{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.46856425282545,
"eval_steps": 500,
"global_step": 5597,
"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": 0.42387330532073975,
"learning_rate": 2e-05,
"loss": 0.8422,
"step": 2550
},
{
"epoch": 0.21431561322729176,
"grad_norm": 0.4319068193435669,
"learning_rate": 2e-05,
"loss": 0.8824,
"step": 2560
},
{
"epoch": 0.21515278359146087,
"grad_norm": 0.4178818464279175,
"learning_rate": 2e-05,
"loss": 0.8442,
"step": 2570
},
{
"epoch": 0.21598995395562998,
"grad_norm": 0.4258483946323395,
"learning_rate": 2e-05,
"loss": 0.8536,
"step": 2580
},
{
"epoch": 0.21682712431979909,
"grad_norm": 0.4532221555709839,
"learning_rate": 2e-05,
"loss": 0.8476,
"step": 2590
},
{
"epoch": 0.2176642946839682,
"grad_norm": 0.4477638304233551,
"learning_rate": 2e-05,
"loss": 0.8707,
"step": 2600
},
{
"epoch": 0.2185014650481373,
"grad_norm": 0.4326961040496826,
"learning_rate": 2e-05,
"loss": 0.8726,
"step": 2610
},
{
"epoch": 0.21933863541230642,
"grad_norm": 0.46689221262931824,
"learning_rate": 2e-05,
"loss": 0.8736,
"step": 2620
},
{
"epoch": 0.22017580577647552,
"grad_norm": 0.4493032991886139,
"learning_rate": 2e-05,
"loss": 0.8711,
"step": 2630
},
{
"epoch": 0.22101297614064463,
"grad_norm": 0.4334334433078766,
"learning_rate": 2e-05,
"loss": 0.8675,
"step": 2640
},
{
"epoch": 0.22185014650481372,
"grad_norm": 0.4326641261577606,
"learning_rate": 2e-05,
"loss": 0.829,
"step": 2650
},
{
"epoch": 0.22268731686898283,
"grad_norm": 0.4365394413471222,
"learning_rate": 2e-05,
"loss": 0.8503,
"step": 2660
},
{
"epoch": 0.22352448723315194,
"grad_norm": 0.47003981471061707,
"learning_rate": 2e-05,
"loss": 0.8567,
"step": 2670
},
{
"epoch": 0.22436165759732105,
"grad_norm": 0.41743093729019165,
"learning_rate": 2e-05,
"loss": 0.8451,
"step": 2680
},
{
"epoch": 0.22519882796149016,
"grad_norm": 0.44406813383102417,
"learning_rate": 2e-05,
"loss": 0.8643,
"step": 2690
},
{
"epoch": 0.22603599832565927,
"grad_norm": 0.42659661173820496,
"learning_rate": 2e-05,
"loss": 0.8687,
"step": 2700
},
{
"epoch": 0.22687316868982838,
"grad_norm": 0.4428755044937134,
"learning_rate": 2e-05,
"loss": 0.8524,
"step": 2710
},
{
"epoch": 0.22771033905399748,
"grad_norm": 0.42310386896133423,
"learning_rate": 2e-05,
"loss": 0.8484,
"step": 2720
},
{
"epoch": 0.2285475094181666,
"grad_norm": 0.4624371826648712,
"learning_rate": 2e-05,
"loss": 0.8327,
"step": 2730
},
{
"epoch": 0.2293846797823357,
"grad_norm": 0.43734869360923767,
"learning_rate": 2e-05,
"loss": 0.8518,
"step": 2740
},
{
"epoch": 0.23022185014650481,
"grad_norm": 0.4506842792034149,
"learning_rate": 2e-05,
"loss": 0.8565,
"step": 2750
},
{
"epoch": 0.23105902051067392,
"grad_norm": 0.48162660002708435,
"learning_rate": 2e-05,
"loss": 0.8417,
"step": 2760
},
{
"epoch": 0.23189619087484303,
"grad_norm": 0.5661482810974121,
"learning_rate": 2e-05,
"loss": 0.8662,
"step": 2770
},
{
"epoch": 0.23273336123901214,
"grad_norm": 0.42844292521476746,
"learning_rate": 2e-05,
"loss": 0.8342,
"step": 2780
},
{
"epoch": 0.23357053160318125,
"grad_norm": 0.43888863921165466,
"learning_rate": 2e-05,
"loss": 0.8846,
"step": 2790
},
{
"epoch": 0.23440770196735036,
"grad_norm": 0.4474732577800751,
"learning_rate": 2e-05,
"loss": 0.8317,
"step": 2800
},
{
"epoch": 0.23524487233151947,
"grad_norm": 0.4584842026233673,
"learning_rate": 2e-05,
"loss": 0.8915,
"step": 2810
},
{
"epoch": 0.23608204269568858,
"grad_norm": 0.43371322751045227,
"learning_rate": 2e-05,
"loss": 0.8526,
"step": 2820
},
{
"epoch": 0.2369192130598577,
"grad_norm": 0.4327155351638794,
"learning_rate": 2e-05,
"loss": 0.8677,
"step": 2830
},
{
"epoch": 0.2377563834240268,
"grad_norm": 0.4316923916339874,
"learning_rate": 2e-05,
"loss": 0.8331,
"step": 2840
},
{
"epoch": 0.2385935537881959,
"grad_norm": 0.42735129594802856,
"learning_rate": 2e-05,
"loss": 0.8485,
"step": 2850
},
{
"epoch": 0.239430724152365,
"grad_norm": 0.4395933449268341,
"learning_rate": 2e-05,
"loss": 0.8362,
"step": 2860
},
{
"epoch": 0.2402678945165341,
"grad_norm": 0.4804455041885376,
"learning_rate": 2e-05,
"loss": 0.8238,
"step": 2870
},
{
"epoch": 0.2411050648807032,
"grad_norm": 0.4475085437297821,
"learning_rate": 2e-05,
"loss": 0.8763,
"step": 2880
},
{
"epoch": 0.24194223524487232,
"grad_norm": 0.4516408443450928,
"learning_rate": 2e-05,
"loss": 0.8444,
"step": 2890
},
{
"epoch": 0.24277940560904143,
"grad_norm": 0.46845370531082153,
"learning_rate": 2e-05,
"loss": 0.8214,
"step": 2900
},
{
"epoch": 0.24361657597321054,
"grad_norm": 0.4366689622402191,
"learning_rate": 2e-05,
"loss": 0.8308,
"step": 2910
},
{
"epoch": 0.24445374633737965,
"grad_norm": 0.4363156855106354,
"learning_rate": 2e-05,
"loss": 0.8394,
"step": 2920
},
{
"epoch": 0.24529091670154876,
"grad_norm": 0.4714019000530243,
