0x70DA's picture
Training in progress, step 4200
bfeb8af
{
"best_metric": 1.288108468055725,
"best_model_checkpoint": "outputs/checkpoint-4200",
"epoch": 1.4373716632443532,
"global_step": 4200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 1e-05,
"loss": 1.8606,
"step": 5
},
{
"epoch": 0.0,
"learning_rate": 2e-05,
"loss": 1.8806,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 3e-05,
"loss": 1.8434,
"step": 15
},
{
"epoch": 0.01,
"learning_rate": 4e-05,
"loss": 1.7431,
"step": 20
},
{
"epoch": 0.01,
"learning_rate": 5e-05,
"loss": 1.7721,
"step": 25
},
{
"epoch": 0.01,
"learning_rate": 6e-05,
"loss": 1.6826,
"step": 30
},
{
"epoch": 0.01,
"learning_rate": 7e-05,
"loss": 1.5892,
"step": 35
},
{
"epoch": 0.01,
"learning_rate": 8e-05,
"loss": 1.6333,
"step": 40
},
{
"epoch": 0.02,
"learning_rate": 9e-05,
"loss": 1.5955,
"step": 45
},
{
"epoch": 0.02,
"learning_rate": 0.0001,
"loss": 1.5504,
"step": 50
},
{
"epoch": 0.02,
"learning_rate": 0.00011000000000000002,
"loss": 1.5621,
"step": 55
},
{
"epoch": 0.02,
"learning_rate": 0.00012,
"loss": 1.5142,
"step": 60
},
{
"epoch": 0.02,
"learning_rate": 0.00013000000000000002,
"loss": 1.4386,
"step": 65
},
{
"epoch": 0.02,
"learning_rate": 0.00014,
"loss": 1.5017,
"step": 70
},
{
"epoch": 0.03,
"learning_rate": 0.00015000000000000001,
"loss": 1.4666,
"step": 75
},
{
"epoch": 0.03,
"learning_rate": 0.00016,
"loss": 1.4295,
"step": 80
},
{
"epoch": 0.03,
"learning_rate": 0.00017,
"loss": 1.4402,
"step": 85
},
{
"epoch": 0.03,
"learning_rate": 0.00018,
"loss": 1.4795,
"step": 90
},
{
"epoch": 0.03,
"learning_rate": 0.00019,
"loss": 1.4138,
"step": 95
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 1.4493,
"step": 100
},
{
"epoch": 0.04,
"learning_rate": 0.0001998259052924791,
"loss": 1.4918,
"step": 105
},
{
"epoch": 0.04,
"learning_rate": 0.00019965181058495822,
"loss": 1.4659,
"step": 110
},
{
"epoch": 0.04,
"learning_rate": 0.00019947771587743734,
"loss": 1.4573,
"step": 115
},
{
"epoch": 0.04,
"learning_rate": 0.00019930362116991646,
"loss": 1.4274,
"step": 120
},
{
"epoch": 0.04,
"learning_rate": 0.00019912952646239555,
"loss": 1.4064,
"step": 125
},
{
"epoch": 0.04,
"learning_rate": 0.00019895543175487465,
"loss": 1.4048,
"step": 130
},
{
"epoch": 0.05,
"learning_rate": 0.00019878133704735376,
"loss": 1.4493,
"step": 135
},
{
"epoch": 0.05,
"learning_rate": 0.00019860724233983288,
"loss": 1.3317,
"step": 140
},
{
"epoch": 0.05,
"learning_rate": 0.00019843314763231198,
"loss": 1.4041,
"step": 145
},
{
"epoch": 0.05,
"learning_rate": 0.0001982590529247911,
"loss": 1.4311,
"step": 150
},
{
"epoch": 0.05,
"learning_rate": 0.0001980849582172702,
"loss": 1.3626,
"step": 155
},
{
"epoch": 0.05,
"learning_rate": 0.00019791086350974934,
"loss": 1.4296,
"step": 160
},
{
"epoch": 0.06,
"learning_rate": 0.00019773676880222843,
"loss": 1.3888,
"step": 165
},
{
"epoch": 0.06,
"learning_rate": 0.00019756267409470752,
"loss": 1.3389,
"step": 170
},
{
"epoch": 0.06,
"learning_rate": 0.00019738857938718664,
"loss": 1.4544,
"step": 175
},
{
"epoch": 0.06,
"learning_rate": 0.00019721448467966573,
"loss": 1.4382,
"step": 180
},
{
"epoch": 0.06,
"learning_rate": 0.00019704038997214485,
"loss": 1.4953,
"step": 185
},
{
"epoch": 0.07,
"learning_rate": 0.00019686629526462397,
"loss": 1.4026,
"step": 190
},
{
"epoch": 0.07,
"learning_rate": 0.00019669220055710306,
"loss": 1.3757,
"step": 195
},
{
"epoch": 0.07,
"learning_rate": 0.00019651810584958218,
"loss": 1.3247,
"step": 200
},
{
"epoch": 0.07,
"eval_loss": 1.3710952997207642,
"eval_runtime": 738.1164,
"eval_samples_per_second": 7.038,
"eval_steps_per_second": 0.881,
"step": 200
},
{
"epoch": 0.07,
"learning_rate": 0.0001963440111420613,
"loss": 1.4409,
"step": 205
},
{
"epoch": 0.07,
"learning_rate": 0.0001961699164345404,
"loss": 1.4023,
"step": 210
},
{
"epoch": 0.07,
"learning_rate": 0.00019599582172701951,
"loss": 1.3736,
"step": 215
},
{
"epoch": 0.08,
"learning_rate": 0.0001958217270194986,
"loss": 1.4321,
"step": 220
},
{
"epoch": 0.08,
"learning_rate": 0.00019564763231197773,
"loss": 1.4344,
"step": 225
},
{
"epoch": 0.08,
"learning_rate": 0.00019547353760445685,
"loss": 1.3539,
"step": 230
},
{
"epoch": 0.08,
"learning_rate": 0.00019529944289693594,
"loss": 1.438,
"step": 235
},
{
"epoch": 0.08,
"learning_rate": 0.00019512534818941506,
"loss": 1.457,
"step": 240
},
{
"epoch": 0.08,
"learning_rate": 0.00019495125348189415,
"loss": 1.429,
"step": 245
},
{
"epoch": 0.09,
"learning_rate": 0.00019477715877437327,
"loss": 1.4465,
"step": 250
},
{
"epoch": 0.09,
"learning_rate": 0.0001946030640668524,
"loss": 1.4202,
"step": 255
},
{
"epoch": 0.09,
"learning_rate": 0.00019442896935933148,
"loss": 1.343,
"step": 260
},
{
"epoch": 0.09,
"learning_rate": 0.0001942548746518106,
"loss": 1.4127,
"step": 265
},
{
"epoch": 0.09,
"learning_rate": 0.0001940807799442897,
"loss": 1.3171,
"step": 270
},
{
"epoch": 0.09,
"learning_rate": 0.0001939066852367688,
"loss": 1.4012,
"step": 275
},
{
"epoch": 0.1,
"learning_rate": 0.00019373259052924793,
"loss": 1.2933,
"step": 280
},
{
"epoch": 0.1,
"learning_rate": 0.00019355849582172702,
"loss": 1.326,
"step": 285
},
{
"epoch": 0.1,
"learning_rate": 0.00019338440111420614,
"loss": 1.3951,
"step": 290
},
{
"epoch": 0.1,
"learning_rate": 0.00019321030640668524,
"loss": 1.3149,
"step": 295
},
{
"epoch": 0.1,
"learning_rate": 0.00019303621169916436,
"loss": 1.4046,
"step": 300
},
{
"epoch": 0.1,
"learning_rate": 0.00019286211699164348,
"loss": 1.343,
"step": 305
},
{
"epoch": 0.11,
"learning_rate": 0.00019268802228412257,
"loss": 1.3676,
"step": 310
},
{
"epoch": 0.11,
"learning_rate": 0.00019251392757660166,
"loss": 1.3593,
"step": 315
},
{
"epoch": 0.11,
"learning_rate": 0.0001923398328690808,
"loss": 1.3869,
"step": 320
},
{
"epoch": 0.11,
"learning_rate": 0.0001921657381615599,
"loss": 1.3841,
"step": 325
},
{
"epoch": 0.11,
"learning_rate": 0.00019199164345403902,
"loss": 1.3806,
"step": 330
},
{
"epoch": 0.11,
"learning_rate": 0.0001918175487465181,
"loss": 1.4527,
"step": 335
},
{
"epoch": 0.12,
"learning_rate": 0.0001916434540389972,
"loss": 1.4161,
"step": 340
},
{
"epoch": 0.12,
"learning_rate": 0.00019146935933147635,
"loss": 1.3019,
"step": 345
},
{
"epoch": 0.12,
"learning_rate": 0.00019129526462395544,
"loss": 1.4082,
"step": 350
},
{
"epoch": 0.12,
"learning_rate": 0.00019112116991643454,
"loss": 1.4261,
"step": 355
},
{
"epoch": 0.12,
"learning_rate": 0.00019094707520891365,
"loss": 1.4152,
"step": 360
},
{
"epoch": 0.12,
"learning_rate": 0.00019077298050139277,
"loss": 1.4289,
"step": 365
},
{
"epoch": 0.13,
"learning_rate": 0.0001905988857938719,
"loss": 1.3951,
"step": 370
},
{
"epoch": 0.13,
"learning_rate": 0.00019042479108635099,
"loss": 1.3578,
"step": 375
},
{
"epoch": 0.13,
"learning_rate": 0.00019025069637883008,
"loss": 1.3342,
"step": 380
},
{
"epoch": 0.13,
"learning_rate": 0.0001900766016713092,
"loss": 1.3959,
"step": 385
},
{
"epoch": 0.13,
"learning_rate": 0.00018990250696378832,
"loss": 1.4336,
"step": 390
},
{
"epoch": 0.14,
"learning_rate": 0.00018972841225626744,
"loss": 1.464,
"step": 395
},
{
"epoch": 0.14,
"learning_rate": 0.00018955431754874653,
"loss": 1.4053,
"step": 400
},
{
"epoch": 0.14,
"eval_loss": 1.3470327854156494,
"eval_runtime": 738.9389,
"eval_samples_per_second": 7.03,
"eval_steps_per_second": 0.88,
"step": 400
},
{
"epoch": 0.14,
"learning_rate": 0.00018938022284122562,
"loss": 1.3582,
"step": 405
},
{
"epoch": 0.14,
"learning_rate": 0.00018920612813370474,
"loss": 1.375,
"step": 410
},
{
"epoch": 0.14,
"learning_rate": 0.00018903203342618386,
"loss": 1.4229,
"step": 415
},
{
"epoch": 0.14,
"learning_rate": 0.00018885793871866295,
"loss": 1.3843,
"step": 420
},
{
"epoch": 0.15,
"learning_rate": 0.00018868384401114207,
"loss": 1.39,
"step": 425
},
{
"epoch": 0.15,
"learning_rate": 0.00018850974930362116,
"loss": 1.3863,
"step": 430
},
{
"epoch": 0.15,
"learning_rate": 0.00018833565459610028,
"loss": 1.3597,
"step": 435
},
{
"epoch": 0.15,
"learning_rate": 0.0001881615598885794,
"loss": 1.4114,
"step": 440
},
{
"epoch": 0.15,
"learning_rate": 0.0001879874651810585,
"loss": 1.2929,
"step": 445
},
{
"epoch": 0.15,
"learning_rate": 0.00018781337047353762,
"loss": 1.3087,
"step": 450
},
{
"epoch": 0.16,
"learning_rate": 0.0001876392757660167,
"loss": 1.3748,
"step": 455
},
{
"epoch": 0.16,
"learning_rate": 0.00018746518105849583,
"loss": 1.3716,
"step": 460
},
{
"epoch": 0.16,
"learning_rate": 0.00018729108635097495,
"loss": 1.404,
"step": 465
},
{
"epoch": 0.16,
"learning_rate": 0.00018711699164345404,
"loss": 1.2931,
"step": 470
},
{
"epoch": 0.16,
"learning_rate": 0.00018694289693593316,
"loss": 1.3345,
"step": 475
},
{
"epoch": 0.16,
"learning_rate": 0.00018676880222841225,
"loss": 1.3836,
"step": 480
},
{
"epoch": 0.17,
"learning_rate": 0.00018659470752089137,
"loss": 1.3923,
"step": 485
},
{
"epoch": 0.17,
"learning_rate": 0.0001864206128133705,
"loss": 1.3166,
"step": 490
},
{
"epoch": 0.17,
"learning_rate": 0.00018624651810584958,
"loss": 1.3697,
"step": 495
},
{
"epoch": 0.17,
"learning_rate": 0.0001860724233983287,
"loss": 1.437,
"step": 500
},
{
"epoch": 0.17,
"learning_rate": 0.00018589832869080782,
"loss": 1.3579,
"step": 505
},
{
"epoch": 0.17,
"learning_rate": 0.00018572423398328691,
"loss": 1.3769,
"step": 510
},
{
"epoch": 0.18,
"learning_rate": 0.00018555013927576603,
"loss": 1.3989,
"step": 515
},
{
"epoch": 0.18,
"learning_rate": 0.00018537604456824513,
"loss": 1.331,
"step": 520
},
{
"epoch": 0.18,
"learning_rate": 0.00018520194986072425,
"loss": 1.3678,
"step": 525
},
{
"epoch": 0.18,
"learning_rate": 0.00018502785515320337,
"loss": 1.3475,
"step": 530
},
{
"epoch": 0.18,
"learning_rate": 0.00018485376044568246,
"loss": 1.4465,
"step": 535
},
{
"epoch": 0.18,
"learning_rate": 0.00018467966573816158,
