{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.23424026789451655,
"eval_steps": 500,
"global_step": 2798,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0008371703641691084,
"grad_norm": 6.286955833435059,
"learning_rate": 1.1061797752808989e-06,
"loss": 2.1571,
"step": 10
},
{
"epoch": 0.0016743407283382169,
"grad_norm": 3.6767687797546387,
"learning_rate": 2.2241573033707866e-06,
"loss": 1.9243,
"step": 20
},
{
"epoch": 0.0025115110925073253,
"grad_norm": 2.151350498199463,
"learning_rate": 3.342134831460675e-06,
"loss": 1.7728,
"step": 30
},
{
"epoch": 0.0033486814566764337,
"grad_norm": 1.2491344213485718,
"learning_rate": 4.4601123595505624e-06,
"loss": 1.4703,
"step": 40
},
{
"epoch": 0.004185851820845542,
"grad_norm": 0.9011292457580566,
"learning_rate": 5.5780898876404495e-06,
"loss": 1.2532,
"step": 50
},
{
"epoch": 0.0050230221850146506,
"grad_norm": 1.1828844547271729,
"learning_rate": 6.6960674157303374e-06,
"loss": 1.1652,
"step": 60
},
{
"epoch": 0.0058601925491837585,
"grad_norm": 0.7618897557258606,
"learning_rate": 7.814044943820226e-06,
"loss": 1.1584,
"step": 70
},
{
"epoch": 0.006697362913352867,
"grad_norm": 0.6916522979736328,
"learning_rate": 8.932022471910112e-06,
"loss": 1.0909,
"step": 80
},
{
"epoch": 0.007534533277521975,
"grad_norm": 0.6934717893600464,
"learning_rate": 1.005e-05,
"loss": 1.0744,
"step": 90
},
{
"epoch": 0.008371703641691083,
"grad_norm": 0.7366052865982056,
"learning_rate": 1.1167977528089888e-05,
"loss": 1.0488,
"step": 100
},
{
"epoch": 0.009208874005860193,
"grad_norm": 0.6335578560829163,
"learning_rate": 1.2285955056179776e-05,
"loss": 1.0163,
"step": 110
},
{
"epoch": 0.010046044370029301,
"grad_norm": 0.6413920521736145,
"learning_rate": 1.3403932584269664e-05,
"loss": 1.0387,
"step": 120
},
{
"epoch": 0.010883214734198409,
"grad_norm": 0.652919352054596,
"learning_rate": 1.4521910112359552e-05,
"loss": 1.0123,
"step": 130
},
{
"epoch": 0.011720385098367517,
"grad_norm": 0.6183255314826965,
"learning_rate": 1.563988764044944e-05,
"loss": 1.0209,
"step": 140
},
{
"epoch": 0.012557555462536627,
"grad_norm": 0.5744184851646423,
"learning_rate": 1.6757865168539328e-05,
"loss": 1.0548,
"step": 150
},
{
"epoch": 0.013394725826705735,
"grad_norm": 0.6852168440818787,
"learning_rate": 1.7875842696629214e-05,
"loss": 1.0805,
"step": 160
},
{
"epoch": 0.014231896190874843,
"grad_norm": 0.6165246963500977,
"learning_rate": 1.89938202247191e-05,
"loss": 1.0197,
"step": 170
},
{
"epoch": 0.01506906655504395,
"grad_norm": 0.6286055445671082,
"learning_rate": 2e-05,
"loss": 0.9775,
"step": 180
},
{
"epoch": 0.01590623691921306,
"grad_norm": 0.5891881585121155,
"learning_rate": 2e-05,
"loss": 1.0042,
"step": 190
},
{
"epoch": 0.016743407283382167,
"grad_norm": 0.6101363897323608,
"learning_rate": 2e-05,
"loss": 1.0048,
"step": 200
},
{
"epoch": 0.017580577647551276,
"grad_norm": 0.5848655700683594,
"learning_rate": 2e-05,
"loss": 0.9719,
"step": 210
},
{
"epoch": 0.018417748011720386,
"grad_norm": 0.5625296235084534,
"learning_rate": 2e-05,
"loss": 0.9727,
"step": 220
},
{
"epoch": 0.019254918375889492,
"grad_norm": 0.5747894048690796,
"learning_rate": 2e-05,
"loss": 0.9626,
"step": 230
},
{
"epoch": 0.020092088740058602,
"grad_norm": 0.5566433072090149,
"learning_rate": 2e-05,
"loss": 0.9992,
"step": 240
},
{
"epoch": 0.020929259104227712,
"grad_norm": 0.6630275249481201,
"learning_rate": 2e-05,
"loss": 0.978,
"step": 250
},
{
"epoch": 0.021766429468396818,
"grad_norm": 0.5642217993736267,
"learning_rate": 2e-05,
"loss": 0.9639,
"step": 260
},
{
"epoch": 0.022603599832565928,
"grad_norm": 0.597459614276886,
"learning_rate": 2e-05,
"loss": 0.9712,
"step": 270
},
{
"epoch": 0.023440770196735034,
"grad_norm": 0.6050856709480286,
"learning_rate": 2e-05,
"loss": 0.9895,
"step": 280
},
{
"epoch": 0.024277940560904144,
"grad_norm": 0.5888883471488953,
"learning_rate": 2e-05,
"loss": 0.9602,
"step": 290
},
{
"epoch": 0.025115110925073254,
"grad_norm": 0.5481868982315063,
"learning_rate": 2e-05,
"loss": 0.9562,
"step": 300
},
{
"epoch": 0.02595228128924236,
"grad_norm": 0.543234646320343,
"learning_rate": 2e-05,
"loss": 0.9804,
"step": 310
},
{
"epoch": 0.02678945165341147,
"grad_norm": 0.5965615510940552,
"learning_rate": 2e-05,
"loss": 0.962,
"step": 320
},
{
"epoch": 0.02762662201758058,
"grad_norm": 0.5193302631378174,
"learning_rate": 2e-05,
"loss": 0.9852,
"step": 330
},
{
"epoch": 0.028463792381749686,
"grad_norm": 0.524551510810852,
"learning_rate": 2e-05,
"loss": 0.9865,
"step": 340
},
{
"epoch": 0.029300962745918795,
"grad_norm": 0.5498046875,
"learning_rate": 2e-05,
