andrewbai's picture
Model save
5f5dc6f verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 732,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.001366120218579235,
"grad_norm": 8.843155743885935,
"learning_rate": 2.702702702702703e-07,
"loss": 1.199,
"step": 1
},
{
"epoch": 0.006830601092896175,
"grad_norm": 8.540631742450893,
"learning_rate": 1.3513513513513515e-06,
"loss": 1.2044,
"step": 5
},
{
"epoch": 0.01366120218579235,
"grad_norm": 8.767200579620665,
"learning_rate": 2.702702702702703e-06,
"loss": 1.186,
"step": 10
},
{
"epoch": 0.020491803278688523,
"grad_norm": 2.6098644670988818,
"learning_rate": 4.0540540540540545e-06,
"loss": 1.0193,
"step": 15
},
{
"epoch": 0.0273224043715847,
"grad_norm": 0.9214100024259756,
"learning_rate": 5.405405405405406e-06,
"loss": 0.9217,
"step": 20
},
{
"epoch": 0.03415300546448088,
"grad_norm": 0.7472855963085931,
"learning_rate": 6.7567567567567575e-06,
"loss": 0.859,
"step": 25
},
{
"epoch": 0.040983606557377046,
"grad_norm": 0.7027313339104094,
"learning_rate": 8.108108108108109e-06,
"loss": 0.8567,
"step": 30
},
{
"epoch": 0.04781420765027322,
"grad_norm": 0.606492697546335,
"learning_rate": 9.45945945945946e-06,
"loss": 0.8564,
"step": 35
},
{
"epoch": 0.0546448087431694,
"grad_norm": 0.5940228911261327,
"learning_rate": 1.0810810810810812e-05,
"loss": 0.8281,
"step": 40
},
{
"epoch": 0.06147540983606557,
"grad_norm": 0.5848291669538546,
"learning_rate": 1.2162162162162164e-05,
"loss": 0.8319,
"step": 45
},
{
"epoch": 0.06830601092896176,
"grad_norm": 0.5535457560314438,
"learning_rate": 1.3513513513513515e-05,
"loss": 0.8194,
"step": 50
},
{
"epoch": 0.07513661202185792,
"grad_norm": 0.5893686332325634,
"learning_rate": 1.4864864864864865e-05,
"loss": 0.828,
"step": 55
},
{
"epoch": 0.08196721311475409,
"grad_norm": 0.5719534274373087,
"learning_rate": 1.6216216216216218e-05,
"loss": 0.8255,
"step": 60
},
{
"epoch": 0.08879781420765027,
"grad_norm": 0.5782518990484358,
"learning_rate": 1.756756756756757e-05,
"loss": 0.8091,
"step": 65
},
{
"epoch": 0.09562841530054644,
"grad_norm": 0.6001941236834596,
"learning_rate": 1.891891891891892e-05,
"loss": 0.8509,
"step": 70
},
{
"epoch": 0.10245901639344263,
"grad_norm": 0.5756334358383789,
"learning_rate": 1.999988602302209e-05,
"loss": 0.7947,
"step": 75
},
{
"epoch": 0.1092896174863388,
"grad_norm": 0.5589039932124558,
"learning_rate": 1.9995897101594454e-05,
"loss": 0.81,
"step": 80
},
{
"epoch": 0.11612021857923498,
"grad_norm": 0.5938570135428684,
"learning_rate": 1.99862119291555e-05,
"loss": 0.8088,
"step": 85
},
{
"epoch": 0.12295081967213115,
"grad_norm": 0.5924615537351454,
"learning_rate": 1.997083602488702e-05,
"loss": 0.8071,
"step": 90
},
{
"epoch": 0.12978142076502733,
"grad_norm": 0.5988590272254397,
"learning_rate": 1.994977815088504e-05,
"loss": 0.8057,
"step": 95
},
{
"epoch": 0.1366120218579235,
"grad_norm": 0.5820148883591653,
"learning_rate": 1.9923050307166655e-05,
