learning_rate": 4.754195849715557e-05,
|
|
"loss": 1.0546,
|
|
"num_input_tokens_seen": 1344848,
|
|
"step": 235,
|
|
"train_runtime": 1560.7834,
|
|
"train_tokens_per_second": 861.649
|
|
},
|
|
{
|
|
"epoch": 0.43825610591189224,
|
|
"grad_norm": 0.991324245929718,
|
|
"learning_rate": 4.743764280057092e-05,
|
|
"loss": 1.1701,
|
|
"num_input_tokens_seen": 1371728,
|
|
"step": 240,
|
|
"train_runtime": 1593.0413,
|
|
"train_tokens_per_second": 861.075
|
|
},
|
|
{
|
|
"epoch": 0.44738644145172335,
|
|
"grad_norm": 1.1479493379592896,
|
|
"learning_rate": 4.73312787262183e-05,
|
|
"loss": 1.0949,
|
|
"num_input_tokens_seen": 1398896,
|
|
"step": 245,
|
|
"train_runtime": 1625.4235,
|
|
"train_tokens_per_second": 860.635
|
|
},
|
|
{
|
|
"epoch": 0.45651677699155446,
|
|
"grad_norm": 0.9881078600883484,
|
|
"learning_rate": 4.722287598428907e-05,
|
|
"loss": 1.1142,
|
|
"num_input_tokens_seen": 1425376,
|
|
"step": 250,
|
|
"train_runtime": 1657.4768,
|
|
"train_tokens_per_second": 859.967
|
|
},
|
|
{
|
|
"epoch": 0.4656471125313855,
|
|
"grad_norm": 1.3233039379119873,
|
|
"learning_rate": 4.711244447108866e-05,
|
|
"loss": 1.0364,
|
|
"num_input_tokens_seen": 1452416,
|
|
"step": 255,
|
|
"train_runtime": 1689.8742,
|
|
"train_tokens_per_second": 859.482
|
|
},
|
|
{
|
|
"epoch": 0.47477744807121663,
|
|
"grad_norm": 1.1027718782424927,
|
|
"learning_rate": 4.6999994268133166e-05,
|
|
"loss": 1.0669,
|
|
"num_input_tokens_seen": 1481440,
|
|
"step": 260,
|
|
"train_runtime": 1722.9242,
|
|
"train_tokens_per_second": 859.84
|
|
},
|
|
{
|
|
"epoch": 0.4839077836110477,
|
|
"grad_norm": 0.9862788915634155,
|
|
"learning_rate": 4.6885535641228904e-05,
|
|
"loss": 1.007,
|
|
"num_input_tokens_seen": 1510240,
|
|
"step": 265,
|
|
"train_runtime": 1756.1254,
|
|
"train_tokens_per_second": 859.984
|
|
},
|
|
{
|
|
"epoch": 0.4930381191508788,
|
|
"grad_norm": 0.8394035696983337,
|
|
"learning_rate": 4.676907903953531e-05,
|
|
"loss": 0.9444,
|
|
"num_input_tokens_seen": 1538208,
|
|
"step": 270,
|
|
"train_runtime": 1788.9168,
|
|
"train_tokens_per_second": 859.854
|
|
},
|
|
{
|
|
"epoch": 0.5021684546907099,
|
|
"grad_norm": 0.9921995401382446,
|
|
"learning_rate": 4.665063509461097e-05,
|
|
"loss": 1.0157,
|
|
"num_input_tokens_seen": 1566880,
|
|
"step": 275,
|
|
"train_runtime": 1821.9921,
|
|
"train_tokens_per_second": 859.982
|
|
},
|
|
{
|
|
"epoch": 0.5112987902305409,
|
|
"grad_norm": 1.0822592973709106,
|
|
"learning_rate": 4.6530214619443037e-05,
|
|
"loss": 1.0188,
|
|
"num_input_tokens_seen": 1593904,
|
|
"step": 280,
|
|
"train_runtime": 1854.3967,
|
|
"train_tokens_per_second": 859.527
|
|
},
|
|
{
|
|
"epoch": 0.520429125770372,
|
|
"grad_norm": 1.1514437198638916,
|
|
"learning_rate": 4.640782860746011e-05,
|
|
"loss": 0.9333,
|
|
"num_input_tokens_seen": 1621440,
|
|
"step": 285,
|
|
"train_runtime": 1887.0679,
|
|
"train_tokens_per_second": 859.238
|
|
},
|
|
{
|
|
"epoch": 0.5295594613102032,
|
|
"grad_norm": 1.1235507726669312,
|
|
"learning_rate": 4.628348823152863e-05,
|
|
"loss": 0.9435,
|
|
"num_input_tokens_seen": 1650064,
|
|
"step": 290,
|
|
"train_runtime": 1920.2198,
|
|
"train_tokens_per_second": 859.31
|
|
},
|
|
{
|
|
"epoch": 0.5386897968500343,
|
|
"grad_norm": 0.8459988832473755,
|
|
"learning_rate": 4.615720484293286e-05,
|
|
"loss": 0.9418,
|
|
"num_input_tokens_seen": 1677472,
|
|
"step": 295,
|
|
"train_runtime": 1952.7783,
|
|
"train_tokens_per_second": 859.018
|
|
},
|
|
{
|
|
"epoch": 0.5478201323898654,
|
|
"grad_norm": 1.2311139106750488,
|
|
"learning_rate": 4.602898997033861e-05,
|
|
"loss": 0.9934,
|
|
"num_input_tokens_seen": 1706672,
|
|
"step": 300,
|
|
"train_runtime": 1986.1813,
|
|
"train_tokens_per_second": 859.273
|
|
},
|
|
{
|
|
"epoch": 0.5569504679296964,
|
|
"grad_norm": 1.1580544710159302,
|
|
"learning_rate": 4.58988553187408e-05,
|
|
"loss": 1.0952,
|
|
"num_input_tokens_seen": 1734704,
|
|
"step": 305,
|
|
"train_runtime": 2020.184,
|
|
"train_tokens_per_second": 858.686
|
|
},
|
|
{
|
|
"epoch": 0.5660808034695275,
|
|
"grad_norm": 0.8693342804908752,
|
|
"learning_rate": 4.576681276839483e-05,
|
|
"loss": 0.9632,
|
|
"num_input_tokens_seen": 1763312,
|
|
"step": 310,
|
|
"train_runtime": 2053.3414,
|
|
"train_tokens_per_second": 858.752
|
|
},
|
|
{
|
|
"epoch": 0.5752111390093586,
|
|
"grad_norm": 0.9932484030723572,
|
|
"learning_rate": 4.5632874373732035e-05,
|
|
"loss": 0.931,
|
|
"num_input_tokens_seen": 1789616,
|
|
"step": 315,
|
|
"train_runtime": 2085.3946,
|
|
"train_tokens_per_second": 858.167
|
|
},
|
|
{
|
|
"epoch": 0.5843414745491897,
|
|
"grad_norm": 1.0481774806976318,
|
|
"learning_rate": 4.549705236225922e-05,
|
|
"loss": 1.0103,
|
|
"num_input_tokens_seen": 1817760,
|
|
"step": 320,
|
|
"train_runtime": 2118.2164,
|
|
"train_tokens_per_second": 858.156
|
|
},
|
|
{
|
|
"epoch": 0.5934718100890207,
|
|
"grad_norm": 0.9734839797019958,
|
|
"learning_rate": 4.5359359133442356e-05,
|
|
"loss": 0.9518,
|
|
"num_input_tokens_seen": 1845664,
|
|
"step": 325,
|
|
"train_runtime": 2150.9302,
|
|
"train_tokens_per_second": 858.077
|
|
},
|
|
{
|
|
"epoch": 0.6026021456288518,
|
|
"grad_norm": 0.935545802116394,
|
|
"learning_rate": 4.521980725757466e-05,
|
|
"loss": 0.8974,
|
|
"num_input_tokens_seen": 1875392,
|
|
"step": 330,
|
|
"train_runtime": 2184.587,
|
|
"train_tokens_per_second": 858.465
|
|
},
|
|
{
|
|
"epoch": 0.611732481168683,
|
|
"grad_norm": 1.1402722597122192,
|
|
"learning_rate": 4.5078409474628966e-05,
|
|
"loss": 0.9171,
|
|
"num_input_tokens_seen": 1902592,
|
|
"step": 335,
|
|
"train_runtime": 2217.1072,
|
|
"train_tokens_per_second": 858.142
|
|
},
|
|
{
|
|
"epoch": 0.6208628167085141,
|
|
"grad_norm": 1.1934939622879028,
|
|
"learning_rate": 4.4935178693094714e-05,
|
|
"loss": 0.899,
|
|
"num_input_tokens_seen": 1931328,
|
|
"step": 340,
|
|
"train_runtime": 2250.2974,
|
|
"train_tokens_per_second": 858.255
|
|
},
|
|
{
|
|
"epoch": 0.6299931522483452,
|
|
"grad_norm": 1.0187445878982544,
|
|
"learning_rate": 4.4790127988799494e-05,
|
|
"loss": 0.8964,
|
|
"num_input_tokens_seen": 1960528,
|
|
"step": 345,
|
|
"train_runtime": 2283.719,
|
|
"train_tokens_per_second": 858.48
|
|
},
|
|
{
|
|
"epoch": 0.6391234877881762,
|
|
"grad_norm": 1.0490012168884277,
|
|
"learning_rate": 4.464327060371529e-05,
|
|
"loss": 1.0919,
|
|
"num_input_tokens_seen": 1987168,
|
|
"step": 350,
|
|
"train_runtime": 2315.9585,
|
|
"train_tokens_per_second": 858.033
|
|
},
|
|
{
|
|
"epoch": 0.6482538233280073,
|
|
"grad_norm": 1.2056529521942139,
|
|
"learning_rate": 4.449461994474968e-05,
|
|
"loss": 1.0469,
|
|
"num_input_tokens_seen": 2014832,
|
|
"step": 355,
|
|
"train_runtime": 2348.6807,
|
|
"train_tokens_per_second": 857.857
|
|
},
|
|
{
|
|
"epoch": 0.6573841588678384,
|
|
"grad_norm": 0.9101769328117371,
|
|
"learning_rate": 4.434418958252179e-05,
|
|
"loss": 0.8841,
|
|
"num_input_tokens_seen": 2043840,
|
|
"step": 360,
|
|
"train_runtime": 2382.0483,
|
|
"train_tokens_per_second": 858.018
|
|
},
|
|
{
|
|
"epoch": 0.6665144944076695,
|
|
"grad_norm": 1.4810435771942139,
|
|
"learning_rate": 4.4191993250123483e-05,
|
|
"loss": 1.0016,
|
|
"num_input_tokens_seen": 2073120,
|
|
"step": 365,
|
|
"train_runtime": 2415.6373,
|
|
"train_tokens_per_second": 858.208
|
|
},
|
|
{
|
|
"epoch": 0.6756448299475005,
|
|
"grad_norm": 1.065366506576538,
|
|
"learning_rate": 4.4038044841865614e-05,
|
|
"loss": 0.9584,
|
|
"num_input_tokens_seen": 2098384,
|
|
"step": 370,
|
|
"train_runtime": 2447.2579,
|
|
"train_tokens_per_second": 857.443
|
|
},
|
|
{
|
|
"epoch": 0.6847751654873316,
|
|
"grad_norm": 1.2886056900024414,
|
|
"learning_rate": 4.388235841200956e-05,
|
|
"loss": 0.9964,
|
|
"num_input_tokens_seen": 2127008,
|
|
"step": 375,
|
|
"train_runtime": 2480.3435,
|
|
"train_tokens_per_second": 857.546
|
|
},
|
|
{
|
|
"epoch": 0.6939055010271628,
|
|
"grad_norm": 1.2109014987945557,
|
|
"learning_rate": 4.3724948173484216e-05,
|
|
"loss": 0.9808,
|
|
"num_input_tokens_seen": 2154624,
|
|
"step": 380,
|
|
"train_runtime": 2512.9908,
|
|
"train_tokens_per_second": 857.394
|
|
},
|
|
{
|
|
"epoch": 0.7030358365669939,
|
|
"grad_norm": 1.0763500928878784,
|
|
"learning_rate": 4.356582849658845e-05,
|
|
"loss": 0.9126,
|
|
"num_input_tokens_seen": 2184768,
|
|
"step": 385,
|
|
"train_runtime": 2546.895,
|
|
"train_tokens_per_second": 857.816
|
|
},
|
|
{
|
|
"epoch": 0.712166172106825,
|
|
"grad_norm": 1.1964282989501953,
|
|
"learning_rate": 4.340501390767924e-05,
|
|
"loss": 0.8749,
|
|
"num_input_tokens_seen": 2214336,
|
|
"step": 390,
|
|
"train_runtime": 2580.5251,
|
|
"train_tokens_per_second": 858.095
|
|
},
|
|
{
|
|
"epoch": 0.721296507646656,
|
|
"grad_norm": 1.2746434211730957,
|
|
"learning_rate": 4.324251908784546e-05,
|
|
"loss": 0.9203,
|
|
"num_input_tokens_seen": 2243296,
|
|
"step": 395,
|
|
"train_runtime": 2613.6736,
|
|
"train_tokens_per_second": 858.292
|
|
},
|
|
{
|
|
"epoch": 0.7304268431864871,
|
|
"grad_norm": 0.9673400521278381,
|
|
"learning_rate": 4.3078358871567706e-05,
|
|
"loss": 0.8857,
|
|
"num_input_tokens_seen": 2273424,
|
|
"step": 400,
|
|
"train_runtime": 2647.5272,
|
|
"train_tokens_per_second": 858.697
|
|
},
|
|
{
|
|
"epoch": 0.7395571787263182,
|
|
"grad_norm": 0.9456354975700378,
|
|
"learning_rate": 4.291254824536396e-05,
|
|
"loss": 0.9175,
|
|
"num_input_tokens_seen": 2303040,
|
|
"step": 405,
|
|
"train_runtime": 2682.2704,
|
|
"train_tokens_per_second": 858.616
|
|
},
|
|
{
|
|
"epoch": 0.7486875142661493,
|
|
"grad_norm": 1.1169666051864624,
|
|
"learning_rate": 4.274510234642148e-05,
|
|
"loss": 0.9572,
|
|
"num_input_tokens_seen": 2330352,
|
|
"step": 410,
