generated from xuyuqing/ailab
19310 lines
383 KiB
JSON
19310 lines
383 KiB
JSON
{
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 9.99922221358015,
|
|
"global_step": 32140,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"epoch": 0.0,
|
|
"learning_rate": 0.0004999998805687496,
|
|
"loss": 1.9389,
|
|
"step": 10
|
|
},
|
|
{
|
|
"epoch": 0.01,
|
|
"learning_rate": 0.0004999995222751128,
|
|
"loss": 1.9106,
|
|
"step": 20
|
|
},
|
|
{
|
|
"epoch": 0.01,
|
|
"learning_rate": 0.0004999989251194318,
|
|
"loss": 1.8389,
|
|
"step": 30
|
|
},
|
|
{
|
|
"epoch": 0.01,
|
|
"learning_rate": 0.000499998089102277,
|
|
"loss": 1.8865,
|
|
"step": 40
|
|
},
|
|
{
|
|
"epoch": 0.02,
|
|
"learning_rate": 0.0004999970142244473,
|
|
"loss": 1.938,
|
|
"step": 50
|
|
},
|
|
{
|
|
"epoch": 0.02,
|
|
"learning_rate": 0.0004999957004869699,
|
|
"loss": 1.7825,
|
|
"step": 60
|
|
},
|
|
{
|
|
"epoch": 0.02,
|
|
"learning_rate": 0.0004999941478910996,
|
|
"loss": 1.8613,
|
|
"step": 70
|
|
},
|
|
{
|
|
"epoch": 0.02,
|
|
"learning_rate": 0.0004999923564383201,
|
|
"loss": 1.8393,
|
|
"step": 80
|
|
},
|
|
{
|
|
"epoch": 0.03,
|
|
"learning_rate": 0.000499990326130343,
|
|
"loss": 1.8197,
|
|
"step": 90
|
|
},
|
|
{
|
|
"epoch": 0.03,
|
|
"learning_rate": 0.0004999880569691082,
|
|
"loss": 1.8327,
|
|
"step": 100
|
|
},
|
|
{
|
|
"epoch": 0.03,
|
|
"learning_rate": 0.0004999855489567837,
|
|
"loss": 1.7863,
|
|
"step": 110
|
|
},
|
|
{
|
|
"epoch": 0.04,
|
|
"learning_rate": 0.0004999828020957657,
|
|
"loss": 1.8215,
|
|
"step": 120
|
|
},
|
|
{
|
|
"epoch": 0.04,
|
|
"learning_rate": 0.0004999798163886789,
|
|
"loss": 1.6967,
|
|
"step": 130
|
|
},
|
|
{
|
|
"epoch": 0.04,
|
|
"learning_rate": 0.0004999765918383759,
|
|
"loss": 1.8287,
|
|
"step": 140
|
|
},
|
|
{
|
|
"epoch": 0.05,
|
|
"learning_rate": 0.0004999731284479374,
|
|
"loss": 1.8981,
|
|
"step": 150
|
|
},
|
|
{
|
|
"epoch": 0.05,
|
|
"learning_rate": 0.0004999694262206728,
|
|
"loss": 1.8071,
|
|
"step": 160
|
|
},
|
|
{
|
|
"epoch": 0.05,
|
|
"learning_rate": 0.0004999654851601192,
|
|
"loss": 1.718,
|
|
"step": 170
|
|
},
|
|
{
|
|
"epoch": 0.06,
|
|
"learning_rate": 0.0004999613052700423,
|
|
"loss": 1.795,
|
|
"step": 180
|
|
},
|
|
{
|
|
"epoch": 0.06,
|
|
"learning_rate": 0.0004999568865544354,
|
|
"loss": 1.7415,
|
|
"step": 190
|
|
},
|
|
{
|
|
"epoch": 0.06,
|
|
"learning_rate": 0.0004999522290175207,
|
|
"loss": 1.7979,
|
|
"step": 200
|
|
},
|
|
{
|
|
"epoch": 0.07,
|
|
"learning_rate": 0.0004999473326637482,
|
|
"loss": 1.7825,
|
|
"step": 210
|
|
},
|
|
{
|
|
"epoch": 0.07,
|
|
"learning_rate": 0.0004999421974977959,
|
|
"loss": 1.8419,
|
|
"step": 220
|
|
},
|
|
{
|
|
"epoch": 0.07,
|
|
"learning_rate": 0.0004999368235245705,
|
|
"loss": 1.8366,
|
|
"step": 230
|
|
},
|
|
{
|
|
"epoch": 0.07,
|
|
"learning_rate": 0.0004999312107492062,
|
|
"loss": 1.7285,
|
|
"step": 240
|
|
},
|
|
{
|
|
"epoch": 0.08,
|
|
"learning_rate": 0.0004999253591770661,
|
|
"loss": 1.7213,
|
|
"step": 250
|
|
},
|
|
{
|
|
"epoch": 0.08,
|
|
"learning_rate": 0.0004999192688137409,
|
|
"loss": 1.7836,
|
|
"step": 260
|
|
},
|
|
{
|
|
"epoch": 0.08,
|
|
"learning_rate": 0.0004999129396650497,
|
|
"loss": 1.9064,
|
|
"step": 270
|
|
},
|
|
{
|
|
"epoch": 0.09,
|
|
"learning_rate": 0.0004999063717370395,
|
|
"loss": 1.7067,
|
|
"step": 280
|
|
},
|
|
{
|
|
"epoch": 0.09,
|
|
"learning_rate": 0.0004998995650359859,
|
|
"loss": 1.7416,
|
|
"step": 290
|
|
},
|
|
{
|
|
"epoch": 0.09,
|
|
"learning_rate": 0.0004998925195683922,
|
|
"loss": 1.7574,
|
|
"step": 300
|
|
},
|
|
{
|
|
"epoch": 0.1,
|
|
"learning_rate": 0.0004998852353409899,
|
|
"loss": 1.7004,
|
|
"step": 310
|
|
},
|
|
{
|
|
"epoch": 0.1,
|
|
"learning_rate": 0.000499877712360739,
|
|
"loss": 1.7429,
|
|
"step": 320
|
|
},
|
|
{
|
|
"epoch": 0.1,
|
|
"learning_rate": 0.000499869950634827,
|
|
"loss": 1.8529,
|
|
"step": 330
|
|
},
|
|
{
|
|
"epoch": 0.11,
|
|
"learning_rate": 0.0004998619501706702,
|
|
"loss": 1.8219,
|
|
"step": 340
|
|
},
|
|
{
|
|
"epoch": 0.11,
|
|
"learning_rate": 0.0004998537109759124,
|
|
"loss": 1.8428,
|
|
"step": 350
|
|
},
|
|
{
|
|
"epoch": 0.11,
|
|
"learning_rate": 0.0004998452330584258,
|
|
"loss": 1.7116,
|
|
"step": 360
|
|
},
|
|
{
|
|
"epoch": 0.12,
|
|
"learning_rate": 0.0004998365164263106,
|
|
"loss": 1.729,
|
|
"step": 370
|
|
},
|
|
{
|
|
"epoch": 0.12,
|
|
"learning_rate": 0.0004998275610878951,
|
|
"loss": 1.8128,
|
|
"step": 380
|
|
},
|
|
{
|
|
"epoch": 0.12,
|
|
"learning_rate": 0.0004998183670517358,
|
|
"loss": 1.7193,
|
|
"step": 390
|
|
},
|
|
{
|
|
"epoch": 0.12,
|
|
"learning_rate": 0.0004998089343266169,
|
|
"loss": 1.7083,
|
|
"step": 400
|
|
},
|
|
{
|
|
"epoch": 0.13,
|
|
"learning_rate": 0.0004997992629215511,
|
|
"loss": 1.7527,
|
|
"step": 410
|
|
},
|
|
{
|
|
"epoch": 0.13,
|
|
"learning_rate": 0.0004997893528457789,
|
|
"loss": 1.7822,
|
|
"step": 420
|
|
},
|
|
{
|
|
"epoch": 0.13,
|
|
"learning_rate": 0.0004997792041087688,
|
|
"loss": 1.6584,
|
|
"step": 430
|
|
},
|
|
{
|
|
"epoch": 0.14,
|
|
"learning_rate": 0.0004997688167202176,
|
|
"loss": 1.8177,
|
|
"step": 440
|
|
},
|
|
{
|
|
"epoch": 0.14,
|
|
"learning_rate": 0.0004997581906900498,
|
|
"loss": 1.7904,
|
|
"step": 450
|
|
},
|
|
{
|
|
"epoch": 0.14,
|
|
"learning_rate": 0.000499747326028418,
|
|
"loss": 1.7827,
|
|
"step": 460
|
|
},
|
|
{
|
|
"epoch": 0.15,
|
|
"learning_rate": 0.0004997362227457029,
|
|
"loss": 1.7819,
|
|
"step": 470
|
|
},
|
|
{
|
|
"epoch": 0.15,
|
|
"learning_rate": 0.0004997248808525131,
|
|
"loss": 1.7798,
|
|
"step": 480
|
|
},
|
|
{
|
|
"epoch": 0.15,
|
|
"learning_rate": 0.0004997133003596853,
|
|
"loss": 1.7215,
|
|
"step": 490
|
|
},
|
|
{
|
|
"epoch": 0.16,
|
|
"learning_rate": 0.000499701481278284,
|
|
"loss": 1.8057,
|
|
"step": 500
|
|
},
|
|
{
|
|
"epoch": 0.16,
|
|
"learning_rate": 0.0004996894236196016,
|
|
"loss": 1.7499,
|
|
"step": 510
|
|
},
|
|
{
|
|
"epoch": 0.16,
|
|
"learning_rate": 0.000499677127395159,
|
|
"loss": 1.7228,
|
|
"step": 520
|
|
},
|
|
{
|
|
"epoch": 0.16,
|
|
"learning_rate": 0.0004996645926167042,
|
|
"loss": 1.6701,
|
|
"step": 530
|
|
},
|
|
{
|
|
"epoch": 0.17,
|
|
"learning_rate": 0.0004996518192962138,
|
|
"loss": 1.8472,
|
|
"step": 540
|
|
},
|
|
{
|
|
"epoch": 0.17,
|
|
"learning_rate": 0.0004996388074458921,
|
|
"loss": 1.7252,
|
|
"step": 550
|
|
},
|
|
{
|
|
"epoch": 0.17,
|
|
"learning_rate": 0.000499625557078171,
|
|
"loss": 1.7309,
|
|
"step": 560
|
|
},
|
|
{
|
|
"epoch": 0.18,
|
|
"learning_rate": 0.0004996120682057108,
|
|
"loss": 1.717,
|
|
"step": 570
|
|
},
|
|
{
|
|
"epoch": 0.18,
|
|
"learning_rate": 0.0004995983408413993,
|
|
"loss": 1.7903,
|
|
"step": 580
|
|
},
|
|
{
|
|
"epoch": 0.18,
|
|
"learning_rate": 0.0004995843749983525,
|
|
"loss": 1.889,
|
|
"step": 590
|
|
},
|
|
{
|
|
"epoch": 0.19,
|
|
"learning_rate": 0.000499570170689914,
|
|
"loss": 1.8804,
|
|
"step": 600
|
|
},
|
|
{
|
|
"epoch": 0.19,
|
|
"learning_rate": 0.0004995557279296552,
|
|
"loss": 1.8694,
|
|
"step": 610
|
|
},
|
|
{
|
|
"epoch": 0.19,
|
|
"learning_rate": 0.0004995410467313754,
|
|
"loss": 1.7587,
|
|
"step": 620
|
|
},
|
|
{
|
|
"epoch": 0.2,
|
|
"learning_rate": 0.0004995261271091019,
|
|
"loss": 1.7979,
|
|
"step": 630
|
|
},
|
|
{
|
|
"epoch": 0.2,
|
|
"learning_rate": 0.0004995109690770897,
|
|
"loss": 1.7325,
|
|
"step": 640
|
|
},
|
|
{
|
|
"epoch": 0.2,
|
|
"learning_rate": 0.0004994955726498214,
|
|
"loss": 1.7166,
|
|
"step": 650
|
|
},
|
|
{
|
|
"epoch": 0.21,
|
|
"learning_rate": 0.0004994799378420074,
|
|
"loss": 1.7867,
|
|
"step": 660
|
|
},
|
|
{
|
|
"epoch": 0.21,
|
|
"learning_rate": 0.0004994640646685863,
|
|
"loss": 1.7599,
|
|
"step": 670
|
|
},
|
|
{
|
|
"epoch": 0.21,
|
|
"learning_rate": 0.0004994479531447239,
|
|
"loss": 1.7526,
|
|
"step": 680
|
|
},
|
|
{
|
|
"epoch": 0.21,
|
|
"learning_rate": 0.000499431603285814,
|
|
"loss": 1.8197,
|
|
"step": 690
|
|
},
|
|
{
|
|
"epoch": 0.22,
|
|
"learning_rate": 0.0004994150151074782,
|
|
"loss": 1.7941,
|
|
"step": 700
|
|
},
|
|
{
|
|
"epoch": 0.22,
|
|
"learning_rate": 0.0004993981886255654,
|
|
"loss": 1.8616,
|
|
"step": 710
|
|
},
|
|
{
|
|
"epoch": 0.22,
|
|
"learning_rate": 0.0004993811238561528,
|
|
"loss": 1.7482,
|
|
"step": 720
|
|
},
|
|
{
|
|
"epoch": 0.23,
|
|
"learning_rate": 0.0004993638208155446,
|
|
"loss": 1.8007,
|
|
"step": 730
|
|
},
|
|
{
|
|
"epoch": 0.23,
|
|
"learning_rate": 0.0004993462795202733,
|
|
"loss": 1.7376,
|
|
"step": 740
|
|
},
|
|
{
|
|
"epoch": 0.23,
|
|
"learning_rate": 0.0004993284999870984,
|
|
"loss": 1.7935,
|
|
"step": 750
|
|
},
|
|
{
|
|
"epoch": 0.24,
|
|
"learning_rate": 0.0004993104822330076,
|
|
"loss": 1.8312,
|
|
"step": 760
|
|
},
|
|
{
|
|
"epoch": 0.24,
|
|
"learning_rate": 0.0004992922262752159,
|
|
"loss": 1.8165,
|
|
"step": 770
|
|
},
|
|
{
|
|
"epoch": 0.24,
|
|
"learning_rate": 0.0004992737321311661,
|
|
"loss": 1.7524,
|
|
"step": 780
|
|
},
|
|
{
|
|
"epoch": 0.25,
|
|
"learning_rate": 0.0004992549998185281,
|
|
"loss": 1.7817,
|
|
"step": 790
|
|
},
|
|
{
|
|
"epoch": 0.25,
|
|
"learning_rate": 0.0004992360293551999,
|
|
"loss": 1.7299,
|
|
"step": 800
|
|
},
|
|
{
|
|
"epoch": 0.25,
|
|
"learning_rate": 0.0004992168207593069,
|
|
"loss": 1.7824,
|
|
"step": 810
|
|
},
|
|
{
|
|
"epoch": 0.26,
|
|
"learning_rate": 0.0004991973740492017,
|
|
"loss": 1.8234,
|
|
"step": 820
|
|
},
|
|
{
|
|
"epoch": 0.26,
|
|
"learning_rate": 0.000499177689243465,
|
|
"loss": 1.818,
|
|
"step": 830
|
|
},
|
|
{
|
|
"epoch": 0.26,
|
|
"learning_rate": 0.0004991577663609043,
|
|
"loss": 1.7867,
|
|
"step": 840
|
|
},
|
|
{
|
|
"epoch": 0.26,
|
|
"learning_rate": 0.0004991376054205551,
|
|
"loss": 1.7903,
|
|
"step": 850
|
|
},
|
|
{
|
|
"epoch": 0.27,
|
|
"learning_rate": 0.0004991172064416803,
|
|
"loss": 1.8069,
|
|
"step": 860
|
|
},
|
|
{
|
|
"epoch": 0.27,
|
|
"learning_rate": 0.0004990965694437698,
|
|
"loss": 1.7544,
|
|
"step": 870
|
|
},
|
|
{
|
|
"epoch": 0.27,
|
|
"learning_rate": 0.0004990756944465414,
|
|
"loss": 1.7152,
|
|
"step": 880
|
|
},
|
|
{
|
|
"epoch": 0.28,
|
|
"learning_rate": 0.0004990545814699401,
|
|
"loss": 1.8597,
|
|
"step": 890
|
|
},
|
|
{
|
|
"epoch": 0.28,
|
|
"learning_rate": 0.0004990332305341382,
|
|
"loss": 1.821,
|
|
"step": 900
|
|
},
|
|
{
|
|
"epoch": 0.28,
|
|
"learning_rate": 0.0004990116416595356,
|
|
"loss": 1.8564,
|
|
"step": 910
|
|
},
|
|
{
|
|
"epoch": 0.29,
|
|
"learning_rate": 0.0004989898148667593,
|
|
"loss": 1.8907,
|
|
"step": 920
|
|
},
|
|
{
|
|
"epoch": 0.29,
|
|
"learning_rate": 0.0004989677501766637,
|
|
"loss": 1.8176,
|
|
"step": 930
|
|
},
|
|
{
|
|
"epoch": 0.29,
|
|
"learning_rate": 0.0004989454476103306,
|
|
"loss": 1.6966,
|
|
"step": 940
|
|
},
|
|
{
|
|
"epoch": 0.3,
|
|
"learning_rate": 0.000498922907189069,
|
|
"loss": 1.7937,
|
|
"step": 950
|
|
},
|
|
{
|
|
"epoch": 0.3,
|
|
"learning_rate": 0.000498900128934415,
|
|
"loss": 1.8252,
|
|
"step": 960
|
|
},
|
|
{
|
|
"epoch": 0.3,
|
|
"learning_rate": 0.0004988771128681322,
|
|
"loss": 1.8496,
|
|
"step": 970
|
|
},
|
|
{
|
|
"epoch": 0.3,
|
|
"learning_rate": 0.0004988538590122112,
|
|
"loss": 1.7762,
|
|
"step": 980
|
|
},
|
|
{
|
|
"epoch": 0.31,
|
|
"learning_rate": 0.00049883036738887,
|
|
"loss": 1.6722,
|
|
"step": 990
|
|
},
|
|
{
|
|
"epoch": 0.31,
|
|
"learning_rate": 0.0004988066380205536,
|
|
"loss": 1.8001,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"epoch": 0.31,
|
|
"learning_rate": 0.0004987826709299342,
|
|
"loss": 1.7967,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"epoch": 0.32,
|
|
"learning_rate": 0.0004987584661399114,
|
|
"loss": 1.7423,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"epoch": 0.32,
|
|
"learning_rate": 0.0004987340236736113,
|
|
"loss": 1.6618,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"epoch": 0.32,
|
|
"learning_rate": 0.0004987093435543876,
|
|
"loss": 1.8013,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"epoch": 0.33,
|
|
"learning_rate": 0.000498684425805821,
|
|
"loss": 1.7008,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"epoch": 0.33,
|
|
"learning_rate": 0.0004986592704517192,
|
|
"loss": 1.8315,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"epoch": 0.33,
|
|
"learning_rate": 0.0004986338775161167,
|
|
"loss": 1.7826,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"epoch": 0.34,
|
|
"learning_rate": 0.0004986082470232753,
|
|
"loss": 1.7943,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"epoch": 0.34,
|
|
"learning_rate": 0.0004985823789976836,
|
|
"loss": 1.7835,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"epoch": 0.34,
|
|
"learning_rate": 0.0004985562734640573,
|
|
"loss": 1.812,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"epoch": 0.35,
|
|
"learning_rate": 0.0004985299304473388,
|
|
"loss": 1.7741,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"epoch": 0.35,
|
|
"learning_rate": 0.0004985033499726976,
|
|
"loss": 1.7437,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"epoch": 0.35,
|
|
"learning_rate": 0.0004984765320655302,
|
|
"loss": 1.8827,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"epoch": 0.35,
|
|
"learning_rate": 0.0004984494767514594,
|
|
"loss": 1.7657,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"epoch": 0.36,
|
|
"learning_rate": 0.0004984221840563355,
|
|
"loss": 1.7692,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"epoch": 0.36,
|
|
"learning_rate": 0.000498394654006235,
|
|
"loss": 1.817,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"epoch": 0.36,
|
|
"learning_rate": 0.0004983668866274619,
|
|
"loss": 1.7605,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"epoch": 0.37,
|
|
"learning_rate": 0.0004983388819465461,
|
|
"loss": 1.7992,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"epoch": 0.37,
|
|
"learning_rate": 0.0004983106399902451,
|
|
"loss": 1.7475,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"epoch": 0.37,
|
|
"learning_rate": 0.0004982821607855424,
|
|
"loss": 1.8526,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"epoch": 0.38,
|
|
"learning_rate": 0.0004982534443596485,
|
|
"loss": 1.7827,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"epoch": 0.38,
|
|
"learning_rate": 0.0004982244907400005,
|
|
"loss": 1.8324,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"epoch": 0.38,
|
|
"learning_rate": 0.0004981952999542622,
|
|
"loss": 1.7241,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"epoch": 0.39,
|
|
"learning_rate": 0.0004981658720303239,
|
|
"loss": 1.7403,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"epoch": 0.39,
|
|
"learning_rate": 0.0004981362069963026,
|
|
"loss": 1.7528,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"epoch": 0.39,
|
|
"learning_rate": 0.0004981063048805416,
|
|
"loss": 1.8543,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"epoch": 0.4,
|
|
"learning_rate": 0.000498076165711611,
|
|
"loss": 1.8203,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"epoch": 0.4,
|
|
"learning_rate": 0.0004980457895183072,
|
|
"loss": 1.7149,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"epoch": 0.4,
|
|
"learning_rate": 0.0004980151763296531,
|
|
"loss": 1.7625,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"epoch": 0.4,
|
|
"learning_rate": 0.0004979843261748982,
|
|
"loss": 1.7602,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"epoch": 0.41,
|
|
"learning_rate": 0.0004979532390835182,
|
|
"loss": 1.6824,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"epoch": 0.41,
|
|
"learning_rate": 0.0004979219150852152,
|
|
"loss": 1.7935,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"epoch": 0.41,
|
|
"learning_rate": 0.0004978903542099179,
|
|
"loss": 1.8073,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"epoch": 0.42,
|
|
"learning_rate": 0.000497858556487781,
|
|
"loss": 1.7461,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"epoch": 0.42,
|
|
"learning_rate": 0.0004978265219491855,
|
|
"loss": 1.7436,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"epoch": 0.42,
|
|
"learning_rate": 0.0004977942506247391,
|
|
"loss": 1.7999,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"epoch": 0.43,
|
|
"learning_rate": 0.0004977617425452753,
|
|
"loss": 1.6704,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"epoch": 0.43,
|
|
"learning_rate": 0.0004977289977418539,
|
|
"loss": 1.8842,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"epoch": 0.43,
|
|
"learning_rate": 0.0004976960162457609,
|
|
"loss": 1.7712,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"epoch": 0.44,
|
|
"learning_rate": 0.0004976627980885085,
|
|
"loss": 1.8097,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"epoch": 0.44,
|
|
"learning_rate": 0.0004976293433018352,
|
|
"loss": 1.7959,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"epoch": 0.44,
|
|
"learning_rate": 0.000497595651917705,
|
|
"loss": 1.6939,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"epoch": 0.44,
|
|
"learning_rate": 0.0004975617239683087,
|
|
"loss": 1.8529,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"epoch": 0.45,
|
|
"learning_rate": 0.0004975275594860625,
|
|
"loss": 1.7525,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"epoch": 0.45,
|
|
"learning_rate": 0.0004974931585036089,
|
|
"loss": 1.772,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"epoch": 0.45,
|
|
"learning_rate": 0.0004974585210538164,
|
|
"loss": 1.7676,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"epoch": 0.46,
|
|
"learning_rate": 0.0004974236471697793,
|
|
"loss": 1.8495,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"epoch": 0.46,
|
|
"learning_rate": 0.0004973885368848179,
|
|
"loss": 1.8095,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"epoch": 0.46,
|
|
"learning_rate": 0.0004973531902324783,
|
|
"loss": 1.7605,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"epoch": 0.47,
|
|
"learning_rate": 0.0004973176072465324,
|
|
"loss": 1.7722,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"epoch": 0.47,
|
|
"learning_rate": 0.000497281787960978,
|
|
"loss": 1.7914,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"epoch": 0.47,
|
|
"learning_rate": 0.0004972457324100387,
|
|
"loss": 1.7663,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"epoch": 0.48,
|
|
"learning_rate": 0.0004972094406281636,
|
|
"loss": 1.896,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"epoch": 0.48,
|
|
"learning_rate": 0.000497172912650028,
|
|
"loss": 1.7859,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"epoch": 0.48,
|
|
"learning_rate": 0.0004971361485105321,
|
|
"loss": 1.6871,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"epoch": 0.49,
|
|
"learning_rate": 0.0004970991482448026,
|
|
"loss": 1.7452,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"epoch": 0.49,
|
|
"learning_rate": 0.0004970619118881913,
|
|
"loss": 1.8276,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"epoch": 0.49,
|
|
"learning_rate": 0.0004970244394762757,
|
|
"loss": 1.7048,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"epoch": 0.49,
|
|
"learning_rate": 0.0004969867310448586,
|
|
"loss": 1.8654,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"epoch": 0.5,
|
|
"learning_rate": 0.0004969487866299687,
|
|
"loss": 1.7607,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"epoch": 0.5,
|
|
"learning_rate": 0.00049691060626786,
|
|
"loss": 1.6932,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"epoch": 0.5,
|
|
"learning_rate": 0.0004968721899950119,
|
|
"loss": 1.7111,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"epoch": 0.51,
|
|
"learning_rate": 0.0004968335378481292,
|
|
"loss": 1.683,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"epoch": 0.51,
|
|
"learning_rate": 0.0004967946498641422,
|
|
"loss": 1.8777,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"epoch": 0.51,
|
|
"learning_rate": 0.0004967555260802063,
|
|
"loss": 1.7996,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"epoch": 0.52,
|
|
"learning_rate": 0.0004967161665337023,
|
|
"loss": 1.7404,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"epoch": 0.52,
|
|
"learning_rate": 0.0004966765712622363,
|
|
"loss": 1.7588,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"epoch": 0.52,
|
|
"learning_rate": 0.0004966367403036398,
|
|
"loss": 1.7674,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"epoch": 0.53,
|
|
"learning_rate": 0.0004965966736959691,
|
|
"loss": 1.7775,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"epoch": 0.53,
|
|
"learning_rate": 0.0004965563714775058,
|
|
"loss": 1.7435,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"epoch": 0.53,
|
|
"learning_rate": 0.0004965158336867567,
|
|
"loss": 1.745,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"epoch": 0.54,
|
|
"learning_rate": 0.0004964750603624537,
|
|
"loss": 1.9576,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"epoch": 0.54,
|
|
"learning_rate": 0.0004964340515435536,
|
|
"loss": 1.7161,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"epoch": 0.54,
|
|
"learning_rate": 0.0004963928072692383,
|
|
"loss": 1.8049,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"epoch": 0.54,
|
|
"learning_rate": 0.0004963513275789148,
|
|
"loss": 1.7207,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"epoch": 0.55,
|
|
"learning_rate": 0.0004963096125122146,
|
|
"loss": 1.9052,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"epoch": 0.55,
|
|
"learning_rate": 0.0004962676621089945,
|
|
"loss": 1.8715,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"epoch": 0.55,
|
|
"learning_rate": 0.0004962254764093359,
|
|
"loss": 1.6938,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"epoch": 0.56,
|
|
"learning_rate": 0.0004961830554535454,
|
|
"loss": 1.7725,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"epoch": 0.56,
|
|
"learning_rate": 0.0004961403992821537,
|
|
"loss": 1.7593,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"epoch": 0.56,
|
|
"learning_rate": 0.000496097507935917,
|
|
"loss": 1.7402,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"epoch": 0.57,
|
|
"learning_rate": 0.0004960543814558157,
|
|
"loss": 1.6593,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"epoch": 0.57,
|
|
"learning_rate": 0.0004960110198830549,
|
|
"loss": 1.8447,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"epoch": 0.57,
|
|
"learning_rate": 0.0004959674232590647,
|
|
"loss": 1.7384,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"epoch": 0.58,
|
|
"learning_rate": 0.0004959235916254991,
|
|
"loss": 1.7226,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"epoch": 0.58,
|
|
"learning_rate": 0.0004958795250242374,
|
|
"loss": 1.7927,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"epoch": 0.58,
|
|
"learning_rate": 0.0004958352234973827,
|
|
"loss": 1.7886,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"epoch": 0.58,
|
|
"learning_rate": 0.0004957906870872632,
|
|
"loss": 1.7869,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"epoch": 0.59,
|
|
"learning_rate": 0.0004957459158364311,
|
|
"loss": 1.8196,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"epoch": 0.59,
|
|
"learning_rate": 0.000495700909787663,
|
|
"loss": 1.7848,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"epoch": 0.59,
|
|
"learning_rate": 0.0004956556689839599,
|
|
"loss": 1.7898,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"epoch": 0.6,
|
|
"learning_rate": 0.0004956101934685475,
|
|
"loss": 1.715,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"epoch": 0.6,
|
|
"learning_rate": 0.0004955644832848749,
|
|
"loss": 1.7374,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"epoch": 0.6,
|
|
"learning_rate": 0.0004955185384766161,
|
|
"loss": 1.7309,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"epoch": 0.61,
|
|
"learning_rate": 0.0004954723590876692,
|
|
"loss": 1.797,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"epoch": 0.61,
|
|
"learning_rate": 0.000495425945162156,
|
|
"loss": 1.7374,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"epoch": 0.61,
|
|
"learning_rate": 0.000495379296744423,
|
|
"loss": 1.5507,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"epoch": 0.62,
|
|
"learning_rate": 0.0004953324138790401,
|
|
"loss": 1.6471,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"epoch": 0.62,
|
|
"learning_rate": 0.0004952852966108019,
|
|
"loss": 1.7719,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"epoch": 0.62,
|
|
"learning_rate": 0.0004952379449847263,
|
|
"loss": 1.7809,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"epoch": 0.63,
|
|
"learning_rate": 0.0004951903590460555,
|
|
"loss": 1.7963,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"epoch": 0.63,
|
|
"learning_rate": 0.0004951425388402557,
|
|
"loss": 1.8083,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"epoch": 0.63,
|
|
"learning_rate": 0.0004950944844130164,
|
|
"loss": 1.8411,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"epoch": 0.63,
|
|
"learning_rate": 0.0004950461958102513,
|
|
"loss": 1.7906,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"epoch": 0.64,
|
|
"learning_rate": 0.0004949976730780978,
|
|
"loss": 1.7833,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"epoch": 0.64,
|
|
"learning_rate": 0.0004949489162629168,
|
|
"loss": 1.6889,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"epoch": 0.64,
|
|
"learning_rate": 0.0004948999254112932,
|
|
"loss": 1.6898,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"epoch": 0.65,
|
|
"learning_rate": 0.0004948507005700354,
|
|
"loss": 1.6113,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"epoch": 0.65,
|
|
"learning_rate": 0.0004948012417861749,
|
|
"loss": 1.7093,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"epoch": 0.65,
|
|
"learning_rate": 0.0004947515491069673,
|
|
"loss": 1.7139,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"epoch": 0.66,
|
|
"learning_rate": 0.0004947016225798915,
|
|
"loss": 1.7321,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"epoch": 0.66,
|
|
"learning_rate": 0.0004946514622526498,
|
|
"loss": 1.7892,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"epoch": 0.66,
|
|
"learning_rate": 0.0004946010681731679,
|
|
"loss": 1.8455,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"epoch": 0.67,
|
|
"learning_rate": 0.0004945504403895947,
|
|
"loss": 1.6183,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"epoch": 0.67,
|
|
"learning_rate": 0.0004944995789503024,
|
|
"loss": 1.8222,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"epoch": 0.67,
|
|
"learning_rate": 0.000494448483903887,
|
|
"loss": 1.6057,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"epoch": 0.68,
|
|
"learning_rate": 0.0004943971552991669,
|
|
"loss": 1.7757,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"epoch": 0.68,
|
|
"learning_rate": 0.0004943455931851842,
|
|
"loss": 1.7974,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"epoch": 0.68,
|
|
"learning_rate": 0.0004942937976112039,
|
|
"loss": 1.7462,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"epoch": 0.68,
|
|
"learning_rate": 0.0004942417686267139,
|
|
"loss": 1.7764,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"epoch": 0.69,
|
|
"learning_rate": 0.0004941895062814254,
|
|
"loss": 1.7549,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"epoch": 0.69,
|
|
"learning_rate": 0.0004941370106252727,
|
|
"loss": 1.7775,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"epoch": 0.69,
|
|
"learning_rate": 0.0004940842817084123,
|
|
"loss": 1.6448,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"epoch": 0.7,
|
|
"learning_rate": 0.0004940313195812245,
|
|
"loss": 1.7438,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"epoch": 0.7,
|
|
"learning_rate": 0.0004939781242943117,
|
|
"loss": 1.7238,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"epoch": 0.7,
|
|
"learning_rate": 0.0004939246958984994,
|
|
"loss": 1.8459,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"epoch": 0.71,
|
|
"learning_rate": 0.0004938710344448358,
|
|
"loss": 1.8362,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"epoch": 0.71,
|
|
"learning_rate": 0.0004938171399845916,
|
|
"loss": 1.7539,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"epoch": 0.71,
|
|
"learning_rate": 0.0004937630125692604,
|
|
"loss": 1.7561,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"epoch": 0.72,
|
|
"learning_rate": 0.0004937086522505583,
|
|
"loss": 1.8264,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"epoch": 0.72,
|
|
"learning_rate": 0.0004936540590804236,
|
|
"loss": 1.6921,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"epoch": 0.72,
|
|
"learning_rate": 0.0004935992331110176,
|
|
"loss": 1.7795,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"epoch": 0.72,
|
|
"learning_rate": 0.0004935441743947238,
|
|
"loss": 1.843,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"epoch": 0.73,
|
|
"learning_rate": 0.0004934888829841478,
|
|
"loss": 1.821,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"epoch": 0.73,
|
|
"learning_rate": 0.0004934333589321179,
|
|
"loss": 1.7411,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"epoch": 0.73,
|
|
"learning_rate": 0.0004933776022916847,
|
|
"loss": 1.7388,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"epoch": 0.74,
|
|
"learning_rate": 0.0004933216131161206,
|
|
"loss": 1.7745,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"epoch": 0.74,
|
|
"learning_rate": 0.0004932653914589207,
|
|
"loss": 1.8524,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"epoch": 0.74,
|
|
"learning_rate": 0.0004932089373738018,
|
|
"loss": 1.8125,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"epoch": 0.75,
|
|
"learning_rate": 0.0004931522509147031,
|
|
"loss": 1.723,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"epoch": 0.75,
|
|
"learning_rate": 0.0004930953321357857,
|
|
"loss": 1.7824,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"epoch": 0.75,
|
|
"learning_rate": 0.0004930381810914325,
|
|
"loss": 1.7507,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"epoch": 0.76,
|
|
"learning_rate": 0.0004929807978362486,
|
|
"loss": 1.7169,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"epoch": 0.76,
|
|
"learning_rate": 0.0004929231824250608,
|
|
"loss": 1.8229,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"epoch": 0.76,
|
|
"learning_rate": 0.0004928653349129176,
|
|
"loss": 1.8047,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"epoch": 0.77,
|
|
"learning_rate": 0.0004928072553550896,
|
|
"loss": 1.6996,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"epoch": 0.77,
|
|
"learning_rate": 0.0004927489438070688,
|
|
"loss": 1.8785,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"epoch": 0.77,
|
|
"learning_rate": 0.000492690400324569,
|
|
"loss": 1.6591,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"epoch": 0.77,
|
|
"learning_rate": 0.0004926316249635256,
|
|
"loss": 1.7437,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"epoch": 0.78,
|
|
"learning_rate": 0.0004925726177800955,
|
|
"loss": 1.7278,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"epoch": 0.78,
|
|
"learning_rate": 0.000492513378830657,
|
|
"loss": 1.8142,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"epoch": 0.78,
|
|
"learning_rate": 0.0004924539081718101,
|
|
"loss": 1.7805,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"epoch": 0.79,
|
|
"learning_rate": 0.0004923942058603761,
|
|
"loss": 1.7567,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"epoch": 0.79,
|
|
"learning_rate": 0.0004923342719533974,
|
|
"loss": 1.6914,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"epoch": 0.79,
|
|
"learning_rate": 0.0004922741065081379,
|
|
"loss": 1.7712,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"epoch": 0.8,
|
|
"learning_rate": 0.0004922137095820828,
|
|
"loss": 1.7937,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"epoch": 0.8,
|
|
"learning_rate": 0.0004921530812329382,
|
|
"loss": 1.8526,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"epoch": 0.8,
|
|
"learning_rate": 0.0004920922215186315,
|
|
"loss": 1.7118,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"epoch": 0.81,
|
|
"learning_rate": 0.0004920311304973111,
|
|
"loss": 1.7153,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"epoch": 0.81,
|
|
"learning_rate": 0.0004919698082273465,
|
|
"loss": 1.841,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"epoch": 0.81,
|
|
"learning_rate": 0.0004919082547673279,
|
|
"loss": 1.6134,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"epoch": 0.82,
|
|
"learning_rate": 0.0004918464701760667,
|
|
"loss": 1.7504,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"epoch": 0.82,
|
|
"learning_rate": 0.0004917844545125949,
|
|
"loss": 1.8351,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"epoch": 0.82,
|
|
"learning_rate": 0.0004917222078361655,
|
|
"loss": 1.7207,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"epoch": 0.82,
|
|
"learning_rate": 0.0004916597302062519,
|
|
"loss": 1.7553,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"epoch": 0.83,
|
|
"learning_rate": 0.0004915970216825484,
|
|
"loss": 1.8727,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"epoch": 0.83,
|
|
"learning_rate": 0.00049153408232497,
|
|
"loss": 1.698,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"epoch": 0.83,
|
|
"learning_rate": 0.0004914709121936519,
|
|
"loss": 1.8109,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"epoch": 0.84,
|
|
"learning_rate": 0.0004914075113489502,
|
|
"loss": 1.6561,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"epoch": 0.84,
|
|
"learning_rate": 0.0004913438798514412,
|
|
"loss": 1.7359,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"epoch": 0.84,
|
|
"learning_rate": 0.0004912800177619215,
|
|
"loss": 1.6776,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"epoch": 0.85,
|
|
"learning_rate": 0.0004912159251414081,
|
|
"loss": 1.6972,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"epoch": 0.85,
|
|
"learning_rate": 0.0004911516020511385,
|
|
"loss": 1.6831,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"epoch": 0.85,
|
|
"learning_rate": 0.00049108704855257,
|
|
"loss": 1.67,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"epoch": 0.86,
|
|
"learning_rate": 0.0004910222647073805,
|
|
"loss": 1.8636,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"epoch": 0.86,
|
|
"learning_rate": 0.0004909572505774674,
|
|
"loss": 1.7179,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"epoch": 0.86,
|
|
"learning_rate": 0.0004908920062249487,
|
|
"loss": 1.6818,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"epoch": 0.86,
|
|
"learning_rate": 0.0004908265317121619,
|
|
"loss": 1.7208,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"epoch": 0.87,
|
|
"learning_rate": 0.000490760827101665,
|
|
"loss": 1.7092,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"epoch": 0.87,
|
|
"learning_rate": 0.000490694892456235,
|
|
"loss": 1.7457,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"epoch": 0.87,
|
|
"learning_rate": 0.0004906287278388694,
|
|
"loss": 1.7435,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"epoch": 0.88,
|
|
"learning_rate": 0.0004905623333127851,
|
|
"loss": 1.7862,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"epoch": 0.88,
|
|
"learning_rate": 0.0004904957089414189,
|
|
"loss": 1.7221,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"epoch": 0.88,
|
|
"learning_rate": 0.0004904288547884269,
|
|
"loss": 1.848,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"epoch": 0.89,
|
|
"learning_rate": 0.000490361770917685,
|
|
"loss": 1.8413,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"epoch": 0.89,
|
|
"learning_rate": 0.0004902944573932885,
|
|
"loss": 1.8343,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"epoch": 0.89,
|
|
"learning_rate": 0.000490226914279552,
|
|
"loss": 1.7847,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"epoch": 0.9,
|
|
"learning_rate": 0.0004901591416410096,
|
|
"loss": 1.9414,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"epoch": 0.9,
|
|
"learning_rate": 0.0004900911395424147,
|
|
"loss": 1.6951,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"epoch": 0.9,
|
|
"learning_rate": 0.0004900229080487399,
|
|
"loss": 1.7335,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"epoch": 0.91,
|
|
"learning_rate": 0.000489954447225177,
|
|
"loss": 1.7744,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"epoch": 0.91,
|
|
"learning_rate": 0.0004898857571371369,
|
|
"loss": 1.6958,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"epoch": 0.91,
|
|
"learning_rate": 0.0004898168378502494,
|
|
"loss": 1.8404,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"epoch": 0.91,
|
|
"learning_rate": 0.0004897476894303636,
|
|
"loss": 1.7764,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"epoch": 0.92,
|
|
"learning_rate": 0.0004896783119435474,
|
|
"loss": 1.8399,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"epoch": 0.92,
|
|
"learning_rate": 0.0004896087054560873,
|
|
"loss": 1.8349,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"epoch": 0.92,
|
|
"learning_rate": 0.000489538870034489,
|
|
"loss": 1.8575,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"epoch": 0.93,
|
|
"learning_rate": 0.0004894688057454767,
|
|
"loss": 1.8285,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"epoch": 0.93,
|
|
"learning_rate": 0.0004893985126559932,
|
|
"loss": 1.8416,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"epoch": 0.93,
|
|
"learning_rate": 0.0004893279908332003,
|
|
"loss": 1.7404,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.94,
|
|
"learning_rate": 0.0004892572403444779,
|
|
"loss": 1.853,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"epoch": 0.94,
|
|
"learning_rate": 0.0004891862612574246,
|
|
"loss": 1.6964,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"epoch": 0.94,
|
|
"learning_rate": 0.0004891150536398573,
|
|
"loss": 1.8078,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"epoch": 0.95,
|
|
"learning_rate": 0.0004890436175598114,