"loss": 0.8043,
"step": 100
},
{
"epoch": 0.14344262295081966,
"grad_norm": 0.6312826892627479,
"learning_rate": 1.989066772483171e-05,
"loss": 0.8125,
"step": 105
},
{
"epoch": 0.15027322404371585,
"grad_norm": 0.5457727775136069,
"learning_rate": 1.9852648857383224e-05,
"loss": 0.795,
"step": 110
},
{
"epoch": 0.15710382513661203,
"grad_norm": 0.5931361564309547,
"learning_rate": 1.9809015370211505e-05,
"loss": 0.8023,
"step": 115
},
{
"epoch": 0.16393442622950818,
"grad_norm": 0.5429570919204767,
"learning_rate": 1.9759792128247922e-05,
"loss": 0.818,
"step": 120
},
{
"epoch": 0.17076502732240437,
"grad_norm": 0.5941429790495816,
"learning_rate": 1.9705007181795416e-05,
"loss": 0.8076,
"step": 125
},
{
"epoch": 0.17759562841530055,
"grad_norm": 0.586524294465549,
"learning_rate": 1.964469175054377e-05,
"loss": 0.7948,
"step": 130
},
{
"epoch": 0.18442622950819673,
"grad_norm": 0.5701970901963691,
"learning_rate": 1.9578880205778793e-05,
"loss": 0.7901,
"step": 135
},
{
"epoch": 0.1912568306010929,
"grad_norm": 0.5531109526566766,
"learning_rate": 1.950761005079556e-05,
"loss": 0.768,
"step": 140
},
{
"epoch": 0.19808743169398907,
"grad_norm": 0.5905328760710993,
"learning_rate": 1.9430921899526786e-05,
"loss": 0.7892,
"step": 145
},
{
"epoch": 0.20491803278688525,
"grad_norm": 0.5887273338658354,
"learning_rate": 1.934885945339865e-05,
"loss": 0.7814,
"step": 150
},
{
"epoch": 0.21174863387978143,
"grad_norm": 0.6013798893637619,
"learning_rate": 1.9261469476427122e-05,
"loss": 0.7957,
"step": 155
},
{
"epoch": 0.2185792349726776,
"grad_norm": 0.5617177815620502,
"learning_rate": 1.916880176856909e-05,
"loss": 0.7591,
"step": 160
},
{
"epoch": 0.22540983606557377,
"grad_norm": 0.6140562235904167,
"learning_rate": 1.907090913734341e-05,
"loss": 0.7787,
"step": 165
},
{
"epoch": 0.23224043715846995,
"grad_norm": 0.586045608127345,
"learning_rate": 1.896784736773805e-05,
"loss": 0.768,
"step": 170
},
{
"epoch": 0.2390710382513661,
"grad_norm": 0.5524101190099344,
"learning_rate": 1.885967519042054e-05,
"loss": 0.7744,
"step": 175
},
{
"epoch": 0.2459016393442623,
"grad_norm": 0.5523610942140554,
"learning_rate": 1.8746454248269777e-05,
"loss": 0.7602,
"step": 180
},
{
"epoch": 0.2527322404371585,
"grad_norm": 0.546789444435313,
"learning_rate": 1.862824906124826e-05,
"loss": 0.784,
"step": 185
},
{
"epoch": 0.25956284153005466,
"grad_norm": 0.5348363807692132,
"learning_rate": 1.850512698963485e-05,
"loss": 0.7579,
"step": 190
},
{
"epoch": 0.26639344262295084,
"grad_norm": 0.5681852755270315,
"learning_rate": 1.8377158195638877e-05,
"loss": 0.7722,
"step": 195
},
{
"epoch": 0.273224043715847,
"grad_norm": 0.5731618955355812,
"learning_rate": 1.8244415603417603e-05,
"loss": 0.7939,
"step": 200
},
{
"epoch": 0.28005464480874315,
"grad_norm": 0.5778873895260302,
"learning_rate": 1.8106974857519737e-05,
"loss": 0.7762,
"step": 205
},
{
"epoch": 0.28688524590163933,
"grad_norm": 0.614463428308708,
