{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9943246311010214,
  "eval_steps": 50,
  "global_step": 1320,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.022701475595913734,
      "grad_norm": 0.98377925157547,
      "learning_rate": 0.0004980988593155894,
      "loss": 2.041,
      "step": 10
    },
    {
      "epoch": 0.04540295119182747,
      "grad_norm": 0.9438253045082092,
      "learning_rate": 0.0004942965779467681,
      "loss": 0.5227,
      "step": 20
    },
    {
      "epoch": 0.0681044267877412,
      "grad_norm": 1.2742111682891846,
      "learning_rate": 0.0004904942965779467,
      "loss": 0.3237,
      "step": 30
    },
    {
      "epoch": 0.09080590238365494,
      "grad_norm": 1.0742741823196411,
      "learning_rate": 0.00048669201520912546,
      "loss": 0.2732,
      "step": 40
    },
    {
      "epoch": 0.11350737797956867,
      "grad_norm": 0.293316513299942,
      "learning_rate": 0.0004828897338403042,
      "loss": 0.2525,
      "step": 50
    },
    {
      "epoch": 0.11350737797956867,
      "eval_loss": 0.22574295103549957,
      "eval_runtime": 222.4911,
      "eval_samples_per_second": 0.899,
      "eval_steps_per_second": 0.449,
      "step": 50
    },
    {
      "epoch": 0.1362088535754824,
      "grad_norm": 0.6410325765609741,
      "learning_rate": 0.00047908745247148286,
      "loss": 0.2252,
      "step": 60
    },
    {
      "epoch": 0.15891032917139614,
      "grad_norm": 0.4331947863101959,
      "learning_rate": 0.0004752851711026616,
      "loss": 0.2028,
      "step": 70
    },
    {
      "epoch": 0.18161180476730987,
      "grad_norm": 0.2875344157218933,
      "learning_rate": 0.00047148288973384027,
      "loss": 0.1861,
      "step": 80
    },
    {
      "epoch": 0.2043132803632236,
      "grad_norm": 0.25494372844696045,
      "learning_rate": 0.000467680608365019,
      "loss": 0.1871,
      "step": 90
    },
    {
      "epoch": 0.22701475595913734,
      "grad_norm": 0.2936597168445587,
      "learning_rate": 0.00046387832699619773,
      "loss": 0.1805,
      "step": 100
    },
    {
      "epoch": 0.22701475595913734,
      "eval_loss": 0.17074081301689148,
      "eval_runtime": 217.5217,
      "eval_samples_per_second": 0.919,
      "eval_steps_per_second": 0.46,
      "step": 100
    },
    {
      "epoch": 0.24971623155505107,
      "grad_norm": 0.23551008105278015,
      "learning_rate": 0.0004600760456273764,
      "loss": 0.1642,
      "step": 110
    },
    {
      "epoch": 0.2724177071509648,
      "grad_norm": 0.21073344349861145,
      "learning_rate": 0.00045627376425855514,
      "loss": 0.1674,
      "step": 120
    },
    {
      "epoch": 0.29511918274687854,
      "grad_norm": 0.27475476264953613,
      "learning_rate": 0.0004524714828897338,
      "loss": 0.1586,
      "step": 130
    },
    {
      "epoch": 0.3178206583427923,
      "grad_norm": 0.19965380430221558,
      "learning_rate": 0.00044866920152091254,
      "loss": 0.1553,
      "step": 140
    },
    {
      "epoch": 0.340522133938706,
      "grad_norm": 0.2891227602958679,
      "learning_rate": 0.0004448669201520912,
      "loss": 0.1484,
      "step": 150
    },
    {
      "epoch": 0.340522133938706,
      "eval_loss": 0.14293429255485535,
      "eval_runtime": 217.6158,
      "eval_samples_per_second": 0.919,
      "eval_steps_per_second": 0.46,
      "step": 150
    },
    {
      "epoch": 0.36322360953461974,
      "grad_norm": 0.18177160620689392,
      "learning_rate": 0.00044106463878326995,
      "loss": 0.1403,
      "step": 160
    },
    {
      "epoch": 0.3859250851305335,