"loss": 1.3304,
"step": 540
},
{
"epoch": 0.19,
"learning_rate": 0.00018450557103064067,
"loss": 1.4006,
"step": 545
},
{
"epoch": 0.19,
"learning_rate": 0.0001843314763231198,
"loss": 1.3645,
"step": 550
},
{
"epoch": 0.19,
"learning_rate": 0.0001841573816155989,
"loss": 1.3217,
"step": 555
},
{
"epoch": 0.19,
"learning_rate": 0.000183983286908078,
"loss": 1.3421,
"step": 560
},
{
"epoch": 0.19,
"learning_rate": 0.0001838091922005571,
"loss": 1.3283,
"step": 565
},
{
"epoch": 0.2,
"learning_rate": 0.0001836350974930362,
"loss": 1.4101,
"step": 570
},
{
"epoch": 0.2,
"learning_rate": 0.00018346100278551533,
"loss": 1.3333,
"step": 575
},
{
"epoch": 0.2,
"learning_rate": 0.00018328690807799445,
"loss": 1.4574,
"step": 580
},
{
"epoch": 0.2,
"learning_rate": 0.00018311281337047354,
"loss": 1.3755,
"step": 585
},
{
"epoch": 0.2,
"learning_rate": 0.00018293871866295264,
"loss": 1.3537,
"step": 590
},
{
"epoch": 0.2,
"learning_rate": 0.00018276462395543176,
"loss": 1.3734,
"step": 595
},
{
"epoch": 0.21,
"learning_rate": 0.00018259052924791088,
"loss": 1.3431,
"step": 600
},
{
"epoch": 0.21,
"eval_loss": 1.3354507684707642,
"eval_runtime": 738.7441,
"eval_samples_per_second": 7.032,
"eval_steps_per_second": 0.88,
"step": 600
},
{
"epoch": 0.21,
"learning_rate": 0.00018241643454039,
"loss": 1.3685,
"step": 605
},
{
"epoch": 0.21,
"learning_rate": 0.0001822423398328691,
"loss": 1.377,
"step": 610
},
{
"epoch": 0.21,
"learning_rate": 0.00018206824512534818,
"loss": 1.4289,
"step": 615
},
{
"epoch": 0.21,
"learning_rate": 0.00018189415041782733,
"loss": 1.398,
"step": 620
},
{
"epoch": 0.21,
"learning_rate": 0.00018172005571030642,
"loss": 1.3915,
"step": 625
},
{
"epoch": 0.22,
"learning_rate": 0.0001815459610027855,
"loss": 1.4608,
"step": 630
},
{
"epoch": 0.22,
"learning_rate": 0.00018137186629526463,
"loss": 1.4408,
"step": 635
},
{
"epoch": 0.22,
"learning_rate": 0.00018119777158774372,
"loss": 1.3443,
"step": 640
},
{
"epoch": 0.22,
"learning_rate": 0.00018102367688022287,
"loss": 1.4033,
"step": 645
},
{
"epoch": 0.22,
"learning_rate": 0.00018084958217270196,
"loss": 1.3086,
"step": 650
},
{
"epoch": 0.22,
"learning_rate": 0.00018067548746518105,
"loss": 1.3581,
"step": 655
},
{
"epoch": 0.23,
"learning_rate": 0.00018050139275766017,
"loss": 1.3457,
"step": 660
},
{
"epoch": 0.23,
"learning_rate": 0.0001803272980501393,
"loss": 1.4488,
"step": 665
},
{
"epoch": 0.23,
"learning_rate": 0.0001801532033426184,
"loss": 1.3765,
"step": 670
},
{
"epoch": 0.23,
"learning_rate": 0.0001799791086350975,
"loss": 1.4061,
"step": 675
},
{
"epoch": 0.23,
"learning_rate": 0.0001798050139275766,
"loss": 1.3556,
"step": 680
},
{
"epoch": 0.23,
"learning_rate": 0.00017963091922005572,
"loss": 1.3359,
"step": 685
},
{
"epoch": 0.24,
"learning_rate": 0.00017945682451253484,
"loss": 1.2965,
"step": 690
},
{
"epoch": 0.24,
"learning_rate": 0.00017928272980501393,
"loss": 1.3211,
"step": 695
},
{
"epoch": 0.24,
"learning_rate": 0.00017910863509749305,
"loss": 1.4063,
"step": 700
},
{
"epoch": 0.24,
"learning_rate": 0.00017893454038997214,
"loss": 1.3837,
"step": 705
},
{
"epoch": 0.24,
"learning_rate": 0.00017876044568245126,
"loss": 1.397,
"step": 710
},
{
"epoch": 0.24,
"learning_rate": 0.00017858635097493038,
"loss": 1.3671,
"step": 715
},
{
"epoch": 0.25,
"learning_rate": 0.00017841225626740947,
"loss": 1.3666,
"step": 720
},
{
"epoch": 0.25,
"learning_rate": 0.0001782381615598886,
"loss": 1.3875,
"step": 725
},
{
"epoch": 0.25,
"learning_rate": 0.00017806406685236768,
"loss": 1.3613,
"step": 730
},
{
"epoch": 0.25,
"learning_rate": 0.0001778899721448468,
"loss": 1.3611,
"step": 735
},
{
"epoch": 0.25,
"learning_rate": 0.00017771587743732592,
"loss": 1.357,
"step": 740
},
{
"epoch": 0.25,
"learning_rate": 0.00017754178272980502,
"loss": 1.3561,
"step": 745
},
{
"epoch": 0.26,
"learning_rate": 0.00017736768802228414,
"loss": 1.4103,
"step": 750
},
{
"epoch": 0.26,
"learning_rate": 0.00017719359331476323,
"loss": 1.4355,
"step": 755
},
{
"epoch": 0.26,
"learning_rate": 0.00017701949860724235,
"loss": 1.3901,
"step": 760
},
{
"epoch": 0.26,
"learning_rate": 0.00017684540389972147,
"loss": 1.4161,
"step": 765
},
{
"epoch": 0.26,
"learning_rate": 0.00017667130919220056,
"loss": 1.4353,
"step": 770
},
{
"epoch": 0.27,
"learning_rate": 0.00017649721448467968,
"loss": 1.3647,
"step": 775
},
{
"epoch": 0.27,
"learning_rate": 0.0001763231197771588,
"loss": 1.3503,
"step": 780
},
{
"epoch": 0.27,
"learning_rate": 0.0001761490250696379,
"loss": 1.3034,
"step": 785
},
{
"epoch": 0.27,
"learning_rate": 0.000175974930362117,
"loss": 1.3908,
"step": 790
},
{
"epoch": 0.27,
"learning_rate": 0.0001758008356545961,
"loss": 1.3361,
"step": 795
},
{
"epoch": 0.27,
"learning_rate": 0.0001756267409470752,
"loss": 1.4012,
"step": 800
},
{
"epoch": 0.27,
"eval_loss": 1.3277837038040161,
"eval_runtime": 737.1439,
"eval_samples_per_second": 7.047,
"eval_steps_per_second": 0.882,
"step": 800
},
{
"epoch": 0.28,
"learning_rate": 0.00017545264623955434,
"loss": 1.3631,
"step": 805
},
{
"epoch": 0.28,
"learning_rate": 0.00017527855153203343,
"loss": 1.3789,
"step": 810
},
{
"epoch": 0.28,
"learning_rate": 0.00017510445682451255,
"loss": 1.3418,
"step": 815
},
{
"epoch": 0.28,
"learning_rate": 0.00017493036211699165,
"loss": 1.3556,
"step": 820
},
{
"epoch": 0.28,
"learning_rate": 0.00017475626740947077,
"loss": 1.339,
"step": 825
},
{
"epoch": 0.28,
"learning_rate": 0.00017458217270194989,
"loss": 1.3419,
"step": 830
},
{
"epoch": 0.29,
"learning_rate": 0.00017440807799442898,
"loss": 1.2919,
"step": 835
},
{
"epoch": 0.29,
"learning_rate": 0.00017423398328690807,
"loss": 1.3757,
"step": 840
},
{
"epoch": 0.29,
"learning_rate": 0.0001740598885793872,
"loss": 1.3165,
"step": 845
},
{
"epoch": 0.29,
"learning_rate": 0.0001738857938718663,
"loss": 1.325,
"step": 850
},
{
"epoch": 0.29,
"learning_rate": 0.00017371169916434543,
"loss": 1.3846,
"step": 855
},
{
"epoch": 0.29,
"learning_rate": 0.00017353760445682452,
"loss": 1.393,
"step": 860
},
{
"epoch": 0.3,
"learning_rate": 0.0001733635097493036,
"loss": 1.3176,
"step": 865
},
{
"epoch": 0.3,
"learning_rate": 0.00017318941504178273,
"loss": 1.3603,
"step": 870
},
{
"epoch": 0.3,
"learning_rate": 0.00017301532033426185,
"loss": 1.3858,
"step": 875
},
{
"epoch": 0.3,
"learning_rate": 0.00017284122562674097,
"loss": 1.3801,
"step": 880
},
{
"epoch": 0.3,
"learning_rate": 0.00017266713091922006,
"loss": 1.3258,
"step": 885
},
{
"epoch": 0.3,
"learning_rate": 0.00017249303621169916,
"loss": 1.3958,
"step": 890
},
{
"epoch": 0.31,
"learning_rate": 0.00017231894150417828,
"loss": 1.3352,
"step": 895
},
{
"epoch": 0.31,
"learning_rate": 0.0001721448467966574,
"loss": 1.3546,
"step": 900
},
{
"epoch": 0.31,
"learning_rate": 0.0001719707520891365,
"loss": 1.3576,
"step": 905
},
{
"epoch": 0.31,
"learning_rate": 0.0001717966573816156,
"loss": 1.5061,
"step": 910
},
{
"epoch": 0.31,
"learning_rate": 0.0001716225626740947,
"loss": 1.3496,
"step": 915
},
{
"epoch": 0.31,
"learning_rate": 0.00017144846796657385,
"loss": 1.4537,
"step": 920
},
{
"epoch": 0.32,
"learning_rate": 0.00017127437325905294,
"loss": 1.4241,
"step": 925
},
{
"epoch": 0.32,
"learning_rate": 0.00017110027855153203,
"loss": 1.4109,
"step": 930
},
{
"epoch": 0.32,
"learning_rate": 0.00017092618384401115,
"loss": 1.4104,
"step": 935
},
{
"epoch": 0.32,
"learning_rate": 0.00017075208913649024,
"loss": 1.4555,
"step": 940
},
{
"epoch": 0.32,
"learning_rate": 0.00017057799442896936,
"loss": 1.2743,
"step": 945
},
{
"epoch": 0.33,
"learning_rate": 0.00017040389972144848,
"loss": 1.3573,
"step": 950
},
{
"epoch": 0.33,
"learning_rate": 0.00017022980501392757,
"loss": 1.3463,
"step": 955
},
{
"epoch": 0.33,
"learning_rate": 0.0001700557103064067,
"loss": 1.3817,
"step": 960
},
{
"epoch": 0.33,
"learning_rate": 0.0001698816155988858,
"loss": 1.4315,
"step": 965
},
{
"epoch": 0.33,
"learning_rate": 0.0001697075208913649,
"loss": 1.3112,
"step": 970
},
{
"epoch": 0.33,
"learning_rate": 0.00016953342618384403,
"loss": 1.3998,
"step": 975
},
{
"epoch": 0.34,
"learning_rate": 0.00016935933147632312,
"loss": 1.3697,
"step": 980
},
{
"epoch": 0.34,
"learning_rate": 0.00016918523676880224,
"loss": 1.3726,
"step": 985
},
{
"epoch": 0.34,
"learning_rate": 0.00016901114206128136,
"loss": 1.4137,
"step": 990
},
{
"epoch": 0.34,
"learning_rate": 0.00016883704735376045,
"loss": 1.3371,
"step": 995
},
{
"epoch": 0.34,
"learning_rate": 0.00016866295264623957,
"loss": 1.3189,
"step": 1000
},
{
"epoch": 0.34,
"eval_loss": 1.3234615325927734,
"eval_runtime": 736.9447,
"eval_samples_per_second": 7.049,
"eval_steps_per_second": 0.882,
"step": 1000
},
{
"epoch": 0.34,
"learning_rate": 0.00016848885793871866,
"loss": 1.3207,
"step": 1005
},
{
"epoch": 0.35,
"learning_rate": 0.00016831476323119778,
"loss": 1.3369,
"step": 1010
},
{
"epoch": 0.35,
"learning_rate": 0.0001681406685236769,
"loss": 1.3205,
"step": 1015
},
{
"epoch": 0.35,
"learning_rate": 0.000167966573816156,
"loss": 1.3124,
"step": 1020
},
{
"epoch": 0.35,
"learning_rate": 0.0001677924791086351,
"loss": 1.3317,
"step": 1025
},
{
"epoch": 0.35,
"learning_rate": 0.0001676183844011142,
"loss": 1.3713,
"step": 1030
},
{
"epoch": 0.35,
"learning_rate": 0.00016744428969359332,
"loss": 1.3276,
"step": 1035
},
{
"epoch": 0.36,
"learning_rate": 0.00016727019498607244,
"loss": 1.2705,
"step": 1040
},
{
"epoch": 0.36,
"learning_rate": 0.00016709610027855154,
"loss": 1.4057,
"step": 1045
},
{
"epoch": 0.36,
"learning_rate": 0.00016692200557103066,
"loss": 1.4044,
"step": 1050
},
{
"epoch": 0.36,
"learning_rate": 0.00016674791086350975,
"loss": 1.3438,
"step": 1055
},
{
"epoch": 0.36,
"learning_rate": 0.00016657381615598887,
"loss": 1.3871,
"step": 1060
},
{
"epoch": 0.36,
"learning_rate": 0.000166399721448468,