|
|
"train_runtime": 2714.6955,
|
|
"train_tokens_per_second": 858.421
|
|
},
|
|
{
|
|
"epoch": 0.7578178498059803,
|
|
"grad_norm": 1.1452381610870361,
|
|
"learning_rate": 4.257603646121484e-05,
|
|
"loss": 1.0534,
|
|
"num_input_tokens_seen": 2357968,
|
|
"step": 415,
|
|
"train_runtime": 2747.2523,
|
|
"train_tokens_per_second": 858.3
|
|
},
|
|
{
|
|
"epoch": 0.7669481853458114,
|
|
"grad_norm": 1.2339755296707153,
|
|
"learning_rate": 4.240536602411048e-05,
|
|
"loss": 0.8583,
|
|
"num_input_tokens_seen": 2386800,
|
|
"step": 420,
|
|
"train_runtime": 2780.5385,
|
|
"train_tokens_per_second": 858.395
|
|
},
|
|
{
|
|
"epoch": 0.7760785208856426,
|
|
"grad_norm": 1.0699409246444702,
|
|
"learning_rate": 4.22331066159576e-05,
|
|
"loss": 0.8049,
|
|
"num_input_tokens_seen": 2416224,
|
|
"step": 425,
|
|
"train_runtime": 2813.8831,
|
|
"train_tokens_per_second": 858.68
|
|
},
|
|
{
|
|
"epoch": 0.7852088564254737,
|
|
"grad_norm": 1.0616157054901123,
|
|
"learning_rate": 4.205927396266577e-05,
|
|
"loss": 0.9599,
|
|
"num_input_tokens_seen": 2445120,
|
|
"step": 430,
|
|
"train_runtime": 2847.2801,
|
|
"train_tokens_per_second": 858.756
|
|
},
|
|
{
|
|
"epoch": 0.7943391919653047,
|
|
"grad_norm": 1.3448375463485718,
|
|
"learning_rate": 4.188388393376933e-05,
|
|
"loss": 0.8874,
|
|
"num_input_tokens_seen": 2473312,
|
|
"step": 435,
|
|
"train_runtime": 2880.2168,
|
|
"train_tokens_per_second": 858.724
|
|
},
|
|
{
|
|
"epoch": 0.8034695275051358,
|
|
"grad_norm": 1.3544775247573853,
|
|
"learning_rate": 4.1706952540978545e-05,
|
|
"loss": 0.8944,
|
|
"num_input_tokens_seen": 2500800,
|
|
"step": 440,
|
|
"train_runtime": 2912.8173,
|
|
"train_tokens_per_second": 858.55
|
|
},
|
|
{
|
|
"epoch": 0.8125998630449669,
|
|
"grad_norm": 1.1478849649429321,
|
|
"learning_rate": 4.152849593671793e-05,
|
|
"loss": 0.9774,
|
|
"num_input_tokens_seen": 2529392,
|
|
"step": 445,
|
|
"train_runtime": 2945.9115,
|
|
"train_tokens_per_second": 858.611
|
|
},
|
|
{
|
|
"epoch": 0.821730198584798,
|
|
"grad_norm": 1.1531591415405273,
|
|
"learning_rate": 4.134853041265162e-05,
|
|
"loss": 0.8543,
|
|
"num_input_tokens_seen": 2559536,
|
|
"step": 450,
|
|
"train_runtime": 2979.5242,
|
|
"train_tokens_per_second": 859.042
|
|
},
|
|
{
|
|
"epoch": 0.8308605341246291,
|
|
"grad_norm": 1.034783959388733,
|
|
"learning_rate": 4.11670723981961e-05,
|
|
"loss": 0.8293,
|
|
"num_input_tokens_seen": 2588144,
|
|
"step": 455,
|
|
"train_runtime": 3012.7186,
|
|
"train_tokens_per_second": 859.073
|
|
},
|
|
{
|
|
"epoch": 0.8399908696644601,
|
|
"grad_norm": 1.181213617324829,
|
|
"learning_rate": 4.098413845902033e-05,
|
|
"loss": 0.9264,
|
|
"num_input_tokens_seen": 2617968,
|
|
"step": 460,
|
|
"train_runtime": 3046.4091,
|
|
"train_tokens_per_second": 859.362
|
|
},
|
|
{
|
|
"epoch": 0.8491212052042912,
|
|
"grad_norm": 1.134751796722412,
|
|
"learning_rate": 4.079974529553341e-05,
|
|
"loss": 0.9641,
|
|
"num_input_tokens_seen": 2646896,
|
|
"step": 465,
|
|
"train_runtime": 3079.7911,
|
|
"train_tokens_per_second": 859.44
|
|
},
|
|
{
|
|
"epoch": 0.8582515407441224,
|
|
"grad_norm": 1.0939092636108398,
|
|
"learning_rate": 4.061390974135997e-05,
|
|
"loss": 0.805,
|
|
"num_input_tokens_seen": 2674288,
|
|
"step": 470,
|
|
"train_runtime": 3112.254,
|
|
"train_tokens_per_second": 859.277
|
|
},
|
|
{
|
|
"epoch": 0.8673818762839535,
|
|
"grad_norm": 1.4272619485855103,
|
|
"learning_rate": 4.042664876180341e-05,
|
|
"loss": 1.0411,
|
|
"num_input_tokens_seen": 2700464,
|
|
"step": 475,
|
|
"train_runtime": 3144.0731,
|
|
"train_tokens_per_second": 858.906
|
|
},
|
|
{
|
|
"epoch": 0.8765122118237845,
|
|
"grad_norm": 1.2609965801239014,
|
|
"learning_rate": 4.0237979452297094e-05,
|
|
"loss": 0.8638,
|
|
"num_input_tokens_seen": 2732112,
|
|
"step": 480,
|
|
"train_runtime": 3178.5283,
|
|
"train_tokens_per_second": 859.553
|
|
},
|
|
{
|
|
"epoch": 0.8856425473636156,
|
|
"grad_norm": 1.5450228452682495,
|
|
"learning_rate": 4.0047919036843675e-05,
|
|
"loss": 1.0152,
|
|
"num_input_tokens_seen": 2757872,
|
|
"step": 485,
|
|
"train_runtime": 3210.3201,
|
|
"train_tokens_per_second": 859.064
|
|
},
|
|
{
|
|
"epoch": 0.8947728829034467,
|
|
"grad_norm": 1.1069929599761963,
|
|
"learning_rate": 3.985648486644267e-05,
|
|
"loss": 0.9046,
|
|
"num_input_tokens_seen": 2786192,
|
|
"step": 490,
|
|
"train_runtime": 3243.3923,
|
|
"train_tokens_per_second": 859.036
|
|
},
|
|
{
|
|
"epoch": 0.9039032184432778,
|
|
"grad_norm": 1.0615628957748413,
|
|
"learning_rate": 3.966369441750648e-05,
|
|
"loss": 0.8428,
|
|
"num_input_tokens_seen": 2812368,
|
|
"step": 495,
|
|
"train_runtime": 3275.3944,
|
|
"train_tokens_per_second": 858.635
|
|
},
|
|
{
|
|
"epoch": 0.9130335539831089,
|
|
"grad_norm": 1.0123751163482666,
|
|
"learning_rate": 3.9469565290264906e-05,
|
|
"loss": 0.8138,
|
|
"num_input_tokens_seen": 2840912,
|
|
"step": 500,
|
|
"train_runtime": 3308.5472,
|
|
"train_tokens_per_second": 858.658
|
|
},
|
|
{
|
|
"epoch": 0.9221638895229399,
|
|
"grad_norm": 1.2222071886062622,
|
|
"learning_rate": 3.92741152071584e-05,
|
|
"loss": 0.8349,
|
|
"num_input_tokens_seen": 2870000,
|
|
"step": 505,
|
|
"train_runtime": 3343.2464,
|
|
"train_tokens_per_second": 858.447
|
|
},
|
|
{
|
|
"epoch": 0.931294225062771,
|
|
"grad_norm": 1.2460840940475464,
|
|
"learning_rate": 3.907736201122014e-05,
|
|
"loss": 0.883,
|
|
"num_input_tokens_seen": 2899328,
|
|
"step": 510,
|
|
"train_runtime": 3376.5896,
|
|
"train_tokens_per_second": 858.656
|
|
},
|
|
{
|
|
"epoch": 0.9404245606026022,
|
|
"grad_norm": 1.1203129291534424,
|
|
"learning_rate": 3.8879323664447096e-05,
|
|
"loss": 0.8141,
|
|
"num_input_tokens_seen": 2928832,
|
|
"step": 515,
|
|
"train_runtime": 3410.0362,
|
|
"train_tokens_per_second": 858.886
|
|
},
|
|
{
|
|
"epoch": 0.9495548961424333,
|
|
"grad_norm": 1.0772883892059326,
|
|
"learning_rate": 3.8680018246160295e-05,
|
|
"loss": 0.8964,
|
|
"num_input_tokens_seen": 2956352,
|
|
"step": 520,
|
|
"train_runtime": 3442.6688,
|
|
"train_tokens_per_second": 858.738
|
|
},
|
|
{
|
|
"epoch": 0.9586852316822643,
|
|
"grad_norm": 1.098358154296875,
|
|
"learning_rate": 3.8479463951354245e-05,
|
|
"loss": 0.7845,
|
|
"num_input_tokens_seen": 2985072,
|
|
"step": 525,
|
|
"train_runtime": 3475.9209,
|
|
"train_tokens_per_second": 858.786
|
|
},
|
|
{
|
|
"epoch": 0.9678155672220954,
|
|
"grad_norm": 1.61497163772583,
|
|
"learning_rate": 3.827767908903592e-05,
|
|
"loss": 0.9675,
|
|
"num_input_tokens_seen": 3013200,
|
|
"step": 530,
|
|
"train_runtime": 3508.7675,
|
|
"train_tokens_per_second": 858.763
|
|
},
|
|
{
|
|
"epoch": 0.9769459027619265,
|
|
"grad_norm": 1.2918585538864136,
|
|
"learning_rate": 3.8074682080553335e-05,
|
|
"loss": 0.9429,
|
|
"num_input_tokens_seen": 3044064,
|
|
"step": 535,
|
|
"train_runtime": 3542.8639,
|
|
"train_tokens_per_second": 859.21
|
|
},
|
|
{
|
|
"epoch": 0.9860762383017576,
|
|
"grad_norm": 1.1658656597137451,
|
|
"learning_rate": 3.7870491457913714e-05,
|
|
"loss": 0.9034,
|
|
"num_input_tokens_seen": 3071008,
|
|
"step": 540,
|
|
"train_runtime": 3575.2913,
|
|
"train_tokens_per_second": 858.953
|
|
},
|
|
{
|
|
"epoch": 0.9952065738415887,
|
|
"grad_norm": 1.8342398405075073,
|
|
"learning_rate": 3.7665125862091765e-05,
|
|
"loss": 0.8696,
|
|
"num_input_tokens_seen": 3100256,
|
|
"step": 545,
|
|
"train_runtime": 3608.7852,
|
|
"train_tokens_per_second": 859.086
|
|
},
|
|
{
|
|
"epoch": 1.0036521342159324,
|
|
"grad_norm": 1.1551634073257446,
|
|
"learning_rate": 3.7458604041327874e-05,
|
|
"loss": 0.9914,
|
|
"num_input_tokens_seen": 3125104,
|
|
"step": 550,
|
|
"train_runtime": 3638.8068,
|
|
"train_tokens_per_second": 858.827
|
|
},
|
|
{
|
|
"epoch": 1.0127824697557635,
|
|
"grad_norm": 1.2146859169006348,
|
|
"learning_rate": 3.725094484941654e-05,
|
|
"loss": 0.7924,
|
|
"num_input_tokens_seen": 3153200,
|
|
"step": 555,
|
|
"train_runtime": 3671.7067,
|
|
"train_tokens_per_second": 858.783
|
|
},
|
|
{
|
|
"epoch": 1.0219128052955946,
|
|
"grad_norm": 1.43285071849823,
|
|
"learning_rate": 3.704216724398515e-05,
|
|
"loss": 0.7542,
|
|
"num_input_tokens_seen": 3180768,
|
|
"step": 560,
|
|
"train_runtime": 3704.3172,
|
|
"train_tokens_per_second": 858.665
|
|
},
|
|
{
|
|
"epoch": 1.0310431408354257,
|
|
"grad_norm": 1.2489193677902222,
|
|
"learning_rate": 3.683229028476334e-05,
|
|
"loss": 0.7216,
|
|
"num_input_tokens_seen": 3208032,
|
|
"step": 565,
|
|
"train_runtime": 3736.7691,
|
|
"train_tokens_per_second": 858.504
|
|
},
|
|
{
|
|
"epoch": 1.0401734763752568,
|
|
"grad_norm": 1.520088791847229,
|
|
"learning_rate": 3.6621333131842994e-05,
|
|
"loss": 0.8276,
|
|
"num_input_tokens_seen": 3235216,
|
|
"step": 570,
|
|
"train_runtime": 3769.2767,
|
|
"train_tokens_per_second": 858.312
|
|
},
|
|
{
|
|
"epoch": 1.049303811915088,
|
|
"grad_norm": 1.1563032865524292,
|
|
"learning_rate": 3.640931504392902e-05,
|
|
"loss": 0.8081,
|
|
"num_input_tokens_seen": 3264128,
|
|
"step": 575,
|
|
"train_runtime": 3802.3942,
|
|
"train_tokens_per_second": 858.44
|
|
},
|
|
{
|
|
"epoch": 1.058434147454919,
|
|
"grad_norm": 1.2162935733795166,
|
|
"learning_rate": 3.6196255376581254e-05,
|
|
"loss": 0.7503,
|
|
"num_input_tokens_seen": 3291488,
|
|
"step": 580,
|
|
"train_runtime": 3834.8435,
|
|
"train_tokens_per_second": 858.311
|
|
},
|
|
{
|
|
"epoch": 1.0675644829947502,
|
|
"grad_norm": 1.1006977558135986,
|
|
"learning_rate": 3.598217358044743e-05,
|
|
"loss": 0.7449,
|
|
"num_input_tokens_seen": 3320544,
|
|
"step": 585,
|
|
"train_runtime": 3868.0173,
|
|
"train_tokens_per_second": 858.462
|
|
},
|
|
{
|
|
"epoch": 1.076694818534581,