"loss": 0.9505,
"step": 350
},
{
"epoch": 0.0301381331100879,
"grad_norm": 0.5638454556465149,
"learning_rate": 2e-05,
"loss": 0.9537,
"step": 360
},
{
"epoch": 0.03097530347425701,
"grad_norm": 0.5428140759468079,
"learning_rate": 2e-05,
"loss": 0.9562,
"step": 370
},
{
"epoch": 0.03181247383842612,
"grad_norm": 0.5936139225959778,
"learning_rate": 2e-05,
"loss": 0.9566,
"step": 380
},
{
"epoch": 0.03264964420259523,
"grad_norm": 0.5149725079536438,
"learning_rate": 2e-05,
"loss": 0.9279,
"step": 390
},
{
"epoch": 0.033486814566764334,
"grad_norm": 0.5177335143089294,
"learning_rate": 2e-05,
"loss": 0.9404,
"step": 400
},
{
"epoch": 0.03432398493093344,
"grad_norm": 0.5363324284553528,
"learning_rate": 2e-05,
"loss": 0.9536,
"step": 410
},
{
"epoch": 0.03516115529510255,
"grad_norm": 0.5618890523910522,
"learning_rate": 2e-05,
"loss": 0.9827,
"step": 420
},
{
"epoch": 0.03599832565927166,
"grad_norm": 0.5098859667778015,
"learning_rate": 2e-05,
"loss": 0.9344,
"step": 430
},
{
"epoch": 0.03683549602344077,
"grad_norm": 0.5013912320137024,
"learning_rate": 2e-05,
"loss": 0.9398,
"step": 440
},
{
"epoch": 0.037672666387609875,
"grad_norm": 0.4910331666469574,
"learning_rate": 2e-05,
"loss": 0.9394,
"step": 450
},
{
"epoch": 0.038509836751778985,
"grad_norm": 0.5443107485771179,
"learning_rate": 2e-05,
"loss": 0.9467,
"step": 460
},
{
"epoch": 0.039347007115948095,
"grad_norm": 0.48179903626441956,
"learning_rate": 2e-05,
"loss": 0.9304,
"step": 470
},
{
"epoch": 0.040184177480117204,
"grad_norm": 0.5266996026039124,
"learning_rate": 2e-05,
"loss": 0.9093,
"step": 480
},
{
"epoch": 0.041021347844286314,
"grad_norm": 0.5182468295097351,
"learning_rate": 2e-05,
"loss": 0.933,
"step": 490
},
{
"epoch": 0.041858518208455424,
"grad_norm": 0.5562992691993713,
"learning_rate": 2e-05,
"loss": 0.8997,
"step": 500
},
{
"epoch": 0.04269568857262453,
"grad_norm": 0.5871270895004272,
"learning_rate": 2e-05,
"loss": 0.9345,
"step": 510
},
{
"epoch": 0.043532858936793636,
"grad_norm": 0.5355167984962463,
"learning_rate": 2e-05,
"loss": 0.9235,
"step": 520
},
{
"epoch": 0.044370029300962746,
"grad_norm": 0.508417546749115,
"learning_rate": 2e-05,
"loss": 0.9142,
"step": 530
},
{
"epoch": 0.045207199665131856,
"grad_norm": 0.5056772828102112,
"learning_rate": 2e-05,
"loss": 0.9211,
"step": 540
},
{
"epoch": 0.046044370029300966,
"grad_norm": 0.5066829919815063,
"learning_rate": 2e-05,
"loss": 0.9124,
"step": 550
},
{
"epoch": 0.04688154039347007,
"grad_norm": 0.5150319933891296,
"learning_rate": 2e-05,
"loss": 0.8999,
"step": 560
},
{
"epoch": 0.04771871075763918,
"grad_norm": 0.5607603192329407,
"learning_rate": 2e-05,
"loss": 0.9378,
"step": 570
},
{
"epoch": 0.04855588112180829,
"grad_norm": 0.5025616884231567,
"learning_rate": 2e-05,
"loss": 0.913,
"step": 580
},
{
"epoch": 0.0493930514859774,
"grad_norm": 0.4901517629623413,
"learning_rate": 2e-05,
"loss": 0.936,
"step": 590
},
{
"epoch": 0.05023022185014651,
"grad_norm": 0.5197919011116028,
"learning_rate": 2e-05,
"loss": 0.9501,
"step": 600
},
{
"epoch": 0.05106739221431561,
"grad_norm": 0.5028531551361084,
"learning_rate": 2e-05,
"loss": 0.9094,
"step": 610
},
{
"epoch": 0.05190456257848472,
"grad_norm": 0.48607340455055237,
"learning_rate": 2e-05,
"loss": 0.9494,
"step": 620
},
{
"epoch": 0.05274173294265383,
"grad_norm": 0.5188357830047607,
"learning_rate": 2e-05,
"loss": 0.9326,
"step": 630
},
{
"epoch": 0.05357890330682294,
"grad_norm": 0.5137494802474976,
"learning_rate": 2e-05,
"loss": 0.9286,
"step": 640
},
{
"epoch": 0.05441607367099205,
"grad_norm": 0.49051663279533386,
"learning_rate": 2e-05,
"loss": 0.9201,
"step": 650
},
{
"epoch": 0.05525324403516116,
"grad_norm": 0.5025955438613892,
"learning_rate": 2e-05,
"loss": 0.9509,
"step": 660
},
{
"epoch": 0.05609041439933026,
"grad_norm": 0.4561798870563507,
"learning_rate": 2e-05,
"loss": 0.902,
"step": 670
},
{
"epoch": 0.05692758476349937,
"grad_norm": 0.5147539973258972,
"learning_rate": 2e-05,
"loss": 0.8891,
"step": 680
},
{
"epoch": 0.05776475512766848,
"grad_norm": 0.512950599193573,
"learning_rate": 2e-05,
"loss": 0.9146,
"step": 690
},
{
"epoch": 0.05860192549183759,
"grad_norm": 0.5343301892280579,
"learning_rate": 2e-05,
"loss": 0.9434,
"step": 700
},
{
"epoch": 0.0594390958560067,
"grad_norm": 0.5037513375282288,
"learning_rate": 2e-05,
"loss": 0.9396,
"step": 710
},
{
"epoch": 0.0602762662201758,
"grad_norm": 0.5113139748573303,
"learning_rate": 2e-05,
"loss": 0.9311,
"step": 720
},
{
"epoch": 0.06111343658434491,
"grad_norm": 0.49999576807022095,
"learning_rate": 2e-05,
"loss": 0.8928,
"step": 730
},
{