|
|
"loss": 1.7731,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"epoch": 0.95,
|
|
"learning_rate": 0.0004889719530855405,
|
|
"loss": 1.8544,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"epoch": 0.95,
|
|
"learning_rate": 0.0004889000602855164,
|
|
"loss": 1.8461,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"epoch": 0.96,
|
|
"learning_rate": 0.0004888279392284291,
|
|
"loss": 1.7281,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"epoch": 0.96,
|
|
"learning_rate": 0.0004887555899831866,
|
|
"loss": 1.8667,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"epoch": 0.96,
|
|
"learning_rate": 0.000488683012618915,
|
|
"loss": 1.8328,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"epoch": 0.96,
|
|
"learning_rate": 0.0004886102072049584,
|
|
"loss": 1.7382,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"epoch": 0.97,
|
|
"learning_rate": 0.0004885371738108787,
|
|
"loss": 1.7657,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"epoch": 0.97,
|
|
"learning_rate": 0.0004884639125064557,
|
|
"loss": 1.6249,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"epoch": 0.97,
|
|
"learning_rate": 0.0004883904233616869,
|
|
"loss": 1.821,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"epoch": 0.98,
|
|
"learning_rate": 0.0004883167064467873,
|
|
"loss": 1.7046,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"epoch": 0.98,
|
|
"learning_rate": 0.00048824276183218995,
|
|
"loss": 1.6906,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"epoch": 0.98,
|
|
"learning_rate": 0.0004881685895885453,
|
|
"loss": 1.726,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"epoch": 0.99,
|
|
"learning_rate": 0.000488094189786721,
|
|
"loss": 1.7502,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"epoch": 0.99,
|
|
"learning_rate": 0.0004880195624978024,
|
|
"loss": 1.8787,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"epoch": 0.99,
|
|
"learning_rate": 0.0004879522034952373,
|
|
"loss": 1.7859,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"epoch": 1.0,
|
|
"learning_rate": 0.0004878771441774581,
|
|
"loss": 1.8009,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"epoch": 1.0,
|
|
"learning_rate": 0.0004878018575799609,
|
|
"loss": 1.7169,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"epoch": 1.0,
|
|
"learning_rate": 0.00048772634377467817,
|
|
"loss": 1.6816,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"epoch": 1.0,
|
|
"learning_rate": 0.0004876506028337596,
|
|
"loss": 1.662,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"epoch": 1.01,
|
|
"learning_rate": 0.00048757463482957205,
|
|
"loss": 1.722,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"epoch": 1.01,
|
|
"learning_rate": 0.000487498439834699,
|
|
"loss": 1.6469,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"epoch": 1.01,
|
|
"learning_rate": 0.00048742201792194095,
|
|
"loss": 1.5895,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"epoch": 1.02,
|
|
"learning_rate": 0.00048734536916431525,
|
|
"loss": 1.5485,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"epoch": 1.02,
|
|
"learning_rate": 0.00048726849363505597,
|
|
"loss": 1.7487,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"epoch": 1.02,
|
|
"learning_rate": 0.0004871913914076139,
|
|
"loss": 1.7245,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"epoch": 1.03,
|
|
"learning_rate": 0.0004871140625556562,
|
|
"loss": 1.728,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"epoch": 1.03,
|
|
"learning_rate": 0.0004870365071530669,
|
|
"loss": 1.594,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"epoch": 1.03,
|
|
"learning_rate": 0.00048695872527394616,
|
|
"loss": 1.6866,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"epoch": 1.04,
|
|
"learning_rate": 0.0004868807169926107,
|
|
"loss": 1.6982,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"epoch": 1.04,
|
|
"learning_rate": 0.00048680248238359357,
|
|
"loss": 1.5755,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"epoch": 1.04,
|
|
"learning_rate": 0.00048672402152164407,
|
|
"loss": 1.674,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"epoch": 1.05,
|
|
"learning_rate": 0.0004866453344817276,
|
|
"loss": 1.6813,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"epoch": 1.05,
|
|
"learning_rate": 0.00048656642133902564,
|
|
"loss": 1.804,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"epoch": 1.05,
|
|
"learning_rate": 0.0004864872821689358,
|
|
"loss": 1.5491,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"epoch": 1.05,
|
|
"learning_rate": 0.0004864079170470716,
|
|
"loss": 1.6667,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"epoch": 1.06,
|
|
"learning_rate": 0.00048632832604926247,
|
|
"loss": 1.7157,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"epoch": 1.06,
|
|
"learning_rate": 0.0004862485092515535,
|
|
"loss": 1.6451,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"epoch": 1.06,
|
|
"learning_rate": 0.00048616846673020585,
|
|
"loss": 1.7579,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"epoch": 1.07,
|
|
"learning_rate": 0.00048608819856169603,
|
|
"loss": 1.6515,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"epoch": 1.07,
|
|
"learning_rate": 0.0004860077048227163,
|
|
"loss": 1.6975,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"epoch": 1.07,
|
|
"learning_rate": 0.0004859269855901742,
|
|
"loss": 1.5199,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"epoch": 1.08,
|
|
"learning_rate": 0.0004858460409411933,
|
|
"loss": 1.599,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"epoch": 1.08,
|
|
"learning_rate": 0.0004857648709531119,
|
|
"loss": 1.5367,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"epoch": 1.08,
|
|
"learning_rate": 0.0004856834757034839,
|
|
"loss": 1.5769,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"epoch": 1.09,
|
|
"learning_rate": 0.0004856018552700785,
|
|
"loss": 1.7115,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"epoch": 1.09,
|
|
"learning_rate": 0.0004855200097308798,
|
|
"loss": 1.6964,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"epoch": 1.09,
|
|
"learning_rate": 0.0004854379391640872,
|
|
"loss": 1.7728,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"epoch": 1.1,
|
|
"learning_rate": 0.00048535564364811503,
|
|
"loss": 1.5691,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"epoch": 1.1,
|
|
"learning_rate": 0.00048527312326159243,
|
|
"loss": 1.7827,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"epoch": 1.1,
|
|
"learning_rate": 0.00048519037808336364,
|
|
"loss": 1.5546,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"epoch": 1.1,
|
|
"learning_rate": 0.00048510740819248754,
|
|
"loss": 1.6412,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"epoch": 1.11,
|
|
"learning_rate": 0.0004850242136682377,
|
|
"loss": 1.6076,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"epoch": 1.11,
|
|
"learning_rate": 0.0004849407945901022,
|
|
"loss": 1.6697,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"epoch": 1.11,
|
|
"learning_rate": 0.00048485715103778395,
|
|
"loss": 1.7326,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"epoch": 1.12,
|
|
"learning_rate": 0.00048477328309120003,
|
|
"loss": 1.7047,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"epoch": 1.12,
|
|
"learning_rate": 0.00048468919083048223,
|
|
"loss": 1.6541,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"epoch": 1.12,
|
|
"learning_rate": 0.0004846048743359765,
|
|
"loss": 1.6462,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"epoch": 1.13,
|
|
"learning_rate": 0.0004845203336882429,
|
|
"loss": 1.7368,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"epoch": 1.13,
|
|
"learning_rate": 0.00048443556896805585,
|
|
"loss": 1.6291,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"epoch": 1.13,
|
|
"learning_rate": 0.0004843505802564039,
|
|
"loss": 1.6471,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"epoch": 1.14,
|
|
"learning_rate": 0.00048426536763448937,
|
|
"loss": 1.7409,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"epoch": 1.14,
|
|
"learning_rate": 0.0004841799311837287,
|
|
"loss": 1.626,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"epoch": 1.14,
|
|
"learning_rate": 0.0004840942709857522,
|
|
"loss": 1.7094,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"epoch": 1.14,
|
|
"learning_rate": 0.0004840083871224039,
|
|
"loss": 1.7576,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"epoch": 1.15,
|
|
"learning_rate": 0.0004839222796757414,
|
|
"loss": 1.7822,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"epoch": 1.15,
|
|
"learning_rate": 0.00048383594872803624,
|
|
"loss": 1.6281,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"epoch": 1.15,
|
|
"learning_rate": 0.00048374939436177333,
|
|
"loss": 1.7843,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"epoch": 1.16,
|
|
"learning_rate": 0.0004836626166596509,
|
|
"loss": 1.6953,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"epoch": 1.16,
|
|
"learning_rate": 0.0004835756157045808,
|
|
"loss": 1.6714,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"epoch": 1.16,
|
|
"learning_rate": 0.000483488391579688,
|
|
"loss": 1.6725,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"epoch": 1.17,
|
|
"learning_rate": 0.00048340094436831086,
|
|
"loss": 1.7812,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"epoch": 1.17,
|
|
"learning_rate": 0.00048331327415400085,
|
|
"loss": 1.8414,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"epoch": 1.17,
|
|
"learning_rate": 0.00048322538102052237,
|
|
"loss": 1.7411,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"epoch": 1.18,
|
|
"learning_rate": 0.00048313726505185304,
|
|
"loss": 1.5748,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"epoch": 1.18,
|
|
"learning_rate": 0.00048304892633218324,
|
|
"loss": 1.6168,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"epoch": 1.18,
|
|
"learning_rate": 0.0004829603649459161,
|
|
"loss": 1.7324,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"epoch": 1.19,
|
|
"learning_rate": 0.0004828715809776677,
|
|
"loss": 1.6923,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"epoch": 1.19,
|
|
"learning_rate": 0.00048278257451226666,
|
|
"loss": 1.7092,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"epoch": 1.19,
|
|
"learning_rate": 0.0004826933456347542,
|
|
"loss": 1.6977,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"epoch": 1.19,
|
|
"learning_rate": 0.000482603894430384,
|
|
"loss": 1.5819,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"epoch": 1.2,
|
|
"learning_rate": 0.0004825142209846223,
|
|
"loss": 1.7308,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"epoch": 1.2,
|
|
"learning_rate": 0.00048242432538314747,
|
|
"loss": 1.6482,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"epoch": 1.2,
|
|
"learning_rate": 0.0004823342077118504,
|
|
"loss": 1.7691,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"epoch": 1.21,
|
|
"learning_rate": 0.00048224386805683397,
|
|
"loss": 1.4949,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"epoch": 1.21,
|
|
"learning_rate": 0.00048215330650441313,
|
|
"loss": 1.814,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"epoch": 1.21,
|
|
"learning_rate": 0.00048206252314111507,
|
|
"loss": 1.6767,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"epoch": 1.22,
|
|
"learning_rate": 0.0004819715180536786,
|
|
"loss": 1.608,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"epoch": 1.22,
|
|
"learning_rate": 0.00048188029132905464,
|
|
"loss": 1.8057,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"epoch": 1.22,
|
|
"learning_rate": 0.0004817888430544057,
|
|
"loss": 1.6973,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"epoch": 1.23,
|
|
"learning_rate": 0.00048169717331710606,
|
|
"loss": 1.6768,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"epoch": 1.23,
|
|
"learning_rate": 0.0004816052822047416,
|
|
"loss": 1.7192,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"epoch": 1.23,
|
|
"learning_rate": 0.0004815131698051096,
|
|
"loss": 1.5955,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"epoch": 1.24,
|
|
"learning_rate": 0.00048142083620621894,
|
|
"loss": 1.5962,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"epoch": 1.24,
|
|
"learning_rate": 0.0004813282814962897,
|
|
"loss": 1.6773,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"epoch": 1.24,
|
|
"learning_rate": 0.0004812355057637533,
|
|
"loss": 1.7788,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"epoch": 1.24,
|
|
"learning_rate": 0.0004811425090972523,
|
|
"loss": 1.6533,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"epoch": 1.25,
|
|
"learning_rate": 0.0004810492915856405,
|
|
"loss": 1.6844,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"epoch": 1.25,
|
|
"learning_rate": 0.0004809558533179823,
|
|
"loss": 1.529,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"epoch": 1.25,
|
|
"learning_rate": 0.0004808621943835535,
|
|
"loss": 1.697,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"epoch": 1.26,
|
|
"learning_rate": 0.0004807683148718405,
|
|
"loss": 1.7395,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"epoch": 1.26,
|
|
"learning_rate": 0.0004806742148725404,
|
|
"loss": 1.7294,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"epoch": 1.26,
|
|
"learning_rate": 0.0004805798944755611,
|
|
"loss": 1.6479,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"epoch": 1.27,
|
|
"learning_rate": 0.000480485353771021,
|
|
"loss": 1.7278,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"epoch": 1.27,
|
|
"learning_rate": 0.000480390592849249,
|
|
"loss": 1.8192,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"epoch": 1.27,
|
|
"learning_rate": 0.00048029561180078456,
|
|
"loss": 1.8135,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"epoch": 1.28,
|
|
"learning_rate": 0.0004802004107163772,
|
|
"loss": 1.7353,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"epoch": 1.28,
|
|
"learning_rate": 0.0004801049896869868,
|
|
"loss": 1.6835,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"epoch": 1.28,
|
|
"learning_rate": 0.0004800093488037834,
|
|
"loss": 1.6945,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"epoch": 1.28,
|
|
"learning_rate": 0.00047991348815814704,
|
|
"loss": 1.7125,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"epoch": 1.29,
|
|
"learning_rate": 0.0004798174078416679,
|
|
"loss": 1.7158,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"epoch": 1.29,
|
|
"learning_rate": 0.00047972110794614574,
|
|
"loss": 1.6723,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"epoch": 1.29,
|
|
"learning_rate": 0.0004796245885635905,
|
|
"loss": 1.6683,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"epoch": 1.3,
|
|
"learning_rate": 0.0004795278497862214,
|
|
"loss": 1.7655,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"epoch": 1.3,
|
|
"learning_rate": 0.0004794308917064677,
|
|
"loss": 1.6771,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"epoch": 1.3,
|
|
"learning_rate": 0.00047933371441696794,
|
|
"loss": 1.6508,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"epoch": 1.31,
|
|
"learning_rate": 0.0004792363180105701,
|
|
"loss": 1.6148,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"epoch": 1.31,
|
|
"learning_rate": 0.00047913870258033163,
|
|
"loss": 1.6412,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"epoch": 1.31,
|
|
"learning_rate": 0.00047904086821951914,
|
|
"loss": 1.6032,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"epoch": 1.32,
|
|
"learning_rate": 0.0004789428150216085,
|
|
"loss": 1.7847,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"epoch": 1.32,
|
|
"learning_rate": 0.0004788445430802847,
|
|
"loss": 1.6475,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"epoch": 1.32,
|
|
"learning_rate": 0.0004787460524894416,
|
|
"loss": 1.5868,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"epoch": 1.33,
|
|
"learning_rate": 0.0004786473433431821,
|
|
"loss": 1.6899,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"epoch": 1.33,
|
|
"learning_rate": 0.00047854841573581776,
|
|
"loss": 1.7372,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"epoch": 1.33,
|
|
"learning_rate": 0.00047844926976186897,
|
|
"loss": 1.73,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"epoch": 1.33,
|
|
"learning_rate": 0.00047834990551606484,
|
|
"loss": 1.6486,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"epoch": 1.34,
|
|
"learning_rate": 0.0004782503230933428,
|
|
"loss": 1.6755,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"epoch": 1.34,
|
|
"learning_rate": 0.00047815052258884903,
|
|
"loss": 1.6398,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"epoch": 1.34,
|
|
"learning_rate": 0.0004780505040979378,
|
|
"loss": 1.7197,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"epoch": 1.35,
|
|
"learning_rate": 0.000477950267716172,
|
|
"loss": 1.7484,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"epoch": 1.35,
|
|
"learning_rate": 0.0004778498135393221,
|
|
"loss": 1.7032,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"epoch": 1.35,
|
|
"learning_rate": 0.00047774914166336737,
|
|
"loss": 1.7668,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"epoch": 1.36,
|
|
"learning_rate": 0.00047764825218449465,
|
|
"loss": 1.688,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"epoch": 1.36,
|
|
"learning_rate": 0.00047754714519909877,
|
|
"loss": 1.7045,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"epoch": 1.36,
|
|
"learning_rate": 0.0004774458208037824,
|
|
"loss": 1.6507,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"epoch": 1.37,
|
|
"learning_rate": 0.0004773442790953559,
|
|
"loss": 1.6594,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"epoch": 1.37,
|
|
"learning_rate": 0.0004772425201708374,
|
|
"loss": 1.6701,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"epoch": 1.37,
|
|
"learning_rate": 0.0004771405441274524,
|
|
"loss": 1.7184,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"epoch": 1.38,
|
|
"learning_rate": 0.00047703835106263393,
|
|
"loss": 1.6241,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"epoch": 1.38,
|
|
"learning_rate": 0.00047693594107402226,
|
|
"loss": 1.7164,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"epoch": 1.38,
|
|
"learning_rate": 0.0004768333142594652,
|
|
"loss": 1.6521,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"epoch": 1.38,
|
|
"learning_rate": 0.0004767304707170174,
|
|
"loss": 1.6171,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"epoch": 1.39,
|
|
"learning_rate": 0.00047662741054494074,
|
|
"loss": 1.7042,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"epoch": 1.39,
|
|
"learning_rate": 0.00047652413384170414,
|
|
"loss": 1.7369,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"epoch": 1.39,
|
|
"learning_rate": 0.00047642064070598325,
|
|
"loss": 1.6475,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"epoch": 1.4,
|
|
"learning_rate": 0.00047631693123666055,
|
|
"loss": 1.7269,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"epoch": 1.4,
|
|
"learning_rate": 0.0004762130055328253,
|
|
"loss": 1.7212,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"epoch": 1.4,
|
|
"learning_rate": 0.0004761088636937734,
|
|
"loss": 1.6988,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"epoch": 1.41,
|
|
"learning_rate": 0.00047600450581900705,
|
|
"loss": 1.6999,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"epoch": 1.41,
|
|
"learning_rate": 0.000475899932008235,
|
|
"loss": 1.6231,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"epoch": 1.41,
|
|
"learning_rate": 0.00047579514236137236,
|
|
"loss": 1.6015,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"epoch": 1.42,
|
|
"learning_rate": 0.00047569013697854035,
|
|
"loss": 1.6755,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"epoch": 1.42,
|
|
"learning_rate": 0.00047558491596006635,
|
|
"loss": 1.7566,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"epoch": 1.42,
|
|
"learning_rate": 0.00047547947940648386,
|
|
"loss": 1.7487,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"epoch": 1.42,
|
|
"learning_rate": 0.00047537382741853214,
|
|
"loss": 1.7032,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"epoch": 1.43,
|
|
"learning_rate": 0.0004752679600971564,
|
|
"loss": 1.7805,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"epoch": 1.43,
|
|
"learning_rate": 0.00047516187754350763,
|
|
"loss": 1.7262,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"epoch": 1.43,
|
|
"learning_rate": 0.0004750555798589424,
|
|
"loss": 1.6603,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"epoch": 1.44,
|
|
"learning_rate": 0.00047494906714502273,
|
|
"loss": 1.7629,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"epoch": 1.44,
|
|
"learning_rate": 0.0004748423395035163,
|
|
"loss": 1.7138,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"epoch": 1.44,
|
|
"learning_rate": 0.000474735397036396,
|
|
"loss": 1.6067,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"epoch": 1.45,
|
|
"learning_rate": 0.00047462823984584,
|
|
"loss": 1.7414,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"epoch": 1.45,
|
|
"learning_rate": 0.00047452086803423166,
|
|
"loss": 1.7043,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"epoch": 1.45,
|
|
"learning_rate": 0.00047441328170415943,
|
|
"loss": 1.6337,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"epoch": 1.46,
|
|
"learning_rate": 0.00047430548095841655,
|
|
"loss": 1.7149,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"epoch": 1.46,
|
|
"learning_rate": 0.0004741974659000013,
|
|
"loss": 1.7524,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"epoch": 1.46,
|
|
"learning_rate": 0.00047408923663211665,
|
|
"loss": 1.7544,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"epoch": 1.47,
|
|
"learning_rate": 0.00047398079325817034,
|
|
"loss": 1.5905,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"epoch": 1.47,
|
|
"learning_rate": 0.0004738721358817745,
|
|
"loss": 1.7763,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"epoch": 1.47,
|
|
"learning_rate": 0.0004737632646067458,
|
|
"loss": 1.775,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"epoch": 1.47,
|
|
"learning_rate": 0.00047365417953710535,
|
|
"loss": 1.7381,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"epoch": 1.48,
|
|
"learning_rate": 0.00047354488077707845,
|
|
"loss": 1.8005,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"epoch": 1.48,
|
|
"learning_rate": 0.0004734353684310947,
|
|
"loss": 1.7326,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"epoch": 1.48,
|
|
"learning_rate": 0.0004733256426037876,
|
|
"loss": 1.6653,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"epoch": 1.49,
|
|
"learning_rate": 0.00047321570339999464,
|
|
"loss": 1.7037,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"epoch": 1.49,
|
|
"learning_rate": 0.0004731055509247573,
|
|
"loss": 1.7905,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"epoch": 1.49,
|
|
"learning_rate": 0.00047299518528332073,
|
|
"loss": 1.7195,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"epoch": 1.5,
|
|
"learning_rate": 0.00047288460658113387,
|
|
"loss": 1.7198,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"epoch": 1.5,
|
|
"learning_rate": 0.00047277381492384895,
|
|
"loss": 1.7505,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"epoch": 1.5,
|
|
"learning_rate": 0.00047266281041732206,
|
|
"loss": 1.7069,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"epoch": 1.51,
|
|
"learning_rate": 0.00047255159316761234,
|
|
"loss": 1.6332,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"epoch": 1.51,
|
|
"learning_rate": 0.0004724401632809824,
|
|
"loss": 1.6012,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"epoch": 1.51,
|
|
"learning_rate": 0.0004723285208638978,
|
|
"loss": 1.637,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"epoch": 1.52,
|
|
"learning_rate": 0.0004722166660230274,
|
|
"loss": 1.5241,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"epoch": 1.52,
|
|
"learning_rate": 0.0004721045988652428,
|
|
"loss": 1.6515,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"epoch": 1.52,
|
|
"learning_rate": 0.00047199231949761865,
|
|
"loss": 1.7355,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"epoch": 1.52,
|
|
"learning_rate": 0.00047187982802743235,
|
|
"loss": 1.7457,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"epoch": 1.53,
|
|
"learning_rate": 0.0004717671245621637,
|
|
"loss": 1.6393,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"epoch": 1.53,
|
|
"learning_rate": 0.00047165420920949533,
|
|
"loss": 1.65,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"epoch": 1.53,
|
|
"learning_rate": 0.00047154108207731214,
|
|
"loss": 1.7968,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"epoch": 1.54,
|
|
"learning_rate": 0.0004714277432737016,
|
|
"loss": 1.6527,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"epoch": 1.54,
|
|
"learning_rate": 0.0004713141929069531,
|
|
"loss": 1.7354,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"epoch": 1.54,
|
|
"learning_rate": 0.00047120043108555843,
|
|
"loss": 1.6562,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"epoch": 1.55,
|
|
"learning_rate": 0.0004710864579182113,
|
|
"loss": 1.7082,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"epoch": 1.55,
|
|
"learning_rate": 0.00047097227351380736,
|
|
"loss": 1.5542,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"epoch": 1.55,
|
|
"learning_rate": 0.0004708578779814441,
|
|
"loss": 1.631,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"epoch": 1.56,
|
|
"learning_rate": 0.0004707432714304207,
|
|
"loss": 1.7107,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"epoch": 1.56,
|
|
"learning_rate": 0.00047062845397023815,
|
|
"loss": 1.6823,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"epoch": 1.56,
|
|
"learning_rate": 0.00047051342571059865,
|
|
"loss": 1.7285,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"epoch": 1.56,
|
|
"learning_rate": 0.0004703981867614059,
|
|
"loss": 1.6042,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"epoch": 1.57,
|
|
"learning_rate": 0.00047028273723276505,
|
|
"loss": 1.7157,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"epoch": 1.57,
|
|
"learning_rate": 0.00047016707723498237,
|
|
"loss": 1.7771,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"epoch": 1.57,
|
|
"learning_rate": 0.0004700512068785652,
|
|
"loss": 1.6668,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"epoch": 1.58,
|
|
"learning_rate": 0.00046993512627422176,
|
|
"loss": 1.8279,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"epoch": 1.58,
|
|
"learning_rate": 0.00046981883553286137,
|
|
"loss": 1.766,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"epoch": 1.58,
|
|
"learning_rate": 0.0004697139942903158,
|
|
"loss": 1.7318,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"epoch": 1.59,
|
|
"learning_rate": 0.00046959730459489703,
|
|
"loss": 1.7036,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"epoch": 1.59,
|
|
"learning_rate": 0.00046948040508523303,
|
|
"loss": 1.736,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"epoch": 1.59,
|
|
"learning_rate": 0.0004693632958730154,
|
|
"loss": 1.7279,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"epoch": 1.6,
|
|
"learning_rate": 0.00046924597707013614,
|
|
"loss": 1.7604,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"epoch": 1.6,
|
|
"learning_rate": 0.00046912844878868755,
|
|
"loss": 1.6979,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"epoch": 1.6,
|
|
"learning_rate": 0.000469010711140962,
|
|
"loss": 1.7373,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"epoch": 1.61,
|
|
"learning_rate": 0.00046889276423945194,
|
|
"loss": 1.6556,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"epoch": 1.61,
|
|
"learning_rate": 0.00046877460819684963,
|
|
"loss": 1.6789,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"epoch": 1.61,
|
|
"learning_rate": 0.00046865624312604736,
|
|
"loss": 1.6415,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"epoch": 1.61,
|
|
"learning_rate": 0.00046853766914013706,
|
|
"loss": 1.7425,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"epoch": 1.62,
|
|
"learning_rate": 0.0004684188863524102,
|
|
"loss": 1.7224,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"epoch": 1.62,
|
|
"learning_rate": 0.00046829989487635784,
|
|
"loss": 1.7424,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"epoch": 1.62,
|
|
"learning_rate": 0.00046818069482567026,
|
|
"loss": 1.6587,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"epoch": 1.63,
|
|
"learning_rate": 0.00046806128631423727,
|
|
"loss": 1.7268,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"epoch": 1.63,
|
|
"learning_rate": 0.00046794166945614773,
|
|
"loss": 1.6707,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"epoch": 1.63,
|
|
"learning_rate": 0.00046782184436568956,
|
|
"loss": 1.6348,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"epoch": 1.64,
|
|
"learning_rate": 0.00046770181115734957,
|
|
"loss": 1.7617,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"epoch": 1.64,
|
|
"learning_rate": 0.0004675815699458136,
|
|
"loss": 1.6061,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"epoch": 1.64,
|
|
"learning_rate": 0.0004674611208459659,
|
|
"loss": 1.6989,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"epoch": 1.65,
|
|
"learning_rate": 0.00046734046397288985,
|
|
"loss": 1.6074,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"epoch": 1.65,
|
|
"learning_rate": 0.0004672195994418669,
|
|
"loss": 1.7078,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"epoch": 1.65,
|
|
"learning_rate": 0.0004670985273683771,
|
|
"loss": 1.7243,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"epoch": 1.66,
|
|
"learning_rate": 0.0004669772478680988,
|
|
"loss": 1.7188,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"epoch": 1.66,
|
|
"learning_rate": 0.0004668557610569084,
|
|
"loss": 1.6849,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"epoch": 1.66,
|
|
"learning_rate": 0.0004667340670508805,
|
|
"loss": 1.7025,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"epoch": 1.66,
|
|
"learning_rate": 0.00046661216596628773,
|
|
"loss": 1.6569,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"epoch": 1.67,
|
|
"learning_rate": 0.00046649005791960045,
|
|
"loss": 1.6911,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"epoch": 1.67,
|
|
"learning_rate": 0.0004663677430274866,
|
|
"loss": 1.5672,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"epoch": 1.67,
|
|
"learning_rate": 0.00046624522140681227,
|
|
"loss": 1.7377,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"epoch": 1.68,
|
|
"learning_rate": 0.0004661224931746405,
|
|
"loss": 1.7147,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"epoch": 1.68,
|
|
"learning_rate": 0.00046599955844823214,
|
|
"loss": 1.6878,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"epoch": 1.68,
|
|
"learning_rate": 0.000465876417345045,
|
|
"loss": 1.6734,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"epoch": 1.69,
|
|
"learning_rate": 0.0004657530699827344,
|
|
"loss": 1.6805,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"epoch": 1.69,
|
|
"learning_rate": 0.00046562951647915253,
|
|
"loss": 1.7576,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"epoch": 1.69,
|
|
"learning_rate": 0.0004655057569523485,
|
|
"loss": 1.6778,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"epoch": 1.7,
|
|
"learning_rate": 0.0004653817915205685,
|
|
"loss": 1.6504,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"epoch": 1.7,
|
|
"learning_rate": 0.0004652576203022552,
|
|
"loss": 1.7902,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"epoch": 1.7,
|
|
"learning_rate": 0.000465133243416048,
|
|
"loss": 1.7524,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"epoch": 1.7,
|
|
"learning_rate": 0.00046500866098078285,
|
|
"loss": 1.7181,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"epoch": 1.71,
|
|
"learning_rate": 0.00046488387311549204,
|
|
"loss": 1.6994,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"epoch": 1.71,
|
|
"learning_rate": 0.000464758879939404,
|
|
"loss": 1.6283,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"epoch": 1.71,
|
|
"learning_rate": 0.0004646336815719436,
|
|
"loss": 1.7109,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"epoch": 1.72,
|
|
"learning_rate": 0.0004645082781327316,
|
|
"loss": 1.7299,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"epoch": 1.72,
|
|
"learning_rate": 0.00046438266974158473,
|
|
"loss": 1.727,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"epoch": 1.72,
|
|
"learning_rate": 0.0004642568565185154,
|
|
"loss": 1.7878,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"epoch": 1.73,
|
|
"learning_rate": 0.000464130838583732,
|
|
"loss": 1.7165,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"epoch": 1.73,
|
|
"learning_rate": 0.00046400461605763835,
|
|
"loss": 1.6004,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"epoch": 1.73,
|
|
"learning_rate": 0.0004638781890608337,
|
|
"loss": 1.7473,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"epoch": 1.74,
|
|
"learning_rate": 0.0004637515577141127,
|
|
"loss": 1.7393,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"epoch": 1.74,
|
|
"learning_rate": 0.00046362472213846534,
|
|
"loss": 1.6784,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"epoch": 1.74,
|
|
"learning_rate": 0.00046349768245507666,
|
|
"loss": 1.5928,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"epoch": 1.75,
|
|
"learning_rate": 0.00046337043878532676,
|
|
"loss": 1.7812,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"epoch": 1.75,
|
|
"learning_rate": 0.0004632429912507905,
|
|
"loss": 1.7762,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"epoch": 1.75,
|
|
"learning_rate": 0.0004631153399732377,
|
|
"loss": 1.6857,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"epoch": 1.75,
|
|
"learning_rate": 0.00046298748507463285,
|
|
"loss": 1.6849,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"epoch": 1.76,
|
|
"learning_rate": 0.00046285942667713474,
|
|
"loss": 1.655,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"epoch": 1.76,
|
|
"learning_rate": 0.0004627311649030969,
|
|
"loss": 1.6488,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"epoch": 1.76,
|
|
"learning_rate": 0.00046260269987506697,
|
|
"loss": 1.7191,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"epoch": 1.77,
|
|
"learning_rate": 0.00046247403171578694,
|
|
"loss": 1.7452,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"epoch": 1.77,
|
|
"learning_rate": 0.00046234516054819265,
|
|
"loss": 1.7273,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"epoch": 1.77,
|
|
"learning_rate": 0.00046221608649541423,
|
|
"loss": 1.6921,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"epoch": 1.78,
|
|
"learning_rate": 0.0004620868096807754,
|
|
"loss": 1.7258,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"epoch": 1.78,
|
|
"learning_rate": 0.00046195733022779366,
|
|
"loss": 1.692,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"epoch": 1.78,
|
|
"learning_rate": 0.0004618276482601803,
|
|
"loss": 1.7428,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"epoch": 1.79,
|
|
"learning_rate": 0.00046169776390183974,
|
|
"loss": 1.7605,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"epoch": 1.79,
|
|
"learning_rate": 0.0004615676772768702,
|
|
"loss": 1.6809,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"epoch": 1.79,
|
|
"learning_rate": 0.00046143738850956277,
|
|
"loss": 1.7304,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"epoch": 1.8,
|
|
"learning_rate": 0.000461306897724402,
|
|
"loss": 1.7114,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"epoch": 1.8,
|
|
"learning_rate": 0.00046117620504606524,
|
|
"loss": 1.6627,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"epoch": 1.8,
|
|
"learning_rate": 0.0004610453105994228,
|
|
"loss": 1.8117,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"epoch": 1.8,
|
|
"learning_rate": 0.0004609142145095377,
|
|
"loss": 1.5929,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"epoch": 1.81,
|
|
"learning_rate": 0.00046078291690166594,
|
|
"loss": 1.7055,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"epoch": 1.81,
|
|
"learning_rate": 0.00046065141790125567,
|
|
"loss": 1.7306,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"epoch": 1.81,
|
|
"learning_rate": 0.0004605197176339475,
|
|
"loss": 1.6857,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"epoch": 1.82,
|
|
"learning_rate": 0.00046038781622557463,
|
|
"loss": 1.6819,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"epoch": 1.82,
|
|
"learning_rate": 0.0004602557138021622,
|
|
"loss": 1.718,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"epoch": 1.82,
|
|
"learning_rate": 0.0004601234104899275,
|
|
"loss": 1.7283,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"epoch": 1.83,
|
|
"learning_rate": 0.0004599909064152796,
|
|
"loss": 1.7607,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"epoch": 1.83,
|
|
"learning_rate": 0.00045985820170481973,
|
|
"loss": 1.7872,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"epoch": 1.83,
|
|
"learning_rate": 0.0004597252964853404,
|
|
"loss": 1.7228,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"epoch": 1.84,
|
|
"learning_rate": 0.00045959219088382604,
|
|
"loss": 1.7719,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"epoch": 1.84,
|
|
"learning_rate": 0.00045945888502745236,
|
|
"loss": 1.7436,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"epoch": 1.84,
|
|
"learning_rate": 0.0004593253790435864,
|
|
"loss": 1.5808,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"epoch": 1.84,
|
|
"learning_rate": 0.00045919167305978647,
|
|