|
|
"grad_norm": 1.2781275510787964,
|
|
"learning_rate": 3.576708919948747e-05,
|
|
"loss": 0.7779,
|
|
"num_input_tokens_seen": 3350544,
|
|
"step": 590,
|
|
"train_runtime": 3901.7778,
|
|
"train_tokens_per_second": 858.722
|
|
},
|
|
{
|
|
"epoch": 1.0858251540744122,
|
|
"grad_norm": 1.8124620914459229,
|
|
"learning_rate": 3.5551021869189286e-05,
|
|
"loss": 0.7257,
|
|
"num_input_tokens_seen": 3380800,
|
|
"step": 595,
|
|
"train_runtime": 3935.5685,
|
|
"train_tokens_per_second": 859.037
|
|
},
|
|
{
|
|
"epoch": 1.0949554896142433,
|
|
"grad_norm": 1.1860169172286987,
|
|
"learning_rate": 3.533399131477624e-05,
|
|
"loss": 0.7348,
|
|
"num_input_tokens_seen": 3408976,
|
|
"step": 600,
|
|
"train_runtime": 3968.4791,
|
|
"train_tokens_per_second": 859.013
|
|
},
|
|
{
|
|
"epoch": 1.1040858251540744,
|
|
"grad_norm": 1.4015891551971436,
|
|
"learning_rate": 3.511601734940636e-05,
|
|
"loss": 0.814,
|
|
"num_input_tokens_seen": 3437392,
|
|
"step": 605,
|
|
"train_runtime": 4002.5648,
|
|
"train_tokens_per_second": 858.797
|
|
},
|
|
{
|
|
"epoch": 1.1132161606939055,
|
|
"grad_norm": 1.445547342300415,
|
|
"learning_rate": 3.489711987236357e-05,
|
|
"loss": 0.6645,
|
|
"num_input_tokens_seen": 3465184,
|
|
"step": 610,
|
|
"train_runtime": 4035.2092,
|
|
"train_tokens_per_second": 858.737
|
|
},
|
|
{
|
|
"epoch": 1.1223464962337366,
|
|
"grad_norm": 1.2986106872558594,
|
|
"learning_rate": 3.467731886724104e-05,
|
|
"loss": 0.7804,
|
|
"num_input_tokens_seen": 3493520,
|
|
"step": 615,
|
|
"train_runtime": 4068.2429,
|
|
"train_tokens_per_second": 858.729
|
|
},
|
|
{
|
|
"epoch": 1.1314768317735677,
|
|
"grad_norm": 1.471055030822754,
|
|
"learning_rate": 3.445663440011685e-05,
|
|
"loss": 0.8645,
|
|
"num_input_tokens_seen": 3520400,
|
|
"step": 620,
|
|
"train_runtime": 4100.7487,
|
|
"train_tokens_per_second": 858.477
|
|
},
|
|
{
|
|
"epoch": 1.1406071673133988,
|
|
"grad_norm": 1.3849546909332275,
|
|
"learning_rate": 3.42350866177221e-05,
|
|
"loss": 0.7509,
|
|
"num_input_tokens_seen": 3550208,
|
|
"step": 625,
|
|
"train_runtime": 4134.4243,
|
|
"train_tokens_per_second": 858.695
|
|
},
|
|
{
|
|
"epoch": 1.1497375028532297,
|
|
"grad_norm": 1.3286018371582031,
|
|
"learning_rate": 3.4012695745601694e-05,
|
|
"loss": 0.738,
|
|
"num_input_tokens_seen": 3579424,
|
|
"step": 630,
|
|
"train_runtime": 4167.8838,
|
|
"train_tokens_per_second": 858.811
|
|
},
|
|
{
|
|
"epoch": 1.158867838393061,
|
|
"grad_norm": 1.5071204900741577,
|
|
"learning_rate": 3.378948208626792e-05,
|
|
"loss": 0.731,
|
|
"num_input_tokens_seen": 3608096,
|
|
"step": 635,
|
|
"train_runtime": 4201.1661,
|
|
"train_tokens_per_second": 858.832
|
|
},
|
|
{
|
|
"epoch": 1.167998173932892,
|
|
"grad_norm": 1.225210428237915,
|
|
"learning_rate": 3.356546601734692e-05,
|
|
"loss": 0.6878,
|
|
"num_input_tokens_seen": 3636352,
|
|
"step": 640,
|
|
"train_runtime": 4234.2595,
|
|
"train_tokens_per_second": 858.793
|
|
},
|
|
{
|
|
"epoch": 1.177128509472723,
|
|
"grad_norm": 1.3939982652664185,
|
|
"learning_rate": 3.3340667989718494e-05,
|
|
"loss": 0.6777,
|
|
"num_input_tokens_seen": 3665104,
|
|
"step": 645,
|
|
"train_runtime": 4267.4915,
|
|
"train_tokens_per_second": 858.843
|
|
},
|
|
{
|
|
"epoch": 1.1862588450125542,
|
|
"grad_norm": 1.551377773284912,
|
|
"learning_rate": 3.3115108525648995e-05,
|
|
"loss": 0.8185,
|
|
"num_input_tokens_seen": 3692784,
|
|
"step": 650,
|
|
"train_runtime": 4300.1569,
|
|
"train_tokens_per_second": 858.756
|
|
},
|
|
{
|
|
"epoch": 1.1953891805523853,
|
|
"grad_norm": 1.4566768407821655,
|
|
"learning_rate": 3.288880821691785e-05,
|
|
"loss": 0.7367,
|
|
"num_input_tokens_seen": 3720544,
|
|
"step": 655,
|
|
"train_runtime": 4332.9255,
|
|
"train_tokens_per_second": 858.668
|
|
},
|
|
{
|
|
"epoch": 1.2045195160922164,
|
|
"grad_norm": 1.6438571214675903,
|
|
"learning_rate": 3.2661787722937705e-05,
|
|
"loss": 0.7812,
|
|
"num_input_tokens_seen": 3748640,
|
|
"step": 660,
|
|
"train_runtime": 4365.8382,
|
|
"train_tokens_per_second": 858.63
|
|
},
|
|
{
|
|
"epoch": 1.2136498516320475,
|
|
"grad_norm": 1.207120418548584,
|
|
"learning_rate": 3.2434067768868365e-05,
|
|
"loss": 0.6602,
|
|
"num_input_tokens_seen": 3779312,
|
|
"step": 665,
|
|
"train_runtime": 4399.8682,
|
|
"train_tokens_per_second": 858.96
|
|
},
|
|
{
|
|
"epoch": 1.2227801871718786,
|
|
"grad_norm": 1.2142479419708252,
|
|
"learning_rate": 3.220566914372477e-05,
|
|
"loss": 0.7918,
|
|
"num_input_tokens_seen": 3807232,
|
|
"step": 670,
|
|
"train_runtime": 4432.6887,
|
|
"train_tokens_per_second": 858.899
|
|
},
|
|
{
|
|
"epoch": 1.2319105227117095,
|
|
"grad_norm": 1.5016285181045532,
|
|
"learning_rate": 3.1976612698479104e-05,
|
|
"loss": 0.6596,
|
|
"num_input_tokens_seen": 3835568,
|
|
"step": 675,
|
|
"train_runtime": 4465.6751,
|
|
"train_tokens_per_second": 858.9
|
|
},
|
|
{
|
|
"epoch": 1.2410408582515409,
|
|
"grad_norm": 1.6100620031356812,
|
|
"learning_rate": 3.174691934415727e-05,
|
|
"loss": 0.595,
|
|
"num_input_tokens_seen": 3866240,
|
|
"step": 680,
|
|
"train_runtime": 4499.6303,
|
|
"train_tokens_per_second": 859.235
|
|
},
|
|
{
|
|
"epoch": 1.2501711937913718,
|
|
"grad_norm": 1.548384666442871,
|
|
"learning_rate": 3.151661004992992e-05,
|
|
"loss": 0.7421,
|
|
"num_input_tokens_seen": 3894400,
|
|
"step": 685,
|
|
"train_runtime": 4532.4548,
|
|
"train_tokens_per_second": 859.225
|
|
},
|
|
{
|
|
"epoch": 1.2593015293312029,
|
|
"grad_norm": 1.2995214462280273,
|
|
"learning_rate": 3.128570584119806e-05,
|
|
"loss": 0.8241,
|
|
"num_input_tokens_seen": 3917984,
|
|
"step": 690,
|
|
"train_runtime": 4563.2092,
|
|
"train_tokens_per_second": 858.603
|
|
},
|
|
{
|
|
"epoch": 1.268431864871034,
|
|
"grad_norm": 2.447808027267456,
|
|
"learning_rate": 3.105422779767369e-05,
|
|
"loss": 0.7889,
|
|
"num_input_tokens_seen": 3943952,
|
|
"step": 695,
|
|
"train_runtime": 4595.1589,
|
|
"train_tokens_per_second": 858.284
|
|
},
|
|
{
|
|
"epoch": 1.277562200410865,
|
|
"grad_norm": 1.6894609928131104,
|
|
"learning_rate": 3.08221970514553e-05,
|
|
"loss": 0.8462,
|
|
"num_input_tokens_seen": 3970976,
|
|
"step": 700,
|
|
"train_runtime": 4627.5505,
|
|
"train_tokens_per_second": 858.116
|
|
},
|
|
{
|
|
"epoch": 1.2866925359506962,
|
|
"grad_norm": 1.449867844581604,
|
|
"learning_rate": 3.058963478509879e-05,
|
|
"loss": 0.8064,
|
|
"num_input_tokens_seen": 3998816,
|
|
"step": 705,
|
|
"train_runtime": 4661.3843,
|
|
"train_tokens_per_second": 857.86
|
|
},
|
|
{
|
|
"epoch": 1.2958228714905273,
|
|
"grad_norm": 1.7921152114868164,
|
|
"learning_rate": 3.0356562229683534e-05,
|
|
"loss": 0.7113,
|
|
"num_input_tokens_seen": 4026144,
|
|
"step": 710,
|
|
"train_runtime": 4693.863,
|
|
"train_tokens_per_second": 857.746
|
|
},
|
|
{
|
|
"epoch": 1.3049532070303584,
|
|
"grad_norm": 1.4323357343673706,
|
|
"learning_rate": 3.0123000662874272e-05,
|
|
"loss": 0.7086,
|
|
"num_input_tokens_seen": 4053232,
|
|
"step": 715,
|
|
"train_runtime": 4726.3529,
|
|
"train_tokens_per_second": 857.581
|
|
},
|
|
{
|
|
"epoch": 1.3140835425701893,
|
|
"grad_norm": 1.779567837715149,
|
|
"learning_rate": 2.9888971406978584e-05,
|
|
"loss": 0.6923,
|
|
"num_input_tokens_seen": 4080992,
|
|
"step": 720,
|
|
"train_runtime": 4759.0105,
|
|
"train_tokens_per_second": 857.53
|
|
},
|
|
{
|
|
"epoch": 1.3232138781100207,
|
|
"grad_norm": 1.556424617767334,
|
|
"learning_rate": 2.965449582700031e-05,
|
|
"loss": 0.7034,
|
|
"num_input_tokens_seen": 4108944,
|
|
"step": 725,
|
|
"train_runtime": 4792.0064,
|
|
"train_tokens_per_second": 857.458
|
|
},
|
|
{
|
|
"epoch": 1.3323442136498516,
|
|
"grad_norm": 1.2673003673553467,
|
|
"learning_rate": 2.9419595328689138e-05,
|
|
"loss": 0.7029,
|
|
"num_input_tokens_seen": 4137872,
|
|
"step": 730,
|
|
"train_runtime": 4825.2446,
|
|
"train_tokens_per_second": 857.547
|
|
},
|
|
{
|
|
"epoch": 1.3414745491896827,
|
|
"grad_norm": 1.414905309677124,
|
|
"learning_rate": 2.918429135658638e-05,
|
|
"loss": 0.7442,
|
|
"num_input_tokens_seen": 4167120,
|
|
"step": 735,
|
|
"train_runtime": 4858.5579,
|
|
"train_tokens_per_second": 857.687
|
|
},
|
|
{
|
|
"epoch": 1.3506048847295138,
|
|
"grad_norm": 2.0791618824005127,
|
|
"learning_rate": 2.8948605392067322e-05,
|
|
"loss": 0.6896,
|
|
"num_input_tokens_seen": 4197456,
|
|
"step": 740,
|
|
"train_runtime": 4892.5846,
|
|
"train_tokens_per_second": 857.922
|
|
},
|
|
{
|
|
"epoch": 1.359735220269345,
|
|
"grad_norm": 1.620800256729126,
|
|
"learning_rate": 2.8712558951380097e-05,
|
|
"loss": 0.7188,
|
|
"num_input_tokens_seen": 4226784,
|
|
"step": 745,
|
|
"train_runtime": 4926.0456,
|
|
"train_tokens_per_second": 858.048
|
|
},
|
|
{
|
|
"epoch": 1.368865555809176,
|
|
"grad_norm": 1.6217539310455322,
|
|
"learning_rate": 2.847617358368142e-05,
|
|
"loss": 0.7536,
|
|
"num_input_tokens_seen": 4257552,
|
|
"step": 750,
|
|
"train_runtime": 4960.2606,
|
|
"train_tokens_per_second": 858.332
|
|
},
|
|
{
|
|
"epoch": 1.3779958913490071,
|
|
"grad_norm": 1.5368753671646118,
|
|
"learning_rate": 2.8239470869069357e-05,
|
|
"loss": 0.6742,
|
|
"num_input_tokens_seen": 4285344,
|
|
"step": 755,
|
|
"train_runtime": 4993.0307,
|
|
"train_tokens_per_second": 858.265
|
|
},
|
|
{
|
|
"epoch": 1.3871262268888382,
|
|
"grad_norm": 1.3456413745880127,
|
|
"learning_rate": 2.800247241661321e-05,
|
|
"loss": 0.6787,
|
|
"num_input_tokens_seen": 4313920,
|
|
"step": 760,
|
|
"train_runtime": 5026.2219,
|
|
"train_tokens_per_second": 858.283
|
|
},
|
|
{
|
|
"epoch": 1.3962565624286691,
|
|
"grad_norm": 1.3520539999008179,
|
|
"learning_rate": 2.776519986238079e-05,
|
|
"loss": 0.8232,
|
|
"num_input_tokens_seen": 4341584,