      "grad_norm": 0.1343546211719513,
      "learning_rate": 0.0004372623574144487,
      "loss": 0.1394,
      "step": 170
    },
    {
      "epoch": 0.4086265607264472,
      "grad_norm": 0.19174069166183472,
      "learning_rate": 0.00043346007604562736,
      "loss": 0.1329,
      "step": 180
    },
    {
      "epoch": 0.43132803632236094,
      "grad_norm": 0.2594343423843384,
      "learning_rate": 0.0004296577946768061,
      "loss": 0.1346,
      "step": 190
    },
    {
      "epoch": 0.4540295119182747,
      "grad_norm": 0.1463007926940918,
      "learning_rate": 0.00042585551330798476,
      "loss": 0.1366,
      "step": 200
    },
    {
      "epoch": 0.4540295119182747,
      "eval_loss": 0.13306422531604767,
      "eval_runtime": 217.7159,
      "eval_samples_per_second": 0.919,
      "eval_steps_per_second": 0.459,
      "step": 200
    },
    {
      "epoch": 0.4767309875141884,
      "grad_norm": 0.25085681676864624,
      "learning_rate": 0.0004220532319391635,
      "loss": 0.125,
      "step": 210
    },
    {
      "epoch": 0.49943246311010214,
      "grad_norm": 0.13558617234230042,
      "learning_rate": 0.0004182509505703422,
      "loss": 0.1354,
      "step": 220
    },
    {
      "epoch": 0.5221339387060159,
      "grad_norm": 0.1223764568567276,
      "learning_rate": 0.0004144486692015209,
      "loss": 0.13,
      "step": 230
    },
    {
      "epoch": 0.5448354143019296,
      "grad_norm": 0.21993857622146606,
      "learning_rate": 0.00041064638783269963,
      "loss": 0.1265,
      "step": 240
    },
    {
      "epoch": 0.5675368898978433,
      "grad_norm": 0.17128345370292664,
      "learning_rate": 0.0004068441064638783,
      "loss": 0.1248,
      "step": 250
    },
    {
      "epoch": 0.5675368898978433,
      "eval_loss": 0.1296500563621521,
      "eval_runtime": 217.6406,
      "eval_samples_per_second": 0.919,
      "eval_steps_per_second": 0.459,
      "step": 250
    },
    {
      "epoch": 0.5902383654937571,
      "grad_norm": 0.13287974894046783,
      "learning_rate": 0.00040304182509505703,
      "loss": 0.1346,
      "step": 260
    },
    {
      "epoch": 0.6129398410896708,
      "grad_norm": 0.1447504311800003,
      "learning_rate": 0.00039923954372623577,
      "loss": 0.1261,
      "step": 270
    },
    {
      "epoch": 0.6356413166855845,
      "grad_norm": 0.12065211683511734,
      "learning_rate": 0.00039543726235741444,
      "loss": 0.1184,
      "step": 280
    },
    {
      "epoch": 0.6583427922814983,
      "grad_norm": 0.11076737195253372,
      "learning_rate": 0.00039163498098859317,
      "loss": 0.1219,
      "step": 290
    },
    {
      "epoch": 0.681044267877412,
      "grad_norm": 0.09753841161727905,
      "learning_rate": 0.00038783269961977185,
      "loss": 0.1236,
      "step": 300
    },
    {
      "epoch": 0.681044267877412,
      "eval_loss": 0.12370797991752625,
      "eval_runtime": 217.5925,
      "eval_samples_per_second": 0.919,
      "eval_steps_per_second": 0.46,
      "step": 300
    },
    {
      "epoch": 0.7037457434733257,
      "grad_norm": 0.1080508679151535,
      "learning_rate": 0.0003840304182509506,
      "loss": 0.1232,
      "step": 310
    },
    {
      "epoch": 0.7264472190692395,
      "grad_norm": 0.11670809239149094,
      "learning_rate": 0.00038022813688212925,
      "loss": 0.116,
      "step": 320
    },
    {
      "epoch": 0.7491486946651532,
      "grad_norm": 0.10847495496273041,
      "learning_rate": 0.000376425855513308,
      "loss": 0.1225,
      "step": 330
    },
    {
      "epoch": 0.771850170261067,