"epoch": 0.06195060694851402,
"grad_norm": 0.5156519412994385,
"learning_rate": 2e-05,
"loss": 0.9134,
"step": 740
},
{
"epoch": 0.06278777731268313,
"grad_norm": 0.5189371705055237,
"learning_rate": 2e-05,
"loss": 0.9147,
"step": 750
},
{
"epoch": 0.06362494767685224,
"grad_norm": 0.5053024291992188,
"learning_rate": 2e-05,
"loss": 0.8988,
"step": 760
},
{
"epoch": 0.06446211804102135,
"grad_norm": 0.49766141176223755,
"learning_rate": 2e-05,
"loss": 0.941,
"step": 770
},
{
"epoch": 0.06529928840519046,
"grad_norm": 0.50629061460495,
"learning_rate": 2e-05,
"loss": 0.9235,
"step": 780
},
{
"epoch": 0.06613645876935957,
"grad_norm": 0.4884129464626312,
"learning_rate": 2e-05,
"loss": 0.911,
"step": 790
},
{
"epoch": 0.06697362913352867,
"grad_norm": 0.5056248307228088,
"learning_rate": 2e-05,
"loss": 0.9273,
"step": 800
},
{
"epoch": 0.06781079949769778,
"grad_norm": 0.47344326972961426,
"learning_rate": 2e-05,
"loss": 0.9276,
"step": 810
},
{
"epoch": 0.06864796986186689,
"grad_norm": 0.49335843324661255,
"learning_rate": 2e-05,
"loss": 0.9277,
"step": 820
},
{
"epoch": 0.069485140226036,
"grad_norm": 0.5105158090591431,
"learning_rate": 2e-05,
"loss": 0.9272,
"step": 830
},
{
"epoch": 0.0703223105902051,
"grad_norm": 0.5000097155570984,
"learning_rate": 2e-05,
"loss": 0.9213,
"step": 840
},
{
"epoch": 0.07115948095437422,
"grad_norm": 0.4862711429595947,
"learning_rate": 2e-05,
"loss": 0.9243,
"step": 850
},
{
"epoch": 0.07199665131854333,
"grad_norm": 0.4822566509246826,
"learning_rate": 2e-05,
"loss": 0.9318,
"step": 860
},
{
"epoch": 0.07283382168271244,
"grad_norm": 0.4932926595211029,
"learning_rate": 2e-05,
"loss": 0.889,
"step": 870
},
{
"epoch": 0.07367099204688154,
"grad_norm": 0.4769861400127411,
"learning_rate": 2e-05,
"loss": 0.9086,
"step": 880
},
{
"epoch": 0.07450816241105065,
"grad_norm": 0.4864020049571991,
"learning_rate": 2e-05,
"loss": 0.9072,
"step": 890
},
{
"epoch": 0.07534533277521975,
"grad_norm": 0.49218103289604187,
"learning_rate": 2e-05,
"loss": 0.9038,
"step": 900
},
{
"epoch": 0.07618250313938886,
"grad_norm": 0.5060418844223022,
"learning_rate": 2e-05,
"loss": 0.9313,
"step": 910
},
{
"epoch": 0.07701967350355797,
"grad_norm": 0.4857514500617981,
"learning_rate": 2e-05,
"loss": 0.8917,
"step": 920
},
{
"epoch": 0.07785684386772708,
"grad_norm": 0.5140605568885803,
"learning_rate": 2e-05,
"loss": 0.9006,
"step": 930
},
{
"epoch": 0.07869401423189619,
"grad_norm": 0.4838702380657196,
"learning_rate": 2e-05,
"loss": 0.9029,
"step": 940
},
{
"epoch": 0.0795311845960653,
"grad_norm": 0.49060988426208496,
"learning_rate": 2e-05,
"loss": 0.9136,
"step": 950
},
{
"epoch": 0.08036835496023441,
"grad_norm": 0.4825526773929596,
"learning_rate": 2e-05,
"loss": 0.9076,
"step": 960
},
{
"epoch": 0.08120552532440352,
"grad_norm": 0.4880685806274414,
"learning_rate": 2e-05,
"loss": 0.8999,
"step": 970
},
{
"epoch": 0.08204269568857263,
"grad_norm": 0.46251583099365234,
"learning_rate": 2e-05,
"loss": 0.8884,
"step": 980
},
{
"epoch": 0.08287986605274174,
"grad_norm": 0.5066401958465576,
"learning_rate": 2e-05,
"loss": 0.916,
"step": 990
},
{
"epoch": 0.08371703641691085,
"grad_norm": 0.47283968329429626,
"learning_rate": 2e-05,
"loss": 0.8951,
"step": 1000
},
{
"epoch": 0.08455420678107994,
"grad_norm": 0.5120212435722351,
"learning_rate": 2e-05,
"loss": 0.9262,
"step": 1010
},
{
"epoch": 0.08539137714524905,
"grad_norm": 0.4767346978187561,
"learning_rate": 2e-05,
"loss": 0.9123,
"step": 1020
},
{
"epoch": 0.08622854750941816,
"grad_norm": 0.5002844929695129,
"learning_rate": 2e-05,
"loss": 0.9067,
"step": 1030
},
{
"epoch": 0.08706571787358727,
"grad_norm": 0.4847468435764313,
"learning_rate": 2e-05,
"loss": 0.8907,
"step": 1040
},
{
"epoch": 0.08790288823775638,
"grad_norm": 0.4965667426586151,
"learning_rate": 2e-05,
"loss": 0.8953,
"step": 1050
},
{
"epoch": 0.08874005860192549,
"grad_norm": 0.46984976530075073,
"learning_rate": 2e-05,
"loss": 0.8958,
"step": 1060
},
{
"epoch": 0.0895772289660946,
"grad_norm": 0.44189727306365967,
"learning_rate": 2e-05,
"loss": 0.8899,
"step": 1070
},
{
"epoch": 0.09041439933026371,
"grad_norm": 0.4697335660457611,
"learning_rate": 2e-05,
"loss": 0.8977,
"step": 1080
},
{
"epoch": 0.09125156969443282,
"grad_norm": 0.4707675576210022,
"learning_rate": 2e-05,
"loss": 0.9103,
"step": 1090
},
{
"epoch": 0.09208874005860193,
"grad_norm": 0.4781976640224457,
"learning_rate": 2e-05,
"loss": 0.8997,
"step": 1100
},
{
"epoch": 0.09292591042277103,
"grad_norm": 0.45466241240501404,
"learning_rate": 2e-05,
"loss": 0.8989,
"step": 1110
},
{
"epoch": 0.09376308078694014,