|
|
"step": 765,
|
|
"train_runtime": 5058.8442,
|
|
"train_tokens_per_second": 858.217
|
|
},
|
|
{
|
|
"epoch": 1.4053868979685005,
|
|
"grad_norm": 1.5738906860351562,
|
|
"learning_rate": 2.75276748674632e-05,
|
|
"loss": 0.7529,
|
|
"num_input_tokens_seen": 4369072,
|
|
"step": 770,
|
|
"train_runtime": 5091.5528,
|
|
"train_tokens_per_second": 858.102
|
|
},
|
|
{
|
|
"epoch": 1.4145172335083314,
|
|
"grad_norm": 1.485304594039917,
|
|
"learning_rate": 2.7289919115997374e-05,
|
|
"loss": 0.7612,
|
|
"num_input_tokens_seen": 4397152,
|
|
"step": 775,
|
|
"train_runtime": 5124.3984,
|
|
"train_tokens_per_second": 858.082
|
|
},
|
|
{
|
|
"epoch": 1.4236475690481625,
|
|
"grad_norm": 1.7065860033035278,
|
|
"learning_rate": 2.7051954313186484e-05,
|
|
"loss": 0.777,
|
|
"num_input_tokens_seen": 4423120,
|
|
"step": 780,
|
|
"train_runtime": 5156.3448,
|
|
"train_tokens_per_second": 857.801
|
|
},
|
|
{
|
|
"epoch": 1.4327779045879936,
|
|
"grad_norm": 2.3600783348083496,
|
|
"learning_rate": 2.6813802183318404e-05,
|
|
"loss": 0.7732,
|
|
"num_input_tokens_seen": 4451328,
|
|
"step": 785,
|
|
"train_runtime": 5189.1907,
|
|
"train_tokens_per_second": 857.808
|
|
},
|
|
{
|
|
"epoch": 1.4419082401278247,
|
|
"grad_norm": 1.3053230047225952,
|
|
"learning_rate": 2.6575484467782486e-05,
|
|
"loss": 0.6874,
|
|
"num_input_tokens_seen": 4480256,
|
|
"step": 790,
|
|
"train_runtime": 5222.4951,
|
|
"train_tokens_per_second": 857.877
|
|
},
|
|
{
|
|
"epoch": 1.4510385756676558,
|
|
"grad_norm": 1.2987860441207886,
|
|
"learning_rate": 2.633702292308473e-05,
|
|
"loss": 0.6866,
|
|
"num_input_tokens_seen": 4509584,
|
|
"step": 795,
|
|
"train_runtime": 5255.8931,
|
|
"train_tokens_per_second": 858.005
|
|
},
|
|
{
|
|
"epoch": 1.460168911207487,
|
|
"grad_norm": 1.6623998880386353,
|
|
"learning_rate": 2.60984393188616e-05,
|
|
"loss": 0.6184,
|
|
"num_input_tokens_seen": 4537136,
|
|
"step": 800,
|
|
"train_runtime": 5288.583,
|
|
"train_tokens_per_second": 857.911
|
|
},
|
|
{
|
|
"epoch": 1.469299246747318,
|
|
"grad_norm": 1.233757734298706,
|
|
"learning_rate": 2.5859755435892597e-05,
|
|
"loss": 0.6364,
|
|
"num_input_tokens_seen": 4565424,
|
|
"step": 805,
|
|
"train_runtime": 5322.8159,
|
|
"train_tokens_per_second": 857.708
|
|
},
|
|
{
|
|
"epoch": 1.478429582287149,
|
|
"grad_norm": 1.917475700378418,
|
|
"learning_rate": 2.5620993064111902e-05,
|
|
"loss": 0.7312,
|
|
"num_input_tokens_seen": 4592976,
|
|
"step": 810,
|
|
"train_runtime": 5355.4266,
|
|
"train_tokens_per_second": 857.63
|
|
},
|
|
{
|
|
"epoch": 1.4875599178269803,
|
|
"grad_norm": 1.3960131406784058,
|
|
"learning_rate": 2.538217400061907e-05,
|
|
"loss": 0.6735,
|
|
"num_input_tokens_seen": 4622416,
|
|
"step": 815,
|
|
"train_runtime": 5388.765,
|
|
"train_tokens_per_second": 857.788
|
|
},
|
|
{
|
|
"epoch": 1.4966902533668112,
|
|
"grad_norm": 2.6439576148986816,
|
|
"learning_rate": 2.5143320047689173e-05,
|
|
"loss": 0.5681,
|
|
"num_input_tokens_seen": 4648848,
|
|
"step": 820,
|
|
"train_runtime": 5421.0274,
|
|
"train_tokens_per_second": 857.558
|
|
},
|
|
{
|
|
"epoch": 1.5058205889066423,
|
|
"grad_norm": 1.6874146461486816,
|
|
"learning_rate": 2.49044530107824e-05,
|
|
"loss": 0.7154,
|
|
"num_input_tokens_seen": 4674688,
|
|
"step": 825,
|
|
"train_runtime": 5453.0982,
|
|
"train_tokens_per_second": 857.254
|
|
},
|
|
{
|
|
"epoch": 1.5149509244464734,
|
|
"grad_norm": 2.135629892349243,
|
|
"learning_rate": 2.4665594696553428e-05,
|
|
"loss": 0.659,
|
|
"num_input_tokens_seen": 4700240,
|
|
"step": 830,
|
|
"train_runtime": 5484.8225,
|
|
"train_tokens_per_second": 856.954
|
|
},
|
|
{
|
|
"epoch": 1.5240812599863045,
|
|
"grad_norm": 1.135087490081787,
|
|
"learning_rate": 2.4426766910860585e-05,
|
|
"loss": 0.66,
|
|
"num_input_tokens_seen": 4729648,
|
|
"step": 835,
|
|
"train_runtime": 5518.3348,
|
|
"train_tokens_per_second": 857.079
|
|
},
|
|
{
|
|
"epoch": 1.5332115955261356,
|
|
"grad_norm": 1.5050617456436157,
|
|
"learning_rate": 2.4187991456775217e-05,
|
|
"loss": 0.8048,
|
|
"num_input_tokens_seen": 4758944,
|
|
"step": 840,
|
|
"train_runtime": 5551.5721,
|
|
"train_tokens_per_second": 857.225
|
|
},
|
|
{
|
|
"epoch": 1.5423419310659665,
|
|
"grad_norm": 2.2734262943267822,
|
|
"learning_rate": 2.3949290132591197e-05,
|
|
"loss": 0.6516,
|
|
"num_input_tokens_seen": 4787360,
|
|
"step": 845,
|
|
"train_runtime": 5584.6087,
|
|
"train_tokens_per_second": 857.242
|
|
},
|
|
{
|
|
"epoch": 1.5514722666057978,
|
|
"grad_norm": 1.2877403497695923,
|
|
"learning_rate": 2.3710684729834954e-05,
|
|
"loss": 0.6813,
|
|
"num_input_tokens_seen": 4815712,
|
|
"step": 850,
|
|
"train_runtime": 5617.6077,
|
|
"train_tokens_per_second": 857.253
|
|
},
|
|
{
|
|
"epoch": 1.5606026021456287,
|
|
"grad_norm": 1.3478307723999023,
|
|
"learning_rate": 2.3472197031276e-05,
|
|
"loss": 0.7308,
|
|
"num_input_tokens_seen": 4845280,
|
|
"step": 855,
|
|
"train_runtime": 5651.0463,
|
|
"train_tokens_per_second": 857.413
|
|
},
|
|
{
|
|
"epoch": 1.56973293768546,
|
|
"grad_norm": 1.378150463104248,
|
|
"learning_rate": 2.3233848808938453e-05,
|
|
"loss": 0.7728,
|
|
"num_input_tokens_seen": 4873936,
|
|
"step": 860,
|
|
"train_runtime": 5684.0879,
|
|
"train_tokens_per_second": 857.47
|
|
},
|
|
{
|
|
"epoch": 1.578863273225291,
|
|
"grad_norm": 1.5141141414642334,
|
|
"learning_rate": 2.299566182211333e-05,
|
|
"loss": 0.6673,
|
|
"num_input_tokens_seen": 4901104,
|
|
"step": 865,
|
|
"train_runtime": 5716.3954,
|
|
"train_tokens_per_second": 857.377
|
|
},
|
|
{
|
|
"epoch": 1.587993608765122,
|
|
"grad_norm": 1.601626992225647,
|
|
"learning_rate": 2.275765781537215e-05,
|
|
"loss": 0.7155,
|
|
"num_input_tokens_seen": 4929696,
|
|
"step": 870,
|
|
"train_runtime": 5749.5599,
|
|
"train_tokens_per_second": 857.404
|
|
},
|
|
{
|
|
"epoch": 1.5971239443049532,
|
|
"grad_norm": 1.5736284255981445,
|
|
"learning_rate": 2.251985851658181e-05,
|
|
"loss": 0.6372,
|
|
"num_input_tokens_seen": 4959408,
|
|
"step": 875,
|
|
"train_runtime": 5783.3079,
|
|
"train_tokens_per_second": 857.538
|
|
},
|
|
{
|
|
"epoch": 1.6062542798447843,
|
|
"grad_norm": 1.464152216911316,
|
|
"learning_rate": 2.228228563492098e-05,
|
|
"loss": 0.7021,
|
|
"num_input_tokens_seen": 4988800,
|
|
"step": 880,
|
|
"train_runtime": 5816.7568,
|
|
"train_tokens_per_second": 857.66
|
|
},
|
|
{
|
|
"epoch": 1.6153846153846154,
|
|
"grad_norm": 2.137424945831299,
|
|
"learning_rate": 2.2044960858898277e-05,
|
|
"loss": 0.6923,
|
|
"num_input_tokens_seen": 5018752,
|
|
"step": 885,
|
|
"train_runtime": 5850.4263,
|
|
"train_tokens_per_second": 857.844
|
|
},
|
|
{
|
|
"epoch": 1.6245149509244463,
|
|
"grad_norm": 1.4711562395095825,
|
|
"learning_rate": 2.1807905854372242e-05,
|
|
"loss": 0.6426,
|
|
"num_input_tokens_seen": 5047792,
|
|
"step": 890,
|
|
"train_runtime": 5883.6717,
|
|
"train_tokens_per_second": 857.932
|
|
},
|
|
{
|
|
"epoch": 1.6336452864642776,
|
|
"grad_norm": 1.6127244234085083,
|
|
"learning_rate": 2.1571142262573457e-05,
|
|
"loss": 0.5618,
|
|
"num_input_tokens_seen": 5076528,
|
|
"step": 895,
|
|
"train_runtime": 5916.924,
|
|
"train_tokens_per_second": 857.967
|
|
},
|
|
{
|
|
"epoch": 1.6427756220041085,
|
|
"grad_norm": 2.0708415508270264,
|
|
"learning_rate": 2.133469169812879e-05,
|
|
"loss": 0.616,
|
|
"num_input_tokens_seen": 5101504,
|
|
"step": 900,
|
|
"train_runtime": 5948.3179,
|
|
"train_tokens_per_second": 857.638
|
|
},
|
|
{
|
|
"epoch": 1.6519059575439399,
|
|
"grad_norm": 1.7397692203521729,
|
|
"learning_rate": 2.109857574708826e-05,
|
|
"loss": 0.6574,
|
|
"num_input_tokens_seen": 5129104,
|
|
"step": 905,
|
|
"train_runtime": 5982.137,
|
|
"train_tokens_per_second": 857.403
|
|
},
|
|
{
|
|
"epoch": 1.6610362930837708,
|
|
"grad_norm": 2.0171751976013184,
|
|
"learning_rate": 2.086281596495434e-05,
|
|
"loss": 0.6823,
|
|
"num_input_tokens_seen": 5156640,
|
|
"step": 910,
|
|
"train_runtime": 6014.8999,
|
|
"train_tokens_per_second": 857.311
|
|
},
|
|
{
|
|
"epoch": 1.6701666286236019,
|
|
"grad_norm": 1.524135708808899,
|
|
"learning_rate": 2.0627433874714115e-05,
|
|
"loss": 0.5728,
|
|
"num_input_tokens_seen": 5184848,
|
|
"step": 915,
|
|
"train_runtime": 6047.8057,
|
|
"train_tokens_per_second": 857.311
|
|
},
|
|
{
|
|
"epoch": 1.679296964163433,
|
|
"grad_norm": 1.4557563066482544,
|
|
"learning_rate": 2.0392450964874415e-05,
|
|
"loss": 0.7025,
|
|
"num_input_tokens_seen": 5212928,
|
|
"step": 920,
|
|
"train_runtime": 6080.8053,
|
|
"train_tokens_per_second": 857.276
|
|
},
|
|
{
|
|
"epoch": 1.688427299703264,
|
|
"grad_norm": 2.1225433349609375,
|
|
"learning_rate": 2.015788868750009e-05,
|
|
"loss": 0.5986,
|
|
"num_input_tokens_seen": 5243568,
|
|
"step": 925,
|
|
"train_runtime": 6114.7733,
|
|
"train_tokens_per_second": 857.525
|
|
},
|
|
{
|
|
"epoch": 1.6975576352430952,
|
|
"grad_norm": 1.5523720979690552,
|
|
"learning_rate": 1.9923768456255594e-05,
|
|
"loss": 0.6195,
|
|
"num_input_tokens_seen": 5269840,
|
|
"step": 930,
|
|
"train_runtime": 6146.8665,
|
|
"train_tokens_per_second": 857.321
|
|
},
|
|
{
|
|
"epoch": 1.7066879707829261,
|
|
"grad_norm": 1.5369882583618164,
|
|
"learning_rate": 1.969011164445011e-05,
|
|
"loss": 0.6283,
|
|
"num_input_tokens_seen": 5299120,
|
|
"step": 935,
|
|
"train_runtime": 6180.3855,
|
|
"train_tokens_per_second": 857.409
|
|
},
|
|
{
|
|
"epoch": 1.7158183063227574,
|
|
"grad_norm": 1.5137027502059937,
|
|
"learning_rate": 1.9456939583086303e-05,
|
|
"loss": 0.5767,
|
|
"num_input_tokens_seen": 5328464,
|
|
"step": 940,
|
|
"train_runtime": 6213.906,
|
|
"train_tokens_per_second": 857.506
|
|
},
|
|
{
|
|