"loss": 1.7742,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"epoch": 1.85,
|
|
"learning_rate": 0.00045905776720380197,
|
|
"loss": 1.6983,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"epoch": 1.85,
|
|
"learning_rate": 0.0004589236616035733,
|
|
"loss": 1.6131,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"epoch": 1.85,
|
|
"learning_rate": 0.00045878935638723155,
|
|
"loss": 1.8226,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"epoch": 1.86,
|
|
"learning_rate": 0.00045865485168309874,
|
|
"loss": 1.666,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"epoch": 1.86,
|
|
"learning_rate": 0.0004585201476196873,
|
|
"loss": 1.8116,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"epoch": 1.86,
|
|
"learning_rate": 0.00045838524432570025,
|
|
"loss": 1.6229,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"epoch": 1.87,
|
|
"learning_rate": 0.00045825014193003104,
|
|
"loss": 1.7702,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 1.87,
|
|
"learning_rate": 0.0004581148405617631,
|
|
"loss": 1.6634,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"epoch": 1.87,
|
|
"learning_rate": 0.0004579793403501703,
|
|
"loss": 1.661,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"epoch": 1.88,
|
|
"learning_rate": 0.0004578436414247161,
|
|
"loss": 1.6714,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"epoch": 1.88,
|
|
"learning_rate": 0.00045770774391505425,
|
|
"loss": 1.647,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"epoch": 1.88,
|
|
"learning_rate": 0.0004575716479510279,
|
|
"loss": 1.5564,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"epoch": 1.89,
|
|
"learning_rate": 0.00045743535366266996,
|
|
"loss": 1.713,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"epoch": 1.89,
|
|
"learning_rate": 0.0004572988611802028,
|
|
"loss": 1.7022,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"epoch": 1.89,
|
|
"learning_rate": 0.00045716217063403826,
|
|
"loss": 1.6818,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"epoch": 1.89,
|
|
"learning_rate": 0.0004570252821547772,
|
|
"loss": 1.6412,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"epoch": 1.9,
|
|
"learning_rate": 0.0004568881958732097,
|
|
"loss": 1.8097,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"epoch": 1.9,
|
|
"learning_rate": 0.00045675091192031505,
|
|
"loss": 1.6231,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"epoch": 1.9,
|
|
"learning_rate": 0.0004566134304272609,
|
|
"loss": 1.7493,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"epoch": 1.91,
|
|
"learning_rate": 0.0004564757515254042,
|
|
"loss": 1.7827,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"epoch": 1.91,
|
|
"learning_rate": 0.00045633787534629015,
|
|
"loss": 1.8124,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"epoch": 1.91,
|
|
"learning_rate": 0.00045619980202165256,
|
|
"loss": 1.6485,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"epoch": 1.92,
|
|
"learning_rate": 0.0004560615316834136,
|
|
"loss": 1.7528,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"epoch": 1.92,
|
|
"learning_rate": 0.0004559230644636837,
|
|
"loss": 1.6978,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"epoch": 1.92,
|
|
"learning_rate": 0.0004557844004947612,
|
|
"loss": 1.7464,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"epoch": 1.93,
|
|
"learning_rate": 0.00045564553990913283,
|
|
"loss": 1.6492,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"epoch": 1.93,
|
|
"learning_rate": 0.0004555064828394727,
|
|
"loss": 1.7655,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"epoch": 1.93,
|
|
"learning_rate": 0.0004553672294186431,
|
|
"loss": 1.6587,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"epoch": 1.94,
|
|
"learning_rate": 0.00045522777977969356,
|
|
"loss": 1.6678,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"epoch": 1.94,
|
|
"learning_rate": 0.0004550881340558613,
|
|
"loss": 1.7724,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"epoch": 1.94,
|
|
"learning_rate": 0.00045494829238057076,
|
|
"loss": 1.6498,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"epoch": 1.94,
|
|
"learning_rate": 0.0004548082548874338,
|
|
"loss": 1.5678,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"epoch": 1.95,
|
|
"learning_rate": 0.00045466802171024924,
|
|
"loss": 1.8154,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"epoch": 1.95,
|
|
"learning_rate": 0.00045452759298300274,
|
|
"loss": 1.7163,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"epoch": 1.95,
|
|
"learning_rate": 0.000454386968839867,
|
|
"loss": 1.6262,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"epoch": 1.96,
|
|
"learning_rate": 0.00045424614941520124,
|
|
"loss": 1.8004,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"epoch": 1.96,
|
|
"learning_rate": 0.00045410513484355153,
|
|
"loss": 1.5996,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"epoch": 1.96,
|
|
"learning_rate": 0.00045396392525965025,
|
|
"loss": 1.7592,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"epoch": 1.97,
|
|
"learning_rate": 0.000453822520798416,
|
|
"loss": 1.7599,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"epoch": 1.97,
|
|
"learning_rate": 0.00045368092159495376,
|
|
"loss": 1.6335,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"epoch": 1.97,
|
|
"learning_rate": 0.00045353912778455446,
|
|
"loss": 1.7326,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"epoch": 1.98,
|
|
"learning_rate": 0.000453397139502695,
|
|
"loss": 1.8057,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"epoch": 1.98,
|
|
"learning_rate": 0.00045325495688503805,
|
|
"loss": 1.7342,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"epoch": 1.98,
|
|
"learning_rate": 0.00045311258006743195,
|
|
"loss": 1.6517,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"epoch": 1.98,
|
|
"learning_rate": 0.0004529700091859107,
|
|
"loss": 1.6949,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"epoch": 1.99,
|
|
"learning_rate": 0.0004528272443766937,
|
|
"loss": 1.7317,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"epoch": 1.99,
|
|
"learning_rate": 0.0004526842857761855,
|
|
"loss": 1.7421,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"epoch": 1.99,
|
|
"learning_rate": 0.00045254113352097595,
|
|
"loss": 1.7394,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"epoch": 2.0,
|
|
"learning_rate": 0.0004523977877478398,
|
|
"loss": 1.6405,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"epoch": 2.0,
|
|
"learning_rate": 0.0004522542485937369,
|
|
"loss": 1.7974,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"epoch": 2.0,
|
|
"learning_rate": 0.00045211051619581155,
|
|
"loss": 1.4943,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"epoch": 2.01,
|
|
"learning_rate": 0.00045196659069139303,
|
|
"loss": 1.513,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"epoch": 2.01,
|
|
"learning_rate": 0.0004518224722179949,
|
|
"loss": 1.6113,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"epoch": 2.01,
|
|
"learning_rate": 0.0004516781609133151,
|
|
"loss": 1.4953,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"epoch": 2.02,
|
|
"learning_rate": 0.000451533656915236,
|
|
"loss": 1.5054,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"epoch": 2.02,
|
|
"learning_rate": 0.00045138896036182386,
|
|
"loss": 1.7071,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"epoch": 2.02,
|
|
"learning_rate": 0.000451244071391329,
|
|
"loss": 1.5807,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"epoch": 2.03,
|
|
"learning_rate": 0.00045109899014218556,
|
|
"loss": 1.6293,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"epoch": 2.03,
|
|
"learning_rate": 0.0004509537167530116,
|
|
"loss": 1.5702,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"epoch": 2.03,
|
|
"learning_rate": 0.00045080825136260827,
|
|
"loss": 1.6553,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"epoch": 2.03,
|
|
"learning_rate": 0.0004506625941099608,
|
|
"loss": 1.7088,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"epoch": 2.04,
|
|
"learning_rate": 0.0004505167451342371,
|
|
"loss": 1.6027,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"epoch": 2.04,
|
|
"learning_rate": 0.0004503707045747889,
|
|
"loss": 1.5612,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"epoch": 2.04,
|
|
"learning_rate": 0.0004502244725711504,
|
|
"loss": 1.4987,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"epoch": 2.05,
|
|
"learning_rate": 0.0004500780492630391,
|
|
"loss": 1.6238,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"epoch": 2.05,
|
|
"learning_rate": 0.000449931434790355,
|
|
"loss": 1.5206,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"epoch": 2.05,
|
|
"learning_rate": 0.00044978462929318115,
|
|
"loss": 1.6022,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"epoch": 2.06,
|
|
"learning_rate": 0.0004496376329117826,
|
|
"loss": 1.6143,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"epoch": 2.06,
|
|
"learning_rate": 0.00044949044578660726,
|
|
"loss": 1.4577,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"epoch": 2.06,
|
|
"learning_rate": 0.00044934306805828497,
|
|
"loss": 1.7306,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"epoch": 2.07,
|
|
"learning_rate": 0.0004491954998676277,
|
|
"loss": 1.5609,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"epoch": 2.07,
|
|
"learning_rate": 0.00044904774135562966,
|
|
"loss": 1.5709,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"epoch": 2.07,
|
|
"learning_rate": 0.0004488997926634665,
|
|
"loss": 1.602,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"epoch": 2.08,
|
|
"learning_rate": 0.00044875165393249594,
|
|
"loss": 1.5884,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"epoch": 2.08,
|
|
"learning_rate": 0.00044860332530425717,
|
|
"loss": 1.5896,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"epoch": 2.08,
|
|
"learning_rate": 0.0004484548069204707,
|
|
"loss": 1.5242,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"epoch": 2.08,
|
|
"learning_rate": 0.0004483060989230384,
|
|
"loss": 1.6844,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"epoch": 2.09,
|
|
"learning_rate": 0.0004481572014540434,
|
|
"loss": 1.5793,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"epoch": 2.09,
|
|
"learning_rate": 0.00044800811465574975,
|
|
"loss": 1.5254,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"epoch": 2.09,
|
|
"learning_rate": 0.0004478588386706025,
|
|
"loss": 1.5462,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"epoch": 2.1,
|
|
"learning_rate": 0.0004477093736412272,
|
|
"loss": 1.5891,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"epoch": 2.1,
|
|
"learning_rate": 0.0004475597197104304,
|
|
"loss": 1.6941,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"epoch": 2.1,
|
|
"learning_rate": 0.0004474098770211989,
|
|
"loss": 1.5751,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"epoch": 2.11,
|
|
"learning_rate": 0.0004472598457166999,
|
|
"loss": 1.4841,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"epoch": 2.11,
|
|
"learning_rate": 0.00044710962594028073,
|
|
"loss": 1.5308,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"epoch": 2.11,
|
|
"learning_rate": 0.00044695921783546893,
|
|
"loss": 1.6964,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"epoch": 2.12,
|
|
"learning_rate": 0.000446808621545972,
|
|
"loss": 1.5533,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"epoch": 2.12,
|
|
"learning_rate": 0.00044665783721567704,
|
|
"loss": 1.5911,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"epoch": 2.12,
|
|
"learning_rate": 0.000446506864988651,
|
|
"loss": 1.5858,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"epoch": 2.12,
|
|
"learning_rate": 0.0004463557050091404,
|
|
"loss": 1.6559,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"epoch": 2.13,
|
|
"learning_rate": 0.00044620435742157076,
|
|
"loss": 1.5727,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"epoch": 2.13,
|
|
"learning_rate": 0.00044605282237054737,
|
|
"loss": 1.6657,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"epoch": 2.13,
|
|
"learning_rate": 0.0004459011000008544,
|
|
"loss": 1.6124,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"epoch": 2.14,
|
|
"learning_rate": 0.0004457491904574549,
|
|
"loss": 1.6228,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"epoch": 2.14,
|
|
"learning_rate": 0.00044559709388549085,
|
|
"loss": 1.6781,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"epoch": 2.14,
|
|
"learning_rate": 0.0004454448104302829,
|
|
"loss": 1.5092,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"epoch": 2.15,
|
|
"learning_rate": 0.00044529234023733035,
|
|
"loss": 1.5866,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"epoch": 2.15,
|
|
"learning_rate": 0.0004451396834523108,
|
|
"loss": 1.5488,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"epoch": 2.15,
|
|
"learning_rate": 0.0004449868402210802,
|
|
"loss": 1.5013,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"epoch": 2.16,
|
|
"learning_rate": 0.00044483381068967257,
|
|
"loss": 1.5835,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"epoch": 2.16,
|
|
"learning_rate": 0.00044468059500430004,
|
|
"loss": 1.697,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"epoch": 2.16,
|
|
"learning_rate": 0.00044452719331135245,
|
|
"loss": 1.5943,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"epoch": 2.17,
|
|
"learning_rate": 0.00044437360575739755,
|
|
"loss": 1.574,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"epoch": 2.17,
|
|
"learning_rate": 0.0004442198324891805,
|
|
"loss": 1.6571,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"epoch": 2.17,
|
|
"learning_rate": 0.00044406587365362394,
|
|
"loss": 1.5966,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"epoch": 2.17,
|
|
"learning_rate": 0.00044391172939782796,
|
|
"loss": 1.6121,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"epoch": 2.18,
|
|
"learning_rate": 0.0004437573998690696,
|
|
"loss": 1.5566,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"epoch": 2.18,
|
|
"learning_rate": 0.00044360288521480307,
|
|
"loss": 1.6067,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"epoch": 2.18,
|
|
"learning_rate": 0.0004434481855826593,
|
|
"loss": 1.6211,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"epoch": 2.19,
|
|
"learning_rate": 0.00044329330112044605,
|
|
"loss": 1.5672,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"epoch": 2.19,
|
|
"learning_rate": 0.0004431382319761479,
|
|
"loss": 1.5804,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"epoch": 2.19,
|
|
"learning_rate": 0.00044298297829792533,
|
|
"loss": 1.5359,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"epoch": 2.2,
|
|
"learning_rate": 0.00044282754023411576,
|
|
"loss": 1.5816,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"epoch": 2.2,
|
|
"learning_rate": 0.00044267191793323236,
|
|
"loss": 1.5433,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"epoch": 2.2,
|
|
"learning_rate": 0.00044251611154396444,
|
|
"loss": 1.5334,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"epoch": 2.21,
|
|
"learning_rate": 0.0004423601212151772,
|
|
"loss": 1.5855,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"epoch": 2.21,
|
|
"learning_rate": 0.00044220394709591174,
|
|
"loss": 1.5417,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"epoch": 2.21,
|
|
"learning_rate": 0.00044204758933538436,
|
|
"loss": 1.6542,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"epoch": 2.22,
|
|
"learning_rate": 0.00044189104808298744,
|
|
"loss": 1.6341,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"epoch": 2.22,
|
|
"learning_rate": 0.00044173432348828796,
|
|
"loss": 1.6055,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"epoch": 2.22,
|
|
"learning_rate": 0.00044157741570102874,
|
|
"loss": 1.6651,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"epoch": 2.22,
|
|
"learning_rate": 0.00044142032487112706,
|
|
"loss": 1.5856,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"epoch": 2.23,
|
|
"learning_rate": 0.0004412630511486755,
|
|
"loss": 1.6855,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"epoch": 2.23,
|
|
"learning_rate": 0.0004411055946839413,
|
|
"loss": 1.5645,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"epoch": 2.23,
|
|
"learning_rate": 0.0004409479556273661,
|
|
"loss": 1.5187,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"epoch": 2.24,
|
|
"learning_rate": 0.00044079013412956627,
|
|
"loss": 1.6653,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"epoch": 2.24,
|
|
"learning_rate": 0.00044063213034133223,
|
|
"loss": 1.6058,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"epoch": 2.24,
|
|
"learning_rate": 0.0004404739444136287,
|
|
"loss": 1.6327,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"epoch": 2.25,
|
|
"learning_rate": 0.00044031557649759455,
|
|
"loss": 1.6876,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"epoch": 2.25,
|
|
"learning_rate": 0.00044015702674454234,
|
|
"loss": 1.6287,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"epoch": 2.25,
|
|
"learning_rate": 0.0004399982953059584,
|
|
"loss": 1.6116,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"epoch": 2.26,
|
|
"learning_rate": 0.0004398393823335027,
|
|
"loss": 1.6334,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"epoch": 2.26,
|
|
"learning_rate": 0.0004396802879790087,
|
|
"loss": 1.5998,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"epoch": 2.26,
|
|
"learning_rate": 0.00043952101239448307,
|
|
"loss": 1.7187,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"epoch": 2.26,
|
|
"learning_rate": 0.00043936155573210555,
|
|
"loss": 1.5474,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"epoch": 2.27,
|
|
"learning_rate": 0.00043920191814422917,
|
|
"loss": 1.5925,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"epoch": 2.27,
|
|
"learning_rate": 0.0004390420997833796,
|
|
"loss": 1.7452,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"epoch": 2.27,
|
|
"learning_rate": 0.0004388821008022553,
|
|
"loss": 1.6014,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"epoch": 2.28,
|
|
"learning_rate": 0.0004387219213537273,
|
|
"loss": 1.5297,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"epoch": 2.28,
|
|
"learning_rate": 0.00043856156159083906,
|
|
"loss": 1.7078,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"epoch": 2.28,
|
|
"learning_rate": 0.0004384010216668063,
|
|
"loss": 1.724,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"epoch": 2.29,
|
|
"learning_rate": 0.0004382403017350168,
|
|
"loss": 1.763,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"epoch": 2.29,
|
|
"learning_rate": 0.0004380794019490306,
|
|
"loss": 1.54,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"epoch": 2.29,
|
|
"learning_rate": 0.00043791832246257935,
|
|
"loss": 1.478,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"epoch": 2.3,
|
|
"learning_rate": 0.0004377570634295664,
|
|
"loss": 1.6418,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"epoch": 2.3,
|
|
"learning_rate": 0.00043759562500406666,
|
|
"loss": 1.6564,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"epoch": 2.3,
|
|
"learning_rate": 0.0004374340073403266,
|
|
"loss": 1.7177,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"epoch": 2.31,
|
|
"learning_rate": 0.00043727221059276355,
|
|
"loss": 1.5582,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"epoch": 2.31,
|
|
"learning_rate": 0.00043711023491596656,
|
|
"loss": 1.6595,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"epoch": 2.31,
|
|
"learning_rate": 0.0004369480804646951,
|
|
"loss": 1.5402,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"epoch": 2.31,
|
|
"learning_rate": 0.00043678574739387967,
|
|
"loss": 1.5898,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"epoch": 2.32,
|
|
"learning_rate": 0.00043662323585862134,
|
|
"loss": 1.5429,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"epoch": 2.32,
|
|
"learning_rate": 0.00043646054601419193,
|
|
"loss": 1.4844,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"epoch": 2.32,
|
|
"learning_rate": 0.0004362976780160333,
|
|
"loss": 1.6215,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"epoch": 2.33,
|
|
"learning_rate": 0.0004361346320197577,
|
|
"loss": 1.6999,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"epoch": 2.33,
|
|
"learning_rate": 0.00043597140818114747,
|
|
"loss": 1.6191,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"epoch": 2.33,
|
|
"learning_rate": 0.0004358080066561547,
|
|
"loss": 1.687,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"epoch": 2.34,
|
|
"learning_rate": 0.00043564442760090163,
|
|
"loss": 1.5728,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"epoch": 2.34,
|
|
"learning_rate": 0.0004354806711716797,
|
|
"loss": 1.7119,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"epoch": 2.34,
|
|
"learning_rate": 0.00043531673752494996,
|
|
"loss": 1.6253,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"epoch": 2.35,
|
|
"learning_rate": 0.0004351526268173428,
|
|
"loss": 1.5524,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"epoch": 2.35,
|
|
"learning_rate": 0.00043498833920565795,
|
|
"loss": 1.669,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"epoch": 2.35,
|
|
"learning_rate": 0.00043484032923188614,
|
|
"loss": 1.5077,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"epoch": 2.36,
|
|
"learning_rate": 0.0004346757059350416,
|
|
"loss": 1.5353,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"epoch": 2.36,
|
|
"learning_rate": 0.00043451090618979333,
|
|
"loss": 1.5849,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"epoch": 2.36,
|
|
"learning_rate": 0.00043434593015359926,
|
|
"loss": 1.6768,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"epoch": 2.36,
|
|
"learning_rate": 0.00043418077798408573,
|
|
"loss": 1.6279,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"epoch": 2.37,
|
|
"learning_rate": 0.00043401544983904736,
|
|
"loss": 1.5883,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"epoch": 2.37,
|
|
"learning_rate": 0.000433849945876447,
|
|
"loss": 1.5158,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"epoch": 2.37,
|
|
"learning_rate": 0.00043368426625441537,
|
|
"loss": 1.7189,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"epoch": 2.38,
|
|
"learning_rate": 0.00043351841113125104,
|
|
"loss": 1.577,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"epoch": 2.38,
|
|
"learning_rate": 0.0004333523806654203,
|
|
"loss": 1.7189,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"epoch": 2.38,
|
|
"learning_rate": 0.000433186175015557,
|
|
"loss": 1.6239,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"epoch": 2.39,
|
|
"learning_rate": 0.00043301979434046237,
|
|
"loss": 1.67,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"epoch": 2.39,
|
|
"learning_rate": 0.00043285323879910465,
|
|
"loss": 1.5498,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"epoch": 2.39,
|
|
"learning_rate": 0.0004326865085506195,
|
|
"loss": 1.562,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"epoch": 2.4,
|
|
"learning_rate": 0.0004325196037543092,
|
|
"loss": 1.6632,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"epoch": 2.4,
|
|
"learning_rate": 0.00043235252456964315,
|
|
"loss": 1.5973,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"epoch": 2.4,
|
|
"learning_rate": 0.00043218527115625687,
|
|
"loss": 1.6593,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"epoch": 2.4,
|
|
"learning_rate": 0.0004320178436739529,
|
|
"loss": 1.562,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"epoch": 2.41,
|
|
"learning_rate": 0.00043185024228269966,
|
|
"loss": 1.5563,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"epoch": 2.41,
|
|
"learning_rate": 0.000431682467142632,
|
|
"loss": 1.6165,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"epoch": 2.41,
|
|
"learning_rate": 0.00043151451841405054,
|
|
"loss": 1.6572,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"epoch": 2.42,
|
|
"learning_rate": 0.0004313463962574221,
|
|
"loss": 1.6,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"epoch": 2.42,
|
|
"learning_rate": 0.0004311781008333788,
|
|
"loss": 1.7105,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"epoch": 2.42,
|
|
"learning_rate": 0.0004310096323027186,
|
|
"loss": 1.6704,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"epoch": 2.43,
|
|
"learning_rate": 0.00043084099082640474,
|
|
"loss": 1.5561,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"epoch": 2.43,
|
|
"learning_rate": 0.00043067217656556577,
|
|
"loss": 1.5365,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"epoch": 2.43,
|
|
"learning_rate": 0.00043050318968149517,
|
|
"loss": 1.545,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"epoch": 2.44,
|
|
"learning_rate": 0.00043033403033565157,
|
|
"loss": 1.5647,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"epoch": 2.44,
|
|
"learning_rate": 0.0004301646986896582,
|
|
"loss": 1.5986,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"epoch": 2.44,
|
|
"learning_rate": 0.0004299951949053029,
|
|
"loss": 1.6631,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"epoch": 2.45,
|
|
"learning_rate": 0.0004298255191445383,
|
|
"loss": 1.6488,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"epoch": 2.45,
|
|
"learning_rate": 0.00042965567156948094,
|
|
"loss": 1.5433,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"epoch": 2.45,
|
|
"learning_rate": 0.0004294856523424116,
|
|
"loss": 1.6742,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"epoch": 2.45,
|
|
"learning_rate": 0.00042931546162577536,
|
|
"loss": 1.6561,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"epoch": 2.46,
|
|
"learning_rate": 0.00042914509958218074,
|
|
"loss": 1.5926,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"epoch": 2.46,
|
|
"learning_rate": 0.00042897456637440033,
|
|
"loss": 1.6451,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"epoch": 2.46,
|
|
"learning_rate": 0.00042880386216537003,
|
|
"loss": 1.5857,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"epoch": 2.47,
|
|
"learning_rate": 0.0004286329871181891,
|
|
"loss": 1.607,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"epoch": 2.47,
|
|
"learning_rate": 0.00042846194139612017,
|
|
"loss": 1.6591,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"epoch": 2.47,
|
|
"learning_rate": 0.00042829072516258895,
|
|
"loss": 1.666,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"epoch": 2.48,
|
|
"learning_rate": 0.0004281193385811838,
|
|
"loss": 1.6707,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"epoch": 2.48,
|
|
"learning_rate": 0.0004279477818156562,
|
|
"loss": 1.7703,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"epoch": 2.48,
|
|
"learning_rate": 0.0004277760550299199,
|
|
"loss": 1.7352,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"epoch": 2.49,
|
|
"learning_rate": 0.0004276041583880514,
|
|
"loss": 1.6835,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"epoch": 2.49,
|
|
"learning_rate": 0.00042743209205428937,
|
|
"loss": 1.5711,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"epoch": 2.49,
|
|
"learning_rate": 0.0004272598561930345,
|
|
"loss": 1.6046,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"epoch": 2.5,
|
|
"learning_rate": 0.00042708745096884954,
|
|
"loss": 1.5859,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"epoch": 2.5,
|
|
"learning_rate": 0.0004269148765464591,
|
|
"loss": 1.6263,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"epoch": 2.5,
|
|
"learning_rate": 0.0004267421330907494,
|
|
"loss": 1.676,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"epoch": 2.5,
|
|
"learning_rate": 0.00042656922076676816,
|
|
"loss": 1.6126,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"epoch": 2.51,
|
|
"learning_rate": 0.00042639613973972446,
|
|
"loss": 1.5596,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"epoch": 2.51,
|
|
"learning_rate": 0.0004262228901749886,
|
|
"loss": 1.6055,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"epoch": 2.51,
|
|
"learning_rate": 0.00042604947223809185,
|
|
"loss": 1.612,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"epoch": 2.52,
|
|
"learning_rate": 0.00042587588609472644,
|
|
"loss": 1.6218,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"epoch": 2.52,
|
|
"learning_rate": 0.00042570213191074516,
|
|
"loss": 1.5185,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"epoch": 2.52,
|
|
"learning_rate": 0.0004255282098521615,
|
|
"loss": 1.6453,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"epoch": 2.53,
|
|
"learning_rate": 0.0004253541200851493,
|
|
"loss": 1.5697,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"epoch": 2.53,
|
|
"learning_rate": 0.0004251798627760426,
|
|
"loss": 1.6706,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"epoch": 2.53,
|
|
"learning_rate": 0.0004250054380913355,
|
|
"loss": 1.7195,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"epoch": 2.54,
|
|
"learning_rate": 0.0004248308461976821,
|
|
"loss": 1.6859,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"epoch": 2.54,
|
|
"learning_rate": 0.0004246560872618963,
|
|
"loss": 1.762,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"epoch": 2.54,
|
|
"learning_rate": 0.00042448116145095145,
|
|
"loss": 1.5864,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"epoch": 2.54,
|
|
"learning_rate": 0.0004243060689319804,
|
|
"loss": 1.563,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"epoch": 2.55,
|
|
"learning_rate": 0.0004241308098722754,
|
|
"loss": 1.5663,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"epoch": 2.55,
|
|
"learning_rate": 0.0004239553844392876,
|
|
"loss": 1.7388,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"epoch": 2.55,
|
|
"learning_rate": 0.00042377979280062734,
|
|
"loss": 1.5661,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"epoch": 2.56,
|
|
"learning_rate": 0.00042360403512406355,
|
|
"loss": 1.6923,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"epoch": 2.56,
|
|
"learning_rate": 0.0004234281115775239,
|
|
"loss": 1.579,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"epoch": 2.56,
|
|
"learning_rate": 0.00042325202232909473,
|
|
"loss": 1.633,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"epoch": 2.57,
|
|
"learning_rate": 0.00042307576754702027,
|
|
"loss": 1.7167,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"epoch": 2.57,
|
|
"learning_rate": 0.00042289934739970326,
|
|
"loss": 1.5728,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"epoch": 2.57,
|
|
"learning_rate": 0.00042272276205570434,
|
|
"loss": 1.6769,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"epoch": 2.58,
|
|
"learning_rate": 0.00042254601168374196,
|
|
"loss": 1.6681,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"epoch": 2.58,
|
|
"learning_rate": 0.00042236909645269226,
|
|
"loss": 1.5987,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"epoch": 2.58,
|
|
"learning_rate": 0.0004221920165315889,
|
|
"loss": 1.5763,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"epoch": 2.59,
|
|
"learning_rate": 0.00042201477208962294,
|
|
"loss": 1.62,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"epoch": 2.59,
|
|
"learning_rate": 0.0004218373632961424,
|
|
"loss": 1.5974,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"epoch": 2.59,
|
|
"learning_rate": 0.00042165979032065274,
|
|
"loss": 1.6041,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"epoch": 2.59,
|
|
"learning_rate": 0.00042148205333281596,
|
|
"loss": 1.6192,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"epoch": 2.6,
|
|
"learning_rate": 0.0004213041525024509,
|
|
"loss": 1.6159,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"epoch": 2.6,
|
|
"learning_rate": 0.00042112608799953286,
|
|
"loss": 1.6805,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"epoch": 2.6,
|
|
"learning_rate": 0.0004209478599941936,
|
|
"loss": 1.5935,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"epoch": 2.61,
|
|
"learning_rate": 0.00042076946865672105,
|
|
"loss": 1.5806,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"epoch": 2.61,
|
|
"learning_rate": 0.00042059091415755926,
|
|
"loss": 1.673,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"epoch": 2.61,
|
|
"learning_rate": 0.00042041219666730803,
|
|
"loss": 1.6002,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"epoch": 2.62,
|
|
"learning_rate": 0.00042023331635672315,
|
|
"loss": 1.6976,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"epoch": 2.62,
|
|
"learning_rate": 0.0004200542733967156,
|
|
"loss": 1.5987,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"epoch": 2.62,
|
|
"learning_rate": 0.0004198750679583521,
|
|
"loss": 1.7076,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"epoch": 2.63,
|
|
"learning_rate": 0.00041969570021285454,
|
|
"loss": 1.6666,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"epoch": 2.63,
|
|
"learning_rate": 0.0004195161703315997,
|
|
"loss": 1.543,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"epoch": 2.63,
|
|
"learning_rate": 0.0004193364784861195,
|
|
"loss": 1.6416,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"epoch": 2.64,
|
|
"learning_rate": 0.0004191566248481005,
|
|
"loss": 1.6789,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"epoch": 2.64,
|
|
"learning_rate": 0.0004189766095893839,
|
|
"loss": 1.5496,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"epoch": 2.64,
|
|
"learning_rate": 0.0004187964328819651,
|
|
"loss": 1.726,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"epoch": 2.64,
|
|
"learning_rate": 0.0004186160948979941,
|
|
"loss": 1.5388,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"epoch": 2.65,
|
|
"learning_rate": 0.0004184355958097749,
|
|
"loss": 1.6899,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"epoch": 2.65,
|
|
"learning_rate": 0.00041825493578976513,
|
|
"loss": 1.5129,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"epoch": 2.65,
|
|
"learning_rate": 0.00041807411501057647,
|
|
"loss": 1.6381,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"epoch": 2.66,
|
|
"learning_rate": 0.0004178931336449743,
|
|
"loss": 1.6156,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"epoch": 2.66,
|
|
"learning_rate": 0.00041771199186587706,
|
|
"loss": 1.6701,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"epoch": 2.66,
|
|
"learning_rate": 0.0004175306898463568,
|
|
"loss": 1.6008,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"epoch": 2.67,
|
|
"learning_rate": 0.0004173492277596385,
|
|
"loss": 1.6947,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"epoch": 2.67,
|
|
"learning_rate": 0.0004171676057791001,
|
|
"loss": 1.5953,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"epoch": 2.67,
|
|
"learning_rate": 0.00041698582407827223,
|
|
"loss": 1.6652,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"epoch": 2.68,
|
|
"learning_rate": 0.0004168038828308384,
|
|
"loss": 1.5672,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"epoch": 2.68,
|
|
"learning_rate": 0.0004166217822106343,
|
|
"loss": 1.5832,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"epoch": 2.68,
|
|
"learning_rate": 0.00041643952239164784,
|
|
"loss": 1.6119,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"epoch": 2.68,
|
|
"learning_rate": 0.0004162571035480194,
|
|
"loss": 1.5509,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"epoch": 2.69,
|
|
"learning_rate": 0.0004160745258540409,
|
|
"loss": 1.7378,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"epoch": 2.69,
|
|
"learning_rate": 0.0004158917894841562,
|
|
"loss": 1.6082,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"epoch": 2.69,
|
|
"learning_rate": 0.0004157088946129608,
|
|
"loss": 1.5394,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"epoch": 2.7,
|
|
"learning_rate": 0.00041552584141520165,
|
|
"loss": 1.6291,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"epoch": 2.7,
|
|
"learning_rate": 0.00041534263006577686,
|
|
"loss": 1.5908,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"epoch": 2.7,
|
|
"learning_rate": 0.00041515926073973575,
|
|
"loss": 1.6548,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"epoch": 2.71,
|
|
"learning_rate": 0.0004149757336122786,
|
|
"loss": 1.6509,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"epoch": 2.71,
|
|
"learning_rate": 0.0004147920488587562,
|
|
"loss": 1.5386,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"epoch": 2.71,
|
|
"learning_rate": 0.0004146082066546704,
|
|
"loss": 1.55,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"epoch": 2.72,
|
|
"learning_rate": 0.0004144242071756731,
|
|
"loss": 1.6144,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"epoch": 2.72,
|
|
"learning_rate": 0.0004142400505975665,
|
|
"loss": 1.6578,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"epoch": 2.72,
|
|
"learning_rate": 0.0004140557370963033,
|
|
"loss": 1.5688,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"epoch": 2.73,
|
|
"learning_rate": 0.0004138712668479856,
|
|
"loss": 1.6456,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"epoch": 2.73,
|
|
"learning_rate": 0.00041368664002886554,
|
|
"loss": 1.7302,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"epoch": 2.73,
|
|
"learning_rate": 0.0004135018568153448,
|
|
"loss": 1.6307,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"epoch": 2.73,
|
|
"learning_rate": 0.0004133169173839746,
|
|
"loss": 1.661,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"epoch": 2.74,
|
|
"learning_rate": 0.00041313182191145525,
|
|
"loss": 1.6648,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"epoch": 2.74,
|
|
"learning_rate": 0.00041294657057463623,
|
|
"loss": 1.5781,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"epoch": 2.74,
|
|
"learning_rate": 0.0004127611635505159,
|
|
"loss": 1.5199,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"epoch": 2.75,
|
|