      "grad_norm": 0.13137522339820862,
      "learning_rate": 0.0003726235741444867,
      "loss": 0.1183,
      "step": 340
    },
    {
      "epoch": 0.7945516458569807,
      "grad_norm": 0.3472500443458557,
      "learning_rate": 0.0003688212927756654,
      "loss": 0.1213,
      "step": 350
    },
    {
      "epoch": 0.7945516458569807,
      "eval_loss": 0.13061952590942383,
      "eval_runtime": 217.6112,
      "eval_samples_per_second": 0.919,
      "eval_steps_per_second": 0.46,
      "step": 350
    },
    {
      "epoch": 0.8172531214528944,
      "grad_norm": 1.0965760946273804,
      "learning_rate": 0.0003650190114068441,
      "loss": 0.1245,
      "step": 360
    },
    {
      "epoch": 0.8399545970488081,
      "grad_norm": 0.11599018424749374,
      "learning_rate": 0.0003612167300380228,
      "loss": 0.1181,
      "step": 370
    },
    {
      "epoch": 0.8626560726447219,
      "grad_norm": 0.1406373679637909,
      "learning_rate": 0.0003574144486692015,
      "loss": 0.1264,
      "step": 380
    },
    {
      "epoch": 0.8853575482406356,
      "grad_norm": 0.1464611142873764,
      "learning_rate": 0.00035361216730038026,
      "loss": 0.1262,
      "step": 390
    },
    {
      "epoch": 0.9080590238365494,
      "grad_norm": 0.11901883035898209,
      "learning_rate": 0.00034980988593155893,
      "loss": 0.1212,
      "step": 400
    },
    {
      "epoch": 0.9080590238365494,
      "eval_loss": 0.1218264177441597,
      "eval_runtime": 217.4651,
      "eval_samples_per_second": 0.92,
      "eval_steps_per_second": 0.46,
      "step": 400
    },
    {
      "epoch": 0.9307604994324631,
      "grad_norm": 0.17761249840259552,
      "learning_rate": 0.00034600760456273766,
      "loss": 0.1224,
      "step": 410
    },
    {
      "epoch": 0.9534619750283768,
      "grad_norm": 0.10262706875801086,
      "learning_rate": 0.00034220532319391634,
      "loss": 0.1218,
      "step": 420
    },
    {
      "epoch": 0.9761634506242906,
      "grad_norm": 0.12772826850414276,
      "learning_rate": 0.00033840304182509507,
      "loss": 0.1177,
      "step": 430
    },
    {
      "epoch": 0.9988649262202043,
      "grad_norm": 0.11388087272644043,
      "learning_rate": 0.00033460076045627375,
      "loss": 0.1202,
      "step": 440
    },
    {
      "epoch": 1.0204313280363224,
      "grad_norm": 0.12442510575056076,
      "learning_rate": 0.0003307984790874525,
      "loss": 0.1178,
      "step": 450
    },
    {
      "epoch": 1.0204313280363224,
      "eval_loss": 0.12656380236148834,
      "eval_runtime": 217.5337,
      "eval_samples_per_second": 0.919,
      "eval_steps_per_second": 0.46,
      "step": 450
    },
    {
      "epoch": 1.043132803632236,
      "grad_norm": 26971.419921875,
      "learning_rate": 0.0003269961977186312,
      "loss": 0.1155,
      "step": 460
    },
    {
      "epoch": 1.0658342792281499,
      "grad_norm": 0.09757928550243378,
      "learning_rate": 0.0003231939163498099,
      "loss": 0.126,
      "step": 470
    },
    {
      "epoch": 1.0885357548240635,
      "grad_norm": 0.11210393160581589,
      "learning_rate": 0.0003193916349809886,
      "loss": 0.1082,
      "step": 480
    },
    {
      "epoch": 1.1112372304199774,
      "grad_norm": 0.10138614475727081,
      "learning_rate": 0.0003155893536121673,
      "loss": 0.1124,
      "step": 490
    },
    {
      "epoch": 1.133938706015891,
      "grad_norm": 0.12984132766723633,
      "learning_rate": 0.000311787072243346,
      "loss": 0.1212,
      "step": 500
    },
    {
      "epoch": 1.133938706015891,
      "eval_loss": 0.11706481873989105,