"learning_rate": 2e-05,
"loss": 0.8688,
"step": 2930
},
{
"epoch": 0.24612808706571787,
"grad_norm": 0.48325541615486145,
"learning_rate": 2e-05,
"loss": 0.8354,
"step": 2940
},
{
"epoch": 0.24696525742988698,
"grad_norm": 0.4532882273197174,
"learning_rate": 2e-05,
"loss": 0.8763,
"step": 2950
},
{
"epoch": 0.2478024277940561,
"grad_norm": 0.4276827573776245,
"learning_rate": 2e-05,
"loss": 0.861,
"step": 2960
},
{
"epoch": 0.2486395981582252,
"grad_norm": 0.42689263820648193,
"learning_rate": 2e-05,
"loss": 0.8619,
"step": 2970
},
{
"epoch": 0.2494767685223943,
"grad_norm": 0.4465515911579132,
"learning_rate": 2e-05,
"loss": 0.8722,
"step": 2980
},
{
"epoch": 0.2503139388865634,
"grad_norm": 0.45104026794433594,
"learning_rate": 2e-05,
"loss": 0.8663,
"step": 2990
},
{
"epoch": 0.25115110925073253,
"grad_norm": 0.44007986783981323,
"learning_rate": 2e-05,
"loss": 0.8301,
"step": 3000
},
{
"epoch": 0.2519882796149016,
"grad_norm": 0.43077486753463745,
"learning_rate": 2e-05,
"loss": 0.8545,
"step": 3010
},
{
"epoch": 0.25282544997907075,
"grad_norm": 0.4256698787212372,
"learning_rate": 2e-05,
"loss": 0.8425,
"step": 3020
},
{
"epoch": 0.25366262034323983,
"grad_norm": 0.44382596015930176,
"learning_rate": 2e-05,
"loss": 0.845,
"step": 3030
},
{
"epoch": 0.25449979070740897,
"grad_norm": 0.44387444853782654,
"learning_rate": 2e-05,
"loss": 0.868,
"step": 3040
},
{
"epoch": 0.25533696107157805,
"grad_norm": 0.42307358980178833,
"learning_rate": 2e-05,
"loss": 0.8586,
"step": 3050
},
{
"epoch": 0.2561741314357472,
"grad_norm": 0.5496047139167786,
"learning_rate": 2e-05,
"loss": 0.875,
"step": 3060
},
{
"epoch": 0.25701130179991627,
"grad_norm": 0.43474847078323364,
"learning_rate": 2e-05,
"loss": 0.8445,
"step": 3070
},
{
"epoch": 0.2578484721640854,
"grad_norm": 0.4298436939716339,
"learning_rate": 2e-05,
"loss": 0.8354,
"step": 3080
},
{
"epoch": 0.2586856425282545,
"grad_norm": 0.433672696352005,
"learning_rate": 2e-05,
"loss": 0.8307,
"step": 3090
},
{
"epoch": 0.2595228128924236,
"grad_norm": 0.4268275797367096,
"learning_rate": 2e-05,
"loss": 0.8408,
"step": 3100
},
{
"epoch": 0.2603599832565927,
"grad_norm": 0.44805261492729187,
"learning_rate": 2e-05,
"loss": 0.8805,
"step": 3110
},
{
"epoch": 0.26119715362076185,
"grad_norm": 0.41279494762420654,
"learning_rate": 2e-05,
"loss": 0.8571,
"step": 3120
},
{
"epoch": 0.26203432398493093,
"grad_norm": 0.4382464587688446,
"learning_rate": 2e-05,
"loss": 0.8408,
"step": 3130
},
{
"epoch": 0.26287149434910007,
"grad_norm": 0.43196719884872437,
"learning_rate": 2e-05,
"loss": 0.8359,
"step": 3140
},
{
"epoch": 0.26370866471326915,
"grad_norm": 0.4206157326698303,
"learning_rate": 2e-05,
"loss": 0.8781,
"step": 3150
},
{
"epoch": 0.2645458350774383,
"grad_norm": 0.4439392387866974,
"learning_rate": 2e-05,
"loss": 0.8353,
"step": 3160
},
{
"epoch": 0.26538300544160737,
"grad_norm": 0.43137675523757935,
"learning_rate": 2e-05,
"loss": 0.8543,
"step": 3170
},
{
"epoch": 0.26622017580577645,
"grad_norm": 0.4718741178512573,
"learning_rate": 2e-05,
"loss": 0.8766,
"step": 3180
},
{
"epoch": 0.2670573461699456,
"grad_norm": 0.4124031662940979,
"learning_rate": 2e-05,
"loss": 0.856,
"step": 3190
},
{
"epoch": 0.26789451653411467,
"grad_norm": 0.44760680198669434,
"learning_rate": 2e-05,
"loss": 0.8495,
"step": 3200
},
{
"epoch": 0.2687316868982838,
"grad_norm": 0.4445425570011139,
"learning_rate": 2e-05,
"loss": 0.866,
"step": 3210
},
{
"epoch": 0.2695688572624529,
"grad_norm": 0.43041038513183594,
"learning_rate": 2e-05,
"loss": 0.8411,
"step": 3220
},
{
"epoch": 0.270406027626622,
"grad_norm": 0.42874640226364136,
"learning_rate": 2e-05,
"loss": 0.8639,
"step": 3230
},
{
"epoch": 0.2712431979907911,
"grad_norm": 0.4241209626197815,
"learning_rate": 2e-05,
"loss": 0.8662,
"step": 3240
},
{
"epoch": 0.27208036835496024,
"grad_norm": 0.4623543322086334,
"learning_rate": 2e-05,
"loss": 0.8692,
"step": 3250
},
{
"epoch": 0.2729175387191293,
"grad_norm": 0.41813695430755615,
"learning_rate": 2e-05,
"loss": 0.8454,
"step": 3260
},
{
"epoch": 0.27375470908329846,
"grad_norm": 0.43213996291160583,
"learning_rate": 2e-05,
"loss": 0.8264,
"step": 3270
},
{
"epoch": 0.27459187944746755,
"grad_norm": 0.43402811884880066,
"learning_rate": 2e-05,
"loss": 0.8485,
"step": 3280
},
{
"epoch": 0.2754290498116367,
"grad_norm": 0.4213794767856598,
"learning_rate": 2e-05,
"loss": 0.8348,
"step": 3290
},
{
"epoch": 0.27626622017580577,
"grad_norm": 0.4604377746582031,
"learning_rate": 2e-05,
"loss": 0.8314,
"step": 3300
},
{
"epoch": 0.2771033905399749,
"grad_norm": 0.41930535435676575,
"learning_rate": 2e-05,
"loss": 0.8619,
"step": 3310
},
{
"epoch": 0.277940560904144,
"grad_norm": 0.44456246495246887,
"learning_rate": 2e-05,
"loss": 0.8373,
"step": 3320
},
{