"loss": 1.3212,
"step": 1065
},
{
"epoch": 0.37,
"learning_rate": 0.00016622562674094708,
"loss": 1.4142,
"step": 1070
},
{
"epoch": 0.37,
"learning_rate": 0.00016605153203342617,
"loss": 1.3637,
"step": 1075
},
{
"epoch": 0.37,
"learning_rate": 0.00016587743732590532,
"loss": 1.2748,
"step": 1080
},
{
"epoch": 0.37,
"learning_rate": 0.0001657033426183844,
"loss": 1.4044,
"step": 1085
},
{
"epoch": 0.37,
"learning_rate": 0.00016552924791086353,
"loss": 1.3374,
"step": 1090
},
{
"epoch": 0.37,
"learning_rate": 0.00016535515320334262,
"loss": 1.3647,
"step": 1095
},
{
"epoch": 0.38,
"learning_rate": 0.00016518105849582171,
"loss": 1.4259,
"step": 1100
},
{
"epoch": 0.38,
"learning_rate": 0.00016500696378830086,
"loss": 1.2926,
"step": 1105
},
{
"epoch": 0.38,
"learning_rate": 0.00016483286908077995,
"loss": 1.4621,
"step": 1110
},
{
"epoch": 0.38,
"learning_rate": 0.00016465877437325905,
"loss": 1.3746,
"step": 1115
},
{
"epoch": 0.38,
"learning_rate": 0.00016448467966573817,
"loss": 1.4036,
"step": 1120
},
{
"epoch": 0.39,
"learning_rate": 0.00016431058495821729,
"loss": 1.4062,
"step": 1125
},
{
"epoch": 0.39,
"learning_rate": 0.0001641364902506964,
"loss": 1.348,
"step": 1130
},
{
"epoch": 0.39,
"learning_rate": 0.0001639623955431755,
"loss": 1.3271,
"step": 1135
},
{
"epoch": 0.39,
"learning_rate": 0.0001637883008356546,
"loss": 1.3663,
"step": 1140
},
{
"epoch": 0.39,
"learning_rate": 0.0001636142061281337,
"loss": 1.3276,
"step": 1145
},
{
"epoch": 0.39,
"learning_rate": 0.00016344011142061283,
"loss": 1.2809,
"step": 1150
},
{
"epoch": 0.4,
"learning_rate": 0.00016326601671309195,
"loss": 1.3586,
"step": 1155
},
{
"epoch": 0.4,
"learning_rate": 0.00016309192200557104,
"loss": 1.3864,
"step": 1160
},
{
"epoch": 0.4,
"learning_rate": 0.00016291782729805013,
"loss": 1.3163,
"step": 1165
},
{
"epoch": 0.4,
"learning_rate": 0.00016274373259052925,
"loss": 1.3677,
"step": 1170
},
{
"epoch": 0.4,
"learning_rate": 0.00016256963788300837,
"loss": 1.2984,
"step": 1175
},
{
"epoch": 0.4,
"learning_rate": 0.00016239554317548746,
"loss": 1.4083,
"step": 1180
},
{
"epoch": 0.41,
"learning_rate": 0.00016222144846796658,
"loss": 1.445,
"step": 1185
},
{
"epoch": 0.41,
"learning_rate": 0.00016204735376044568,
"loss": 1.3306,
"step": 1190
},
{
"epoch": 0.41,
"learning_rate": 0.0001618732590529248,
"loss": 1.4185,
"step": 1195
},
{
"epoch": 0.41,
"learning_rate": 0.00016169916434540392,
"loss": 1.3581,
"step": 1200
},
{
"epoch": 0.41,
"eval_loss": 1.318132996559143,
"eval_runtime": 737.5524,
"eval_samples_per_second": 7.044,
"eval_steps_per_second": 0.881,
"step": 1200
},
{
"epoch": 0.41,
"learning_rate": 0.000161525069637883,
"loss": 1.383,
"step": 1205
},
{
"epoch": 0.41,
"learning_rate": 0.00016135097493036213,
"loss": 1.4161,
"step": 1210
},
{
"epoch": 0.42,
"learning_rate": 0.00016117688022284122,
"loss": 1.3449,
"step": 1215
},
{
"epoch": 0.42,
"learning_rate": 0.00016100278551532034,
"loss": 1.3172,
"step": 1220
},
{
"epoch": 0.42,
"learning_rate": 0.00016082869080779946,
"loss": 1.3987,
"step": 1225
},
{
"epoch": 0.42,
"learning_rate": 0.00016065459610027855,
"loss": 1.3752,
"step": 1230
},
{
"epoch": 0.42,
"learning_rate": 0.00016048050139275767,
"loss": 1.4369,
"step": 1235
},
{
"epoch": 0.42,
"learning_rate": 0.00016030640668523676,
"loss": 1.3258,
"step": 1240
},
{
"epoch": 0.43,
"learning_rate": 0.00016013231197771588,
"loss": 1.3256,
"step": 1245
},
{
"epoch": 0.43,
"learning_rate": 0.000159958217270195,
"loss": 1.3357,
"step": 1250
},
{
"epoch": 0.43,
"learning_rate": 0.0001597841225626741,
"loss": 1.3671,
"step": 1255
},
{
"epoch": 0.43,
"learning_rate": 0.00015961002785515321,
"loss": 1.3605,
"step": 1260
},
{
"epoch": 0.43,
"learning_rate": 0.00015943593314763233,
"loss": 1.3404,
"step": 1265
},
{
"epoch": 0.43,
"learning_rate": 0.00015926183844011143,
"loss": 1.3915,
"step": 1270
},
{
"epoch": 0.44,
"learning_rate": 0.00015908774373259055,
"loss": 1.3559,
"step": 1275
},
{
"epoch": 0.44,
"learning_rate": 0.00015891364902506964,
"loss": 1.3285,
"step": 1280
},
{
"epoch": 0.44,
"learning_rate": 0.00015873955431754876,
"loss": 1.3949,
"step": 1285
},
{
"epoch": 0.44,
"learning_rate": 0.00015856545961002788,
"loss": 1.3825,
"step": 1290
},
{
"epoch": 0.44,
"learning_rate": 0.00015839136490250697,
"loss": 1.3211,
"step": 1295
},
{
"epoch": 0.44,
"learning_rate": 0.0001582172701949861,
"loss": 1.332,
"step": 1300
},
{
"epoch": 0.45,
"learning_rate": 0.00015804317548746518,
"loss": 1.4379,
"step": 1305
},
{
"epoch": 0.45,
"learning_rate": 0.0001578690807799443,
"loss": 1.3406,
"step": 1310
},
{
"epoch": 0.45,
"learning_rate": 0.00015769498607242342,
"loss": 1.3467,
"step": 1315
},
{
"epoch": 0.45,
"learning_rate": 0.0001575208913649025,
"loss": 1.374,
"step": 1320
},
{
"epoch": 0.45,
"learning_rate": 0.0001573467966573816,
"loss": 1.3525,
"step": 1325
},
{
"epoch": 0.46,
"learning_rate": 0.00015717270194986072,
"loss": 1.3739,
"step": 1330
},
{
"epoch": 0.46,
"learning_rate": 0.00015699860724233984,
"loss": 1.3458,
"step": 1335
},
{
"epoch": 0.46,
"learning_rate": 0.00015682451253481896,
"loss": 1.3588,
"step": 1340
},
{
"epoch": 0.46,
"learning_rate": 0.00015665041782729806,
"loss": 1.3362,
"step": 1345
},
{
"epoch": 0.46,
"learning_rate": 0.00015647632311977715,
"loss": 1.3553,
"step": 1350
},
{
"epoch": 0.46,
"learning_rate": 0.00015630222841225627,
"loss": 1.4328,
"step": 1355
},
{
"epoch": 0.47,
"learning_rate": 0.0001561281337047354,
"loss": 1.2763,
"step": 1360
},
{
"epoch": 0.47,
"learning_rate": 0.0001559540389972145,
"loss": 1.3359,
"step": 1365
},
{
"epoch": 0.47,
"learning_rate": 0.0001557799442896936,
"loss": 1.3164,
"step": 1370
},
{
"epoch": 0.47,
"learning_rate": 0.0001556058495821727,
"loss": 1.29,
"step": 1375
},
{
"epoch": 0.47,
"learning_rate": 0.00015543175487465184,
"loss": 1.4188,
"step": 1380
},
{
"epoch": 0.47,
"learning_rate": 0.00015525766016713093,
"loss": 1.3594,
"step": 1385
},
{
"epoch": 0.48,
"learning_rate": 0.00015508356545961002,
"loss": 1.3535,
"step": 1390
},
{
"epoch": 0.48,
"learning_rate": 0.00015490947075208914,
"loss": 1.3415,
"step": 1395
},
{
"epoch": 0.48,
"learning_rate": 0.00015473537604456823,
"loss": 1.3417,
"step": 1400
},
{
"epoch": 0.48,
"eval_loss": 1.313808798789978,
"eval_runtime": 733.0569,
"eval_samples_per_second": 7.087,
"eval_steps_per_second": 0.887,
"step": 1400
},
{
"epoch": 0.48,
"learning_rate": 0.00015456128133704738,
"loss": 1.3421,
"step": 1405
},
{
"epoch": 0.48,
"learning_rate": 0.00015438718662952647,
"loss": 1.3915,
"step": 1410
},
{
"epoch": 0.48,
"learning_rate": 0.00015421309192200557,
"loss": 1.3097,
"step": 1415
},
{
"epoch": 0.49,
"learning_rate": 0.00015403899721448469,
"loss": 1.2905,
"step": 1420
},
{
"epoch": 0.49,
"learning_rate": 0.0001538649025069638,
"loss": 1.3719,
"step": 1425
},
{
"epoch": 0.49,
"learning_rate": 0.00015369080779944292,
"loss": 1.2958,
"step": 1430
},
{
"epoch": 0.49,
"learning_rate": 0.00015351671309192202,
"loss": 1.2922,
"step": 1435
},
{
"epoch": 0.49,
"learning_rate": 0.0001533426183844011,
"loss": 1.3139,
"step": 1440
},
{
"epoch": 0.49,
"learning_rate": 0.00015316852367688023,
"loss": 1.3396,
"step": 1445
},
{
"epoch": 0.5,
"learning_rate": 0.00015299442896935935,
"loss": 1.2605,
"step": 1450
},
{
"epoch": 0.5,
"learning_rate": 0.00015282033426183844,
"loss": 1.4605,
"step": 1455
},
{
"epoch": 0.5,
"learning_rate": 0.00015264623955431756,
"loss": 1.4972,
"step": 1460
},
{
"epoch": 0.5,
"learning_rate": 0.00015247214484679665,
"loss": 1.3068,
"step": 1465
},
{
"epoch": 0.5,
"learning_rate": 0.00015229805013927577,
"loss": 1.3249,
"step": 1470
},
{
"epoch": 0.5,
"learning_rate": 0.0001521239554317549,
"loss": 1.3316,
"step": 1475
},
{
"epoch": 0.51,
"learning_rate": 0.00015194986072423398,
"loss": 1.434,
"step": 1480
},
{
"epoch": 0.51,
"learning_rate": 0.0001517757660167131,
"loss": 1.4266,
"step": 1485
},
{
"epoch": 0.51,
"learning_rate": 0.0001516016713091922,
"loss": 1.3159,
"step": 1490
},
{
"epoch": 0.51,
"learning_rate": 0.00015142757660167132,
"loss": 1.2304,
"step": 1495
},
{
"epoch": 0.51,
"learning_rate": 0.00015125348189415043,
"loss": 1.3826,
"step": 1500
},
{
"epoch": 0.52,
"learning_rate": 0.00015107938718662953,
"loss": 1.4042,
"step": 1505
},
{
"epoch": 0.52,
"learning_rate": 0.00015090529247910865,
"loss": 1.335,
"step": 1510
},
{
"epoch": 0.52,
"learning_rate": 0.00015073119777158774,
"loss": 1.3166,
"step": 1515
},
{
"epoch": 0.52,
"learning_rate": 0.00015055710306406686,
"loss": 1.284,
"step": 1520
},
{
"epoch": 0.52,
"learning_rate": 0.00015038300835654598,
"loss": 1.2927,
"step": 1525
},
{
"epoch": 0.52,
"learning_rate": 0.00015020891364902507,
"loss": 1.4464,
"step": 1530
},
{
"epoch": 0.53,
"learning_rate": 0.0001500348189415042,
"loss": 1.319,
"step": 1535
},
{
"epoch": 0.53,
"learning_rate": 0.0001498607242339833,
"loss": 1.3213,
"step": 1540
},
{
"epoch": 0.53,
"learning_rate": 0.0001496866295264624,
"loss": 1.4009,
"step": 1545
},
{
"epoch": 0.53,
"learning_rate": 0.00014951253481894152,
"loss": 1.3166,
"step": 1550
},
{
"epoch": 0.53,
"learning_rate": 0.00014933844011142061,
"loss": 1.3605,
"step": 1555
},
{
"epoch": 0.53,
"learning_rate": 0.0001491643454038997,
"loss": 1.401,
"step": 1560
},
{
"epoch": 0.54,
"learning_rate": 0.00014899025069637885,
"loss": 1.3219,
"step": 1565
},
{
"epoch": 0.54,
"learning_rate": 0.00014881615598885795,
"loss": 1.3484,
"step": 1570
},
{
"epoch": 0.54,
"learning_rate": 0.00014864206128133706,
"loss": 1.3743,
"step": 1575
},
{
"epoch": 0.54,
"learning_rate": 0.00014846796657381616,
"loss": 1.3498,
"step": 1580
},
{
"epoch": 0.54,
"learning_rate": 0.00014829387186629528,
"loss": 1.2985,
"step": 1585
},
{
"epoch": 0.54,
"learning_rate": 0.0001481197771587744,
"loss": 1.3355,
"step": 1590
},
{
"epoch": 0.55,