"learning_rate": 1.7964914279778716e-05,
"loss": 0.7522,
"step": 210
},
{
"epoch": 0.2937158469945355,
"grad_norm": 0.5703542529393416,
"learning_rate": 1.78183148246803e-05,
"loss": 0.7641,
"step": 215
},
{
"epoch": 0.3005464480874317,
"grad_norm": 0.6153806412407196,
"learning_rate": 1.7667260033229953e-05,
"loss": 0.7798,
"step": 220
},
{
"epoch": 0.3073770491803279,
"grad_norm": 0.5851057407860113,
"learning_rate": 1.751183598534625e-05,
"loss": 0.7647,
"step": 225
},
{
"epoch": 0.31420765027322406,
"grad_norm": 0.6316856459688894,
"learning_rate": 1.7352131250807466e-05,
"loss": 0.769,
"step": 230
},
{
"epoch": 0.32103825136612024,
"grad_norm": 0.5516002849247819,
"learning_rate": 1.7188236838779297e-05,
"loss": 0.7518,
"step": 235
},
{
"epoch": 0.32786885245901637,
"grad_norm": 0.5604362168665755,
"learning_rate": 1.702024614595248e-05,
"loss": 0.7736,
"step": 240
},
{
"epoch": 0.33469945355191255,
"grad_norm": 0.6287905939345914,
"learning_rate": 1.6848254903319866e-05,
"loss": 0.7487,
"step": 245
},
{
"epoch": 0.34153005464480873,
"grad_norm": 0.5691120534757109,
"learning_rate": 1.6672361121623238e-05,
"loss": 0.7614,
"step": 250
},
{
"epoch": 0.3483606557377049,
"grad_norm": 0.5460125409110708,
"learning_rate": 1.6492665035501048e-05,
"loss": 0.7587,
"step": 255
},
{
"epoch": 0.3551912568306011,
"grad_norm": 0.57597601156693,
"learning_rate": 1.6309269046368777e-05,
"loss": 0.7673,
"step": 260
},
{
"epoch": 0.3620218579234973,
"grad_norm": 0.5966304605065128,
"learning_rate": 1.612227766406461e-05,
"loss": 0.7816,
"step": 265
},
{
"epoch": 0.36885245901639346,
"grad_norm": 0.5734953007972787,
"learning_rate": 1.5931797447293553e-05,
"loss": 0.7665,
"step": 270
},
{
"epoch": 0.3756830601092896,
"grad_norm": 0.5811602692803652,
"learning_rate": 1.5737936942904025e-05,
"loss": 0.7514,
"step": 275
},
{
"epoch": 0.3825136612021858,
"grad_norm": 0.5490754114059545,
"learning_rate": 1.554080662403144e-05,
"loss": 0.7588,
"step": 280
},
{
"epoch": 0.38934426229508196,
"grad_norm": 0.5730964675833344,
"learning_rate": 1.5340518827144145e-05,
"loss": 0.7559,
"step": 285
},
{
"epoch": 0.39617486338797814,
"grad_norm": 0.5589786160518924,
"learning_rate": 1.5137187688027437e-05,
"loss": 0.7535,
"step": 290
},
{
"epoch": 0.4030054644808743,
"grad_norm": 0.5482919352886477,
"learning_rate": 1.4930929076742317e-05,
"loss": 0.7408,
"step": 295
},
{
"epoch": 0.4098360655737705,
"grad_norm": 0.5546311270276107,
"learning_rate": 1.4721860531595868e-05,
"loss": 0.771,
"step": 300
},
{
"epoch": 0.4166666666666667,
"grad_norm": 0.5655833815736454,
"learning_rate": 1.451010119216102e-05,
"loss": 0.7367,
"step": 305
},
{
"epoch": 0.42349726775956287,
"grad_norm": 0.6197227214321215,
"learning_rate": 1.4295771731383799e-05,
"loss": 0.7527,
"step": 310
},
{
"epoch": 0.430327868852459,
"grad_norm": 0.5476311997058135,
"learning_rate": 1.4078994286816768e-05,
"loss": 0.7295,
"step": 315