"epoch": 1.7249486418625883,
|
|
"grad_norm": 1.5988773107528687,
|
|
"learning_rate": 1.9224273558913024e-05,
|
|
"loss": 0.5237,
|
|
"num_input_tokens_seen": 5354896,
|
|
"step": 945,
|
|
"train_runtime": 6245.9758,
|
|
"train_tokens_per_second": 857.335
|
|
},
|
|
{
|
|
"epoch": 1.7340789774024197,
|
|
"grad_norm": 1.878609538078308,
|
|
"learning_rate": 1.8992134812481915e-05,
|
|
"loss": 0.7184,
|
|
"num_input_tokens_seen": 5383856,
|
|
"step": 950,
|
|
"train_runtime": 6279.2585,
|
|
"train_tokens_per_second": 857.403
|
|
},
|
|
{
|
|
"epoch": 1.7432093129422506,
|
|
"grad_norm": 1.5450001955032349,
|
|
"learning_rate": 1.876054453620841e-05,
|
|
"loss": 0.6595,
|
|
"num_input_tokens_seen": 5412864,
|
|
"step": 955,
|
|
"train_runtime": 6312.6127,
|
|
"train_tokens_per_second": 857.468
|
|
},
|
|
{
|
|
"epoch": 1.7523396484820817,
|
|
"grad_norm": 1.623189091682434,
|
|
"learning_rate": 1.852952387243698e-05,
|
|
"loss": 0.6161,
|
|
"num_input_tokens_seen": 5441392,
|
|
"step": 960,
|
|
"train_runtime": 6345.6472,
|
|
"train_tokens_per_second": 857.5
|
|
},
|
|
{
|
|
"epoch": 1.7614699840219128,
|
|
"grad_norm": 1.7493008375167847,
|
|
"learning_rate": 1.829909391151103e-05,
|
|
"loss": 0.6076,
|
|
"num_input_tokens_seen": 5470928,
|
|
"step": 965,
|
|
"train_runtime": 6379.1343,
|
|
"train_tokens_per_second": 857.629
|
|
},
|
|
{
|
|
"epoch": 1.770600319561744,
|
|
"grad_norm": 1.557199478149414,
|
|
"learning_rate": 1.8069275689847466e-05,
|
|
"loss": 0.5543,
|
|
"num_input_tokens_seen": 5500576,
|
|
"step": 970,
|
|
"train_runtime": 6412.7424,
|
|
"train_tokens_per_second": 857.757
|
|
},
|
|
{
|
|
"epoch": 1.779730655101575,
|
|
"grad_norm": 1.6990467309951782,
|
|
"learning_rate": 1.784009018801634e-05,
|
|
"loss": 0.6496,
|
|
"num_input_tokens_seen": 5528288,
|
|
"step": 975,
|
|
"train_runtime": 6445.5057,
|
|
"train_tokens_per_second": 857.697
|
|
},
|
|
{
|
|
"epoch": 1.788860990641406,
|
|
"grad_norm": 1.5374281406402588,
|
|
"learning_rate": 1.7611558328825384e-05,
|
|
"loss": 0.6315,
|
|
"num_input_tokens_seen": 5557472,
|
|
"step": 980,
|
|
"train_runtime": 6478.8281,
|
|
"train_tokens_per_second": 857.79
|
|
},
|
|
{
|
|
"epoch": 1.7979913261812372,
|
|
"grad_norm": 1.4920860528945923,
|
|
"learning_rate": 1.738370097541e-05,
|
|
"loss": 0.5654,
|
|
"num_input_tokens_seen": 5585120,
|
|
"step": 985,
|
|
"train_runtime": 6511.6592,
|
|
"train_tokens_per_second": 857.711
|
|
},
|
|
{
|
|
"epoch": 1.8071216617210681,
|
|
"grad_norm": 1.4632899761199951,
|
|
"learning_rate": 1.7156538929328593e-05,
|
|
"loss": 0.5803,
|
|
"num_input_tokens_seen": 5613760,
|
|
"step": 990,
|
|
"train_runtime": 6544.853,
|
|
"train_tokens_per_second": 857.737
|
|
},
|
|
{
|
|
"epoch": 1.8162519972608995,
|
|
"grad_norm": 1.9237911701202393,
|
|
"learning_rate": 1.6930092928663532e-05,
|
|
"loss": 0.5516,
|
|
"num_input_tokens_seen": 5643504,
|
|
"step": 995,
|
|
"train_runtime": 6578.4548,
|
|
"train_tokens_per_second": 857.877
|
|
},
|
|
{
|
|
"epoch": 1.8253823328007304,
|
|
"grad_norm": 2.859373092651367,
|
|
"learning_rate": 1.6704383646127973e-05,
|
|
"loss": 0.653,
|
|
"num_input_tokens_seen": 5671936,
|
|
"step": 1000,
|
|
"train_runtime": 6611.438,
|
|
"train_tokens_per_second": 857.897
|
|
},
|
|
{
|
|
"epoch": 1.8345126683405615,
|
|
"grad_norm": 1.613446593284607,
|
|
"learning_rate": 1.6479431687178584e-05,
|
|
"loss": 0.6456,
|
|
"num_input_tokens_seen": 5701200,
|
|
"step": 1005,
|
|
"train_runtime": 6646.1194,
|
|
"train_tokens_per_second": 857.824
|
|
},
|
|
{
|
|
"epoch": 1.8436430038803926,
|
|
"grad_norm": 2.326117753982544,
|
|
"learning_rate": 1.6255257588134426e-05,
|
|
"loss": 0.6778,
|
|
"num_input_tokens_seen": 5728032,
|
|
"step": 1010,
|
|
"train_runtime": 6678.532,
|
|
"train_tokens_per_second": 857.678
|
|
},
|
|
{
|
|
"epoch": 1.8527733394202237,
|
|
"grad_norm": 1.6666271686553955,
|
|
"learning_rate": 1.603188181430216e-05,
|
|
"loss": 0.6779,
|
|
"num_input_tokens_seen": 5756080,
|
|
"step": 1015,
|
|
"train_runtime": 6711.4743,
|
|
"train_tokens_per_second": 857.648
|
|
},
|
|
{
|
|
"epoch": 1.8619036749600548,
|
|
"grad_norm": 1.2438191175460815,
|
|
"learning_rate": 1.580932475810772e-05,
|
|
"loss": 0.5039,
|
|
"num_input_tokens_seen": 5785760,
|
|
"step": 1020,
|
|
"train_runtime": 6745.102,
|
|
"train_tokens_per_second": 857.772
|
|
},
|
|
{
|
|
"epoch": 1.8710340104998857,
|
|
"grad_norm": 1.6979848146438599,
|
|
"learning_rate": 1.5587606737234654e-05,
|
|
"loss": 0.6694,
|
|
"num_input_tokens_seen": 5813936,
|
|
"step": 1025,
|
|
"train_runtime": 6777.9312,
|
|
"train_tokens_per_second": 857.774
|
|
},
|
|
{
|
|
"epoch": 1.880164346039717,
|
|
"grad_norm": 1.7147233486175537,
|
|
"learning_rate": 1.5366747992769287e-05,
|
|
"loss": 0.5749,
|
|
"num_input_tokens_seen": 5844128,
|
|
"step": 1030,
|
|
"train_runtime": 6811.7365,
|
|
"train_tokens_per_second": 857.95
|
|
},
|
|
{
|
|
"epoch": 1.889294681579548,
|
|
"grad_norm": 1.3455411195755005,
|
|
"learning_rate": 1.5146768687352864e-05,
|
|
"loss": 0.5602,
|
|
"num_input_tokens_seen": 5872512,
|
|
"step": 1035,
|
|
"train_runtime": 6844.8473,
|
|
"train_tokens_per_second": 857.946
|
|
},
|
|
{
|
|
"epoch": 1.8984250171193793,
|
|
"grad_norm": 1.3454474210739136,
|
|
"learning_rate": 1.4927688903340836e-05,
|
|
"loss": 0.645,
|
|
"num_input_tokens_seen": 5898992,
|
|
"step": 1040,
|
|
"train_runtime": 6877.0142,
|
|
"train_tokens_per_second": 857.784
|
|
},
|
|
{
|
|
"epoch": 1.9075553526592102,
|
|
"grad_norm": 1.5111793279647827,
|
|
"learning_rate": 1.4709528640969552e-05,
|
|
"loss": 0.6209,
|
|
"num_input_tokens_seen": 5929632,
|
|
"step": 1045,
|
|
"train_runtime": 6910.9697,
|
|
"train_tokens_per_second": 858.003
|
|
},
|
|
{
|
|
"epoch": 1.9166856881990413,
|
|
"grad_norm": 1.53132164478302,
|
|
"learning_rate": 1.4492307816530375e-05,
|
|
"loss": 0.5908,
|
|
"num_input_tokens_seen": 5956832,
|
|
"step": 1050,
|
|
"train_runtime": 6943.4823,
|
|
"train_tokens_per_second": 857.903
|
|
},
|
|
{
|
|
"epoch": 1.9258160237388724,
|
|
"grad_norm": 1.7620954513549805,
|
|
"learning_rate": 1.4276046260551462e-05,
|
|
"loss": 0.5957,
|
|
"num_input_tokens_seen": 5985104,
|
|
"step": 1055,
|
|
"train_runtime": 6976.3497,
|
|
"train_tokens_per_second": 857.913
|
|
},
|
|
{
|
|
"epoch": 1.9349463592787035,
|
|
"grad_norm": 1.6221617460250854,
|
|
"learning_rate": 1.4060763715987418e-05,
|
|
"loss": 0.6543,
|
|
"num_input_tokens_seen": 6010992,
|
|
"step": 1060,
|
|
"train_runtime": 7008.2681,
|
|
"train_tokens_per_second": 857.7
|
|
},
|
|
{
|
|
"epoch": 1.9440766948185346,
|
|
"grad_norm": 1.9814153909683228,
|
|
"learning_rate": 1.3846479836416929e-05,
|
|
"loss": 0.5055,
|
|
"num_input_tokens_seen": 6041008,
|
|
"step": 1065,
|
|
"train_runtime": 7042.0949,
|
|
"train_tokens_per_second": 857.842
|
|
},
|
|
{
|
|
"epoch": 1.9532070303583655,
|
|
"grad_norm": 1.3477661609649658,
|
|
"learning_rate": 1.3633214184248521e-05,
|
|
"loss": 0.5246,
|
|
"num_input_tokens_seen": 6070832,
|
|
"step": 1070,
|
|
"train_runtime": 7075.8177,
|
|
"train_tokens_per_second": 857.969
|
|
},
|
|
{
|
|
"epoch": 1.9623373658981969,
|
|
"grad_norm": 2.347092390060425,
|
|
"learning_rate": 1.342098622893469e-05,
|
|
"loss": 0.5412,
|
|
"num_input_tokens_seen": 6100064,
|
|
"step": 1075,
|
|
"train_runtime": 7109.1762,
|
|
"train_tokens_per_second": 858.055
|
|
},
|
|
{
|
|
"epoch": 1.9714677014380277,
|
|
"grad_norm": 1.9612821340560913,
|
|
"learning_rate": 1.3209815345194496e-05,
|
|
"loss": 0.624,
|
|
"num_input_tokens_seen": 6127088,
|
|
"step": 1080,
|
|
"train_runtime": 7141.5945,
|
|
"train_tokens_per_second": 857.944
|
|
},
|
|
{
|
|
"epoch": 1.980598036977859,
|
|
"grad_norm": 1.7594658136367798,
|
|
"learning_rate": 1.2999720811244767e-05,
|
|
"loss": 0.5854,
|
|
"num_input_tokens_seen": 6154768,
|
|
"step": 1085,
|
|
"train_runtime": 7174.3094,
|
|
"train_tokens_per_second": 857.89
|
|
},
|
|
{
|
|
"epoch": 1.98972837251769,
|
|
"grad_norm": 1.341110110282898,
|
|
"learning_rate": 1.2790721807040216e-05,
|
|
"loss": 0.5972,
|
|
"num_input_tokens_seen": 6181824,
|
|
"step": 1090,
|
|
"train_runtime": 7206.6527,
|
|
"train_tokens_per_second": 857.794
|
|
},
|
|
{
|
|
"epoch": 1.998858708057521,
|
|
"grad_norm": 1.0875003337860107,
|
|
"learning_rate": 1.2582837412522418e-05,
|
|
"loss": 0.5627,
|
|
"num_input_tokens_seen": 6211904,
|
|
"step": 1095,
|
|
"train_runtime": 7240.3539,
|
|
"train_tokens_per_second": 857.956
|
|
},
|
|
{
|
|
"epoch": 2.0073042684318647,
|
|
"grad_norm": 1.4245753288269043,
|
|
"learning_rate": 1.2376086605877976e-05,
|
|
"loss": 0.544,
|
|
"num_input_tokens_seen": 6238272,
|
|
"step": 1100,
|
|
"train_runtime": 7270.9785,
|
|
"train_tokens_per_second": 857.969
|
|
},
|
|
{
|
|
"epoch": 2.016434603971696,
|
|
"grad_norm": 1.5748745203018188,
|
|
"learning_rate": 1.2170488261805978e-05,
|
|
"loss": 0.4701,
|
|
"num_input_tokens_seen": 6268288,
|
|
"step": 1105,
|
|
"train_runtime": 7305.8219,
|
|
"train_tokens_per_second": 857.985
|
|
},
|
|
{
|
|
"epoch": 2.025564939511527,
|
|
"grad_norm": 1.5691639184951782,
|
|
"learning_rate": 1.1966061149794846e-05,
|
|
"loss": 0.4359,
|
|
"num_input_tokens_seen": 6299168,
|
|
"step": 1110,
|
|
"train_runtime": 7339.8668,
|
|
"train_tokens_per_second": 858.213
|
|
},
|
|
{
|
|
"epoch": 2.0346952750513583,
|
|
"grad_norm": 1.7195948362350464,
|
|
"learning_rate": 1.176282393240888e-05,
|
|
"loss": 0.4436,
|
|
"num_input_tokens_seen": 6329296,
|
|
"step": 1115,
|
|
"train_runtime": 7373.7902,
|
|
"train_tokens_per_second": 858.35
|
|
},
|
|
{
|
|
"epoch": 2.043825610591189,
|
|
"grad_norm": 1.504329800605774,
|
|
"learning_rate": 1.1560795163584492e-05,