"learning_rate": 0.0001479456824512535,
"loss": 1.3278,
"step": 1595
},
{
"epoch": 0.55,
"learning_rate": 0.00014777158774373258,
"loss": 1.3111,
"step": 1600
},
{
"epoch": 0.55,
"eval_loss": 1.3110042810440063,
"eval_runtime": 733.0309,
"eval_samples_per_second": 7.087,
"eval_steps_per_second": 0.887,
"step": 1600
},
{
"epoch": 0.55,
"learning_rate": 0.0001475974930362117,
"loss": 1.3197,
"step": 1605
},
{
"epoch": 0.55,
"learning_rate": 0.00014742339832869082,
"loss": 1.4121,
"step": 1610
},
{
"epoch": 0.55,
"learning_rate": 0.00014724930362116994,
"loss": 1.34,
"step": 1615
},
{
"epoch": 0.55,
"learning_rate": 0.00014707520891364903,
"loss": 1.3669,
"step": 1620
},
{
"epoch": 0.56,
"learning_rate": 0.00014690111420612812,
"loss": 1.3248,
"step": 1625
},
{
"epoch": 0.56,
"learning_rate": 0.00014672701949860724,
"loss": 1.2567,
"step": 1630
},
{
"epoch": 0.56,
"learning_rate": 0.00014655292479108636,
"loss": 1.3399,
"step": 1635
},
{
"epoch": 0.56,
"learning_rate": 0.00014637883008356548,
"loss": 1.315,
"step": 1640
},
{
"epoch": 0.56,
"learning_rate": 0.00014620473537604458,
"loss": 1.2658,
"step": 1645
},
{
"epoch": 0.56,
"learning_rate": 0.00014603064066852367,
"loss": 1.3854,
"step": 1650
},
{
"epoch": 0.57,
"learning_rate": 0.0001458565459610028,
"loss": 1.3889,
"step": 1655
},
{
"epoch": 0.57,
"learning_rate": 0.0001456824512534819,
"loss": 1.3587,
"step": 1660
},
{
"epoch": 0.57,
"learning_rate": 0.000145508356545961,
"loss": 1.3507,
"step": 1665
},
{
"epoch": 0.57,
"learning_rate": 0.00014533426183844012,
"loss": 1.3647,
"step": 1670
},
{
"epoch": 0.57,
"learning_rate": 0.0001451601671309192,
"loss": 1.2777,
"step": 1675
},
{
"epoch": 0.57,
"learning_rate": 0.00014498607242339836,
"loss": 1.3376,
"step": 1680
},
{
"epoch": 0.58,
"learning_rate": 0.00014481197771587745,
"loss": 1.2869,
"step": 1685
},
{
"epoch": 0.58,
"learning_rate": 0.00014463788300835654,
"loss": 1.2855,
"step": 1690
},
{
"epoch": 0.58,
"learning_rate": 0.00014446378830083566,
"loss": 1.3387,
"step": 1695
},
{
"epoch": 0.58,
"learning_rate": 0.00014428969359331475,
"loss": 1.3416,
"step": 1700
},
{
"epoch": 0.58,
"learning_rate": 0.00014411559888579387,
"loss": 1.3574,
"step": 1705
},
{
"epoch": 0.59,
"learning_rate": 0.000143941504178273,
"loss": 1.375,
"step": 1710
},
{
"epoch": 0.59,
"learning_rate": 0.00014376740947075209,
"loss": 1.3952,
"step": 1715
},
{
"epoch": 0.59,
"learning_rate": 0.0001435933147632312,
"loss": 1.3429,
"step": 1720
},
{
"epoch": 0.59,
"learning_rate": 0.00014341922005571032,
"loss": 1.3726,
"step": 1725
},
{
"epoch": 0.59,
"learning_rate": 0.00014324512534818942,
"loss": 1.2442,
"step": 1730
},
{
"epoch": 0.59,
"learning_rate": 0.00014307103064066854,
"loss": 1.2478,
"step": 1735
},
{
"epoch": 0.6,
"learning_rate": 0.00014289693593314763,
"loss": 1.3317,
"step": 1740
},
{
"epoch": 0.6,
"learning_rate": 0.00014272284122562675,
"loss": 1.3172,
"step": 1745
},
{
"epoch": 0.6,
"learning_rate": 0.00014254874651810587,
"loss": 1.3594,
"step": 1750
},
{
"epoch": 0.6,
"learning_rate": 0.00014237465181058496,
"loss": 1.3597,
"step": 1755
},
{
"epoch": 0.6,
"learning_rate": 0.00014220055710306408,
"loss": 1.3468,
"step": 1760
},
{
"epoch": 0.6,
"learning_rate": 0.00014202646239554317,
"loss": 1.369,
"step": 1765
},
{
"epoch": 0.61,
"learning_rate": 0.0001418523676880223,
"loss": 1.2807,
"step": 1770
},
{
"epoch": 0.61,
"learning_rate": 0.0001416782729805014,
"loss": 1.3454,
"step": 1775
},
{
"epoch": 0.61,
"learning_rate": 0.0001415041782729805,
"loss": 1.3576,
"step": 1780
},
{
"epoch": 0.61,
"learning_rate": 0.00014133008356545962,
"loss": 1.397,
"step": 1785
},
{
"epoch": 0.61,
"learning_rate": 0.00014115598885793872,
"loss": 1.2672,
"step": 1790
},
{
"epoch": 0.61,
"learning_rate": 0.00014098189415041784,
"loss": 1.3121,
"step": 1795
},
{
"epoch": 0.62,
"learning_rate": 0.00014080779944289695,
"loss": 1.3547,
"step": 1800
},
{
"epoch": 0.62,
"eval_loss": 1.306809425354004,
"eval_runtime": 733.2137,
"eval_samples_per_second": 7.085,
"eval_steps_per_second": 0.887,
"step": 1800
},
{
"epoch": 0.62,
"learning_rate": 0.00014063370473537605,
"loss": 1.3878,
"step": 1805
},
{
"epoch": 0.62,
"learning_rate": 0.00014045961002785517,
"loss": 1.2847,
"step": 1810
},
{
"epoch": 0.62,
"learning_rate": 0.00014028551532033426,
"loss": 1.3002,
"step": 1815
},
{
"epoch": 0.62,
"learning_rate": 0.00014011142061281338,
"loss": 1.29,
"step": 1820
},
{
"epoch": 0.62,
"learning_rate": 0.0001399373259052925,
"loss": 1.3643,
"step": 1825
},
{
"epoch": 0.63,
"learning_rate": 0.0001397632311977716,
"loss": 1.2768,
"step": 1830
},
{
"epoch": 0.63,
"learning_rate": 0.00013958913649025068,
"loss": 1.3229,
"step": 1835
},
{
"epoch": 0.63,
"learning_rate": 0.00013941504178272983,
"loss": 1.3588,
"step": 1840
},
{
"epoch": 0.63,
"learning_rate": 0.00013924094707520892,
"loss": 1.3441,
"step": 1845
},
{
"epoch": 0.63,
"learning_rate": 0.00013906685236768804,
"loss": 1.3363,
"step": 1850
},
{
"epoch": 0.63,
"learning_rate": 0.00013889275766016713,
"loss": 1.2517,
"step": 1855
},
{
"epoch": 0.64,
"learning_rate": 0.00013871866295264623,
"loss": 1.2044,
"step": 1860
},
{
"epoch": 0.64,
"learning_rate": 0.00013854456824512537,
"loss": 1.382,
"step": 1865
},
{
"epoch": 0.64,
"learning_rate": 0.00013837047353760446,
"loss": 1.2676,
"step": 1870
},
{
"epoch": 0.64,
"learning_rate": 0.00013819637883008356,
"loss": 1.3313,
"step": 1875
},
{
"epoch": 0.64,
"learning_rate": 0.00013802228412256268,
"loss": 1.3407,
"step": 1880
},
{
"epoch": 0.65,
"learning_rate": 0.0001378481894150418,
"loss": 1.3454,
"step": 1885
},
{
"epoch": 0.65,
"learning_rate": 0.00013767409470752092,
"loss": 1.3517,
"step": 1890
},
{
"epoch": 0.65,
"learning_rate": 0.0001375,
"loss": 1.3419,
"step": 1895
},
{
"epoch": 0.65,
"learning_rate": 0.0001373259052924791,
"loss": 1.323,
"step": 1900
},
{
"epoch": 0.65,
"learning_rate": 0.00013715181058495822,
"loss": 1.3523,
"step": 1905
},
{
"epoch": 0.65,
"learning_rate": 0.00013697771587743734,
"loss": 1.3689,
"step": 1910
},
{
"epoch": 0.66,
"learning_rate": 0.00013680362116991646,
"loss": 1.2813,
"step": 1915
},
{
"epoch": 0.66,
"learning_rate": 0.00013662952646239555,
"loss": 1.2873,
"step": 1920
},
{
"epoch": 0.66,
"learning_rate": 0.00013645543175487464,
"loss": 1.3936,
"step": 1925
},
{
"epoch": 0.66,
"learning_rate": 0.00013628133704735376,
"loss": 1.4143,
"step": 1930
},
{
"epoch": 0.66,
"learning_rate": 0.00013610724233983288,
"loss": 1.3495,
"step": 1935
},
{
"epoch": 0.66,
"learning_rate": 0.00013593314763231198,
"loss": 1.3029,
"step": 1940
},
{
"epoch": 0.67,
"learning_rate": 0.0001357590529247911,
"loss": 1.3457,
"step": 1945
},
{
"epoch": 0.67,
"learning_rate": 0.0001355849582172702,
"loss": 1.3519,
"step": 1950
},
{
"epoch": 0.67,
"learning_rate": 0.0001354108635097493,
"loss": 1.313,
"step": 1955
},
{
"epoch": 0.67,
"learning_rate": 0.00013523676880222843,
"loss": 1.3421,
"step": 1960
},
{
"epoch": 0.67,
"learning_rate": 0.00013506267409470752,
"loss": 1.4057,
"step": 1965
},
{
"epoch": 0.67,
"learning_rate": 0.00013488857938718664,
"loss": 1.3156,
"step": 1970
},
{
"epoch": 0.68,
"learning_rate": 0.00013471448467966573,
"loss": 1.3147,
"step": 1975
},
{
"epoch": 0.68,
"learning_rate": 0.00013454038997214485,
"loss": 1.3831,
"step": 1980
},
{
"epoch": 0.68,
"learning_rate": 0.00013436629526462397,
"loss": 1.2535,
"step": 1985
},
{
"epoch": 0.68,
"learning_rate": 0.00013419220055710306,
"loss": 1.3173,
"step": 1990
},
{
"epoch": 0.68,
"learning_rate": 0.00013401810584958218,
"loss": 1.3519,
"step": 1995
},
{
"epoch": 0.68,
"learning_rate": 0.00013384401114206127,
"loss": 1.3725,
"step": 2000
},
{
"epoch": 0.68,
"eval_loss": 1.3058445453643799,
"eval_runtime": 733.4218,
"eval_samples_per_second": 7.083,
"eval_steps_per_second": 0.886,
"step": 2000
},
{
"epoch": 0.69,
"learning_rate": 0.0001336699164345404,
"loss": 1.4021,
"step": 2005
},
{
"epoch": 0.69,
"learning_rate": 0.0001334958217270195,
"loss": 1.2751,
"step": 2010
},
{
"epoch": 0.69,
"learning_rate": 0.0001333217270194986,
"loss": 1.3458,
"step": 2015
},
{
"epoch": 0.69,
"learning_rate": 0.00013314763231197772,
"loss": 1.272,
"step": 2020
},
{
"epoch": 0.69,
"learning_rate": 0.00013297353760445684,
"loss": 1.3671,
"step": 2025
},
{
"epoch": 0.69,
"learning_rate": 0.00013279944289693594,
"loss": 1.3424,
"step": 2030
},
{
"epoch": 0.7,
"learning_rate": 0.00013262534818941506,
"loss": 1.3302,
"step": 2035
},
{
"epoch": 0.7,
"learning_rate": 0.00013245125348189415,
"loss": 1.3084,
"step": 2040
},
{
"epoch": 0.7,
"learning_rate": 0.00013227715877437327,
"loss": 1.3688,
"step": 2045
},
{
"epoch": 0.7,
"learning_rate": 0.0001321030640668524,
"loss": 1.3742,
"step": 2050
},
{
"epoch": 0.7,
"learning_rate": 0.00013192896935933148,
"loss": 1.3327,
"step": 2055
},
{
"epoch": 0.7,
"learning_rate": 0.0001317548746518106,
"loss": 1.3348,
"step": 2060
},
{
"epoch": 0.71,
"learning_rate": 0.0001315807799442897,
"loss": 1.3634,
"step": 2065
},
{
"epoch": 0.71,
"learning_rate": 0.0001314066852367688,
"loss": 1.4085,
"step": 2070
},
{
"epoch": 0.71,
"learning_rate": 0.00013123259052924793,
"loss": 1.37,
"step": 2075
},
{
"epoch": 0.71,
"learning_rate": 0.00013105849582172702,
"loss": 1.379,
"step": 2080
},
{
"epoch": 0.71,
"learning_rate": 0.00013088440111420614,
"loss": 1.3195,
"step": 2085
},
{
"epoch": 0.72,
"learning_rate": 0.00013071030640668524,
"loss": 1.3618,
"step": 2090
},
{
"epoch": 0.72,
"learning_rate": 0.00013053621169916435,
"loss": 1.2982,
"step": 2095
},
{
"epoch": 0.72,
"learning_rate": 0.00013036211699164347,
"loss": 1.3429,
"step": 2100
},
{
"epoch": 0.72,
"learning_rate": 0.00013018802228412257,
"loss": 1.2857,
"step": 2105
},
{
"epoch": 0.72,
"learning_rate": 0.00013001392757660166,
"loss": 1.3079,
"step": 2110
},
{
"epoch": 0.72,