      "eval_runtime": 217.5308,
      "eval_samples_per_second": 0.919,
      "eval_steps_per_second": 0.46,
      "step": 500
    },
    {
      "epoch": 1.1566401816118048,
      "grad_norm": 0.11328810453414917,
      "learning_rate": 0.00030798479087452475,
      "loss": 0.1144,
      "step": 510
    },
    {
      "epoch": 1.1793416572077184,
      "grad_norm": 0.1247556060552597,
      "learning_rate": 0.0003041825095057034,
      "loss": 0.1172,
      "step": 520
    },
    {
      "epoch": 1.2020431328036323,
      "grad_norm": 0.11804669350385666,
      "learning_rate": 0.00030038022813688215,
      "loss": 0.1204,
      "step": 530
    },
    {
      "epoch": 1.224744608399546,
      "grad_norm": 0.11827069520950317,
      "learning_rate": 0.00029657794676806083,
      "loss": 0.1188,
      "step": 540
    },
    {
      "epoch": 1.2474460839954598,
      "grad_norm": 0.1352234184741974,
      "learning_rate": 0.00029277566539923956,
      "loss": 0.1165,
      "step": 550
    },
    {
      "epoch": 1.2474460839954598,
      "eval_loss": 0.11637674272060394,
      "eval_runtime": 217.5994,
      "eval_samples_per_second": 0.919,
      "eval_steps_per_second": 0.46,
      "step": 550
    },
    {
      "epoch": 1.2701475595913734,
      "grad_norm": 0.12024690955877304,
      "learning_rate": 0.00028897338403041824,
      "loss": 0.1178,
      "step": 560
    },
    {
      "epoch": 1.2928490351872872,
      "grad_norm": 0.09398236870765686,
      "learning_rate": 0.00028517110266159697,
      "loss": 0.1164,
      "step": 570
    },
    {
      "epoch": 1.3155505107832008,
      "grad_norm": 0.09315728396177292,
      "learning_rate": 0.0002813688212927757,
      "loss": 0.1118,
      "step": 580
    },
    {
      "epoch": 1.3382519863791147,
      "grad_norm": 0.09556794911623001,
      "learning_rate": 0.0002775665399239544,
      "loss": 0.114,
      "step": 590
    },
    {
      "epoch": 1.3609534619750283,
      "grad_norm": 0.12721088528633118,
      "learning_rate": 0.0002737642585551331,
      "loss": 0.1206,
      "step": 600
    },
    {
      "epoch": 1.3609534619750283,
      "eval_loss": 0.11379682272672653,
      "eval_runtime": 217.4599,
      "eval_samples_per_second": 0.92,
      "eval_steps_per_second": 0.46,
      "step": 600
    },
    {
      "epoch": 1.3836549375709422,
      "grad_norm": 0.11218762397766113,
      "learning_rate": 0.0002699619771863118,
      "loss": 0.1143,
      "step": 610
    },
    {
      "epoch": 1.4063564131668558,
      "grad_norm": 0.1336316615343094,
      "learning_rate": 0.0002661596958174905,
      "loss": 0.1157,
      "step": 620
    },
    {
      "epoch": 1.4290578887627696,
      "grad_norm": 0.1047380119562149,
      "learning_rate": 0.00026235741444866924,
      "loss": 0.1155,
      "step": 630
    },
    {
      "epoch": 1.4517593643586832,
      "grad_norm": 0.10472728312015533,
      "learning_rate": 0.0002585551330798479,
      "loss": 0.112,
      "step": 640
    },
    {
      "epoch": 1.474460839954597,
      "grad_norm": 0.11173685640096664,
      "learning_rate": 0.00025475285171102665,
      "loss": 0.116,
      "step": 650
    },
    {
      "epoch": 1.474460839954597,
      "eval_loss": 0.11390363425016403,
      "eval_runtime": 217.503,
      "eval_samples_per_second": 0.92,
      "eval_steps_per_second": 0.46,
      "step": 650
    },
    {
      "epoch": 1.4971623155505107,
      "grad_norm": 0.09606759250164032,
      "learning_rate": 0.0002509505703422053,
      "loss": 0.1106,
      "step": 660
    },
    {
      "epoch": 1.5198637911464246,