"grad_norm": 0.45188242197036743,
"learning_rate": 2e-05,
"loss": 0.9157,
"step": 1120
},
{
"epoch": 0.09460025115110925,
"grad_norm": 0.48571550846099854,
"learning_rate": 2e-05,
"loss": 0.8939,
"step": 1130
},
{
"epoch": 0.09543742151527836,
"grad_norm": 0.5890725255012512,
"learning_rate": 2e-05,
"loss": 0.9035,
"step": 1140
},
{
"epoch": 0.09627459187944747,
"grad_norm": 0.4557766914367676,
"learning_rate": 2e-05,
"loss": 0.916,
"step": 1150
},
{
"epoch": 0.09711176224361658,
"grad_norm": 0.4784591495990753,
"learning_rate": 2e-05,
"loss": 0.8826,
"step": 1160
},
{
"epoch": 0.09794893260778569,
"grad_norm": 0.501518189907074,
"learning_rate": 2e-05,
"loss": 0.8908,
"step": 1170
},
{
"epoch": 0.0987861029719548,
"grad_norm": 0.4712284803390503,
"learning_rate": 2e-05,
"loss": 0.8822,
"step": 1180
},
{
"epoch": 0.0996232733361239,
"grad_norm": 0.48043906688690186,
"learning_rate": 2e-05,
"loss": 0.9054,
"step": 1190
},
{
"epoch": 0.10046044370029301,
"grad_norm": 0.5000447034835815,
"learning_rate": 2e-05,
"loss": 0.8955,
"step": 1200
},
{
"epoch": 0.10129761406446212,
"grad_norm": 0.4876522123813629,
"learning_rate": 2e-05,
"loss": 0.9194,
"step": 1210
},
{
"epoch": 0.10213478442863122,
"grad_norm": 0.47112202644348145,
"learning_rate": 2e-05,
"loss": 0.9175,
"step": 1220
},
{
"epoch": 0.10297195479280033,
"grad_norm": 0.4968307614326477,
"learning_rate": 2e-05,
"loss": 0.9004,
"step": 1230
},
{
"epoch": 0.10380912515696944,
"grad_norm": 0.4805414080619812,
"learning_rate": 2e-05,
"loss": 0.8862,
"step": 1240
},
{
"epoch": 0.10464629552113855,
"grad_norm": 0.4705885648727417,
"learning_rate": 2e-05,
"loss": 0.894,
"step": 1250
},
{
"epoch": 0.10548346588530766,
"grad_norm": 0.5161804556846619,
"learning_rate": 2e-05,
"loss": 0.9077,
"step": 1260
},
{
"epoch": 0.10632063624947677,
"grad_norm": 0.4699770212173462,
"learning_rate": 2e-05,
"loss": 0.8988,
"step": 1270
},
{
"epoch": 0.10715780661364588,
"grad_norm": 0.45899173617362976,
"learning_rate": 2e-05,
"loss": 0.8799,
"step": 1280
},
{
"epoch": 0.10799497697781499,
"grad_norm": 0.4808332622051239,
"learning_rate": 2e-05,
"loss": 0.9132,
"step": 1290
},
{
"epoch": 0.1088321473419841,
"grad_norm": 0.46036213636398315,
"learning_rate": 2e-05,
"loss": 0.8565,
"step": 1300
},
{
"epoch": 0.10966931770615321,
"grad_norm": 0.46063363552093506,
"learning_rate": 2e-05,
"loss": 0.9342,
"step": 1310
},
{
"epoch": 0.11050648807032232,
"grad_norm": 0.4611421525478363,
"learning_rate": 2e-05,
"loss": 0.8941,
"step": 1320
},
{
"epoch": 0.11134365843449141,
"grad_norm": 0.4850688576698303,
"learning_rate": 2e-05,
"loss": 0.8741,
"step": 1330
},
{
"epoch": 0.11218082879866052,
"grad_norm": 0.4596725404262543,
"learning_rate": 2e-05,
"loss": 0.8929,
"step": 1340
},
{
"epoch": 0.11301799916282963,
"grad_norm": 0.46708545088768005,
"learning_rate": 2e-05,
"loss": 0.8806,
"step": 1350
},
{
"epoch": 0.11385516952699874,
"grad_norm": 0.46161842346191406,
"learning_rate": 2e-05,
"loss": 0.8986,
"step": 1360
},
{
"epoch": 0.11469233989116785,
"grad_norm": 0.4660196602344513,
"learning_rate": 2e-05,
"loss": 0.8935,
"step": 1370
},
{
"epoch": 0.11552951025533696,
"grad_norm": 0.4572381377220154,
"learning_rate": 2e-05,
"loss": 0.8861,
"step": 1380
},
{
"epoch": 0.11636668061950607,
"grad_norm": 0.45686715841293335,
"learning_rate": 2e-05,
"loss": 0.8809,
"step": 1390
},
{
"epoch": 0.11720385098367518,
"grad_norm": 0.4713088572025299,
"learning_rate": 2e-05,
"loss": 0.8483,
"step": 1400
},
{
"epoch": 0.11804102134784429,
"grad_norm": 0.4591504633426666,
"learning_rate": 2e-05,
"loss": 0.8993,
"step": 1410
},
{
"epoch": 0.1188781917120134,
"grad_norm": 0.4753212034702301,
"learning_rate": 2e-05,
"loss": 0.8871,
"step": 1420
},
{
"epoch": 0.1197153620761825,
"grad_norm": 0.4820215404033661,
"learning_rate": 2e-05,
"loss": 0.8849,
"step": 1430
},
{
"epoch": 0.1205525324403516,
"grad_norm": 0.46577829122543335,
"learning_rate": 2e-05,
"loss": 0.8699,
"step": 1440
},
{
"epoch": 0.12138970280452072,
"grad_norm": 0.46643346548080444,
"learning_rate": 2e-05,
"loss": 0.9081,
"step": 1450
},
{
"epoch": 0.12222687316868983,
"grad_norm": 0.4909195899963379,
"learning_rate": 2e-05,
"loss": 0.9072,
"step": 1460
},
{
"epoch": 0.12306404353285894,
"grad_norm": 0.4641784131526947,
"learning_rate": 2e-05,
"loss": 0.8778,
"step": 1470
},
{
"epoch": 0.12390121389702805,
"grad_norm": 0.47702017426490784,
"learning_rate": 2e-05,
"loss": 0.8771,
"step": 1480
},
{
"epoch": 0.12473838426119715,
"grad_norm": 0.45714545249938965,
"learning_rate": 2e-05,
"loss": 0.8859,
"step": 1490
},
{
"epoch": 0.12557555462536626,