"epoch": 0.2787777312683131,
"grad_norm": 0.42515015602111816,
"learning_rate": 2e-05,
"loss": 0.8325,
"step": 3330
},
{
"epoch": 0.2796149016324822,
"grad_norm": 0.543720543384552,
"learning_rate": 2e-05,
"loss": 0.8514,
"step": 3340
},
{
"epoch": 0.28045207199665134,
"grad_norm": 0.4654465317726135,
"learning_rate": 2e-05,
"loss": 0.8256,
"step": 3350
},
{
"epoch": 0.2812892423608204,
"grad_norm": 0.43853747844696045,
"learning_rate": 2e-05,
"loss": 0.8471,
"step": 3360
},
{
"epoch": 0.28212641272498956,
"grad_norm": 0.4390884339809418,
"learning_rate": 2e-05,
"loss": 0.83,
"step": 3370
},
{
"epoch": 0.28296358308915864,
"grad_norm": 0.427254319190979,
"learning_rate": 2e-05,
"loss": 0.8267,
"step": 3380
},
{
"epoch": 0.2838007534533277,
"grad_norm": 0.5277079343795776,
"learning_rate": 2e-05,
"loss": 0.8306,
"step": 3390
},
{
"epoch": 0.28463792381749686,
"grad_norm": 0.4379133880138397,
"learning_rate": 2e-05,
"loss": 0.8403,
"step": 3400
},
{
"epoch": 0.28547509418166594,
"grad_norm": 0.4159203767776489,
"learning_rate": 2e-05,
"loss": 0.8257,
"step": 3410
},
{
"epoch": 0.2863122645458351,
"grad_norm": 0.40820810198783875,
"learning_rate": 2e-05,
"loss": 0.8397,
"step": 3420
},
{
"epoch": 0.28714943491000416,
"grad_norm": 0.4453214406967163,
"learning_rate": 2e-05,
"loss": 0.8553,
"step": 3430
},
{
"epoch": 0.2879866052741733,
"grad_norm": 0.44322121143341064,
"learning_rate": 2e-05,
"loss": 0.8469,
"step": 3440
},
{
"epoch": 0.2888237756383424,
"grad_norm": 0.4469110667705536,
"learning_rate": 2e-05,
"loss": 0.8271,
"step": 3450
},
{
"epoch": 0.2896609460025115,
"grad_norm": 0.4392768442630768,
"learning_rate": 2e-05,
"loss": 0.8399,
"step": 3460
},
{
"epoch": 0.2904981163666806,
"grad_norm": 0.4181481897830963,
"learning_rate": 2e-05,
"loss": 0.8604,
"step": 3470
},
{
"epoch": 0.29133528673084974,
"grad_norm": 0.428493857383728,
"learning_rate": 2e-05,
"loss": 0.8402,
"step": 3480
},
{
"epoch": 0.2921724570950188,
"grad_norm": 0.4284713566303253,
"learning_rate": 2e-05,
"loss": 0.8434,
"step": 3490
},
{
"epoch": 0.29300962745918796,
"grad_norm": 0.43312734365463257,
"learning_rate": 2e-05,
"loss": 0.8188,
"step": 3500
},
{
"epoch": 0.29384679782335704,
"grad_norm": 0.4221225678920746,
"learning_rate": 2e-05,
"loss": 0.847,
"step": 3510
},
{
"epoch": 0.2946839681875262,
"grad_norm": 0.4417845606803894,
"learning_rate": 2e-05,
"loss": 0.8526,
"step": 3520
},
{
"epoch": 0.29552113855169526,
"grad_norm": 0.417818546295166,
"learning_rate": 2e-05,
"loss": 0.835,
"step": 3530
},
{
"epoch": 0.2963583089158644,
"grad_norm": 0.4408692419528961,
"learning_rate": 2e-05,
"loss": 0.8325,
"step": 3540
},
{
"epoch": 0.2971954792800335,
"grad_norm": 0.42140427231788635,
"learning_rate": 2e-05,
"loss": 0.86,
"step": 3550
},
{
"epoch": 0.2980326496442026,
"grad_norm": 0.42939653992652893,
"learning_rate": 2e-05,
"loss": 0.848,
"step": 3560
},
{
"epoch": 0.2988698200083717,
"grad_norm": 0.4309823513031006,
"learning_rate": 2e-05,
"loss": 0.8467,
"step": 3570
},
{
"epoch": 0.29970699037254084,
"grad_norm": 0.41343390941619873,
"learning_rate": 2e-05,
"loss": 0.8462,
"step": 3580
},
{
"epoch": 0.3005441607367099,
"grad_norm": 0.44925427436828613,
"learning_rate": 2e-05,
"loss": 0.8608,
"step": 3590
},
{
"epoch": 0.301381331100879,
"grad_norm": 0.4298679530620575,
"learning_rate": 2e-05,
"loss": 0.834,
"step": 3600
},
{
"epoch": 0.30221850146504814,
"grad_norm": 0.43456289172172546,
"learning_rate": 2e-05,
"loss": 0.8484,
"step": 3610
},
{
"epoch": 0.3030556718292172,
"grad_norm": 0.441661536693573,
"learning_rate": 2e-05,
"loss": 0.8242,
"step": 3620
},
{
"epoch": 0.30389284219338636,
"grad_norm": 0.4271041750907898,
"learning_rate": 2e-05,
"loss": 0.812,
"step": 3630
},
{
"epoch": 0.30473001255755544,
"grad_norm": 0.41006773710250854,
"learning_rate": 2e-05,
"loss": 0.8424,
"step": 3640
},
{
"epoch": 0.3055671829217246,
"grad_norm": 0.4275254011154175,
"learning_rate": 2e-05,
"loss": 0.8317,
"step": 3650
},
{
"epoch": 0.30640435328589366,
"grad_norm": 0.42956051230430603,
"learning_rate": 2e-05,
"loss": 0.8585,
"step": 3660
},
{
"epoch": 0.3072415236500628,
"grad_norm": 0.44132646918296814,
"learning_rate": 2e-05,
"loss": 0.8378,
"step": 3670
},
{
"epoch": 0.3080786940142319,
"grad_norm": 0.45235463976860046,
"learning_rate": 2e-05,
"loss": 0.8573,
"step": 3680
},
{
"epoch": 0.308915864378401,
"grad_norm": 0.4310559630393982,
"learning_rate": 2e-05,
"loss": 0.8248,
"step": 3690
},
{
"epoch": 0.3097530347425701,
"grad_norm": 0.44843408465385437,
"learning_rate": 2e-05,
"loss": 0.8343,
"step": 3700
},
{
"epoch": 0.31059020510673924,
"grad_norm": 0.4408901035785675,
"learning_rate": 2e-05,
"loss": 0.8326,
"step": 3710
},
{
"epoch": 0.3114273754709083,
"grad_norm": 0.43724024295806885,
"learning_rate": 2e-05,
"loss": 0.8313,