},
{
"epoch": 0.4371584699453552,
"grad_norm": 0.5984718358075056,
"learning_rate": 1.3859892391017867e-05,
"loss": 0.747,
"step": 320
},
{
"epoch": 0.44398907103825136,
"grad_norm": 0.5609136301558824,
"learning_rate": 1.3638590901154276e-05,
"loss": 0.7314,
"step": 325
},
{
"epoch": 0.45081967213114754,
"grad_norm": 0.5678828594627737,
"learning_rate": 1.341521592785145e-05,
"loss": 0.7416,
"step": 330
},
{
"epoch": 0.4576502732240437,
"grad_norm": 0.6045615515916248,
"learning_rate": 1.3189894763327851e-05,
"loss": 0.7575,
"step": 335
},
{
"epoch": 0.4644808743169399,
"grad_norm": 0.6102125885340797,
"learning_rate": 1.2962755808856341e-05,
"loss": 0.7233,
"step": 340
},
{
"epoch": 0.4713114754098361,
"grad_norm": 0.5569824101385544,
"learning_rate": 1.2733928501593587e-05,
"loss": 0.7513,
"step": 345
},
{
"epoch": 0.4781420765027322,
"grad_norm": 0.5900237407977923,
"learning_rate": 1.2503543240819127e-05,
"loss": 0.7247,
"step": 350
},
{
"epoch": 0.4849726775956284,
"grad_norm": 0.5680127868499019,
"learning_rate": 1.227173131362619e-05,
"loss": 0.7311,
"step": 355
},
{
"epoch": 0.4918032786885246,
"grad_norm": 0.5625573721414876,
"learning_rate": 1.2038624820106572e-05,
"loss": 0.723,
"step": 360
},
{
"epoch": 0.49863387978142076,
"grad_norm": 0.5756982415323313,
"learning_rate": 1.1804356598072223e-05,
"loss": 0.7392,
"step": 365
},
{
"epoch": 0.505464480874317,
"grad_norm": 0.5946932612905129,
"learning_rate": 1.1569060147356441e-05,
"loss": 0.7287,
"step": 370
},
{
"epoch": 0.5122950819672131,
"grad_norm": 0.6113580526324344,
"learning_rate": 1.133286955373779e-05,
"loss": 0.7568,
"step": 375
},
{
"epoch": 0.5191256830601093,
"grad_norm": 0.6964655258277292,
"learning_rate": 1.1095919412530136e-05,
"loss": 0.7257,
"step": 380
},
{
"epoch": 0.5259562841530054,
"grad_norm": 0.558955112992284,
"learning_rate": 1.0858344751882304e-05,
"loss": 0.7468,
"step": 385
},
{
"epoch": 0.5327868852459017,
"grad_norm": 0.6215470265457846,
"learning_rate": 1.0620280955831088e-05,
"loss": 0.7537,
"step": 390
},
{
"epoch": 0.5396174863387978,
"grad_norm": 0.5750613153322487,
"learning_rate": 1.038186368715145e-05,
"loss": 0.7343,
"step": 395
},
{
"epoch": 0.546448087431694,
"grad_norm": 0.5701696384507413,
"learning_rate": 1.0143228810047877e-05,
"loss": 0.7358,
"step": 400
},
{
"epoch": 0.5532786885245902,
"grad_norm": 0.5635496322641829,
"learning_rate": 9.904512312730948e-06,
"loss": 0.723,
"step": 405
},
{
"epoch": 0.5601092896174863,
"grad_norm": 0.5331086289619262,
"learning_rate": 9.665850229923258e-06,
"loss": 0.7359,
"step": 410
},
{
"epoch": 0.5669398907103825,
"grad_norm": 0.5696605773767074,
"learning_rate": 9.4273785653388e-06,
"loss": 0.7266,
"step": 415
},
{
"epoch": 0.5737704918032787,
"grad_norm": 0.5530919852682804,
"learning_rate": 9.189233214180057e-06,
"loss": 0.7245,
"step": 420
},
{
"epoch": 0.5806010928961749,
"grad_norm": 0.6180570767094125,
"learning_rate": 8.951549885696889e-06,