      "grad_norm": 0.10025890916585922,
      "learning_rate": 0.00024714828897338405,
      "loss": 0.1104,
      "step": 670
    },
    {
      "epoch": 1.5425652667423382,
      "grad_norm": 0.09173867851495743,
      "learning_rate": 0.00024334600760456273,
      "loss": 0.1138,
      "step": 680
    },
    {
      "epoch": 1.565266742338252,
      "grad_norm": 0.11808419227600098,
      "learning_rate": 0.00023954372623574143,
      "loss": 0.1176,
      "step": 690
    },
    {
      "epoch": 1.5879682179341659,
      "grad_norm": 0.10776414722204208,
      "learning_rate": 0.00023574144486692014,
      "loss": 0.1168,
      "step": 700
    },
    {
      "epoch": 1.5879682179341659,
      "eval_loss": 0.11171030253171921,
      "eval_runtime": 217.522,
      "eval_samples_per_second": 0.919,
      "eval_steps_per_second": 0.46,
      "step": 700
    },
    {
      "epoch": 1.6106696935300795,
      "grad_norm": 0.1097252145409584,
      "learning_rate": 0.00023193916349809887,
      "loss": 0.1094,
      "step": 710
    },
    {
      "epoch": 1.6333711691259931,
      "grad_norm": 0.10685060173273087,
      "learning_rate": 0.00022813688212927757,
      "loss": 0.1109,
      "step": 720
    },
    {
      "epoch": 1.656072644721907,
      "grad_norm": 0.13034620881080627,
      "learning_rate": 0.00022433460076045627,
      "loss": 0.1116,
      "step": 730
    },
    {
      "epoch": 1.6787741203178208,
      "grad_norm": 0.09243394434452057,
      "learning_rate": 0.00022053231939163497,
      "loss": 0.1181,
      "step": 740
    },
    {
      "epoch": 1.7014755959137344,
      "grad_norm": 0.09220673888921738,
      "learning_rate": 0.00021673003802281368,
      "loss": 0.1156,
      "step": 750
    },
    {
      "epoch": 1.7014755959137344,
      "eval_loss": 0.11321926862001419,
      "eval_runtime": 217.4623,
      "eval_samples_per_second": 0.92,
      "eval_steps_per_second": 0.46,
      "step": 750
    },
    {
      "epoch": 1.724177071509648,
      "grad_norm": 0.08847390860319138,
      "learning_rate": 0.00021292775665399238,
      "loss": 0.1142,
      "step": 760
    },
    {
      "epoch": 1.746878547105562,
      "grad_norm": 0.10436313599348068,
      "learning_rate": 0.0002091254752851711,
      "loss": 0.1116,
      "step": 770
    },
    {
      "epoch": 1.7695800227014757,
      "grad_norm": 0.10285446792840958,
      "learning_rate": 0.00020532319391634981,
      "loss": 0.1122,
      "step": 780
    },
    {
      "epoch": 1.7922814982973894,
      "grad_norm": 0.11135664582252502,
      "learning_rate": 0.00020152091254752852,
      "loss": 0.1121,
      "step": 790
    },
    {
      "epoch": 1.814982973893303,
      "grad_norm": 0.10696069896221161,
      "learning_rate": 0.00019771863117870722,
      "loss": 0.113,
      "step": 800
    },
    {
      "epoch": 1.814982973893303,
      "eval_loss": 0.10933104157447815,
      "eval_runtime": 217.663,
      "eval_samples_per_second": 0.919,
      "eval_steps_per_second": 0.459,
      "step": 800
    },
    {
      "epoch": 1.8376844494892168,
      "grad_norm": 0.10220722109079361,
      "learning_rate": 0.00019391634980988592,
      "loss": 0.1131,
      "step": 810
    },
    {
      "epoch": 1.8603859250851307,
      "grad_norm": 0.10076457262039185,
      "learning_rate": 0.00019011406844106463,
      "loss": 0.1105,
      "step": 820
    },
    {
      "epoch": 1.8830874006810443,
      "grad_norm": 0.09080884605646133,
      "learning_rate": 0.00018631178707224336,
      "loss": 0.1135,
      "step": 830
    },
    {
      "epoch": 1.905788876276958,