"learning_rate": 0.00012983983286908078,
"loss": 1.3331,
"step": 2115
},
{
"epoch": 0.73,
"learning_rate": 0.0001296657381615599,
"loss": 1.3805,
"step": 2120
},
{
"epoch": 0.73,
"learning_rate": 0.00012949164345403902,
"loss": 1.3735,
"step": 2125
},
{
"epoch": 0.73,
"learning_rate": 0.0001293175487465181,
"loss": 1.3509,
"step": 2130
},
{
"epoch": 0.73,
"learning_rate": 0.0001291434540389972,
"loss": 1.3057,
"step": 2135
},
{
"epoch": 0.73,
"learning_rate": 0.00012896935933147635,
"loss": 1.3151,
"step": 2140
},
{
"epoch": 0.73,
"learning_rate": 0.00012879526462395544,
"loss": 1.3399,
"step": 2145
},
{
"epoch": 0.74,
"learning_rate": 0.00012862116991643453,
"loss": 1.3866,
"step": 2150
},
{
"epoch": 0.74,
"learning_rate": 0.00012844707520891365,
"loss": 1.3843,
"step": 2155
},
{
"epoch": 0.74,
"learning_rate": 0.00012827298050139275,
"loss": 1.3211,
"step": 2160
},
{
"epoch": 0.74,
"learning_rate": 0.0001280988857938719,
"loss": 1.303,
"step": 2165
},
{
"epoch": 0.74,
"learning_rate": 0.00012792479108635098,
"loss": 1.4432,
"step": 2170
},
{
"epoch": 0.74,
"learning_rate": 0.00012775069637883008,
"loss": 1.3461,
"step": 2175
},
{
"epoch": 0.75,
"learning_rate": 0.0001275766016713092,
"loss": 1.3664,
"step": 2180
},
{
"epoch": 0.75,
"learning_rate": 0.00012740250696378832,
"loss": 1.3216,
"step": 2185
},
{
"epoch": 0.75,
"learning_rate": 0.00012722841225626744,
"loss": 1.3525,
"step": 2190
},
{
"epoch": 0.75,
"learning_rate": 0.00012705431754874653,
"loss": 1.2865,
"step": 2195
},
{
"epoch": 0.75,
"learning_rate": 0.00012688022284122562,
"loss": 1.3574,
"step": 2200
},
{
"epoch": 0.75,
"eval_loss": 1.302751064300537,
"eval_runtime": 734.76,
"eval_samples_per_second": 7.07,
"eval_steps_per_second": 0.885,
"step": 2200
},
{
"epoch": 0.75,
"learning_rate": 0.00012670612813370474,
"loss": 1.3621,
"step": 2205
},
{
"epoch": 0.76,
"learning_rate": 0.00012653203342618386,
"loss": 1.4331,
"step": 2210
},
{
"epoch": 0.76,
"learning_rate": 0.00012635793871866295,
"loss": 1.3252,
"step": 2215
},
{
"epoch": 0.76,
"learning_rate": 0.00012618384401114207,
"loss": 1.2945,
"step": 2220
},
{
"epoch": 0.76,
"learning_rate": 0.00012600974930362116,
"loss": 1.3286,
"step": 2225
},
{
"epoch": 0.76,
"learning_rate": 0.00012583565459610028,
"loss": 1.2922,
"step": 2230
},
{
"epoch": 0.76,
"learning_rate": 0.0001256615598885794,
"loss": 1.2644,
"step": 2235
},
{
"epoch": 0.77,
"learning_rate": 0.0001254874651810585,
"loss": 1.3052,
"step": 2240
},
{
"epoch": 0.77,
"learning_rate": 0.00012531337047353761,
"loss": 1.2918,
"step": 2245
},
{
"epoch": 0.77,
"learning_rate": 0.0001251392757660167,
"loss": 1.3455,
"step": 2250
},
{
"epoch": 0.77,
"learning_rate": 0.00012496518105849583,
"loss": 1.3509,
"step": 2255
},
{
"epoch": 0.77,
"learning_rate": 0.00012479108635097495,
"loss": 1.3038,
"step": 2260
},
{
"epoch": 0.78,
"learning_rate": 0.00012461699164345404,
"loss": 1.2552,
"step": 2265
},
{
"epoch": 0.78,
"learning_rate": 0.00012444289693593316,
"loss": 1.3511,
"step": 2270
},
{
"epoch": 0.78,
"learning_rate": 0.00012426880222841225,
"loss": 1.3912,
"step": 2275
},
{
"epoch": 0.78,
"learning_rate": 0.00012409470752089137,
"loss": 1.358,
"step": 2280
},
{
"epoch": 0.78,
"learning_rate": 0.0001239206128133705,
"loss": 1.3028,
"step": 2285
},
{
"epoch": 0.78,
"learning_rate": 0.00012374651810584958,
"loss": 1.3647,
"step": 2290
},
{
"epoch": 0.79,
"learning_rate": 0.0001235724233983287,
"loss": 1.2736,
"step": 2295
},
{
"epoch": 0.79,
"learning_rate": 0.00012339832869080782,
"loss": 1.2978,
"step": 2300
},
{
"epoch": 0.79,
"learning_rate": 0.0001232242339832869,
"loss": 1.3406,
"step": 2305
},
{
"epoch": 0.79,
"learning_rate": 0.00012305013927576603,
"loss": 1.3424,
"step": 2310
},
{
"epoch": 0.79,
"learning_rate": 0.00012287604456824513,
"loss": 1.3182,
"step": 2315
},
{
"epoch": 0.79,
"learning_rate": 0.00012270194986072422,
"loss": 1.3059,
"step": 2320
},
{
"epoch": 0.8,
"learning_rate": 0.00012252785515320336,
"loss": 1.2854,
"step": 2325
},
{
"epoch": 0.8,
"learning_rate": 0.00012235376044568246,
"loss": 1.2978,
"step": 2330
},
{
"epoch": 0.8,
"learning_rate": 0.00012217966573816158,
"loss": 1.2419,
"step": 2335
},
{
"epoch": 0.8,
"learning_rate": 0.00012200557103064068,
"loss": 1.3188,
"step": 2340
},
{
"epoch": 0.8,
"learning_rate": 0.00012183147632311977,
"loss": 1.2925,
"step": 2345
},
{
"epoch": 0.8,
"learning_rate": 0.0001216573816155989,
"loss": 1.3548,
"step": 2350
},
{
"epoch": 0.81,
"learning_rate": 0.000121483286908078,
"loss": 1.3569,
"step": 2355
},
{
"epoch": 0.81,
"learning_rate": 0.00012130919220055709,
"loss": 1.3378,
"step": 2360
},
{
"epoch": 0.81,
"learning_rate": 0.00012113509749303623,
"loss": 1.2776,
"step": 2365
},
{
"epoch": 0.81,
"learning_rate": 0.00012096100278551532,
"loss": 1.3191,
"step": 2370
},
{
"epoch": 0.81,
"learning_rate": 0.00012078690807799444,
"loss": 1.3439,
"step": 2375
},
{
"epoch": 0.81,
"learning_rate": 0.00012061281337047354,
"loss": 1.3,
"step": 2380
},
{
"epoch": 0.82,
"learning_rate": 0.00012043871866295265,
"loss": 1.3663,
"step": 2385
},
{
"epoch": 0.82,
"learning_rate": 0.00012026462395543177,
"loss": 1.3978,
"step": 2390
},
{
"epoch": 0.82,
"learning_rate": 0.00012009052924791086,
"loss": 1.3929,
"step": 2395
},
{
"epoch": 0.82,
"learning_rate": 0.00011991643454039,
"loss": 1.3773,
"step": 2400
},
{
"epoch": 0.82,
"eval_loss": 1.2999300956726074,
"eval_runtime": 732.8294,
"eval_samples_per_second": 7.089,
"eval_steps_per_second": 0.887,
"step": 2400
},
{
"epoch": 0.82,
"learning_rate": 0.00011974233983286909,
"loss": 1.3097,
"step": 2405
},
{
"epoch": 0.82,
"learning_rate": 0.00011956824512534819,
"loss": 1.3452,
"step": 2410
},
{
"epoch": 0.83,
"learning_rate": 0.00011939415041782731,
"loss": 1.3555,
"step": 2415
},
{
"epoch": 0.83,
"learning_rate": 0.0001192200557103064,
"loss": 1.3182,
"step": 2420
},
{
"epoch": 0.83,
"learning_rate": 0.00011904596100278551,
"loss": 1.3665,
"step": 2425
},
{
"epoch": 0.83,
"learning_rate": 0.00011887186629526463,
"loss": 1.2431,
"step": 2430
},
{
"epoch": 0.83,
"learning_rate": 0.00011869777158774374,
"loss": 1.3146,
"step": 2435
},
{
"epoch": 0.84,
"learning_rate": 0.00011852367688022286,
"loss": 1.3499,
"step": 2440
},
{
"epoch": 0.84,
"learning_rate": 0.00011834958217270196,
"loss": 1.3353,
"step": 2445
},
{
"epoch": 0.84,
"learning_rate": 0.00011817548746518105,
"loss": 1.3442,
"step": 2450
},
{
"epoch": 0.84,
"learning_rate": 0.00011800139275766017,
"loss": 1.3142,
"step": 2455
},
{
"epoch": 0.84,
"learning_rate": 0.00011782729805013928,
"loss": 1.3017,
"step": 2460
},
{
"epoch": 0.84,
"learning_rate": 0.0001176532033426184,
"loss": 1.3205,
"step": 2465
},
{
"epoch": 0.85,
"learning_rate": 0.0001174791086350975,
"loss": 1.3205,
"step": 2470
},
{
"epoch": 0.85,
"learning_rate": 0.0001173050139275766,
"loss": 1.3755,
"step": 2475
},
{
"epoch": 0.85,
"learning_rate": 0.00011713091922005573,
"loss": 1.4142,
"step": 2480
},
{
"epoch": 0.85,
"learning_rate": 0.00011695682451253482,
"loss": 1.3415,
"step": 2485
},
{
"epoch": 0.85,
"learning_rate": 0.00011678272980501393,
"loss": 1.3956,
"step": 2490
},
{
"epoch": 0.85,
"learning_rate": 0.00011660863509749305,
"loss": 1.3654,
"step": 2495
},
{
"epoch": 0.86,
"learning_rate": 0.00011643454038997214,
"loss": 1.3569,
"step": 2500
},
{
"epoch": 0.86,
"learning_rate": 0.00011626044568245127,
"loss": 1.339,
"step": 2505
},
{
"epoch": 0.86,
"learning_rate": 0.00011608635097493037,
"loss": 1.3619,
"step": 2510
},
{
"epoch": 0.86,
"learning_rate": 0.00011591225626740947,
"loss": 1.3503,
"step": 2515
},
{
"epoch": 0.86,
"learning_rate": 0.00011573816155988859,
"loss": 1.2833,
"step": 2520
},
{
"epoch": 0.86,
"learning_rate": 0.0001155640668523677,
"loss": 1.3404,
"step": 2525
},
{
"epoch": 0.87,
"learning_rate": 0.00011538997214484679,
"loss": 1.3855,
"step": 2530
},
{
"epoch": 0.87,
"learning_rate": 0.00011521587743732591,
"loss": 1.3225,
"step": 2535
},
{
"epoch": 0.87,
"learning_rate": 0.00011504178272980501,
"loss": 1.413,
"step": 2540
},
{
"epoch": 0.87,
"learning_rate": 0.00011486768802228413,
"loss": 1.3811,
"step": 2545
},
{
"epoch": 0.87,
"learning_rate": 0.00011469359331476324,
"loss": 1.311,
"step": 2550
},
{
"epoch": 0.87,
"learning_rate": 0.00011451949860724233,
"loss": 1.3874,
"step": 2555
},
{
"epoch": 0.88,
"learning_rate": 0.00011434540389972147,
"loss": 1.4261,
"step": 2560
},
{
"epoch": 0.88,
"learning_rate": 0.00011417130919220056,
"loss": 1.3014,
"step": 2565
},
{
"epoch": 0.88,
"learning_rate": 0.00011399721448467968,
"loss": 1.3277,
"step": 2570
},
{
"epoch": 0.88,
"learning_rate": 0.00011382311977715878,
"loss": 1.2828,
"step": 2575
},
{
"epoch": 0.88,
"learning_rate": 0.00011364902506963788,
"loss": 1.3378,
"step": 2580
},
{
"epoch": 0.88,
"learning_rate": 0.00011347493036211701,
"loss": 1.2749,
"step": 2585
},
{
"epoch": 0.89,
"learning_rate": 0.0001133008356545961,
"loss": 1.2597,
"step": 2590
},
{
"epoch": 0.89,
"learning_rate": 0.00011312674094707521,
"loss": 1.3568,
"step": 2595
},
{
"epoch": 0.89,
"learning_rate": 0.00011295264623955433,
"loss": 1.2944,
"step": 2600
},
{
"epoch": 0.89,
"eval_loss": 1.2979168891906738,
"eval_runtime": 738.7601,
"eval_samples_per_second": 7.032,
"eval_steps_per_second": 0.88,
"step": 2600
},
{
"epoch": 0.89,
"learning_rate": 0.00011277855153203343,
"loss": 1.2839,
"step": 2605
},
{
"epoch": 0.89,
"learning_rate": 0.00011260445682451255,
"loss": 1.267,
"step": 2610
},
{
"epoch": 0.89,
"learning_rate": 0.00011243036211699164,
"loss": 1.3281,
"step": 2615
},
{
"epoch": 0.9,
"learning_rate": 0.00011225626740947075,
"loss": 1.3206,
"step": 2620
},
{
"epoch": 0.9,
"learning_rate": 0.00011208217270194987,
"loss": 1.3363,
"step": 2625
},
{
"epoch": 0.9,
"learning_rate": 0.00011190807799442898,
"loss": 1.3629,
"step": 2630
},