|
|
"loss": 0.5898,
|
|
"num_input_tokens_seen": 6356992,
|
|
"step": 1120,
|
|
"train_runtime": 7406.474,
|
|
"train_tokens_per_second": 858.302
|
|
},
|
|
{
|
|
"epoch": 2.0529559461310205,
|
|
"grad_norm": 1.5670088529586792,
|
|
"learning_rate": 1.1359993286936382e-05,
|
|
"loss": 0.5882,
|
|
"num_input_tokens_seen": 6382256,
|
|
"step": 1125,
|
|
"train_runtime": 7438.1266,
|
|
"train_tokens_per_second": 858.046
|
|
},
|
|
{
|
|
"epoch": 2.0620862816708514,
|
|
"grad_norm": 1.3568974733352661,
|
|
"learning_rate": 1.1160436634073786e-05,
|
|
"loss": 0.4388,
|
|
"num_input_tokens_seen": 6410016,
|
|
"step": 1130,
|
|
"train_runtime": 7470.9275,
|
|
"train_tokens_per_second": 857.995
|
|
},
|
|
{
|
|
"epoch": 2.0712166172106823,
|
|
"grad_norm": 1.301599144935608,
|
|
"learning_rate": 1.0962143422926929e-05,
|
|
"loss": 0.5827,
|
|
"num_input_tokens_seen": 6438768,
|
|
"step": 1135,
|
|
"train_runtime": 7504.1642,
|
|
"train_tokens_per_second": 858.026
|
|
},
|
|
{
|
|
"epoch": 2.0803469527505136,
|
|
"grad_norm": 1.7366254329681396,
|
|
"learning_rate": 1.0765131756083899e-05,
|
|
"loss": 0.5261,
|
|
"num_input_tokens_seen": 6466400,
|
|
"step": 1140,
|
|
"train_runtime": 7536.8587,
|
|
"train_tokens_per_second": 857.97
|
|
},
|
|
{
|
|
"epoch": 2.0894772882903445,
|
|
"grad_norm": 1.5877344608306885,
|
|
"learning_rate": 1.0569419619138012e-05,
|
|
"loss": 0.5661,
|
|
"num_input_tokens_seen": 6493488,
|
|
"step": 1145,
|
|
"train_runtime": 7569.2668,
|
|
"train_tokens_per_second": 857.875
|
|
},
|
|
{
|
|
"epoch": 2.098607623830176,
|
|
"grad_norm": 1.3803666830062866,
|
|
"learning_rate": 1.0375024879045889e-05,
|
|
"loss": 0.538,
|
|
"num_input_tokens_seen": 6521104,
|
|
"step": 1150,
|
|
"train_runtime": 7601.999,
|
|
"train_tokens_per_second": 857.814
|
|
},
|
|
{
|
|
"epoch": 2.1077379593700067,
|
|
"grad_norm": 1.4870142936706543,
|
|
"learning_rate": 1.0181965282496289e-05,
|
|
"loss": 0.7164,
|
|
"num_input_tokens_seen": 6548832,
|
|
"step": 1155,
|
|
"train_runtime": 7634.8619,
|
|
"train_tokens_per_second": 857.754
|
|
},
|
|
{
|
|
"epoch": 2.116868294909838,
|
|
"grad_norm": 2.605409860610962,
|
|
"learning_rate": 9.990258454290055e-06,
|
|
"loss": 0.5611,
|
|
"num_input_tokens_seen": 6577648,
|
|
"step": 1160,
|
|
"train_runtime": 7668.0751,
|
|
"train_tokens_per_second": 857.796
|
|
},
|
|
{
|
|
"epoch": 2.125998630449669,
|
|
"grad_norm": 1.7612236738204956,
|
|
"learning_rate": 9.799921895731062e-06,
|
|
"loss": 0.5341,
|
|
"num_input_tokens_seen": 6604720,
|
|
"step": 1165,
|
|
"train_runtime": 7700.4964,
|
|
"train_tokens_per_second": 857.701
|
|
},
|
|
{
|
|
"epoch": 2.1351289659895003,
|
|
"grad_norm": 1.2417925596237183,
|
|
"learning_rate": 9.610972983028493e-06,
|
|
"loss": 0.4899,
|
|
"num_input_tokens_seen": 6631696,
|
|
"step": 1170,
|
|
"train_runtime": 7732.822,
|
|
"train_tokens_per_second": 857.604
|
|
},
|
|
{
|
|
"epoch": 2.144259301529331,
|
|
"grad_norm": 1.9707194566726685,
|
|
"learning_rate": 9.423428965710554e-06,
|
|
"loss": 0.6115,
|
|
"num_input_tokens_seen": 6659728,
|
|
"step": 1175,
|
|
"train_runtime": 7765.6556,
|
|
"train_tokens_per_second": 857.587
|
|
},
|
|
{
|
|
"epoch": 2.153389637069162,
|
|
"grad_norm": 1.5473870038986206,
|
|
"learning_rate": 9.237306965049677e-06,
|
|
"loss": 0.5713,
|
|
"num_input_tokens_seen": 6688928,
|
|
"step": 1180,
|
|
"train_runtime": 7799.0145,
|
|
"train_tokens_per_second": 857.663
|
|
},
|
|
{
|
|
"epoch": 2.1625199726089934,
|
|
"grad_norm": 1.9179930686950684,
|
|
"learning_rate": 9.05262397249955e-06,
|
|
"loss": 0.5144,
|
|
"num_input_tokens_seen": 6717488,
|
|
"step": 1185,
|
|
"train_runtime": 7832.0227,
|
|
"train_tokens_per_second": 857.695
|
|
},
|
|
{
|
|
"epoch": 2.1716503081488243,
|
|
"grad_norm": 2.1739985942840576,
|
|
"learning_rate": 8.869396848143893e-06,
|
|
"loss": 0.5139,
|
|
"num_input_tokens_seen": 6746864,
|
|
"step": 1190,
|
|
"train_runtime": 7865.4644,
|
|
"train_tokens_per_second": 857.783
|
|
},
|
|
{
|
|
"epoch": 2.1807806436886557,
|
|
"grad_norm": 1.552583932876587,
|
|
"learning_rate": 8.687642319157279e-06,
|
|
"loss": 0.5763,
|
|
"num_input_tokens_seen": 6775216,
|
|
"step": 1195,
|
|
"train_runtime": 7898.5982,
|
|
"train_tokens_per_second": 857.774
|
|
},
|
|
{
|
|
"epoch": 2.1899109792284865,
|
|
"grad_norm": 1.612890362739563,
|
|
"learning_rate": 8.507376978278053e-06,
|
|
"loss": 0.5669,
|
|
"num_input_tokens_seen": 6806496,
|
|
"step": 1200,
|
|
"train_runtime": 7932.917,
|
|
"train_tokens_per_second": 858.007
|
|
},
|
|
{
|
|
"epoch": 2.199041314768318,
|
|
"grad_norm": 1.8803805112838745,
|
|
"learning_rate": 8.328617282293591e-06,
|
|
"loss": 0.5508,
|
|
"num_input_tokens_seen": 6835744,
|
|
"step": 1205,
|
|
"train_runtime": 7967.5177,
|
|
"train_tokens_per_second": 857.952
|
|
},
|
|
{
|
|
"epoch": 2.2081716503081488,
|
|
"grad_norm": 1.420291781425476,
|
|
"learning_rate": 8.151379550537894e-06,
|
|
"loss": 0.5538,
|
|
"num_input_tokens_seen": 6864560,
|
|
"step": 1210,
|
|
"train_runtime": 8000.595,
|
|
"train_tokens_per_second": 858.006
|
|
},
|
|
{
|
|
"epoch": 2.21730198584798,
|
|
"grad_norm": 1.4852449893951416,
|
|
"learning_rate": 7.975679963401772e-06,
|
|
"loss": 0.4806,
|
|
"num_input_tokens_seen": 6893360,
|
|
"step": 1215,
|
|
"train_runtime": 8033.8187,
|
|
"train_tokens_per_second": 858.043
|
|
},
|
|
{
|
|
"epoch": 2.226432321387811,
|
|
"grad_norm": 1.8254742622375488,
|
|
"learning_rate": 7.801534560855703e-06,
|
|
"loss": 0.4594,
|
|
"num_input_tokens_seen": 6922336,
|
|
"step": 1220,
|
|
"train_runtime": 8067.0217,
|
|
"train_tokens_per_second": 858.103
|
|
},
|
|
{
|
|
"epoch": 2.235562656927642,
|
|
"grad_norm": 1.6726877689361572,
|
|
"learning_rate": 7.628959240985514e-06,
|
|
"loss": 0.4625,
|
|
"num_input_tokens_seen": 6952464,
|
|
"step": 1225,
|
|
"train_runtime": 8100.7878,
|
|
"train_tokens_per_second": 858.245
|
|
},
|
|
{
|
|
"epoch": 2.2446929924674732,
|
|
"grad_norm": 1.6740381717681885,
|
|
"learning_rate": 7.457969758541009e-06,
|
|
"loss": 0.5248,
|
|
"num_input_tokens_seen": 6978480,
|
|
"step": 1230,
|
|
"train_runtime": 8132.8942,
|
|
"train_tokens_per_second": 858.056
|
|
},
|
|
{
|
|
"epoch": 2.253823328007304,
|
|
"grad_norm": 1.6061497926712036,
|
|
"learning_rate": 7.288581723497689e-06,
|
|
"loss": 0.5796,
|
|
"num_input_tokens_seen": 7006576,
|
|
"step": 1235,
|
|
"train_runtime": 8165.7446,
|
|
"train_tokens_per_second": 858.045
|
|
},
|
|
{
|
|
"epoch": 2.2629536635471355,
|
|
"grad_norm": 1.6302696466445923,
|
|
"learning_rate": 7.12081059963168e-06,
|
|
"loss": 0.4509,
|
|
"num_input_tokens_seen": 7034848,
|
|
"step": 1240,
|
|
"train_runtime": 8198.7143,
|
|
"train_tokens_per_second": 858.043
|
|
},
|
|
{
|
|
"epoch": 2.2720839990869663,
|
|
"grad_norm": 2.3190863132476807,
|
|
"learning_rate": 6.954671703108034e-06,
|
|
"loss": 0.4935,
|
|
"num_input_tokens_seen": 7064656,
|
|
"step": 1245,
|
|
"train_runtime": 8232.3363,
|
|
"train_tokens_per_second": 858.159
|
|
},
|
|
{
|
|
"epoch": 2.2812143346267977,
|
|
"grad_norm": 1.5536160469055176,
|
|
"learning_rate": 6.790180201082439e-06,
|
|
"loss": 0.5073,
|
|
"num_input_tokens_seen": 7093536,
|
|
"step": 1250,
|
|
"train_runtime": 8265.6241,
|
|
"train_tokens_per_second": 858.197
|
|
},
|
|
{
|
|
"epoch": 2.2903446701666286,
|
|
"grad_norm": 1.4936327934265137,
|
|
"learning_rate": 6.627351110316635e-06,
|
|
"loss": 0.4892,
|
|
"num_input_tokens_seen": 7122352,
|
|
"step": 1255,
|
|
"train_runtime": 8299.0146,
|
|
"train_tokens_per_second": 858.217
|
|
},
|
|
{
|
|
"epoch": 2.2994750057064595,
|
|
"grad_norm": 1.524456262588501,
|
|
"learning_rate": 6.466199295807471e-06,
|
|
"loss": 0.5268,
|
|
"num_input_tokens_seen": 7149840,
|
|
"step": 1260,
|
|
"train_runtime": 8331.6714,
|
|
"train_tokens_per_second": 858.152
|
|
},
|
|
{
|
|
"epoch": 2.308605341246291,
|
|
"grad_norm": 1.4873135089874268,
|
|
"learning_rate": 6.306739469429859e-06,
|
|
"loss": 0.5226,
|
|
"num_input_tokens_seen": 7175312,
|
|
"step": 1265,
|
|
"train_runtime": 8363.3798,
|
|
"train_tokens_per_second": 857.944
|
|
},
|
|
{
|
|
"epoch": 2.317735676786122,
|
|
"grad_norm": 1.4220759868621826,
|
|
"learning_rate": 6.1489861885936805e-06,
|
|
"loss": 0.4098,
|
|
"num_input_tokens_seen": 7205408,
|
|
"step": 1270,
|
|
"train_runtime": 8397.1884,
|
|
"train_tokens_per_second": 858.074
|
|
},
|
|
{
|
|
"epoch": 2.326866012325953,
|
|
"grad_norm": 1.7989997863769531,
|
|
"learning_rate": 5.992953854914838e-06,
|
|
"loss": 0.5064,
|
|
"num_input_tokens_seen": 7230896,
|
|
"step": 1275,
|
|
"train_runtime": 8428.9734,
|
|
"train_tokens_per_second": 857.862
|
|
},
|
|
{
|
|
"epoch": 2.335996347865784,
|
|
"grad_norm": 1.6997673511505127,
|
|
"learning_rate": 5.838656712900487e-06,
|
|
"loss": 0.486,
|
|
"num_input_tokens_seen": 7258640,
|
|
"step": 1280,
|
|
"train_runtime": 8461.701,
|
|
"train_tokens_per_second": 857.823
|
|
},
|
|
{
|
|
"epoch": 2.3451266834056153,
|
|
"grad_norm": 1.655226469039917,
|
|
"learning_rate": 5.686108848648624e-06,
|
|
"loss": 0.5659,
|
|
"num_input_tokens_seen": 7287552,
|
|
"step": 1285,
|
|
"train_runtime": 8494.9769,
|
|
"train_tokens_per_second": 857.866
|
|
},
|
|
{
|
|
"epoch": 2.354257018945446,
|
|
"grad_norm": 1.5733911991119385,
|
|
"learning_rate": 5.535324188562157e-06,
|
|
"loss": 0.5572,
|
|
"num_input_tokens_seen": 7315152,
|
|
"step": 1290,
|
|
"train_runtime": 8527.6021,
|
|
"train_tokens_per_second": 857.821
|
|
},
|
|
{
|
|
"epoch": 2.3633873544852775,
|
|
"grad_norm": 1.6711825132369995,
|
|
"learning_rate": 5.386316498077492e-06,
|
|
"loss": 0.5891,
|
|
"num_input_tokens_seen": 7341792,
|
|
"step": 1295,
|
|