      "grad_norm": 0.09699123352766037,
      "learning_rate": 0.00018250950570342206,
      "loss": 0.1128,
      "step": 840
    },
    {
      "epoch": 1.9284903518728718,
      "grad_norm": 0.13103429973125458,
      "learning_rate": 0.00017870722433460076,
      "loss": 0.1125,
      "step": 850
    },
    {
      "epoch": 1.9284903518728718,
      "eval_loss": 0.08514724671840668,
      "eval_runtime": 217.5471,
      "eval_samples_per_second": 0.919,
      "eval_steps_per_second": 0.46,
      "step": 850
    },
    {
      "epoch": 1.9511918274687856,
      "grad_norm": 0.10150181502103806,
      "learning_rate": 0.00017490494296577947,
      "loss": 0.1104,
      "step": 860
    },
    {
      "epoch": 1.9738933030646992,
      "grad_norm": 0.09728129953145981,
      "learning_rate": 0.00017110266159695817,
      "loss": 0.1117,
      "step": 870
    },
    {
      "epoch": 1.9965947786606129,
      "grad_norm": 0.11810111254453659,
      "learning_rate": 0.00016730038022813687,
      "loss": 0.1088,
      "step": 880
    },
    {
      "epoch": 2.018161180476731,
      "grad_norm": 0.12136723101139069,
      "learning_rate": 0.0001634980988593156,
      "loss": 0.1099,
      "step": 890
    },
    {
      "epoch": 2.040862656072645,
      "grad_norm": 0.09833360463380814,
      "learning_rate": 0.0001596958174904943,
      "loss": 0.104,
      "step": 900
    },
    {
      "epoch": 2.040862656072645,
      "eval_loss": 0.11464639753103256,
      "eval_runtime": 217.5705,
      "eval_samples_per_second": 0.919,
      "eval_steps_per_second": 0.46,
      "step": 900
    },
    {
      "epoch": 2.0635641316685582,
      "grad_norm": 0.1004079207777977,
      "learning_rate": 0.000155893536121673,
      "loss": 0.1045,
      "step": 910
    },
    {
      "epoch": 2.086265607264472,
      "grad_norm": 0.12761454284191132,
      "learning_rate": 0.0001520912547528517,
      "loss": 0.1091,
      "step": 920
    },
    {
      "epoch": 2.108967082860386,
      "grad_norm": 0.10577848553657532,
      "learning_rate": 0.00014828897338403042,
      "loss": 0.1095,
      "step": 930
    },
    {
      "epoch": 2.1316685584562998,
      "grad_norm": 0.10021686553955078,
      "learning_rate": 0.00014448669201520912,
      "loss": 0.1038,
      "step": 940
    },
    {
      "epoch": 2.1543700340522136,
      "grad_norm": 0.12449836730957031,
      "learning_rate": 0.00014068441064638785,
      "loss": 0.1114,
      "step": 950
    },
    {
      "epoch": 2.1543700340522136,
      "eval_loss": 0.11278806626796722,
      "eval_runtime": 217.472,
      "eval_samples_per_second": 0.92,
      "eval_steps_per_second": 0.46,
      "step": 950
    },
    {
      "epoch": 2.177071509648127,
      "grad_norm": 0.11041835695505142,
      "learning_rate": 0.00013688212927756655,
      "loss": 0.1115,
      "step": 960
    },
    {
      "epoch": 2.199772985244041,
      "grad_norm": 0.12451056391000748,
      "learning_rate": 0.00013307984790874526,
      "loss": 0.1067,
      "step": 970
    },
    {
      "epoch": 2.2224744608399547,
      "grad_norm": 0.11106307804584503,
      "learning_rate": 0.00012927756653992396,
      "loss": 0.107,
      "step": 980
    },
    {
      "epoch": 2.245175936435868,
      "grad_norm": 0.11006781458854675,
      "learning_rate": 0.00012547528517110266,
      "loss": 0.1041,
      "step": 990
    },
    {
      "epoch": 2.267877412031782,
      "grad_norm": 0.12557250261306763,
      "learning_rate": 0.00012167300380228136,
      "loss": 0.1106,
      "step": 1000
    },
    {
      "epoch": 2.267877412031782,
      "eval_loss": 0.111506387591362,