"loss": 0.7152,
"step": 425
},
{
"epoch": 0.587431693989071,
"grad_norm": 0.5435168155874842,
"learning_rate": 8.714464025851428e-06,
"loss": 0.7329,
"step": 430
},
{
"epoch": 0.5942622950819673,
"grad_norm": 0.5918089418612534,
"learning_rate": 8.478110740132971e-06,
"loss": 0.7394,
"step": 435
},
{
"epoch": 0.6010928961748634,
"grad_norm": 0.5775872171354361,
"learning_rate": 8.242624716566928e-06,
"loss": 0.7386,
"step": 440
},
{
"epoch": 0.6079234972677595,
"grad_norm": 0.560805508558742,
"learning_rate": 8.008140148961642e-06,
"loss": 0.7286,
"step": 445
},
{
"epoch": 0.6147540983606558,
"grad_norm": 0.5659035847143471,
"learning_rate": 7.774790660436857e-06,
"loss": 0.7395,
"step": 450
},
{
"epoch": 0.6215846994535519,
"grad_norm": 0.5934950402129012,
"learning_rate": 7.542709227277396e-06,
"loss": 0.7256,
"step": 455
},
{
"epoch": 0.6284153005464481,
"grad_norm": 0.5440391404753762,
"learning_rate": 7.312028103155426e-06,
"loss": 0.7115,
"step": 460
},
{
"epoch": 0.6352459016393442,
"grad_norm": 0.525973972202757,
"learning_rate": 7.0828787437645455e-06,
"loss": 0.7253,
"step": 465
},
{
"epoch": 0.6420765027322405,
"grad_norm": 0.5381242803100431,
"learning_rate": 6.8553917319085676e-06,
"loss": 0.715,
"step": 470
},
{
"epoch": 0.6489071038251366,
"grad_norm": 0.5407688729054287,
"learning_rate": 6.629696703087755e-06,
"loss": 0.7145,
"step": 475
},
{
"epoch": 0.6557377049180327,
"grad_norm": 0.5510841812349385,
"learning_rate": 6.405922271624874e-06,
"loss": 0.6676,
"step": 480
},
{
"epoch": 0.662568306010929,
"grad_norm": 0.5574387613507912,
"learning_rate": 6.184195957373176e-06,
"loss": 0.7353,
"step": 485
},
{
"epoch": 0.6693989071038251,
"grad_norm": 0.6253673572306452,
"learning_rate": 5.964644113048079e-06,
"loss": 0.7065,
"step": 490
},
{
"epoch": 0.6762295081967213,
"grad_norm": 0.5452906786267165,
"learning_rate": 5.74739185222394e-06,
"loss": 0.7336,
"step": 495
},
{
"epoch": 0.6830601092896175,
"grad_norm": 0.5560796717868584,
"learning_rate": 5.532562978036964e-06,
"loss": 0.7207,
"step": 500
},
{
"epoch": 0.6898907103825137,
"grad_norm": 0.6056533738818196,
"learning_rate": 5.320279912634907e-06,
"loss": 0.7186,
"step": 505
},
{
"epoch": 0.6967213114754098,
"grad_norm": 0.569520229311181,
"learning_rate": 5.110663627413695e-06,
"loss": 0.7377,
"step": 510
},
{
"epoch": 0.703551912568306,
"grad_norm": 0.5563155283253095,
"learning_rate": 4.903833574080825e-06,
"loss": 0.7065,
"step": 515
},
{
"epoch": 0.7103825136612022,
"grad_norm": 0.6065562069673966,
"learning_rate": 4.6999076165847214e-06,
"loss": 0.7436,
"step": 520
},
{
"epoch": 0.7172131147540983,
"grad_norm": 0.5561597356740903,
"learning_rate": 4.499001963948929e-06,
"loss": 0.7279,
"step": 525
},
{
"epoch": 0.7240437158469946,
"grad_norm": 0.540260398768991,
"learning_rate": 4.301231104049359e-06,
"loss": 0.7102,
"step": 530
},
{
"epoch": 0.7308743169398907,
"grad_norm": 0.5312643673085101,