"learning_rate": 0.0004125756010162415,
|
|
"loss": 1.6862,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"epoch": 2.75,
|
|
"learning_rate": 0.0004123898831491086,
|
|
"loss": 1.6795,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"epoch": 2.75,
|
|
"learning_rate": 0.00041220401012656137,
|
|
"loss": 1.5917,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"epoch": 2.76,
|
|
"learning_rate": 0.00041201798212619237,
|
|
"loss": 1.4938,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"epoch": 2.76,
|
|
"learning_rate": 0.00041183179932574186,
|
|
"loss": 1.6443,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"epoch": 2.76,
|
|
"learning_rate": 0.00041164546190309827,
|
|
"loss": 1.5768,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"epoch": 2.77,
|
|
"learning_rate": 0.00041145897003629767,
|
|
"loss": 1.6864,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"epoch": 2.77,
|
|
"learning_rate": 0.00041127232390352376,
|
|
"loss": 1.6241,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"epoch": 2.77,
|
|
"learning_rate": 0.00041108552368310746,
|
|
"loss": 1.6445,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"epoch": 2.78,
|
|
"learning_rate": 0.00041089856955352726,
|
|
"loss": 1.7085,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"epoch": 2.78,
|
|
"learning_rate": 0.00041071146169340835,
|
|
"loss": 1.7206,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"epoch": 2.78,
|
|
"learning_rate": 0.00041052420028152287,
|
|
"loss": 1.5838,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"epoch": 2.78,
|
|
"learning_rate": 0.0004103367854967898,
|
|
"loss": 1.5339,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"epoch": 2.79,
|
|
"learning_rate": 0.0004101492175182747,
|
|
"loss": 1.6166,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"epoch": 2.79,
|
|
"learning_rate": 0.0004099614965251892,
|
|
"loss": 1.7333,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"epoch": 2.79,
|
|
"learning_rate": 0.0004097736226968915,
|
|
"loss": 1.5789,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"epoch": 2.8,
|
|
"learning_rate": 0.0004095855962128856,
|
|
"loss": 1.6474,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"epoch": 2.8,
|
|
"learning_rate": 0.0004093974172528213,
|
|
"loss": 1.6581,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 2.8,
|
|
"learning_rate": 0.00040920908599649433,
|
|
"loss": 1.7313,
|
|
"step": 9010
|
|
},
|
|
{
|
|
"epoch": 2.81,
|
|
"learning_rate": 0.00040902060262384564,
|
|
"loss": 1.6668,
|
|
"step": 9020
|
|
},
|
|
{
|
|
"epoch": 2.81,
|
|
"learning_rate": 0.00040883196731496187,
|
|
"loss": 1.6532,
|
|
"step": 9030
|
|
},
|
|
{
|
|
"epoch": 2.81,
|
|
"learning_rate": 0.0004086431802500744,
|
|
"loss": 1.627,
|
|
"step": 9040
|
|
},
|
|
{
|
|
"epoch": 2.82,
|
|
"learning_rate": 0.00040845424160956004,
|
|
"loss": 1.7869,
|
|
"step": 9050
|
|
},
|
|
{
|
|
"epoch": 2.82,
|
|
"learning_rate": 0.0004082651515739401,
|
|
"loss": 1.6982,
|
|
"step": 9060
|
|
},
|
|
{
|
|
"epoch": 2.82,
|
|
"learning_rate": 0.0004080759103238806,
|
|
"loss": 1.6882,
|
|
"step": 9070
|
|
},
|
|
{
|
|
"epoch": 2.82,
|
|
"learning_rate": 0.00040788651804019217,
|
|
"loss": 1.5885,
|
|
"step": 9080
|
|
},
|
|
{
|
|
"epoch": 2.83,
|
|
"learning_rate": 0.00040769697490382974,
|
|
"loss": 1.6393,
|
|
"step": 9090
|
|
},
|
|
{
|
|
"epoch": 2.83,
|
|
"learning_rate": 0.00040750728109589226,
|
|
"loss": 1.7882,
|
|
"step": 9100
|
|
},
|
|
{
|
|
"epoch": 2.83,
|
|
"learning_rate": 0.00040731743679762257,
|
|
"loss": 1.5666,
|
|
"step": 9110
|
|
},
|
|
{
|
|
"epoch": 2.84,
|
|
"learning_rate": 0.00040712744219040747,
|
|
"loss": 1.6115,
|
|
"step": 9120
|
|
},
|
|
{
|
|
"epoch": 2.84,
|
|
"learning_rate": 0.00040693729745577736,
|
|
"loss": 1.5805,
|
|
"step": 9130
|
|
},
|
|
{
|
|
"epoch": 2.84,
|
|
"learning_rate": 0.00040674700277540594,
|
|
"loss": 1.676,
|
|
"step": 9140
|
|
},
|
|
{
|
|
"epoch": 2.85,
|
|
"learning_rate": 0.0004065565583311103,
|
|
"loss": 1.6885,
|
|
"step": 9150
|
|
},
|
|
{
|
|
"epoch": 2.85,
|
|
"learning_rate": 0.00040636596430485065,
|
|
"loss": 1.6474,
|
|
"step": 9160
|
|
},
|
|
{
|
|
"epoch": 2.85,
|
|
"learning_rate": 0.00040617522087872996,
|
|
"loss": 1.6966,
|
|
"step": 9170
|
|
},
|
|
{
|
|
"epoch": 2.86,
|
|
"learning_rate": 0.0004059843282349941,
|
|
"loss": 1.6538,
|
|
"step": 9180
|
|
},
|
|
{
|
|
"epoch": 2.86,
|
|
"learning_rate": 0.00040579328655603145,
|
|
"loss": 1.5881,
|
|
"step": 9190
|
|
},
|
|
{
|
|
"epoch": 2.86,
|
|
"learning_rate": 0.0004056020960243727,
|
|
"loss": 1.5409,
|
|
"step": 9200
|
|
},
|
|
{
|
|
"epoch": 2.87,
|
|
"learning_rate": 0.0004054107568226909,
|
|
"loss": 1.6688,
|
|
"step": 9210
|
|
},
|
|
{
|
|
"epoch": 2.87,
|
|
"learning_rate": 0.00040521926913380103,
|
|
"loss": 1.6602,
|
|
"step": 9220
|
|
},
|
|
{
|
|
"epoch": 2.87,
|
|
"learning_rate": 0.00040502763314066015,
|
|
"loss": 1.6861,
|
|
"step": 9230
|
|
},
|
|
{
|
|
"epoch": 2.87,
|
|
"learning_rate": 0.0004048358490263667,
|
|
"loss": 1.6763,
|
|
"step": 9240
|
|
},
|
|
{
|
|
"epoch": 2.88,
|
|
"learning_rate": 0.000404643916974161,
|
|
"loss": 1.6515,
|
|
"step": 9250
|
|
},
|
|
{
|
|
"epoch": 2.88,
|
|
"learning_rate": 0.00040445183716742437,
|
|
"loss": 1.5856,
|
|
"step": 9260
|
|
},
|
|
{
|
|
"epoch": 2.88,
|
|
"learning_rate": 0.00040425960978967944,
|
|
"loss": 1.6202,
|
|
"step": 9270
|
|
},
|
|
{
|
|
"epoch": 2.89,
|
|
"learning_rate": 0.00040406723502459,
|
|
"loss": 1.5565,
|
|
"step": 9280
|
|
},
|
|
{
|
|
"epoch": 2.89,
|
|
"learning_rate": 0.00040387471305596044,
|
|
"loss": 1.6218,
|
|
"step": 9290
|
|
},
|
|
{
|
|
"epoch": 2.89,
|
|
"learning_rate": 0.0004036820440677359,
|
|
"loss": 1.7129,
|
|
"step": 9300
|
|
},
|
|
{
|
|
"epoch": 2.9,
|
|
"learning_rate": 0.00040348922824400197,
|
|
"loss": 1.7564,
|
|
"step": 9310
|
|
},
|
|
{
|
|
"epoch": 2.9,
|
|
"learning_rate": 0.0004032962657689845,
|
|
"loss": 1.6491,
|
|
"step": 9320
|
|
},
|
|
{
|
|
"epoch": 2.9,
|
|
"learning_rate": 0.0004031031568270495,
|
|
"loss": 1.6838,
|
|
"step": 9330
|
|
},
|
|
{
|
|
"epoch": 2.91,
|
|
"learning_rate": 0.0004029099016027029,
|
|
"loss": 1.7136,
|
|
"step": 9340
|
|
},
|
|
{
|
|
"epoch": 2.91,
|
|
"learning_rate": 0.00040271650028059035,
|
|
"loss": 1.553,
|
|
"step": 9350
|
|
},
|
|
{
|
|
"epoch": 2.91,
|
|
"learning_rate": 0.00040252295304549733,
|
|
"loss": 1.7111,
|
|
"step": 9360
|
|
},
|
|
{
|
|
"epoch": 2.92,
|
|
"learning_rate": 0.00040232926008234833,
|
|
"loss": 1.6083,
|
|
"step": 9370
|
|
},
|
|
{
|
|
"epoch": 2.92,
|
|
"learning_rate": 0.0004021354215762074,
|
|
"loss": 1.645,
|
|
"step": 9380
|
|
},
|
|
{
|
|
"epoch": 2.92,
|
|
"learning_rate": 0.0004019414377122776,
|
|
"loss": 1.6572,
|
|
"step": 9390
|
|
},
|
|
{
|
|
"epoch": 2.92,
|
|
"learning_rate": 0.00040174730867590064,
|
|
"loss": 1.6857,
|
|
"step": 9400
|
|
},
|
|
{
|
|
"epoch": 2.93,
|
|
"learning_rate": 0.0004015530346525572,
|
|
"loss": 1.6076,
|
|
"step": 9410
|
|
},
|
|
{
|
|
"epoch": 2.93,
|
|
"learning_rate": 0.0004013586158278665,
|
|
"loss": 1.6349,
|
|
"step": 9420
|
|
},
|
|
{
|
|
"epoch": 2.93,
|
|
"learning_rate": 0.00040116405238758583,
|
|
"loss": 1.6281,
|
|
"step": 9430
|
|
},
|
|
{
|
|
"epoch": 2.94,
|
|
"learning_rate": 0.00040096934451761104,
|
|
"loss": 1.6824,
|
|
"step": 9440
|
|
},
|
|
{
|
|
"epoch": 2.94,
|
|
"learning_rate": 0.0004007744924039755,
|
|
"loss": 1.6164,
|
|
"step": 9450
|
|
},
|
|
{
|
|
"epoch": 2.94,
|
|
"learning_rate": 0.00040057949623285085,
|
|
"loss": 1.6341,
|
|
"step": 9460
|
|
},
|
|
{
|
|
"epoch": 2.95,
|
|
"learning_rate": 0.00040038435619054613,
|
|
"loss": 1.6749,
|
|
"step": 9470
|
|
},
|
|
{
|
|
"epoch": 2.95,
|
|
"learning_rate": 0.00040018907246350786,
|
|
"loss": 1.6795,
|
|
"step": 9480
|
|
},
|
|
{
|
|
"epoch": 2.95,
|
|
"learning_rate": 0.00039999364523831993,
|
|
"loss": 1.6865,
|
|
"step": 9490
|
|
},
|
|
{
|
|
"epoch": 2.96,
|
|
"learning_rate": 0.00039979807470170325,
|
|
"loss": 1.6162,
|
|
"step": 9500
|
|
},
|
|
{
|
|
"epoch": 2.96,
|
|
"learning_rate": 0.0003996023610405157,
|
|
"loss": 1.7061,
|
|
"step": 9510
|
|
},
|
|
{
|
|
"epoch": 2.96,
|
|
"learning_rate": 0.000399406504441752,
|
|
"loss": 1.6719,
|
|
"step": 9520
|
|
},
|
|
{
|
|
"epoch": 2.96,
|
|
"learning_rate": 0.0003992105050925431,
|
|
"loss": 1.5946,
|
|
"step": 9530
|
|
},
|
|
{
|
|
"epoch": 2.97,
|
|
"learning_rate": 0.00039901436318015685,
|
|
"loss": 1.6041,
|
|
"step": 9540
|
|
},
|
|
{
|
|
"epoch": 2.97,
|
|
"learning_rate": 0.0003988180788919968,
|
|
"loss": 1.6945,
|
|
"step": 9550
|
|
},
|
|
{
|
|
"epoch": 2.97,
|
|
"learning_rate": 0.00039862165241560287,
|
|
"loss": 1.6002,
|
|
"step": 9560
|
|
},
|
|
{
|
|
"epoch": 2.98,
|
|
"learning_rate": 0.00039842508393865084,
|
|
"loss": 1.6392,
|
|
"step": 9570
|
|
},
|
|
{
|
|
"epoch": 2.98,
|
|
"learning_rate": 0.00039822837364895193,
|
|
"loss": 1.5827,
|
|
"step": 9580
|
|
},
|
|
{
|
|
"epoch": 2.98,
|
|
"learning_rate": 0.00039803152173445303,
|
|
"loss": 1.7386,
|
|
"step": 9590
|
|
},
|
|
{
|
|
"epoch": 2.99,
|
|
"learning_rate": 0.0003978345283832363,
|
|
"loss": 1.6798,
|
|
"step": 9600
|
|
},
|
|
{
|
|
"epoch": 2.99,
|
|
"learning_rate": 0.00039763739378351903,
|
|
"loss": 1.5784,
|
|
"step": 9610
|
|
},
|
|
{
|
|
"epoch": 2.99,
|
|
"learning_rate": 0.00039744011812365353,
|
|
"loss": 1.7054,
|
|
"step": 9620
|
|
},
|
|
{
|
|
"epoch": 3.0,
|
|
"learning_rate": 0.0003972427015921267,
|
|
"loss": 1.7326,
|
|
"step": 9630
|
|
},
|
|
{
|
|
"epoch": 3.0,
|
|
"learning_rate": 0.00039704514437756037,
|
|
"loss": 1.6946,
|
|
"step": 9640
|
|
},
|
|
{
|
|
"epoch": 3.0,
|
|
"learning_rate": 0.00039684744666871035,
|
|
"loss": 1.5495,
|
|
"step": 9650
|
|
},
|
|
{
|
|
"epoch": 3.01,
|
|
"learning_rate": 0.0003966496086544671,
|
|
"loss": 1.4663,
|
|
"step": 9660
|
|
},
|
|
{
|
|
"epoch": 3.01,
|
|
"learning_rate": 0.0003964516305238548,
|
|
"loss": 1.4592,
|
|
"step": 9670
|
|
},
|
|
{
|
|
"epoch": 3.01,
|
|
"learning_rate": 0.0003962535124660318,
|
|
"loss": 1.3916,
|
|
"step": 9680
|
|
},
|
|
{
|
|
"epoch": 3.01,
|
|
"learning_rate": 0.0003960552546702899,
|
|
"loss": 1.4646,
|
|
"step": 9690
|
|
},
|
|
{
|
|
"epoch": 3.02,
|
|
"learning_rate": 0.00039585685732605454,
|
|
"loss": 1.4788,
|
|
"step": 9700
|
|
},
|
|
{
|
|
"epoch": 3.02,
|
|
"learning_rate": 0.00039565832062288443,
|
|
"loss": 1.6099,
|
|
"step": 9710
|
|
},
|
|
{
|
|
"epoch": 3.02,
|
|
"learning_rate": 0.00039545964475047157,
|
|
"loss": 1.5089,
|
|
"step": 9720
|
|
},
|
|
{
|
|
"epoch": 3.03,
|
|
"learning_rate": 0.00039526082989864073,
|
|
"loss": 1.5463,
|
|
"step": 9730
|
|
},
|
|
{
|
|
"epoch": 3.03,
|
|
"learning_rate": 0.00039506187625734955,
|
|
"loss": 1.557,
|
|
"step": 9740
|
|
},
|
|
{
|
|
"epoch": 3.03,
|
|
"learning_rate": 0.0003948627840166884,
|
|
"loss": 1.4348,
|
|
"step": 9750
|
|
},
|
|
{
|
|
"epoch": 3.04,
|
|
"learning_rate": 0.0003946635533668798,
|
|
"loss": 1.556,
|
|
"step": 9760
|
|
},
|
|
{
|
|
"epoch": 3.04,
|
|
"learning_rate": 0.00039446418449827877,
|
|
"loss": 1.5531,
|
|
"step": 9770
|
|
},
|
|
{
|
|
"epoch": 3.04,
|
|
"learning_rate": 0.0003942646776013723,
|
|
"loss": 1.5718,
|
|
"step": 9780
|
|
},
|
|
{
|
|
"epoch": 3.05,
|
|
"learning_rate": 0.0003940650328667792,
|
|
"loss": 1.5025,
|
|
"step": 9790
|
|
},
|
|
{
|
|
"epoch": 3.05,
|
|
"learning_rate": 0.00039386525048525013,
|
|
"loss": 1.492,
|
|
"step": 9800
|
|
},
|
|
{
|
|
"epoch": 3.05,
|
|
"learning_rate": 0.0003936653306476671,
|
|
"loss": 1.4639,
|
|
"step": 9810
|
|
},
|
|
{
|
|
"epoch": 3.06,
|
|
"learning_rate": 0.00039346527354504346,
|
|
"loss": 1.5359,
|
|
"step": 9820
|
|
},
|
|
{
|
|
"epoch": 3.06,
|
|
"learning_rate": 0.0003932650793685239,
|
|
"loss": 1.4742,
|
|
"step": 9830
|
|
},
|
|
{
|
|
"epoch": 3.06,
|
|
"learning_rate": 0.0003930647483093839,
|
|
"loss": 1.546,
|
|
"step": 9840
|
|
},
|
|
{
|
|
"epoch": 3.06,
|
|
"learning_rate": 0.00039286428055902966,
|
|
"loss": 1.5213,
|
|
"step": 9850
|
|
},
|
|
{
|
|
"epoch": 3.07,
|
|
"learning_rate": 0.00039266367630899824,
|
|
"loss": 1.4893,
|
|
"step": 9860
|
|
},
|
|
{
|
|
"epoch": 3.07,
|
|
"learning_rate": 0.0003924629357509569,
|
|
"loss": 1.5304,
|
|
"step": 9870
|
|
},
|
|
{
|
|
"epoch": 3.07,
|
|
"learning_rate": 0.0003922620590767033,
|
|
"loss": 1.3787,
|
|
"step": 9880
|
|
},
|
|
{
|
|
"epoch": 3.08,
|
|
"learning_rate": 0.0003920610464781649,
|
|
"loss": 1.4978,
|
|
"step": 9890
|
|
},
|
|
{
|
|
"epoch": 3.08,
|
|
"learning_rate": 0.0003918598981473993,
|
|
"loss": 1.6318,
|
|
"step": 9900
|
|
},
|
|
{
|
|
"epoch": 3.08,
|
|
"learning_rate": 0.00039165861427659364,
|
|
"loss": 1.5803,
|
|
"step": 9910
|
|
},
|
|
{
|
|
"epoch": 3.09,
|
|
"learning_rate": 0.0003914571950580646,
|
|
"loss": 1.4688,
|
|
"step": 9920
|
|
},
|
|
{
|
|
"epoch": 3.09,
|
|
"learning_rate": 0.00039125564068425816,
|
|
"loss": 1.5946,
|
|
"step": 9930
|
|
},
|
|
{
|
|
"epoch": 3.09,
|
|
"learning_rate": 0.0003910539513477495,
|
|
"loss": 1.5052,
|
|
"step": 9940
|
|
},
|
|
{
|
|
"epoch": 3.1,
|
|
"learning_rate": 0.00039085212724124257,
|
|
"loss": 1.4879,
|
|
"step": 9950
|
|
},
|
|
{
|
|
"epoch": 3.1,
|
|
"learning_rate": 0.0003906501685575704,
|
|
"loss": 1.6032,
|
|
"step": 9960
|
|
},
|
|
{
|
|
"epoch": 3.1,
|
|
"learning_rate": 0.00039044807548969425,
|
|
"loss": 1.5124,
|
|
"step": 9970
|
|
},
|
|
{
|
|
"epoch": 3.1,
|
|
"learning_rate": 0.000390245848230704,
|
|
"loss": 1.4945,
|
|
"step": 9980
|
|
},
|
|
{
|
|
"epoch": 3.11,
|
|
"learning_rate": 0.00039004348697381774,
|
|
"loss": 1.4955,
|
|
"step": 9990
|
|
},
|
|
{
|
|
"epoch": 3.11,
|
|
"learning_rate": 0.0003898409919123814,
|
|
"loss": 1.5849,
|
|
"step": 10000
|
|
},
|
|
{
|
|
"epoch": 3.11,
|
|
"learning_rate": 0.00038963836323986905,
|
|
"loss": 1.5095,
|
|
"step": 10010
|
|
},
|
|
{
|
|
"epoch": 3.12,
|
|
"learning_rate": 0.00038943560114988214,
|
|
"loss": 1.5413,
|
|
"step": 10020
|
|
},
|
|
{
|
|
"epoch": 3.12,
|
|
"learning_rate": 0.00038923270583614977,
|
|
"loss": 1.497,
|
|
"step": 10030
|
|
},
|
|
{
|
|
"epoch": 3.12,
|
|
"learning_rate": 0.00038902967749252827,
|
|
"loss": 1.4986,
|
|
"step": 10040
|
|
},
|
|
{
|
|
"epoch": 3.13,
|
|
"learning_rate": 0.0003888265163130009,
|
|
"loss": 1.5852,
|
|
"step": 10050
|
|
},
|
|
{
|
|
"epoch": 3.13,
|
|
"learning_rate": 0.00038862322249167834,
|
|
"loss": 1.6439,
|
|
"step": 10060
|
|
},
|
|
{
|
|
"epoch": 3.13,
|
|
"learning_rate": 0.0003884197962227974,
|
|
"loss": 1.4993,
|
|
"step": 10070
|
|
},
|
|
{
|
|
"epoch": 3.14,
|
|
"learning_rate": 0.0003882162377007218,
|
|
"loss": 1.4263,
|
|
"step": 10080
|
|
},
|
|
{
|
|
"epoch": 3.14,
|
|
"learning_rate": 0.0003880125471199415,
|
|
"loss": 1.5004,
|
|
"step": 10090
|
|
},
|
|
{
|
|
"epoch": 3.14,
|
|
"learning_rate": 0.0003878087246750728,
|
|
"loss": 1.5558,
|
|
"step": 10100
|
|
},
|
|
{
|
|
"epoch": 3.15,
|
|
"learning_rate": 0.00038760477056085763,
|
|
"loss": 1.4298,
|
|
"step": 10110
|
|
},
|
|
{
|
|
"epoch": 3.15,
|
|
"learning_rate": 0.0003874006849721641,
|
|
"loss": 1.5326,
|
|
"step": 10120
|
|
},
|
|
{
|
|
"epoch": 3.15,
|
|
"learning_rate": 0.0003871964681039858,
|
|
"loss": 1.5704,
|
|
"step": 10130
|
|
},
|
|
{
|
|
"epoch": 3.15,
|
|
"learning_rate": 0.00038699212015144165,
|
|
"loss": 1.5477,
|
|
"step": 10140
|
|
},
|
|
{
|
|
"epoch": 3.16,
|
|
"learning_rate": 0.0003867876413097759,
|
|
"loss": 1.5744,
|
|
"step": 10150
|
|
},
|
|
{
|
|
"epoch": 3.16,
|
|
"learning_rate": 0.00038658303177435796,
|
|
"loss": 1.4123,
|
|
"step": 10160
|
|
},
|
|
{
|
|
"epoch": 3.16,
|
|
"learning_rate": 0.00038637829174068195,
|
|
"loss": 1.533,
|
|
"step": 10170
|
|
},
|
|
{
|
|
"epoch": 3.17,
|
|
"learning_rate": 0.0003861734214043667,
|
|
"loss": 1.6009,
|
|
"step": 10180
|
|
},
|
|
{
|
|
"epoch": 3.17,
|
|
"learning_rate": 0.0003859684209611557,
|
|
"loss": 1.5344,
|
|
"step": 10190
|
|
},
|
|
{
|
|
"epoch": 3.17,
|
|
"learning_rate": 0.0003857632906069165,
|
|
"loss": 1.3245,
|
|
"step": 10200
|
|
},
|
|
{
|
|
"epoch": 3.18,
|
|
"learning_rate": 0.00038555803053764087,
|
|
"loss": 1.6431,
|
|
"step": 10210
|
|
},
|
|
{
|
|
"epoch": 3.18,
|
|
"learning_rate": 0.00038535264094944466,
|
|
"loss": 1.5669,
|
|
"step": 10220
|
|
},
|
|
{
|
|
"epoch": 3.18,
|
|
"learning_rate": 0.00038514712203856726,
|
|
"loss": 1.5995,
|
|
"step": 10230
|
|
},
|
|
{
|
|
"epoch": 3.19,
|
|
"learning_rate": 0.0003849414740013718,
|
|
"loss": 1.4524,
|
|
"step": 10240
|
|
},
|
|
{
|
|
"epoch": 3.19,
|
|
"learning_rate": 0.0003847356970343446,
|
|
"loss": 1.5412,
|
|
"step": 10250
|
|
},
|
|
{
|
|
"epoch": 3.19,
|
|
"learning_rate": 0.00038452979133409536,
|
|
"loss": 1.5279,
|
|
"step": 10260
|
|
},
|
|
{
|
|
"epoch": 3.2,
|
|
"learning_rate": 0.00038432375709735665,
|
|
"loss": 1.5043,
|
|
"step": 10270
|
|
},
|
|
{
|
|
"epoch": 3.2,
|
|
"learning_rate": 0.0003841175945209839,
|
|
"loss": 1.4546,
|
|
"step": 10280
|
|
},
|
|
{
|
|
"epoch": 3.2,
|
|
"learning_rate": 0.0003839113038019551,
|
|
"loss": 1.6715,
|
|
"step": 10290
|
|
},
|
|
{
|
|
"epoch": 3.2,
|
|
"learning_rate": 0.00038370488513737064,
|
|
"loss": 1.5198,
|
|
"step": 10300
|
|
},
|
|
{
|
|
"epoch": 3.21,
|
|
"learning_rate": 0.0003834983387244534,
|
|
"loss": 1.546,
|
|
"step": 10310
|
|
},
|
|
{
|
|
"epoch": 3.21,
|
|
"learning_rate": 0.000383291664760548,
|
|
"loss": 1.5489,
|
|
"step": 10320
|
|
},
|
|
{
|
|
"epoch": 3.21,
|
|
"learning_rate": 0.00038308486344312126,
|
|
"loss": 1.4662,
|
|
"step": 10330
|
|
},
|
|
{
|
|
"epoch": 3.22,
|
|
"learning_rate": 0.00038287793496976134,
|
|
"loss": 1.5104,
|
|
"step": 10340
|
|
},
|
|
{
|
|
"epoch": 3.22,
|
|
"learning_rate": 0.0003826708795381781,
|
|
"loss": 1.5669,
|
|
"step": 10350
|
|
},
|
|
{
|
|
"epoch": 3.22,
|
|
"learning_rate": 0.0003824636973462027,
|
|
"loss": 1.5804,
|
|
"step": 10360
|
|
},
|
|
{
|
|
"epoch": 3.23,
|
|
"learning_rate": 0.00038225638859178725,
|
|
"loss": 1.5564,
|
|
"step": 10370
|
|
},
|
|
{
|
|
"epoch": 3.23,
|
|
"learning_rate": 0.000382048953473005,
|
|
"loss": 1.5173,
|
|
"step": 10380
|
|
},
|
|
{
|
|
"epoch": 3.23,
|
|
"learning_rate": 0.0003818413921880498,
|
|
"loss": 1.6542,
|
|
"step": 10390
|
|
},
|
|
{
|
|
"epoch": 3.24,
|
|
"learning_rate": 0.00038163370493523614,
|
|
"loss": 1.5069,
|
|
"step": 10400
|
|
},
|
|
{
|
|
"epoch": 3.24,
|
|
"learning_rate": 0.0003814258919129987,
|
|
"loss": 1.6282,
|
|
"step": 10410
|
|
},
|
|
{
|
|
"epoch": 3.24,
|
|
"learning_rate": 0.0003812179533198926,
|
|
"loss": 1.4525,
|
|
"step": 10420
|
|
},
|
|
{
|
|
"epoch": 3.24,
|
|
"learning_rate": 0.0003810098893545926,
|
|
"loss": 1.5132,
|
|
"step": 10430
|
|
},
|
|
{
|
|
"epoch": 3.25,
|
|
"learning_rate": 0.0003808017002158934,
|
|
"loss": 1.5797,
|
|
"step": 10440
|
|
},
|
|
{
|
|
"epoch": 3.25,
|
|
"learning_rate": 0.00038059338610270946,
|
|
"loss": 1.4396,
|
|
"step": 10450
|
|
},
|
|
{
|
|
"epoch": 3.25,
|
|
"learning_rate": 0.00038038494721407437,
|
|
"loss": 1.5515,
|
|
"step": 10460
|
|
},
|
|
{
|
|
"epoch": 3.26,
|
|
"learning_rate": 0.0003801763837491411,
|
|
"loss": 1.5756,
|
|
"step": 10470
|
|
},
|
|
{
|
|
"epoch": 3.26,
|
|
"learning_rate": 0.0003799676959071817,
|
|
"loss": 1.5012,
|
|
"step": 10480
|
|
},
|
|
{
|
|
"epoch": 3.26,
|
|
"learning_rate": 0.00037975888388758693,
|
|
"loss": 1.3617,
|
|
"step": 10490
|
|
},
|
|
{
|
|
"epoch": 3.27,
|
|
"learning_rate": 0.00037954994788986607,
|
|
"loss": 1.5157,
|
|
"step": 10500
|
|
},
|
|
{
|
|
"epoch": 3.27,
|
|
"learning_rate": 0.00037934088811364733,
|
|
"loss": 1.6242,
|
|
"step": 10510
|
|
},
|
|
{
|
|
"epoch": 3.27,
|
|
"learning_rate": 0.00037913170475867666,
|
|
"loss": 1.6129,
|
|
"step": 10520
|
|
},
|
|
{
|
|
"epoch": 3.28,
|
|
"learning_rate": 0.0003789223980248182,
|
|
"loss": 1.4664,
|
|
"step": 10530
|
|
},
|
|
{
|
|
"epoch": 3.28,
|
|
"learning_rate": 0.00037871296811205435,
|
|
"loss": 1.5835,
|
|
"step": 10540
|
|
},
|
|
{
|
|
"epoch": 3.28,
|
|
"learning_rate": 0.0003785034152204848,
|
|
"loss": 1.4849,
|
|
"step": 10550
|
|
},
|
|
{
|
|
"epoch": 3.29,
|
|
"learning_rate": 0.00037829373955032677,
|
|
"loss": 1.5231,
|
|
"step": 10560
|
|
},
|
|
{
|
|
"epoch": 3.29,
|
|
"learning_rate": 0.00037808394130191497,
|
|
"loss": 1.5915,
|
|
"step": 10570
|
|
},
|
|
{
|
|
"epoch": 3.29,
|
|
"learning_rate": 0.0003778740206757011,
|
|
"loss": 1.3772,
|
|
"step": 10580
|
|
},
|
|
{
|
|
"epoch": 3.29,
|
|
"learning_rate": 0.0003776639778722539,
|
|
"loss": 1.562,
|
|
"step": 10590
|
|
},
|
|
{
|
|
"epoch": 3.3,
|
|
"learning_rate": 0.00037745381309225865,
|
|
"loss": 1.4732,
|
|
"step": 10600
|
|
},
|
|
{
|
|
"epoch": 3.3,
|
|
"learning_rate": 0.0003772435265365174,
|
|
"loss": 1.5909,
|
|
"step": 10610
|
|
},
|
|
{
|
|
"epoch": 3.3,
|
|
"learning_rate": 0.00037703311840594833,
|
|
"loss": 1.5539,
|
|
"step": 10620
|
|
},
|
|
{
|
|
"epoch": 3.31,
|
|
"learning_rate": 0.00037682258890158593,
|
|
"loss": 1.5168,
|
|
"step": 10630
|
|
},
|
|
{
|
|
"epoch": 3.31,
|
|
"learning_rate": 0.0003766119382245807,
|
|
"loss": 1.5071,
|
|
"step": 10640
|
|
},
|
|
{
|
|
"epoch": 3.31,
|
|
"learning_rate": 0.0003764011665761987,
|
|
"loss": 1.5776,
|
|
"step": 10650
|
|
},
|
|
{
|
|
"epoch": 3.32,
|
|
"learning_rate": 0.0003761902741578218,
|
|
"loss": 1.542,
|
|
"step": 10660
|
|
},
|
|
{
|
|
"epoch": 3.32,
|
|
"learning_rate": 0.00037597926117094715,
|
|
"loss": 1.5513,
|
|
"step": 10670
|
|
},
|
|
{
|
|
"epoch": 3.32,
|
|
"learning_rate": 0.0003757681278171871,
|
|
"loss": 1.5653,
|
|
"step": 10680
|
|
},
|
|
{
|
|
"epoch": 3.33,
|
|
"learning_rate": 0.0003755568742982689,
|
|
"loss": 1.5879,
|
|
"step": 10690
|
|
},
|
|
{
|
|
"epoch": 3.33,
|
|
"learning_rate": 0.00037534550081603493,
|
|
"loss": 1.6391,
|
|
"step": 10700
|
|
},
|
|
{
|
|
"epoch": 3.33,
|
|
"learning_rate": 0.00037513400757244175,
|
|
"loss": 1.5984,
|
|
"step": 10710
|
|
},
|
|
{
|
|
"epoch": 3.34,
|
|
"learning_rate": 0.0003749223947695608,
|
|
"loss": 1.5419,
|
|
"step": 10720
|
|
},
|
|
{
|
|
"epoch": 3.34,
|
|
"learning_rate": 0.00037471066260957744,
|
|
"loss": 1.5344,
|
|
"step": 10730
|
|
},
|
|
{
|
|
"epoch": 3.34,
|
|
"learning_rate": 0.00037449881129479113,
|
|
"loss": 1.564,
|
|
"step": 10740
|
|
},
|
|
{
|
|
"epoch": 3.34,
|
|
"learning_rate": 0.00037428684102761527,
|
|
"loss": 1.4002,
|
|
"step": 10750
|
|
},
|
|
{
|
|
"epoch": 3.35,
|
|
"learning_rate": 0.00037407475201057676,
|
|
"loss": 1.6283,
|
|
"step": 10760
|
|
},
|
|
{
|
|
"epoch": 3.35,
|
|
"learning_rate": 0.00037386254444631624,
|
|
"loss": 1.5262,
|
|
"step": 10770
|
|
},
|
|
{
|
|
"epoch": 3.35,
|
|
"learning_rate": 0.00037365021853758717,
|
|
"loss": 1.5495,
|
|
"step": 10780
|
|
},
|
|
{
|
|
"epoch": 3.36,
|
|
"learning_rate": 0.0003734377744872565,
|
|
"loss": 1.5597,
|
|
"step": 10790
|
|
},
|
|
{
|
|
"epoch": 3.36,
|
|
"learning_rate": 0.000373225212498304,
|
|
"loss": 1.4976,
|
|
"step": 10800
|
|
},
|
|
{
|
|
"epoch": 3.36,
|
|
"learning_rate": 0.00037301253277382174,
|
|
"loss": 1.6466,
|
|
"step": 10810
|
|
},
|
|
{
|
|
"epoch": 3.37,
|
|
"learning_rate": 0.00037279973551701485,
|
|
"loss": 1.6416,
|
|
"step": 10820
|
|
},
|
|
{
|
|
"epoch": 3.37,
|
|
"learning_rate": 0.00037258682093120024,
|
|
"loss": 1.7664,
|
|
"step": 10830
|
|
},
|
|
{
|
|
"epoch": 3.37,
|
|
"learning_rate": 0.00037237378921980724,
|
|
"loss": 1.5381,
|
|
"step": 10840
|
|
},
|
|
{
|
|
"epoch": 3.38,
|
|
"learning_rate": 0.0003721606405863771,
|
|
"loss": 1.5454,
|
|
"step": 10850
|
|
},
|
|
{
|
|
"epoch": 3.38,
|
|
"learning_rate": 0.00037194737523456247,
|
|
"loss": 1.6505,
|
|
"step": 10860
|
|
},
|
|
{
|
|
"epoch": 3.38,
|
|
"learning_rate": 0.00037173399336812795,
|
|
"loss": 1.5572,
|
|
"step": 10870
|
|
},
|
|
{
|
|
"epoch": 3.38,
|
|
"learning_rate": 0.00037152049519094914,
|
|
"loss": 1.6156,
|
|
"step": 10880
|
|
},
|
|
{
|
|
"epoch": 3.39,
|
|
"learning_rate": 0.0003713068809070129,
|
|
"loss": 1.5494,
|
|
"step": 10890
|
|
},
|
|
{
|
|
"epoch": 3.39,
|
|
"learning_rate": 0.0003710931507204169,
|
|
"loss": 1.5541,
|
|
"step": 10900
|
|
},
|
|
{
|
|
"epoch": 3.39,
|
|
"learning_rate": 0.00037087930483536974,
|
|
"loss": 1.5523,
|
|
"step": 10910
|
|
},
|
|
{
|
|
"epoch": 3.4,
|
|
"learning_rate": 0.0003706653434561905,
|
|
"loss": 1.6494,
|
|
"step": 10920
|
|
},
|
|
{
|
|
"epoch": 3.4,
|
|
"learning_rate": 0.0003704512667873085,
|
|
"loss": 1.4959,
|
|
"step": 10930
|
|
},
|
|
{
|
|
"epoch": 3.4,
|
|
"learning_rate": 0.00037023707503326344,
|
|
"loss": 1.6128,
|
|
"step": 10940
|
|
},
|
|
{
|
|
"epoch": 3.41,
|
|
"learning_rate": 0.00037002276839870465,
|
|
"loss": 1.6016,
|
|
"step": 10950
|
|
},
|
|
{
|
|
"epoch": 3.41,
|
|
"learning_rate": 0.00036980834708839146,
|
|
"loss": 1.5113,
|
|
"step": 10960
|
|
},
|
|
{
|
|
"epoch": 3.41,
|
|
"learning_rate": 0.00036959381130719274,
|
|
"loss": 1.5841,
|
|
"step": 10970
|
|
},
|
|
{
|
|
"epoch": 3.42,
|
|
"learning_rate": 0.00036937916126008664,
|
|
"loss": 1.592,
|
|
"step": 10980
|
|
},
|
|
{
|
|
"epoch": 3.42,
|
|
"learning_rate": 0.00036916439715216066,
|
|
"loss": 1.5937,
|
|
"step": 10990
|
|
},
|
|
{
|
|
"epoch": 3.42,
|
|
"learning_rate": 0.0003689495191886111,
|
|
"loss": 1.613,
|
|
"step": 11000
|
|
},
|
|
{
|
|
"epoch": 3.43,
|
|
"learning_rate": 0.0003687345275747432,
|
|
"loss": 1.4872,
|
|
"step": 11010
|
|
},
|
|
{
|
|
"epoch": 3.43,
|
|
"learning_rate": 0.0003685194225159705,
|
|
"loss": 1.5947,
|
|
"step": 11020
|
|
},
|
|
{
|
|
"epoch": 3.43,
|
|
"learning_rate": 0.0003683042042178153,
|
|
"loss": 1.5622,
|
|
"step": 11030
|
|
},
|
|
{
|
|
"epoch": 3.43,
|
|
"learning_rate": 0.00036808887288590785,
|
|
"loss": 1.5363,
|
|
"step": 11040
|
|
},
|
|
{
|
|
"epoch": 3.44,
|
|
"learning_rate": 0.0003678734287259865,
|
|
"loss": 1.5554,
|
|
"step": 11050
|
|
},
|
|
{
|
|
"epoch": 3.44,
|
|
"learning_rate": 0.00036765787194389737,
|
|
"loss": 1.621,
|
|
"step": 11060
|
|
},
|
|
{
|
|
"epoch": 3.44,
|
|
"learning_rate": 0.00036744220274559413,
|
|
"loss": 1.544,
|
|
"step": 11070
|
|
},
|
|
{
|
|
"epoch": 3.45,
|
|
"learning_rate": 0.00036722642133713815,
|
|
"loss": 1.57,
|
|
"step": 11080
|
|
},
|
|
{
|
|
"epoch": 3.45,
|
|
"learning_rate": 0.00036701052792469736,
|
|
"loss": 1.6605,
|
|
"step": 11090
|
|
},
|
|
{
|
|
"epoch": 3.45,
|
|
"learning_rate": 0.0003667945227145475,
|
|
"loss": 1.573,
|
|
"step": 11100
|
|
},
|
|
{
|
|
"epoch": 3.46,
|
|
"learning_rate": 0.00036657840591307057,
|
|
"loss": 1.4672,
|
|
"step": 11110
|
|
},
|
|
{
|
|
"epoch": 3.46,
|
|
"learning_rate": 0.00036636217772675536,
|
|
"loss": 1.5387,
|
|
"step": 11120
|
|
},
|
|
{
|
|
"epoch": 3.46,
|
|
"learning_rate": 0.0003661458383621972,
|
|
"loss": 1.6112,
|
|
"step": 11130
|
|
},
|
|
{
|
|
"epoch": 3.47,
|
|
"learning_rate": 0.00036592938802609744,
|
|
"loss": 1.471,
|
|
"step": 11140
|
|
},
|
|
{
|
|
"epoch": 3.47,
|
|
"learning_rate": 0.00036571282692526364,
|
|
"loss": 1.5291,
|
|
"step": 11150
|
|
},
|
|
{
|
|
"epoch": 3.47,
|
|
"learning_rate": 0.00036549615526660896,
|
|
"loss": 1.6086,
|
|
"step": 11160
|
|
},
|
|
{
|
|
"epoch": 3.48,
|
|
"learning_rate": 0.0003652793732571525,
|
|
"loss": 1.5244,
|
|
"step": 11170
|
|
},
|
|
{
|
|
"epoch": 3.48,
|
|
"learning_rate": 0.00036506248110401853,
|
|
"loss": 1.6,
|
|
"step": 11180
|
|
},
|
|
{
|
|
"epoch": 3.48,
|
|
"learning_rate": 0.00036484547901443666,
|
|
"loss": 1.6261,
|
|
"step": 11190
|
|
},
|
|
{
|
|
"epoch": 3.48,
|
|
"learning_rate": 0.0003646283671957417,
|
|
"loss": 1.539,
|
|
"step": 11200
|
|
},
|
|
{
|
|
"epoch": 3.49,
|
|
"learning_rate": 0.00036441114585537284,
|
|
"loss": 1.5555,
|
|
"step": 11210
|
|
},
|
|
{
|
|
"epoch": 3.49,
|
|
"learning_rate": 0.0003641938152008745,
|
|
"loss": 1.4818,
|
|
"step": 11220
|
|
},
|
|
{
|
|
"epoch": 3.49,
|
|
"learning_rate": 0.00036397637543989506,
|
|
"loss": 1.5092,
|
|
"step": 11230
|
|
},
|
|
{
|
|
"epoch": 3.5,
|
|
"learning_rate": 0.00036375882678018733,
|
|
"loss": 1.6164,
|
|
"step": 11240
|
|
},
|
|
{
|
|
"epoch": 3.5,
|
|
"learning_rate": 0.00036354116942960836,
|
|
"loss": 1.5182,
|
|
"step": 11250
|
|
},
|
|
{
|
|
"epoch": 3.5,
|
|
"learning_rate": 0.0003633234035961187,
|
|
"loss": 1.6308,
|
|
"step": 11260
|
|
},
|
|
{
|
|
"epoch": 3.51,
|
|
"learning_rate": 0.00036310552948778284,
|
|
"loss": 1.5704,
|
|
"step": 11270
|
|
},
|
|
{
|
|
"epoch": 3.51,
|
|
"learning_rate": 0.0003628875473127685,
|
|
"loss": 1.611,
|
|
"step": 11280
|
|
},
|
|
{
|
|
"epoch": 3.51,
|
|
"learning_rate": 0.0003626694572793468,
|
|
"loss": 1.5092,
|
|
"step": 11290
|
|
},
|
|
{
|
|
"epoch": 3.52,
|
|
"learning_rate": 0.0003624512595958919,
|
|
"loss": 1.5603,
|
|
"step": 11300
|
|
},
|
|
{
|
|
"epoch": 3.52,
|
|
"learning_rate": 0.0003622329544708806,
|
|
"loss": 1.6439,
|
|
"step": 11310
|
|
},
|
|
{
|
|
"epoch": 3.52,
|
|
"learning_rate": 0.00036201454211289274,
|
|
"loss": 1.5465,
|
|
"step": 11320
|
|
},
|
|
{
|
|
"epoch": 3.52,
|
|
"learning_rate": 0.0003617960227306103,
|
|
"loss": 1.5306,
|
|
"step": 11330
|
|
},
|
|
{
|
|
"epoch": 3.53,
|
|
"learning_rate": 0.0003615773965328176,
|
|
"loss": 1.5054,
|
|
"step": 11340
|
|
},
|
|
{
|
|
"epoch": 3.53,
|
|
"learning_rate": 0.0003613586637284012,
|
|
"loss": 1.5649,
|
|
"step": 11350
|
|
},
|
|
{
|
|
"epoch": 3.53,
|
|
"learning_rate": 0.0003611398245263492,
|
|
"loss": 1.4901,
|
|
"step": 11360
|
|
},
|
|
{
|
|
"epoch": 3.54,
|
|
"learning_rate": 0.00036092087913575154,
|
|
"loss": 1.5677,
|
|
"step": 11370
|
|
},
|
|
{
|
|
"epoch": 3.54,
|
|
"learning_rate": 0.00036070182776579965,
|
|
"loss": 1.6236,
|
|
"step": 11380
|
|
},
|
|
{
|
|
"epoch": 3.54,
|
|
"learning_rate": 0.0003604826706257861,
|
|
"loss": 1.6349,
|
|
"step": 11390
|
|
},
|
|
{
|
|
"epoch": 3.55,
|
|
"learning_rate": 0.00036026340792510465,
|
|
"loss": 1.5497,
|
|
"step": 11400
|
|
},
|
|
{
|
|
"epoch": 3.55,
|
|
"learning_rate": 0.0003600440398732498,
|
|
"loss": 1.567,
|
|
"step": 11410
|
|
},
|
|
{
|
|
"epoch": 3.55,
|
|
"learning_rate": 0.00035982456667981675,
|
|
"loss": 1.5693,
|
|
"step": 11420
|
|
},
|
|
{
|
|
"epoch": 3.56,
|
|
"learning_rate": 0.0003596049885545012,
|
|
"loss": 1.5644,
|
|
"step": 11430
|
|
},
|
|
{
|
|
"epoch": 3.56,
|
|
"learning_rate": 0.000359385305707099,
|
|
"loss": 1.5497,
|
|
"step": 11440
|
|
},
|
|
{
|
|
"epoch": 3.56,
|
|
"learning_rate": 0.00035916551834750613,
|
|
"loss": 1.5784,
|
|
"step": 11450
|
|
},
|
|
{
|
|
"epoch": 3.57,
|
|
"learning_rate": 0.0003589456266857186,
|
|
"loss": 1.6417,
|
|
"step": 11460
|
|
},
|
|
{
|
|
"epoch": 3.57,
|
|
"learning_rate": 0.0003587256309318317,
|
|
"loss": 1.5024,
|
|
"step": 11470
|
|
},
|
|
{
|
|
"epoch": 3.57,
|
|
"learning_rate": 0.0003585055312960405,
|
|
"loss": 1.5518,
|
|
"step": 11480
|
|
},
|
|
{
|
|
"epoch": 3.57,
|
|
"learning_rate": 0.0003582853279886391,
|
|
"loss": 1.5342,
|
|
"step": 11490
|
|
},
|
|
{
|
|
"epoch": 3.58,
|
|
"learning_rate": 0.00035806502122002077,
|
|
"loss": 1.6007,
|
|
"step": 11500
|
|
},
|
|
{
|
|
"epoch": 3.58,
|
|
"learning_rate": 0.00035784461120067765,
|
|
"loss": 1.5577,
|
|
"step": 11510
|
|
},
|
|
{
|
|
"epoch": 3.58,
|
|
"learning_rate": 0.0003576240981412004,
|
|
"loss": 1.5048,
|
|
"step": 11520
|
|
},
|
|
{
|
|
"epoch": 3.59,
|
|
"learning_rate": 0.0003574034822522785,
|
|
"loss": 1.5128,
|
|
"step": 11530
|
|
},
|
|
{
|
|
"epoch": 3.59,
|
|
"learning_rate": 0.00035718276374469894,
|
|
"loss": 1.4782,
|
|
"step": 11540
|
|
},
|
|
{
|
|
"epoch": 3.59,
|
|
"learning_rate": 0.0003569619428293477,
|
|
"loss": 1.56,
|
|
"step": 11550
|
|
},
|
|
{
|
|
"epoch": 3.6,
|
|
"learning_rate": 0.0003567410197172078,
|
|
"loss": 1.6436,
|
|
"step": 11560
|
|
},
|
|
{
|
|
"epoch": 3.6,
|
|
"learning_rate": 0.00035651999461936036,
|
|
"loss": 1.6082,
|
|
"step": 11570
|
|
},
|
|
{
|
|
"epoch": 3.6,
|
|
"learning_rate": 0.0003562988677469837,
|
|
"loss": 1.6309,
|
|
"step": 11580
|
|
},
|
|
{
|
|
"epoch": 3.61,
|
|
"learning_rate": 0.0003560776393113537,
|
|
"loss": 1.4407,
|
|
"step": 11590
|
|
},
|
|
{
|
|
"epoch": 3.61,
|
|
"learning_rate": 0.00035585630952384285,
|
|
"loss": 1.7247,
|
|
"step": 11600
|
|
},
|
|
{
|
|
"epoch": 3.61,
|
|
"learning_rate": 0.0003556348785959208,
|
|
"loss": 1.5435,
|
|
"step": 11610
|
|
},
|
|
{
|
|
"epoch": 3.62,
|
|
"learning_rate": 0.0003554133467391538,
|
|
"loss": 1.6798,
|
|
"step": 11620
|
|
},
|
|
{
|
|
"epoch": 3.62,
|
|
"learning_rate": 0.0003551917141652043,
|
|
"loss": 1.5802,
|
|
"step": 11630
|
|
},
|
|
{
|
|
"epoch": 3.62,
|
|
"learning_rate": 0.00035496998108583124,
|
|
"loss": 1.605,
|
|
"step": 11640
|
|
},
|
|
{
|
|
"epoch": 3.62,
|
|
"learning_rate": 0.0003547481477128895,
|
|
"loss": 1.4892,
|
|
"step": 11650
|
|
},
|
|
{
|
|
"epoch": 3.63,
|
|
"learning_rate": 0.0003545262142583297,
|
|
"loss": 1.5403,
|
|
"step": 11660
|
|
},
|
|
{
|
|
"epoch": 3.63,
|
|
"learning_rate": 0.00035430418093419824,
|
|
"loss": 1.552,
|
|
"step": 11670
|
|
},
|
|
{
|
|
"epoch": 3.63,
|
|
"learning_rate": 0.00035408204795263685,
|
|
"loss": 1.5908,
|
|
"step": 11680
|
|
},
|
|
{
|
|
"epoch": 3.64,
|
|
"learning_rate": 0.0003538598155258825,
|
|
"loss": 1.6148,
|
|
"step": 11690
|
|
},
|
|
{
|
|
"epoch": 3.64,
|
|
"learning_rate": 0.00035363748386626706,
|
|
"loss": 1.5749,
|
|
"step": 11700
|
|
},
|
|
{
|
|
"epoch": 3.64,
|
|
"learning_rate": 0.00035341505318621736,
|
|
"loss": 1.6851,
|
|
"step": 11710
|
|
},
|
|
{
|
|
"epoch": 3.65,
|
|
"learning_rate": 0.00035319252369825496,
|
|
"loss": 1.4887,
|
|
"step": 11720
|
|
},
|
|
{
|
|
"epoch": 3.65,
|
|
"learning_rate": 0.0003529698956149954,
|
|
"loss": 1.5288,
|
|
"step": 11730
|
|
},
|
|
{
|
|
"epoch": 3.65,
|
|
"learning_rate": 0.0003527471691491489,
|
|
"loss": 1.572,
|
|
"step": 11740
|
|
},
|
|
{
|
|
"epoch": 3.66,
|
|
"learning_rate": 0.00035252434451351933,
|
|
"loss": 1.5058,
|
|
"step": 11750
|
|
},
|
|
{
|
|
"epoch": 3.66,
|
|
"learning_rate": 0.0003523014219210045,
|
|
"loss": 1.566,
|
|
"step": 11760
|
|
},
|
|
{
|
|
"epoch": 3.66,
|
|
"learning_rate": 0.0003520784015845958,
|
|
"loss": 1.5676,
|
|
"step": 11770
|
|
},
|
|
{
|
|
"epoch": 3.66,
|
|
"learning_rate": 0.00035187759988691147,
|
|
"loss": 1.5842,
|
|
"step": 11780
|
|
},
|
|
{
|
|
"epoch": 3.67,
|
|
"learning_rate": 0.00035165439442423006,
|
|
"loss": 1.5028,
|
|
"step": 11790
|
|
},
|
|
{
|
|
"epoch": 3.67,
|
|
"learning_rate": 0.0003514310918358573,
|
|
"loss": 1.4973,
|
|
"step": 11800
|
|
},
|
|
{
|
|
"epoch": 3.67,
|
|
"learning_rate": 0.00035120769233514757,
|
|
"loss": 1.6743,
|
|
"step": 11810
|
|
},
|
|
{
|
|
"epoch": 3.68,
|
|
"learning_rate": 0.00035098419613554795,
|
|
"loss": 1.6269,
|
|
"step": 11820
|
|
},
|
|
{
|
|
"epoch": 3.68,
|
|
"learning_rate": 0.0003507606034505978,
|
|
"loss": 1.673,
|
|
"step": 11830
|
|
},
|
|
{
|
|
"epoch": 3.68,
|
|
"learning_rate": 0.00035053691449392886,
|
|
"loss": 1.4514,
|
|
"step": 11840
|
|
},
|
|
{
|
|
"epoch": 3.69,
|
|
"learning_rate": 0.00035031312947926476,
|
|
"loss": 1.4201,
|
|
"step": 11850
|
|
},
|
|
{
|
|
"epoch": 3.69,
|
|
"learning_rate": 0.0003500892486204207,
|
|
"loss": 1.4854,
|
|
"step": 11860
|
|
},
|
|
{
|
|
"epoch": 3.69,
|
|
"learning_rate": 0.0003498652721313039,
|
|
"loss": 1.5756,
|
|
"step": 11870
|
|
},
|
|
{
|
|
"epoch": 3.7,
|
|
"learning_rate": 0.00034964120022591255,
|
|
"loss": 1.615,
|
|
"step": 11880
|
|
},
|
|
{
|
|
"epoch": 3.7,
|
|
"learning_rate": 0.0003494170331183361,
|
|
"loss": 1.6448,
|
|
"step": 11890
|
|
},
|
|
{
|
|
"epoch": 3.7,
|
|
"learning_rate": 0.00034919277102275526,
|
|
"loss": 1.4845,
|
|
"step": 11900
|
|
},
|
|
{
|
|
"epoch": 3.71,
|
|
"learning_rate": 0.000348968414153441,
|
|
"loss": 1.4864,
|
|
"step": 11910
|
|
},
|
|
{
|
|
"epoch": 3.71,
|
|
"learning_rate": 0.00034874396272475516,
|
|
"loss": 1.6102,
|
|
"step": 11920
|
|
},
|
|
{
|
|
"epoch": 3.71,
|
|
"learning_rate": 0.00034851941695114986,
|
|
"loss": 1.5423,
|
|
"step": 11930
|
|
},
|
|
{
|
|
"epoch": 3.71,
|
|
"learning_rate": 0.0003482947770471674,
|
|
"loss": 1.5472,
|
|
"step": 11940
|
|
},
|
|
{
|
|
"epoch": 3.72,
|
|
"learning_rate": 0.00034807004322744,
|
|
"loss": 1.5697,
|
|
"step": 11950
|
|
},
|
|
{
|
|
"epoch": 3.72,
|
|
"learning_rate": 0.0003478452157066895,
|
|
"loss": 1.6184,
|
|
"step": 11960
|
|
},
|
|
{
|
|
"epoch": 3.72,
|
|
"learning_rate": 0.0003476202946997274,
|
|
"loss": 1.6437,
|
|
"step": 11970
|
|
},
|
|
{
|
|
"epoch": 3.73,
|
|
"learning_rate": 0.00034739528042145447,
|
|
"loss": 1.5443,
|
|
"step": 11980
|
|
},
|
|
{
|
|
"epoch": 3.73,
|
|
"learning_rate": 0.0003471701730868606,
|
|
"loss": 1.6096,
|
|
"step": 11990
|
|
},
|
|
{
|
|
"epoch": 3.73,
|
|
"learning_rate": 0.0003469449729110246,
|
|
"loss": 1.6227,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"epoch": 3.74,
|
|
"learning_rate": 0.000346719680109114,
|
|
"loss": 1.5605,
|
|
"step": 12010
|
|
},
|
|
{
|
|
"epoch": 3.74,
|
|
"learning_rate": 0.00034649429489638474,
|
|
"loss": 1.6978,
|
|
"step": 12020
|
|
},
|
|
{
|
|
"epoch": 3.74,
|
|
"learning_rate": 0.00034626881748818115,
|
|
"loss": 1.5046,
|
|
"step": 12030
|
|
},
|
|
{
|
|
"epoch": 3.75,
|
|
"learning_rate": 0.0003460432480999358,
|
|
"loss": 1.601,
|
|
"step": 12040
|
|
},
|
|
{
|
|
"epoch": 3.75,
|
|
"learning_rate": 0.00034581758694716866,
|
|
"loss": 1.6148,
|
|
"step": 12050
|
|
},
|
|
{
|
|
"epoch": 3.75,
|
|
"learning_rate": 0.00034559183424548787,
|
|
"loss": 1.5932,
|
|
"step": 12060
|
|
},
|
|
{
|
|
"epoch": 3.76,
|
|
"learning_rate": 0.0003453659902105888,
|
|
"loss": 1.498,
|
|
"step": 12070
|
|
},
|
|
{
|
|
"epoch": 3.76,
|
|
"learning_rate": 0.0003451400550582541,
|
|
"loss": 1.5856,
|
|
"step": 12080
|
|
},
|
|
{
|
|
"epoch": 3.76,
|
|
"learning_rate": 0.00034491402900435354,
|
|
"loss": 1.6399,
|
|
"step": 12090
|
|
},
|
|
{
|
|
"epoch": 3.76,
|
|
"learning_rate": 0.00034468791226484373,
|
|
"loss": 1.631,
|
|
"step": 12100
|
|
},
|
|
{
|
|
"epoch": 3.77,
|
|
"learning_rate": 0.00034446170505576795,
|
|
"loss": 1.5986,
|
|
"step": 12110
|
|
},
|
|
{
|
|
"epoch": 3.77,
|
|
"learning_rate": 0.0003442354075932557,
|
|
"loss": 1.5666,
|
|
"step": 12120
|
|
},
|
|
{
|
|
"epoch": 3.77,
|
|
"learning_rate": 0.0003440090200935232,
|
|
"loss": 1.681,
|