{
"epoch": 0.9,
"learning_rate": 0.00011173398328690807,
"loss": 1.2982,
"step": 2635
},
{
"epoch": 0.9,
"learning_rate": 0.0001115598885793872,
"loss": 1.318,
"step": 2640
},
{
"epoch": 0.91,
"learning_rate": 0.0001113857938718663,
"loss": 1.3328,
"step": 2645
},
{
"epoch": 0.91,
"learning_rate": 0.00011121169916434541,
"loss": 1.4585,
"step": 2650
},
{
"epoch": 0.91,
"learning_rate": 0.00011103760445682452,
"loss": 1.3041,
"step": 2655
},
{
"epoch": 0.91,
"learning_rate": 0.00011086350974930361,
"loss": 1.3435,
"step": 2660
},
{
"epoch": 0.91,
"learning_rate": 0.00011068941504178274,
"loss": 1.3172,
"step": 2665
},
{
"epoch": 0.91,
"learning_rate": 0.00011051532033426184,
"loss": 1.335,
"step": 2670
},
{
"epoch": 0.92,
"learning_rate": 0.00011034122562674096,
"loss": 1.3163,
"step": 2675
},
{
"epoch": 0.92,
"learning_rate": 0.00011016713091922006,
"loss": 1.2974,
"step": 2680
},
{
"epoch": 0.92,
"learning_rate": 0.00010999303621169917,
"loss": 1.3252,
"step": 2685
},
{
"epoch": 0.92,
"learning_rate": 0.00010981894150417829,
"loss": 1.2321,
"step": 2690
},
{
"epoch": 0.92,
"learning_rate": 0.00010964484679665738,
"loss": 1.3204,
"step": 2695
},
{
"epoch": 0.92,
"learning_rate": 0.00010947075208913649,
"loss": 1.3555,
"step": 2700
},
{
"epoch": 0.93,
"learning_rate": 0.0001092966573816156,
"loss": 1.334,
"step": 2705
},
{
"epoch": 0.93,
"learning_rate": 0.00010912256267409471,
"loss": 1.393,
"step": 2710
},
{
"epoch": 0.93,
"learning_rate": 0.00010894846796657383,
"loss": 1.3994,
"step": 2715
},
{
"epoch": 0.93,
"learning_rate": 0.00010877437325905294,
"loss": 1.3573,
"step": 2720
},
{
"epoch": 0.93,
"learning_rate": 0.00010860027855153203,
"loss": 1.3483,
"step": 2725
},
{
"epoch": 0.93,
"learning_rate": 0.00010842618384401115,
"loss": 1.273,
"step": 2730
},
{
"epoch": 0.94,
"learning_rate": 0.00010825208913649026,
"loss": 1.3775,
"step": 2735
},
{
"epoch": 0.94,
"learning_rate": 0.00010807799442896935,
"loss": 1.2803,
"step": 2740
},
{
"epoch": 0.94,
"learning_rate": 0.00010790389972144848,
"loss": 1.2606,
"step": 2745
},
{
"epoch": 0.94,
"learning_rate": 0.00010772980501392757,
"loss": 1.2591,
"step": 2750
},
{
"epoch": 0.94,
"learning_rate": 0.00010755571030640669,
"loss": 1.2515,
"step": 2755
},
{
"epoch": 0.94,
"learning_rate": 0.0001073816155988858,
"loss": 1.4989,
"step": 2760
},
{
"epoch": 0.95,
"learning_rate": 0.0001072075208913649,
"loss": 1.3527,
"step": 2765
},
{
"epoch": 0.95,
"learning_rate": 0.00010703342618384402,
"loss": 1.4096,
"step": 2770
},
{
"epoch": 0.95,
"learning_rate": 0.00010685933147632312,
"loss": 1.3479,
"step": 2775
},
{
"epoch": 0.95,
"learning_rate": 0.00010668523676880225,
"loss": 1.3262,
"step": 2780
},
{
"epoch": 0.95,
"learning_rate": 0.00010651114206128134,
"loss": 1.3421,
"step": 2785
},
{
"epoch": 0.95,
"learning_rate": 0.00010633704735376045,
"loss": 1.3808,
"step": 2790
},
{
"epoch": 0.96,
"learning_rate": 0.00010616295264623957,
"loss": 1.3222,
"step": 2795
},
{
"epoch": 0.96,
"learning_rate": 0.00010598885793871866,
"loss": 1.2433,
"step": 2800
},
{
"epoch": 0.96,
"eval_loss": 1.2961724996566772,
"eval_runtime": 732.0495,
"eval_samples_per_second": 7.097,
"eval_steps_per_second": 0.888,
"step": 2800
},
{
"epoch": 0.96,
"learning_rate": 0.00010581476323119777,
"loss": 1.2961,
"step": 2805
},
{
"epoch": 0.96,
"learning_rate": 0.00010564066852367689,
"loss": 1.3239,
"step": 2810
},
{
"epoch": 0.96,
"learning_rate": 0.00010546657381615599,
"loss": 1.4174,
"step": 2815
},
{
"epoch": 0.97,
"learning_rate": 0.00010529247910863511,
"loss": 1.4159,
"step": 2820
},
{
"epoch": 0.97,
"learning_rate": 0.00010511838440111422,
"loss": 1.2958,
"step": 2825
},
{
"epoch": 0.97,
"learning_rate": 0.00010494428969359331,
"loss": 1.3396,
"step": 2830
},
{
"epoch": 0.97,
"learning_rate": 0.00010477019498607243,
"loss": 1.3403,
"step": 2835
},
{
"epoch": 0.97,
"learning_rate": 0.00010459610027855153,
"loss": 1.3568,
"step": 2840
},
{
"epoch": 0.97,
"learning_rate": 0.00010442200557103065,
"loss": 1.2791,
"step": 2845
},
{
"epoch": 0.98,
"learning_rate": 0.00010424791086350976,
"loss": 1.3467,
"step": 2850
},
{
"epoch": 0.98,
"learning_rate": 0.00010407381615598885,
"loss": 1.3204,
"step": 2855
},
{
"epoch": 0.98,
"learning_rate": 0.00010389972144846799,
"loss": 1.3143,
"step": 2860
},
{
"epoch": 0.98,
"learning_rate": 0.00010372562674094708,
"loss": 1.3111,
"step": 2865
},
{
"epoch": 0.98,
"learning_rate": 0.00010355153203342618,
"loss": 1.2282,
"step": 2870
},
{
"epoch": 0.98,
"learning_rate": 0.0001033774373259053,
"loss": 1.3535,
"step": 2875
},
{
"epoch": 0.99,
"learning_rate": 0.0001032033426183844,
"loss": 1.3183,
"step": 2880
},
{
"epoch": 0.99,
"learning_rate": 0.00010302924791086353,
"loss": 1.2829,
"step": 2885
},
{
"epoch": 0.99,
"learning_rate": 0.00010285515320334262,
"loss": 1.1567,
"step": 2890
},
{
"epoch": 0.99,
"learning_rate": 0.00010268105849582173,
"loss": 1.3606,
"step": 2895
},
{
"epoch": 0.99,
"learning_rate": 0.00010250696378830085,
"loss": 1.3111,
"step": 2900
},
{
"epoch": 0.99,
"learning_rate": 0.00010233286908077995,
"loss": 1.3117,
"step": 2905
},
{
"epoch": 1.0,
"learning_rate": 0.00010215877437325904,
"loss": 1.3033,
"step": 2910
},
{
"epoch": 1.0,
"learning_rate": 0.00010198467966573816,
"loss": 1.3488,
"step": 2915
},
{
"epoch": 1.0,
"learning_rate": 0.00010181058495821727,
"loss": 1.2972,
"step": 2920
},
{
"epoch": 1.0,
"learning_rate": 0.00010163649025069639,
"loss": 1.3485,
"step": 2925
},
{
"epoch": 1.0,
"learning_rate": 0.0001014623955431755,
"loss": 1.371,
"step": 2930
},
{
"epoch": 1.0,
"learning_rate": 0.00010128830083565459,
"loss": 1.3131,
"step": 2935
},
{
"epoch": 1.01,
"learning_rate": 0.00010111420612813372,
"loss": 1.3348,
"step": 2940
},
{
"epoch": 1.01,
"learning_rate": 0.00010094011142061281,
"loss": 1.4028,
"step": 2945
},
{
"epoch": 1.01,
"learning_rate": 0.00010076601671309193,
"loss": 1.2784,
"step": 2950
},
{
"epoch": 1.01,
"learning_rate": 0.00010059192200557104,
"loss": 1.3039,
"step": 2955
},
{
"epoch": 1.01,
"learning_rate": 0.00010041782729805013,
"loss": 1.4023,
"step": 2960
},
{
"epoch": 1.01,
"learning_rate": 0.00010024373259052926,
"loss": 1.3074,
"step": 2965
},
{
"epoch": 1.02,
"learning_rate": 0.00010006963788300836,
"loss": 1.259,
"step": 2970
},
{
"epoch": 1.02,
"learning_rate": 9.989554317548748e-05,
"loss": 1.3248,
"step": 2975
},
{
"epoch": 1.02,
"learning_rate": 9.972144846796658e-05,
"loss": 1.3227,
"step": 2980
},
{
"epoch": 1.02,
"learning_rate": 9.954735376044569e-05,
"loss": 1.294,
"step": 2985
},
{
"epoch": 1.02,
"learning_rate": 9.93732590529248e-05,
"loss": 1.2245,
"step": 2990
},
{
"epoch": 1.02,
"learning_rate": 9.91991643454039e-05,
"loss": 1.2731,
"step": 2995
},
{
"epoch": 1.03,
"learning_rate": 9.902506963788302e-05,
"loss": 1.2349,
"step": 3000
},
{
"epoch": 1.03,
"eval_loss": 1.2951756715774536,
"eval_runtime": 732.4846,
"eval_samples_per_second": 7.092,
"eval_steps_per_second": 0.887,
"step": 3000
},
{
"epoch": 1.03,
"learning_rate": 9.885097493036211e-05,
"loss": 1.3739,
"step": 3005
},
{
"epoch": 1.03,
"learning_rate": 9.867688022284123e-05,
"loss": 1.3928,
"step": 3010
},
{
"epoch": 1.03,
"learning_rate": 9.850278551532034e-05,
"loss": 1.2705,
"step": 3015
},
{
"epoch": 1.03,
"learning_rate": 9.832869080779946e-05,
"loss": 1.306,
"step": 3020
},
{
"epoch": 1.04,
"learning_rate": 9.815459610027855e-05,
"loss": 1.262,
"step": 3025
},
{
"epoch": 1.04,
"learning_rate": 9.798050139275766e-05,
"loss": 1.2923,
"step": 3030
},
{
"epoch": 1.04,
"learning_rate": 9.780640668523678e-05,
"loss": 1.3027,
"step": 3035
},
{
"epoch": 1.04,
"learning_rate": 9.763231197771588e-05,
"loss": 1.3312,
"step": 3040
},
{
"epoch": 1.04,
"learning_rate": 9.7458217270195e-05,
"loss": 1.3507,
"step": 3045
},
{
"epoch": 1.04,
"learning_rate": 9.728412256267409e-05,
"loss": 1.2724,
"step": 3050
},
{
"epoch": 1.05,
"learning_rate": 9.711002785515321e-05,
"loss": 1.2655,
"step": 3055
},
{
"epoch": 1.05,
"learning_rate": 9.693593314763232e-05,
"loss": 1.352,
"step": 3060
},
{
"epoch": 1.05,
"learning_rate": 9.676183844011142e-05,
"loss": 1.3074,
"step": 3065
},
{
"epoch": 1.05,
"learning_rate": 9.658774373259053e-05,
"loss": 1.3014,
"step": 3070
},
{
"epoch": 1.05,
"learning_rate": 9.641364902506964e-05,
"loss": 1.3362,
"step": 3075
},
{
"epoch": 1.05,
"learning_rate": 9.623955431754876e-05,
"loss": 1.3764,
"step": 3080
},
{
"epoch": 1.06,
"learning_rate": 9.606545961002786e-05,
"loss": 1.2733,
"step": 3085
},
{
"epoch": 1.06,
"learning_rate": 9.589136490250697e-05,
"loss": 1.2318,
"step": 3090
},
{
"epoch": 1.06,
"learning_rate": 9.571727019498607e-05,
"loss": 1.3198,
"step": 3095
},
{
"epoch": 1.06,
"learning_rate": 9.554317548746519e-05,
"loss": 1.3222,
"step": 3100
},
{
"epoch": 1.06,
"learning_rate": 9.53690807799443e-05,
"loss": 1.2183,
"step": 3105
},
{
"epoch": 1.06,
"learning_rate": 9.519498607242339e-05,
"loss": 1.342,
"step": 3110
},
{
"epoch": 1.07,
"learning_rate": 9.502089136490251e-05,
"loss": 1.268,
"step": 3115
},
{
"epoch": 1.07,
"learning_rate": 9.484679665738162e-05,
"loss": 1.373,
"step": 3120
},
{
"epoch": 1.07,
"learning_rate": 9.467270194986074e-05,
"loss": 1.326,
"step": 3125
},
{
"epoch": 1.07,
"learning_rate": 9.449860724233984e-05,
"loss": 1.3662,
"step": 3130
},
{
"epoch": 1.07,
"learning_rate": 9.432451253481895e-05,
"loss": 1.327,
"step": 3135
},
{
"epoch": 1.07,
"learning_rate": 9.415041782729805e-05,
"loss": 1.2587,
"step": 3140
},
{
"epoch": 1.08,
"learning_rate": 9.397632311977716e-05,
"loss": 1.2852,
"step": 3145
},
{
"epoch": 1.08,
"learning_rate": 9.380222841225628e-05,
"loss": 1.2778,
"step": 3150
},
{
"epoch": 1.08,
"learning_rate": 9.362813370473537e-05,
"loss": 1.3912,
"step": 3155
},
{
"epoch": 1.08,
"learning_rate": 9.345403899721449e-05,
"loss": 1.2293,