"grad_norm": 0.45355841517448425,
"learning_rate": 2e-05,
"loss": 0.8945,
"step": 1500
},
{
"epoch": 0.12641272498953537,
"grad_norm": 0.584877610206604,
"learning_rate": 2e-05,
"loss": 0.8901,
"step": 1510
},
{
"epoch": 0.12724989535370448,
"grad_norm": 0.5109133124351501,
"learning_rate": 2e-05,
"loss": 0.8709,
"step": 1520
},
{
"epoch": 0.1280870657178736,
"grad_norm": 0.4634550213813782,
"learning_rate": 2e-05,
"loss": 0.9303,
"step": 1530
},
{
"epoch": 0.1289242360820427,
"grad_norm": 0.46686896681785583,
"learning_rate": 2e-05,
"loss": 0.8873,
"step": 1540
},
{
"epoch": 0.1297614064462118,
"grad_norm": 0.46461957693099976,
"learning_rate": 2e-05,
"loss": 0.9004,
"step": 1550
},
{
"epoch": 0.13059857681038092,
"grad_norm": 0.4640693664550781,
"learning_rate": 2e-05,
"loss": 0.9212,
"step": 1560
},
{
"epoch": 0.13143574717455003,
"grad_norm": 0.45362356305122375,
"learning_rate": 2e-05,
"loss": 0.8629,
"step": 1570
},
{
"epoch": 0.13227291753871914,
"grad_norm": 0.4508582055568695,
"learning_rate": 2e-05,
"loss": 0.862,
"step": 1580
},
{
"epoch": 0.13311008790288822,
"grad_norm": 0.4616556465625763,
"learning_rate": 2e-05,
"loss": 0.9102,
"step": 1590
},
{
"epoch": 0.13394725826705733,
"grad_norm": 0.47913822531700134,
"learning_rate": 2e-05,
"loss": 0.8826,
"step": 1600
},
{
"epoch": 0.13478442863122644,
"grad_norm": 0.47434917092323303,
"learning_rate": 2e-05,
"loss": 0.8941,
"step": 1610
},
{
"epoch": 0.13562159899539555,
"grad_norm": 0.4437176585197449,
"learning_rate": 2e-05,
"loss": 0.8694,
"step": 1620
},
{
"epoch": 0.13645876935956466,
"grad_norm": 0.46696802973747253,
"learning_rate": 2e-05,
"loss": 0.86,
"step": 1630
},
{
"epoch": 0.13729593972373377,
"grad_norm": 0.4766770899295807,
"learning_rate": 2e-05,
"loss": 0.9089,
"step": 1640
},
{
"epoch": 0.13813311008790288,
"grad_norm": 0.4405345916748047,
"learning_rate": 2e-05,
"loss": 0.8723,
"step": 1650
},
{
"epoch": 0.138970280452072,
"grad_norm": 0.4427041709423065,
"learning_rate": 2e-05,
"loss": 0.8725,
"step": 1660
},
{
"epoch": 0.1398074508162411,
"grad_norm": 0.4577621817588806,
"learning_rate": 2e-05,
"loss": 0.8701,
"step": 1670
},
{
"epoch": 0.1406446211804102,
"grad_norm": 0.47423696517944336,
"learning_rate": 2e-05,
"loss": 0.8669,
"step": 1680
},
{
"epoch": 0.14148179154457932,
"grad_norm": 0.44417867064476013,
"learning_rate": 2e-05,
"loss": 0.8693,
"step": 1690
},
{
"epoch": 0.14231896190874843,
"grad_norm": 0.45095181465148926,
"learning_rate": 2e-05,
"loss": 0.8832,
"step": 1700
},
{
"epoch": 0.14315613227291754,
"grad_norm": 0.4428626000881195,
"learning_rate": 2e-05,
"loss": 0.8731,
"step": 1710
},
{
"epoch": 0.14399330263708665,
"grad_norm": 0.47432005405426025,
"learning_rate": 2e-05,
"loss": 0.8844,
"step": 1720
},
{
"epoch": 0.14483047300125576,
"grad_norm": 0.43629175424575806,
"learning_rate": 2e-05,
"loss": 0.8358,
"step": 1730
},
{
"epoch": 0.14566764336542487,
"grad_norm": 0.4563296437263489,
"learning_rate": 2e-05,
"loss": 0.8826,
"step": 1740
},
{
"epoch": 0.14650481372959398,
"grad_norm": 0.47259217500686646,
"learning_rate": 2e-05,
"loss": 0.8889,
"step": 1750
},
{
"epoch": 0.1473419840937631,
"grad_norm": 0.4536290764808655,
"learning_rate": 2e-05,
"loss": 0.8768,
"step": 1760
},
{
"epoch": 0.1481791544579322,
"grad_norm": 0.45183804631233215,
"learning_rate": 2e-05,
"loss": 0.8752,
"step": 1770
},
{
"epoch": 0.1490163248221013,
"grad_norm": 0.46316322684288025,
"learning_rate": 2e-05,
"loss": 0.8614,
"step": 1780
},
{
"epoch": 0.14985349518627042,
"grad_norm": 0.4563836455345154,
"learning_rate": 2e-05,
"loss": 0.8634,
"step": 1790
},
{
"epoch": 0.1506906655504395,
"grad_norm": 0.4589375853538513,
"learning_rate": 2e-05,
"loss": 0.8864,
"step": 1800
},
{
"epoch": 0.1515278359146086,
"grad_norm": 0.4381108582019806,
"learning_rate": 2e-05,
"loss": 0.8911,
"step": 1810
},
{
"epoch": 0.15236500627877772,
"grad_norm": 0.4347422122955322,
"learning_rate": 2e-05,
"loss": 0.8715,
"step": 1820
},
{
"epoch": 0.15320217664294683,
"grad_norm": 0.4662458598613739,
"learning_rate": 2e-05,
"loss": 0.8749,
"step": 1830
},
{
"epoch": 0.15403934700711594,
"grad_norm": 0.4737149178981781,
"learning_rate": 2e-05,
"loss": 0.8617,
"step": 1840
},
{
"epoch": 0.15487651737128505,
"grad_norm": 0.4526223838329315,
"learning_rate": 2e-05,
"loss": 0.8528,
"step": 1850
},
{
"epoch": 0.15571368773545416,
"grad_norm": 0.44724318385124207,
"learning_rate": 2e-05,
"loss": 0.8786,
"step": 1860
},
{
"epoch": 0.15655085809962327,
"grad_norm": 0.47638562321662903,
"learning_rate": 2e-05,
"loss": 0.8774,
"step": 1870
},
{
"epoch": 0.15738802846379238,