"step": 3720
},
{
"epoch": 0.31226454583507746,
"grad_norm": 0.41545209288597107,
"learning_rate": 2e-05,
"loss": 0.8299,
"step": 3730
},
{
"epoch": 0.31310171619924654,
"grad_norm": 0.43244078755378723,
"learning_rate": 2e-05,
"loss": 0.8495,
"step": 3740
},
{
"epoch": 0.3139388865634157,
"grad_norm": 0.4475247263908386,
"learning_rate": 2e-05,
"loss": 0.8181,
"step": 3750
},
{
"epoch": 0.31477605692758476,
"grad_norm": 0.4203198254108429,
"learning_rate": 2e-05,
"loss": 0.8505,
"step": 3760
},
{
"epoch": 0.3156132272917539,
"grad_norm": 0.4319896101951599,
"learning_rate": 2e-05,
"loss": 0.8182,
"step": 3770
},
{
"epoch": 0.316450397655923,
"grad_norm": 0.4427873194217682,
"learning_rate": 2e-05,
"loss": 0.8509,
"step": 3780
},
{
"epoch": 0.3172875680200921,
"grad_norm": 0.4312664568424225,
"learning_rate": 2e-05,
"loss": 0.8504,
"step": 3790
},
{
"epoch": 0.3181247383842612,
"grad_norm": 0.4734603464603424,
"learning_rate": 2e-05,
"loss": 0.8639,
"step": 3800
},
{
"epoch": 0.3189619087484303,
"grad_norm": 0.42495936155319214,
"learning_rate": 2e-05,
"loss": 0.8335,
"step": 3810
},
{
"epoch": 0.3197990791125994,
"grad_norm": 0.42727217078208923,
"learning_rate": 2e-05,
"loss": 0.8107,
"step": 3820
},
{
"epoch": 0.3206362494767685,
"grad_norm": 0.41671445965766907,
"learning_rate": 2e-05,
"loss": 0.8558,
"step": 3830
},
{
"epoch": 0.32147341984093764,
"grad_norm": 0.41387617588043213,
"learning_rate": 2e-05,
"loss": 0.8058,
"step": 3840
},
{
"epoch": 0.3223105902051067,
"grad_norm": 0.45229795575141907,
"learning_rate": 2e-05,
"loss": 0.8558,
"step": 3850
},
{
"epoch": 0.32314776056927585,
"grad_norm": 0.453480988740921,
"learning_rate": 2e-05,
"loss": 0.8251,
"step": 3860
},
{
"epoch": 0.32398493093344494,
"grad_norm": 0.4310716390609741,
"learning_rate": 2e-05,
"loss": 0.8372,
"step": 3870
},
{
"epoch": 0.3248221012976141,
"grad_norm": 0.41317251324653625,
"learning_rate": 2e-05,
"loss": 0.838,
"step": 3880
},
{
"epoch": 0.32565927166178316,
"grad_norm": 0.41291454434394836,
"learning_rate": 2e-05,
"loss": 0.833,
"step": 3890
},
{
"epoch": 0.3264964420259523,
"grad_norm": 0.4336530566215515,
"learning_rate": 2e-05,
"loss": 0.8128,
"step": 3900
},
{
"epoch": 0.3273336123901214,
"grad_norm": 0.4162159860134125,
"learning_rate": 2e-05,
"loss": 0.8258,
"step": 3910
},
{
"epoch": 0.3281707827542905,
"grad_norm": 0.43340811133384705,
"learning_rate": 2e-05,
"loss": 0.8643,
"step": 3920
},
{
"epoch": 0.3290079531184596,
"grad_norm": 0.4096095561981201,
"learning_rate": 2e-05,
"loss": 0.8387,
"step": 3930
},
{
"epoch": 0.32984512348262873,
"grad_norm": 0.4369688332080841,
"learning_rate": 2e-05,
"loss": 0.8285,
"step": 3940
},
{
"epoch": 0.3306822938467978,
"grad_norm": 0.459893137216568,
"learning_rate": 2e-05,
"loss": 0.858,
"step": 3950
},
{
"epoch": 0.33151946421096695,
"grad_norm": 0.4191811978816986,
"learning_rate": 2e-05,
"loss": 0.8116,
"step": 3960
},
{
"epoch": 0.33235663457513603,
"grad_norm": 0.4309510886669159,
"learning_rate": 2e-05,
"loss": 0.8391,
"step": 3970
},
{
"epoch": 0.33319380493930517,
"grad_norm": 0.4352155923843384,
"learning_rate": 2e-05,
"loss": 0.8508,
"step": 3980
},
{
"epoch": 0.33403097530347425,
"grad_norm": 0.4311888515949249,
"learning_rate": 2e-05,
"loss": 0.8085,
"step": 3990
},
{
"epoch": 0.3348681456676434,
"grad_norm": 0.42564472556114197,
"learning_rate": 2e-05,
"loss": 0.8175,
"step": 4000
},
{
"epoch": 0.3357053160318125,
"grad_norm": 0.4221665561199188,
"learning_rate": 2e-05,
"loss": 0.8323,
"step": 4010
},
{
"epoch": 0.33654248639598155,
"grad_norm": 0.43019554018974304,
"learning_rate": 2e-05,
"loss": 0.8532,
"step": 4020
},
{
"epoch": 0.3373796567601507,
"grad_norm": 0.4272821843624115,
"learning_rate": 2e-05,
"loss": 0.8313,
"step": 4030
},
{
"epoch": 0.3382168271243198,
"grad_norm": 0.4159959852695465,
"learning_rate": 2e-05,
"loss": 0.8188,
"step": 4040
},
{
"epoch": 0.3390539974884889,
"grad_norm": 0.43675434589385986,
"learning_rate": 2e-05,
"loss": 0.8059,
"step": 4050
},
{
"epoch": 0.339891167852658,
"grad_norm": 0.43672120571136475,
"learning_rate": 2e-05,
"loss": 0.8453,
"step": 4060
},
{
"epoch": 0.34072833821682713,
"grad_norm": 0.427731990814209,
"learning_rate": 2e-05,
"loss": 0.8355,
"step": 4070
},
{
"epoch": 0.3415655085809962,
"grad_norm": 0.41670680046081543,
"learning_rate": 2e-05,
"loss": 0.8242,
"step": 4080
},
{
"epoch": 0.34240267894516535,
"grad_norm": 0.4309384226799011,
"learning_rate": 2e-05,
"loss": 0.827,
"step": 4090
},
{
"epoch": 0.34323984930933443,
"grad_norm": 0.42762354016304016,
"learning_rate": 2e-05,
"loss": 0.8564,
"step": 4100
},
{
"epoch": 0.34407701967350357,
"grad_norm": 0.4144584834575653,
"learning_rate": 2e-05,
"loss": 0.8427,
"step": 4110
},
{
"epoch": 0.34491419003767265,
"grad_norm": 0.4221765398979187,