"step": 3160
},
{
"epoch": 1.08,
"learning_rate": 9.32799442896936e-05,
"loss": 1.3164,
"step": 3165
},
{
"epoch": 1.08,
"learning_rate": 9.310584958217272e-05,
"loss": 1.3641,
"step": 3170
},
{
"epoch": 1.09,
"learning_rate": 9.293175487465181e-05,
"loss": 1.2796,
"step": 3175
},
{
"epoch": 1.09,
"learning_rate": 9.275766016713092e-05,
"loss": 1.3221,
"step": 3180
},
{
"epoch": 1.09,
"learning_rate": 9.258356545961003e-05,
"loss": 1.3635,
"step": 3185
},
{
"epoch": 1.09,
"learning_rate": 9.240947075208914e-05,
"loss": 1.2781,
"step": 3190
},
{
"epoch": 1.09,
"learning_rate": 9.223537604456825e-05,
"loss": 1.3838,
"step": 3195
},
{
"epoch": 1.1,
"learning_rate": 9.206128133704735e-05,
"loss": 1.3126,
"step": 3200
},
{
"epoch": 1.1,
"eval_loss": 1.2933902740478516,
"eval_runtime": 732.1293,
"eval_samples_per_second": 7.096,
"eval_steps_per_second": 0.888,
"step": 3200
},
{
"epoch": 1.1,
"learning_rate": 9.188718662952647e-05,
"loss": 1.2489,
"step": 3205
},
{
"epoch": 1.1,
"learning_rate": 9.171309192200558e-05,
"loss": 1.3376,
"step": 3210
},
{
"epoch": 1.1,
"learning_rate": 9.153899721448468e-05,
"loss": 1.2556,
"step": 3215
},
{
"epoch": 1.1,
"learning_rate": 9.136490250696379e-05,
"loss": 1.3112,
"step": 3220
},
{
"epoch": 1.1,
"learning_rate": 9.11908077994429e-05,
"loss": 1.2835,
"step": 3225
},
{
"epoch": 1.11,
"learning_rate": 9.101671309192202e-05,
"loss": 1.2976,
"step": 3230
},
{
"epoch": 1.11,
"learning_rate": 9.084261838440112e-05,
"loss": 1.266,
"step": 3235
},
{
"epoch": 1.11,
"learning_rate": 9.066852367688023e-05,
"loss": 1.3171,
"step": 3240
},
{
"epoch": 1.11,
"learning_rate": 9.049442896935933e-05,
"loss": 1.4022,
"step": 3245
},
{
"epoch": 1.11,
"learning_rate": 9.032033426183845e-05,
"loss": 1.2727,
"step": 3250
},
{
"epoch": 1.11,
"learning_rate": 9.014623955431756e-05,
"loss": 1.3149,
"step": 3255
},
{
"epoch": 1.12,
"learning_rate": 8.997214484679665e-05,
"loss": 1.3104,
"step": 3260
},
{
"epoch": 1.12,
"learning_rate": 8.979805013927577e-05,
"loss": 1.2367,
"step": 3265
},
{
"epoch": 1.12,
"learning_rate": 8.962395543175488e-05,
"loss": 1.2615,
"step": 3270
},
{
"epoch": 1.12,
"learning_rate": 8.9449860724234e-05,
"loss": 1.3045,
"step": 3275
},
{
"epoch": 1.12,
"learning_rate": 8.927576601671309e-05,
"loss": 1.2793,
"step": 3280
},
{
"epoch": 1.12,
"learning_rate": 8.910167130919221e-05,
"loss": 1.3093,
"step": 3285
},
{
"epoch": 1.13,
"learning_rate": 8.892757660167131e-05,
"loss": 1.3182,
"step": 3290
},
{
"epoch": 1.13,
"learning_rate": 8.875348189415042e-05,
"loss": 1.2849,
"step": 3295
},
{
"epoch": 1.13,
"learning_rate": 8.857938718662953e-05,
"loss": 1.3269,
"step": 3300
},
{
"epoch": 1.13,
"learning_rate": 8.840529247910863e-05,
"loss": 1.2924,
"step": 3305
},
{
"epoch": 1.13,
"learning_rate": 8.823119777158775e-05,
"loss": 1.2871,
"step": 3310
},
{
"epoch": 1.13,
"learning_rate": 8.805710306406686e-05,
"loss": 1.3247,
"step": 3315
},
{
"epoch": 1.14,
"learning_rate": 8.788300835654598e-05,
"loss": 1.4262,
"step": 3320
},
{
"epoch": 1.14,
"learning_rate": 8.770891364902507e-05,
"loss": 1.4257,
"step": 3325
},
{
"epoch": 1.14,
"learning_rate": 8.753481894150418e-05,
"loss": 1.2515,
"step": 3330
},
{
"epoch": 1.14,
"learning_rate": 8.73607242339833e-05,
"loss": 1.3327,
"step": 3335
},
{
"epoch": 1.14,
"learning_rate": 8.71866295264624e-05,
"loss": 1.2946,
"step": 3340
},
{
"epoch": 1.14,
"learning_rate": 8.70125348189415e-05,
"loss": 1.3422,
"step": 3345
},
{
"epoch": 1.15,
"learning_rate": 8.683844011142061e-05,
"loss": 1.3492,
"step": 3350
},
{
"epoch": 1.15,
"learning_rate": 8.666434540389973e-05,
"loss": 1.3511,
"step": 3355
},
{
"epoch": 1.15,
"learning_rate": 8.649025069637884e-05,
"loss": 1.2687,
"step": 3360
},
{
"epoch": 1.15,
"learning_rate": 8.631615598885794e-05,
"loss": 1.3712,
"step": 3365
},
{
"epoch": 1.15,
"learning_rate": 8.614206128133705e-05,
"loss": 1.3567,
"step": 3370
},
{
"epoch": 1.16,
"learning_rate": 8.596796657381616e-05,
"loss": 1.3005,
"step": 3375
},
{
"epoch": 1.16,
"learning_rate": 8.579387186629528e-05,
"loss": 1.213,
"step": 3380
},
{
"epoch": 1.16,
"learning_rate": 8.561977715877437e-05,
"loss": 1.2404,
"step": 3385
},
{
"epoch": 1.16,
"learning_rate": 8.544568245125349e-05,
"loss": 1.3713,
"step": 3390
},
{
"epoch": 1.16,
"learning_rate": 8.52715877437326e-05,
"loss": 1.3294,
"step": 3395
},
{
"epoch": 1.16,
"learning_rate": 8.509749303621171e-05,
"loss": 1.284,
"step": 3400
},
{
"epoch": 1.16,
"eval_loss": 1.2925370931625366,
"eval_runtime": 732.6042,
"eval_samples_per_second": 7.091,
"eval_steps_per_second": 0.887,
"step": 3400
},
{
"epoch": 1.17,
"learning_rate": 8.49233983286908e-05,
"loss": 1.355,
"step": 3405
},
{
"epoch": 1.17,
"learning_rate": 8.474930362116991e-05,
"loss": 1.3339,
"step": 3410
},
{
"epoch": 1.17,
"learning_rate": 8.457520891364903e-05,
"loss": 1.2847,
"step": 3415
},
{
"epoch": 1.17,
"learning_rate": 8.440111420612814e-05,
"loss": 1.3614,
"step": 3420
},
{
"epoch": 1.17,
"learning_rate": 8.422701949860726e-05,
"loss": 1.2328,
"step": 3425
},
{
"epoch": 1.17,
"learning_rate": 8.405292479108635e-05,
"loss": 1.3357,
"step": 3430
},
{
"epoch": 1.18,
"learning_rate": 8.387883008356547e-05,
"loss": 1.2801,
"step": 3435
},
{
"epoch": 1.18,
"learning_rate": 8.370473537604457e-05,
"loss": 1.2555,
"step": 3440
},
{
"epoch": 1.18,
"learning_rate": 8.353064066852368e-05,
"loss": 1.2358,
"step": 3445
},
{
"epoch": 1.18,
"learning_rate": 8.335654596100279e-05,
"loss": 1.3348,
"step": 3450
},
{
"epoch": 1.18,
"learning_rate": 8.318245125348189e-05,
"loss": 1.3154,
"step": 3455
},
{
"epoch": 1.18,
"learning_rate": 8.300835654596101e-05,
"loss": 1.2447,
"step": 3460
},
{
"epoch": 1.19,
"learning_rate": 8.283426183844012e-05,
"loss": 1.3446,
"step": 3465
},
{
"epoch": 1.19,
"learning_rate": 8.266016713091922e-05,
"loss": 1.2923,
"step": 3470
},
{
"epoch": 1.19,
"learning_rate": 8.248607242339833e-05,
"loss": 1.2936,
"step": 3475
},
{
"epoch": 1.19,
"learning_rate": 8.231197771587745e-05,
"loss": 1.2774,
"step": 3480
},
{
"epoch": 1.19,
"learning_rate": 8.213788300835655e-05,
"loss": 1.2417,
"step": 3485
},
{
"epoch": 1.19,
"learning_rate": 8.196378830083565e-05,
"loss": 1.3392,
"step": 3490
},
{
"epoch": 1.2,
"learning_rate": 8.178969359331477e-05,
"loss": 1.2959,
"step": 3495
},
{
"epoch": 1.2,
"learning_rate": 8.161559888579387e-05,
"loss": 1.3219,
"step": 3500
},
{
"epoch": 1.2,
"learning_rate": 8.144150417827299e-05,
"loss": 1.3028,
"step": 3505
},
{
"epoch": 1.2,
"learning_rate": 8.12674094707521e-05,
"loss": 1.3052,
"step": 3510
},
{
"epoch": 1.2,
"learning_rate": 8.10933147632312e-05,
"loss": 1.311,
"step": 3515
},
{
"epoch": 1.2,
"learning_rate": 8.091922005571031e-05,
"loss": 1.262,
"step": 3520
},
{
"epoch": 1.21,
"learning_rate": 8.074512534818942e-05,
"loss": 1.317,
"step": 3525
},
{
"epoch": 1.21,
"learning_rate": 8.057103064066854e-05,
"loss": 1.2233,
"step": 3530
},
{
"epoch": 1.21,
"learning_rate": 8.039693593314763e-05,
"loss": 1.3121,
"step": 3535
},
{
"epoch": 1.21,
"learning_rate": 8.022284122562675e-05,
"loss": 1.3265,
"step": 3540
},
{
"epoch": 1.21,
"learning_rate": 8.004874651810585e-05,
"loss": 1.323,
"step": 3545
},
{
"epoch": 1.21,
"learning_rate": 7.987465181058497e-05,
"loss": 1.3179,
"step": 3550
},
{
"epoch": 1.22,
"learning_rate": 7.970055710306406e-05,
"loss": 1.2651,
"step": 3555
},
{
"epoch": 1.22,
"learning_rate": 7.952646239554317e-05,
"loss": 1.2636,
"step": 3560
},
{
"epoch": 1.22,
"learning_rate": 7.935236768802229e-05,
"loss": 1.3234,
"step": 3565
},
{
"epoch": 1.22,
"learning_rate": 7.91782729805014e-05,
"loss": 1.2657,
"step": 3570
},
{
"epoch": 1.22,
"learning_rate": 7.90041782729805e-05,
"loss": 1.2825,
"step": 3575
},
{
"epoch": 1.23,
"learning_rate": 7.883008356545961e-05,
"loss": 1.3906,
"step": 3580
},
{
"epoch": 1.23,
"learning_rate": 7.865598885793873e-05,
"loss": 1.3652,
"step": 3585
},
{
"epoch": 1.23,
"learning_rate": 7.848189415041783e-05,
"loss": 1.3134,
"step": 3590
},
{
"epoch": 1.23,
"learning_rate": 7.830779944289694e-05,
"loss": 1.3358,
"step": 3595
},
{
"epoch": 1.23,
"learning_rate": 7.813370473537605e-05,
"loss": 1.2194,
"step": 3600
},
{
"epoch": 1.23,
"eval_loss": 1.2912499904632568,
"eval_runtime": 732.4213,
"eval_samples_per_second": 7.093,
"eval_steps_per_second": 0.887,
"step": 3600
},
{
"epoch": 1.23,
"learning_rate": 7.795961002785515e-05,
"loss": 1.3917,
"step": 3605
},
{
"epoch": 1.24,
"learning_rate": 7.778551532033427e-05,
"loss": 1.2922,
"step": 3610
},
{
"epoch": 1.24,
"learning_rate": 7.761142061281338e-05,
"loss": 1.3084,
"step": 3615
},
{
"epoch": 1.24,
"learning_rate": 7.743732590529248e-05,
"loss": 1.3974,
"step": 3620
},
{
"epoch": 1.24,
"learning_rate": 7.726323119777159e-05,
"loss": 1.3267,
"step": 3625
},
{
"epoch": 1.24,
"learning_rate": 7.708913649025071e-05,
"loss": 1.2931,
"step": 3630
},
{
"epoch": 1.24,
"learning_rate": 7.691504178272981e-05,
"loss": 1.2374,
"step": 3635
},
{
"epoch": 1.25,
"learning_rate": 7.674094707520891e-05,
"loss": 1.2701,
"step": 3640
},
{
"epoch": 1.25,
"learning_rate": 7.656685236768803e-05,
"loss": 1.3962,
"step": 3645
},
{
"epoch": 1.25,
"learning_rate": 7.639275766016713e-05,
"loss": 1.3269,
"step": 3650
},
{
"epoch": 1.25,
"learning_rate": 7.621866295264625e-05,
"loss": 1.3424,
"step": 3655
},
{
"epoch": 1.25,
"learning_rate": 7.604456824512534e-05,
"loss": 1.285,
"step": 3660
},
{
"epoch": 1.25,
"learning_rate": 7.587047353760446e-05,
"loss": 1.3711,
"step": 3665
},
{
"epoch": 1.26,
"learning_rate": 7.569637883008357e-05,
"loss": 1.3403,
"step": 3670
},
{
"epoch": 1.26,
"learning_rate": 7.552228412256268e-05,
"loss": 1.3563,
"step": 3675
},
{
"epoch": 1.26,
"learning_rate": 7.534818941504178e-05,
"loss": 1.2999,
"step": 3680
},
{
"epoch": 1.26,
"learning_rate": 7.517409470752089e-05,