|
"step": 12130
|
|
},
|
|
{
|
|
"epoch": 3.78,
|
|
"learning_rate": 0.00034378254277287205,
|
|
"loss": 1.4739,
|
|
"step": 12140
|
|
},
|
|
{
|
|
"epoch": 3.78,
|
|
"learning_rate": 0.00034355597584769014,
|
|
"loss": 1.6459,
|
|
"step": 12150
|
|
},
|
|
{
|
|
"epoch": 3.78,
|
|
"learning_rate": 0.000343329319534451,
|
|
"loss": 1.6171,
|
|
"step": 12160
|
|
},
|
|
{
|
|
"epoch": 3.79,
|
|
"learning_rate": 0.0003431025740497132,
|
|
"loss": 1.4488,
|
|
"step": 12170
|
|
},
|
|
{
|
|
"epoch": 3.79,
|
|
"learning_rate": 0.0003428757396101208,
|
|
"loss": 1.6936,
|
|
"step": 12180
|
|
},
|
|
{
|
|
"epoch": 3.79,
|
|
"learning_rate": 0.0003426488164324028,
|
|
"loss": 1.672,
|
|
"step": 12190
|
|
},
|
|
{
|
|
"epoch": 3.8,
|
|
"learning_rate": 0.00034242180473337275,
|
|
"loss": 1.5922,
|
|
"step": 12200
|
|
},
|
|
{
|
|
"epoch": 3.8,
|
|
"learning_rate": 0.0003421947047299292,
|
|
"loss": 1.5709,
|
|
"step": 12210
|
|
},
|
|
{
|
|
"epoch": 3.8,
|
|
"learning_rate": 0.00034196751663905477,
|
|
"loss": 1.5916,
|
|
"step": 12220
|
|
},
|
|
{
|
|
"epoch": 3.8,
|
|
"learning_rate": 0.00034174024067781637,
|
|
"loss": 1.5417,
|
|
"step": 12230
|
|
},
|
|
{
|
|
"epoch": 3.81,
|
|
"learning_rate": 0.00034151287706336473,
|
|
"loss": 1.5256,
|
|
"step": 12240
|
|
},
|
|
{
|
|
"epoch": 3.81,
|
|
"learning_rate": 0.0003412854260129345,
|
|
"loss": 1.4379,
|
|
"step": 12250
|
|
},
|
|
{
|
|
"epoch": 3.81,
|
|
"learning_rate": 0.00034105788774384374,
|
|
"loss": 1.5402,
|
|
"step": 12260
|
|
},
|
|
{
|
|
"epoch": 3.82,
|
|
"learning_rate": 0.0003408302624734938,
|
|
"loss": 1.6276,
|
|
"step": 12270
|
|
},
|
|
{
|
|
"epoch": 3.82,
|
|
"learning_rate": 0.00034060255041936944,
|
|
"loss": 1.5808,
|
|
"step": 12280
|
|
},
|
|
{
|
|
"epoch": 3.82,
|
|
"learning_rate": 0.00034039753555034814,
|
|
"loss": 1.6386,
|
|
"step": 12290
|
|
},
|
|
{
|
|
"epoch": 3.83,
|
|
"learning_rate": 0.00034016965920651894,
|
|
"loss": 1.5301,
|
|
"step": 12300
|
|
},
|
|
{
|
|
"epoch": 3.83,
|
|
"learning_rate": 0.0003399416967100886,
|
|
"loss": 1.5111,
|
|
"step": 12310
|
|
},
|
|
{
|
|
"epoch": 3.83,
|
|
"learning_rate": 0.00033971364827886397,
|
|
"loss": 1.5325,
|
|
"step": 12320
|
|
},
|
|
{
|
|
"epoch": 3.84,
|
|
"learning_rate": 0.0003394855141307338,
|
|
"loss": 1.6297,
|
|
"step": 12330
|
|
},
|
|
{
|
|
"epoch": 3.84,
|
|
"learning_rate": 0.00033925729448366893,
|
|
"loss": 1.5411,
|
|
"step": 12340
|
|
},
|
|
{
|
|
"epoch": 3.84,
|
|
"learning_rate": 0.0003390289895557218,
|
|
"loss": 1.6439,
|
|
"step": 12350
|
|
},
|
|
{
|
|
"epoch": 3.85,
|
|
"learning_rate": 0.0003388005995650264,
|
|
"loss": 1.7264,
|
|
"step": 12360
|
|
},
|
|
{
|
|
"epoch": 3.85,
|
|
"learning_rate": 0.0003385721247297978,
|
|
"loss": 1.5737,
|
|
"step": 12370
|
|
},
|
|
{
|
|
"epoch": 3.85,
|
|
"learning_rate": 0.00033834356526833253,
|
|
"loss": 1.6245,
|
|
"step": 12380
|
|
},
|
|
{
|
|
"epoch": 3.85,
|
|
"learning_rate": 0.0003381149213990076,
|
|
"loss": 1.5903,
|
|
"step": 12390
|
|
},
|
|
{
|
|
"epoch": 3.86,
|
|
"learning_rate": 0.0003378861933402807,
|
|
"loss": 1.7218,
|
|
"step": 12400
|
|
},
|
|
{
|
|
"epoch": 3.86,
|
|
"learning_rate": 0.0003376573813106902,
|
|
"loss": 1.4611,
|
|
"step": 12410
|
|
},
|
|
{
|
|
"epoch": 3.86,
|
|
"learning_rate": 0.00033742848552885445,
|
|
"loss": 1.5502,
|
|
"step": 12420
|
|
},
|
|
{
|
|
"epoch": 3.87,
|
|
"learning_rate": 0.000337199506213472,
|
|
"loss": 1.5395,
|
|
"step": 12430
|
|
},
|
|
{
|
|
"epoch": 3.87,
|
|
"learning_rate": 0.00033697044358332114,
|
|
"loss": 1.6033,
|
|
"step": 12440
|
|
},
|
|
{
|
|
"epoch": 3.87,
|
|
"learning_rate": 0.0003367412978572597,
|
|
"loss": 1.5053,
|
|
"step": 12450
|
|
},
|
|
{
|
|
"epoch": 3.88,
|
|
"learning_rate": 0.00033651206925422504,
|
|
"loss": 1.548,
|
|
"step": 12460
|
|
},
|
|
{
|
|
"epoch": 3.88,
|
|
"learning_rate": 0.0003362827579932335,
|
|
"loss": 1.5732,
|
|
"step": 12470
|
|
},
|
|
{
|
|
"epoch": 3.88,
|
|
"learning_rate": 0.0003360533642933807,
|
|
"loss": 1.6019,
|
|
"step": 12480
|
|
},
|
|
{
|
|
"epoch": 3.89,
|
|
"learning_rate": 0.0003358238883738407,
|
|
"loss": 1.565,
|
|
"step": 12490
|
|
},
|
|
{
|
|
"epoch": 3.89,
|
|
"learning_rate": 0.00033559433045386635,
|
|
"loss": 1.6462,
|
|
"step": 12500
|
|
},
|
|
{
|
|
"epoch": 3.89,
|
|
"learning_rate": 0.0003353646907527887,
|
|
"loss": 1.471,
|
|
"step": 12510
|
|
},
|
|
{
|
|
"epoch": 3.9,
|
|
"learning_rate": 0.0003351349694900171,
|
|
"loss": 1.6445,
|
|
"step": 12520
|
|
},
|
|
{
|
|
"epoch": 3.9,
|
|
"learning_rate": 0.00033490516688503865,
|
|
"loss": 1.5972,
|
|
"step": 12530
|
|
},
|
|
{
|
|
"epoch": 3.9,
|
|
"learning_rate": 0.00033467528315741824,
|
|
"loss": 1.4766,
|
|
"step": 12540
|
|
},
|
|
{
|
|
"epoch": 3.9,
|
|
"learning_rate": 0.00033444531852679836,
|
|
"loss": 1.5922,
|
|
"step": 12550
|
|
},
|
|
{
|
|
"epoch": 3.91,
|
|
"learning_rate": 0.00033421527321289866,
|
|
"loss": 1.6022,
|
|
"step": 12560
|
|
},
|
|
{
|
|
"epoch": 3.91,
|
|
"learning_rate": 0.000333985147435516,
|
|
"loss": 1.5141,
|
|
"step": 12570
|
|
},
|
|
{
|
|
"epoch": 3.91,
|
|
"learning_rate": 0.000333754941414524,
|
|
"loss": 1.4962,
|
|
"step": 12580
|
|
},
|
|
{
|
|
"epoch": 3.92,
|
|
"learning_rate": 0.00033352465536987293,
|
|
"loss": 1.5655,
|
|
"step": 12590
|
|
},
|
|
{
|
|
"epoch": 3.92,
|
|
"learning_rate": 0.0003332942895215897,
|
|
"loss": 1.465,
|
|
"step": 12600
|
|
},
|
|
{
|
|
"epoch": 3.92,
|
|
"learning_rate": 0.0003330638440897774,
|
|
"loss": 1.556,
|
|
"step": 12610
|
|
},
|
|
{
|
|
"epoch": 3.93,
|
|
"learning_rate": 0.000332833319294615,
|
|
"loss": 1.6355,
|
|
"step": 12620
|
|
},
|
|
{
|
|
"epoch": 3.93,
|
|
"learning_rate": 0.00033260271535635736,
|
|
"loss": 1.5577,
|
|
"step": 12630
|
|
},
|
|
{
|
|
"epoch": 3.93,
|
|
"learning_rate": 0.00033237203249533525,
|
|
"loss": 1.5799,
|
|
"step": 12640
|
|
},
|
|
{
|
|
"epoch": 3.94,
|
|
"learning_rate": 0.0003321412709319544,
|
|
"loss": 1.5626,
|
|
"step": 12650
|
|
},
|
|
{
|
|
"epoch": 3.94,
|
|
"learning_rate": 0.00033191043088669605,
|
|
"loss": 1.6754,
|
|
"step": 12660
|
|
},
|
|
{
|
|
"epoch": 3.94,
|
|
"learning_rate": 0.0003316795125801163,
|
|
"loss": 1.5933,
|
|
"step": 12670
|
|
},
|
|
{
|
|
"epoch": 3.94,
|
|
"learning_rate": 0.00033144851623284605,
|
|
"loss": 1.5532,
|
|
"step": 12680
|
|
},
|
|
{
|
|
"epoch": 3.95,
|
|
"learning_rate": 0.00033121744206559075,
|
|
"loss": 1.5251,
|
|
"step": 12690
|
|
},
|
|
{
|
|
"epoch": 3.95,
|
|
"learning_rate": 0.0003309862902991302,
|
|
"loss": 1.5453,
|
|
"step": 12700
|
|
},
|
|
{
|
|
"epoch": 3.95,
|
|
"learning_rate": 0.00033075506115431833,
|
|
"loss": 1.4655,
|
|
"step": 12710
|
|
},
|
|
{
|
|
"epoch": 3.96,
|
|
"learning_rate": 0.0003305237548520832,
|
|
"loss": 1.5496,
|
|
"step": 12720
|
|
},
|
|
{
|
|
"epoch": 3.96,
|
|
"learning_rate": 0.0003302923716134261,
|
|
"loss": 1.486,
|
|
"step": 12730
|
|
},
|
|
{
|
|
"epoch": 3.96,
|
|
"learning_rate": 0.00033006091165942245,
|
|
"loss": 1.689,
|
|
"step": 12740
|
|
},
|
|
{
|
|
"epoch": 3.97,
|
|
"learning_rate": 0.00032982937521122056,
|
|
"loss": 1.5153,
|
|
"step": 12750
|
|
},
|
|
{
|
|
"epoch": 3.97,
|
|
"learning_rate": 0.00032959776249004186,
|
|
"loss": 1.4855,
|
|
"step": 12760
|
|
},
|
|
{
|
|
"epoch": 3.97,
|
|
"learning_rate": 0.0003293660737171808,
|
|
"loss": 1.638,
|
|
"step": 12770
|
|
},
|
|
{
|
|
"epoch": 3.98,
|
|
"learning_rate": 0.00032913430911400444,
|
|
"loss": 1.5496,
|
|
"step": 12780
|
|
},
|
|
{
|
|
"epoch": 3.98,
|
|
"learning_rate": 0.0003289024689019522,
|
|
"loss": 1.6065,
|
|
"step": 12790
|
|
},
|
|
{
|
|
"epoch": 3.98,
|
|
"learning_rate": 0.0003286705533025358,
|
|
"loss": 1.5438,
|
|
"step": 12800
|
|
},
|
|
{
|
|
"epoch": 3.99,
|
|
"learning_rate": 0.0003284385625373391,
|
|
"loss": 1.53,
|
|
"step": 12810
|
|
},
|
|
{
|
|
"epoch": 3.99,
|
|
"learning_rate": 0.0003282064968280175,
|
|
"loss": 1.5858,
|
|
"step": 12820
|
|
},
|
|
{
|
|
"epoch": 3.99,
|
|
"learning_rate": 0.00032797435639629846,
|
|
"loss": 1.6059,
|
|
"step": 12830
|
|
},
|
|
{
|
|
"epoch": 3.99,
|
|
"learning_rate": 0.00032774214146398035,
|
|
"loss": 1.6215,
|
|
"step": 12840
|
|
},
|
|
{
|
|
"epoch": 4.0,
|
|
"learning_rate": 0.00032750985225293296,
|
|
"loss": 1.5878,
|
|
"step": 12850
|
|
},
|
|
{
|
|
"epoch": 4.0,
|
|
"learning_rate": 0.000327277488985097,
|
|
"loss": 1.4829,
|
|
"step": 12860
|
|
},
|
|
{
|
|
"epoch": 4.0,
|
|
"learning_rate": 0.000327045051882484,
|
|
"loss": 1.4431,
|
|
"step": 12870
|
|
},
|
|
{
|
|
"epoch": 4.01,
|
|
"learning_rate": 0.00032681254116717607,
|
|
"loss": 1.4274,
|
|
"step": 12880
|
|
},
|
|
{
|
|
"epoch": 4.01,
|
|
"learning_rate": 0.00032657995706132534,
|
|
"loss": 1.5379,
|
|
"step": 12890
|
|
},
|
|
{
|
|
"epoch": 4.01,
|
|
"learning_rate": 0.0003263472997871545,
|
|
"loss": 1.5651,
|
|
"step": 12900
|
|
},
|
|
{
|
|
"epoch": 4.02,
|
|
"learning_rate": 0.0003261145695669559,
|
|
"loss": 1.3823,
|
|
"step": 12910
|
|
},
|
|
{
|
|
"epoch": 4.02,
|
|
"learning_rate": 0.0003258817666230915,
|
|
"loss": 1.3874,
|
|
"step": 12920
|
|
},
|
|
{
|
|
"epoch": 4.02,
|
|
"learning_rate": 0.0003256488911779931,
|
|
"loss": 1.3826,
|
|
"step": 12930
|
|
},
|
|
{
|
|
"epoch": 4.03,
|
|
"learning_rate": 0.00032541594345416143,
|
|
"loss": 1.4346,
|
|
"step": 12940
|
|
},
|
|
{
|
|
"epoch": 4.03,
|
|
"learning_rate": 0.0003251829236741663,
|
|
"loss": 1.4174,
|
|
"step": 12950
|
|
},
|
|
{
|
|
"epoch": 4.03,
|
|
"learning_rate": 0.0003249498320606466,
|
|
"loss": 1.5485,
|
|
"step": 12960
|
|
},
|
|
{
|
|
"epoch": 4.04,
|
|
"learning_rate": 0.0003247166688363097,
|
|
"loss": 1.3452,
|
|
"step": 12970
|
|
},
|
|
{
|
|
"epoch": 4.04,
|
|
"learning_rate": 0.00032448343422393136,
|
|
"loss": 1.3724,
|
|
"step": 12980
|
|
},
|
|
{
|
|
"epoch": 4.04,
|
|
"learning_rate": 0.0003242501284463555,
|
|
"loss": 1.5267,
|
|
"step": 12990
|
|
},
|
|
{
|
|
"epoch": 4.04,
|
|
"learning_rate": 0.0003240167517264943,
|
|
"loss": 1.4702,
|
|
"step": 13000
|
|
},
|
|
{
|
|
"epoch": 4.05,
|
|
"learning_rate": 0.00032378330428732744,
|
|
"loss": 1.4088,
|
|
"step": 13010
|
|
},
|
|
{
|
|
"epoch": 4.05,
|
|
"learning_rate": 0.0003235497863519023,
|
|
"loss": 1.408,
|
|
"step": 13020
|
|
},
|
|
{
|
|
"epoch": 4.05,
|
|
"learning_rate": 0.0003233161981433336,
|
|
"loss": 1.3855,
|
|
"step": 13030
|
|
},
|
|
{
|
|
"epoch": 4.06,
|
|
"learning_rate": 0.0003230825398848032,
|
|
"loss": 1.3995,
|
|
"step": 13040
|
|
},
|
|
{
|
|
"epoch": 4.06,
|
|
"learning_rate": 0.0003228488117995599,
|
|
"loss": 1.4739,
|
|
"step": 13050
|
|
},
|
|
{
|
|
"epoch": 4.06,
|
|
"learning_rate": 0.0003226150141109191,
|
|
"loss": 1.5798,
|
|
"step": 13060
|
|
},
|
|
{
|
|
"epoch": 4.07,
|
|
"learning_rate": 0.000322381147042263,
|
|
"loss": 1.4914,
|
|
"step": 13070
|
|
},
|
|
{
|
|
"epoch": 4.07,
|
|
"learning_rate": 0.0003221472108170396,
|
|
"loss": 1.3969,
|
|
"step": 13080
|
|
},
|
|
{
|
|
"epoch": 4.07,
|
|
"learning_rate": 0.0003219132056587636,
|
|
"loss": 1.4156,
|
|
"step": 13090
|
|
},
|
|
{
|
|
"epoch": 4.08,
|
|
"learning_rate": 0.00032167913179101507,
|
|
"loss": 1.4479,
|
|
"step": 13100
|
|
},
|
|
{
|
|
"epoch": 4.08,
|
|
"learning_rate": 0.0003214449894374398,
|
|
"loss": 1.4748,
|
|
"step": 13110
|
|
},
|
|
{
|
|
"epoch": 4.08,
|
|
"learning_rate": 0.00032121077882174917,
|
|
"loss": 1.5538,
|
|
"step": 13120
|
|
},
|
|
{
|
|
"epoch": 4.08,
|
|
"learning_rate": 0.00032097650016771974,
|
|
"loss": 1.472,
|
|
"step": 13130
|
|
},
|
|
{
|
|
"epoch": 4.09,
|
|
"learning_rate": 0.00032074215369919313,
|
|
"loss": 1.3544,
|
|
"step": 13140
|
|
},
|
|
{
|
|
"epoch": 4.09,
|
|
"learning_rate": 0.0003205077396400754,
|
|
"loss": 1.3877,
|
|
"step": 13150
|
|
},
|
|
{
|
|
"epoch": 4.09,
|
|
"learning_rate": 0.0003202732582143378,
|
|
"loss": 1.4537,
|
|
"step": 13160
|
|
},
|
|
{
|
|
"epoch": 4.1,
|
|
"learning_rate": 0.00032003870964601543,
|
|
"loss": 1.5374,
|
|
"step": 13170
|
|
},
|
|
{
|
|
"epoch": 4.1,
|
|
"learning_rate": 0.0003198040941592077,
|
|
"loss": 1.3963,
|
|
"step": 13180
|
|
},
|
|
{
|
|
"epoch": 4.1,
|
|
"learning_rate": 0.000319569411978078,
|
|
"loss": 1.4065,
|
|
"step": 13190
|
|
},
|
|
{
|
|
"epoch": 4.11,
|
|
"learning_rate": 0.0003193346633268535,
|
|
"loss": 1.4315,
|
|
"step": 13200
|
|
},
|
|
{
|
|
"epoch": 4.11,
|
|
"learning_rate": 0.00031909984842982476,
|
|
"loss": 1.3609,
|
|
"step": 13210
|
|
},
|
|
{
|
|
"epoch": 4.11,
|
|
"learning_rate": 0.00031886496751134565,
|
|
"loss": 1.3737,
|
|
"step": 13220
|
|
},
|
|
{
|
|
"epoch": 4.12,
|
|
"learning_rate": 0.00031863002079583313,
|
|
"loss": 1.4164,
|
|
"step": 13230
|
|
},
|
|
{
|
|
"epoch": 4.12,
|
|
"learning_rate": 0.0003183950085077671,
|
|
"loss": 1.5029,
|
|
"step": 13240
|
|
},
|
|
{
|
|
"epoch": 4.12,
|
|
"learning_rate": 0.0003181599308716899,
|
|
"loss": 1.4984,
|
|
"step": 13250
|
|
},
|
|
{
|
|
"epoch": 4.13,
|
|
"learning_rate": 0.0003179247881122067,
|
|
"loss": 1.4664,
|
|
"step": 13260
|
|
},
|
|
{
|
|
"epoch": 4.13,
|
|
"learning_rate": 0.0003176895804539844,
|
|
"loss": 1.5039,
|
|
"step": 13270
|
|
},
|
|
{
|
|
"epoch": 4.13,
|
|
"learning_rate": 0.00031745430812175234,
|
|
"loss": 1.4399,
|
|
"step": 13280
|
|
},
|
|
{
|
|
"epoch": 4.13,
|
|
"learning_rate": 0.0003172189713403014,
|
|
"loss": 1.541,
|
|
"step": 13290
|
|
},
|
|
{
|
|
"epoch": 4.14,
|
|
"learning_rate": 0.0003169835703344842,
|
|
"loss": 1.4455,
|
|
"step": 13300
|
|
},
|
|
{
|
|
"epoch": 4.14,
|
|
"learning_rate": 0.0003167481053292144,
|
|
"loss": 1.3949,
|
|
"step": 13310
|
|
},
|
|
{
|
|
"epoch": 4.14,
|
|
"learning_rate": 0.0003165125765494673,
|
|
"loss": 1.4006,
|
|
"step": 13320
|
|
},
|
|
{
|
|
"epoch": 4.15,
|
|
"learning_rate": 0.00031627698422027873,
|
|
"loss": 1.4306,
|
|
"step": 13330
|
|
},
|
|
{
|
|
"epoch": 4.15,
|
|
"learning_rate": 0.0003160413285667454,
|
|
"loss": 1.4956,
|
|
"step": 13340
|
|
},
|
|
{
|
|
"epoch": 4.15,
|
|
"learning_rate": 0.0003158056098140246,
|
|
"loss": 1.4142,
|
|
"step": 13350
|
|
},
|
|
{
|
|
"epoch": 4.16,
|
|
"learning_rate": 0.00031556982818733357,
|
|
"loss": 1.4263,
|
|
"step": 13360
|
|
},
|
|
{
|
|
"epoch": 4.16,
|
|
"learning_rate": 0.0003153339839119501,
|
|
"loss": 1.411,
|
|
"step": 13370
|
|
},
|
|
{
|
|
"epoch": 4.16,
|
|
"learning_rate": 0.0003150980772132116,
|
|
"loss": 1.5037,
|
|
"step": 13380
|
|
},
|
|
{
|
|
"epoch": 4.17,
|
|
"learning_rate": 0.00031486210831651495,
|
|
"loss": 1.4712,
|
|
"step": 13390
|
|
},
|
|
{
|
|
"epoch": 4.17,
|
|
"learning_rate": 0.0003146260774473169,
|
|
"loss": 1.5827,
|
|
"step": 13400
|
|
},
|
|
{
|
|
"epoch": 4.17,
|
|
"learning_rate": 0.0003143899848311328,
|
|
"loss": 1.469,
|
|
"step": 13410
|
|
},
|
|
{
|
|
"epoch": 4.18,
|
|
"learning_rate": 0.0003141538306935376,
|
|
"loss": 1.3563,
|
|
"step": 13420
|
|
},
|
|
{
|
|
"epoch": 4.18,
|
|
"learning_rate": 0.00031391761526016474,
|
|
"loss": 1.4043,
|
|
"step": 13430
|
|
},
|
|
{
|
|
"epoch": 4.18,
|
|
"learning_rate": 0.0003136813387567061,
|
|
"loss": 1.3011,
|
|
"step": 13440
|
|
},
|
|
{
|
|
"epoch": 4.18,
|
|
"learning_rate": 0.00031344500140891224,
|
|
"loss": 1.4643,
|
|
"step": 13450
|
|
},
|
|
{
|
|
"epoch": 4.19,
|
|
"learning_rate": 0.0003132086034425916,
|
|
"loss": 1.4704,
|
|
"step": 13460
|
|
},
|
|
{
|
|
"epoch": 4.19,
|
|
"learning_rate": 0.00031297214508361066,
|
|
"loss": 1.5165,
|
|
"step": 13470
|
|
},
|
|
{
|
|
"epoch": 4.19,
|
|
"learning_rate": 0.00031273562655789353,
|
|
"loss": 1.4728,
|
|
"step": 13480
|
|
},
|
|
{
|
|
"epoch": 4.2,
|
|
"learning_rate": 0.0003124990480914219,
|
|
"loss": 1.4348,
|
|
"step": 13490
|
|
},
|
|
{
|
|
"epoch": 4.2,
|
|
"learning_rate": 0.00031226240991023444,
|
|
"loss": 1.5113,
|
|
"step": 13500
|
|
},
|
|
{
|
|
"epoch": 4.2,
|
|
"learning_rate": 0.00031202571224042745,
|
|
"loss": 1.5212,
|
|
"step": 13510
|
|
},
|
|
{
|
|
"epoch": 4.21,
|
|
"learning_rate": 0.0003117889553081535,
|
|
"loss": 1.3206,
|
|
"step": 13520
|
|
},
|
|
{
|
|
"epoch": 4.21,
|
|
"learning_rate": 0.000311552139339622,
|
|
"loss": 1.465,
|
|
"step": 13530
|
|
},
|
|
{
|
|
"epoch": 4.21,
|
|
"learning_rate": 0.0003113152645610988,
|
|
"loss": 1.4619,
|
|
"step": 13540
|
|
},
|
|
{
|
|
"epoch": 4.22,
|
|
"learning_rate": 0.00031107833119890587,
|
|
"loss": 1.4778,
|
|
"step": 13550
|
|
},
|
|
{
|
|
"epoch": 4.22,
|
|
"learning_rate": 0.00031084133947942137,
|
|
"loss": 1.49,
|
|
"step": 13560
|
|
},
|
|
{
|
|
"epoch": 4.22,
|
|
"learning_rate": 0.0003106042896290788,
|
|
"loss": 1.5603,
|
|
"step": 13570
|
|
},
|
|
{
|
|
"epoch": 4.22,
|
|
"learning_rate": 0.00031036718187436754,
|
|
"loss": 1.4719,
|
|
"step": 13580
|
|
},
|
|
{
|
|
"epoch": 4.23,
|
|
"learning_rate": 0.00031013001644183226,
|
|
"loss": 1.5059,
|
|
"step": 13590
|
|
},
|
|
{
|
|
"epoch": 4.23,
|
|
"learning_rate": 0.00030989279355807253,
|
|
"loss": 1.4334,
|
|
"step": 13600
|
|
},
|
|
{
|
|
"epoch": 4.23,
|
|
"learning_rate": 0.0003096555134497431,
|
|
"loss": 1.4196,
|
|
"step": 13610
|
|
},
|
|
{
|
|
"epoch": 4.24,
|
|
"learning_rate": 0.00030941817634355326,
|
|
"loss": 1.538,
|
|
"step": 13620
|
|
},
|
|
{
|
|
"epoch": 4.24,
|
|
"learning_rate": 0.0003091807824662666,
|
|
"loss": 1.474,
|
|
"step": 13630
|
|
},
|
|
{
|
|
"epoch": 4.24,
|
|
"learning_rate": 0.0003089433320447011,
|
|
"loss": 1.5226,
|
|
"step": 13640
|
|
},
|
|
{
|
|
"epoch": 4.25,
|
|
"learning_rate": 0.0003087058253057289,
|
|
"loss": 1.4448,
|
|
"step": 13650
|
|
},
|
|
{
|
|
"epoch": 4.25,
|
|
"learning_rate": 0.00030846826247627585,
|
|
"loss": 1.4685,
|
|
"step": 13660
|
|
},
|
|
{
|
|
"epoch": 4.25,
|
|
"learning_rate": 0.0003082306437833211,
|
|
"loss": 1.5566,
|
|
"step": 13670
|
|
},
|
|
{
|
|
"epoch": 4.26,
|
|
"learning_rate": 0.0003079929694538978,
|
|
"loss": 1.454,
|
|
"step": 13680
|
|
},
|
|
{
|
|
"epoch": 4.26,
|
|
"learning_rate": 0.0003077552397150915,
|
|
"loss": 1.3966,
|
|
"step": 13690
|
|
},
|
|
{
|
|
"epoch": 4.26,
|
|
"learning_rate": 0.00030751745479404134,
|
|
"loss": 1.5694,
|
|
"step": 13700
|
|
},
|
|
{
|
|
"epoch": 4.27,
|
|
"learning_rate": 0.0003072796149179388,
|
|
"loss": 1.3581,
|
|
"step": 13710
|
|
},
|
|
{
|
|
"epoch": 4.27,
|
|
"learning_rate": 0.0003070417203140281,
|
|
"loss": 1.4418,
|
|
"step": 13720
|
|
},
|
|
{
|
|
"epoch": 4.27,
|
|
"learning_rate": 0.0003068037712096056,
|
|
"loss": 1.4149,
|
|
"step": 13730
|
|
},
|
|
{
|
|
"epoch": 4.27,
|
|
"learning_rate": 0.0003065657678320196,
|
|
"loss": 1.3675,
|
|
"step": 13740
|
|
},
|
|
{
|
|
"epoch": 4.28,
|
|
"learning_rate": 0.00030632771040867076,
|
|
"loss": 1.5359,
|
|
"step": 13750
|
|
},
|
|
{
|
|
"epoch": 4.28,
|
|
"learning_rate": 0.0003060895991670107,
|
|
"loss": 1.431,
|
|
"step": 13760
|
|
},
|
|
{
|
|
"epoch": 4.28,
|
|
"learning_rate": 0.0003058514343345431,
|
|
"loss": 1.5657,
|
|
"step": 13770
|
|
},
|
|
{
|
|
"epoch": 4.29,
|
|
"learning_rate": 0.0003056132161388224,
|
|
"loss": 1.5098,
|
|
"step": 13780
|
|
},
|
|
{
|
|
"epoch": 4.29,
|
|
"learning_rate": 0.00030537494480745414,
|
|
"loss": 1.3896,
|
|
"step": 13790
|
|
},
|
|
{
|
|
"epoch": 4.29,
|
|
"learning_rate": 0.0003051366205680947,
|
|
"loss": 1.5489,
|
|
"step": 13800
|
|
},
|
|
{
|
|
"epoch": 4.3,
|
|
"learning_rate": 0.00030489824364845103,
|
|
"loss": 1.5523,
|
|
"step": 13810
|
|
},
|
|
{
|
|
"epoch": 4.3,
|
|
"learning_rate": 0.0003046598142762804,
|
|
"loss": 1.5375,
|
|
"step": 13820
|
|
},
|
|
{
|
|
"epoch": 4.3,
|
|
"learning_rate": 0.00030442133267938993,
|
|
"loss": 1.4852,
|
|
"step": 13830
|
|
},
|
|
{
|
|
"epoch": 4.31,
|
|
"learning_rate": 0.00030418279908563713,
|
|
"loss": 1.3864,
|
|
"step": 13840
|
|
},
|
|
{
|
|
"epoch": 4.31,
|
|
"learning_rate": 0.00030394421372292873,
|
|
"loss": 1.5272,
|
|
"step": 13850
|
|
},
|
|
{
|
|
"epoch": 4.31,
|
|
"learning_rate": 0.00030370557681922116,
|
|
"loss": 1.3969,
|
|
"step": 13860
|
|
},
|
|
{
|
|
"epoch": 4.32,
|
|
"learning_rate": 0.0003034668886025202,
|
|
"loss": 1.4874,
|
|
"step": 13870
|
|
},
|
|
{
|
|
"epoch": 4.32,
|
|
"learning_rate": 0.00030322814930088026,
|
|
"loss": 1.4915,
|
|
"step": 13880
|
|
},
|
|
{
|
|
"epoch": 4.32,
|
|
"learning_rate": 0.000302989359142405,
|
|
"loss": 1.4955,
|
|
"step": 13890
|
|
},
|
|
{
|
|
"epoch": 4.32,
|
|
"learning_rate": 0.0003027505183552464,
|
|
"loss": 1.5482,
|
|
"step": 13900
|
|
},
|
|
{
|
|
"epoch": 4.33,
|
|
"learning_rate": 0.0003025116271676049,
|
|
"loss": 1.4735,
|
|
"step": 13910
|
|
},
|
|
{
|
|
"epoch": 4.33,
|
|
"learning_rate": 0.0003022726858077291,
|
|
"loss": 1.4371,
|
|
"step": 13920
|
|
},
|
|
{
|
|
"epoch": 4.33,
|
|
"learning_rate": 0.0003020336945039154,
|
|
"loss": 1.4502,
|
|
"step": 13930
|
|
},
|
|
{
|
|
"epoch": 4.34,
|
|
"learning_rate": 0.0003017946534845083,
|
|
"loss": 1.5387,
|
|
"step": 13940
|
|
},
|
|
{
|
|
"epoch": 4.34,
|
|
"learning_rate": 0.00030155556297789933,
|
|
"loss": 1.4437,
|
|
"step": 13950
|
|
},
|
|
{
|
|
"epoch": 4.34,
|
|
"learning_rate": 0.00030131642321252756,
|
|
"loss": 1.3629,
|
|
"step": 13960
|
|
},
|
|
{
|
|
"epoch": 4.35,
|
|
"learning_rate": 0.00030107723441687905,
|
|
"loss": 1.4616,
|
|
"step": 13970
|
|
},
|
|
{
|
|
"epoch": 4.35,
|
|
"learning_rate": 0.00030083799681948685,
|
|
"loss": 1.4589,
|
|
"step": 13980
|
|
},
|
|
{
|
|
"epoch": 4.35,
|
|
"learning_rate": 0.00030059871064893045,
|
|
"loss": 1.4069,
|
|
"step": 13990
|
|
},
|
|
{
|
|
"epoch": 4.36,
|
|
"learning_rate": 0.00030035937613383587,
|
|
"loss": 1.5544,
|
|
"step": 14000
|
|
},
|
|
{
|
|
"epoch": 4.36,
|
|
"learning_rate": 0.00030011999350287524,
|
|
"loss": 1.4727,
|
|
"step": 14010
|
|
},
|
|
{
|
|
"epoch": 4.36,
|
|
"learning_rate": 0.00029988056298476653,
|
|
"loss": 1.4991,
|
|
"step": 14020
|
|
},
|
|
{
|
|
"epoch": 4.36,
|
|
"learning_rate": 0.00029964108480827397,
|
|
"loss": 1.3473,
|
|
"step": 14030
|
|
},
|
|
{
|
|
"epoch": 4.37,
|
|
"learning_rate": 0.0002994015592022067,
|
|
"loss": 1.5917,
|
|
"step": 14040
|
|
},
|
|
{
|
|
"epoch": 4.37,
|
|
"learning_rate": 0.0002991619863954196,
|
|
"loss": 1.5073,
|
|
"step": 14050
|
|
},
|
|
{
|
|
"epoch": 4.37,
|
|
"learning_rate": 0.0002989223666168124,
|
|
"loss": 1.5191,
|
|
"step": 14060
|
|
},
|
|
{
|
|
"epoch": 4.38,
|
|
"learning_rate": 0.00029868270009532995,
|
|
"loss": 1.527,
|
|
"step": 14070
|
|
},
|
|
{
|
|
"epoch": 4.38,
|
|
"learning_rate": 0.0002984429870599616,
|
|
"loss": 1.3783,
|
|
"step": 14080
|
|
},
|
|
{
|
|
"epoch": 4.38,
|
|
"learning_rate": 0.000298203227739741,
|
|
"loss": 1.4445,
|
|
"step": 14090
|
|
},
|
|
{
|
|
"epoch": 4.39,
|
|
"learning_rate": 0.0002979634223637465,
|
|
"loss": 1.4078,
|
|
"step": 14100
|
|
},
|
|
{
|
|
"epoch": 4.39,
|
|
"learning_rate": 0.00029772357116109987,
|
|
"loss": 1.4679,
|
|
"step": 14110
|
|
},
|
|
{
|
|
"epoch": 4.39,
|
|
"learning_rate": 0.000297483674360967,
|
|
"loss": 1.5622,
|
|
"step": 14120
|
|
},
|
|
{
|
|
"epoch": 4.4,
|
|
"learning_rate": 0.0002972437321925575,
|
|
"loss": 1.4684,
|
|
"step": 14130
|
|
},
|
|
{
|
|
"epoch": 4.4,
|
|
"learning_rate": 0.00029700374488512385,
|
|
"loss": 1.6185,
|
|
"step": 14140
|
|
},
|
|
{
|
|
"epoch": 4.4,
|
|
"learning_rate": 0.00029676371266796204,
|
|
"loss": 1.3668,
|
|
"step": 14150
|
|
},
|
|
{
|
|
"epoch": 4.41,
|
|
"learning_rate": 0.00029652363577041085,
|
|
"loss": 1.4113,
|
|
"step": 14160
|
|
},
|
|
{
|
|
"epoch": 4.41,
|
|
"learning_rate": 0.0002962835144218517,
|
|
"loss": 1.4482,
|
|
"step": 14170
|
|
},
|
|
{
|
|
"epoch": 4.41,
|
|
"learning_rate": 0.0002960433488517086,
|
|
"loss": 1.4842,
|
|
"step": 14180
|
|
},
|
|
{
|
|
"epoch": 4.41,
|
|
"learning_rate": 0.00029580313928944773,
|
|
"loss": 1.5429,
|
|
"step": 14190
|
|
},
|
|
{
|
|
"epoch": 4.42,
|
|
"learning_rate": 0.0002955628859645774,
|
|
"loss": 1.41,
|
|
"step": 14200
|
|
},
|
|
{
|
|
"epoch": 4.42,
|
|
"learning_rate": 0.0002953225891066474,
|
|
"loss": 1.4991,
|
|
"step": 14210
|
|
},
|
|
{
|
|
"epoch": 4.42,
|
|
"learning_rate": 0.0002950822489452496,
|
|
"loss": 1.5019,
|
|
"step": 14220
|
|
},
|
|
{
|
|
"epoch": 4.43,
|
|
"learning_rate": 0.00029484186571001686,
|
|
"loss": 1.4446,
|
|
"step": 14230
|
|
},
|
|
{
|
|
"epoch": 4.43,
|
|
"learning_rate": 0.0002946014396306235,
|
|
"loss": 1.4268,
|
|
"step": 14240
|
|
},
|
|
{
|
|
"epoch": 4.43,
|
|
"learning_rate": 0.00029436097093678444,
|
|
"loss": 1.572,
|
|
"step": 14250
|
|
},
|
|
{
|
|
"epoch": 4.44,
|
|
"learning_rate": 0.0002941204598582556,
|
|
"loss": 1.5158,
|
|
"step": 14260
|
|
},
|
|
{
|
|
"epoch": 4.44,
|
|
"learning_rate": 0.0002938799066248334,
|
|
"loss": 1.5207,
|
|
"step": 14270
|
|
},
|
|
{
|
|
"epoch": 4.44,
|
|
"learning_rate": 0.00029363931146635406,
|
|
"loss": 1.4554,
|
|
"step": 14280
|
|
},
|
|
{
|
|
"epoch": 4.45,
|
|
"learning_rate": 0.0002933986746126947,
|
|
"loss": 1.4061,
|
|
"step": 14290
|
|
},
|
|
{
|
|
"epoch": 4.45,
|
|
"learning_rate": 0.00029315799629377144,
|
|
"loss": 1.4877,
|
|
"step": 14300
|
|
},
|
|
{
|
|
"epoch": 4.45,
|
|
"learning_rate": 0.00029291727673954053,
|
|
"loss": 1.5001,
|
|
"step": 14310
|
|
},
|
|
{
|
|
"epoch": 4.46,
|
|
"learning_rate": 0.00029267651617999747,
|
|
"loss": 1.3957,
|
|
"step": 14320
|
|
},
|
|
{
|
|
"epoch": 4.46,
|
|
"learning_rate": 0.0002924357148451769,
|
|
"loss": 1.4243,
|
|
"step": 14330
|
|
},
|
|
{
|
|
"epoch": 4.46,
|
|
"learning_rate": 0.0002921948729651525,
|
|
"loss": 1.5417,
|
|
"step": 14340
|
|
},
|
|
{
|
|
"epoch": 4.46,
|
|
"learning_rate": 0.00029195399077003656,
|
|
"loss": 1.4721,
|
|
"step": 14350
|
|
},
|
|
{
|
|
"epoch": 4.47,
|
|
"learning_rate": 0.0002917130684899801,
|
|
"loss": 1.4792,
|
|
"step": 14360
|
|
},
|
|
{
|
|
"epoch": 4.47,
|
|
"learning_rate": 0.0002914721063551722,
|
|
"loss": 1.4413,
|
|
"step": 14370
|
|
},
|
|
{
|
|
"epoch": 4.47,
|
|
"learning_rate": 0.0002912311045958401,
|
|
"loss": 1.4493,
|
|
"step": 14380
|
|
},
|
|
{
|
|
"epoch": 4.48,
|
|
"learning_rate": 0.0002909900634422491,
|
|
"loss": 1.5605,
|
|
"step": 14390
|
|
},
|
|
{
|
|
"epoch": 4.48,
|
|
"learning_rate": 0.00029074898312470183,
|
|
"loss": 1.469,
|
|
"step": 14400
|
|
},
|
|
{
|
|
"epoch": 4.48,
|
|
"learning_rate": 0.0002905078638735386,
|
|
"loss": 1.4648,
|
|
"step": 14410
|
|
},
|
|
{
|
|
"epoch": 4.49,
|
|
"learning_rate": 0.00029026670591913664,
|
|
"loss": 1.5473,
|
|
"step": 14420
|
|
},
|
|
{
|
|
"epoch": 4.49,
|
|
"learning_rate": 0.0002900255094919105,
|
|
"loss": 1.5787,
|
|
"step": 14430
|
|
},
|
|
{
|
|
"epoch": 4.49,
|
|
"learning_rate": 0.0002897842748223111,
|
|
"loss": 1.4247,
|
|
"step": 14440
|
|
},
|
|
{
|
|
"epoch": 4.5,
|
|
"learning_rate": 0.00028954300214082616,
|
|
"loss": 1.4921,
|
|
"step": 14450
|
|
},
|
|
{
|
|
"epoch": 4.5,
|
|
"learning_rate": 0.0002893016916779799,
|
|
"loss": 1.4119,
|
|
"step": 14460
|
|
},
|
|
{
|
|
"epoch": 4.5,
|
|
"learning_rate": 0.0002890603436643322,
|
|
"loss": 1.5274,
|
|
"step": 14470
|
|
},
|
|
{
|
|
"epoch": 4.5,
|
|
"learning_rate": 0.0002888189583304789,
|
|
"loss": 1.4881,
|
|
"step": 14480
|
|
},
|
|
{
|
|
"epoch": 4.51,
|
|
"learning_rate": 0.00028857753590705196,
|
|
"loss": 1.4025,
|
|
"step": 14490
|
|
},
|
|
{
|
|
"epoch": 4.51,
|
|
"learning_rate": 0.00028833607662471806,
|
|
"loss": 1.5234,
|
|
"step": 14500
|
|
},
|
|
{
|
|
"epoch": 4.51,
|
|
"learning_rate": 0.00028809458071417973,
|
|
"loss": 1.5,
|
|
"step": 14510
|
|
},
|
|
{
|
|
"epoch": 4.52,
|
|
"learning_rate": 0.00028785304840617417,
|
|
"loss": 1.5149,
|
|
"step": 14520
|
|
},
|
|
{
|
|
"epoch": 4.52,
|
|
"learning_rate": 0.0002876114799314734,
|
|
"loss": 1.5449,
|
|
"step": 14530
|
|
},
|
|
{
|
|
"epoch": 4.52,
|
|
"learning_rate": 0.000287369875520884,
|
|
"loss": 1.5103,
|
|
"step": 14540
|
|
},
|
|
{
|
|
"epoch": 4.53,
|
|
"learning_rate": 0.00028712823540524694,
|
|
"loss": 1.5542,
|
|
"step": 14550
|
|
},
|
|
{
|
|
"epoch": 4.53,
|
|
"learning_rate": 0.0002868865598154373,
|
|
"loss": 1.4673,
|
|
"step": 14560
|
|
},
|
|
{
|
|
"epoch": 4.53,
|
|
"learning_rate": 0.00028664484898236397,
|
|
"loss": 1.4422,
|
|
"step": 14570
|
|
},
|
|
{
|
|
"epoch": 4.54,
|
|
"learning_rate": 0.0002864031031369696,
|
|
"loss": 1.5804,
|
|
"step": 14580
|
|
},
|
|
{
|
|
"epoch": 4.54,
|
|
"learning_rate": 0.0002861613225102302,
|
|
"loss": 1.4625,
|
|
"step": 14590
|
|
},
|
|
{
|
|
"epoch": 4.54,
|
|
"learning_rate": 0.0002859195073331552,
|
|
"loss": 1.3843,
|
|
"step": 14600
|
|
},
|
|
{
|
|
"epoch": 4.55,
|
|
"learning_rate": 0.0002856776578367867,
|
|
"loss": 1.6409,
|
|
"step": 14610
|
|
},
|
|
{
|
|
"epoch": 4.55,
|
|
"learning_rate": 0.0002854357742522,
|
|
"loss": 1.3922,
|
|
"step": 14620
|
|
},
|
|
{
|
|
"epoch": 4.55,
|
|
"learning_rate": 0.0002851938568105027,
|
|
"loss": 1.5565,
|
|
"step": 14630
|
|
},
|
|
{
|
|
"epoch": 4.55,
|
|
"learning_rate": 0.0002849519057428348,
|
|
"loss": 1.6263,
|
|
"step": 14640
|
|
},
|
|
{
|
|
"epoch": 4.56,
|
|
"learning_rate": 0.0002847099212803684,
|
|
"loss": 1.4783,
|
|
"step": 14650
|
|
},
|
|
{
|
|
"epoch": 4.56,
|
|
"learning_rate": 0.00028446790365430774,
|
|
"loss": 1.5834,
|
|
"step": 14660
|
|
},
|
|
{
|
|
"epoch": 4.56,
|
|
"learning_rate": 0.0002842258530958884,
|
|
"loss": 1.4861,
|
|
"step": 14670
|
|
},
|
|
{
|
|
"epoch": 4.57,
|
|
"learning_rate": 0.0002839837698363776,
|
|
"loss": 1.4623,
|
|
"step": 14680
|
|
},
|
|
{
|
|
"epoch": 4.57,
|
|
"learning_rate": 0.0002837416541070739,
|
|
"loss": 1.3971,
|
|
"step": 14690
|
|
},
|
|
{
|
|
"epoch": 4.57,
|
|
"learning_rate": 0.00028349950613930656,
|
|
"loss": 1.4917,
|
|
"step": 14700
|
|
},
|
|
{
|
|
"epoch": 4.58,
|
|
"learning_rate": 0.00028325732616443615,
|
|
"loss": 1.3458,
|
|
"step": 14710
|
|
},
|
|
{
|
|
"epoch": 4.58,
|
|
"learning_rate": 0.0002830151144138533,
|
|
"loss": 1.392,
|
|
"step": 14720
|
|
},
|
|
{
|
|
"epoch": 4.58,
|
|
"learning_rate": 0.00028277287111897923,
|
|
"loss": 1.4966,
|
|
"step": 14730
|
|
},
|
|
{
|
|
"epoch": 4.59,
|
|
"learning_rate": 0.0002825305965112654,
|
|
"loss": 1.5073,
|
|
"step": 14740
|
|
},
|
|
{
|
|
"epoch": 4.59,
|
|
"learning_rate": 0.0002822882908221931,
|
|
"loss": 1.4921,
|
|
"step": 14750
|
|
},
|
|
{
|
|
"epoch": 4.59,
|
|
"learning_rate": 0.0002820459542832733,
|
|
"loss": 1.4958,
|
|
"step": 14760
|
|
},
|
|
{
|
|
"epoch": 4.6,
|
|
"learning_rate": 0.00028180358712604625,
|
|
"loss": 1.5369,
|
|
"step": 14770
|
|
},
|
|
{
|
|
"epoch": 4.6,
|
|
"learning_rate": 0.0002815611895820818,
|
|
"loss": 1.5217,
|
|
"step": 14780
|
|
},
|
|
{
|
|
"epoch": 4.6,
|
|
"learning_rate": 0.0002813187618829788,
|
|
"loss": 1.4921,
|
|
"step": 14790
|
|
},
|
|
{
|
|
"epoch": 4.6,
|
|
"learning_rate": 0.0002810763042603646,
|
|
"loss": 1.387,
|
|
"step": 14800
|
|
},
|
|
{
|
|
"epoch": 4.61,
|
|
"learning_rate": 0.0002808338169458955,
|
|
"loss": 1.4973,
|
|
"step": 14810
|
|
},
|
|
{
|
|
"epoch": 4.61,
|
|
"learning_rate": 0.0002805913001712558,
|
|
"loss": 1.5589,
|
|
"step": 14820
|
|
},
|
|
{
|
|
"epoch": 4.61,
|
|
"learning_rate": 0.00028034875416815835,
|
|
"loss": 1.5613,
|
|
"step": 14830
|
|
},
|
|
{
|
|
"epoch": 4.62,
|
|
"learning_rate": 0.0002801061791683436,
|
|
"loss": 1.361,
|
|
"step": 14840
|
|
},
|
|
{
|
|
"epoch": 4.62,
|
|
"learning_rate": 0.0002798635754035799,
|
|
"loss": 1.5219,
|
|
"step": 14850
|
|
},
|
|
{
|
|
"epoch": 4.62,
|
|
"learning_rate": 0.0002796209431056631,
|
|
"loss": 1.4841,
|
|
"step": 14860
|
|
},
|
|
{
|
|
"epoch": 4.63,
|
|
"learning_rate": 0.00027937828250641593,
|
|
"loss": 1.4541,
|
|
"step": 14870
|
|
},
|
|
{
|
|
"epoch": 4.63,
|
|
"learning_rate": 0.00027913559383768884,
|
|
"loss": 1.5241,
|
|
"step": 14880
|
|
},
|
|
{
|
|
"epoch": 4.63,
|
|
"learning_rate": 0.0002788928773313585,
|
|
"loss": 1.5166,
|
|
"step": 14890
|
|
},
|
|
{
|
|
"epoch": 4.64,
|
|
"learning_rate": 0.0002786501332193284,
|
|
"loss": 1.5285,
|
|
"step": 14900
|
|
},
|
|
{
|
|
"epoch": 4.64,
|
|
"learning_rate": 0.00027840736173352843,
|
|
"loss": 1.4522,
|
|
"step": 14910
|
|
},
|
|
{
|
|
"epoch": 4.64,
|
|
"learning_rate": 0.00027816456310591467,
|
|
"loss": 1.4794,
|
|
"step": 14920
|
|
},
|
|
{
|
|
"epoch": 4.64,
|
|
"learning_rate": 0.00027792173756846896,
|
|
"loss": 1.5739,
|
|
"step": 14930
|
|
},
|
|
{
|
|
"epoch": 4.65,
|
|
"learning_rate": 0.000277678885353199,
|
|
"loss": 1.5283,
|
|
"step": 14940
|
|
},
|
|
{
|
|
"epoch": 4.65,
|
|
"learning_rate": 0.0002774360066921381,
|
|
"loss": 1.4332,
|
|
"step": 14950
|
|
},
|
|
{
|
|
"epoch": 4.65,
|
|
"learning_rate": 0.00027719310181734434,
|
|
"loss": 1.5159,
|
|
"step": 14960
|
|
},
|
|
{
|
|
"epoch": 4.66,
|
|
"learning_rate": 0.0002769501709609015,
|
|
"loss": 1.4922,
|
|
"step": 14970
|
|
},
|
|
{
|
|
"epoch": 4.66,
|
|
"learning_rate": 0.0002767072143549178,
|
|
"loss": 1.4616,
|
|
"step": 14980
|
|
},
|
|
{
|
|
"epoch": 4.66,
|
|
"learning_rate": 0.00027646423223152587,
|
|
"loss": 1.5222,
|
|
"step": 14990
|
|
},
|
|
{
|
|
"epoch": 4.67,
|
|
"learning_rate": 0.00027622122482288334,
|
|
"loss": 1.5526,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"epoch": 4.67,
|
|
"learning_rate": 0.0002759781923611715,
|
|
"loss": 1.4716,
|
|
"step": 15010
|
|
},
|
|
{
|
|
"epoch": 4.67,
|
|
"learning_rate": 0.00027573513507859565,
|
|
"loss": 1.4495,
|
|
"step": 15020
|
|
},
|
|
{
|
|
"epoch": 4.68,
|
|
"learning_rate": 0.0002754920532073849,
|
|
"loss": 1.4022,
|
|
"step": 15030
|
|
},
|
|
{
|
|
"epoch": 4.68,
|
|
"learning_rate": 0.00027524894697979186,
|
|
"loss": 1.4078,
|
|
"step": 15040
|
|
},
|
|
{
|
|
"epoch": 4.68,
|
|
"learning_rate": 0.00027500581662809245,
|
|
"loss": 1.4446,
|
|
"step": 15050
|
|
},
|
|
{
|
|
"epoch": 4.69,
|
|
"learning_rate": 0.0002747626623845853,
|
|
"loss": 1.5081,
|
|
"step": 15060
|
|
},
|
|
{
|
|
"epoch": 4.69,
|
|
"learning_rate": 0.00027451948448159246,
|
|
"loss": 1.5254,
|
|
"step": 15070
|
|
},
|
|
{
|
|
"epoch": 4.69,
|
|
"learning_rate": 0.000274276283151458,
|
|
"loss": 1.4874,
|
|
"step": 15080
|
|
},
|
|
{
|
|
"epoch": 4.69,
|
|
"learning_rate": 0.00027403305862654884,
|
|
"loss": 1.4086,
|
|
"step": 15090
|
|
},
|
|
{
|
|
"epoch": 4.7,
|
|
"learning_rate": 0.0002737898111392537,
|
|
"loss": 1.4737,
|
|
"step": 15100
|
|
},
|
|
{
|
|
"epoch": 4.7,
|
|
"learning_rate": 0.0002735465409219834,
|
|
"loss": 1.4726,
|
|
"step": 15110
|
|
},
|
|
{
|
|
"epoch": 4.7,
|
|
"learning_rate": 0.0002733032482071706,
|
|
"loss": 1.4746,
|
|
"step": 15120
|
|
},
|
|
{
|
|
"epoch": 4.71,
|
|
"learning_rate": 0.00027305993322726925,
|
|
"loss": 1.5857,
|
|
"step": 15130
|
|
},
|
|
{
|
|
"epoch": 4.71,
|
|
"learning_rate": 0.00027281659621475465,
|
|
"loss": 1.4243,
|
|
"step": 15140
|
|
},
|
|
{
|
|
"epoch": 4.71,
|
|
"learning_rate": 0.00027257323740212305,
|
|
"loss": 1.5847,
|
|
"step": 15150
|
|
},
|
|
{
|
|
"epoch": 4.72,
|
|
"learning_rate": 0.00027232985702189174,
|
|
"loss": 1.4719,
|
|
"step": 15160
|
|
},
|
|
{
|
|
"epoch": 4.72,
|
|
"learning_rate": 0.00027208645530659846,
|
|
"loss": 1.3787,
|
|
"step": 15170
|
|
},
|
|
{
|
|
"epoch": 4.72,
|
|
"learning_rate": 0.00027184303248880144,
|
|
"loss": 1.5601,
|
|
"step": 15180
|
|
},
|
|
{
|
|
"epoch": 4.73,
|
|
"learning_rate": 0.00027159958880107894,
|
|
"loss": 1.446,
|
|
"step": 15190
|
|
},
|
|
{
|
|
"epoch": 4.73,
|
|
"learning_rate": 0.0002713561244760293,
|
|
"loss": 1.5001,
|
|
"step": 15200
|
|
},
|
|
{
|
|
"epoch": 4.73,
|
|
"learning_rate": 0.0002711126397462705,
|
|
"loss": 1.4447,
|
|
"step": 15210
|
|
},
|
|
{
|
|
"epoch": 4.74,
|
|
"learning_rate": 0.0002708691348444399,
|
|
"loss": 1.5993,
|
|
"step": 15220
|
|
},
|
|
{
|
|
"epoch": 4.74,
|
|
"learning_rate": 0.0002706256100031945,
|
|
"loss": 1.4907,
|
|
"step": 15230
|
|
},
|
|
{
|
|
"epoch": 4.74,
|
|
"learning_rate": 0.00027038206545520983,
|
|
"loss": 1.5213,
|
|
"step": 15240
|
|
},
|
|
{
|
|
"epoch": 4.74,
|
|
"learning_rate": 0.0002701385014331807,
|
|
"loss": 1.4264,
|
|
"step": 15250
|
|
},
|
|
{
|
|
"epoch": 4.75,
|
|
"learning_rate": 0.0002698949181698203,
|
|
"loss": 1.3852,
|
|
"step": 15260
|
|
},
|
|
{
|
|
"epoch": 4.75,
|
|
"learning_rate": 0.00026965131589786037,
|
|
"loss": 1.4967,
|
|
"step": 15270
|
|
},
|
|
{
|
|
"epoch": 4.75,
|
|
"learning_rate": 0.00026940769485005064,
|
|
"loss": 1.5631,
|
|
"step": 15280
|
|
},
|
|
{
|
|
"epoch": 4.76,
|
|
"learning_rate": 0.00026916405525915864,
|
|
"loss": 1.5389,
|
|
"step": 15290
|
|
},
|
|
{
|
|
"epoch": 4.76,
|
|
"learning_rate": 0.0002689203973579701,
|
|
"loss": 1.4886,
|
|
"step": 15300
|
|
},
|
|
{
|
|
"epoch": 4.76,
|
|
"learning_rate": 0.0002686767213792879,
|
|
"loss": 1.5379,
|
|
"step": 15310
|
|
},
|
|
{
|
|
"epoch": 4.77,
|
|
"learning_rate": 0.0002684330275559321,
|
|
"loss": 1.5281,
|
|
"step": 15320
|
|
},
|
|
{
|
|
"epoch": 4.77,
|
|
"learning_rate": 0.00026818931612074016,
|
|
"loss": 1.6081,
|
|
"step": 15330
|
|
},
|
|
{
|
|
"epoch": 4.77,
|
|
"learning_rate": 0.000267945587306566,
|
|
"loss": 1.5092,
|
|
"step": 15340
|
|
},
|
|
{
|
|
"epoch": 4.78,
|
|
"learning_rate": 0.00026770184134628053,
|
|
"loss": 1.5375,
|
|
"step": 15350
|
|
},
|
|
{
|
|
"epoch": 4.78,
|
|
"learning_rate": 0.0002674580784727706,
|
|
"loss": 1.5024,
|
|
"step": 15360
|
|
},
|
|
{
|
|
"epoch": 4.78,
|
|
"learning_rate": 0.00026721429891893956,
|
|
"loss": 1.5059,
|
|
"step": 15370
|
|
},
|
|
{
|
|
"epoch": 4.78,
|
|
"learning_rate": 0.00026697050291770656,
|
|
"loss": 1.4756,
|
|
"step": 15380
|
|
},
|
|
{
|
|
"epoch": 4.79,
|
|
"learning_rate": 0.00026672669070200656,
|
|
"loss": 1.4847,
|
|
"step": 15390
|
|
},
|
|
{
|
|
"epoch": 4.79,
|
|
"learning_rate": 0.00026648286250478993,
|
|
"loss": 1.3507,
|
|
"step": 15400
|
|
},
|
|
{
|
|
"epoch": 4.79,
|
|
"learning_rate": 0.00026623901855902214,
|
|
"loss": 1.5594,
|
|
"step": 15410
|
|
},
|
|
{
|
|
"epoch": 4.8,
|
|
"learning_rate": 0.00026599515909768413,
|
|
"loss": 1.5085,
|
|
"step": 15420
|
|
},
|
|
{
|
|
"epoch": 4.8,
|
|
"learning_rate": 0.0002657512843537712,
|
|
"loss": 1.5137,
|
|
"step": 15430
|
|
},
|
|
{
|
|
"epoch": 4.8,
|
|
"learning_rate": 0.00026550739456029373,
|
|
"loss": 1.4379,
|
|
"step": 15440
|
|
},
|
|
{
|
|
"epoch": 4.81,
|
|
"learning_rate": 0.000265263489950276,
|
|
"loss": 1.5422,
|
|
"step": 15450
|
|
},
|
|
{
|
|
"epoch": 4.81,
|
|