      "eval_runtime": 219.8537,
      "eval_samples_per_second": 0.91,
      "eval_steps_per_second": 0.455,
      "step": 1000
    },
    {
      "epoch": 2.290578887627696,
      "grad_norm": 0.10331263393163681,
      "learning_rate": 0.00011787072243346007,
      "loss": 0.1086,
      "step": 1010
    },
    {
      "epoch": 2.3132803632236096,
      "grad_norm": 0.19199371337890625,
      "learning_rate": 0.00011406844106463878,
      "loss": 0.1075,
      "step": 1020
    },
    {
      "epoch": 2.3359818388195235,
      "grad_norm": 0.1070881262421608,
      "learning_rate": 0.00011026615969581749,
      "loss": 0.0407,
      "step": 1030
    },
    {
      "epoch": 2.358683314415437,
      "grad_norm": 0.12608259916305542,
      "learning_rate": 0.00010646387832699619,
      "loss": 0.11,
      "step": 1040
    },
    {
      "epoch": 2.3813847900113507,
      "grad_norm": 0.13995610177516937,
      "learning_rate": 0.00010266159695817491,
      "loss": 0.1019,
      "step": 1050
    },
    {
      "epoch": 2.3813847900113507,
      "eval_loss": 0.11113368719816208,
      "eval_runtime": 219.8288,
      "eval_samples_per_second": 0.91,
      "eval_steps_per_second": 0.455,
      "step": 1050
    },
    {
      "epoch": 2.4040862656072646,
      "grad_norm": 0.11652055382728577,
      "learning_rate": 9.885931558935361e-05,
      "loss": 0.1077,
      "step": 1060
    },
    {
      "epoch": 2.426787741203178,
      "grad_norm": 0.1517985761165619,
      "learning_rate": 9.505703422053231e-05,
      "loss": 0.1068,
      "step": 1070
    },
    {
      "epoch": 2.449489216799092,
      "grad_norm": 0.10748250037431717,
      "learning_rate": 9.125475285171103e-05,
      "loss": 0.1057,
      "step": 1080
    },
    {
      "epoch": 2.4721906923950057,
      "grad_norm": 0.11488188803195953,
      "learning_rate": 8.745247148288973e-05,
      "loss": 0.1075,
      "step": 1090
    },
    {
      "epoch": 2.4948921679909195,
      "grad_norm": 0.1252240389585495,
      "learning_rate": 8.365019011406844e-05,
      "loss": 0.1043,
      "step": 1100
    },
    {
      "epoch": 2.4948921679909195,
      "eval_loss": 0.11009979248046875,
      "eval_runtime": 219.9087,
      "eval_samples_per_second": 0.909,
      "eval_steps_per_second": 0.455,
      "step": 1100
    },
    {
      "epoch": 2.5175936435868334,
      "grad_norm": 0.13906443119049072,
      "learning_rate": 7.984790874524715e-05,
      "loss": 0.107,
      "step": 1110
    },
    {
      "epoch": 2.5402951191827468,
      "grad_norm": 0.1267954409122467,
      "learning_rate": 7.604562737642586e-05,
      "loss": 0.1071,
      "step": 1120
    },
    {
      "epoch": 2.5629965947786606,
      "grad_norm": 0.14272169768810272,
      "learning_rate": 7.224334600760456e-05,
      "loss": 0.1095,
      "step": 1130
    },
    {
      "epoch": 2.5856980703745744,
      "grad_norm": 0.14471879601478577,
      "learning_rate": 6.844106463878328e-05,
      "loss": 0.1094,
      "step": 1140
    },
    {
      "epoch": 2.608399545970488,
      "grad_norm": 0.14543314278125763,
      "learning_rate": 6.463878326996198e-05,
      "loss": 0.1045,
      "step": 1150
    },
    {
      "epoch": 2.608399545970488,
      "eval_loss": 0.10972020775079727,
      "eval_runtime": 219.8328,
      "eval_samples_per_second": 0.91,
      "eval_steps_per_second": 0.455,
      "step": 1150
    },
    {
      "epoch": 2.6311010215664017,
      "grad_norm": 3218.48046875,
      "learning_rate": 6.083650190114068e-05,
      "loss": 0.1031,
      "step": 1160
    },
    {
      "epoch": 2.6538024971623155,