"grad_norm": 0.43727222084999084,
"learning_rate": 2e-05,
"loss": 0.8815,
"step": 1880
},
{
"epoch": 0.1582251988279615,
"grad_norm": 0.49028047919273376,
"learning_rate": 2e-05,
"loss": 0.8807,
"step": 1890
},
{
"epoch": 0.1590623691921306,
"grad_norm": 0.4596083462238312,
"learning_rate": 2e-05,
"loss": 0.9151,
"step": 1900
},
{
"epoch": 0.1598995395562997,
"grad_norm": 0.441745400428772,
"learning_rate": 2e-05,
"loss": 0.8605,
"step": 1910
},
{
"epoch": 0.16073670992046882,
"grad_norm": 0.4500328600406647,
"learning_rate": 2e-05,
"loss": 0.8636,
"step": 1920
},
{
"epoch": 0.16157388028463793,
"grad_norm": 0.4569918215274811,
"learning_rate": 2e-05,
"loss": 0.8626,
"step": 1930
},
{
"epoch": 0.16241105064880704,
"grad_norm": 0.6225832104682922,
"learning_rate": 2e-05,
"loss": 0.8611,
"step": 1940
},
{
"epoch": 0.16324822101297615,
"grad_norm": 0.5002962350845337,
"learning_rate": 2e-05,
"loss": 0.8811,
"step": 1950
},
{
"epoch": 0.16408539137714526,
"grad_norm": 0.45770740509033203,
"learning_rate": 2e-05,
"loss": 0.8823,
"step": 1960
},
{
"epoch": 0.16492256174131437,
"grad_norm": 0.456687331199646,
"learning_rate": 2e-05,
"loss": 0.8713,
"step": 1970
},
{
"epoch": 0.16575973210548348,
"grad_norm": 0.4765065610408783,
"learning_rate": 2e-05,
"loss": 0.8961,
"step": 1980
},
{
"epoch": 0.16659690246965259,
"grad_norm": 0.44931989908218384,
"learning_rate": 2e-05,
"loss": 0.8734,
"step": 1990
},
{
"epoch": 0.1674340728338217,
"grad_norm": 0.4341471791267395,
"learning_rate": 2e-05,
"loss": 0.8465,
"step": 2000
},
{
"epoch": 0.16827124319799078,
"grad_norm": 0.4397622346878052,
"learning_rate": 2e-05,
"loss": 0.8663,
"step": 2010
},
{
"epoch": 0.1691084135621599,
"grad_norm": 0.4476166367530823,
"learning_rate": 2e-05,
"loss": 0.8835,
"step": 2020
},
{
"epoch": 0.169945583926329,
"grad_norm": 0.4278470277786255,
"learning_rate": 2e-05,
"loss": 0.8695,
"step": 2030
},
{
"epoch": 0.1707827542904981,
"grad_norm": 0.45106714963912964,
"learning_rate": 2e-05,
"loss": 0.8724,
"step": 2040
},
{
"epoch": 0.17161992465466722,
"grad_norm": 0.44101276993751526,
"learning_rate": 2e-05,
"loss": 0.8607,
"step": 2050
},
{
"epoch": 0.17245709501883633,
"grad_norm": 0.4804248511791229,
"learning_rate": 2e-05,
"loss": 0.8921,
"step": 2060
},
{
"epoch": 0.17329426538300544,
"grad_norm": 0.4646872878074646,
"learning_rate": 2e-05,
"loss": 0.9011,
"step": 2070
},
{
"epoch": 0.17413143574717455,
"grad_norm": 0.46392732858657837,
"learning_rate": 2e-05,
"loss": 0.8636,
"step": 2080
},
{
"epoch": 0.17496860611134366,
"grad_norm": 0.4388207495212555,
"learning_rate": 2e-05,
"loss": 0.8762,
"step": 2090
},
{
"epoch": 0.17580577647551276,
"grad_norm": 0.4509705901145935,
"learning_rate": 2e-05,
"loss": 0.8428,
"step": 2100
},
{
"epoch": 0.17664294683968187,
"grad_norm": 0.43261757493019104,
"learning_rate": 2e-05,
"loss": 0.8458,
"step": 2110
},
{
"epoch": 0.17748011720385098,
"grad_norm": 0.44039949774742126,
"learning_rate": 2e-05,
"loss": 0.8654,
"step": 2120
},
{
"epoch": 0.1783172875680201,
"grad_norm": 0.44489777088165283,
"learning_rate": 2e-05,
"loss": 0.8619,
"step": 2130
},
{
"epoch": 0.1791544579321892,
"grad_norm": 0.4366418421268463,
"learning_rate": 2e-05,
"loss": 0.8816,
"step": 2140
},
{
"epoch": 0.1799916282963583,
"grad_norm": 0.4640413522720337,
"learning_rate": 2e-05,
"loss": 0.8647,
"step": 2150
},
{
"epoch": 0.18082879866052742,
"grad_norm": 0.4382632374763489,
"learning_rate": 2e-05,
"loss": 0.8677,
"step": 2160
},
{
"epoch": 0.18166596902469653,
"grad_norm": 0.4480655789375305,
"learning_rate": 2e-05,
"loss": 0.8655,
"step": 2170
},
{
"epoch": 0.18250313938886564,
"grad_norm": 0.45486730337142944,
"learning_rate": 2e-05,
"loss": 0.8733,
"step": 2180
},
{
"epoch": 0.18334030975303475,
"grad_norm": 0.45164886116981506,
"learning_rate": 2e-05,
"loss": 0.8742,
"step": 2190
},
{
"epoch": 0.18417748011720386,
"grad_norm": 0.430537611246109,
"learning_rate": 2e-05,
"loss": 0.8707,
"step": 2200
},
{
"epoch": 0.18501465048137297,
"grad_norm": 0.48182976245880127,
"learning_rate": 2e-05,
"loss": 0.8398,
"step": 2210
},
{
"epoch": 0.18585182084554205,
"grad_norm": 0.44728755950927734,
"learning_rate": 2e-05,
"loss": 0.8579,
"step": 2220
},
{
"epoch": 0.18668899120971116,
"grad_norm": 0.438927561044693,
"learning_rate": 2e-05,
"loss": 0.8746,
"step": 2230
},
{
"epoch": 0.18752616157388027,
"grad_norm": 0.4833535850048065,
"learning_rate": 2e-05,
"loss": 0.8615,
"step": 2240
},
{
"epoch": 0.18836333193804938,
"grad_norm": 0.4395700991153717,
"learning_rate": 2e-05,
"loss": 0.8502,
"step": 2250
},
{
"epoch": 0.1892005023022185,