"learning_rate": 0.00026501957075675676,
|
|
"loss": 1.488,
|
|
"step": 15460
|
|
},
|
|
{
|
|
"epoch": 4.81,
|
|
"learning_rate": 0.0002647756372127887,
|
|
"loss": 1.5011,
|
|
"step": 15470
|
|
},
|
|
{
|
|
"epoch": 4.82,
|
|
"learning_rate": 0.00026453168955143785,
|
|
"loss": 1.5074,
|
|
"step": 15480
|
|
},
|
|
{
|
|
"epoch": 4.82,
|
|
"learning_rate": 0.00026428772800578433,
|
|
"loss": 1.4921,
|
|
"step": 15490
|
|
},
|
|
{
|
|
"epoch": 4.82,
|
|
"learning_rate": 0.000264043752808921,
|
|
"loss": 1.5019,
|
|
"step": 15500
|
|
},
|
|
{
|
|
"epoch": 4.83,
|
|
"learning_rate": 0.000263799764193954,
|
|
"loss": 1.553,
|
|
"step": 15510
|
|
},
|
|
{
|
|
"epoch": 4.83,
|
|
"learning_rate": 0.0002635557623940023,
|
|
"loss": 1.4387,
|
|
"step": 15520
|
|
},
|
|
{
|
|
"epoch": 4.83,
|
|
"learning_rate": 0.00026331174764219735,
|
|
"loss": 1.5472,
|
|
"step": 15530
|
|
},
|
|
{
|
|
"epoch": 4.83,
|
|
"learning_rate": 0.0002630677201716831,
|
|
"loss": 1.495,
|
|
"step": 15540
|
|
},
|
|
{
|
|
"epoch": 4.84,
|
|
"learning_rate": 0.0002628236802156155,
|
|
"loss": 1.6113,
|
|
"step": 15550
|
|
},
|
|
{
|
|
"epoch": 4.84,
|
|
"learning_rate": 0.00026257962800716275,
|
|
"loss": 1.3589,
|
|
"step": 15560
|
|
},
|
|
{
|
|
"epoch": 4.84,
|
|
"learning_rate": 0.0002623355637795043,
|
|
"loss": 1.4904,
|
|
"step": 15570
|
|
},
|
|
{
|
|
"epoch": 4.85,
|
|
"learning_rate": 0.0002620914877658314,
|
|
"loss": 1.4045,
|
|
"step": 15580
|
|
},
|
|
{
|
|
"epoch": 4.85,
|
|
"learning_rate": 0.0002618474001993465,
|
|
"loss": 1.4139,
|
|
"step": 15590
|
|
},
|
|
{
|
|
"epoch": 4.85,
|
|
"learning_rate": 0.00026160330131326303,
|
|
"loss": 1.49,
|
|
"step": 15600
|
|
},
|
|
{
|
|
"epoch": 4.86,
|
|
"learning_rate": 0.0002613591913408053,
|
|
"loss": 1.464,
|
|
"step": 15610
|
|
},
|
|
{
|
|
"epoch": 4.86,
|
|
"learning_rate": 0.0002611150705152082,
|
|
"loss": 1.5029,
|
|
"step": 15620
|
|
},
|
|
{
|
|
"epoch": 4.86,
|
|
"learning_rate": 0.00026087093906971697,
|
|
"loss": 1.5159,
|
|
"step": 15630
|
|
},
|
|
{
|
|
"epoch": 4.87,
|
|
"learning_rate": 0.00026062679723758684,
|
|
"loss": 1.4139,
|
|
"step": 15640
|
|
},
|
|
{
|
|
"epoch": 4.87,
|
|
"learning_rate": 0.0002603826452520834,
|
|
"loss": 1.5064,
|
|
"step": 15650
|
|
},
|
|
{
|
|
"epoch": 4.87,
|
|
"learning_rate": 0.0002601384833464815,
|
|
"loss": 1.5791,
|
|
"step": 15660
|
|
},
|
|
{
|
|
"epoch": 4.88,
|
|
"learning_rate": 0.00025989431175406564,
|
|
"loss": 1.5537,
|
|
"step": 15670
|
|
},
|
|
{
|
|
"epoch": 4.88,
|
|
"learning_rate": 0.0002596501307081296,
|
|
"loss": 1.6391,
|
|
"step": 15680
|
|
},
|
|
{
|
|
"epoch": 4.88,
|
|
"learning_rate": 0.0002594059404419761,
|
|
"loss": 1.4464,
|
|
"step": 15690
|
|
},
|
|
{
|
|
"epoch": 4.88,
|
|
"learning_rate": 0.0002591617411889168,
|
|
"loss": 1.5652,
|
|
"step": 15700
|
|
},
|
|
{
|
|
"epoch": 4.89,
|
|
"learning_rate": 0.0002589175331822719,
|
|
"loss": 1.6393,
|
|
"step": 15710
|
|
},
|
|
{
|
|
"epoch": 4.89,
|
|
"learning_rate": 0.00025867331665536985,
|
|
"loss": 1.506,
|
|
"step": 15720
|
|
},
|
|
{
|
|
"epoch": 4.89,
|
|
"learning_rate": 0.0002584290918415475,
|
|
"loss": 1.4811,
|
|
"step": 15730
|
|
},
|
|
{
|
|
"epoch": 4.9,
|
|
"learning_rate": 0.0002581848589741492,
|
|
"loss": 1.563,
|
|
"step": 15740
|
|
},
|
|
{
|
|
"epoch": 4.9,
|
|
"learning_rate": 0.0002579406182865274,
|
|
"loss": 1.5751,
|
|
"step": 15750
|
|
},
|
|
{
|
|
"epoch": 4.9,
|
|
"learning_rate": 0.0002576963700120418,
|
|
"loss": 1.4409,
|
|
"step": 15760
|
|
},
|
|
{
|
|
"epoch": 4.91,
|
|
"learning_rate": 0.00025745211438405954,
|
|
"loss": 1.5078,
|
|
"step": 15770
|
|
},
|
|
{
|
|
"epoch": 4.91,
|
|
"learning_rate": 0.0002572078516359545,
|
|
"loss": 1.505,
|
|
"step": 15780
|
|
},
|
|
{
|
|
"epoch": 4.91,
|
|
"learning_rate": 0.00025696358200110765,
|
|
"loss": 1.5333,
|
|
"step": 15790
|
|
},
|
|
{
|
|
"epoch": 4.92,
|
|
"learning_rate": 0.0002567193057129063,
|
|
"loss": 1.4718,
|
|
"step": 15800
|
|
},
|
|
{
|
|
"epoch": 4.92,
|
|
"learning_rate": 0.0002564750230047443,
|
|
"loss": 1.5388,
|
|
"step": 15810
|
|
},
|
|
{
|
|
"epoch": 4.92,
|
|
"learning_rate": 0.0002562307341100216,
|
|
"loss": 1.4473,
|
|
"step": 15820
|
|
},
|
|
{
|
|
"epoch": 4.92,
|
|
"learning_rate": 0.000255986439262144,
|
|
"loss": 1.4389,
|
|
"step": 15830
|
|
},
|
|
{
|
|
"epoch": 4.93,
|
|
"learning_rate": 0.00025574213869452287,
|
|
"loss": 1.4496,
|
|
"step": 15840
|
|
},
|
|
{
|
|
"epoch": 4.93,
|
|
"learning_rate": 0.0002554978326405754,
|
|
"loss": 1.4992,
|
|
"step": 15850
|
|
},
|
|
{
|
|
"epoch": 4.93,
|
|
"learning_rate": 0.0002552535213337237,
|
|
"loss": 1.5028,
|
|
"step": 15860
|
|
},
|
|
{
|
|
"epoch": 4.94,
|
|
"learning_rate": 0.00025500920500739506,
|
|
"loss": 1.5433,
|
|
"step": 15870
|
|
},
|
|
{
|
|
"epoch": 4.94,
|
|
"learning_rate": 0.0002547648838950214,
|
|
"loss": 1.4839,
|
|
"step": 15880
|
|
},
|
|
{
|
|
"epoch": 4.94,
|
|
"learning_rate": 0.0002545205582300395,
|
|
"loss": 1.4982,
|
|
"step": 15890
|
|
},
|
|
{
|
|
"epoch": 4.95,
|
|
"learning_rate": 0.00025427622824589013,
|
|
"loss": 1.5381,
|
|
"step": 15900
|
|
},
|
|
{
|
|
"epoch": 4.95,
|
|
"learning_rate": 0.0002540318941760186,
|
|
"loss": 1.6486,
|
|
"step": 15910
|
|
},
|
|
{
|
|
"epoch": 4.95,
|
|
"learning_rate": 0.0002537875562538737,
|
|
"loss": 1.5377,
|
|
"step": 15920
|
|
},
|
|
{
|
|
"epoch": 4.96,
|
|
"learning_rate": 0.0002535432147129081,
|
|
"loss": 1.4335,
|
|
"step": 15930
|
|
},
|
|
{
|
|
"epoch": 4.96,
|
|
"learning_rate": 0.0002532988697865781,
|
|
"loss": 1.3687,
|
|
"step": 15940
|
|
},
|
|
{
|
|
"epoch": 4.96,
|
|
"learning_rate": 0.00025305452170834293,
|
|
"loss": 1.4713,
|
|
"step": 15950
|
|
},
|
|
{
|
|
"epoch": 4.97,
|
|
"learning_rate": 0.00025281017071166503,
|
|
"loss": 1.5098,
|
|
"step": 15960
|
|
},
|
|
{
|
|
"epoch": 4.97,
|
|
"learning_rate": 0.00025256581703000935,
|
|
"loss": 1.596,
|
|
"step": 15970
|
|
},
|
|
{
|
|
"epoch": 4.97,
|
|
"learning_rate": 0.00025232146089684387,
|
|
"loss": 1.45,
|
|
"step": 15980
|
|
},
|
|
{
|
|
"epoch": 4.97,
|
|
"learning_rate": 0.00025207710254563867,
|
|
"loss": 1.531,
|
|
"step": 15990
|
|
},
|
|
{
|
|
"epoch": 4.98,
|
|
"learning_rate": 0.0002518327422098657,
|
|
"loss": 1.5411,
|
|
"step": 16000
|
|
},
|
|
{
|
|
"epoch": 4.98,
|
|
"learning_rate": 0.0002515883801229993,
|
|
"loss": 1.5545,
|
|
"step": 16010
|
|
},
|
|
{
|
|
"epoch": 4.98,
|
|
"learning_rate": 0.00025134401651851504,
|
|
"loss": 1.5417,
|
|
"step": 16020
|
|
},
|
|
{
|
|
"epoch": 4.99,
|
|
"learning_rate": 0.00025109965162989015,
|
|
"loss": 1.5805,
|
|
"step": 16030
|
|
},
|
|
{
|
|
"epoch": 4.99,
|
|
"learning_rate": 0.00025085528569060314,
|
|
"loss": 1.5122,
|
|
"step": 16040
|
|
},
|
|
{
|
|
"epoch": 4.99,
|
|
"learning_rate": 0.0002506109189341334,
|
|
"loss": 1.386,
|
|
"step": 16050
|
|
},
|
|
{
|
|
"epoch": 5.0,
|
|
"learning_rate": 0.00025036655159396123,
|
|
"loss": 1.5122,
|
|
"step": 16060
|
|
},
|
|
{
|
|
"epoch": 5.0,
|
|
"learning_rate": 0.00025012218390356726,
|
|
"loss": 1.4323,
|
|
"step": 16070
|
|
},
|
|
{
|
|
"epoch": 5.0,
|
|
"learning_rate": 0.0002498778160964328,
|
|
"loss": 1.2918,
|
|
"step": 16080
|
|
},
|
|
{
|
|
"epoch": 5.01,
|
|
"learning_rate": 0.00024963344840603884,
|
|
"loss": 1.3107,
|
|
"step": 16090
|
|
},
|
|
{
|
|
"epoch": 5.01,
|
|
"learning_rate": 0.0002493890810658666,
|
|
"loss": 1.43,
|
|
"step": 16100
|
|
},
|
|
{
|
|
"epoch": 5.01,
|
|
"learning_rate": 0.0002491447143093968,
|
|
"loss": 1.4013,
|
|
"step": 16110
|
|
},
|
|
{
|
|
"epoch": 5.02,
|
|
"learning_rate": 0.00024890034837010986,
|
|
"loss": 1.1893,
|
|
"step": 16120
|
|
},
|
|
{
|
|
"epoch": 5.02,
|
|
"learning_rate": 0.000248655983481485,
|
|
"loss": 1.4037,
|
|
"step": 16130
|
|
},
|
|
{
|
|
"epoch": 5.02,
|
|
"learning_rate": 0.0002484116198770008,
|
|
"loss": 1.4053,
|
|
"step": 16140
|
|
},
|
|
{
|
|
"epoch": 5.02,
|
|
"learning_rate": 0.00024816725779013433,
|
|
"loss": 1.3452,
|
|
"step": 16150
|
|
},
|
|
{
|
|
"epoch": 5.03,
|
|
"learning_rate": 0.00024792289745436145,
|
|
"loss": 1.5493,
|
|
"step": 16160
|
|
},
|
|
{
|
|
"epoch": 5.03,
|
|
"learning_rate": 0.00024767853910315614,
|
|
"loss": 1.3463,
|
|
"step": 16170
|
|
},
|
|
{
|
|
"epoch": 5.03,
|
|
"learning_rate": 0.0002474341829699906,
|
|
"loss": 1.3293,
|
|
"step": 16180
|
|
},
|
|
{
|
|
"epoch": 5.04,
|
|
"learning_rate": 0.00024718982928833503,
|
|
"loss": 1.4586,
|
|
"step": 16190
|
|
},
|
|
{
|
|
"epoch": 5.04,
|
|
"learning_rate": 0.00024694547829165714,
|
|
"loss": 1.3472,
|
|
"step": 16200
|
|
},
|
|
{
|
|
"epoch": 5.04,
|
|
"learning_rate": 0.00024670113021342196,
|
|
"loss": 1.3472,
|
|
"step": 16210
|
|
},
|
|
{
|
|
"epoch": 5.05,
|
|
"learning_rate": 0.00024645678528709196,
|
|
"loss": 1.4781,
|
|
"step": 16220
|
|
},
|
|
{
|
|
"epoch": 5.05,
|
|
"learning_rate": 0.00024621244374612637,
|
|
"loss": 1.2548,
|
|
"step": 16230
|
|
},
|
|
{
|
|
"epoch": 5.05,
|
|
"learning_rate": 0.0002459681058239814,
|
|
"loss": 1.3688,
|
|
"step": 16240
|
|
},
|
|
{
|
|
"epoch": 5.06,
|
|
"learning_rate": 0.00024572377175410983,
|
|
"loss": 1.3349,
|
|
"step": 16250
|
|
},
|
|
{
|
|
"epoch": 5.06,
|
|
"learning_rate": 0.0002454794417699605,
|
|
"loss": 1.3376,
|
|
"step": 16260
|
|
},
|
|
{
|
|
"epoch": 5.06,
|
|
"learning_rate": 0.0002452351161049786,
|
|
"loss": 1.3762,
|
|
"step": 16270
|
|
},
|
|
{
|
|
"epoch": 5.06,
|
|
"learning_rate": 0.000244990794992605,
|
|
"loss": 1.371,
|
|
"step": 16280
|
|
},
|
|
{
|
|
"epoch": 5.07,
|
|
"learning_rate": 0.0002447464786662764,
|
|
"loss": 1.2863,
|
|
"step": 16290
|
|
},
|
|
{
|
|
"epoch": 5.07,
|
|
"learning_rate": 0.00024450216735942467,
|
|
"loss": 1.5088,
|
|
"step": 16300
|
|
},
|
|
{
|
|
"epoch": 5.07,
|
|
"learning_rate": 0.00024425786130547714,
|
|
"loss": 1.3161,
|
|
"step": 16310
|
|
},
|
|
{
|
|
"epoch": 5.08,
|
|
"learning_rate": 0.0002440379905410811,
|
|
"loss": 1.2766,
|
|
"step": 16320
|
|
},
|
|
{
|
|
"epoch": 5.08,
|
|
"learning_rate": 0.00024379369511072545,
|
|
"loss": 1.3914,
|
|
"step": 16330
|
|
},
|
|
{
|
|
"epoch": 5.08,
|
|
"learning_rate": 0.00024354940561018384,
|
|
"loss": 1.4055,
|
|
"step": 16340
|
|
},
|
|
{
|
|
"epoch": 5.09,
|
|
"learning_rate": 0.00024330512227286276,
|
|
"loss": 1.2868,
|
|
"step": 16350
|
|
},
|
|
{
|
|
"epoch": 5.09,
|
|
"learning_rate": 0.00024306084533216255,
|
|
"loss": 1.3467,
|
|
"step": 16360
|
|
},
|
|
{
|
|
"epoch": 5.09,
|
|
"learning_rate": 0.00024281657502147767,
|
|
"loss": 1.3891,
|
|
"step": 16370
|
|
},
|
|
{
|
|
"epoch": 5.1,
|
|
"learning_rate": 0.00024257231157419627,
|
|
"loss": 1.2334,
|
|
"step": 16380
|
|
},
|
|
{
|
|
"epoch": 5.1,
|
|
"learning_rate": 0.00024232805522369973,
|
|
"loss": 1.3768,
|
|
"step": 16390
|
|
},
|
|
{
|
|
"epoch": 5.1,
|
|
"learning_rate": 0.0002420838062033628,
|
|
"loss": 1.416,
|
|
"step": 16400
|
|
},
|
|
{
|
|
"epoch": 5.11,
|
|
"learning_rate": 0.00024183956474655333,
|
|
"loss": 1.3544,
|
|
"step": 16410
|
|
},
|
|
{
|
|
"epoch": 5.11,
|
|
"learning_rate": 0.00024159533108663174,
|
|
"loss": 1.3642,
|
|
"step": 16420
|
|
},
|
|
{
|
|
"epoch": 5.11,
|
|
"learning_rate": 0.00024135110545695111,
|
|
"loss": 1.4016,
|
|
"step": 16430
|
|
},
|
|
{
|
|
"epoch": 5.11,
|
|
"learning_rate": 0.00024110688809085673,
|
|
"loss": 1.1986,
|
|
"step": 16440
|
|
},
|
|
{
|
|
"epoch": 5.12,
|
|
"learning_rate": 0.00024086267922168625,
|
|
"loss": 1.3907,
|
|
"step": 16450
|
|
},
|
|
{
|
|
"epoch": 5.12,
|
|
"learning_rate": 0.00024061847908276874,
|
|
"loss": 1.4162,
|
|
"step": 16460
|
|
},
|
|
{
|
|
"epoch": 5.12,
|
|
"learning_rate": 0.0002403742879074256,
|
|
"loss": 1.3866,
|
|
"step": 16470
|
|
},
|
|
{
|
|
"epoch": 5.13,
|
|
"learning_rate": 0.000240130105928969,
|
|
"loss": 1.4066,
|
|
"step": 16480
|
|
},
|
|
{
|
|
"epoch": 5.13,
|
|
"learning_rate": 0.00023988593338070274,
|
|
"loss": 1.3238,
|
|
"step": 16490
|
|
},
|
|
{
|
|
"epoch": 5.13,
|
|
"learning_rate": 0.00023964177049592153,
|
|
"loss": 1.3427,
|
|
"step": 16500
|
|
},
|
|
{
|
|
"epoch": 5.14,
|
|
"learning_rate": 0.00023939761750791066,
|
|
"loss": 1.3429,
|
|
"step": 16510
|
|
},
|
|
{
|
|
"epoch": 5.14,
|
|
"learning_rate": 0.0002391534746499462,
|
|
"loss": 1.3707,
|
|
"step": 16520
|
|
},
|
|
{
|
|
"epoch": 5.14,
|
|
"learning_rate": 0.00023890934215529432,
|
|
"loss": 1.431,
|
|
"step": 16530
|
|
},
|
|
{
|
|
"epoch": 5.15,
|
|
"learning_rate": 0.00023866522025721163,
|
|
"loss": 1.2703,
|
|
"step": 16540
|
|
},
|
|
{
|
|
"epoch": 5.15,
|
|
"learning_rate": 0.0002384211091889442,
|
|
"loss": 1.3906,
|
|
"step": 16550
|
|
},
|
|
{
|
|
"epoch": 5.15,
|
|
"learning_rate": 0.00023817700918372806,
|
|
"loss": 1.3486,
|
|
"step": 16560
|
|
},
|
|
{
|
|
"epoch": 5.16,
|
|
"learning_rate": 0.00023793292047478857,
|
|
"loss": 1.3592,
|
|
"step": 16570
|
|
},
|
|
{
|
|
"epoch": 5.16,
|
|
"learning_rate": 0.0002376888432953402,
|
|
"loss": 1.3861,
|
|
"step": 16580
|
|
},
|
|
{
|
|
"epoch": 5.16,
|
|
"learning_rate": 0.00023744477787858643,
|
|
"loss": 1.3926,
|
|
"step": 16590
|
|
},
|
|
{
|
|
"epoch": 5.16,
|
|
"learning_rate": 0.00023720072445771974,
|
|
"loss": 1.4087,
|
|
"step": 16600
|
|
},
|
|
{
|
|
"epoch": 5.17,
|
|
"learning_rate": 0.000236956683265921,
|
|
"loss": 1.3686,
|
|
"step": 16610
|
|
},
|
|
{
|
|
"epoch": 5.17,
|
|
"learning_rate": 0.00023671265453635917,
|
|
"loss": 1.3718,
|
|
"step": 16620
|
|
},
|
|
{
|
|
"epoch": 5.17,
|
|
"learning_rate": 0.00023646863850219164,
|
|
"loss": 1.3282,
|
|
"step": 16630
|
|
},
|
|
{
|
|
"epoch": 5.18,
|
|
"learning_rate": 0.0002362246353965635,
|
|
"loss": 1.4175,
|
|
"step": 16640
|
|
},
|
|
{
|
|
"epoch": 5.18,
|
|
"learning_rate": 0.00023598064545260749,
|
|
"loss": 1.3373,
|
|
"step": 16650
|
|
},
|
|
{
|
|
"epoch": 5.18,
|
|
"learning_rate": 0.00023573666890344374,
|
|
"loss": 1.427,
|
|
"step": 16660
|
|
},
|
|
{
|
|
"epoch": 5.19,
|
|
"learning_rate": 0.0002354927059821798,
|
|
"loss": 1.3301,
|
|
"step": 16670
|
|
},
|
|
{
|
|
"epoch": 5.19,
|
|
"learning_rate": 0.00023524875692190996,
|
|
"loss": 1.4515,
|
|
"step": 16680
|
|
},
|
|
{
|
|
"epoch": 5.19,
|
|
"learning_rate": 0.00023500482195571538,
|
|
"loss": 1.4536,
|
|
"step": 16690
|
|
},
|
|
{
|
|
"epoch": 5.2,
|
|
"learning_rate": 0.00023476090131666367,
|
|
"loss": 1.399,
|
|
"step": 16700
|
|
},
|
|
{
|
|
"epoch": 5.2,
|
|
"learning_rate": 0.00023451699523780887,
|
|
"loss": 1.3825,
|
|
"step": 16710
|
|
},
|
|
{
|
|
"epoch": 5.2,
|
|
"learning_rate": 0.00023427310395219086,
|
|
"loss": 1.4483,
|
|
"step": 16720
|
|
},
|
|
{
|
|
"epoch": 5.2,
|
|
"learning_rate": 0.0002340292276928359,
|
|
"loss": 1.4247,
|
|
"step": 16730
|
|
},
|
|
{
|
|
"epoch": 5.21,
|
|
"learning_rate": 0.00023378536669275531,
|
|
"loss": 1.4065,
|
|
"step": 16740
|
|
},
|
|
{
|
|
"epoch": 5.21,
|
|
"learning_rate": 0.00023354152118494617,
|
|
"loss": 1.3972,
|
|
"step": 16750
|
|
},
|
|
{
|
|
"epoch": 5.21,
|
|
"learning_rate": 0.0002332976914023907,
|
|
"loss": 1.2382,
|
|
"step": 16760
|
|
},
|
|
{
|
|
"epoch": 5.22,
|
|
"learning_rate": 0.00023305387757805598,
|
|
"loss": 1.3391,
|
|
"step": 16770
|
|
},
|
|
{
|
|
"epoch": 5.22,
|
|
"learning_rate": 0.00023281007994489404,
|
|
"loss": 1.4444,
|
|
"step": 16780
|
|
},
|
|
{
|
|
"epoch": 5.22,
|
|
"learning_rate": 0.00023256629873584107,
|
|
"loss": 1.4621,
|
|
"step": 16790
|
|
},
|
|
{
|
|
"epoch": 5.23,
|
|
"learning_rate": 0.00023232253418381822,
|
|
"loss": 1.4319,
|
|
"step": 16800
|
|
},
|
|
{
|
|
"epoch": 5.23,
|
|
"learning_rate": 0.00023207878652173002,
|
|
"loss": 1.402,
|
|
"step": 16810
|
|
},
|
|
{
|
|
"epoch": 5.23,
|
|
"learning_rate": 0.00023183505598246533,
|
|
"loss": 1.4485,
|
|
"step": 16820
|
|
},
|
|
{
|
|
"epoch": 5.24,
|
|
"learning_rate": 0.00023159134279889649,
|
|
"loss": 1.4214,
|
|
"step": 16830
|
|
},
|
|
{
|
|
"epoch": 5.24,
|
|
"learning_rate": 0.00023134764720387916,
|
|
"loss": 1.3234,
|
|
"step": 16840
|
|
},
|
|
{
|
|
"epoch": 5.24,
|
|
"learning_rate": 0.0002311039694302523,
|
|
"loss": 1.4023,
|
|
"step": 16850
|
|
},
|
|
{
|
|
"epoch": 5.25,
|
|
"learning_rate": 0.00023086030971083797,
|
|
"loss": 1.3859,
|
|
"step": 16860
|
|
},
|
|
{
|
|
"epoch": 5.25,
|
|
"learning_rate": 0.0002306166682784408,
|
|
"loss": 1.3741,
|
|
"step": 16870
|
|
},
|
|
{
|
|
"epoch": 5.25,
|
|
"learning_rate": 0.00023037304536584793,
|
|
"loss": 1.437,
|
|
"step": 16880
|
|
},
|
|
{
|
|
"epoch": 5.25,
|
|
"learning_rate": 0.00023012944120582896,
|
|
"loss": 1.3678,
|
|
"step": 16890
|
|
},
|
|
{
|
|
"epoch": 5.26,
|
|
"learning_rate": 0.00022988585603113545,
|
|
"loss": 1.3119,
|
|
"step": 16900
|
|
},
|
|
{
|
|
"epoch": 5.26,
|
|
"learning_rate": 0.0002296422900745008,
|
|
"loss": 1.386,
|
|
"step": 16910
|
|
},
|
|
{
|
|
"epoch": 5.26,
|
|
"learning_rate": 0.0002293987435686401,
|
|
"loss": 1.4575,
|
|
"step": 16920
|
|
},
|
|
{
|
|
"epoch": 5.27,
|
|
"learning_rate": 0.00022915521674624997,
|
|
"loss": 1.469,
|
|
"step": 16930
|
|
},
|
|
{
|
|
"epoch": 5.27,
|
|
"learning_rate": 0.0002289117098400081,
|
|
"loss": 1.3983,
|
|
"step": 16940
|
|
},
|
|
{
|
|
"epoch": 5.27,
|
|
"learning_rate": 0.0002286682230825731,
|
|
"loss": 1.4609,
|
|
"step": 16950
|
|
},
|
|
{
|
|
"epoch": 5.28,
|
|
"learning_rate": 0.00022842475670658435,
|
|
"loss": 1.4824,
|
|
"step": 16960
|
|
},
|
|
{
|
|
"epoch": 5.28,
|
|
"learning_rate": 0.00022818131094466196,
|
|
"loss": 1.2775,
|
|
"step": 16970
|
|
},
|
|
{
|
|
"epoch": 5.28,
|
|
"learning_rate": 0.00022793788602940593,
|
|
"loss": 1.3613,
|
|
"step": 16980
|
|
},
|
|
{
|
|
"epoch": 5.29,
|
|
"learning_rate": 0.00022769448219339688,
|
|
"loss": 1.3435,
|
|
"step": 16990
|
|
},
|
|
{
|
|
"epoch": 5.29,
|
|
"learning_rate": 0.00022745109966919487,
|
|
"loss": 1.3608,
|
|
"step": 17000
|
|
},
|
|
{
|
|
"epoch": 5.29,
|
|
"learning_rate": 0.0002272077386893397,
|
|
"loss": 1.3963,
|
|
"step": 17010
|
|
},
|
|
{
|
|
"epoch": 5.3,
|
|
"learning_rate": 0.0002269643994863507,
|
|
"loss": 1.2912,
|
|
"step": 17020
|
|
},
|
|
{
|
|
"epoch": 5.3,
|
|
"learning_rate": 0.00022672108229272625,
|
|
"loss": 1.4451,
|
|
"step": 17030
|
|
},
|
|
{
|
|
"epoch": 5.3,
|
|
"learning_rate": 0.00022647778734094382,
|
|
"loss": 1.4312,
|
|
"step": 17040
|
|
},
|
|
{
|
|
"epoch": 5.3,
|
|
"learning_rate": 0.0002262345148634594,
|
|
"loss": 1.4474,
|
|
"step": 17050
|
|
},
|
|
{
|
|
"epoch": 5.31,
|
|
"learning_rate": 0.00022601558904135623,
|
|
"loss": 1.359,
|
|
"step": 17060
|
|
},
|
|
{
|
|
"epoch": 5.31,
|
|
"learning_rate": 0.00022577235990537794,
|
|
"loss": 1.3494,
|
|
"step": 17070
|
|
},
|
|
{
|
|
"epoch": 5.31,
|
|
"learning_rate": 0.00022552915391769855,
|
|
"loss": 1.5048,
|
|
"step": 17080
|
|
},
|
|
{
|
|
"epoch": 5.32,
|
|
"learning_rate": 0.00022528597131068906,
|
|
"loss": 1.4696,
|
|
"step": 17090
|
|
},
|
|
{
|
|
"epoch": 5.32,
|
|
"learning_rate": 0.00022504281231669842,
|
|
"loss": 1.3764,
|
|
"step": 17100
|
|
},
|
|
{
|
|
"epoch": 5.32,
|
|
"learning_rate": 0.0002247996771680528,
|
|
"loss": 1.2933,
|
|
"step": 17110
|
|
},
|
|
{
|
|
"epoch": 5.33,
|
|
"learning_rate": 0.00022455656609705565,
|
|
"loss": 1.3735,
|
|
"step": 17120
|
|
},
|
|
{
|
|
"epoch": 5.33,
|
|
"learning_rate": 0.00022431347933598756,
|
|
"loss": 1.4258,
|
|
"step": 17130
|
|
},
|
|
{
|
|
"epoch": 5.33,
|
|
"learning_rate": 0.00022407041711710555,
|
|
"loss": 1.4216,
|
|
"step": 17140
|
|
},
|
|
{
|
|
"epoch": 5.34,
|
|
"learning_rate": 0.0002238273796726437,
|
|
"loss": 1.4688,
|
|
"step": 17150
|
|
},
|
|
{
|
|
"epoch": 5.34,
|
|
"learning_rate": 0.000223584367234812,
|
|
"loss": 1.4486,
|
|
"step": 17160
|
|
},
|
|
{
|
|
"epoch": 5.34,
|
|
"learning_rate": 0.00022334138003579672,
|
|
"loss": 1.3775,
|
|
"step": 17170
|
|
},
|
|
{
|
|
"epoch": 5.34,
|
|
"learning_rate": 0.00022309841830775993,
|
|
"loss": 1.3852,
|
|
"step": 17180
|
|
},
|
|
{
|
|
"epoch": 5.35,
|
|
"learning_rate": 0.00022285548228283942,
|
|
"loss": 1.348,
|
|
"step": 17190
|
|
},
|
|
{
|
|
"epoch": 5.35,
|
|
"learning_rate": 0.0002226125721931484,
|
|
"loss": 1.4084,
|
|
"step": 17200
|
|
},
|
|
{
|
|
"epoch": 5.35,
|
|
"learning_rate": 0.00022236968827077537,
|
|
"loss": 1.4103,
|
|
"step": 17210
|
|
},
|
|
{
|
|
"epoch": 5.36,
|
|
"learning_rate": 0.00022212683074778383,
|
|
"loss": 1.4331,
|
|
"step": 17220
|
|
},
|
|
{
|
|
"epoch": 5.36,
|
|
"learning_rate": 0.00022188399985621185,
|
|
"loss": 1.3972,
|
|
"step": 17230
|
|
},
|
|
{
|
|
"epoch": 5.36,
|
|
"learning_rate": 0.0002216411958280723,
|
|
"loss": 1.4354,
|
|
"step": 17240
|
|
},
|
|
{
|
|
"epoch": 5.37,
|
|
"learning_rate": 0.00022139841889535234,
|
|
"loss": 1.3772,
|
|
"step": 17250
|
|
},
|
|
{
|
|
"epoch": 5.37,
|
|
"learning_rate": 0.00022115566929001304,
|
|
"loss": 1.4245,
|
|
"step": 17260
|
|
},
|
|
{
|
|
"epoch": 5.37,
|
|
"learning_rate": 0.00022091294724398952,
|
|
"loss": 1.3302,
|
|
"step": 17270
|
|
},
|
|
{
|
|
"epoch": 5.38,
|
|
"learning_rate": 0.00022067025298919073,
|
|
"loss": 1.3565,
|
|
"step": 17280
|
|
},
|
|
{
|
|
"epoch": 5.38,
|
|
"learning_rate": 0.00022042758675749883,
|
|
"loss": 1.3372,
|
|
"step": 17290
|
|
},
|
|
{
|
|
"epoch": 5.38,
|
|
"learning_rate": 0.0002201849487807692,
|
|
"loss": 1.418,
|
|
"step": 17300
|
|
},
|
|
{
|
|
"epoch": 5.39,
|
|
"learning_rate": 0.0002199423392908303,
|
|
"loss": 1.3701,
|
|
"step": 17310
|
|
},
|
|
{
|
|
"epoch": 5.39,
|
|
"learning_rate": 0.0002196997585194835,
|
|
"loss": 1.3738,
|
|
"step": 17320
|
|
},
|
|
{
|
|
"epoch": 5.39,
|
|
"learning_rate": 0.00021945720669850239,
|
|
"loss": 1.437,
|
|
"step": 17330
|
|
},
|
|
{
|
|
"epoch": 5.39,
|
|
"learning_rate": 0.00021921468405963323,
|
|
"loss": 1.5081,
|
|
"step": 17340
|
|
},
|
|
{
|
|
"epoch": 5.4,
|
|
"learning_rate": 0.00021897219083459433,
|
|
"loss": 1.5451,
|
|
"step": 17350
|
|
},
|
|
{
|
|
"epoch": 5.4,
|
|
"learning_rate": 0.0002187297272550758,
|
|
"loss": 1.465,
|
|
"step": 17360
|
|
},
|
|
{
|
|
"epoch": 5.4,
|
|
"learning_rate": 0.0002184872935527394,
|
|
"loss": 1.3977,
|
|
"step": 17370
|
|
},
|
|
{
|
|
"epoch": 5.41,
|
|
"learning_rate": 0.00021824488995921844,
|
|
"loss": 1.2904,
|
|
"step": 17380
|
|
},
|
|
{
|
|
"epoch": 5.41,
|
|
"learning_rate": 0.00021800251670611747,
|
|
"loss": 1.4823,
|
|
"step": 17390
|
|
},
|
|
{
|
|
"epoch": 5.41,
|
|
"learning_rate": 0.0002177601740250119,
|
|
"loss": 1.4138,
|
|
"step": 17400
|
|
},
|
|
{
|
|
"epoch": 5.42,
|
|
"learning_rate": 0.0002175178621474483,
|
|
"loss": 1.2277,
|
|
"step": 17410
|
|
},
|
|
{
|
|
"epoch": 5.42,
|
|
"learning_rate": 0.00021727558130494332,
|
|
"loss": 1.4126,
|
|
"step": 17420
|
|
},
|
|
{
|
|
"epoch": 5.42,
|
|
"learning_rate": 0.0002170333317289843,
|
|
"loss": 1.2922,
|
|
"step": 17430
|
|
},
|
|
{
|
|
"epoch": 5.43,
|
|
"learning_rate": 0.00021679111365102856,
|
|
"loss": 1.4362,
|
|
"step": 17440
|
|
},
|
|
{
|
|
"epoch": 5.43,
|
|
"learning_rate": 0.00021654892730250337,
|
|
"loss": 1.4516,
|
|
"step": 17450
|
|
},
|
|
{
|
|
"epoch": 5.43,
|
|
"learning_rate": 0.00021630677291480558,
|
|
"loss": 1.4139,
|
|
"step": 17460
|
|
},
|
|
{
|
|
"epoch": 5.44,
|
|
"learning_rate": 0.00021606465071930176,
|
|
"loss": 1.3357,
|
|
"step": 17470
|
|
},
|
|
{
|
|
"epoch": 5.44,
|
|
"learning_rate": 0.00021582256094732758,
|
|
"loss": 1.4526,
|
|
"step": 17480
|
|
},
|
|
{
|
|
"epoch": 5.44,
|
|
"learning_rate": 0.00021558050383018758,
|
|
"loss": 1.3515,
|
|
"step": 17490
|
|
},
|
|
{
|
|
"epoch": 5.44,
|
|
"learning_rate": 0.00021533847959915532,
|
|
"loss": 1.3833,
|
|
"step": 17500
|
|
},
|
|
{
|
|
"epoch": 5.45,
|
|
"learning_rate": 0.00021509648848547276,
|
|
"loss": 1.5164,
|
|
"step": 17510
|
|
},
|
|
{
|
|
"epoch": 5.45,
|
|
"learning_rate": 0.00021485453072035037,
|
|
"loss": 1.4543,
|
|
"step": 17520
|
|
},
|
|
{
|
|
"epoch": 5.45,
|
|
"learning_rate": 0.00021461260653496663,
|
|
"loss": 1.4028,
|
|
"step": 17530
|
|
},
|
|
{
|
|
"epoch": 5.46,
|
|
"learning_rate": 0.00021437071616046816,
|
|
"loss": 1.4679,
|
|
"step": 17540
|
|
},
|
|
{
|
|
"epoch": 5.46,
|
|
"learning_rate": 0.00021412885982796906,
|
|
"loss": 1.328,
|
|
"step": 17550
|
|
},
|
|
{
|
|
"epoch": 5.46,
|
|
"learning_rate": 0.00021388703776855088,
|
|
"loss": 1.5427,
|
|
"step": 17560
|
|
},
|
|
{
|
|
"epoch": 5.47,
|
|
"learning_rate": 0.00021364525021326256,
|
|
"loss": 1.4287,
|
|
"step": 17570
|
|
},
|
|
{
|
|
"epoch": 5.47,
|
|
"learning_rate": 0.00021340349739312008,
|
|
"loss": 1.4558,
|
|
"step": 17580
|
|
},
|
|
{
|
|
"epoch": 5.47,
|
|
"learning_rate": 0.00021316177953910597,
|
|
"loss": 1.3547,
|
|
"step": 17590
|
|
},
|
|
{
|
|
"epoch": 5.48,
|
|
"learning_rate": 0.00021292009688216978,
|
|
"loss": 1.4305,
|
|
"step": 17600
|
|
},
|
|
{
|
|
"epoch": 5.48,
|
|
"learning_rate": 0.00021267844965322711,
|
|
"loss": 1.4302,
|
|
"step": 17610
|
|
},
|
|
{
|
|
"epoch": 5.48,
|
|
"learning_rate": 0.0002124368380831599,
|
|
"loss": 1.4,
|
|
"step": 17620
|
|
},
|
|
{
|
|
"epoch": 5.48,
|
|
"learning_rate": 0.00021219526240281571,
|
|
"loss": 1.3629,
|
|
"step": 17630
|
|
},
|
|
{
|
|
"epoch": 5.49,
|
|
"learning_rate": 0.00021195372284300824,
|
|
"loss": 1.4081,
|
|
"step": 17640
|
|
},
|
|
{
|
|
"epoch": 5.49,
|
|
"learning_rate": 0.0002117122196345164,
|
|
"loss": 1.4194,
|
|
"step": 17650
|
|
},
|
|
{
|
|
"epoch": 5.49,
|
|
"learning_rate": 0.0002114707530080843,
|
|
"loss": 1.3978,
|
|
"step": 17660
|
|
},
|
|
{
|
|
"epoch": 5.5,
|
|
"learning_rate": 0.0002112293231944214,
|
|
"loss": 1.5403,
|
|
"step": 17670
|
|
},
|
|
{
|
|
"epoch": 5.5,
|
|
"learning_rate": 0.00021098793042420176,
|
|
"loss": 1.3632,
|
|
"step": 17680
|
|
},
|
|
{
|
|
"epoch": 5.5,
|
|
"learning_rate": 0.00021074657492806416,
|
|
"loss": 1.3046,
|
|
"step": 17690
|
|
},
|
|
{
|
|
"epoch": 5.51,
|
|
"learning_rate": 0.00021050525693661157,
|
|
"loss": 1.4514,
|
|
"step": 17700
|
|
},
|
|
{
|
|
"epoch": 5.51,
|
|
"learning_rate": 0.00021026397668041135,
|
|
"loss": 1.4432,
|
|
"step": 17710
|
|
},
|
|
{
|
|
"epoch": 5.51,
|
|
"learning_rate": 0.00021002273438999467,
|
|
"loss": 1.3373,
|
|
"step": 17720
|
|
},
|
|
{
|
|
"epoch": 5.52,
|
|
"learning_rate": 0.00020978153029585657,
|
|
"loss": 1.437,
|
|
"step": 17730
|
|
},
|
|
{
|
|
"epoch": 5.52,
|
|
"learning_rate": 0.0002095403646284555,
|
|
"loss": 1.3637,
|
|
"step": 17740
|
|
},
|
|
{
|
|
"epoch": 5.52,
|
|
"learning_rate": 0.0002092992376182131,
|
|
"loss": 1.5094,
|
|
"step": 17750
|
|
},
|
|
{
|
|
"epoch": 5.53,
|
|
"learning_rate": 0.0002090581494955143,
|
|
"loss": 1.3651,
|
|
"step": 17760
|
|
},
|
|
{
|
|
"epoch": 5.53,
|
|
"learning_rate": 0.0002088171004907066,
|
|
"loss": 1.4485,
|
|
"step": 17770
|
|
},
|
|
{
|
|
"epoch": 5.53,
|
|
"learning_rate": 0.00020857609083410034,
|
|
"loss": 1.4588,
|
|
"step": 17780
|
|
},
|
|
{
|
|
"epoch": 5.53,
|
|
"learning_rate": 0.00020833512075596816,
|
|
"loss": 1.4155,
|
|
"step": 17790
|
|
},
|
|
{
|
|
"epoch": 5.54,
|
|
"learning_rate": 0.00020809419048654503,
|
|
"loss": 1.456,
|
|
"step": 17800
|
|
},
|
|
{
|
|
"epoch": 5.54,
|
|
"learning_rate": 0.00020785330025602773,
|
|
"loss": 1.4344,
|
|
"step": 17810
|
|
},
|
|
{
|
|
"epoch": 5.54,
|
|
"learning_rate": 0.00020761245029457477,
|
|
"loss": 1.4131,
|
|
"step": 17820
|
|
},
|
|
{
|
|
"epoch": 5.55,
|
|
"learning_rate": 0.00020737164083230628,
|
|
"loss": 1.4282,
|
|
"step": 17830
|
|
},
|
|
{
|
|
"epoch": 5.55,
|
|
"learning_rate": 0.00020713087209930372,
|
|
"loss": 1.3318,
|
|
"step": 17840
|
|
},
|
|
{
|
|
"epoch": 5.55,
|
|
"learning_rate": 0.00020689014432560943,
|
|
"loss": 1.3336,
|
|
"step": 17850
|
|
},
|
|
{
|
|
"epoch": 5.56,
|
|
"learning_rate": 0.0002066494577412269,
|
|
"loss": 1.444,
|
|
"step": 17860
|
|
},
|
|
{
|
|
"epoch": 5.56,
|
|
"learning_rate": 0.0002064088125761201,
|
|
"loss": 1.4165,
|
|
"step": 17870
|
|
},
|
|
{
|
|
"epoch": 5.56,
|
|
"learning_rate": 0.00020616820906021349,
|
|
"loss": 1.3446,
|
|
"step": 17880
|
|
},
|
|
{
|
|
"epoch": 5.57,
|
|
"learning_rate": 0.0002059276474233916,
|
|
"loss": 1.5309,
|
|
"step": 17890
|
|
},
|
|
{
|
|
"epoch": 5.57,
|
|
"learning_rate": 0.00020568712789549907,
|
|
"loss": 1.5186,
|
|
"step": 17900
|
|
},
|
|
{
|
|
"epoch": 5.57,
|
|
"learning_rate": 0.0002054466507063404,
|
|
"loss": 1.4729,
|
|
"step": 17910
|
|
},
|
|
{
|
|
"epoch": 5.58,
|
|
"learning_rate": 0.00020520621608567926,
|
|
"loss": 1.3097,
|
|
"step": 17920
|
|
},
|
|
{
|
|
"epoch": 5.58,
|
|
"learning_rate": 0.00020496582426323917,
|
|
"loss": 1.3455,
|
|
"step": 17930
|
|
},
|
|
{
|
|
"epoch": 5.58,
|
|
"learning_rate": 0.00020472547546870244,
|
|
"loss": 1.4515,
|
|
"step": 17940
|
|
},
|
|
{
|
|
"epoch": 5.58,
|
|
"learning_rate": 0.0002044851699317103,
|
|
"loss": 1.5015,
|
|
"step": 17950
|
|
},
|
|
{
|
|
"epoch": 5.59,
|
|
"learning_rate": 0.00020424490788186262,
|
|
"loss": 1.4476,
|
|
"step": 17960
|
|
},
|
|
{
|
|
"epoch": 5.59,
|
|
"learning_rate": 0.00020400468954871786,
|
|
"loss": 1.3625,
|
|
"step": 17970
|
|
},
|
|
{
|
|
"epoch": 5.59,
|
|
"learning_rate": 0.00020376451516179248,
|
|
"loss": 1.4852,
|
|
"step": 17980
|
|
},
|
|
{
|
|
"epoch": 5.6,
|
|
"learning_rate": 0.00020352438495056135,
|
|
"loss": 1.5328,
|
|
"step": 17990
|
|
},
|
|
{
|
|
"epoch": 5.6,
|
|
"learning_rate": 0.00020328429914445668,
|
|
"loss": 1.3633,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"epoch": 5.6,
|
|
"learning_rate": 0.0002030442579728685,
|
|
"loss": 1.5372,
|
|
"step": 18010
|
|
},
|
|
{
|
|
"epoch": 5.61,
|
|
"learning_rate": 0.00020280426166514426,
|
|
"loss": 1.4389,
|
|
"step": 18020
|
|
},
|
|
{
|
|
"epoch": 5.61,
|
|
"learning_rate": 0.00020256431045058824,
|
|
"loss": 1.4435,
|
|
"step": 18030
|
|
},
|
|
{
|
|
"epoch": 5.61,
|
|
"learning_rate": 0.00020232440455846194,
|
|
"loss": 1.3845,
|
|
"step": 18040
|
|
},
|
|
{
|
|
"epoch": 5.62,
|
|
"learning_rate": 0.0002020845442179834,
|
|
"loss": 1.416,
|
|
"step": 18050
|
|
},
|
|
{
|
|
"epoch": 5.62,
|
|
"learning_rate": 0.00020184472965832724,
|
|
"loss": 1.4206,
|
|
"step": 18060
|
|
},
|
|
{
|
|
"epoch": 5.62,
|
|
"learning_rate": 0.00020160496110862428,
|
|
"loss": 1.3715,
|
|
"step": 18070
|
|
},
|
|
{
|
|
"epoch": 5.62,
|
|
"learning_rate": 0.00020136523879796134,
|
|
"loss": 1.4126,
|
|
"step": 18080
|
|
},
|
|
{
|
|
"epoch": 5.63,
|
|
"learning_rate": 0.00020112556295538115,
|
|
"loss": 1.3651,
|
|
"step": 18090
|
|
},
|
|
{
|
|
"epoch": 5.63,
|
|
"learning_rate": 0.00020088593380988194,
|
|
"loss": 1.4611,
|
|
"step": 18100
|
|
},
|
|
{
|
|
"epoch": 5.63,
|
|
"learning_rate": 0.00020064635159041733,
|
|
"loss": 1.4533,
|
|
"step": 18110
|
|
},
|
|
{
|
|
"epoch": 5.64,
|
|
"learning_rate": 0.00020040681652589627,
|
|
"loss": 1.3729,
|
|
"step": 18120
|
|
},
|
|
{
|
|
"epoch": 5.64,
|
|
"learning_rate": 0.00020016732884518249,
|
|
"loss": 1.3607,
|
|
"step": 18130
|
|
},
|
|
{
|
|
"epoch": 5.64,
|
|
"learning_rate": 0.00019992788877709456,
|
|
"loss": 1.2754,
|
|
"step": 18140
|
|
},
|
|
{
|
|
"epoch": 5.65,
|
|
"learning_rate": 0.00019968849655040537,
|
|
"loss": 1.3683,
|
|
"step": 18150
|
|
},
|
|
{
|
|
"epoch": 5.65,
|
|
"learning_rate": 0.00019944915239384226,
|
|
"loss": 1.3094,
|
|
"step": 18160
|
|
},
|
|
{
|
|
"epoch": 5.65,
|
|
"learning_rate": 0.0001992098565360866,
|
|
"loss": 1.472,
|
|
"step": 18170
|
|
},
|
|
{
|
|
"epoch": 5.66,
|
|
"learning_rate": 0.00019897060920577375,
|
|
"loss": 1.4875,
|
|
"step": 18180
|
|
},
|
|
{
|
|
"epoch": 5.66,
|
|
"learning_rate": 0.0001987314106314924,
|
|
"loss": 1.4231,
|
|
"step": 18190
|
|
},
|
|
{
|
|
"epoch": 5.66,
|
|
"learning_rate": 0.0001984922610417849,
|
|
"loss": 1.5234,
|
|
"step": 18200
|
|
},
|
|
{
|
|
"epoch": 5.67,
|
|
"learning_rate": 0.0001982531606651468,
|
|
"loss": 1.439,
|
|
"step": 18210
|
|
},
|
|
{
|
|
"epoch": 5.67,
|
|
"learning_rate": 0.00019801410973002643,
|
|
"loss": 1.4979,
|
|
"step": 18220
|
|
},
|
|
{
|
|
"epoch": 5.67,
|
|
"learning_rate": 0.000197775108464825,
|
|
"loss": 1.371,
|
|
"step": 18230
|
|
},
|
|
{
|
|
"epoch": 5.67,
|
|
"learning_rate": 0.00019753615709789632,
|
|
"loss": 1.5346,
|
|
"step": 18240
|
|
},
|
|
{
|
|
"epoch": 5.68,
|
|
"learning_rate": 0.00019729725585754658,
|
|
"loss": 1.4801,
|
|
"step": 18250
|
|
},
|
|
{
|
|
"epoch": 5.68,
|
|
"learning_rate": 0.0001970584049720338,
|
|
"loss": 1.4782,
|
|
"step": 18260
|
|
},
|
|
{
|
|
"epoch": 5.68,
|
|
"learning_rate": 0.00019681960466956815,
|
|
"loss": 1.4757,
|
|
"step": 18270
|
|
},
|
|
{
|
|
"epoch": 5.69,
|
|
"learning_rate": 0.00019658085517831138,
|
|
"loss": 1.5626,
|
|
"step": 18280
|
|
},
|
|
{
|
|
"epoch": 5.69,
|
|
"learning_rate": 0.00019634215672637663,
|
|
"loss": 1.4595,
|
|
"step": 18290
|
|
},
|
|
{
|
|
"epoch": 5.69,
|
|
"learning_rate": 0.00019610350954182832,
|
|
"loss": 1.3133,
|
|
"step": 18300
|
|
},
|
|
{
|
|
"epoch": 5.7,
|
|
"learning_rate": 0.00019586491385268202,
|
|
"loss": 1.4903,
|
|
"step": 18310
|
|
},
|
|
{
|
|
"epoch": 5.7,
|
|
"learning_rate": 0.00019562636988690397,
|
|
"loss": 1.4082,
|
|
"step": 18320
|
|
},
|
|
{
|
|
"epoch": 5.7,
|
|
"learning_rate": 0.0001953878778724109,
|
|
"loss": 1.5481,
|
|
"step": 18330
|
|
},
|
|
{
|
|
"epoch": 5.71,
|
|
"learning_rate": 0.0001951494380370701,
|
|
"loss": 1.4263,
|
|
"step": 18340
|
|
},
|
|
{
|
|
"epoch": 5.71,
|
|
"learning_rate": 0.00019491105060869885,
|
|
"loss": 1.4284,
|
|
"step": 18350
|
|
},
|
|
{
|
|
"epoch": 5.71,
|
|
"learning_rate": 0.00019467271581506443,
|
|
"loss": 1.3756,
|
|
"step": 18360
|
|
},
|
|
{
|
|
"epoch": 5.72,
|
|
"learning_rate": 0.00019443443388388377,
|
|
"loss": 1.4989,
|
|
"step": 18370
|
|
},
|
|
{
|
|
"epoch": 5.72,
|
|
"learning_rate": 0.00019419620504282345,
|
|
"loss": 1.3389,
|
|
"step": 18380
|
|
},
|
|
{
|
|
"epoch": 5.72,
|
|
"learning_rate": 0.00019395802951949917,
|
|
"loss": 1.3711,
|
|
"step": 18390
|
|
},
|
|
{
|
|
"epoch": 5.72,
|
|
"learning_rate": 0.0001937199075414758,
|
|
"loss": 1.3367,
|
|
"step": 18400
|
|
},
|
|
{
|
|
"epoch": 5.73,
|
|
"learning_rate": 0.00019348183933626684,
|
|
"loss": 1.425,
|
|
"step": 18410
|
|
},
|
|
{
|
|
"epoch": 5.73,
|
|
"learning_rate": 0.0001932438251313347,
|
|
"loss": 1.3828,
|
|
"step": 18420
|
|
},
|
|
{
|
|
"epoch": 5.73,
|
|
"learning_rate": 0.00019300586515408986,
|
|
"loss": 1.4029,
|
|
"step": 18430
|
|
},
|
|
{
|
|
"epoch": 5.74,
|
|
"learning_rate": 0.0001927679596318914,
|
|
"loss": 1.3238,
|
|
"step": 18440
|
|
},
|
|
{
|
|
"epoch": 5.74,
|
|
"learning_rate": 0.00019253010879204604,
|
|
"loss": 1.3376,
|
|
"step": 18450
|
|
},
|
|
{
|
|
"epoch": 5.74,
|
|
"learning_rate": 0.0001922923128618084,
|
|
"loss": 1.5125,
|
|
"step": 18460
|
|
},
|
|
{
|
|
"epoch": 5.75,
|
|
"learning_rate": 0.0001920545720683806,
|
|
"loss": 1.4313,
|
|
"step": 18470
|
|
},
|
|
{
|
|
"epoch": 5.75,
|
|
"learning_rate": 0.00019181688663891206,
|
|
"loss": 1.5805,
|
|
"step": 18480
|
|
},
|
|
{
|
|
"epoch": 5.75,
|
|
"learning_rate": 0.0001915792568004993,
|
|
"loss": 1.4181,
|
|
"step": 18490
|
|
},
|
|
{
|
|
"epoch": 5.76,
|
|
"learning_rate": 0.00019134168278018575,
|
|
"loss": 1.4378,
|
|
"step": 18500
|
|
},
|
|
{
|
|
"epoch": 5.76,
|
|
"learning_rate": 0.0001911041648049617,
|
|
"loss": 1.4496,
|
|
"step": 18510
|
|
},
|
|
{
|
|
"epoch": 5.76,
|
|
"learning_rate": 0.0001908667031017634,
|
|
"loss": 1.5063,
|
|
"step": 18520
|
|
},
|
|
{
|
|
"epoch": 5.76,
|
|
"learning_rate": 0.0001906292978974738,
|
|
"loss": 1.3577,
|
|
"step": 18530
|
|
},
|
|
{
|
|
"epoch": 5.77,
|
|
"learning_rate": 0.00019039194941892175,
|
|
"loss": 1.4388,
|
|
"step": 18540
|
|
},
|
|
{
|
|
"epoch": 5.77,
|
|
"learning_rate": 0.00019015465789288172,
|
|
"loss": 1.3575,
|
|
"step": 18550
|
|
},
|
|
{
|
|
"epoch": 5.77,
|
|
"learning_rate": 0.00018991742354607392,
|
|
"loss": 1.3512,
|
|
"step": 18560
|
|
},
|
|
{
|
|
"epoch": 5.78,
|
|
"learning_rate": 0.00018968024660516398,
|
|
"loss": 1.5638,
|
|
"step": 18570
|
|
},
|
|
{
|
|
"epoch": 5.78,
|
|
"learning_rate": 0.00018944312729676267,
|
|
"loss": 1.4364,
|
|
"step": 18580
|
|
},
|
|
{
|
|
"epoch": 5.78,
|
|
"learning_rate": 0.00018920606584742544,
|
|
"loss": 1.4959,
|
|
"step": 18590
|
|
},
|
|
{
|
|
"epoch": 5.79,
|
|
"learning_rate": 0.00018896906248365279,
|
|
"loss": 1.3437,
|
|
"step": 18600
|
|
},
|
|
{
|
|
"epoch": 5.79,
|
|
"learning_rate": 0.0001887321174318896,
|
|
"loss": 1.4091,
|
|
"step": 18610
|
|
},
|
|
{
|
|
"epoch": 5.79,
|
|
"learning_rate": 0.0001884952309185249,
|
|
"loss": 1.4395,
|
|
"step": 18620
|
|
},
|
|
{
|
|
"epoch": 5.8,
|
|
"learning_rate": 0.00018825840316989196,
|
|
"loss": 1.4182,
|
|
"step": 18630
|
|
},
|
|
{
|
|
"epoch": 5.8,
|
|
"learning_rate": 0.00018802163441226788,
|
|
"loss": 1.3945,
|
|
"step": 18640
|
|
},
|
|
{
|
|
"epoch": 5.8,
|
|
"learning_rate": 0.0001877849248718734,
|
|
"loss": 1.3258,
|
|
"step": 18650
|
|
},
|
|
{
|
|
"epoch": 5.81,
|
|
"learning_rate": 0.00018754827477487267,
|
|
"loss": 1.3398,
|
|
"step": 18660
|
|
},
|
|
{
|
|
"epoch": 5.81,
|
|
"learning_rate": 0.0001873116843473729,
|
|
"loss": 1.4669,
|
|
"step": 18670
|
|
},
|
|
{
|
|
"epoch": 5.81,
|
|
"learning_rate": 0.00018707515381542452,
|
|
"loss": 1.3767,
|
|
"step": 18680
|
|
},
|
|
{
|
|
"epoch": 5.81,
|
|
"learning_rate": 0.00018683868340502047,
|
|
"loss": 1.4927,
|
|
"step": 18690
|
|
},
|
|
{
|
|
"epoch": 5.82,
|
|
"learning_rate": 0.00018660227334209664,
|
|
"loss": 1.3945,
|
|
"step": 18700
|
|
},
|
|
{
|
|
"epoch": 5.82,
|
|
"learning_rate": 0.0001863659238525309,
|
|
"loss": 1.3969,
|
|
"step": 18710
|
|
},
|
|
{
|
|
"epoch": 5.82,
|
|
"learning_rate": 0.0001861296351621434,
|
|
"loss": 1.3592,
|
|
"step": 18720
|
|
},
|
|
{
|
|
"epoch": 5.83,
|
|
"learning_rate": 0.00018589340749669615,
|
|
"loss": 1.4006,
|
|
"step": 18730
|
|
},
|
|
{
|
|
"epoch": 5.83,
|
|
"learning_rate": 0.00018565724108189283,
|
|
"loss": 1.5053,
|
|
"step": 18740
|
|
},
|
|
{
|
|
"epoch": 5.83,
|
|
"learning_rate": 0.00018542113614337876,
|
|
"loss": 1.3905,
|
|
"step": 18750
|
|
},
|
|
{
|
|
"epoch": 5.84,
|
|
"learning_rate": 0.00018518509290674017,
|
|
"loss": 1.4486,
|
|
"step": 18760
|
|
},
|
|
{
|
|
"epoch": 5.84,
|
|
"learning_rate": 0.00018494911159750487,
|
|
"loss": 1.4558,
|
|
"step": 18770
|
|
},
|
|
{
|
|