      "grad_norm": 0.15402665734291077,
      "learning_rate": 5.703422053231939e-05,
      "loss": 0.1083,
      "step": 1170
    },
    {
      "epoch": 2.6765039727582294,
      "grad_norm": 0.12117785960435867,
      "learning_rate": 5.3231939163498095e-05,
      "loss": 0.1034,
      "step": 1180
    },
    {
      "epoch": 2.699205448354143,
      "grad_norm": 0.15971869230270386,
      "learning_rate": 4.9429657794676805e-05,
      "loss": 0.1018,
      "step": 1190
    },
    {
      "epoch": 2.7219069239500566,
      "grad_norm": 0.176614910364151,
      "learning_rate": 4.5627376425855515e-05,
      "loss": 0.1029,
      "step": 1200
    },
    {
      "epoch": 2.7219069239500566,
      "eval_loss": 0.10988742858171463,
      "eval_runtime": 219.8843,
      "eval_samples_per_second": 0.91,
      "eval_steps_per_second": 0.455,
      "step": 1200
    },
    {
      "epoch": 2.7446083995459705,
      "grad_norm": 0.13368096947669983,
      "learning_rate": 4.182509505703422e-05,
      "loss": 0.1022,
      "step": 1210
    },
    {
      "epoch": 2.7673098751418843,
      "grad_norm": 0.18552756309509277,
      "learning_rate": 3.802281368821293e-05,
      "loss": 0.1093,
      "step": 1220
    },
    {
      "epoch": 2.7900113507377977,
      "grad_norm": 0.12576653063297272,
      "learning_rate": 3.422053231939164e-05,
      "loss": 0.1089,
      "step": 1230
    },
    {
      "epoch": 2.8127128263337116,
      "grad_norm": 0.156230628490448,
      "learning_rate": 3.041825095057034e-05,
      "loss": 0.1005,
      "step": 1240
    },
    {
      "epoch": 2.8354143019296254,
      "grad_norm": 0.14209876954555511,
      "learning_rate": 2.6615969581749048e-05,
      "loss": 0.1049,
      "step": 1250
    },
    {
      "epoch": 2.8354143019296254,
      "eval_loss": 0.10819864273071289,
      "eval_runtime": 219.473,
      "eval_samples_per_second": 0.911,
      "eval_steps_per_second": 0.456,
      "step": 1250
    },
    {
      "epoch": 2.8581157775255392,
      "grad_norm": 0.1460907757282257,
      "learning_rate": 2.2813688212927758e-05,
      "loss": 0.1066,
      "step": 1260
    },
    {
      "epoch": 2.880817253121453,
      "grad_norm": 0.12771661579608917,
      "learning_rate": 1.9011406844106464e-05,
      "loss": 0.1032,
      "step": 1270
    },
    {
      "epoch": 2.9035187287173665,
      "grad_norm": 0.16184042394161224,
      "learning_rate": 1.520912547528517e-05,
      "loss": 0.1015,
      "step": 1280
    },
    {
      "epoch": 2.9262202043132803,
      "grad_norm": 0.15833236277103424,
      "learning_rate": 1.1406844106463879e-05,
      "loss": 0.1054,
      "step": 1290
    },
    {
      "epoch": 2.948921679909194,
      "grad_norm": 0.1427476406097412,
      "learning_rate": 7.604562737642585e-06,
      "loss": 0.0987,
      "step": 1300
    },
    {
      "epoch": 2.948921679909194,
      "eval_loss": 0.10615785419940948,
      "eval_runtime": 219.4485,
      "eval_samples_per_second": 0.911,
      "eval_steps_per_second": 0.456,
      "step": 1300
    },
    {
      "epoch": 2.9716231555051076,
      "grad_norm": 0.17593209445476532,
      "learning_rate": 3.8022813688212926e-06,
      "loss": 0.1046,
      "step": 1310
    },
    {
      "epoch": 2.9943246311010214,
      "grad_norm": 0.15066806972026825,
      "learning_rate": 0.0,
      "loss": 0.1081,
      "step": 1320
    }
  ],
  "logging_steps": 10,
  "max_steps": 1320,
  "num_input_tokens_seen": 0,
  "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": 8.234027242780262e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}