"learning_rate": 2e-05,
"loss": 0.8122,
"step": 4120
},
{
"epoch": 0.3457513604018418,
"grad_norm": 0.4422992467880249,
"learning_rate": 2e-05,
"loss": 0.8219,
"step": 4130
},
{
"epoch": 0.34658853076601087,
"grad_norm": 0.4365583658218384,
"learning_rate": 2e-05,
"loss": 0.8432,
"step": 4140
},
{
"epoch": 0.34742570113018,
"grad_norm": 0.3962838053703308,
"learning_rate": 2e-05,
"loss": 0.8413,
"step": 4150
},
{
"epoch": 0.3482628714943491,
"grad_norm": 0.43464258313179016,
"learning_rate": 2e-05,
"loss": 0.8494,
"step": 4160
},
{
"epoch": 0.34910004185851823,
"grad_norm": 0.4626946747303009,
"learning_rate": 2e-05,
"loss": 0.8419,
"step": 4170
},
{
"epoch": 0.3499372122226873,
"grad_norm": 0.4124692678451538,
"learning_rate": 2e-05,
"loss": 0.8163,
"step": 4180
},
{
"epoch": 0.35077438258685645,
"grad_norm": 0.4296865165233612,
"learning_rate": 2e-05,
"loss": 0.8438,
"step": 4190
},
{
"epoch": 0.35161155295102553,
"grad_norm": 0.40684860944747925,
"learning_rate": 2e-05,
"loss": 0.813,
"step": 4200
},
{
"epoch": 0.35244872331519467,
"grad_norm": 0.43835723400115967,
"learning_rate": 2e-05,
"loss": 0.8444,
"step": 4210
},
{
"epoch": 0.35328589367936375,
"grad_norm": 0.43864011764526367,
"learning_rate": 2e-05,
"loss": 0.8293,
"step": 4220
},
{
"epoch": 0.35412306404353283,
"grad_norm": 0.4002416431903839,
"learning_rate": 2e-05,
"loss": 0.8104,
"step": 4230
},
{
"epoch": 0.35496023440770197,
"grad_norm": 0.43456172943115234,
"learning_rate": 2e-05,
"loss": 0.8428,
"step": 4240
},
{
"epoch": 0.35579740477187105,
"grad_norm": 0.43075916171073914,
"learning_rate": 2e-05,
"loss": 0.8571,
"step": 4250
},
{
"epoch": 0.3566345751360402,
"grad_norm": 0.4223424196243286,
"learning_rate": 2e-05,
"loss": 0.821,
"step": 4260
},
{
"epoch": 0.35747174550020927,
"grad_norm": 0.43250206112861633,
"learning_rate": 2e-05,
"loss": 0.8144,
"step": 4270
},
{
"epoch": 0.3583089158643784,
"grad_norm": 0.41428571939468384,
"learning_rate": 2e-05,
"loss": 0.8397,
"step": 4280
},
{
"epoch": 0.3591460862285475,
"grad_norm": 0.43673330545425415,
"learning_rate": 2e-05,
"loss": 0.837,
"step": 4290
},
{
"epoch": 0.3599832565927166,
"grad_norm": 0.4234159588813782,
"learning_rate": 2e-05,
"loss": 0.8376,
"step": 4300
},
{
"epoch": 0.3608204269568857,
"grad_norm": 0.4296039044857025,
"learning_rate": 2e-05,
"loss": 0.8396,
"step": 4310
},
{
"epoch": 0.36165759732105485,
"grad_norm": 0.41784560680389404,
"learning_rate": 2e-05,
"loss": 0.798,
"step": 4320
},
{
"epoch": 0.36249476768522393,
"grad_norm": 0.4596424400806427,
"learning_rate": 2e-05,
"loss": 0.8442,
"step": 4330
},
{
"epoch": 0.36333193804939307,
"grad_norm": 0.4594140350818634,
"learning_rate": 2e-05,
"loss": 0.8428,
"step": 4340
},
{
"epoch": 0.36416910841356215,
"grad_norm": 0.408284991979599,
"learning_rate": 2e-05,
"loss": 0.8223,
"step": 4350
},
{
"epoch": 0.3650062787777313,
"grad_norm": 0.431534081697464,
"learning_rate": 2e-05,
"loss": 0.8533,
"step": 4360
},
{
"epoch": 0.36584344914190037,
"grad_norm": 0.42122581601142883,
"learning_rate": 2e-05,
"loss": 0.8118,
"step": 4370
},
{
"epoch": 0.3666806195060695,
"grad_norm": 0.4410568177700043,
"learning_rate": 2e-05,
"loss": 0.8503,
"step": 4380
},
{
"epoch": 0.3675177898702386,
"grad_norm": 0.48844408988952637,
"learning_rate": 2e-05,
"loss": 0.8378,
"step": 4390
},
{
"epoch": 0.3683549602344077,
"grad_norm": 0.4141460359096527,
"learning_rate": 2e-05,
"loss": 0.8253,
"step": 4400
},
{
"epoch": 0.3691921305985768,
"grad_norm": 0.4506625831127167,
"learning_rate": 2e-05,
"loss": 0.8279,
"step": 4410
},
{
"epoch": 0.37002930096274594,
"grad_norm": 0.42208731174468994,
"learning_rate": 2e-05,
"loss": 0.7994,
"step": 4420
},
{
"epoch": 0.370866471326915,
"grad_norm": 0.4610078036785126,
"learning_rate": 2e-05,
"loss": 0.8222,
"step": 4430
},
{
"epoch": 0.3717036416910841,
"grad_norm": 0.41858646273612976,
"learning_rate": 2e-05,
"loss": 0.8421,
"step": 4440
},
{
"epoch": 0.37254081205525325,
"grad_norm": 0.47338756918907166,
"learning_rate": 2e-05,
"loss": 0.84,
"step": 4450
},
{
"epoch": 0.3733779824194223,
"grad_norm": 0.4165925979614258,
"learning_rate": 2e-05,
"loss": 0.8103,
"step": 4460
},
{
"epoch": 0.37421515278359146,
"grad_norm": 0.41632720828056335,
"learning_rate": 2e-05,
"loss": 0.833,
"step": 4470
},
{
"epoch": 0.37505232314776055,
"grad_norm": 0.4042990803718567,
"learning_rate": 2e-05,
"loss": 0.8246,
"step": 4480
},
{
"epoch": 0.3758894935119297,
"grad_norm": 0.4438692033290863,
"learning_rate": 2e-05,
"loss": 0.8333,
"step": 4490
},
{
"epoch": 0.37672666387609877,
"grad_norm": 0.4200449287891388,
"learning_rate": 2e-05,
"loss": 0.8242,
"step": 4500
},
{
"epoch": 0.3775638342402679,
"grad_norm": 0.4096335470676422,
"learning_rate": 2e-05,
"loss": 0.8156,
"step": 4510
},
{
"epoch": 0.378401004604437,