"grad_norm": 0.5781416296958923,
"learning_rate": 2e-05,
"loss": 0.8625,
"step": 2260
},
{
"epoch": 0.1900376726663876,
"grad_norm": 0.42882025241851807,
"learning_rate": 2e-05,
"loss": 0.8533,
"step": 2270
},
{
"epoch": 0.1908748430305567,
"grad_norm": 0.44762805104255676,
"learning_rate": 2e-05,
"loss": 0.8412,
"step": 2280
},
{
"epoch": 0.19171201339472582,
"grad_norm": 0.45068269968032837,
"learning_rate": 2e-05,
"loss": 0.8588,
"step": 2290
},
{
"epoch": 0.19254918375889493,
"grad_norm": 0.437988817691803,
"learning_rate": 2e-05,
"loss": 0.883,
"step": 2300
},
{
"epoch": 0.19338635412306404,
"grad_norm": 0.448384165763855,
"learning_rate": 2e-05,
"loss": 0.8528,
"step": 2310
},
{
"epoch": 0.19422352448723315,
"grad_norm": 0.474157452583313,
"learning_rate": 2e-05,
"loss": 0.8593,
"step": 2320
},
{
"epoch": 0.19506069485140226,
"grad_norm": 0.45292016863822937,
"learning_rate": 2e-05,
"loss": 0.8254,
"step": 2330
},
{
"epoch": 0.19589786521557137,
"grad_norm": 0.43578028678894043,
"learning_rate": 2e-05,
"loss": 0.8503,
"step": 2340
},
{
"epoch": 0.19673503557974048,
"grad_norm": 0.43714937567710876,
"learning_rate": 2e-05,
"loss": 0.8308,
"step": 2350
},
{
"epoch": 0.1975722059439096,
"grad_norm": 0.4639517068862915,
"learning_rate": 2e-05,
"loss": 0.8762,
"step": 2360
},
{
"epoch": 0.1984093763080787,
"grad_norm": 0.44235238432884216,
"learning_rate": 2e-05,
"loss": 0.8547,
"step": 2370
},
{
"epoch": 0.1992465466722478,
"grad_norm": 0.44393929839134216,
"learning_rate": 2e-05,
"loss": 0.8522,
"step": 2380
},
{
"epoch": 0.20008371703641692,
"grad_norm": 0.46399083733558655,
"learning_rate": 2e-05,
"loss": 0.871,
"step": 2390
},
{
"epoch": 0.20092088740058603,
"grad_norm": 0.43202951550483704,
"learning_rate": 2e-05,
"loss": 0.8465,
"step": 2400
},
{
"epoch": 0.20175805776475514,
"grad_norm": 0.44708123803138733,
"learning_rate": 2e-05,
"loss": 0.8665,
"step": 2410
},
{
"epoch": 0.20259522812892425,
"grad_norm": 0.4400118291378021,
"learning_rate": 2e-05,
"loss": 0.8524,
"step": 2420
},
{
"epoch": 0.20343239849309336,
"grad_norm": 0.42689865827560425,
"learning_rate": 2e-05,
"loss": 0.8455,
"step": 2430
},
{
"epoch": 0.20426956885726244,
"grad_norm": 0.45444467663764954,
"learning_rate": 2e-05,
"loss": 0.8492,
"step": 2440
},
{
"epoch": 0.20510673922143155,
"grad_norm": 0.47486284375190735,
"learning_rate": 2e-05,
"loss": 0.8689,
"step": 2450
},
{
"epoch": 0.20594390958560066,
"grad_norm": 0.4352690875530243,
"learning_rate": 2e-05,
"loss": 0.8516,
"step": 2460
},
{
"epoch": 0.20678107994976977,
"grad_norm": 0.4403368830680847,
"learning_rate": 2e-05,
"loss": 0.847,
"step": 2470
},
{
"epoch": 0.20761825031393888,
"grad_norm": 0.44160476326942444,
"learning_rate": 2e-05,
"loss": 0.8681,
"step": 2480
},
{
"epoch": 0.208455420678108,
"grad_norm": 0.43098336458206177,
"learning_rate": 2e-05,
"loss": 0.8433,
"step": 2490
},
{
"epoch": 0.2092925910422771,
"grad_norm": 0.46148884296417236,
"learning_rate": 2e-05,
"loss": 0.8577,
"step": 2500
},
{
"epoch": 0.2101297614064462,
"grad_norm": 0.4290294051170349,
"learning_rate": 2e-05,
"loss": 0.8546,
"step": 2510
},
{
"epoch": 0.21096693177061532,
"grad_norm": 0.4311007559299469,
"learning_rate": 2e-05,
"loss": 0.8763,
"step": 2520
},
{
"epoch": 0.21180410213478443,
"grad_norm": 0.45104533433914185,
"learning_rate": 2e-05,
"loss": 0.8489,
"step": 2530
},
{
"epoch": 0.21264127249895354,
"grad_norm": 0.42825406789779663,
"learning_rate": 2e-05,
"loss": 0.8633,
"step": 2540
},
{
"epoch": 0.21347844286312265,
"grad_norm": 0.42183905839920044,
"learning_rate": 1.9980979278401095e-05,
"loss": 0.8422,
"step": 2550
},
{
"epoch": 0.21431561322729176,
"grad_norm": 0.432753324508667,
"learning_rate": 1.982924955463327e-05,
"loss": 0.8824,
"step": 2560
},
{
"epoch": 0.21515278359146087,
"grad_norm": 0.42494094371795654,
"learning_rate": 1.9528108298328235e-05,
"loss": 0.8441,
"step": 2570
},
{
"epoch": 0.21598995395562998,
"grad_norm": 0.42465174198150635,
"learning_rate": 1.9082156473635994e-05,
"loss": 0.8533,
"step": 2580
},
{
"epoch": 0.21682712431979909,
"grad_norm": 0.4523787200450897,
"learning_rate": 1.8498207522139434e-05,
"loss": 0.847,
"step": 2590
},
{
"epoch": 0.2176642946839682,
"grad_norm": 0.44029274582862854,
"learning_rate": 1.7785183264196977e-05,
"loss": 0.8695,
"step": 2600
},
{
"epoch": 0.2185014650481373,
"grad_norm": 0.43642333149909973,
"learning_rate": 1.6953977587577846e-05,
"loss": 0.8709,
"step": 2610
},
{
"epoch": 0.21933863541230642,
"grad_norm": 0.4292779564857483,
"learning_rate": 1.601729000601297e-05,
"loss": 0.871,
"step": 2620
},
{
"epoch": 0.22017580577647552,