"train_runtime": 8559.7095,
|
|
"train_tokens_per_second": 857.715
|
|
},
|
|
{
|
|
"epoch": 2.3725176900251084,
|
|
"grad_norm": 1.575325846672058,
|
|
"learning_rate": 5.239099380407916e-06,
|
|
"loss": 0.5121,
|
|
"num_input_tokens_seen": 7369360,
|
|
"step": 1300,
|
|
"train_runtime": 8592.4006,
|
|
"train_tokens_per_second": 857.66
|
|
},
|
|
{
|
|
"epoch": 2.3816480255649397,
|
|
"grad_norm": 1.923042893409729,
|
|
"learning_rate": 5.09368627530169e-06,
|
|
"loss": 0.4585,
|
|
"num_input_tokens_seen": 7399936,
|
|
"step": 1305,
|
|
"train_runtime": 8627.583,
|
|
"train_tokens_per_second": 857.707
|
|
},
|
|
{
|
|
"epoch": 2.3907783611047706,
|
|
"grad_norm": 1.294421911239624,
|
|
"learning_rate": 4.950090457815129e-06,
|
|
"loss": 0.5115,
|
|
"num_input_tokens_seen": 7426080,
|
|
"step": 1310,
|
|
"train_runtime": 8659.572,
|
|
"train_tokens_per_second": 857.557
|
|
},
|
|
{
|
|
"epoch": 2.3999086966446015,
|
|
"grad_norm": 1.5188215970993042,
|
|
"learning_rate": 4.808325037100691e-06,
|
|
"loss": 0.3663,
|
|
"num_input_tokens_seen": 7454432,
|
|
"step": 1315,
|
|
"train_runtime": 8701.6759,
|
|
"train_tokens_per_second": 856.666
|
|
},
|
|
{
|
|
"epoch": 2.409039032184433,
|
|
"grad_norm": 1.4130005836486816,
|
|
"learning_rate": 4.6684029552101886e-06,
|
|
"loss": 0.4918,
|
|
"num_input_tokens_seen": 7484848,
|
|
"step": 1320,
|
|
"train_runtime": 8735.6362,
|
|
"train_tokens_per_second": 856.818
|
|
},
|
|
{
|
|
"epoch": 2.4181693677242637,
|
|
"grad_norm": 1.4493566751480103,
|
|
"learning_rate": 4.530336985913333e-06,
|
|
"loss": 0.4168,
|
|
"num_input_tokens_seen": 7514592,
|
|
"step": 1325,
|
|
"train_runtime": 8769.282,
|
|
"train_tokens_per_second": 856.922
|
|
},
|
|
{
|
|
"epoch": 2.427299703264095,
|
|
"grad_norm": 1.8940752744674683,
|
|
"learning_rate": 4.394139733531555e-06,
|
|
"loss": 0.4658,
|
|
"num_input_tokens_seen": 7545680,
|
|
"step": 1330,
|
|
"train_runtime": 8803.6245,
|
|
"train_tokens_per_second": 857.111
|
|
},
|
|
{
|
|
"epoch": 2.436430038803926,
|
|
"grad_norm": 1.8865268230438232,
|
|
"learning_rate": 4.259823631787346e-06,
|
|
"loss": 0.4081,
|
|
"num_input_tokens_seen": 7575472,
|
|
"step": 1335,
|
|
"train_runtime": 8837.4345,
|
|
"train_tokens_per_second": 857.203
|
|
},
|
|
{
|
|
"epoch": 2.4455603743437573,
|
|
"grad_norm": 1.537660002708435,
|
|
"learning_rate": 4.127400942669141e-06,
|
|
"loss": 0.4739,
|
|
"num_input_tokens_seen": 7604016,
|
|
"step": 1340,
|
|
"train_runtime": 8870.4991,
|
|
"train_tokens_per_second": 857.225
|
|
},
|
|
{
|
|
"epoch": 2.454690709883588,
|
|
"grad_norm": 1.0611555576324463,
|
|
"learning_rate": 3.996883755311917e-06,
|
|
"loss": 0.3149,
|
|
"num_input_tokens_seen": 7636112,
|
|
"step": 1345,
|
|
"train_runtime": 8905.1047,
|
|
"train_tokens_per_second": 857.498
|
|
},
|
|
{
|
|
"epoch": 2.463821045423419,
|
|
"grad_norm": 2.0281214714050293,
|
|
"learning_rate": 3.868283984893542e-06,
|
|
"loss": 0.565,
|
|
"num_input_tokens_seen": 7665152,
|
|
"step": 1350,
|
|
"train_runtime": 8938.4023,
|
|
"train_tokens_per_second": 857.553
|
|
},
|
|
{
|
|
"epoch": 2.4729513809632504,
|
|
"grad_norm": 1.5192010402679443,
|
|
"learning_rate": 3.741613371547023e-06,
|
|
"loss": 0.4656,
|
|
"num_input_tokens_seen": 7692112,
|
|
"step": 1355,
|
|
"train_runtime": 8970.7428,
|
|
"train_tokens_per_second": 857.467
|
|
},
|
|
{
|
|
"epoch": 2.4820817165030817,
|
|
"grad_norm": 1.6683508157730103,
|
|
"learning_rate": 3.6168834792887103e-06,
|
|
"loss": 0.4552,
|
|
"num_input_tokens_seen": 7720064,
|
|
"step": 1360,
|
|
"train_runtime": 9003.5935,
|
|
"train_tokens_per_second": 857.443
|
|
},
|
|
{
|
|
"epoch": 2.4912120520429126,
|
|
"grad_norm": 1.5640547275543213,
|
|
"learning_rate": 3.494105694962596e-06,
|
|
"loss": 0.4571,
|
|
"num_input_tokens_seen": 7751040,
|
|
"step": 1365,
|
|
"train_runtime": 9037.7684,
|
|
"train_tokens_per_second": 857.628
|
|
},
|
|
{
|
|
"epoch": 2.5003423875827435,
|
|
"grad_norm": 2.0412251949310303,
|
|
"learning_rate": 3.373291227200806e-06,
|
|
"loss": 0.5344,
|
|
"num_input_tokens_seen": 7776944,
|
|
"step": 1370,
|
|
"train_runtime": 9069.7333,
|
|
"train_tokens_per_second": 857.461
|
|
},
|
|
{
|
|
"epoch": 2.509472723122575,
|
|
"grad_norm": 1.6897809505462646,
|
|
"learning_rate": 3.2544511054003246e-06,
|
|
"loss": 0.501,
|
|
"num_input_tokens_seen": 7804880,
|
|
"step": 1375,
|
|
"train_runtime": 9102.5099,
|
|
"train_tokens_per_second": 857.443
|
|
},
|
|
{
|
|
"epoch": 2.5186030586624057,
|
|
"grad_norm": 1.7537122964859009,
|
|
"learning_rate": 3.1375961787160983e-06,
|
|
"loss": 0.5723,
|
|
"num_input_tokens_seen": 7834144,
|
|
"step": 1380,
|
|
"train_runtime": 9135.9522,
|
|
"train_tokens_per_second": 857.507
|
|
},
|
|
{
|
|
"epoch": 2.527733394202237,
|
|
"grad_norm": 1.6396698951721191,
|
|
"learning_rate": 3.0227371150706035e-06,
|
|
"loss": 0.5347,
|
|
"num_input_tokens_seen": 7862112,
|
|
"step": 1385,
|
|
"train_runtime": 9168.7182,
|
|
"train_tokens_per_second": 857.493
|
|
},
|
|
{
|
|
"epoch": 2.536863729742068,
|
|
"grad_norm": 1.4223724603652954,
|
|
"learning_rate": 2.9098844001799407e-06,
|
|
"loss": 0.4727,
|
|
"num_input_tokens_seen": 7889648,
|
|
"step": 1390,
|
|
"train_runtime": 9201.3802,
|
|
"train_tokens_per_second": 857.442
|
|
},
|
|
{
|
|
"epoch": 2.5459940652818993,
|
|
"grad_norm": 2.2084455490112305,
|
|
"learning_rate": 2.7990483365965825e-06,
|
|
"loss": 0.6187,
|
|
"num_input_tokens_seen": 7917840,
|
|
"step": 1395,
|
|
"train_runtime": 9234.3184,
|
|
"train_tokens_per_second": 857.436
|
|
},
|
|
{
|
|
"epoch": 2.55512440082173,
|
|
"grad_norm": 1.9658094644546509,
|
|
"learning_rate": 2.6902390427688273e-06,
|
|
"loss": 0.5945,
|
|
"num_input_tokens_seen": 7945968,
|
|
"step": 1400,
|
|
"train_runtime": 9267.0379,
|
|
"train_tokens_per_second": 857.444
|
|
},
|
|
{
|
|
"epoch": 2.564254736361561,
|
|
"grad_norm": 1.4048709869384766,
|
|
"learning_rate": 2.5834664521170504e-06,
|
|
"loss": 0.5123,
|
|
"num_input_tokens_seen": 7976608,
|
|
"step": 1405,
|
|
"train_runtime": 9302.2298,
|
|
"train_tokens_per_second": 857.494
|
|
},
|
|
{
|
|
"epoch": 2.5733850719013924,
|
|
"grad_norm": 1.8931680917739868,
|
|
"learning_rate": 2.4787403121268955e-06,
|
|
"loss": 0.4564,
|
|
"num_input_tokens_seen": 8005312,
|
|
"step": 1410,
|
|
"train_runtime": 9335.3807,
|
|
"train_tokens_per_second": 857.524
|
|
},
|
|
{
|
|
"epoch": 2.5825154074412233,
|
|
"grad_norm": 1.8574892282485962,
|
|
"learning_rate": 2.3760701834593806e-06,
|
|
"loss": 0.5329,
|
|
"num_input_tokens_seen": 8032320,
|
|
"step": 1415,
|
|
"train_runtime": 9367.8306,
|
|
"train_tokens_per_second": 857.437
|
|
},
|
|
{
|
|
"epoch": 2.5916457429810547,
|
|
"grad_norm": 1.5250113010406494,
|
|
"learning_rate": 2.2754654390780924e-06,
|
|
"loss": 0.5803,
|
|
"num_input_tokens_seen": 8059600,
|
|
"step": 1420,
|
|
"train_runtime": 9400.4807,
|
|
"train_tokens_per_second": 857.36
|
|
},
|
|
{
|
|
"epoch": 2.6007760785208855,
|
|
"grad_norm": 1.251405954360962,
|
|
"learning_rate": 2.1769352633935175e-06,
|
|
"loss": 0.4759,
|
|
"num_input_tokens_seen": 8090544,
|
|
"step": 1425,
|
|
"train_runtime": 9434.7027,
|
|
"train_tokens_per_second": 857.53
|
|
},
|
|
{
|
|
"epoch": 2.609906414060717,
|
|
"grad_norm": 2.3054699897766113,
|
|
"learning_rate": 2.0804886514245726e-06,
|
|
"loss": 0.4964,
|
|
"num_input_tokens_seen": 8117472,
|
|
"step": 1430,
|
|
"train_runtime": 9467.0753,
|
|
"train_tokens_per_second": 857.442
|
|
},
|
|
{
|
|
"epoch": 2.6190367496005478,
|
|
"grad_norm": 1.6009160280227661,
|
|
"learning_rate": 1.986134407977416e-06,
|
|
"loss": 0.4652,
|
|
"num_input_tokens_seen": 8145360,
|
|
"step": 1435,
|
|
"train_runtime": 9499.7537,
|
|
"train_tokens_per_second": 857.429
|
|
},
|
|
{
|
|
"epoch": 2.6281670851403787,
|
|
"grad_norm": 1.5399287939071655,
|
|
"learning_rate": 1.8938811468416695e-06,
|
|
"loss": 0.5859,
|
|
"num_input_tokens_seen": 8171552,
|
|
"step": 1440,
|
|
"train_runtime": 9531.6877,
|
|
"train_tokens_per_second": 857.304
|
|
},
|
|
{
|
|
"epoch": 2.63729742068021,
|
|
"grad_norm": 1.5960819721221924,
|
|
"learning_rate": 1.8037372900040289e-06,
|
|
"loss": 0.6222,
|
|
"num_input_tokens_seen": 8199280,
|
|
"step": 1445,
|
|
"train_runtime": 9564.4618,
|
|
"train_tokens_per_second": 857.265
|
|
},
|
|
{
|
|
"epoch": 2.6464277562200413,
|
|
"grad_norm": 1.9178729057312012,
|
|
"learning_rate": 1.7157110668794108e-06,
|
|
"loss": 0.3722,
|
|
"num_input_tokens_seen": 8226656,
|
|
"step": 1450,
|
|
"train_runtime": 9596.9118,
|
|
"train_tokens_per_second": 857.219
|
|
},
|
|
{
|
|
"epoch": 2.6555580917598722,
|
|
"grad_norm": 1.9778716564178467,
|
|
"learning_rate": 1.6298105135596569e-06,
|
|
"loss": 0.5299,
|
|
"num_input_tokens_seen": 8255232,
|
|
"step": 1455,
|
|
"train_runtime": 9630.1532,
|
|
"train_tokens_per_second": 857.227
|
|
},
|
|
{
|
|
"epoch": 2.664688427299703,
|
|
"grad_norm": 1.8453866243362427,
|
|
"learning_rate": 1.5460434720799278e-06,
|
|
"loss": 0.447,
|
|
"num_input_tokens_seen": 8281744,
|
|
"step": 1460,
|
|
"train_runtime": 9662.2517,
|
|
"train_tokens_per_second": 857.124
|
|
},
|
|
{
|
|
"epoch": 2.6738187628395345,
|
|
"grad_norm": 1.5484800338745117,
|
|
"learning_rate": 1.464417589702774e-06,
|
|
"loss": 0.3965,
|
|
"num_input_tokens_seen": 8310384,
|
|
"step": 1465,
|
|
"train_runtime": 9695.4301,
|
|
"train_tokens_per_second": 857.144
|
|
},
|
|
{
|
|
"epoch": 2.6829490983793653,
|
|
"grad_norm": 1.297414779663086,
|
|
"learning_rate": 1.3849403182199988e-06,
|
|
"loss": 0.4579,
|
|
"num_input_tokens_seen": 8340384,
|
|
"step": 1470,
|
|
"train_runtime": 9729.2243,
|
|
"train_tokens_per_second": 857.251
|
|
},
|
|
{
|
|