"learning_rate": 4.106707738372357e-06,
"loss": 0.696,
"step": 535
},
{
"epoch": 0.7377049180327869,
"grad_norm": 0.5886875453265892,
"learning_rate": 3.915542717790759e-06,
"loss": 0.7225,
"step": 540
},
{
"epoch": 0.744535519125683,
"grad_norm": 0.5771137703202747,
"learning_rate": 3.727844979394526e-06,
"loss": 0.7369,
"step": 545
},
{
"epoch": 0.7513661202185792,
"grad_norm": 0.5513216324725466,
"learning_rate": 3.543721484411976e-06,
"loss": 0.7381,
"step": 550
},
{
"epoch": 0.7581967213114754,
"grad_norm": 0.5821599254967618,
"learning_rate": 3.3632771572569878e-06,
"loss": 0.7346,
"step": 555
},
{
"epoch": 0.7650273224043715,
"grad_norm": 0.5434619637496027,
"learning_rate": 3.1866148257368666e-06,
"loss": 0.6955,
"step": 560
},
{
"epoch": 0.7718579234972678,
"grad_norm": 0.5508768490641304,
"learning_rate": 3.0138351624550165e-06,
"loss": 0.7088,
"step": 565
},
{
"epoch": 0.7786885245901639,
"grad_norm": 0.5522627907801693,
"learning_rate": 2.845036627441755e-06,
"loss": 0.7029,
"step": 570
},
{
"epoch": 0.7855191256830601,
"grad_norm": 0.5484073193031532,
"learning_rate": 2.6803154120460007e-06,
"loss": 0.6981,
"step": 575
},
{
"epoch": 0.7923497267759563,
"grad_norm": 0.5460127035608994,
"learning_rate": 2.5197653841197546e-06,
"loss": 0.7359,
"step": 580
},
{
"epoch": 0.7991803278688525,
"grad_norm": 0.5649471360604418,
"learning_rate": 2.3634780345266805e-06,
"loss": 0.7273,
"step": 585
},
{
"epoch": 0.8060109289617486,
"grad_norm": 0.5701788726901212,
"learning_rate": 2.211542425005223e-06,
"loss": 0.7093,
"step": 590
},
{
"epoch": 0.8128415300546448,
"grad_norm": 0.5541668671991618,
"learning_rate": 2.064045137415982e-06,
"loss": 0.7464,
"step": 595
},
{
"epoch": 0.819672131147541,
"grad_norm": 0.5330522987281802,
"learning_rate": 1.9210702244022616e-06,
"loss": 0.715,
"step": 600
},
{
"epoch": 0.8265027322404371,
"grad_norm": 0.5298294565996464,
"learning_rate": 1.7826991614919264e-06,
"loss": 0.7223,
"step": 605
},
{
"epoch": 0.8333333333333334,
"grad_norm": 0.5610592085239171,
"learning_rate": 1.6490108006678495e-06,
"loss": 0.7247,
"step": 610
},
{
"epoch": 0.8401639344262295,
"grad_norm": 0.5682288942071054,
"learning_rate": 1.5200813254334013e-06,
"loss": 0.7054,
"step": 615
},
{
"epoch": 0.8469945355191257,
"grad_norm": 0.5693548112007653,
"learning_rate": 1.3959842073986085e-06,
"loss": 0.7266,
"step": 620
},
{
"epoch": 0.8538251366120219,
"grad_norm": 0.5448533977882911,
"learning_rate": 1.2767901644116943e-06,
"loss": 0.7154,
"step": 625
},
{
"epoch": 0.860655737704918,
"grad_norm": 0.567356173427535,
"learning_rate": 1.1625671202598875e-06,
"loss": 0.7042,
"step": 630
},
{
"epoch": 0.8674863387978142,
"grad_norm": 0.5923179681072539,
"learning_rate": 1.0533801659624531e-06,
"loss": 0.696,
"step": 635
},
{
"epoch": 0.8743169398907104,
"grad_norm": 0.5471124778528522,
"learning_rate": 9.492915226779809e-07,
"loss": 0.7037,
"step": 640
},
{
"epoch": 0.8811475409836066,