"grad_norm": 0.44597575068473816,
"learning_rate": 1.4989431630624763e-05,
"loss": 0.8673,
"step": 2630
},
{
"epoch": 0.22101297614064463,
"grad_norm": 0.4210914969444275,
"learning_rate": 1.3886106518686746e-05,
"loss": 0.8626,
"step": 2640
},
{
"epoch": 0.22185014650481372,
"grad_norm": 0.4179028272628784,
"learning_rate": 1.2724171740359612e-05,
"loss": 0.8229,
"step": 2650
},
{
"epoch": 0.22268731686898283,
"grad_norm": 0.4223529100418091,
"learning_rate": 1.1521379829206218e-05,
"loss": 0.8428,
"step": 2660
},
{
"epoch": 0.22352448723315194,
"grad_norm": 0.4477887451648712,
"learning_rate": 1.029610755143595e-05,
"loss": 0.8481,
"step": 2670
},
{
"epoch": 0.22436165759732105,
"grad_norm": 0.4088965654373169,
"learning_rate": 9.067075137857348e-06,
"loss": 0.8352,
"step": 2680
},
{
"epoch": 0.22519882796149016,
"grad_norm": 0.4290041923522949,
"learning_rate": 7.853060268232525e-06,
"loss": 0.8532,
"step": 2690
},
{
"epoch": 0.22603599832565927,
"grad_norm": 0.41104647517204285,
"learning_rate": 6.672611177902054e-06,
"loss": 0.8564,
"step": 2700
},
{
"epoch": 0.22687316868982838,
"grad_norm": 0.5251089930534363,
"learning_rate": 5.543763269959312e-06,
"loss": 0.8384,
"step": 2710
},
{
"epoch": 0.22771033905399748,
"grad_norm": 0.4120629131793976,
"learning_rate": 4.483763562693867e-06,
"loss": 0.8339,
"step": 2720
},
{
"epoch": 0.2285475094181666,
"grad_norm": 0.41700199246406555,
"learning_rate": 3.508807182313187e-06,
"loss": 0.8184,
"step": 2730
},
{
"epoch": 0.2293846797823357,
"grad_norm": 0.45491278171539307,
"learning_rate": 2.6337899269187294e-06,
"loss": 0.8363,
"step": 2740
},
{
"epoch": 0.23022185014650481,
"grad_norm": 0.42362427711486816,
"learning_rate": 1.8720806821693126e-06,
"loss": 0.8385,
"step": 2750
},
{
"epoch": 0.23105902051067392,
"grad_norm": 0.4634353220462799,
"learning_rate": 1.2353171657619887e-06,
"loss": 0.824,
"step": 2760
},
{
"epoch": 0.23189619087484303,
"grad_norm": 0.4274537265300751,
"learning_rate": 7.332281214330356e-07,
"loss": 0.85,
"step": 2770
},
{
"epoch": 0.23273336123901214,
"grad_norm": 0.41241827607154846,
"learning_rate": 3.73484679074808e-07,
"loss": 0.8173,
"step": 2780
},
{
"epoch": 0.23357053160318125,
"grad_norm": 0.4182555675506592,
"learning_rate": 1.61583151951702e-07,
"loss": 0.8667,
"step": 2790
},
{
"epoch": 0.23424026789451655,
"step": 2798,
"total_flos": 1.1366756130249245e+19,
"train_loss": 0.07698175445294875,
"train_runtime": 2327.9923,
"train_samples_per_second": 14.423,
"train_steps_per_second": 1.202
}
],
"logging_steps": 10,
"max_steps": 2798,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 159,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.1366756130249245e+19,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.23424026789451655,
"eval_steps": 500,
"global_step": 2798,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0008371703641691084,
"grad_norm": 6.286955833435059,
"learning_rate": 1.1061797752808989e-06,
"loss": 2.1571,
"step": 10
},
{
"epoch": 0.0016743407283382169,
"grad_norm": 3.6767687797546387,
"learning_rate": 2.2241573033707866e-06,
"loss": 1.9243,
"step": 20
},
{
"epoch": 0.0025115110925073253,
"grad_norm": 2.151350498199463,
"learning_rate": 3.342134831460675e-06,
"loss": 1.7728,
"step": 30
},
{
"epoch": 0.0033486814566764337,
"grad_norm": 1.2491344213485718,
"learning_rate": 4.4601123595505624e-06,
"loss": 1.4703,
"step": 40
},
{
"epoch": 0.004185851820845542,
"grad_norm": 0.9011292457580566,
"learning_rate": 5.5780898876404495e-06,
"loss": 1.2532,
"step": 50
},
{
"epoch": 0.0050230221850146506,
"grad_norm": 1.1828844547271729,
"learning_rate": 6.6960674157303374e-06,
"loss": 1.1652,
"step": 60
},
{
"epoch": 0.0058601925491837585,
"grad_norm": 0.7618897557258606,
"learning_rate": 7.814044943820226e-06,
"loss": 1.1584,
"step": 70
},
{
"epoch": 0.006697362913352867,
"grad_norm": 0.6916522979736328,
"learning_rate": 8.932022471910112e-06,
"loss": 1.0909,
"step": 80
},
{
"epoch": 0.007534533277521975,
"grad_norm": 0.6934717893600464,
"learning_rate": 1.005e-05,
"loss": 1.0744,
"step": 90
},
{
"epoch": 0.008371703641691083,
"grad_norm": 0.7366052865982056,
"learning_rate": 1.1167977528089888e-05,
"loss": 1.0488,
"step": 100
},
{
"epoch": 0.009208874005860193,
"grad_norm": 0.6335578560829163,
"learning_rate": 1.2285955056179776e-05,
"loss": 1.0163,
"step": 110
},
{
"epoch": 0.010046044370029301,
"grad_norm": 0.6413920521736145,
"learning_rate": 1.3403932584269664e-05,
"loss": 1.0387,
"step": 120
},
{
"epoch": 0.010883214734198409,
"grad_norm": 0.652919352054596,
"learning_rate": 1.4521910112359552e-05,
"loss": 1.0123,