"grad_norm": 0.44866660237312317,
"learning_rate": 2e-05,
"loss": 0.8311,
"step": 4520
},
{
"epoch": 0.3792381749686061,
"grad_norm": 0.4202701449394226,
"learning_rate": 2e-05,
"loss": 0.8331,
"step": 4530
},
{
"epoch": 0.3800753453327752,
"grad_norm": 0.44000279903411865,
"learning_rate": 2e-05,
"loss": 0.8577,
"step": 4540
},
{
"epoch": 0.38091251569694434,
"grad_norm": 0.4213865399360657,
"learning_rate": 2e-05,
"loss": 0.8257,
"step": 4550
},
{
"epoch": 0.3817496860611134,
"grad_norm": 0.4106435775756836,
"learning_rate": 2e-05,
"loss": 0.8158,
"step": 4560
},
{
"epoch": 0.38258685642528256,
"grad_norm": 0.42261892557144165,
"learning_rate": 2e-05,
"loss": 0.8365,
"step": 4570
},
{
"epoch": 0.38342402678945164,
"grad_norm": 0.42611584067344666,
"learning_rate": 2e-05,
"loss": 0.8441,
"step": 4580
},
{
"epoch": 0.3842611971536208,
"grad_norm": 0.4328523874282837,
"learning_rate": 2e-05,
"loss": 0.8227,
"step": 4590
},
{
"epoch": 0.38509836751778986,
"grad_norm": 0.4371832609176636,
"learning_rate": 2e-05,
"loss": 0.8143,
"step": 4600
},
{
"epoch": 0.385935537881959,
"grad_norm": 0.44326528906822205,
"learning_rate": 2e-05,
"loss": 0.8204,
"step": 4610
},
{
"epoch": 0.3867727082461281,
"grad_norm": 0.4146097004413605,
"learning_rate": 2e-05,
"loss": 0.8255,
"step": 4620
},
{
"epoch": 0.3876098786102972,
"grad_norm": 0.4093981385231018,
"learning_rate": 2e-05,
"loss": 0.8407,
"step": 4630
},
{
"epoch": 0.3884470489744663,
"grad_norm": 0.4069594740867615,
"learning_rate": 2e-05,
"loss": 0.8501,
"step": 4640
},
{
"epoch": 0.38928421933863544,
"grad_norm": 0.42581525444984436,
"learning_rate": 2e-05,
"loss": 0.8113,
"step": 4650
},
{
"epoch": 0.3901213897028045,
"grad_norm": 0.40370485186576843,
"learning_rate": 2e-05,
"loss": 0.8108,
"step": 4660
},
{
"epoch": 0.3909585600669736,
"grad_norm": 0.42503565549850464,
"learning_rate": 2e-05,
"loss": 0.8327,
"step": 4670
},
{
"epoch": 0.39179573043114274,
"grad_norm": 0.4641563296318054,
"learning_rate": 2e-05,
"loss": 0.8133,
"step": 4680
},
{
"epoch": 0.3926329007953118,
"grad_norm": 0.4232136607170105,
"learning_rate": 2e-05,
"loss": 0.7952,
"step": 4690
},
{
"epoch": 0.39347007115948096,
"grad_norm": 0.4193868935108185,
"learning_rate": 2e-05,
"loss": 0.8256,
"step": 4700
},
{
"epoch": 0.39430724152365004,
"grad_norm": 0.43483099341392517,
"learning_rate": 2e-05,
"loss": 0.8425,
"step": 4710
},
{
"epoch": 0.3951444118878192,
"grad_norm": 0.425460547208786,
"learning_rate": 2e-05,
"loss": 0.8098,
"step": 4720
},
{
"epoch": 0.39598158225198826,
"grad_norm": 0.40391620993614197,
"learning_rate": 2e-05,
"loss": 0.835,
"step": 4730
},
{
"epoch": 0.3968187526161574,
"grad_norm": 0.4231874346733093,
"learning_rate": 2e-05,
"loss": 0.818,
"step": 4740
},
{
"epoch": 0.3976559229803265,
"grad_norm": 0.4210924804210663,
"learning_rate": 2e-05,
"loss": 0.8347,
"step": 4750
},
{
"epoch": 0.3984930933444956,
"grad_norm": 0.39859437942504883,
"learning_rate": 2e-05,
"loss": 0.8397,
"step": 4760
},
{
"epoch": 0.3993302637086647,
"grad_norm": 0.41163817048072815,
"learning_rate": 2e-05,
"loss": 0.8256,
"step": 4770
},
{
"epoch": 0.40016743407283384,
"grad_norm": 0.4214293360710144,
"learning_rate": 2e-05,
"loss": 0.8478,
"step": 4780
},
{
"epoch": 0.4010046044370029,
"grad_norm": 0.40330448746681213,
"learning_rate": 2e-05,
"loss": 0.8337,
"step": 4790
},
{
"epoch": 0.40184177480117206,
"grad_norm": 0.4489496350288391,
"learning_rate": 2e-05,
"loss": 0.8351,
"step": 4800
},
{
"epoch": 0.40267894516534114,
"grad_norm": 0.4314161241054535,
"learning_rate": 2e-05,
"loss": 0.801,
"step": 4810
},
{
"epoch": 0.4035161155295103,
"grad_norm": 0.4279036223888397,
"learning_rate": 2e-05,
"loss": 0.8279,
"step": 4820
},
{
"epoch": 0.40435328589367936,
"grad_norm": 0.41456297039985657,
"learning_rate": 2e-05,
"loss": 0.8196,
"step": 4830
},
{
"epoch": 0.4051904562578485,
"grad_norm": 0.41446003317832947,
"learning_rate": 2e-05,
"loss": 0.837,
"step": 4840
},
{
"epoch": 0.4060276266220176,
"grad_norm": 0.428045392036438,
"learning_rate": 2e-05,
"loss": 0.8272,
"step": 4850
},
{
"epoch": 0.4068647969861867,
"grad_norm": 0.42162343859672546,
"learning_rate": 2e-05,
"loss": 0.8537,
"step": 4860
},
{
"epoch": 0.4077019673503558,
"grad_norm": 0.4241536259651184,
"learning_rate": 2e-05,
"loss": 0.8161,
"step": 4870
},
{
"epoch": 0.4085391377145249,
"grad_norm": 0.42472705245018005,
"learning_rate": 2e-05,
"loss": 0.8267,
"step": 4880
},
{
"epoch": 0.409376308078694,
"grad_norm": 0.415218710899353,
"learning_rate": 2e-05,
"loss": 0.844,
"step": 4890
},
{
"epoch": 0.4102134784428631,
"grad_norm": 0.432001531124115,
"learning_rate": 2e-05,
"loss": 0.8059,
"step": 4900
},
{
"epoch": 0.41105064880703224,
"grad_norm": 0.41773557662963867,
"learning_rate": 2e-05,
"loss": 0.818,