"epoch": 2.6920794339191967,
|
|
"grad_norm": 1.7842596769332886,
|
|
"learning_rate": 1.3076189132723764e-06,
|
|
"loss": 0.5361,
|
|
"num_input_tokens_seen": 8368224,
|
|
"step": 1475,
|
|
"train_runtime": 9761.9824,
|
|
"train_tokens_per_second": 857.226
|
|
},
|
|
{
|
|
"epoch": 2.7012097694590276,
|
|
"grad_norm": 1.3124113082885742,
|
|
"learning_rate": 1.2324604336872658e-06,
|
|
"loss": 0.4439,
|
|
"num_input_tokens_seen": 8398976,
|
|
"step": 1480,
|
|
"train_runtime": 9796.1279,
|
|
"train_tokens_per_second": 857.377
|
|
},
|
|
{
|
|
"epoch": 2.710340104998859,
|
|
"grad_norm": 1.8986421823501587,
|
|
"learning_rate": 1.159471740834195e-06,
|
|
"loss": 0.3843,
|
|
"num_input_tokens_seen": 8426000,
|
|
"step": 1485,
|
|
"train_runtime": 9828.5258,
|
|
"train_tokens_per_second": 857.3
|
|
},
|
|
{
|
|
"epoch": 2.71947044053869,
|
|
"grad_norm": 1.2986937761306763,
|
|
"learning_rate": 1.0886594979984816e-06,
|
|
"loss": 0.4191,
|
|
"num_input_tokens_seen": 8452800,
|
|
"step": 1490,
|
|
"train_runtime": 9860.8783,
|
|
"train_tokens_per_second": 857.206
|
|
},
|
|
{
|
|
"epoch": 2.7286007760785207,
|
|
"grad_norm": 1.4023627042770386,
|
|
"learning_rate": 1.0200301697729204e-06,
|
|
"loss": 0.4898,
|
|
"num_input_tokens_seen": 8478592,
|
|
"step": 1495,
|
|
"train_runtime": 9892.7604,
|
|
"train_tokens_per_second": 857.05
|
|
},
|
|
{
|
|
"epoch": 2.737731111618352,
|
|
"grad_norm": 1.7444908618927002,
|
|
"learning_rate": 9.535900214676097e-07,
|
|
"loss": 0.4288,
|
|
"num_input_tokens_seen": 8506240,
|
|
"step": 1500,
|
|
"train_runtime": 9925.5818,
|
|
"train_tokens_per_second": 857.002
|
|
},
|
|
{
|
|
"epoch": 2.746861447158183,
|
|
"grad_norm": 1.5377986431121826,
|
|
"learning_rate": 8.893451185379958e-07,
|
|
"loss": 0.4114,
|
|
"num_input_tokens_seen": 8533840,
|
|
"step": 1505,
|
|
"train_runtime": 9959.5353,
|
|
"train_tokens_per_second": 856.851
|
|
},
|
|
{
|
|
"epoch": 2.7559917826980143,
|
|
"grad_norm": 1.6170401573181152,
|
|
"learning_rate": 8.273013260311379e-07,
|
|
"loss": 0.4987,
|
|
"num_input_tokens_seen": 8559296,
|
|
"step": 1510,
|
|
"train_runtime": 9991.2783,
|
|
"train_tokens_per_second": 856.677
|
|
},
|
|
{
|
|
"epoch": 2.765122118237845,
|
|
"grad_norm": 2.0063154697418213,
|
|
"learning_rate": 7.674643080502724e-07,
|
|
"loss": 0.4648,
|
|
"num_input_tokens_seen": 8587664,
|
|
"step": 1515,
|
|
"train_runtime": 10761.2574,
|
|
"train_tokens_per_second": 798.017
|
|
},
|
|
{
|
|
"epoch": 2.7742524537776765,
|
|
"grad_norm": 1.877916693687439,
|
|
"learning_rate": 7.098395272377295e-07,
|
|
"loss": 0.5213,
|
|
"num_input_tokens_seen": 8614480,
|
|
"step": 1520,
|
|
"train_runtime": 10793.6481,
|
|
"train_tokens_per_second": 798.106
|
|
},
|
|
{
|
|
"epoch": 2.7833827893175074,
|
|
"grad_norm": 1.7010425329208374,
|
|
"learning_rate": 6.544322442762318e-07,
|
|
"loss": 0.499,
|
|
"num_input_tokens_seen": 8642960,
|
|
"step": 1525,
|
|
"train_runtime": 10826.7994,
|
|
"train_tokens_per_second": 798.293
|
|
},
|
|
{
|
|
"epoch": 2.7925131248573383,
|
|
"grad_norm": 1.5449343919754028,
|
|
"learning_rate": 6.012475174086485e-07,
|
|
"loss": 0.4285,
|
|
"num_input_tokens_seen": 8671248,
|
|
"step": 1530,
|
|
"train_runtime": 10859.8866,
|
|
"train_tokens_per_second": 798.466
|
|
},
|
|
{
|
|
"epoch": 2.8016434603971696,
|
|
"grad_norm": 1.7787251472473145,
|
|
"learning_rate": 5.502902019762002e-07,
|
|
"loss": 0.4615,
|
|
"num_input_tokens_seen": 8698912,
|
|
"step": 1535,
|
|
"train_runtime": 10892.5607,
|
|
"train_tokens_per_second": 798.61
|
|
},
|
|
{
|
|
"epoch": 2.810773795937001,
|
|
"grad_norm": 1.502289891242981,
|
|
"learning_rate": 5.015649499752279e-07,
|
|
"loss": 0.4648,
|
|
"num_input_tokens_seen": 8726896,
|
|
"step": 1540,
|
|
"train_runtime": 10925.4558,
|
|
"train_tokens_per_second": 798.767
|
|
},
|
|
{
|
|
"epoch": 2.819904131476832,
|
|
"grad_norm": 1.522641658782959,
|
|
"learning_rate": 4.5507620963247954e-07,
|
|
"loss": 0.4858,
|
|
"num_input_tokens_seen": 8751920,
|
|
"step": 1545,
|
|
"train_runtime": 10956.9252,
|
|
"train_tokens_per_second": 798.757
|
|
},
|
|
{
|
|
"epoch": 2.8290344670166627,
|
|
"grad_norm": 2.1871094703674316,
|
|
"learning_rate": 4.1082822499903253e-07,
|
|
"loss": 0.4944,
|
|
"num_input_tokens_seen": 8780080,
|
|
"step": 1550,
|
|
"train_runtime": 10989.8787,
|
|
"train_tokens_per_second": 798.924
|
|
},
|
|
{
|
|
"epoch": 2.838164802556494,
|
|
"grad_norm": 1.5429576635360718,
|
|
"learning_rate": 3.6882503556285307e-07,
|
|
"loss": 0.4598,
|
|
"num_input_tokens_seen": 8804880,
|
|
"step": 1555,
|
|
"train_runtime": 11021.2763,
|
|
"train_tokens_per_second": 798.898
|
|
},
|
|
{
|
|
"epoch": 2.847295138096325,
|
|
"grad_norm": 1.883806586265564,
|
|
"learning_rate": 3.290704758800139e-07,
|
|
"loss": 0.4981,
|
|
"num_input_tokens_seen": 8834736,
|
|
"step": 1560,
|
|
"train_runtime": 11055.0559,
|
|
"train_tokens_per_second": 799.158
|
|
},
|
|
{
|
|
"epoch": 2.8564254736361563,
|
|
"grad_norm": 1.7535673379898071,
|
|
"learning_rate": 2.915681752246241e-07,
|
|
"loss": 0.5183,
|
|
"num_input_tokens_seen": 8862544,
|
|
"step": 1565,
|
|
"train_runtime": 11087.6895,
|
|
"train_tokens_per_second": 799.314
|
|
},
|
|
{
|
|
"epoch": 2.865555809175987,
|
|
"grad_norm": 2.0906741619110107,
|
|
"learning_rate": 2.563215572575273e-07,
|
|
"loss": 0.4789,
|
|
"num_input_tokens_seen": 8892720,
|
|
"step": 1570,
|
|
"train_runtime": 11121.4717,
|
|
"train_tokens_per_second": 799.599
|
|
},
|
|
{
|
|
"epoch": 2.8746861447158185,
|
|
"grad_norm": 1.9282186031341553,
|
|
"learning_rate": 2.2333383971372413e-07,
|
|
"loss": 0.4666,
|
|
"num_input_tokens_seen": 8918880,
|
|
"step": 1575,
|
|
"train_runtime": 11153.5256,
|
|
"train_tokens_per_second": 799.647
|
|
},
|
|
{
|
|
"epoch": 2.8838164802556494,
|
|
"grad_norm": 1.4631140232086182,
|
|
"learning_rate": 1.9260803410863226e-07,
|
|
"loss": 0.4199,
|
|
"num_input_tokens_seen": 8952352,
|
|
"step": 1580,
|
|
"train_runtime": 11188.7542,
|
|
"train_tokens_per_second": 800.121
|
|
},
|
|
{
|
|
"epoch": 2.8929468157954803,
|
|
"grad_norm": 1.2672832012176514,
|
|
"learning_rate": 1.641469454631561e-07,
|
|
"loss": 0.4318,
|
|
"num_input_tokens_seen": 8981984,
|
|
"step": 1585,
|
|
"train_runtime": 11222.3784,
|
|
"train_tokens_per_second": 800.364
|
|
},
|
|
{
|
|
"epoch": 2.9020771513353116,
|
|
"grad_norm": 1.3364146947860718,
|
|
"learning_rate": 1.3795317204761128e-07,
|
|
"loss": 0.36,
|
|
"num_input_tokens_seen": 9012864,
|
|
"step": 1590,
|
|
"train_runtime": 11256.7019,
|
|
"train_tokens_per_second": 800.666
|
|
},
|
|
{
|
|
"epoch": 2.9112074868751425,
|
|
"grad_norm": 1.5411438941955566,
|
|
"learning_rate": 1.140291051445197e-07,
|
|
"loss": 0.4392,
|
|
"num_input_tokens_seen": 9040848,
|
|
"step": 1595,
|
|
"train_runtime": 11289.6253,
|
|
"train_tokens_per_second": 800.81
|
|
},
|
|
{
|
|
"epoch": 2.920337822414974,
|
|
"grad_norm": 1.6634502410888672,
|
|
"learning_rate": 9.237692883031502e-08,
|
|
"loss": 0.4489,
|
|
"num_input_tokens_seen": 9071104,
|
|
"step": 1600,
|
|
"train_runtime": 11323.3685,
|
|
"train_tokens_per_second": 801.096
|
|
},
|
|
{
|
|
"epoch": 2.9294681579548048,
|
|
"grad_norm": 1.9743751287460327,
|
|
"learning_rate": 7.29986197759408e-08,
|
|
"loss": 0.5492,
|
|
"num_input_tokens_seen": 9101904,
|
|
"step": 1605,
|
|
"train_runtime": 11358.5692,
|
|
"train_tokens_per_second": 801.325
|
|
},
|
|
{
|
|
"epoch": 2.938598493494636,
|
|
"grad_norm": 1.0921943187713623,
|
|
"learning_rate": 5.589594706640055e-08,
|
|
"loss": 0.503,
|
|
"num_input_tokens_seen": 9131728,
|
|
"step": 1610,
|
|
"train_runtime": 11392.3267,
|
|
"train_tokens_per_second": 801.568
|
|
},
|
|
{
|
|
"epoch": 2.947728829034467,
|
|
"grad_norm": 1.501896858215332,
|
|
"learning_rate": 4.1070472039259065e-08,
|
|
"loss": 0.4689,
|
|
"num_input_tokens_seen": 9162144,
|
|
"step": 1615,
|
|
"train_runtime": 11426.2624,
|
|
"train_tokens_per_second": 801.85
|
|
},
|
|
{
|
|
"epoch": 2.956859164574298,
|
|
"grad_norm": 1.5929884910583496,
|
|
"learning_rate": 2.8523548142103673e-08,
|
|
"loss": 0.542,
|
|
"num_input_tokens_seen": 9189808,
|
|
"step": 1620,
|
|
"train_runtime": 11458.9394,
|
|
"train_tokens_per_second": 801.977
|
|
},
|
|
{
|
|
"epoch": 2.965989500114129,
|
|
"grad_norm": 1.3482941389083862,
|
|
"learning_rate": 1.825632080897366e-08,
|
|
"loss": 0.3969,
|
|
"num_input_tokens_seen": 9220032,
|
|
"step": 1625,
|
|
"train_runtime": 11492.8101,
|
|
"train_tokens_per_second": 802.243
|
|
},
|
|
{
|
|
"epoch": 2.9751198356539605,
|
|
"grad_norm": 1.901435136795044,
|
|
"learning_rate": 1.026972735581333e-08,
|
|
"loss": 0.496,
|
|
"num_input_tokens_seen": 9248592,
|
|
"step": 1630,
|
|
"train_runtime": 11525.8653,
|
|
"train_tokens_per_second": 802.421
|
|
},
|
|
{
|
|
"epoch": 2.9842501711937914,
|
|
"grad_norm": 1.747241735458374,
|
|
"learning_rate": 4.564496894882142e-09,
|
|
"loss": 0.5585,
|
|
"num_input_tokens_seen": 9276416,
|
|
"step": 1635,
|
|
"train_runtime": 11558.7218,
|
|
"train_tokens_per_second": 802.547
|
|
},
|
|
{
|
|
"epoch": 2.9933805067336223,
|
|
"grad_norm": 1.4872362613677979,
|
|
"learning_rate": 1.1411502681996088e-09,
|
|
"loss": 0.4553,
|
|
"num_input_tokens_seen": 9306352,
|
|
"step": 1640,
|
|
"train_runtime": 11592.3707,
|
|
"train_tokens_per_second": 802.8
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 1644,
|
|
"num_input_tokens_seen": 9328224,
|
|
"num_train_epochs": 3,
|
|
"save_steps": 100,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": true
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 8.278651518536909e+16,
|
|
"train_batch_size": 2,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|