"epoch": 5.84,
|
|
"learning_rate": 0.00018471319244114104,
|
|
"loss": 1.4868,
|
|
"step": 18780
|
|
},
|
|
{
|
|
"epoch": 5.85,
|
|
"learning_rate": 0.00018447733566305765,
|
|
"loss": 1.484,
|
|
"step": 18790
|
|
},
|
|
{
|
|
"epoch": 5.85,
|
|
"learning_rate": 0.00018424154148860415,
|
|
"loss": 1.3754,
|
|
"step": 18800
|
|
},
|
|
{
|
|
"epoch": 5.85,
|
|
"learning_rate": 0.00018400581014306992,
|
|
"loss": 1.6066,
|
|
"step": 18810
|
|
},
|
|
{
|
|
"epoch": 5.86,
|
|
"learning_rate": 0.0001837701418516845,
|
|
"loss": 1.2723,
|
|
"step": 18820
|
|
},
|
|
{
|
|
"epoch": 5.86,
|
|
"learning_rate": 0.00018353453683961728,
|
|
"loss": 1.3614,
|
|
"step": 18830
|
|
},
|
|
{
|
|
"epoch": 5.86,
|
|
"learning_rate": 0.0001832989953319771,
|
|
"loss": 1.3235,
|
|
"step": 18840
|
|
},
|
|
{
|
|
"epoch": 5.86,
|
|
"learning_rate": 0.00018306351755381195,
|
|
"loss": 1.355,
|
|
"step": 18850
|
|
},
|
|
{
|
|
"epoch": 5.87,
|
|
"learning_rate": 0.00018282810373010912,
|
|
"loss": 1.4677,
|
|
"step": 18860
|
|
},
|
|
{
|
|
"epoch": 5.87,
|
|
"learning_rate": 0.0001825927540857948,
|
|
"loss": 1.4433,
|
|
"step": 18870
|
|
},
|
|
{
|
|
"epoch": 5.87,
|
|
"learning_rate": 0.00018235746884573368,
|
|
"loss": 1.4059,
|
|
"step": 18880
|
|
},
|
|
{
|
|
"epoch": 5.88,
|
|
"learning_rate": 0.0001821222482347291,
|
|
"loss": 1.3477,
|
|
"step": 18890
|
|
},
|
|
{
|
|
"epoch": 5.88,
|
|
"learning_rate": 0.00018188709247752273,
|
|
"loss": 1.2779,
|
|
"step": 18900
|
|
},
|
|
{
|
|
"epoch": 5.88,
|
|
"learning_rate": 0.00018165200179879403,
|
|
"loss": 1.3732,
|
|
"step": 18910
|
|
},
|
|
{
|
|
"epoch": 5.89,
|
|
"learning_rate": 0.00018141697642316032,
|
|
"loss": 1.3745,
|
|
"step": 18920
|
|
},
|
|
{
|
|
"epoch": 5.89,
|
|
"learning_rate": 0.0001811820165751767,
|
|
"loss": 1.4114,
|
|
"step": 18930
|
|
},
|
|
{
|
|
"epoch": 5.89,
|
|
"learning_rate": 0.00018094712247933555,
|
|
"loss": 1.3761,
|
|
"step": 18940
|
|
},
|
|
{
|
|
"epoch": 5.9,
|
|
"learning_rate": 0.00018071229436006624,
|
|
"loss": 1.2995,
|
|
"step": 18950
|
|
},
|
|
{
|
|
"epoch": 5.9,
|
|
"learning_rate": 0.0001804775324417357,
|
|
"loss": 1.3517,
|
|
"step": 18960
|
|
},
|
|
{
|
|
"epoch": 5.9,
|
|
"learning_rate": 0.00018024283694864686,
|
|
"loss": 1.5024,
|
|
"step": 18970
|
|
},
|
|
{
|
|
"epoch": 5.9,
|
|
"learning_rate": 0.00018000820810503966,
|
|
"loss": 1.3624,
|
|
"step": 18980
|
|
},
|
|
{
|
|
"epoch": 5.91,
|
|
"learning_rate": 0.00017977364613509022,
|
|
"loss": 1.5412,
|
|
"step": 18990
|
|
},
|
|
{
|
|
"epoch": 5.91,
|
|
"learning_rate": 0.00017953915126291077,
|
|
"loss": 1.3945,
|
|
"step": 19000
|
|
},
|
|
{
|
|
"epoch": 5.91,
|
|
"learning_rate": 0.00017930472371254945,
|
|
"loss": 1.5254,
|
|
"step": 19010
|
|
},
|
|
{
|
|
"epoch": 5.92,
|
|
"learning_rate": 0.00017907036370798986,
|
|
"loss": 1.4901,
|
|
"step": 19020
|
|
},
|
|
{
|
|
"epoch": 5.92,
|
|
"learning_rate": 0.00017883607147315165,
|
|
"loss": 1.4399,
|
|
"step": 19030
|
|
},
|
|
{
|
|
"epoch": 5.92,
|
|
"learning_rate": 0.00017860184723188908,
|
|
"loss": 1.4498,
|
|
"step": 19040
|
|
},
|
|
{
|
|
"epoch": 5.93,
|
|
"learning_rate": 0.00017836769120799174,
|
|
"loss": 1.3891,
|
|
"step": 19050
|
|
},
|
|
{
|
|
"epoch": 5.93,
|
|
"learning_rate": 0.0001781336036251841,
|
|
"loss": 1.4582,
|
|
"step": 19060
|
|
},
|
|
{
|
|
"epoch": 5.93,
|
|
"learning_rate": 0.000177899584707125,
|
|
"loss": 1.4035,
|
|
"step": 19070
|
|
},
|
|
{
|
|
"epoch": 5.94,
|
|
"learning_rate": 0.00017766563467740782,
|
|
"loss": 1.4113,
|
|
"step": 19080
|
|
},
|
|
{
|
|
"epoch": 5.94,
|
|
"learning_rate": 0.00017743175375956025,
|
|
"loss": 1.4257,
|
|
"step": 19090
|
|
},
|
|
{
|
|
"epoch": 5.94,
|
|
"learning_rate": 0.00017719794217704377,
|
|
"loss": 1.4298,
|
|
"step": 19100
|
|
},
|
|
{
|
|
"epoch": 5.95,
|
|
"learning_rate": 0.00017696420015325359,
|
|
"loss": 1.4491,
|
|
"step": 19110
|
|
},
|
|
{
|
|
"epoch": 5.95,
|
|
"learning_rate": 0.00017673052791151856,
|
|
"loss": 1.4573,
|
|
"step": 19120
|
|
},
|
|
{
|
|
"epoch": 5.95,
|
|
"learning_rate": 0.0001764969256751009,
|
|
"loss": 1.4397,
|
|
"step": 19130
|
|
},
|
|
{
|
|
"epoch": 5.95,
|
|
"learning_rate": 0.0001762633936671957,
|
|
"loss": 1.3514,
|
|
"step": 19140
|
|
},
|
|
{
|
|
"epoch": 5.96,
|
|
"learning_rate": 0.0001760299321109312,
|
|
"loss": 1.4332,
|
|
"step": 19150
|
|
},
|
|
{
|
|
"epoch": 5.96,
|
|
"learning_rate": 0.0001757965412293683,
|
|
"loss": 1.3734,
|
|
"step": 19160
|
|
},
|
|
{
|
|
"epoch": 5.96,
|
|
"learning_rate": 0.00017556322124550033,
|
|
"loss": 1.3832,
|
|
"step": 19170
|
|
},
|
|
{
|
|
"epoch": 5.97,
|
|
"learning_rate": 0.00017532997238225276,
|
|
"loss": 1.4696,
|
|
"step": 19180
|
|
},
|
|
{
|
|
"epoch": 5.97,
|
|
"learning_rate": 0.00017509679486248325,
|
|
"loss": 1.4463,
|
|
"step": 19190
|
|
},
|
|
{
|
|
"epoch": 5.97,
|
|
"learning_rate": 0.00017486368890898138,
|
|
"loss": 1.4297,
|
|
"step": 19200
|
|
},
|
|
{
|
|
"epoch": 5.98,
|
|
"learning_rate": 0.00017463065474446798,
|
|
"loss": 1.4798,
|
|
"step": 19210
|
|
},
|
|
{
|
|
"epoch": 5.98,
|
|
"learning_rate": 0.00017439769259159583,
|
|
"loss": 1.4395,
|
|
"step": 19220
|
|
},
|
|
{
|
|
"epoch": 5.98,
|
|
"learning_rate": 0.00017416480267294846,
|
|
"loss": 1.3572,
|
|
"step": 19230
|
|
},
|
|
{
|
|
"epoch": 5.99,
|
|
"learning_rate": 0.00017393198521104062,
|
|
"loss": 1.4152,
|
|
"step": 19240
|
|
},
|
|
{
|
|
"epoch": 5.99,
|
|
"learning_rate": 0.00017369924042831764,
|
|
"loss": 1.4066,
|
|
"step": 19250
|
|
},
|
|
{
|
|
"epoch": 5.99,
|
|
"learning_rate": 0.0001734665685471556,
|
|
"loss": 1.4521,
|
|
"step": 19260
|
|
},
|
|
{
|
|
"epoch": 6.0,
|
|
"learning_rate": 0.00017323396978986092,
|
|
"loss": 1.3883,
|
|
"step": 19270
|
|
},
|
|
{
|
|
"epoch": 6.0,
|
|
"learning_rate": 0.0001730014443786698,
|
|
"loss": 1.4245,
|
|
"step": 19280
|
|
},
|
|
{
|
|
"epoch": 6.0,
|
|
"learning_rate": 0.00017276899253574907,
|
|
"loss": 1.3935,
|
|
"step": 19290
|
|
},
|
|
{
|
|
"epoch": 6.0,
|
|
"learning_rate": 0.00017253661448319454,
|
|
"loss": 1.3101,
|
|
"step": 19300
|
|
},
|
|
{
|
|
"epoch": 6.01,
|
|
"learning_rate": 0.0001723043104430319,
|
|
"loss": 1.2479,
|
|
"step": 19310
|
|
},
|
|
{
|
|
"epoch": 6.01,
|
|
"learning_rate": 0.00017207208063721614,
|
|
"loss": 1.3674,
|
|
"step": 19320
|
|
},
|
|
{
|
|
"epoch": 6.01,
|
|
"learning_rate": 0.00017183992528763104,
|
|
"loss": 1.2575,
|
|
"step": 19330
|
|
},
|
|
{
|
|
"epoch": 6.02,
|
|
"learning_rate": 0.00017160784461608947,
|
|
"loss": 1.2798,
|
|
"step": 19340
|
|
},
|
|
{
|
|
"epoch": 6.02,
|
|
"learning_rate": 0.00017137583884433306,
|
|
"loss": 1.286,
|
|
"step": 19350
|
|
},
|
|
{
|
|
"epoch": 6.02,
|
|
"learning_rate": 0.00017114390819403163,
|
|
"loss": 1.3434,
|
|
"step": 19360
|
|
},
|
|
{
|
|
"epoch": 6.03,
|
|
"learning_rate": 0.00017091205288678336,
|
|
"loss": 1.4234,
|
|
"step": 19370
|
|
},
|
|
{
|
|
"epoch": 6.03,
|
|
"learning_rate": 0.00017068027314411427,
|
|
"loss": 1.3358,
|
|
"step": 19380
|
|
},
|
|
{
|
|
"epoch": 6.03,
|
|
"learning_rate": 0.00017044856918747853,
|
|
"loss": 1.2829,
|
|
"step": 19390
|
|
},
|
|
{
|
|
"epoch": 6.04,
|
|
"learning_rate": 0.00017021694123825747,
|
|
"loss": 1.2754,
|
|
"step": 19400
|
|
},
|
|
{
|
|
"epoch": 6.04,
|
|
"learning_rate": 0.0001699853895177601,
|
|
"loss": 1.3159,
|
|
"step": 19410
|
|
},
|
|
{
|
|
"epoch": 6.04,
|
|
"learning_rate": 0.00016975391424722255,
|
|
"loss": 1.3269,
|
|
"step": 19420
|
|
},
|
|
{
|
|
"epoch": 6.04,
|
|
"learning_rate": 0.0001695225156478079,
|
|
"loss": 1.3769,
|
|
"step": 19430
|
|
},
|
|
{
|
|
"epoch": 6.05,
|
|
"learning_rate": 0.00016929119394060586,
|
|
"loss": 1.3192,
|
|
"step": 19440
|
|
},
|
|
{
|
|
"epoch": 6.05,
|
|
"learning_rate": 0.00016905994934663277,
|
|
"loss": 1.2832,
|
|
"step": 19450
|
|
},
|
|
{
|
|
"epoch": 6.05,
|
|
"learning_rate": 0.00016882878208683132,
|
|
"loss": 1.3557,
|
|
"step": 19460
|
|
},
|
|
{
|
|
"epoch": 6.06,
|
|
"learning_rate": 0.00016859769238207007,
|
|
"loss": 1.3223,
|
|
"step": 19470
|
|
},
|
|
{
|
|
"epoch": 6.06,
|
|
"learning_rate": 0.00016836668045314403,
|
|
"loss": 1.3191,
|
|
"step": 19480
|
|
},
|
|
{
|
|
"epoch": 6.06,
|
|
"learning_rate": 0.00016813574652077331,
|
|
"loss": 1.3213,
|
|
"step": 19490
|
|
},
|
|
{
|
|
"epoch": 6.07,
|
|
"learning_rate": 0.00016790489080560384,
|
|
"loss": 1.3545,
|
|
"step": 19500
|
|
},
|
|
{
|
|
"epoch": 6.07,
|
|
"learning_rate": 0.00016767411352820662,
|
|
"loss": 1.3313,
|
|
"step": 19510
|
|
},
|
|
{
|
|
"epoch": 6.07,
|
|
"learning_rate": 0.00016744341490907783,
|
|
"loss": 1.3915,
|
|
"step": 19520
|
|
},
|
|
{
|
|
"epoch": 6.08,
|
|
"learning_rate": 0.0001672127951686386,
|
|
"loss": 1.2131,
|
|
"step": 19530
|
|
},
|
|
{
|
|
"epoch": 6.08,
|
|
"learning_rate": 0.0001669822545272342,
|
|
"loss": 1.3258,
|
|
"step": 19540
|
|
},
|
|
{
|
|
"epoch": 6.08,
|
|
"learning_rate": 0.00016675179320513512,
|
|
"loss": 1.2423,
|
|
"step": 19550
|
|
},
|
|
{
|
|
"epoch": 6.09,
|
|
"learning_rate": 0.00016652141142253535,
|
|
"loss": 1.3789,
|
|
"step": 19560
|
|
},
|
|
{
|
|
"epoch": 6.09,
|
|
"learning_rate": 0.00016629110939955335,
|
|
"loss": 1.3098,
|
|
"step": 19570
|
|
},
|
|
{
|
|
"epoch": 6.09,
|
|
"learning_rate": 0.00016606088735623105,
|
|
"loss": 1.4157,
|
|
"step": 19580
|
|
},
|
|
{
|
|
"epoch": 6.09,
|
|
"learning_rate": 0.00016583074551253414,
|
|
"loss": 1.2835,
|
|
"step": 19590
|
|
},
|
|
{
|
|
"epoch": 6.1,
|
|
"learning_rate": 0.00016560068408835154,
|
|
"loss": 1.2379,
|
|
"step": 19600
|
|
},
|
|
{
|
|
"epoch": 6.1,
|
|
"learning_rate": 0.00016537070330349568,
|
|
"loss": 1.1922,
|
|
"step": 19610
|
|
},
|
|
{
|
|
"epoch": 6.1,
|
|
"learning_rate": 0.00016514080337770158,
|
|
"loss": 1.2498,
|
|
"step": 19620
|
|
},
|
|
{
|
|
"epoch": 6.11,
|
|
"learning_rate": 0.00016491098453062707,
|
|
"loss": 1.3121,
|
|
"step": 19630
|
|
},
|
|
{
|
|
"epoch": 6.11,
|
|
"learning_rate": 0.0001646812469818526,
|
|
"loss": 1.2769,
|
|
"step": 19640
|
|
},
|
|
{
|
|
"epoch": 6.11,
|
|
"learning_rate": 0.000164451590950881,
|
|
"loss": 1.3457,
|
|
"step": 19650
|
|
},
|
|
{
|
|
"epoch": 6.12,
|
|
"learning_rate": 0.000164222016657137,
|
|
"loss": 1.352,
|
|
"step": 19660
|
|
},
|
|
{
|
|
"epoch": 6.12,
|
|
"learning_rate": 0.00016399252431996734,
|
|
"loss": 1.2943,
|
|
"step": 19670
|
|
},
|
|
{
|
|
"epoch": 6.12,
|
|
"learning_rate": 0.00016376311415864059,
|
|
"loss": 1.3315,
|
|
"step": 19680
|
|
},
|
|
{
|
|
"epoch": 6.13,
|
|
"learning_rate": 0.00016353378639234672,
|
|
"loss": 1.3335,
|
|
"step": 19690
|
|
},
|
|
{
|
|
"epoch": 6.13,
|
|
"learning_rate": 0.0001633045412401968,
|
|
"loss": 1.3319,
|
|
"step": 19700
|
|
},
|
|
{
|
|
"epoch": 6.13,
|
|
"learning_rate": 0.0001630753789212232,
|
|
"loss": 1.1872,
|
|
"step": 19710
|
|
},
|
|
{
|
|
"epoch": 6.14,
|
|
"learning_rate": 0.00016284629965437907,
|
|
"loss": 1.3247,
|
|
"step": 19720
|
|
},
|
|
{
|
|
"epoch": 6.14,
|
|
"learning_rate": 0.00016261730365853806,
|
|
"loss": 1.2435,
|
|
"step": 19730
|
|
},
|
|
{
|
|
"epoch": 6.14,
|
|
"learning_rate": 0.00016238839115249455,
|
|
"loss": 1.3624,
|
|
"step": 19740
|
|
},
|
|
{
|
|
"epoch": 6.14,
|
|
"learning_rate": 0.00016215956235496293,
|
|
"loss": 1.2836,
|
|
"step": 19750
|
|
},
|
|
{
|
|
"epoch": 6.15,
|
|
"learning_rate": 0.00016193081748457777,
|
|
"loss": 1.3739,
|
|
"step": 19760
|
|
},
|
|
{
|
|
"epoch": 6.15,
|
|
"learning_rate": 0.00016170215675989318,
|
|
"loss": 1.3382,
|
|
"step": 19770
|
|
},
|
|
{
|
|
"epoch": 6.15,
|
|
"learning_rate": 0.0001614735803993832,
|
|
"loss": 1.2731,
|
|
"step": 19780
|
|
},
|
|
{
|
|
"epoch": 6.16,
|
|
"learning_rate": 0.000161245088621441,
|
|
"loss": 1.1556,
|
|
"step": 19790
|
|
},
|
|
{
|
|
"epoch": 6.16,
|
|
"learning_rate": 0.00016101668164437914,
|
|
"loss": 1.4239,
|
|
"step": 19800
|
|
},
|
|
{
|
|
"epoch": 6.16,
|
|
"learning_rate": 0.00016078835968642908,
|
|
"loss": 1.1934,
|
|
"step": 19810
|
|
},
|
|
{
|
|
"epoch": 6.17,
|
|
"learning_rate": 0.00016056012296574096,
|
|
"loss": 1.2857,
|
|
"step": 19820
|
|
},
|
|
{
|
|
"epoch": 6.17,
|
|
"learning_rate": 0.00016033197170038362,
|
|
"loss": 1.2933,
|
|
"step": 19830
|
|
},
|
|
{
|
|
"epoch": 6.17,
|
|
"learning_rate": 0.0001601039061083441,
|
|
"loss": 1.3504,
|
|
"step": 19840
|
|
},
|
|
{
|
|
"epoch": 6.18,
|
|
"learning_rate": 0.00015987592640752773,
|
|
"loss": 1.3045,
|
|
"step": 19850
|
|
},
|
|
{
|
|
"epoch": 6.18,
|
|
"learning_rate": 0.00015964803281575768,
|
|
"loss": 1.3286,
|
|
"step": 19860
|
|
},
|
|
{
|
|
"epoch": 6.18,
|
|
"learning_rate": 0.00015942022555077496,
|
|
"loss": 1.467,
|
|
"step": 19870
|
|
},
|
|
{
|
|
"epoch": 6.18,
|
|
"learning_rate": 0.000159192504830238,
|
|
"loss": 1.3644,
|
|
"step": 19880
|
|
},
|
|
{
|
|
"epoch": 6.19,
|
|
"learning_rate": 0.00015896487087172252,
|
|
"loss": 1.333,
|
|
"step": 19890
|
|
},
|
|
{
|
|
"epoch": 6.19,
|
|
"learning_rate": 0.0001587373238927214,
|
|
"loss": 1.3811,
|
|
"step": 19900
|
|
},
|
|
{
|
|
"epoch": 6.19,
|
|
"learning_rate": 0.0001585098641106444,
|
|
"loss": 1.2656,
|
|
"step": 19910
|
|
},
|
|
{
|
|
"epoch": 6.2,
|
|
"learning_rate": 0.00015828249174281792,
|
|
"loss": 1.2756,
|
|
"step": 19920
|
|
},
|
|
{
|
|
"epoch": 6.2,
|
|
"learning_rate": 0.00015805520700648502,
|
|
"loss": 1.2864,
|
|
"step": 19930
|
|
},
|
|
{
|
|
"epoch": 6.2,
|
|
"learning_rate": 0.00015782801011880477,
|
|
"loss": 1.3953,
|
|
"step": 19940
|
|
},
|
|
{
|
|
"epoch": 6.21,
|
|
"learning_rate": 0.00015760090129685256,
|
|
"loss": 1.3146,
|
|
"step": 19950
|
|
},
|
|
{
|
|
"epoch": 6.21,
|
|
"learning_rate": 0.00015737388075761944,
|
|
"loss": 1.2957,
|
|
"step": 19960
|
|
},
|
|
{
|
|
"epoch": 6.21,
|
|
"learning_rate": 0.00015714694871801215,
|
|
"loss": 1.3544,
|
|
"step": 19970
|
|
},
|
|
{
|
|
"epoch": 6.22,
|
|
"learning_rate": 0.000156920105394853,
|
|
"loss": 1.2073,
|
|
"step": 19980
|
|
},
|
|
{
|
|
"epoch": 6.22,
|
|
"learning_rate": 0.0001566933510048793,
|
|
"loss": 1.3704,
|
|
"step": 19990
|
|
},
|
|
{
|
|
"epoch": 6.22,
|
|
"learning_rate": 0.0001564666857647437,
|
|
"loss": 1.2967,
|
|
"step": 20000
|
|
},
|
|
{
|
|
"epoch": 6.23,
|
|
"learning_rate": 0.0001562401098910134,
|
|
"loss": 1.2802,
|
|
"step": 20010
|
|
},
|
|
{
|
|
"epoch": 6.23,
|
|
"learning_rate": 0.0001560136236001704,
|
|
"loss": 1.3406,
|
|
"step": 20020
|
|
},
|
|
{
|
|
"epoch": 6.23,
|
|
"learning_rate": 0.00015578722710861097,
|
|
"loss": 1.2521,
|
|
"step": 20030
|
|
},
|
|
{
|
|
"epoch": 6.23,
|
|
"learning_rate": 0.0001555609206326456,
|
|
"loss": 1.3541,
|
|
"step": 20040
|
|
},
|
|
{
|
|
"epoch": 6.24,
|
|
"learning_rate": 0.00015533470438849884,
|
|
"loss": 1.452,
|
|
"step": 20050
|
|
},
|
|
{
|
|
"epoch": 6.24,
|
|
"learning_rate": 0.0001551085785923091,
|
|
"loss": 1.4244,
|
|
"step": 20060
|
|
},
|
|
{
|
|
"epoch": 6.24,
|
|
"learning_rate": 0.00015488254346012815,
|
|
"loss": 1.2892,
|
|
"step": 20070
|
|
},
|
|
{
|
|
"epoch": 6.25,
|
|
"learning_rate": 0.0001546565992079213,
|
|
"loss": 1.2932,
|
|
"step": 20080
|
|
},
|
|
{
|
|
"epoch": 6.25,
|
|
"learning_rate": 0.00015443074605156704,
|
|
"loss": 1.3654,
|
|
"step": 20090
|
|
},
|
|
{
|
|
"epoch": 6.25,
|
|
"learning_rate": 0.00015420498420685665,
|
|
"loss": 1.3328,
|
|
"step": 20100
|
|
},
|
|
{
|
|
"epoch": 6.26,
|
|
"learning_rate": 0.00015397931388949436,
|
|
"loss": 1.2787,
|
|
"step": 20110
|
|
},
|
|
{
|
|
"epoch": 6.26,
|
|
"learning_rate": 0.00015375373531509683,
|
|
"loss": 1.33,
|
|
"step": 20120
|
|
},
|
|
{
|
|
"epoch": 6.26,
|
|
"learning_rate": 0.00015352824869919318,
|
|
"loss": 1.2941,
|
|
"step": 20130
|
|
},
|
|
{
|
|
"epoch": 6.27,
|
|
"learning_rate": 0.00015330285425722463,
|
|
"loss": 1.2896,
|
|
"step": 20140
|
|
},
|
|
{
|
|
"epoch": 6.27,
|
|
"learning_rate": 0.00015307755220454416,
|
|
"loss": 1.2911,
|
|
"step": 20150
|
|
},
|
|
{
|
|
"epoch": 6.27,
|
|
"learning_rate": 0.00015285234275641673,
|
|
"loss": 1.3201,
|
|
"step": 20160
|
|
},
|
|
{
|
|
"epoch": 6.28,
|
|
"learning_rate": 0.00015262722612801867,
|
|
"loss": 1.3236,
|
|
"step": 20170
|
|
},
|
|
{
|
|
"epoch": 6.28,
|
|
"learning_rate": 0.00015240220253443757,
|
|
"loss": 1.3202,
|
|
"step": 20180
|
|
},
|
|
{
|
|
"epoch": 6.28,
|
|
"learning_rate": 0.00015217727219067238,
|
|
"loss": 1.2735,
|
|
"step": 20190
|
|
},
|
|
{
|
|
"epoch": 6.28,
|
|
"learning_rate": 0.00015195243531163273,
|
|
"loss": 1.2774,
|
|
"step": 20200
|
|
},
|
|
{
|
|
"epoch": 6.29,
|
|
"learning_rate": 0.00015172769211213905,
|
|
"loss": 1.2621,
|
|
"step": 20210
|
|
},
|
|
{
|
|
"epoch": 6.29,
|
|
"learning_rate": 0.00015150304280692217,
|
|
"loss": 1.3403,
|
|
"step": 20220
|
|
},
|
|
{
|
|
"epoch": 6.29,
|
|
"learning_rate": 0.0001512784876106233,
|
|
"loss": 1.2761,
|
|
"step": 20230
|
|
},
|
|
{
|
|
"epoch": 6.3,
|
|
"learning_rate": 0.00015105402673779372,
|
|
"loss": 1.2799,
|
|
"step": 20240
|
|
},
|
|
{
|
|
"epoch": 6.3,
|
|
"learning_rate": 0.00015082966040289448,
|
|
"loss": 1.2744,
|
|
"step": 20250
|
|
},
|
|
{
|
|
"epoch": 6.3,
|
|
"learning_rate": 0.00015060538882029652,
|
|
"loss": 1.2773,
|
|
"step": 20260
|
|
},
|
|
{
|
|
"epoch": 6.31,
|
|
"learning_rate": 0.00015038121220428005,
|
|
"loss": 1.3547,
|
|
"step": 20270
|
|
},
|
|
{
|
|
"epoch": 6.31,
|
|
"learning_rate": 0.0001501571307690347,
|
|
"loss": 1.3128,
|
|
"step": 20280
|
|
},
|
|
{
|
|
"epoch": 6.31,
|
|
"learning_rate": 0.00014993314472865898,
|
|
"loss": 1.3576,
|
|
"step": 20290
|
|
},
|
|
{
|
|
"epoch": 6.32,
|
|
"learning_rate": 0.00014970925429716038,
|
|
"loss": 1.4753,
|
|
"step": 20300
|
|
},
|
|
{
|
|
"epoch": 6.32,
|
|
"learning_rate": 0.00014948545968845498,
|
|
"loss": 1.2585,
|
|
"step": 20310
|
|
},
|
|
{
|
|
"epoch": 6.32,
|
|
"learning_rate": 0.00014926176111636747,
|
|
"loss": 1.3926,
|
|
"step": 20320
|
|
},
|
|
{
|
|
"epoch": 6.32,
|
|
"learning_rate": 0.00014903815879463057,
|
|
"loss": 1.3064,
|
|
"step": 20330
|
|
},
|
|
{
|
|
"epoch": 6.33,
|
|
"learning_rate": 0.00014881465293688508,
|
|
"loss": 1.3746,
|
|
"step": 20340
|
|
},
|
|
{
|
|
"epoch": 6.33,
|
|
"learning_rate": 0.00014859124375667972,
|
|
"loss": 1.3529,
|
|
"step": 20350
|
|
},
|
|
{
|
|
"epoch": 6.33,
|
|
"learning_rate": 0.00014836793146747075,
|
|
"loss": 1.3557,
|
|
"step": 20360
|
|
},
|
|
{
|
|
"epoch": 6.34,
|
|
"learning_rate": 0.00014814471628262193,
|
|
"loss": 1.4359,
|
|
"step": 20370
|
|
},
|
|
{
|
|
"epoch": 6.34,
|
|
"learning_rate": 0.00014792159841540414,
|
|
"loss": 1.3968,
|
|
"step": 20380
|
|
},
|
|
{
|
|
"epoch": 6.34,
|
|
"learning_rate": 0.00014769857807899557,
|
|
"loss": 1.3382,
|
|
"step": 20390
|
|
},
|
|
{
|
|
"epoch": 6.35,
|
|
"learning_rate": 0.00014747565548648073,
|
|
"loss": 1.3953,
|
|
"step": 20400
|
|
},
|
|
{
|
|
"epoch": 6.35,
|
|
"learning_rate": 0.00014725283085085115,
|
|
"loss": 1.306,
|
|
"step": 20410
|
|
},
|
|
{
|
|
"epoch": 6.35,
|
|
"learning_rate": 0.00014703010438500463,
|
|
"loss": 1.3105,
|
|
"step": 20420
|
|
},
|
|
{
|
|
"epoch": 6.36,
|
|
"learning_rate": 0.00014680747630174513,
|
|
"loss": 1.3497,
|
|
"step": 20430
|
|
},
|
|
{
|
|
"epoch": 6.36,
|
|
"learning_rate": 0.0001465849468137826,
|
|
"loss": 1.3213,
|
|
"step": 20440
|
|
},
|
|
{
|
|
"epoch": 6.36,
|
|
"learning_rate": 0.00014636251613373298,
|
|
"loss": 1.2935,
|
|
"step": 20450
|
|
},
|
|
{
|
|
"epoch": 6.37,
|
|
"learning_rate": 0.00014614018447411752,
|
|
"loss": 1.3249,
|
|
"step": 20460
|
|
},
|
|
{
|
|
"epoch": 6.37,
|
|
"learning_rate": 0.0001459179520473632,
|
|
"loss": 1.2734,
|
|
"step": 20470
|
|
},
|
|
{
|
|
"epoch": 6.37,
|
|
"learning_rate": 0.00014569581906580186,
|
|
"loss": 1.3305,
|
|
"step": 20480
|
|
},
|
|
{
|
|
"epoch": 6.37,
|
|
"learning_rate": 0.00014547378574167034,
|
|
"loss": 1.3268,
|
|
"step": 20490
|
|
},
|
|
{
|
|
"epoch": 6.38,
|
|
"learning_rate": 0.00014525185228711062,
|
|
"loss": 1.3083,
|
|
"step": 20500
|
|
},
|
|
{
|
|
"epoch": 6.38,
|
|
"learning_rate": 0.00014503001891416877,
|
|
"loss": 1.3585,
|
|
"step": 20510
|
|
},
|
|
{
|
|
"epoch": 6.38,
|
|
"learning_rate": 0.00014480828583479576,
|
|
"loss": 1.3252,
|
|
"step": 20520
|
|
},
|
|
{
|
|
"epoch": 6.39,
|
|
"learning_rate": 0.00014458665326084626,
|
|
"loss": 1.2715,
|
|
"step": 20530
|
|
},
|
|
{
|
|
"epoch": 6.39,
|
|
"learning_rate": 0.00014436512140407926,
|
|
"loss": 1.3436,
|
|
"step": 20540
|
|
},
|
|
{
|
|
"epoch": 6.39,
|
|
"learning_rate": 0.00014414369047615724,
|
|
"loss": 1.3614,
|
|
"step": 20550
|
|
},
|
|
{
|
|
"epoch": 6.4,
|
|
"learning_rate": 0.0001439223606886464,
|
|
"loss": 1.2727,
|
|
"step": 20560
|
|
},
|
|
{
|
|
"epoch": 6.4,
|
|
"learning_rate": 0.00014370113225301625,
|
|
"loss": 1.3891,
|
|
"step": 20570
|
|
},
|
|
{
|
|
"epoch": 6.4,
|
|
"learning_rate": 0.0001434800053806397,
|
|
"loss": 1.2802,
|
|
"step": 20580
|
|
},
|
|
{
|
|
"epoch": 6.41,
|
|
"learning_rate": 0.00014325898028279223,
|
|
"loss": 1.3727,
|
|
"step": 20590
|
|
},
|
|
{
|
|
"epoch": 6.41,
|
|
"learning_rate": 0.00014303805717065236,
|
|
"loss": 1.3844,
|
|
"step": 20600
|
|
},
|
|
{
|
|
"epoch": 6.41,
|
|
"learning_rate": 0.00014281723625530107,
|
|
"loss": 1.3758,
|
|
"step": 20610
|
|
},
|
|
{
|
|
"epoch": 6.42,
|
|
"learning_rate": 0.0001425965177477217,
|
|
"loss": 1.42,
|
|
"step": 20620
|
|
},
|
|
{
|
|
"epoch": 6.42,
|
|
"learning_rate": 0.0001423759018587996,
|
|
"loss": 1.3521,
|
|
"step": 20630
|
|
},
|
|
{
|
|
"epoch": 6.42,
|
|
"learning_rate": 0.00014215538879932236,
|
|
"loss": 1.4453,
|
|
"step": 20640
|
|
},
|
|
{
|
|
"epoch": 6.42,
|
|
"learning_rate": 0.0001419349787799793,
|
|
"loss": 1.2807,
|
|
"step": 20650
|
|
},
|
|
{
|
|
"epoch": 6.43,
|
|
"learning_rate": 0.0001417146720113609,
|
|
"loss": 1.3317,
|
|
"step": 20660
|
|
},
|
|
{
|
|
"epoch": 6.43,
|
|
"learning_rate": 0.00014149446870395955,
|
|
"loss": 1.2651,
|
|
"step": 20670
|
|
},
|
|
{
|
|
"epoch": 6.43,
|
|
"learning_rate": 0.00014127436906816835,
|
|
"loss": 1.3387,
|
|
"step": 20680
|
|
},
|
|
{
|
|
"epoch": 6.44,
|
|
"learning_rate": 0.0001410543733142814,
|
|
"loss": 1.4489,
|
|
"step": 20690
|
|
},
|
|
{
|
|
"epoch": 6.44,
|
|
"learning_rate": 0.00014083448165249374,
|
|
"loss": 1.4073,
|
|
"step": 20700
|
|
},
|
|
{
|
|
"epoch": 6.44,
|
|
"learning_rate": 0.00014061469429290104,
|
|
"loss": 1.4025,
|
|
"step": 20710
|
|
},
|
|
{
|
|
"epoch": 6.45,
|
|
"learning_rate": 0.00014039501144549887,
|
|
"loss": 1.4292,
|
|
"step": 20720
|
|
},
|
|
{
|
|
"epoch": 6.45,
|
|
"learning_rate": 0.00014017543332018326,
|
|
"loss": 1.3708,
|
|
"step": 20730
|
|
},
|
|
{
|
|
"epoch": 6.45,
|
|
"learning_rate": 0.00013995596012675028,
|
|
"loss": 1.4343,
|
|
"step": 20740
|
|
},
|
|
{
|
|
"epoch": 6.46,
|
|
"learning_rate": 0.00013973659207489544,
|
|
"loss": 1.4268,
|
|
"step": 20750
|
|
},
|
|
{
|
|
"epoch": 6.46,
|
|
"learning_rate": 0.0001395173293742139,
|
|
"loss": 1.3464,
|
|
"step": 20760
|
|
},
|
|
{
|
|
"epoch": 6.46,
|
|
"learning_rate": 0.00013929817223420034,
|
|
"loss": 1.3075,
|
|
"step": 20770
|
|
},
|
|
{
|
|
"epoch": 6.46,
|
|
"learning_rate": 0.00013907912086424845,
|
|
"loss": 1.3758,
|
|
"step": 20780
|
|
},
|
|
{
|
|
"epoch": 6.47,
|
|
"learning_rate": 0.00013886017547365086,
|
|
"loss": 1.3496,
|
|
"step": 20790
|
|
},
|
|
{
|
|
"epoch": 6.47,
|
|
"learning_rate": 0.0001386413362715988,
|
|
"loss": 1.3166,
|
|
"step": 20800
|
|
},
|
|
{
|
|
"epoch": 6.47,
|
|
"learning_rate": 0.0001384226034671824,
|
|
"loss": 1.3522,
|
|
"step": 20810
|
|
},
|
|
{
|
|
"epoch": 6.48,
|
|
"learning_rate": 0.0001382039772693898,
|
|
"loss": 1.2841,
|
|
"step": 20820
|
|
},
|
|
{
|
|
"epoch": 6.48,
|
|
"learning_rate": 0.0001379854578871073,
|
|
"loss": 1.2873,
|
|
"step": 20830
|
|
},
|
|
{
|
|
"epoch": 6.48,
|
|
"learning_rate": 0.00013776704552911936,
|
|
"loss": 1.261,
|
|
"step": 20840
|
|
},
|
|
{
|
|
"epoch": 6.49,
|
|
"learning_rate": 0.0001375487404041082,
|
|
"loss": 1.3217,
|
|
"step": 20850
|
|
},
|
|
{
|
|
"epoch": 6.49,
|
|
"learning_rate": 0.00013733054272065326,
|
|
"loss": 1.362,
|
|
"step": 20860
|
|
},
|
|
{
|
|
"epoch": 6.49,
|
|
"learning_rate": 0.0001371124526872315,
|
|
"loss": 1.3548,
|
|
"step": 20870
|
|
},
|
|
{
|
|
"epoch": 6.5,
|
|
"learning_rate": 0.0001368944705122172,
|
|
"loss": 1.1949,
|
|
"step": 20880
|
|
},
|
|
{
|
|
"epoch": 6.5,
|
|
"learning_rate": 0.00013667659640388135,
|
|
"loss": 1.3021,
|
|
"step": 20890
|
|
},
|
|
{
|
|
"epoch": 6.5,
|
|
"learning_rate": 0.00013645883057039168,
|
|
"loss": 1.2855,
|
|
"step": 20900
|
|
},
|
|
{
|
|
"epoch": 6.51,
|
|
"learning_rate": 0.00013624117321981262,
|
|
"loss": 1.3536,
|
|
"step": 20910
|
|
},
|
|
{
|
|
"epoch": 6.51,
|
|
"learning_rate": 0.00013602362456010503,
|
|
"loss": 1.3959,
|
|
"step": 20920
|
|
},
|
|
{
|
|
"epoch": 6.51,
|
|
"learning_rate": 0.00013580618479912566,
|
|
"loss": 1.38,
|
|
"step": 20930
|
|
},
|
|
{
|
|
"epoch": 6.51,
|
|
"learning_rate": 0.0001355888541446272,
|
|
"loss": 1.274,
|
|
"step": 20940
|
|
},
|
|
{
|
|
"epoch": 6.52,
|
|
"learning_rate": 0.00013537163280425842,
|
|
"loss": 1.3637,
|
|
"step": 20950
|
|
},
|
|
{
|
|
"epoch": 6.52,
|
|
"learning_rate": 0.0001351545209855633,
|
|
"loss": 1.3191,
|
|
"step": 20960
|
|
},
|
|
{
|
|
"epoch": 6.52,
|
|
"learning_rate": 0.0001349375188959815,
|
|
"loss": 1.3704,
|
|
"step": 20970
|
|
},
|
|
{
|
|
"epoch": 6.53,
|
|
"learning_rate": 0.00013472062674284752,
|
|
"loss": 1.3643,
|
|
"step": 20980
|
|
},
|
|
{
|
|
"epoch": 6.53,
|
|
"learning_rate": 0.00013450384473339105,
|
|
"loss": 1.2485,
|
|
"step": 20990
|
|
},
|
|
{
|
|
"epoch": 6.53,
|
|
"learning_rate": 0.00013428717307473648,
|
|
"loss": 1.3136,
|
|
"step": 21000
|
|
},
|
|
{
|
|
"epoch": 6.54,
|
|
"learning_rate": 0.00013407061197390257,
|
|
"loss": 1.3917,
|
|
"step": 21010
|
|
},
|
|
{
|
|
"epoch": 6.54,
|
|
"learning_rate": 0.0001338541616378029,
|
|
"loss": 1.229,
|
|
"step": 21020
|
|
},
|
|
{
|
|
"epoch": 6.54,
|
|
"learning_rate": 0.00013363782227324465,
|
|
"loss": 1.2798,
|
|
"step": 21030
|
|
},
|
|
{
|
|
"epoch": 6.55,
|
|
"learning_rate": 0.00013342159408692952,
|
|
"loss": 1.3142,
|
|
"step": 21040
|
|
},
|
|
{
|
|
"epoch": 6.55,
|
|
"learning_rate": 0.00013320547728545252,
|
|
"loss": 1.3533,
|
|
"step": 21050
|
|
},
|
|
{
|
|
"epoch": 6.55,
|
|
"learning_rate": 0.00013298947207530267,
|
|
"loss": 1.4024,
|
|
"step": 21060
|
|
},
|
|
{
|
|
"epoch": 6.56,
|
|
"learning_rate": 0.00013277357866286205,
|
|
"loss": 1.3645,
|
|
"step": 21070
|
|
},
|
|
{
|
|
"epoch": 6.56,
|
|
"learning_rate": 0.00013255779725440586,
|
|
"loss": 1.2366,
|
|
"step": 21080
|
|
},
|
|
{
|
|
"epoch": 6.56,
|
|
"learning_rate": 0.00013234212805610262,
|
|
"loss": 1.2907,
|
|
"step": 21090
|
|
},
|
|
{
|
|
"epoch": 6.56,
|
|
"learning_rate": 0.00013212657127401354,
|
|
"loss": 1.3845,
|
|
"step": 21100
|
|
},
|
|
{
|
|
"epoch": 6.57,
|
|
"learning_rate": 0.00013191112711409222,
|
|
"loss": 1.3804,
|
|
"step": 21110
|
|
},
|
|
{
|
|
"epoch": 6.57,
|
|
"learning_rate": 0.00013169579578218473,
|
|
"loss": 1.293,
|
|
"step": 21120
|
|
},
|
|
{
|
|
"epoch": 6.57,
|
|
"learning_rate": 0.00013148057748402957,
|
|
"loss": 1.3565,
|
|
"step": 21130
|
|
},
|
|
{
|
|
"epoch": 6.58,
|
|
"learning_rate": 0.00013126547242525694,
|
|
"loss": 1.3767,
|
|
"step": 21140
|
|
},
|
|
{
|
|
"epoch": 6.58,
|
|
"learning_rate": 0.00013105048081138893,
|
|
"loss": 1.3828,
|
|
"step": 21150
|
|
},
|
|
{
|
|
"epoch": 6.58,
|
|
"learning_rate": 0.0001308356028478393,
|
|
"loss": 1.3658,
|
|
"step": 21160
|
|
},
|
|
{
|
|
"epoch": 6.59,
|
|
"learning_rate": 0.00013062083873991337,
|
|
"loss": 1.3017,
|
|
"step": 21170
|
|
},
|
|
{
|
|
"epoch": 6.59,
|
|
"learning_rate": 0.00013040618869280738,
|
|
"loss": 1.4465,
|
|
"step": 21180
|
|
},
|
|
{
|
|
"epoch": 6.59,
|
|
"learning_rate": 0.0001301916529116086,
|
|
"loss": 1.4526,
|
|
"step": 21190
|
|
},
|
|
{
|
|
"epoch": 6.6,
|
|
"learning_rate": 0.0001299772316012955,
|
|
"loss": 1.3104,
|
|
"step": 21200
|
|
},
|
|
{
|
|
"epoch": 6.6,
|
|
"learning_rate": 0.0001297629249667367,
|
|
"loss": 1.3025,
|
|
"step": 21210
|
|
},
|
|
{
|
|
"epoch": 6.6,
|
|
"learning_rate": 0.0001295487332126914,
|
|
"loss": 1.2884,
|
|
"step": 21220
|
|
},
|
|
{
|
|
"epoch": 6.6,
|
|
"learning_rate": 0.0001293346565438095,
|
|
"loss": 1.3681,
|
|
"step": 21230
|
|
},
|
|
{
|
|
"epoch": 6.61,
|
|
"learning_rate": 0.00012912069516463027,
|
|
"loss": 1.3917,
|
|
"step": 21240
|
|
},
|
|
{
|
|
"epoch": 6.61,
|
|
"learning_rate": 0.0001289068492795831,
|
|
"loss": 1.2553,
|
|
"step": 21250
|
|
},
|
|
{
|
|
"epoch": 6.61,
|
|
"learning_rate": 0.0001286931190929872,
|
|
"loss": 1.2623,
|
|
"step": 21260
|
|
},
|
|
{
|
|
"epoch": 6.62,
|
|
"learning_rate": 0.00012847950480905095,
|
|
"loss": 1.3819,
|
|
"step": 21270
|
|
},
|
|
{
|
|
"epoch": 6.62,
|
|
"learning_rate": 0.00012826600663187214,
|
|
"loss": 1.3884,
|
|
"step": 21280
|
|
},
|
|
{
|
|
"epoch": 6.62,
|
|
"learning_rate": 0.00012805262476543746,
|
|
"loss": 1.3044,
|
|
"step": 21290
|
|
},
|
|
{
|
|
"epoch": 6.63,
|
|
"learning_rate": 0.00012783935941362295,
|
|
"loss": 1.2559,
|
|
"step": 21300
|
|
},
|
|
{
|
|
"epoch": 6.63,
|
|
"learning_rate": 0.00012762621078019282,
|
|
"loss": 1.3207,
|
|
"step": 21310
|
|
},
|
|
{
|
|
"epoch": 6.63,
|
|
"learning_rate": 0.0001274131790687998,
|
|
"loss": 1.2632,
|
|
"step": 21320
|
|
},
|
|
{
|
|
"epoch": 6.64,
|
|
"learning_rate": 0.00012720026448298524,
|
|
"loss": 1.3932,
|
|
"step": 21330
|
|
},
|
|
{
|
|
"epoch": 6.64,
|
|
"learning_rate": 0.00012698746722617833,
|
|
"loss": 1.2696,
|
|
"step": 21340
|
|
},
|
|
{
|
|
"epoch": 6.64,
|
|
"learning_rate": 0.00012677478750169609,
|
|
"loss": 1.354,
|
|
"step": 21350
|
|
},
|
|
{
|
|
"epoch": 6.65,
|
|
"learning_rate": 0.00012656222551274345,
|
|
"loss": 1.307,
|
|
"step": 21360
|
|
},
|
|
{
|
|
"epoch": 6.65,
|
|
"learning_rate": 0.00012634978146241284,
|
|
"loss": 1.3517,
|
|
"step": 21370
|
|
},
|
|
{
|
|
"epoch": 6.65,
|
|
"learning_rate": 0.00012613745555368388,
|
|
"loss": 1.403,
|
|
"step": 21380
|
|
},
|
|
{
|
|
"epoch": 6.65,
|
|
"learning_rate": 0.00012592524798942322,
|
|
"loss": 1.4897,
|
|
"step": 21390
|
|
},
|
|
{
|
|
"epoch": 6.66,
|
|
"learning_rate": 0.00012573436253368752,
|
|
"loss": 1.3974,
|
|
"step": 21400
|
|
},
|
|
{
|
|
"epoch": 6.66,
|
|
"learning_rate": 0.00012552238038240974,
|
|
"loss": 1.4099,
|
|
"step": 21410
|
|
},
|
|
{
|
|
"epoch": 6.66,
|
|
"learning_rate": 0.00012531051716327404,
|
|
"loss": 1.3609,
|
|
"step": 21420
|
|
},
|
|
{
|
|
"epoch": 6.67,
|
|
"learning_rate": 0.00012509877307870503,
|
|
"loss": 1.3701,
|
|
"step": 21430
|
|
},
|
|
{
|
|
"epoch": 6.67,
|
|
"learning_rate": 0.00012488714833101355,
|
|
"loss": 1.3377,
|
|
"step": 21440
|
|
},
|
|
{
|
|
"epoch": 6.67,
|
|
"learning_rate": 0.00012467564312239652,
|
|
"loss": 1.4084,
|
|
"step": 21450
|
|
},
|
|
{
|
|
"epoch": 6.68,
|
|
"learning_rate": 0.00012446425765493669,
|
|
"loss": 1.3717,
|
|
"step": 21460
|
|
},
|
|
{
|
|
"epoch": 6.68,
|
|
"learning_rate": 0.00012425299213060222,
|
|
"loss": 1.4658,
|
|
"step": 21470
|
|
},
|
|
{
|
|
"epoch": 6.68,
|
|
"learning_rate": 0.00012404184675124662,
|
|
"loss": 1.34,
|
|
"step": 21480
|
|
},
|
|
{
|
|
"epoch": 6.69,
|
|
"learning_rate": 0.000123830821718609,
|
|
"loss": 1.3986,
|
|
"step": 21490
|
|
},
|
|
{
|
|
"epoch": 6.69,
|
|
"learning_rate": 0.00012361991723431308,
|
|
"loss": 1.3489,
|
|
"step": 21500
|
|
},
|
|
{
|
|
"epoch": 6.69,
|
|
"learning_rate": 0.00012340913349986746,
|
|
"loss": 1.4022,
|
|
"step": 21510
|
|
},
|
|
{
|
|
"epoch": 6.7,
|
|
"learning_rate": 0.0001231984707166656,
|
|
"loss": 1.3591,
|
|
"step": 21520
|
|
},
|
|
{
|
|
"epoch": 6.7,
|
|
"learning_rate": 0.0001229879290859853,
|
|
"loss": 1.3601,
|
|
"step": 21530
|
|
},
|
|
{
|
|
"epoch": 6.7,
|
|
"learning_rate": 0.0001227775088089885,
|
|
"loss": 1.2276,
|
|
"step": 21540
|
|
},
|
|
{
|
|
"epoch": 6.7,
|
|
"learning_rate": 0.00012256721008672115,
|
|
"loss": 1.4543,
|
|
"step": 21550
|
|
},
|
|
{
|
|
"epoch": 6.71,
|
|
"learning_rate": 0.00012235703312011334,
|
|
"loss": 1.2053,
|
|
"step": 21560
|
|
},
|
|
{
|
|
"epoch": 6.71,
|
|
"learning_rate": 0.0001221469781099785,
|
|
"loss": 1.3285,
|
|
"step": 21570
|
|
},
|
|
{
|
|
"epoch": 6.71,
|
|
"learning_rate": 0.00012193704525701383,
|
|
"loss": 1.3329,
|
|
"step": 21580
|
|
},
|
|
{
|
|
"epoch": 6.72,
|
|
"learning_rate": 0.0001217272347617995,
|
|
"loss": 1.3438,
|
|
"step": 21590
|
|
},
|
|
{
|
|
"epoch": 6.72,
|
|
"learning_rate": 0.00012151754682479918,
|
|
"loss": 1.4019,
|
|
"step": 21600
|
|
},
|
|
{
|
|
"epoch": 6.72,
|
|
"learning_rate": 0.00012130798164635906,
|
|
"loss": 1.3823,
|
|
"step": 21610
|
|
},
|
|
{
|
|
"epoch": 6.73,
|
|
"learning_rate": 0.00012109853942670812,
|
|
"loss": 1.3338,
|
|
"step": 21620
|
|
},
|
|
{
|
|
"epoch": 6.73,
|
|
"learning_rate": 0.00012088922036595812,
|
|
"loss": 1.399,
|
|
"step": 21630
|
|
},
|
|
{
|
|
"epoch": 6.73,
|
|
"learning_rate": 0.00012068002466410277,
|
|
"loss": 1.399,
|
|
"step": 21640
|
|
},
|
|
{
|
|
"epoch": 6.74,
|
|
"learning_rate": 0.00012047095252101828,
|
|
"loss": 1.348,
|
|
"step": 21650
|
|
},
|
|
{
|
|
"epoch": 6.74,
|
|
"learning_rate": 0.00012026200413646246,
|
|
"loss": 1.3701,
|
|
"step": 21660
|
|
},
|
|
{
|
|
"epoch": 6.74,
|
|
"learning_rate": 0.0001200531797100752,
|
|
"loss": 1.2793,
|
|
"step": 21670
|
|
},
|
|
{
|
|
"epoch": 6.74,
|
|
"learning_rate": 0.00011984447944137775,
|
|
"loss": 1.2881,
|
|
"step": 21680
|
|
},
|
|
{
|
|
"epoch": 6.75,
|
|
"learning_rate": 0.00011963590352977266,
|
|
"loss": 1.2723,
|
|
"step": 21690
|
|
},
|
|
{
|
|
"epoch": 6.75,
|
|
"learning_rate": 0.00011942745217454387,
|
|
"loss": 1.3051,
|
|
"step": 21700
|
|
},
|
|
{
|
|
"epoch": 6.75,
|
|
"learning_rate": 0.00011921912557485637,
|
|
"loss": 1.267,
|
|
"step": 21710
|
|
},
|
|
{
|
|
"epoch": 6.76,
|
|
"learning_rate": 0.00011901092392975566,
|
|
"loss": 1.2767,
|
|
"step": 21720
|
|
},
|
|
{
|
|
"epoch": 6.76,
|
|
"learning_rate": 0.00011880284743816792,
|
|
"loss": 1.2443,
|
|
"step": 21730
|
|
},
|
|
{
|
|
"epoch": 6.76,
|
|
"learning_rate": 0.00011859489629890002,
|
|
"loss": 1.3475,
|
|
"step": 21740
|
|
},
|
|
{
|
|
"epoch": 6.77,
|
|
"learning_rate": 0.00011838707071063885,
|
|
"loss": 1.2928,
|
|
"step": 21750
|
|
},
|
|
{
|
|
"epoch": 6.77,
|
|
"learning_rate": 0.00011817937087195116,
|
|
"loss": 1.3126,
|
|
"step": 21760
|
|
},
|
|
{
|
|
"epoch": 6.77,
|
|
"learning_rate": 0.00011797179698128396,
|
|
"loss": 1.3624,
|
|
"step": 21770
|
|
},
|
|
{
|
|
"epoch": 6.78,
|
|
"learning_rate": 0.00011776434923696375,
|
|
"loss": 1.4589,
|
|
"step": 21780
|
|
},
|
|
{
|
|
"epoch": 6.78,
|
|
"learning_rate": 0.0001175570278371964,
|
|
"loss": 1.3899,
|
|
"step": 21790
|
|
},
|
|
{
|
|
"epoch": 6.78,
|
|
"learning_rate": 0.0001173498329800671,
|
|
"loss": 1.3612,
|
|
"step": 21800
|
|
},
|
|
{
|
|
"epoch": 6.79,
|
|
"learning_rate": 0.00011714276486354029,
|
|
"loss": 1.3365,
|
|
"step": 21810
|
|
},
|
|
{
|
|
"epoch": 6.79,
|
|
"learning_rate": 0.00011693582368545913,
|
|
"loss": 1.3049,
|
|
"step": 21820
|
|
},
|
|
{
|
|
"epoch": 6.79,
|
|
"learning_rate": 0.0001167290096435455,
|
|
"loss": 1.4128,
|
|
"step": 21830
|
|
},
|
|
{
|
|
"epoch": 6.79,
|
|
"learning_rate": 0.00011652232293539993,
|
|
"loss": 1.2887,
|
|
"step": 21840
|
|
},
|
|
{
|
|
"epoch": 6.8,
|
|
"learning_rate": 0.00011631576375850139,
|
|
"loss": 1.2448,
|
|
"step": 21850
|
|
},
|
|
{
|
|
"epoch": 6.8,
|
|
"learning_rate": 0.0001161093323102067,
|
|
"loss": 1.3798,
|
|
"step": 21860
|
|
},
|
|
{
|
|
"epoch": 6.8,
|
|
"learning_rate": 0.00011590302878775073,
|
|
"loss": 1.3453,
|
|
"step": 21870
|
|
},
|
|
{
|
|
"epoch": 6.81,
|
|
"learning_rate": 0.00011569685338824631,
|
|
"loss": 1.3685,
|
|
"step": 21880
|
|
},
|
|
{
|
|
"epoch": 6.81,
|
|
"learning_rate": 0.00011549080630868373,
|
|
"loss": 1.3221,
|
|
"step": 21890
|
|
},
|
|
{
|
|
"epoch": 6.81,
|
|
"learning_rate": 0.00011528488774593037,
|
|
"loss": 1.316,
|
|
"step": 21900
|
|
},
|
|
{
|
|
"epoch": 6.82,
|
|
"learning_rate": 0.00011507909789673157,
|
|
"loss": 1.3797,
|
|
"step": 21910
|
|
},
|
|
{
|
|
"epoch": 6.82,
|
|
"learning_rate": 0.00011487343695770905,
|
|
"loss": 1.3546,
|
|
"step": 21920
|
|
},
|
|
{
|
|
"epoch": 6.82,
|
|
"learning_rate": 0.00011466790512536155,
|
|
"loss": 1.3156,
|
|
"step": 21930
|
|
},
|
|
{
|
|
"epoch": 6.83,
|
|
"learning_rate": 0.00011446250259606434,
|
|
"loss": 1.2615,
|
|
"step": 21940
|
|
},
|
|
{
|
|
"epoch": 6.83,
|
|
"learning_rate": 0.00011425722956606948,
|
|
"loss": 1.3169,
|
|
"step": 21950
|
|
},
|
|
{
|
|
"epoch": 6.83,
|
|
"learning_rate": 0.0001140520862315049,
|
|
"loss": 1.335,
|
|
"step": 21960
|
|
},
|
|
{
|
|
"epoch": 6.84,
|
|
"learning_rate": 0.00011384707278837487,
|
|
"loss": 1.3072,
|
|
"step": 21970
|
|
},
|
|
{
|
|
"epoch": 6.84,
|
|
"learning_rate": 0.00011364218943255961,
|
|
"loss": 1.235,
|
|
"step": 21980
|
|
},
|
|
{
|
|
"epoch": 6.84,
|
|
"learning_rate": 0.0001134374363598148,
|
|
"loss": 1.2826,
|
|
"step": 21990
|
|
},
|
|
{
|
|
"epoch": 6.84,
|
|
"learning_rate": 0.0001132328137657718,
|
|
"loss": 1.2708,
|
|
"step": 22000
|
|
},
|
|
{
|
|
"epoch": 6.85,
|
|
"learning_rate": 0.00011302832184593711,
|
|
"loss": 1.3697,
|
|
"step": 22010
|
|
},
|
|
{
|
|
"epoch": 6.85,
|
|
"learning_rate": 0.00011282396079569282,
|
|
"loss": 1.4099,
|
|
"step": 22020
|
|
},
|
|
{
|
|
"epoch": 6.85,
|
|
"learning_rate": 0.00011261973081029542,
|
|
"loss": 1.2513,
|
|
"step": 22030
|
|
},
|
|
{
|
|
"epoch": 6.86,
|
|
"learning_rate": 0.00011241563208487657,
|
|
"loss": 1.2657,
|
|
"step": 22040
|
|
},
|
|
{
|
|
"epoch": 6.86,
|
|
"learning_rate": 0.00011221166481444254,
|
|
"loss": 1.3476,
|
|
"step": 22050
|
|
},
|
|
{
|
|
"epoch": 6.86,
|
|
"learning_rate": 0.00011200782919387368,
|
|
"loss": 1.3392,
|
|
"step": 22060
|
|
},
|
|
{
|
|
"epoch": 6.87,
|
|
"learning_rate": 0.0001118041254179247,
|
|
"loss": 1.2665,
|
|
"step": 22070
|
|
},
|
|
{
|
|
"epoch": 6.87,
|
|
"learning_rate": 0.00011160055368122454,
|
|
"loss": 1.3858,
|
|
"step": 22080
|
|
},
|
|
{
|
|
"epoch": 6.87,
|
|
"learning_rate": 0.00011139711417827564,
|
|