"step": 4910
},
{
"epoch": 0.4118878191712013,
"grad_norm": 0.40862348675727844,
"learning_rate": 2e-05,
"loss": 0.8217,
"step": 4920
},
{
"epoch": 0.41272498953537046,
"grad_norm": 0.4347500205039978,
"learning_rate": 2e-05,
"loss": 0.8666,
"step": 4930
},
{
"epoch": 0.41356215989953954,
"grad_norm": 0.4370155930519104,
"learning_rate": 2e-05,
"loss": 0.8303,
"step": 4940
},
{
"epoch": 0.4143993302637087,
"grad_norm": 0.42120909690856934,
"learning_rate": 2e-05,
"loss": 0.8132,
"step": 4950
},
{
"epoch": 0.41523650062787776,
"grad_norm": 0.4310665428638458,
"learning_rate": 2e-05,
"loss": 0.8219,
"step": 4960
},
{
"epoch": 0.4160736709920469,
"grad_norm": 0.4336986243724823,
"learning_rate": 2e-05,
"loss": 0.8019,
"step": 4970
},
{
"epoch": 0.416910841356216,
"grad_norm": 0.4416171908378601,
"learning_rate": 2e-05,
"loss": 0.8289,
"step": 4980
},
{
"epoch": 0.4177480117203851,
"grad_norm": 0.41987624764442444,
"learning_rate": 2e-05,
"loss": 0.8182,
"step": 4990
},
{
"epoch": 0.4185851820845542,
"grad_norm": 0.43798530101776123,
"learning_rate": 2e-05,
"loss": 0.8369,
"step": 5000
},
{
"epoch": 0.41942235244872333,
"grad_norm": 0.4883551001548767,
"learning_rate": 2e-05,
"loss": 0.8616,
"step": 5010
},
{
"epoch": 0.4202595228128924,
"grad_norm": 0.46935969591140747,
"learning_rate": 2e-05,
"loss": 0.8396,
"step": 5020
},
{
"epoch": 0.42109669317706155,
"grad_norm": 0.4080098569393158,
"learning_rate": 2e-05,
"loss": 0.8062,
"step": 5030
},
{
"epoch": 0.42193386354123064,
"grad_norm": 0.4224624037742615,
"learning_rate": 2e-05,
"loss": 0.7853,
"step": 5040
},
{
"epoch": 0.4227710339053998,
"grad_norm": 0.42404913902282715,
"learning_rate": 2e-05,
"loss": 0.8284,
"step": 5050
},
{
"epoch": 0.42360820426956886,
"grad_norm": 0.423594206571579,
"learning_rate": 2e-05,
"loss": 0.8183,
"step": 5060
},
{
"epoch": 0.424445374633738,
"grad_norm": 0.43580183386802673,
"learning_rate": 2e-05,
"loss": 0.8207,
"step": 5070
},
{
"epoch": 0.4252825449979071,
"grad_norm": 0.4515228867530823,
"learning_rate": 2e-05,
"loss": 0.8067,
"step": 5080
},
{
"epoch": 0.42611971536207616,
"grad_norm": 0.41995805501937866,
"learning_rate": 1.9999810479633703e-05,
"loss": 0.8382,
"step": 5090
},
{
"epoch": 0.4269568857262453,
"grad_norm": 0.4237562119960785,
"learning_rate": 1.997707677020786e-05,
"loss": 0.8264,
"step": 5100
},
{
"epoch": 0.4277940560904144,
"grad_norm": 0.4281562864780426,
"learning_rate": 1.9916538196124637e-05,
"loss": 0.8117,
"step": 5110
},
{
"epoch": 0.4286312264545835,
"grad_norm": 0.4315643906593323,
"learning_rate": 1.9818425303863402e-05,
"loss": 0.8359,
"step": 5120
},
{
"epoch": 0.4294683968187526,
"grad_norm": 0.4087998569011688,
"learning_rate": 1.9683111732582887e-05,
"loss": 0.8292,
"step": 5130
},
{
"epoch": 0.43030556718292173,
"grad_norm": 0.4139174520969391,
"learning_rate": 1.951111279120706e-05,
"loss": 0.8209,
"step": 5140
},
{
"epoch": 0.4311427375470908,
"grad_norm": 0.4710979759693146,
"learning_rate": 1.9303083495996028e-05,
"loss": 0.8384,
"step": 5150
},
{
"epoch": 0.43197990791125995,
"grad_norm": 0.4124601483345032,
"learning_rate": 1.9059816076075482e-05,
"loss": 0.8166,
"step": 5160
},
{
"epoch": 0.43281707827542903,
"grad_norm": 0.41296881437301636,
"learning_rate": 1.8782236956424142e-05,
"loss": 0.8198,
"step": 5170
},
{
"epoch": 0.43365424863959817,
"grad_norm": 0.4230596721172333,
"learning_rate": 1.8471403229808897e-05,
"loss": 0.8085,
"step": 5180
},
{
"epoch": 0.43449141900376725,
"grad_norm": 0.41695263981819153,
"learning_rate": 1.8128498631103333e-05,
"loss": 0.8415,
"step": 5190
},
{
"epoch": 0.4353285893679364,
"grad_norm": 0.4144802391529083,
"learning_rate": 1.7754829029320507e-05,
"loss": 0.8069,
"step": 5200
},
{
"epoch": 0.4361657597321055,
"grad_norm": 0.42298662662506104,
"learning_rate": 1.7351817454527473e-05,
"loss": 0.8303,
"step": 5210
},
{
"epoch": 0.4370029300962746,
"grad_norm": 0.4189456105232239,
"learning_rate": 1.6920998678580345e-05,
"loss": 0.7994,
"step": 5220
},
{
"epoch": 0.4378401004604437,
"grad_norm": 0.4280220568180084,
"learning_rate": 1.6464013370317854e-05,
"loss": 0.8445,
"step": 5230
},
{
"epoch": 0.43867727082461283,
"grad_norm": 0.4229801297187805,
"learning_rate": 1.5982601847471915e-05,
"loss": 0.8133,
"step": 5240
},
{
"epoch": 0.4395144411887819,
"grad_norm": 0.42390570044517517,
"learning_rate": 1.5478597449089553e-05,
"loss": 0.827,
"step": 5250
},
{
"epoch": 0.44035161155295105,
"grad_norm": 0.4077486991882324,
"learning_rate": 1.4953919553705725e-05,
"loss": 0.8192,
"step": 5260
},
{
"epoch": 0.44118878191712013,
"grad_norm": 0.41402313113212585,
"learning_rate": 1.441056626985559e-05,
"loss": 0.8283,
"step": 5270
},
{
"epoch": 0.44202595228128927,
"grad_norm": 0.39898577332496643,
"learning_rate": 1.3850606826762668e-05,