"grad_norm": 0.7367442278445117,
"learning_rate": 8.503605062471187e-07,
"loss": 0.7285,
"step": 645
},
{
"epoch": 0.8879781420765027,
"grad_norm": 0.5411387873270271,
"learning_rate": 7.566434933909006e-07,
"loss": 0.7167,
"step": 650
},
{
"epoch": 0.894808743169399,
"grad_norm": 0.5402678284774802,
"learning_rate": 6.681938895839746e-07,
"loss": 0.6901,
"step": 655
},
{
"epoch": 0.9016393442622951,
"grad_norm": 0.5526115125845628,
"learning_rate": 5.850620986210198e-07,
"loss": 0.7028,
"step": 660
},
{
"epoch": 0.9084699453551912,
"grad_norm": 0.557503740636623,
"learning_rate": 5.072954938936925e-07,
"loss": 0.7059,
"step": 665
},
{
"epoch": 0.9153005464480874,
"grad_norm": 0.6069774844130886,
"learning_rate": 4.3493839139447716e-07,
"loss": 0.709,
"step": 670
},
{
"epoch": 0.9221311475409836,
"grad_norm": 0.5659313165055196,
"learning_rate": 3.6803202446282217e-07,
"loss": 0.7173,
"step": 675
},
{
"epoch": 0.9289617486338798,
"grad_norm": 0.546500310034168,
"learning_rate": 3.0661452028795335e-07,
"loss": 0.6963,
"step": 680
},
{
"epoch": 0.9357923497267759,
"grad_norm": 0.5278636280522998,
"learning_rate": 2.507208781817638e-07,
"loss": 0.7062,
"step": 685
},
{
"epoch": 0.9426229508196722,
"grad_norm": 0.5368853646294492,
"learning_rate": 2.0038294963413251e-07,
"loss": 0.7303,
"step": 690
},
{
"epoch": 0.9494535519125683,
"grad_norm": 0.5295882031597404,
"learning_rate": 1.556294201620734e-07,
"loss": 0.7077,
"step": 695
},
{
"epoch": 0.9562841530054644,
"grad_norm": 0.5590243905068004,
"learning_rate": 1.1648579296304252e-07,
"loss": 0.71,
"step": 700
},
{
"epoch": 0.9631147540983607,
"grad_norm": 0.5607413731294414,
"learning_rate": 8.297437438170797e-08,
"loss": 0.716,
"step": 705
},
{
"epoch": 0.9699453551912568,
"grad_norm": 0.5580234118888867,
"learning_rate": 5.51142611984834e-08,
"loss": 0.7147,
"step": 710
},
{
"epoch": 0.976775956284153,
"grad_norm": 0.5435574659414255,
"learning_rate": 3.2921329747056527e-08,
"loss": 0.7131,
"step": 715
},
{
"epoch": 0.9836065573770492,
"grad_norm": 0.6153543980271695,
"learning_rate": 1.6408226867118404e-08,
"loss": 0.714,
"step": 720
},
{
"epoch": 0.9904371584699454,
"grad_norm": 0.5542963142607653,
"learning_rate": 5.584362697453882e-09,
"loss": 0.7282,
"step": 725
},
{
"epoch": 0.9972677595628415,
"grad_norm": 1.0209900402406562,
"learning_rate": 4.5590531348227443e-10,
"loss": 0.7115,
"step": 730
},
{
"epoch": 1.0,
"eval_loss": 0.7274145483970642,
"eval_runtime": 9.4843,
"eval_samples_per_second": 52.719,
"eval_steps_per_second": 1.687,
"step": 732
},
{
"epoch": 1.0,
"step": 732,
"total_flos": 106034689474560.0,
"train_loss": 0.7575202535410397,
"train_runtime": 8959.9133,
"train_samples_per_second": 10.452,
"train_steps_per_second": 0.082
}
],
"logging_steps": 5,
"max_steps": 732,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 100,
"total_flos": 106034689474560.0,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}