"loss": 1.2715,
"step": 3685
},
{
"epoch": 1.26,
"learning_rate": 7.500000000000001e-05,
"loss": 1.3427,
"step": 3690
},
{
"epoch": 1.26,
"learning_rate": 7.482590529247911e-05,
"loss": 1.2558,
"step": 3695
},
{
"epoch": 1.27,
"learning_rate": 7.465181058495823e-05,
"loss": 1.3071,
"step": 3700
},
{
"epoch": 1.27,
"learning_rate": 7.447771587743732e-05,
"loss": 1.2598,
"step": 3705
},
{
"epoch": 1.27,
"learning_rate": 7.430362116991643e-05,
"loss": 1.3291,
"step": 3710
},
{
"epoch": 1.27,
"learning_rate": 7.412952646239555e-05,
"loss": 1.3219,
"step": 3715
},
{
"epoch": 1.27,
"learning_rate": 7.395543175487466e-05,
"loss": 1.346,
"step": 3720
},
{
"epoch": 1.27,
"learning_rate": 7.378133704735376e-05,
"loss": 1.3308,
"step": 3725
},
{
"epoch": 1.28,
"learning_rate": 7.360724233983287e-05,
"loss": 1.2899,
"step": 3730
},
{
"epoch": 1.28,
"learning_rate": 7.343314763231199e-05,
"loss": 1.2938,
"step": 3735
},
{
"epoch": 1.28,
"learning_rate": 7.32590529247911e-05,
"loss": 1.2433,
"step": 3740
},
{
"epoch": 1.28,
"learning_rate": 7.30849582172702e-05,
"loss": 1.3381,
"step": 3745
},
{
"epoch": 1.28,
"learning_rate": 7.29108635097493e-05,
"loss": 1.3111,
"step": 3750
},
{
"epoch": 1.29,
"learning_rate": 7.273676880222841e-05,
"loss": 1.3363,
"step": 3755
},
{
"epoch": 1.29,
"learning_rate": 7.256267409470753e-05,
"loss": 1.273,
"step": 3760
},
{
"epoch": 1.29,
"learning_rate": 7.238857938718662e-05,
"loss": 1.3039,
"step": 3765
},
{
"epoch": 1.29,
"learning_rate": 7.221448467966574e-05,
"loss": 1.2538,
"step": 3770
},
{
"epoch": 1.29,
"learning_rate": 7.204038997214485e-05,
"loss": 1.2903,
"step": 3775
},
{
"epoch": 1.29,
"learning_rate": 7.186629526462397e-05,
"loss": 1.3772,
"step": 3780
},
{
"epoch": 1.3,
"learning_rate": 7.169220055710307e-05,
"loss": 1.215,
"step": 3785
},
{
"epoch": 1.3,
"learning_rate": 7.151810584958217e-05,
"loss": 1.3577,
"step": 3790
},
{
"epoch": 1.3,
"learning_rate": 7.134401114206129e-05,
"loss": 1.3559,
"step": 3795
},
{
"epoch": 1.3,
"learning_rate": 7.116991643454039e-05,
"loss": 1.2885,
"step": 3800
},
{
"epoch": 1.3,
"eval_loss": 1.2902462482452393,
"eval_runtime": 737.6841,
"eval_samples_per_second": 7.042,
"eval_steps_per_second": 0.881,
"step": 3800
},
{
"epoch": 1.3,
"learning_rate": 7.099582172701951e-05,
"loss": 1.322,
"step": 3805
},
{
"epoch": 1.3,
"learning_rate": 7.08217270194986e-05,
"loss": 1.2344,
"step": 3810
},
{
"epoch": 1.31,
"learning_rate": 7.064763231197772e-05,
"loss": 1.2122,
"step": 3815
},
{
"epoch": 1.31,
"learning_rate": 7.047353760445683e-05,
"loss": 1.3973,
"step": 3820
},
{
"epoch": 1.31,
"learning_rate": 7.029944289693594e-05,
"loss": 1.2172,
"step": 3825
},
{
"epoch": 1.31,
"learning_rate": 7.012534818941504e-05,
"loss": 1.263,
"step": 3830
},
{
"epoch": 1.31,
"learning_rate": 6.995125348189415e-05,
"loss": 1.3488,
"step": 3835
},
{
"epoch": 1.31,
"learning_rate": 6.977715877437327e-05,
"loss": 1.391,
"step": 3840
},
{
"epoch": 1.32,
"learning_rate": 6.960306406685237e-05,
"loss": 1.3284,
"step": 3845
},
{
"epoch": 1.32,
"learning_rate": 6.942896935933148e-05,
"loss": 1.2766,
"step": 3850
},
{
"epoch": 1.32,
"learning_rate": 6.925487465181058e-05,
"loss": 1.3801,
"step": 3855
},
{
"epoch": 1.32,
"learning_rate": 6.90807799442897e-05,
"loss": 1.3323,
"step": 3860
},
{
"epoch": 1.32,
"learning_rate": 6.890668523676881e-05,
"loss": 1.2127,
"step": 3865
},
{
"epoch": 1.32,
"learning_rate": 6.87325905292479e-05,
"loss": 1.2669,
"step": 3870
},
{
"epoch": 1.33,
"learning_rate": 6.855849582172702e-05,
"loss": 1.3096,
"step": 3875
},
{
"epoch": 1.33,
"learning_rate": 6.838440111420613e-05,
"loss": 1.3761,
"step": 3880
},
{
"epoch": 1.33,
"learning_rate": 6.821030640668525e-05,
"loss": 1.3147,
"step": 3885
},
{
"epoch": 1.33,
"learning_rate": 6.803621169916435e-05,
"loss": 1.3225,
"step": 3890
},
{
"epoch": 1.33,
"learning_rate": 6.786211699164346e-05,
"loss": 1.3215,
"step": 3895
},
{
"epoch": 1.33,
"learning_rate": 6.768802228412257e-05,
"loss": 1.3797,
"step": 3900
},
{
"epoch": 1.34,
"learning_rate": 6.751392757660167e-05,
"loss": 1.2743,
"step": 3905
},
{
"epoch": 1.34,
"learning_rate": 6.733983286908079e-05,
"loss": 1.2811,
"step": 3910
},
{
"epoch": 1.34,
"learning_rate": 6.716573816155988e-05,
"loss": 1.3509,
"step": 3915
},
{
"epoch": 1.34,
"learning_rate": 6.6991643454039e-05,
"loss": 1.2394,
"step": 3920
},
{
"epoch": 1.34,
"learning_rate": 6.681754874651811e-05,
"loss": 1.2732,
"step": 3925
},
{
"epoch": 1.34,
"learning_rate": 6.664345403899723e-05,
"loss": 1.3003,
"step": 3930
},
{
"epoch": 1.35,
"learning_rate": 6.646935933147632e-05,
"loss": 1.2553,
"step": 3935
},
{
"epoch": 1.35,
"learning_rate": 6.629526462395543e-05,
"loss": 1.3428,
"step": 3940
},
{
"epoch": 1.35,
"learning_rate": 6.612116991643455e-05,
"loss": 1.3241,
"step": 3945
},
{
"epoch": 1.35,
"learning_rate": 6.594707520891365e-05,
"loss": 1.3564,
"step": 3950
},
{
"epoch": 1.35,
"learning_rate": 6.577298050139276e-05,
"loss": 1.3064,
"step": 3955
},
{
"epoch": 1.36,
"learning_rate": 6.559888579387186e-05,
"loss": 1.3194,
"step": 3960
},
{
"epoch": 1.36,
"learning_rate": 6.542479108635098e-05,
"loss": 1.3197,
"step": 3965
},
{
"epoch": 1.36,
"learning_rate": 6.525069637883009e-05,
"loss": 1.3256,
"step": 3970
},
{
"epoch": 1.36,
"learning_rate": 6.50766016713092e-05,
"loss": 1.2681,
"step": 3975
},
{
"epoch": 1.36,
"learning_rate": 6.49025069637883e-05,
"loss": 1.2085,
"step": 3980
},
{
"epoch": 1.36,
"learning_rate": 6.472841225626741e-05,
"loss": 1.3024,
"step": 3985
},
{
"epoch": 1.37,
"learning_rate": 6.455431754874653e-05,
"loss": 1.2928,
"step": 3990
},
{
"epoch": 1.37,
"learning_rate": 6.438022284122563e-05,
"loss": 1.2967,
"step": 3995
},
{
"epoch": 1.37,
"learning_rate": 6.420612813370474e-05,
"loss": 1.2159,
"step": 4000
},
{
"epoch": 1.37,
"eval_loss": 1.288769245147705,
"eval_runtime": 737.8329,
"eval_samples_per_second": 7.041,
"eval_steps_per_second": 0.881,
"step": 4000
},
{
"epoch": 1.37,
"learning_rate": 6.403203342618384e-05,
"loss": 1.3855,
"step": 4005
},
{
"epoch": 1.37,
"learning_rate": 6.385793871866296e-05,
"loss": 1.3212,
"step": 4010
},
{
"epoch": 1.37,
"learning_rate": 6.368384401114207e-05,
"loss": 1.3354,
"step": 4015
},
{
"epoch": 1.38,
"learning_rate": 6.350974930362116e-05,
"loss": 1.294,
"step": 4020
},
{
"epoch": 1.38,
"learning_rate": 6.333565459610028e-05,
"loss": 1.2667,
"step": 4025
},
{
"epoch": 1.38,
"learning_rate": 6.316155988857939e-05,
"loss": 1.3167,
"step": 4030
},
{
"epoch": 1.38,
"learning_rate": 6.298746518105851e-05,
"loss": 1.3521,
"step": 4035
},
{
"epoch": 1.38,
"learning_rate": 6.28133704735376e-05,
"loss": 1.248,
"step": 4040
},
{
"epoch": 1.38,
"learning_rate": 6.263927576601672e-05,
"loss": 1.2941,
"step": 4045
},
{
"epoch": 1.39,
"learning_rate": 6.246518105849583e-05,
"loss": 1.3428,
"step": 4050
},
{
"epoch": 1.39,
"learning_rate": 6.229108635097493e-05,
"loss": 1.1704,
"step": 4055
},
{
"epoch": 1.39,
"learning_rate": 6.211699164345404e-05,
"loss": 1.3148,
"step": 4060
},
{
"epoch": 1.39,
"learning_rate": 6.194289693593314e-05,
"loss": 1.275,
"step": 4065
},
{
"epoch": 1.39,
"learning_rate": 6.176880222841226e-05,
"loss": 1.3346,
"step": 4070
},
{
"epoch": 1.39,
"learning_rate": 6.159470752089137e-05,
"loss": 1.3067,
"step": 4075
},
{
"epoch": 1.4,
"learning_rate": 6.142061281337049e-05,
"loss": 1.3264,
"step": 4080
},
{
"epoch": 1.4,
"learning_rate": 6.124651810584958e-05,
"loss": 1.2819,
"step": 4085
},
{
"epoch": 1.4,
"learning_rate": 6.107242339832869e-05,
"loss": 1.3631,
"step": 4090
},
{
"epoch": 1.4,
"learning_rate": 6.0898328690807806e-05,
"loss": 1.2887,
"step": 4095
},
{
"epoch": 1.4,
"learning_rate": 6.072423398328692e-05,
"loss": 1.3059,
"step": 4100
},
{
"epoch": 1.4,
"learning_rate": 6.055013927576602e-05,
"loss": 1.2826,
"step": 4105
},
{
"epoch": 1.41,
"learning_rate": 6.0376044568245124e-05,
"loss": 1.3932,
"step": 4110
},
{
"epoch": 1.41,
"learning_rate": 6.0201949860724236e-05,
"loss": 1.2938,
"step": 4115
},
{
"epoch": 1.41,
"learning_rate": 6.002785515320335e-05,
"loss": 1.3074,
"step": 4120
},
{
"epoch": 1.41,
"learning_rate": 5.985376044568245e-05,
"loss": 1.2826,
"step": 4125
},
{
"epoch": 1.41,
"learning_rate": 5.967966573816156e-05,
"loss": 1.3634,
"step": 4130
},
{
"epoch": 1.42,
"learning_rate": 5.9505571030640674e-05,
"loss": 1.3375,
"step": 4135
},
{
"epoch": 1.42,
"learning_rate": 5.9331476323119787e-05,
"loss": 1.3556,
"step": 4140
},
{
"epoch": 1.42,
"learning_rate": 5.9157381615598886e-05,
"loss": 1.2967,
"step": 4145
},
{
"epoch": 1.42,
"learning_rate": 5.898328690807799e-05,
"loss": 1.3048,
"step": 4150
},
{
"epoch": 1.42,
"learning_rate": 5.8809192200557104e-05,
"loss": 1.2729,
"step": 4155
},
{
"epoch": 1.42,
"learning_rate": 5.863509749303622e-05,
"loss": 1.1831,
"step": 4160
},
{
"epoch": 1.43,
"learning_rate": 5.846100278551533e-05,
"loss": 1.3411,
"step": 4165
},
{
"epoch": 1.43,
"learning_rate": 5.828690807799443e-05,
"loss": 1.2939,
"step": 4170
},
{
"epoch": 1.43,
"learning_rate": 5.811281337047354e-05,
"loss": 1.3429,
"step": 4175
},
{
"epoch": 1.43,
"learning_rate": 5.7938718662952654e-05,
"loss": 1.3192,
"step": 4180
},
{
"epoch": 1.43,
"learning_rate": 5.776462395543176e-05,
"loss": 1.2657,
"step": 4185
},
{
"epoch": 1.43,
"learning_rate": 5.759052924791086e-05,
"loss": 1.3071,
"step": 4190
},
{
"epoch": 1.44,
"learning_rate": 5.741643454038997e-05,
"loss": 1.3702,
"step": 4195
},
{
"epoch": 1.44,
"learning_rate": 5.7242339832869085e-05,
"loss": 1.2832,
"step": 4200
},
{
"epoch": 1.44,
"eval_loss": 1.288108468055725,
"eval_runtime": 737.6272,
"eval_samples_per_second": 7.043,
"eval_steps_per_second": 0.881,
"step": 4200
}
],
"max_steps": 5844,
"num_train_epochs": 2,
"total_flos": 2.5013277853483008e+17,
"trial_name": null,
"trial_params": null
}