"loss": 0.808,
"step": 5280
},
{
"epoch": 0.44286312264545835,
"grad_norm": 0.42293351888656616,
"learning_rate": 1.3276173694181128e-05,
"loss": 0.8378,
"step": 5290
},
{
"epoch": 0.44370029300962743,
"grad_norm": 0.4331302046775818,
"learning_rate": 1.2689454461401822e-05,
"loss": 0.8233,
"step": 5300
},
{
"epoch": 0.44453746337379657,
"grad_norm": 0.43309012055397034,
"learning_rate": 1.2092683506348939e-05,
"loss": 0.7984,
"step": 5310
},
{
"epoch": 0.44537463373796565,
"grad_norm": 0.4053444266319275,
"learning_rate": 1.14881334864935e-05,
"loss": 0.786,
"step": 5320
},
{
"epoch": 0.4462118041021348,
"grad_norm": 0.40127238631248474,
"learning_rate": 1.0878106683988481e-05,
"loss": 0.8203,
"step": 5330
},
{
"epoch": 0.4470489744663039,
"grad_norm": 0.4119478464126587,
"learning_rate": 1.026492623798551e-05,
"loss": 0.7902,
"step": 5340
},
{
"epoch": 0.447886144830473,
"grad_norm": 0.43283018469810486,
"learning_rate": 9.650927297522743e-06,
"loss": 0.8103,
"step": 5350
},
{
"epoch": 0.4487233151946421,
"grad_norm": 0.39513882994651794,
"learning_rate": 9.038448128676012e-06,
"loss": 0.798,
"step": 5360
},
{
"epoch": 0.44956048555881123,
"grad_norm": 0.4041348993778229,
"learning_rate": 8.42982120983949e-06,
"loss": 0.8135,
"step": 5370
},
{
"epoch": 0.4503976559229803,
"grad_norm": 0.4008016288280487,
"learning_rate": 7.827364349047303e-06,
"loss": 0.7889,
"step": 5380
},
{
"epoch": 0.45123482628714945,
"grad_norm": 0.41570982336997986,
"learning_rate": 7.233371857163706e-06,
"loss": 0.7989,
"step": 5390
},
{
"epoch": 0.45207199665131853,
"grad_norm": 0.42794978618621826,
"learning_rate": 6.650105810556492e-06,
"loss": 0.799,
"step": 5400
},
{
"epoch": 0.45290916701548767,
"grad_norm": 0.40999123454093933,
"learning_rate": 6.079787436527681e-06,
"loss": 0.7763,
"step": 5410
},
{
"epoch": 0.45374633737965675,
"grad_norm": 0.39142709970474243,
"learning_rate": 5.524588654307961e-06,
"loss": 0.7982,
"step": 5420
},
{
"epoch": 0.4545835077438259,
"grad_norm": 0.3829934298992157,
"learning_rate": 4.986623803828985e-06,
"loss": 0.7884,
"step": 5430
},
{
"epoch": 0.45542067810799497,
"grad_norm": 0.4008808732032776,
"learning_rate": 4.467941593772423e-06,
"loss": 0.7819,
"step": 5440
},
{
"epoch": 0.4562578484721641,
"grad_norm": 0.40441596508026123,
"learning_rate": 3.9705172995597606e-06,
"loss": 0.8241,
"step": 5450
},
{
"epoch": 0.4570950188363332,
"grad_norm": 0.4000427722930908,
"learning_rate": 3.4962452409948346e-06,
"loss": 0.8266,
"step": 5460
},
{
"epoch": 0.4579321892005023,
"grad_norm": 0.4030681252479553,
"learning_rate": 3.046931568206211e-06,
"loss": 0.8,
"step": 5470
},
{
"epoch": 0.4587693595646714,
"grad_norm": 0.3945789039134979,
"learning_rate": 2.624287383362404e-06,
"loss": 0.8219,
"step": 5480
},
{
"epoch": 0.45960652992884055,
"grad_norm": 0.4006154537200928,
"learning_rate": 2.2299222243541845e-06,
"loss": 0.8231,
"step": 5490
},
{
"epoch": 0.46044370029300963,
"grad_norm": 0.4019671082496643,
"learning_rate": 1.8653379352598246e-06,
"loss": 0.7808,
"step": 5500
},
{
"epoch": 0.4612808706571787,
"grad_norm": 0.3889995515346527,
"learning_rate": 1.5319229469361075e-06,
"loss": 0.8121,
"step": 5510
},
{
"epoch": 0.46211804102134785,
"grad_norm": 0.38585489988327026,
"learning_rate": 1.2309469895160917e-06,
"loss": 0.799,
"step": 5520
},
{
"epoch": 0.46295521138551693,
"grad_norm": 0.3910485804080963,
"learning_rate": 9.635562569497974e-07,
"loss": 0.8085,
"step": 5530
},
{
"epoch": 0.46379238174968607,
"grad_norm": 0.4955495595932007,
"learning_rate": 7.307690420024867e-07,
"loss": 0.8201,
"step": 5540
},
{
"epoch": 0.46462955211385515,
"grad_norm": 0.39832013845443726,
"learning_rate": 5.334718583335942e-07,
"loss": 0.8119,
"step": 5550
},
{
"epoch": 0.4654667224780243,
"grad_norm": 0.38776344060897827,
"learning_rate": 3.7241606442442763e-07,
"loss": 0.7765,
"step": 5560
},
{
"epoch": 0.46630389284219337,
"grad_norm": 0.405020534992218,
"learning_rate": 2.482150022115879e-07,
"loss": 0.7886,
"step": 5570
},
{
"epoch": 0.4671410632063625,
"grad_norm": 0.4081546664237976,
"learning_rate": 1.6134166132293174e-07,
"loss": 0.7932,
"step": 5580
},
{
"epoch": 0.4679782335705316,
"grad_norm": 0.3950470983982086,
"learning_rate": 1.1212687781127357e-07,
"loss": 0.7593,
"step": 5590
},
{
"epoch": 0.46856425282545,
"step": 5597,
"total_flos": 2.2737574718397743e+19,
"train_loss": 0.0271956187093686,
"train_runtime": 1791.5793,
"train_samples_per_second": 37.489,
"train_steps_per_second": 3.124
}
],
"logging_steps": 10,
"max_steps": 5597,
"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": 2.2737574718397743e+19,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.46856425282545,
"eval_steps": 500,
"global_step": 5597,
"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,