"loss": 1.3111,
|
|
"step": 22090
|
|
},
|
|
{
|
|
"epoch": 6.88,
|
|
"learning_rate": 0.00011119380710345444,
|
|
"loss": 1.2999,
|
|
"step": 22100
|
|
},
|
|
{
|
|
"epoch": 6.88,
|
|
"learning_rate": 0.00011099063265101056,
|
|
"loss": 1.2343,
|
|
"step": 22110
|
|
},
|
|
{
|
|
"epoch": 6.88,
|
|
"learning_rate": 0.00011078759101506714,
|
|
"loss": 1.2738,
|
|
"step": 22120
|
|
},
|
|
{
|
|
"epoch": 6.88,
|
|
"learning_rate": 0.00011058468238962024,
|
|
"loss": 1.3328,
|
|
"step": 22130
|
|
},
|
|
{
|
|
"epoch": 6.89,
|
|
"learning_rate": 0.00011038190696853883,
|
|
"loss": 1.3339,
|
|
"step": 22140
|
|
},
|
|
{
|
|
"epoch": 6.89,
|
|
"learning_rate": 0.00011017926494556477,
|
|
"loss": 1.4093,
|
|
"step": 22150
|
|
},
|
|
{
|
|
"epoch": 6.89,
|
|
"learning_rate": 0.00010997675651431249,
|
|
"loss": 1.3204,
|
|
"step": 22160
|
|
},
|
|
{
|
|
"epoch": 6.9,
|
|
"learning_rate": 0.00010977438186826854,
|
|
"loss": 1.3279,
|
|
"step": 22170
|
|
},
|
|
{
|
|
"epoch": 6.9,
|
|
"learning_rate": 0.00010957214120079173,
|
|
"loss": 1.3109,
|
|
"step": 22180
|
|
},
|
|
{
|
|
"epoch": 6.9,
|
|
"learning_rate": 0.00010937003470511308,
|
|
"loss": 1.3269,
|
|
"step": 22190
|
|
},
|
|
{
|
|
"epoch": 6.91,
|
|
"learning_rate": 0.00010916806257433511,
|
|
"loss": 1.2505,
|
|
"step": 22200
|
|
},
|
|
{
|
|
"epoch": 6.91,
|
|
"learning_rate": 0.00010896622500143205,
|
|
"loss": 1.2771,
|
|
"step": 22210
|
|
},
|
|
{
|
|
"epoch": 6.91,
|
|
"learning_rate": 0.00010876452217924967,
|
|
"loss": 1.4613,
|
|
"step": 22220
|
|
},
|
|
{
|
|
"epoch": 6.92,
|
|
"learning_rate": 0.00010856295430050505,
|
|
"loss": 1.3381,
|
|
"step": 22230
|
|
},
|
|
{
|
|
"epoch": 6.92,
|
|
"learning_rate": 0.00010836152155778611,
|
|
"loss": 1.1864,
|
|
"step": 22240
|
|
},
|
|
{
|
|
"epoch": 6.92,
|
|
"learning_rate": 0.00010816022414355167,
|
|
"loss": 1.4416,
|
|
"step": 22250
|
|
},
|
|
{
|
|
"epoch": 6.93,
|
|
"learning_rate": 0.00010795906225013155,
|
|
"loss": 1.2887,
|
|
"step": 22260
|
|
},
|
|
{
|
|
"epoch": 6.93,
|
|
"learning_rate": 0.00010775803606972576,
|
|
"loss": 1.351,
|
|
"step": 22270
|
|
},
|
|
{
|
|
"epoch": 6.93,
|
|
"learning_rate": 0.00010755714579440471,
|
|
"loss": 1.3093,
|
|
"step": 22280
|
|
},
|
|
{
|
|
"epoch": 6.93,
|
|
"learning_rate": 0.00010735639161610905,
|
|
"loss": 1.3654,
|
|
"step": 22290
|
|
},
|
|
{
|
|
"epoch": 6.94,
|
|
"learning_rate": 0.00010715577372664951,
|
|
"loss": 1.4104,
|
|
"step": 22300
|
|
},
|
|
{
|
|
"epoch": 6.94,
|
|
"learning_rate": 0.00010695529231770632,
|
|
"loss": 1.3468,
|
|
"step": 22310
|
|
},
|
|
{
|
|
"epoch": 6.94,
|
|
"learning_rate": 0.00010675494758082937,
|
|
"loss": 1.3042,
|
|
"step": 22320
|
|
},
|
|
{
|
|
"epoch": 6.95,
|
|
"learning_rate": 0.00010655473970743823,
|
|
"loss": 1.2815,
|
|
"step": 22330
|
|
},
|
|
{
|
|
"epoch": 6.95,
|
|
"learning_rate": 0.00010635466888882143,
|
|
"loss": 1.3292,
|
|
"step": 22340
|
|
},
|
|
{
|
|
"epoch": 6.95,
|
|
"learning_rate": 0.00010615473531613649,
|
|
"loss": 1.3262,
|
|
"step": 22350
|
|
},
|
|
{
|
|
"epoch": 6.96,
|
|
"learning_rate": 0.00010595493918041007,
|
|
"loss": 1.3407,
|
|
"step": 22360
|
|
},
|
|
{
|
|
"epoch": 6.96,
|
|
"learning_rate": 0.0001057552806725375,
|
|
"loss": 1.2763,
|
|
"step": 22370
|
|
},
|
|
{
|
|
"epoch": 6.96,
|
|
"learning_rate": 0.0001055557599832824,
|
|
"loss": 1.3058,
|
|
"step": 22380
|
|
},
|
|
{
|
|
"epoch": 6.97,
|
|
"learning_rate": 0.00010535637730327669,
|
|
"loss": 1.3351,
|
|
"step": 22390
|
|
},
|
|
{
|
|
"epoch": 6.97,
|
|
"learning_rate": 0.00010515713282302075,
|
|
"loss": 1.4053,
|
|
"step": 22400
|
|
},
|
|
{
|
|
"epoch": 6.97,
|
|
"learning_rate": 0.00010495802673288257,
|
|
"loss": 1.3326,
|
|
"step": 22410
|
|
},
|
|
{
|
|
"epoch": 6.98,
|
|
"learning_rate": 0.00010475905922309819,
|
|
"loss": 1.4257,
|
|
"step": 22420
|
|
},
|
|
{
|
|
"epoch": 6.98,
|
|
"learning_rate": 0.00010456023048377097,
|
|
"loss": 1.3353,
|
|
"step": 22430
|
|
},
|
|
{
|
|
"epoch": 6.98,
|
|
"learning_rate": 0.00010436154070487203,
|
|
"loss": 1.3911,
|
|
"step": 22440
|
|
},
|
|
{
|
|
"epoch": 6.98,
|
|
"learning_rate": 0.00010416299007623939,
|
|
"loss": 1.2697,
|
|
"step": 22450
|
|
},
|
|
{
|
|
"epoch": 6.99,
|
|
"learning_rate": 0.00010396457878757815,
|
|
"loss": 1.3325,
|
|
"step": 22460
|
|
},
|
|
{
|
|
"epoch": 6.99,
|
|
"learning_rate": 0.0001037663070284606,
|
|
"loss": 1.3284,
|
|
"step": 22470
|
|
},
|
|
{
|
|
"epoch": 6.99,
|
|
"learning_rate": 0.0001035681749883253,
|
|
"loss": 1.3567,
|
|
"step": 22480
|
|
},
|
|
{
|
|
"epoch": 7.0,
|
|
"learning_rate": 0.00010337018285647768,
|
|
"loss": 1.3003,
|
|
"step": 22490
|
|
},
|
|
{
|
|
"epoch": 7.0,
|
|
"learning_rate": 0.00010317233082208913,
|
|
"loss": 1.4002,
|
|
"step": 22500
|
|
},
|
|
{
|
|
"epoch": 7.0,
|
|
"learning_rate": 0.00010297461907419758,
|
|
"loss": 1.3377,
|
|
"step": 22510
|
|
},
|
|
{
|
|
"epoch": 7.01,
|
|
"learning_rate": 0.00010277704780170663,
|
|
"loss": 1.2031,
|
|
"step": 22520
|
|
},
|
|
{
|
|
"epoch": 7.01,
|
|
"learning_rate": 0.00010257961719338563,
|
|
"loss": 1.2384,
|
|
"step": 22530
|
|
},
|
|
{
|
|
"epoch": 7.01,
|
|
"learning_rate": 0.0001023823274378698,
|
|
"loss": 1.2546,
|
|
"step": 22540
|
|
},
|
|
{
|
|
"epoch": 7.02,
|
|
"learning_rate": 0.00010218517872365968,
|
|
"loss": 1.349,
|
|
"step": 22550
|
|
},
|
|
{
|
|
"epoch": 7.02,
|
|
"learning_rate": 0.00010198817123912082,
|
|
"loss": 1.3096,
|
|
"step": 22560
|
|
},
|
|
{
|
|
"epoch": 7.02,
|
|
"learning_rate": 0.00010179130517248428,
|
|
"loss": 1.1924,
|
|
"step": 22570
|
|
},
|
|
{
|
|
"epoch": 7.02,
|
|
"learning_rate": 0.00010159458071184557,
|
|
"loss": 1.1466,
|
|
"step": 22580
|
|
},
|
|
{
|
|
"epoch": 7.03,
|
|
"learning_rate": 0.00010139799804516511,
|
|
"loss": 1.3049,
|
|
"step": 22590
|
|
},
|
|
{
|
|
"epoch": 7.03,
|
|
"learning_rate": 0.0001012015573602677,
|
|
"loss": 1.1356,
|
|
"step": 22600
|
|
},
|
|
{
|
|
"epoch": 7.03,
|
|
"learning_rate": 0.00010100525884484274,
|
|
"loss": 1.2372,
|
|
"step": 22610
|
|
},
|
|
{
|
|
"epoch": 7.04,
|
|
"learning_rate": 0.00010080910268644366,
|
|
"loss": 1.1561,
|
|
"step": 22620
|
|
},
|
|
{
|
|
"epoch": 7.04,
|
|
"learning_rate": 0.00010061308907248773,
|
|
"loss": 1.3597,
|
|
"step": 22630
|
|
},
|
|
{
|
|
"epoch": 7.04,
|
|
"learning_rate": 0.00010041721819025635,
|
|
"loss": 1.3172,
|
|
"step": 22640
|
|
},
|
|
{
|
|
"epoch": 7.05,
|
|
"learning_rate": 0.00010022149022689422,
|
|
"loss": 1.1837,
|
|
"step": 22650
|
|
},
|
|
{
|
|
"epoch": 7.05,
|
|
"learning_rate": 0.00010002590536940956,
|
|
"loss": 1.2498,
|
|
"step": 22660
|
|
},
|
|
{
|
|
"epoch": 7.05,
|
|
"learning_rate": 9.9830463804674e-05,
|
|
"loss": 1.2723,
|
|
"step": 22670
|
|
},
|
|
{
|
|
"epoch": 7.06,
|
|
"learning_rate": 9.963516571942227e-05,
|
|
"loss": 1.2505,
|
|
"step": 22680
|
|
},
|
|
{
|
|
"epoch": 7.06,
|
|
"learning_rate": 9.944001130025188e-05,
|
|
"loss": 1.2317,
|
|
"step": 22690
|
|
},
|
|
{
|
|
"epoch": 7.06,
|
|
"learning_rate": 9.924500073362296e-05,
|
|
"loss": 1.3426,
|
|
"step": 22700
|
|
},
|
|
{
|
|
"epoch": 7.07,
|
|
"learning_rate": 9.905013420585862e-05,
|
|
"loss": 1.1887,
|
|
"step": 22710
|
|
},
|
|
{
|
|
"epoch": 7.07,
|
|
"learning_rate": 9.885541190314393e-05,
|
|
"loss": 1.1939,
|
|
"step": 22720
|
|
},
|
|
{
|
|
"epoch": 7.07,
|
|
"learning_rate": 9.866083401152623e-05,
|
|
"loss": 1.2226,
|
|
"step": 22730
|
|
},
|
|
{
|
|
"epoch": 7.07,
|
|
"learning_rate": 9.846640071691507e-05,
|
|
"loss": 1.329,
|
|
"step": 22740
|
|
},
|
|
{
|
|
"epoch": 7.08,
|
|
"learning_rate": 9.827211220508184e-05,
|
|
"loss": 1.2544,
|
|
"step": 22750
|
|
},
|
|
{
|
|
"epoch": 7.08,
|
|
"learning_rate": 9.80779686616594e-05,
|
|
"loss": 1.3286,
|
|
"step": 22760
|
|
},
|
|
{
|
|
"epoch": 7.08,
|
|
"learning_rate": 9.788397027214213e-05,
|
|
"loss": 1.2301,
|
|
"step": 22770
|
|
},
|
|
{
|
|
"epoch": 7.09,
|
|
"learning_rate": 9.769011722188592e-05,
|
|
"loss": 1.2018,
|
|
"step": 22780
|
|
},
|
|
{
|
|
"epoch": 7.09,
|
|
"learning_rate": 9.749640969610762e-05,
|
|
"loss": 1.1948,
|
|
"step": 22790
|
|
},
|
|
{
|
|
"epoch": 7.09,
|
|
"learning_rate": 9.730284787988499e-05,
|
|
"loss": 1.1953,
|
|
"step": 22800
|
|
},
|
|
{
|
|
"epoch": 7.1,
|
|
"learning_rate": 9.710943195815675e-05,
|
|
"loss": 1.2396,
|
|
"step": 22810
|
|
},
|
|
{
|
|
"epoch": 7.1,
|
|
"learning_rate": 9.691616211572225e-05,
|
|
"loss": 1.1299,
|
|
"step": 22820
|
|
},
|
|
{
|
|
"epoch": 7.1,
|
|
"learning_rate": 9.672303853724104e-05,
|
|
"loss": 1.2238,
|
|
"step": 22830
|
|
},
|
|
{
|
|
"epoch": 7.11,
|
|
"learning_rate": 9.653006140723298e-05,
|
|
"loss": 1.2011,
|
|
"step": 22840
|
|
},
|
|
{
|
|
"epoch": 7.11,
|
|
"learning_rate": 9.633723091007823e-05,
|
|
"loss": 1.249,
|
|
"step": 22850
|
|
},
|
|
{
|
|
"epoch": 7.11,
|
|
"learning_rate": 9.614454723001661e-05,
|
|
"loss": 1.2674,
|
|
"step": 22860
|
|
},
|
|
{
|
|
"epoch": 7.12,
|
|
"learning_rate": 9.595201055114766e-05,
|
|
"loss": 1.2515,
|
|
"step": 22870
|
|
},
|
|
{
|
|
"epoch": 7.12,
|
|
"learning_rate": 9.575962105743064e-05,
|
|
"loss": 1.2058,
|
|
"step": 22880
|
|
},
|
|
{
|
|
"epoch": 7.12,
|
|
"learning_rate": 9.556737893268417e-05,
|
|
"loss": 1.361,
|
|
"step": 22890
|
|
},
|
|
{
|
|
"epoch": 7.12,
|
|
"learning_rate": 9.53752843605859e-05,
|
|
"loss": 1.3597,
|
|
"step": 22900
|
|
},
|
|
{
|
|
"epoch": 7.13,
|
|
"learning_rate": 9.51833375246725e-05,
|
|
"loss": 1.2816,
|
|
"step": 22910
|
|
},
|
|
{
|
|
"epoch": 7.13,
|
|
"learning_rate": 9.499153860833976e-05,
|
|
"loss": 1.3282,
|
|
"step": 22920
|
|
},
|
|
{
|
|
"epoch": 7.13,
|
|
"learning_rate": 9.479988779484178e-05,
|
|
"loss": 1.2959,
|
|
"step": 22930
|
|
},
|
|
{
|
|
"epoch": 7.14,
|
|
"learning_rate": 9.460838526729148e-05,
|
|
"loss": 1.3699,
|
|
"step": 22940
|
|
},
|
|
{
|
|
"epoch": 7.14,
|
|
"learning_rate": 9.441703120865983e-05,
|
|
"loss": 1.2139,
|
|
"step": 22950
|
|
},
|
|
{
|
|
"epoch": 7.14,
|
|
"learning_rate": 9.422582580177616e-05,
|
|
"loss": 1.2532,
|
|
"step": 22960
|
|
},
|
|
{
|
|
"epoch": 7.15,
|
|
"learning_rate": 9.403476922932768e-05,
|
|
"loss": 1.2559,
|
|
"step": 22970
|
|
},
|
|
{
|
|
"epoch": 7.15,
|
|
"learning_rate": 9.384386167385925e-05,
|
|
"loss": 1.2645,
|
|
"step": 22980
|
|
},
|
|
{
|
|
"epoch": 7.15,
|
|
"learning_rate": 9.365310331777365e-05,
|
|
"loss": 1.1829,
|
|
"step": 22990
|
|
},
|
|
{
|
|
"epoch": 7.16,
|
|
"learning_rate": 9.346249434333084e-05,
|
|
"loss": 1.201,
|
|
"step": 23000
|
|
},
|
|
{
|
|
"epoch": 7.16,
|
|
"learning_rate": 9.32720349326483e-05,
|
|
"loss": 1.1911,
|
|
"step": 23010
|
|
},
|
|
{
|
|
"epoch": 7.16,
|
|
"learning_rate": 9.30817252677003e-05,
|
|
"loss": 1.1993,
|
|
"step": 23020
|
|
},
|
|
{
|
|
"epoch": 7.16,
|
|
"learning_rate": 9.28915655303184e-05,
|
|
"loss": 1.3303,
|
|
"step": 23030
|
|
},
|
|
{
|
|
"epoch": 7.17,
|
|
"learning_rate": 9.270155590219062e-05,
|
|
"loss": 1.2912,
|
|
"step": 23040
|
|
},
|
|
{
|
|
"epoch": 7.17,
|
|
"learning_rate": 9.251169656486159e-05,
|
|
"loss": 1.29,
|
|
"step": 23050
|
|
},
|
|
{
|
|
"epoch": 7.17,
|
|
"learning_rate": 9.23219876997325e-05,
|
|
"loss": 1.1453,
|
|
"step": 23060
|
|
},
|
|
{
|
|
"epoch": 7.18,
|
|
"learning_rate": 9.213242948806072e-05,
|
|
"loss": 1.2032,
|
|
"step": 23070
|
|
},
|
|
{
|
|
"epoch": 7.18,
|
|
"learning_rate": 9.194302211095961e-05,
|
|
"loss": 1.2197,
|
|
"step": 23080
|
|
},
|
|
{
|
|
"epoch": 7.18,
|
|
"learning_rate": 9.17537657493984e-05,
|
|
"loss": 1.3339,
|
|
"step": 23090
|
|
},
|
|
{
|
|
"epoch": 7.19,
|
|
"learning_rate": 9.156466058420216e-05,
|
|
"loss": 1.2329,
|
|
"step": 23100
|
|
},
|
|
{
|
|
"epoch": 7.19,
|
|
"learning_rate": 9.137570679605137e-05,
|
|
"loss": 1.3419,
|
|
"step": 23110
|
|
},
|
|
{
|
|
"epoch": 7.19,
|
|
"learning_rate": 9.118690456548188e-05,
|
|
"loss": 1.253,
|
|
"step": 23120
|
|
},
|
|
{
|
|
"epoch": 7.2,
|
|
"learning_rate": 9.099825407288484e-05,
|
|
"loss": 1.194,
|
|
"step": 23130
|
|
},
|
|
{
|
|
"epoch": 7.2,
|
|
"learning_rate": 9.080975549850642e-05,
|
|
"loss": 1.2608,
|
|
"step": 23140
|
|
},
|
|
{
|
|
"epoch": 7.2,
|
|
"learning_rate": 9.062140902244747e-05,
|
|
"loss": 1.1979,
|
|
"step": 23150
|
|
},
|
|
{
|
|
"epoch": 7.21,
|
|
"learning_rate": 9.043321482466376e-05,
|
|
"loss": 1.3896,
|
|
"step": 23160
|
|
},
|
|
{
|
|
"epoch": 7.21,
|
|
"learning_rate": 9.024517308496536e-05,
|
|
"loss": 1.181,
|
|
"step": 23170
|
|
},
|
|
{
|
|
"epoch": 7.21,
|
|
"learning_rate": 9.005728398301677e-05,
|
|
"loss": 1.2401,
|
|
"step": 23180
|
|
},
|
|
{
|
|
"epoch": 7.21,
|
|
"learning_rate": 8.986954769833643e-05,
|
|
"loss": 1.3146,
|
|
"step": 23190
|
|
},
|
|
{
|
|
"epoch": 7.22,
|
|
"learning_rate": 8.968196441029733e-05,
|
|
"loss": 1.3334,
|
|
"step": 23200
|
|
},
|
|
{
|
|
"epoch": 7.22,
|
|
"learning_rate": 8.949453429812576e-05,
|
|
"loss": 1.1953,
|
|
"step": 23210
|
|
},
|
|
{
|
|
"epoch": 7.22,
|
|
"learning_rate": 8.930725754090175e-05,
|
|
"loss": 1.2547,
|
|
"step": 23220
|
|
},
|
|
{
|
|
"epoch": 7.23,
|
|
"learning_rate": 8.9120134317559e-05,
|
|
"loss": 1.2867,
|
|
"step": 23230
|
|
},
|
|
{
|
|
"epoch": 7.23,
|
|
"learning_rate": 8.893316480688435e-05,
|
|
"loss": 1.252,
|
|
"step": 23240
|
|
},
|
|
{
|
|
"epoch": 7.23,
|
|
"learning_rate": 8.874634918751782e-05,
|
|
"loss": 1.3482,
|
|
"step": 23250
|
|
},
|
|
{
|
|
"epoch": 7.24,
|
|
"learning_rate": 8.855968763795218e-05,
|
|
"loss": 1.2118,
|
|
"step": 23260
|
|
},
|
|
{
|
|
"epoch": 7.24,
|
|
"learning_rate": 8.83731803365336e-05,
|
|
"loss": 1.2695,
|
|
"step": 23270
|
|
},
|
|
{
|
|
"epoch": 7.24,
|
|
"learning_rate": 8.818682746146028e-05,
|
|
"loss": 1.1475,
|
|
"step": 23280
|
|
},
|
|
{
|
|
"epoch": 7.25,
|
|
"learning_rate": 8.800062919078302e-05,
|
|
"loss": 1.2013,
|
|
"step": 23290
|
|
},
|
|
{
|
|
"epoch": 7.25,
|
|
"learning_rate": 8.781458570240508e-05,
|
|
"loss": 1.2121,
|
|
"step": 23300
|
|
},
|
|
{
|
|
"epoch": 7.25,
|
|
"learning_rate": 8.762869717408167e-05,
|
|
"loss": 1.2442,
|
|
"step": 23310
|
|
},
|
|
{
|
|
"epoch": 7.26,
|
|
"learning_rate": 8.74429637834199e-05,
|
|
"loss": 1.1955,
|
|
"step": 23320
|
|
},
|
|
{
|
|
"epoch": 7.26,
|
|
"learning_rate": 8.725738570787881e-05,
|
|
"loss": 1.1789,
|
|
"step": 23330
|
|
},
|
|
{
|
|
"epoch": 7.26,
|
|
"learning_rate": 8.707196312476903e-05,
|
|
"loss": 1.2295,
|
|
"step": 23340
|
|
},
|
|
{
|
|
"epoch": 7.26,
|
|
"learning_rate": 8.688669621125253e-05,
|
|
"loss": 1.2921,
|
|
"step": 23350
|
|
},
|
|
{
|
|
"epoch": 7.27,
|
|
"learning_rate": 8.670158514434245e-05,
|
|
"loss": 1.1572,
|
|
"step": 23360
|
|
},
|
|
{
|
|
"epoch": 7.27,
|
|
"learning_rate": 8.651663010090338e-05,
|
|
"loss": 1.2775,
|
|
"step": 23370
|
|
},
|
|
{
|
|
"epoch": 7.27,
|
|
"learning_rate": 8.63318312576505e-05,
|
|
"loss": 1.2255,
|
|
"step": 23380
|
|
},
|
|
{
|
|
"epoch": 7.28,
|
|
"learning_rate": 8.614718879114983e-05,
|
|
"loss": 1.2202,
|
|
"step": 23390
|
|
},
|
|
{
|
|
"epoch": 7.28,
|
|
"learning_rate": 8.596270287781802e-05,
|
|
"loss": 1.1631,
|
|
"step": 23400
|
|
},
|
|
{
|
|
"epoch": 7.28,
|
|
"learning_rate": 8.57967995544667e-05,
|
|
"loss": 1.1994,
|
|
"step": 23410
|
|
},
|
|
{
|
|
"epoch": 7.29,
|
|
"learning_rate": 8.56126115776478e-05,
|
|
"loss": 1.232,
|
|
"step": 23420
|
|
},
|
|
{
|
|
"epoch": 7.29,
|
|
"learning_rate": 8.542858066475969e-05,
|
|
"loss": 1.2904,
|
|
"step": 23430
|
|
},
|
|
{
|
|
"epoch": 7.29,
|
|
"learning_rate": 8.524470699163461e-05,
|
|
"loss": 1.3113,
|
|
"step": 23440
|
|
},
|
|
{
|
|
"epoch": 7.3,
|
|
"learning_rate": 8.50609907339546e-05,
|
|
"loss": 1.344,
|
|
"step": 23450
|
|
},
|
|
{
|
|
"epoch": 7.3,
|
|
"learning_rate": 8.487743206725149e-05,
|
|
"loss": 1.1735,
|
|
"step": 23460
|
|
},
|
|
{
|
|
"epoch": 7.3,
|
|
"learning_rate": 8.469403116690635e-05,
|
|
"loss": 1.2419,
|
|
"step": 23470
|
|
},
|
|
{
|
|
"epoch": 7.3,
|
|
"learning_rate": 8.451078820814948e-05,
|
|
"loss": 1.3204,
|
|
"step": 23480
|
|
},
|
|
{
|
|
"epoch": 7.31,
|
|
"learning_rate": 8.432770336606044e-05,
|
|
"loss": 1.355,
|
|
"step": 23490
|
|
},
|
|
{
|
|
"epoch": 7.31,
|
|
"learning_rate": 8.414477681556776e-05,
|
|
"loss": 1.3,
|
|
"step": 23500
|
|
},
|
|
{
|
|
"epoch": 7.31,
|
|
"learning_rate": 8.396200873144849e-05,
|
|
"loss": 1.1883,
|
|
"step": 23510
|
|
},
|
|
{
|
|
"epoch": 7.32,
|
|
"learning_rate": 8.377939928832834e-05,
|
|
"loss": 1.223,
|
|
"step": 23520
|
|
},
|
|
{
|
|
"epoch": 7.32,
|
|
"learning_rate": 8.359694866068166e-05,
|
|
"loss": 1.1616,
|
|
"step": 23530
|
|
},
|
|
{
|
|
"epoch": 7.32,
|
|
"learning_rate": 8.341465702283071e-05,
|
|
"loss": 1.2473,
|
|
"step": 23540
|
|
},
|
|
{
|
|
"epoch": 7.33,
|
|
"learning_rate": 8.323252454894625e-05,
|
|
"loss": 1.2471,
|
|
"step": 23550
|
|
},
|
|
{
|
|
"epoch": 7.33,
|
|
"learning_rate": 8.305055141304654e-05,
|
|
"loss": 1.2728,
|
|
"step": 23560
|
|
},
|
|
{
|
|
"epoch": 7.33,
|
|
"learning_rate": 8.286873778899803e-05,
|
|
"loss": 1.3031,
|
|
"step": 23570
|
|
},
|
|
{
|
|
"epoch": 7.34,
|
|
"learning_rate": 8.268708385051444e-05,
|
|
"loss": 1.289,
|
|
"step": 23580
|
|
},
|
|
{
|
|
"epoch": 7.34,
|
|
"learning_rate": 8.25055897711569e-05,
|
|
"loss": 1.2523,
|
|
"step": 23590
|
|
},
|
|
{
|
|
"epoch": 7.34,
|
|
"learning_rate": 8.232425572433418e-05,
|
|
"loss": 1.3111,
|
|
"step": 23600
|
|
},
|
|
{
|
|
"epoch": 7.35,
|
|
"learning_rate": 8.214308188330167e-05,
|
|
"loss": 1.2108,
|
|
"step": 23610
|
|
},
|
|
{
|
|
"epoch": 7.35,
|
|
"learning_rate": 8.19620684211621e-05,
|
|
"loss": 1.2291,
|
|
"step": 23620
|
|
},
|
|
{
|
|
"epoch": 7.35,
|
|
"learning_rate": 8.178121551086459e-05,
|
|
"loss": 1.2933,
|
|
"step": 23630
|
|
},
|
|
{
|
|
"epoch": 7.35,
|
|
"learning_rate": 8.160052332520526e-05,
|
|
"loss": 1.2852,
|
|
"step": 23640
|
|
},
|
|
{
|
|
"epoch": 7.36,
|
|
"learning_rate": 8.141999203682637e-05,
|
|
"loss": 1.1909,
|
|
"step": 23650
|
|
},
|
|
{
|
|
"epoch": 7.36,
|
|
"learning_rate": 8.123962181821645e-05,
|
|
"loss": 1.1926,
|
|
"step": 23660
|
|
},
|
|
{
|
|
"epoch": 7.36,
|
|
"learning_rate": 8.105941284171028e-05,
|
|
"loss": 1.2179,
|
|
"step": 23670
|
|
},
|
|
{
|
|
"epoch": 7.37,
|
|
"learning_rate": 8.087936527948866e-05,
|
|
"loss": 1.2941,
|
|
"step": 23680
|
|
},
|
|
{
|
|
"epoch": 7.37,
|
|
"learning_rate": 8.069947930357793e-05,
|
|
"loss": 1.2979,
|
|
"step": 23690
|
|
},
|
|
{
|
|
"epoch": 7.37,
|
|
"learning_rate": 8.051975508585005e-05,
|
|
"loss": 1.2334,
|
|
"step": 23700
|
|
},
|
|
{
|
|
"epoch": 7.38,
|
|
"learning_rate": 8.034019279802268e-05,
|
|
"loss": 1.2422,
|
|
"step": 23710
|
|
},
|
|
{
|
|
"epoch": 7.38,
|
|
"learning_rate": 8.016079261165856e-05,
|
|
"loss": 1.3097,
|
|
"step": 23720
|
|
},
|
|
{
|
|
"epoch": 7.38,
|
|
"learning_rate": 7.998155469816551e-05,
|
|
"loss": 1.3028,
|
|
"step": 23730
|
|
},
|
|
{
|
|
"epoch": 7.39,
|
|
"learning_rate": 7.980247922879649e-05,
|
|
"loss": 1.2412,
|
|
"step": 23740
|
|
},
|
|
{
|
|
"epoch": 7.39,
|
|
"learning_rate": 7.962356637464919e-05,
|
|
"loss": 1.3179,
|
|
"step": 23750
|
|
},
|
|
{
|
|
"epoch": 7.39,
|
|
"learning_rate": 7.944481630666584e-05,
|
|
"loss": 1.2778,
|
|
"step": 23760
|
|
},
|
|
{
|
|
"epoch": 7.4,
|
|
"learning_rate": 7.926622919563312e-05,
|
|
"loss": 1.3183,
|
|
"step": 23770
|
|
},
|
|
{
|
|
"epoch": 7.4,
|
|
"learning_rate": 7.908780521218226e-05,
|
|
"loss": 1.265,
|
|
"step": 23780
|
|
},
|
|
{
|
|
"epoch": 7.4,
|
|
"learning_rate": 7.890954452678834e-05,
|
|
"loss": 1.2544,
|
|
"step": 23790
|
|
},
|
|
{
|
|
"epoch": 7.4,
|
|
"learning_rate": 7.873144730977047e-05,
|
|
"loss": 1.2597,
|
|
"step": 23800
|
|
},
|
|
{
|
|
"epoch": 7.41,
|
|
"learning_rate": 7.855351373129171e-05,
|
|
"loss": 1.2712,
|
|
"step": 23810
|
|
},
|
|
{
|
|
"epoch": 7.41,
|
|
"learning_rate": 7.83757439613588e-05,
|
|
"loss": 1.29,
|
|
"step": 23820
|
|
},
|
|
{
|
|
"epoch": 7.41,
|
|
"learning_rate": 7.819813816982177e-05,
|
|
"loss": 1.2795,
|
|
"step": 23830
|
|
},
|
|
{
|
|
"epoch": 7.42,
|
|
"learning_rate": 7.8020696526374e-05,
|
|
"loss": 1.1652,
|
|
"step": 23840
|
|
},
|
|
{
|
|
"epoch": 7.42,
|
|
"learning_rate": 7.784341920055223e-05,
|
|
"loss": 1.2117,
|
|
"step": 23850
|
|
},
|
|
{
|
|
"epoch": 7.42,
|
|
"learning_rate": 7.766630636173608e-05,
|
|
"loss": 1.2254,
|
|
"step": 23860
|
|
},
|
|
{
|
|
"epoch": 7.43,
|
|
"learning_rate": 7.748935817914779e-05,
|
|
"loss": 1.1811,
|
|
"step": 23870
|
|
},
|
|
{
|
|
"epoch": 7.43,
|
|
"learning_rate": 7.731257482185283e-05,
|
|
"loss": 1.2741,
|
|
"step": 23880
|
|
},
|
|
{
|
|
"epoch": 7.43,
|
|
"learning_rate": 7.713595645875874e-05,
|
|
"loss": 1.3053,
|
|
"step": 23890
|
|
},
|
|
{
|
|
"epoch": 7.44,
|
|
"learning_rate": 7.695950325861548e-05,
|
|
"loss": 1.2452,
|
|
"step": 23900
|
|
},
|
|
{
|
|
"epoch": 7.44,
|
|
"learning_rate": 7.67832153900152e-05,
|
|
"loss": 1.1593,
|
|
"step": 23910
|
|
},
|
|
{
|
|
"epoch": 7.44,
|
|
"learning_rate": 7.660709302139233e-05,
|
|
"loss": 1.2587,
|
|
"step": 23920
|
|
},
|
|
{
|
|
"epoch": 7.44,
|
|
"learning_rate": 7.64311363210228e-05,
|
|
"loss": 1.2252,
|
|
"step": 23930
|
|
},
|
|
{
|
|
"epoch": 7.45,
|
|
"learning_rate": 7.62553454570245e-05,
|
|
"loss": 1.2079,
|
|
"step": 23940
|
|
},
|
|
{
|
|
"epoch": 7.45,
|
|
"learning_rate": 7.607972059735696e-05,
|
|
"loss": 1.3291,
|
|
"step": 23950
|
|
},
|
|
{
|
|
"epoch": 7.45,
|
|
"learning_rate": 7.59042619098208e-05,
|
|
"loss": 1.3155,
|
|
"step": 23960
|
|
},
|
|
{
|
|
"epoch": 7.46,
|
|
"learning_rate": 7.572896956205807e-05,
|
|
"loss": 1.26,
|
|
"step": 23970
|
|
},
|
|
{
|
|
"epoch": 7.46,
|
|
"learning_rate": 7.555384372155174e-05,
|
|
"loss": 1.3089,
|
|
"step": 23980
|
|
},
|
|
{
|
|
"epoch": 7.46,
|
|
"learning_rate": 7.537888455562597e-05,
|
|
"loss": 1.3774,
|
|
"step": 23990
|
|
},
|
|
{
|
|
"epoch": 7.47,
|
|
"learning_rate": 7.520409223144533e-05,
|
|
"loss": 1.2407,
|
|
"step": 24000
|
|
},
|
|
{
|
|
"epoch": 7.47,
|
|
"learning_rate": 7.502946691601523e-05,
|
|
"loss": 1.2927,
|
|
"step": 24010
|
|
},
|
|
{
|
|
"epoch": 7.47,
|
|
"learning_rate": 7.485500877618148e-05,
|
|
"loss": 1.255,
|
|
"step": 24020
|
|
},
|
|
{
|
|
"epoch": 7.48,
|
|
"learning_rate": 7.468071797863008e-05,
|
|
"loss": 1.2512,
|
|
"step": 24030
|
|
},
|
|
{
|
|
"epoch": 7.48,
|
|
"learning_rate": 7.450659468988705e-05,
|
|
"loss": 1.2703,
|
|
"step": 24040
|
|
},
|
|
{
|
|
"epoch": 7.48,
|
|
"learning_rate": 7.433263907631869e-05,
|
|
"loss": 1.2952,
|
|
"step": 24050
|
|
},
|
|
{
|
|
"epoch": 7.49,
|
|
"learning_rate": 7.415885130413067e-05,
|
|
"loss": 1.1651,
|
|
"step": 24060
|
|
},
|
|
{
|
|
"epoch": 7.49,
|
|
"learning_rate": 7.398523153936874e-05,
|
|
"loss": 1.3077,
|
|
"step": 24070
|
|
},
|
|
{
|
|
"epoch": 7.49,
|
|
"learning_rate": 7.381177994791768e-05,
|
|
"loss": 1.1978,
|
|
"step": 24080
|
|
},
|
|
{
|
|
"epoch": 7.49,
|
|
"learning_rate": 7.363849669550205e-05,
|
|
"loss": 1.3924,
|
|
"step": 24090
|
|
},
|
|
{
|
|
"epoch": 7.5,
|
|
"learning_rate": 7.346538194768518e-05,
|
|
"loss": 1.2992,
|
|
"step": 24100
|
|
},
|
|
{
|
|
"epoch": 7.5,
|
|
"learning_rate": 7.329243586986952e-05,
|
|
"loss": 1.3395,
|
|
"step": 24110
|
|
},
|
|
{
|
|
"epoch": 7.5,
|
|
"learning_rate": 7.311965862729658e-05,
|
|
"loss": 1.3667,
|
|
"step": 24120
|
|
},
|
|
{
|
|
"epoch": 7.51,
|
|
"learning_rate": 7.294705038504614e-05,
|
|
"loss": 1.2174,
|
|
"step": 24130
|
|
},
|
|
{
|
|
"epoch": 7.51,
|
|
"learning_rate": 7.2774611308037e-05,
|
|
"loss": 1.2122,
|
|
"step": 24140
|
|
},
|
|
{
|
|
"epoch": 7.51,
|
|
"learning_rate": 7.260234156102585e-05,
|
|
"loss": 1.3198,
|
|
"step": 24150
|
|
},
|
|
{
|
|
"epoch": 7.52,
|
|
"learning_rate": 7.2430241308608e-05,
|
|
"loss": 1.258,
|
|
"step": 24160
|
|
},
|
|
{
|
|
"epoch": 7.52,
|
|
"learning_rate": 7.225831071521655e-05,
|
|
"loss": 1.2196,
|
|
"step": 24170
|
|
},
|
|
{
|
|
"epoch": 7.52,
|
|
"learning_rate": 7.208654994512254e-05,
|
|
"loss": 1.2716,
|
|
"step": 24180
|
|
},
|
|
{
|
|
"epoch": 7.53,
|
|
"learning_rate": 7.191495916243482e-05,
|
|
"loss": 1.2825,
|
|
"step": 24190
|
|
},
|
|
{
|
|
"epoch": 7.53,
|
|
"learning_rate": 7.174353853109994e-05,
|
|
"loss": 1.234,
|
|
"step": 24200
|
|
},
|
|
{
|
|
"epoch": 7.53,
|
|
"learning_rate": 7.157228821490161e-05,
|
|
"loss": 1.244,
|
|
"step": 24210
|
|
},
|
|
{
|
|
"epoch": 7.54,
|
|
"learning_rate": 7.140120837746092e-05,
|
|
"loss": 1.2099,
|
|
"step": 24220
|
|
},
|
|
{
|
|
"epoch": 7.54,
|
|
"learning_rate": 7.12302991822362e-05,
|
|
"loss": 1.3434,
|
|
"step": 24230
|
|
},
|
|
{
|
|
"epoch": 7.54,
|
|
"learning_rate": 7.105956079252262e-05,
|
|
"loss": 1.2335,
|
|
"step": 24240
|
|
},
|
|
{
|
|
"epoch": 7.54,
|
|
"learning_rate": 7.088899337145207e-05,
|
|
"loss": 1.2585,
|
|
"step": 24250
|
|
},
|
|
{
|
|
"epoch": 7.55,
|
|
"learning_rate": 7.071859708199327e-05,
|
|
"loss": 1.2021,
|
|
"step": 24260
|
|
},
|
|
{
|
|
"epoch": 7.55,
|
|
"learning_rate": 7.054837208695142e-05,
|
|
"loss": 1.2528,
|
|
"step": 24270
|
|
},
|
|
{
|
|
"epoch": 7.55,
|
|
"learning_rate": 7.037831854896795e-05,
|
|
"loss": 1.2296,
|
|
"step": 24280
|
|
},
|
|
{
|
|
"epoch": 7.56,
|
|
"learning_rate": 7.02084366305204e-05,
|
|
"loss": 1.3105,
|
|
"step": 24290
|
|
},
|
|
{
|
|
"epoch": 7.56,
|
|
"learning_rate": 7.003872649392265e-05,
|
|
"loss": 1.2392,
|
|
"step": 24300
|
|
},
|
|
{
|
|
"epoch": 7.56,
|
|
"learning_rate": 6.986918830132411e-05,
|
|
"loss": 1.2554,
|
|
"step": 24310
|
|
},
|
|
{
|
|
"epoch": 7.57,
|
|
"learning_rate": 6.969982221471002e-05,
|
|
"loss": 1.2858,
|
|
"step": 24320
|
|
},
|
|
{
|
|
"epoch": 7.57,
|
|
"learning_rate": 6.953062839590124e-05,
|
|
"loss": 1.2584,
|
|
"step": 24330
|
|
},
|
|
{
|
|
"epoch": 7.57,
|
|
"learning_rate": 6.936160700655414e-05,
|
|
"loss": 1.2499,
|
|
"step": 24340
|
|
},
|
|
{
|
|
"epoch": 7.58,
|
|
"learning_rate": 6.91927582081601e-05,
|
|
"loss": 1.3407,
|
|
"step": 24350
|
|
},
|
|
{
|
|
"epoch": 7.58,
|
|
"learning_rate": 6.902408216204561e-05,
|
|
"loss": 1.2077,
|
|
"step": 24360
|
|
},
|
|
{
|
|
"epoch": 7.58,
|
|
"learning_rate": 6.885557902937237e-05,
|
|
"loss": 1.2672,
|
|
"step": 24370
|
|
},
|
|
{
|
|
"epoch": 7.58,
|
|
"learning_rate": 6.868724897113654e-05,
|
|
"loss": 1.2475,
|
|
"step": 24380
|
|
},
|
|
{
|
|
"epoch": 7.59,
|
|
"learning_rate": 6.851909214816926e-05,
|
|
"loss": 1.2968,
|
|
"step": 24390
|
|
},
|
|
{
|
|
"epoch": 7.59,
|
|
"learning_rate": 6.835110872113576e-05,
|
|
"loss": 1.291,
|
|
"step": 24400
|
|
},
|
|
{
|
|
"epoch": 7.59,
|
|
"learning_rate": 6.818329885053597e-05,
|
|
"loss": 1.3261,
|
|
"step": 24410
|
|
},
|
|
{
|
|
"epoch": 7.6,
|
|
"learning_rate": 6.80156626967038e-05,
|
|
"loss": 1.2771,
|
|
"step": 24420
|
|
},
|
|
{
|
|
"epoch": 7.6,
|
|
"learning_rate": 6.78482004198071e-05,
|
|
"loss": 1.2391,
|
|
"step": 24430
|
|
},
|
|
{
|
|
"epoch": 7.6,
|
|
"learning_rate": 6.768091217984787e-05,
|
|
"loss": 1.3067,
|
|
"step": 24440
|
|
},
|
|
{
|
|
"epoch": 7.61,
|
|
"learning_rate": 6.75137981366615e-05,
|
|
"loss": 1.1717,
|
|
"step": 24450
|
|
},
|
|
{
|
|
"epoch": 7.61,
|
|
"learning_rate": 6.734685844991722e-05,
|
|
"loss": 1.2879,
|
|
"step": 24460
|
|
},
|
|
{
|
|
"epoch": 7.61,
|
|
"learning_rate": 6.718009327911748e-05,
|
|
"loss": 1.2897,
|
|
"step": 24470
|
|
},
|
|
{
|
|
"epoch": 7.62,
|
|
"learning_rate": 6.701350278359817e-05,
|
|
"loss": 1.2976,
|
|
"step": 24480
|
|
},
|
|
{
|
|
"epoch": 7.62,
|
|
"learning_rate": 6.684708712252807e-05,
|
|
"loss": 1.3391,
|
|
"step": 24490
|
|
},
|
|
{
|
|
"epoch": 7.62,
|
|
"learning_rate": 6.668084645490899e-05,
|
|
"loss": 1.2888,
|
|
"step": 24500
|
|
},
|
|
{
|
|
"epoch": 7.63,
|
|
"learning_rate": 6.651478093957567e-05,
|
|
"loss": 1.2593,
|
|
"step": 24510
|
|
},
|
|
{
|
|
"epoch": 7.63,
|
|
"learning_rate": 6.634889073519542e-05,
|
|
"loss": 1.2818,
|
|
"step": 24520
|
|
},
|
|
{
|
|
"epoch": 7.63,
|
|
"learning_rate": 6.618317600026796e-05,
|
|
"loss": 1.1669,
|
|
"step": 24530
|
|
},
|
|
{
|
|
"epoch": 7.63,
|
|
"learning_rate": 6.601763689312553e-05,
|
|
"loss": 1.3301,
|
|
"step": 24540
|
|
},
|
|
{
|
|
"epoch": 7.64,
|
|
"learning_rate": 6.58522735719324e-05,
|
|
"loss": 1.2604,
|
|
"step": 24550
|
|
},
|
|
{
|
|
"epoch": 7.64,
|
|
"learning_rate": 6.5687086194685e-05,
|
|
"loss": 1.3117,
|
|
"step": 24560
|
|
},
|
|
{
|
|
"epoch": 7.64,
|
|
"learning_rate": 6.55220749192115e-05,
|
|
"loss": 1.2847,
|
|
"step": 24570
|
|
},
|
|
{
|
|
"epoch": 7.65,
|
|
"learning_rate": 6.535723990317197e-05,
|
|
"loss": 1.2053,
|
|
"step": 24580
|
|
},
|
|
{
|
|
"epoch": 7.65,
|
|
"learning_rate": 6.519258130405817e-05,
|
|
"loss": 1.2339,
|
|
"step": 24590
|
|
},
|
|
{
|
|
"epoch": 7.65,
|
|
"learning_rate": 6.502809927919295e-05,
|
|
"loss": 1.2967,
|
|
"step": 24600
|
|
},
|
|
{
|
|
"epoch": 7.66,
|
|
"learning_rate": 6.486379398573083e-05,
|
|
"loss": 1.3409,
|
|
"step": 24610
|
|
},
|
|
{
|
|
"epoch": 7.66,
|
|
"learning_rate": 6.469966558065724e-05,
|
|
"loss": 1.372,
|
|
"step": 24620
|
|
},
|
|
{
|
|
"epoch": 7.66,
|
|
"learning_rate": 6.453571422078858e-05,
|
|
"loss": 1.278,
|
|
"step": 24630
|
|
},
|
|
{
|
|
"epoch": 7.67,
|
|
"learning_rate": 6.437194006277225e-05,
|
|
"loss": 1.2732,
|
|
"step": 24640
|
|
},
|
|
{
|
|
"epoch": 7.67,
|
|
"learning_rate": 6.420834326308636e-05,
|
|
"loss": 1.2592,
|
|
"step": 24650
|
|
},
|
|
{
|
|
"epoch": 7.67,
|
|
"learning_rate": 6.404492397803938e-05,
|
|
"loss": 1.2647,
|
|
"step": 24660
|
|
},
|
|
{
|
|
"epoch": 7.68,
|
|
"learning_rate": 6.388168236377018e-05,
|
|
"loss": 1.21,
|
|
"step": 24670
|
|
},
|
|
{
|
|
"epoch": 7.68,
|
|
"learning_rate": 6.371861857624814e-05,
|
|
"loss": 1.2262,
|
|
"step": 24680
|
|
},
|
|
{
|
|
"epoch": 7.68,
|
|
"learning_rate": 6.355573277127249e-05,
|
|
"loss": 1.2423,
|
|
"step": 24690
|
|
},
|
|
{
|
|
"epoch": 7.68,
|
|
"learning_rate": 6.339302510447237e-05,
|
|
"loss": 1.185,
|
|
"step": 24700
|
|
},
|
|
{
|
|
"epoch": 7.69,
|
|
"learning_rate": 6.323049573130688e-05,
|
|
"loss": 1.3196,
|
|
"step": 24710
|
|
},
|
|
{
|
|
"epoch": 7.69,
|
|
"learning_rate": 6.306814480706483e-05,
|
|
"loss": 1.4347,
|
|
"step": 24720
|
|
},
|
|
{
|
|
"epoch": 7.69,
|
|
"learning_rate": 6.29059724868643e-05,
|
|
"loss": 1.2859,
|
|
"step": 24730
|
|
},
|
|
{
|
|
"epoch": 7.7,
|
|
"learning_rate": 6.274397892565278e-05,
|
|
"loss": 1.2577,
|
|
"step": 24740
|
|
},
|
|
{
|
|
"epoch": 7.7,
|
|
"learning_rate": 6.258216427820714e-05,
|
|
"loss": 1.2662,
|
|
"step": 24750
|
|
},
|
|
{
|
|
"epoch": 7.7,
|
|
"learning_rate": 6.242052869913314e-05,
|
|
"loss": 1.2829,
|
|
"step": 24760
|
|
},
|
|
{
|
|
"epoch": 7.71,
|
|
"learning_rate": 6.225907234286544e-05,
|
|
"loss": 1.2754,
|
|
"step": 24770
|
|
},
|
|
{
|
|
"epoch": 7.71,
|
|
"learning_rate": 6.209779536366756e-05,
|
|
"loss": 1.1949,
|
|
"step": 24780
|
|
},
|
|
{
|
|
"epoch": 7.71,
|
|
"learning_rate": 6.193669791563164e-05,
|
|
"loss": 1.1404,
|
|
"step": 24790
|
|
},
|
|
{
|
|
"epoch": 7.72,
|
|
"learning_rate": 6.177578015267817e-05,
|
|
"loss": 1.3365,
|
|
"step": 24800
|
|
},
|
|
{
|
|
"epoch": 7.72,
|
|
"learning_rate": 6.161504222855602e-05,
|
|
"loss": 1.3557,
|
|
"step": 24810
|
|
},
|
|
{
|
|
"epoch": 7.72,
|
|
"learning_rate": 6.145448429684233e-05,
|
|
"loss": 1.1364,
|
|
"step": 24820
|
|
},
|
|
{
|
|
"epoch": 7.72,
|
|
"learning_rate": 6.129410651094209e-05,
|
|
"loss": 1.2313,
|
|
"step": 24830
|
|
},
|
|
{
|
|
"epoch": 7.73,
|
|
"learning_rate": 6.113390902408822e-05,
|
|
"loss": 1.1698,
|
|
"step": 24840
|
|
},
|
|
{
|
|
"epoch": 7.73,
|
|
"learning_rate": 6.097389198934147e-05,
|
|
"loss": 1.3365,
|
|
"step": 24850
|
|
},
|
|
{
|
|
"epoch": 7.73,
|
|
"learning_rate": 6.081405555959018e-05,
|
|
"loss": 1.3433,
|
|
"step": 24860
|
|
},
|
|
{
|
|
"epoch": 7.74,
|
|
"learning_rate": 6.0654399887550006e-05,
|
|
"loss": 1.3199,
|
|
"step": 24870
|
|
},
|
|
{
|
|
"epoch": 7.74,
|
|
"learning_rate": 6.049492512576388e-05,
|
|
"loss": 1.173,
|
|
"step": 24880
|
|
},
|
|
{
|
|
"epoch": 7.74,
|
|
"learning_rate": 6.033563142660212e-05,
|
|
"loss": 1.3625,
|
|
"step": 24890
|
|
},
|
|
{
|
|
"epoch": 7.75,
|
|
"learning_rate": 6.017651894226173e-05,
|
|
"loss": 1.3926,
|
|
"step": 24900
|
|
},
|
|
{
|
|
"epoch": 7.75,
|
|
"learning_rate": 6.001758782476688e-05,
|
|
"loss": 1.2723,
|
|
"step": 24910
|
|
},
|
|
{
|
|
"epoch": 7.75,
|
|
"learning_rate": 5.9858838225968184e-05,
|
|
"loss": 1.3253,
|
|
"step": 24920
|
|
},
|
|
{
|
|
"epoch": 7.76,
|
|
"learning_rate": 5.970027029754305e-05,
|
|
"loss": 1.4048,
|
|
"step": 24930
|
|
},
|
|
{
|
|
"epoch": 7.76,
|
|
"learning_rate": 5.9541884190995185e-05,
|
|
"loss": 1.2903,
|
|
"step": 24940
|
|
},
|
|
{
|
|
"epoch": 7.76,
|
|
"learning_rate": 5.938368005765449e-05,
|
|
"loss": 1.2163,
|
|
"step": 24950
|
|
},
|
|
{
|
|
"epoch": 7.77,
|
|
"learning_rate": 5.9225658048677245e-05,
|
|
"loss": 1.1524,
|
|
"step": 24960
|
|
},
|
|
{
|
|
"epoch": 7.77,
|
|
"learning_rate": 5.9067818315045454e-05,
|
|
"loss": 1.2961,
|
|
"step": 24970
|
|
},
|
|
{
|
|
"epoch": 7.77,
|
|
"learning_rate": 5.891016100756721e-05,
|
|
"loss": 1.3555,
|
|
"step": 24980
|
|
},
|
|
{
|
|
"epoch": 7.77,
|
|
"learning_rate": 5.8752686276876076e-05,
|
|
"loss": 1.2769,
|
|
"step": 24990
|
|
},
|
|
{
|
|
"epoch": 7.78,
|
|
"learning_rate": 5.859539427343141e-05,
|
|
"loss": 1.2575,
|
|
"step": 25000
|
|
},
|
|
{
|
|
"epoch": 7.78,
|
|
"learning_rate": 5.843828514751781e-05,
|
|
"loss": 1.2992,
|
|
"step": 25010
|
|
},
|
|
{
|
|
"epoch": 7.78,
|
|
"learning_rate": 5.828135904924506e-05,
|
|
"loss": 1.3171,
|
|
"step": 25020
|
|
},
|
|
{
|
|
"epoch": 7.79,
|
|
"learning_rate": 5.812461612854833e-05,
|
|
"loss": 1.2837,
|
|
"step": 25030
|
|
},
|
|
{
|
|
"epoch": 7.79,
|
|
"learning_rate": 5.796805653518769e-05,
|
|
"loss": 1.2199,
|
|
"step": 25040
|
|
},
|
|
{
|
|
"epoch": 7.79,
|
|
"learning_rate": 5.781168041874793e-05,
|
|
"loss": 1.3308,
|
|
"step": 25050
|
|
},
|
|
{
|
|
"epoch": 7.8,
|
|
"learning_rate": 5.7655487928638536e-05,
|
|
"loss": 1.1787,
|
|
"step": 25060
|
|
},
|
|
{
|
|
"epoch": 7.8,
|
|
"learning_rate": 5.7499479214093794e-05,
|
|
"loss": 1.2644,
|
|
"step": 25070
|
|
},
|
|
{
|
|
"epoch": 7.8,
|
|
"learning_rate": 5.734365442417214e-05,
|
|
"loss": 1.3556,
|
|
"step": 25080
|
|
},
|
|
{
|
|
"epoch": 7.81,
|
|
"learning_rate": 5.7188013707756307e-05,
|
|
"loss": 1.2423,
|
|
"step": 25090
|
|
},
|
|
{
|
|
"epoch": 7.81,
|
|
"learning_rate": 5.703255721355327e-05,
|
|
"loss": 1.3837,
|
|
"step": 25100
|
|
},
|
|
{
|
|
"epoch": 7.81,
|
|
"learning_rate": 5.687728509009402e-05,
|
|
"loss": 1.3556,
|
|
"step": 25110
|
|
},
|
|
{
|
|
"epoch": 7.82,
|
|
"learning_rate": 5.672219748573315e-05,
|
|
"loss": 1.2157,
|
|
"step": 25120
|
|
},
|
|
{
|
|
"epoch": 7.82,
|
|
"learning_rate": 5.656729454864928e-05,
|
|
"loss": 1.2398,
|
|
"step": 25130
|
|
},
|
|
{
|
|
"epoch": 7.82,
|
|
"learning_rate": 5.641257642684436e-05,
|
|
"loss": 1.2448,
|
|
"step": 25140
|
|
},
|
|
{
|
|
"epoch": 7.82,
|
|
"learning_rate": 5.625804326814379e-05,
|
|
"loss": 1.2192,
|
|
"step": 25150
|
|
},
|
|
{
|
|
"epoch": 7.83,
|
|
"learning_rate": 5.610369522019615e-05,
|
|
"loss": 1.1683,
|
|
"step": 25160
|
|
},
|
|
{
|
|
"epoch": 7.83,
|
|
"learning_rate": 5.5949532430473546e-05,
|
|
"loss": 1.2751,
|
|
"step": 25170
|
|
},
|
|
{
|
|
"epoch": 7.83,
|
|
"learning_rate": 5.579555504627068e-05,
|
|
"loss": 1.3197,
|
|
"step": 25180
|
|
},
|
|
{
|
|
"epoch": 7.84,
|
|
"learning_rate": 5.564176321470521e-05,
|
|
"loss": 1.3682,
|
|
"step": 25190
|
|
},
|
|
{
|
|
"epoch": 7.84,
|
|
"learning_rate": 5.548815708271765e-05,
|
|
"loss": 1.2612,
|
|
"step": 25200
|
|
},
|
|
{
|
|
"epoch": 7.84,
|
|
"learning_rate": 5.533473679707091e-05,
|
|
"loss": 1.2914,
|
|
"step": 25210
|
|
},
|
|
{
|
|
"epoch": 7.85,
|
|
"learning_rate": 5.518150250435042e-05,
|
|
"loss": 1.2488,
|
|
"step": 25220
|
|
},
|
|
{
|
|
"epoch": 7.85,
|
|
"learning_rate": 5.504375078586346e-05,
|
|
"loss": 1.2784,
|
|
"step": 25230
|
|
},
|
|
{
|
|
"epoch": 7.85,
|
|
"learning_rate": 5.4890870282909036e-05,
|
|
"loss": 1.308,
|
|
"step": 25240
|
|
},
|
|
{
|
|
"epoch": 7.86,
|
|
"learning_rate": 5.4738176196973e-05,
|
|
"loss": 1.2584,
|
|
"step": 25250
|
|
},
|
|
{
|
|
"epoch": 7.86,
|
|
"learning_rate": 5.458566867394715e-05,
|
|
"loss": 1.2689,
|
|
"step": 25260
|
|
},
|
|
{
|
|
"epoch": 7.86,
|
|
"learning_rate": 5.443334785954468e-05,
|
|
"loss": 1.2912,
|
|
"step": 25270
|
|
},
|
|
{
|
|
"epoch": 7.86,
|
|
"learning_rate": 5.428121389930052e-05,
|
|
"loss": 1.305,
|
|
"step": 25280
|
|
},
|
|
{
|
|
"epoch": 7.87,
|
|
"learning_rate": 5.412926693857098e-05,
|
|
"loss": 1.1544,
|
|
"step": 25290
|
|
},
|
|
{
|
|
"epoch": 7.87,
|
|
"learning_rate": 5.397750712253391e-05,
|
|
"loss": 1.3483,
|
|
"step": 25300
|
|
},
|
|
{
|
|
"epoch": 7.87,
|
|
"learning_rate": 5.3825934596188174e-05,
|
|
"loss": 1.2162,
|
|
"step": 25310
|
|
},
|
|
{
|
|
"epoch": 7.88,
|
|
"learning_rate": 5.367454950435363e-05,
|
|
"loss": 1.212,
|
|
"step": 25320
|
|
},
|
|
{
|
|
"epoch": 7.88,
|
|
"learning_rate": 5.352335199167138e-05,
|
|
"loss": 1.3204,
|
|
"step": 25330
|
|
},
|
|
{
|
|
"epoch": 7.88,
|
|
"learning_rate": 5.337234220260301e-05,
|
|
"loss": 1.348,
|
|
"step": 25340
|
|
},
|
|
{
|
|
"epoch": 7.89,
|
|
"learning_rate": 5.3221520281430735e-05,
|
|
"loss": 1.2001,
|
|
"step": 25350
|
|
},
|
|
{
|
|
"epoch": 7.89,
|
|
"learning_rate": 5.307088637225746e-05,
|
|
"loss": 1.1838,
|
|
"step": 25360
|
|
},
|
|
{
|
|
"epoch": 7.89,
|
|
"learning_rate": 5.292044061900633e-05,
|
|
"loss": 1.3242,
|
|
"step": 25370
|
|
},
|
|
{
|
|
"epoch": 7.9,
|
|
"learning_rate": 5.2770183165420675e-05,
|
|
"loss": 1.2566,
|
|
"step": 25380
|
|
},
|
|
{
|
|
"epoch": 7.9,
|
|
"learning_rate": 5.262011415506402e-05,
|
|
"loss": 1.3165,
|
|
"step": 25390
|
|
},
|
|
{
|
|
"epoch": 7.9,
|
|
"learning_rate": 5.247023373131987e-05,
|
|
"loss": 1.2359,
|
|
"step": 25400
|
|
},
|
|
{
|
|
"epoch": 7.91,
|
|
"learning_rate": 5.232054203739142e-05,
|
|
"loss": 1.1318,
|
|
"step": 25410
|
|
},
|
|
{
|
|
"epoch": 7.91,
|
|
"learning_rate": 5.217103921630154e-05,
|
|
"loss": 1.2897,
|
|
"step": 25420
|
|
},
|
|
{
|
|
"epoch": 7.91,
|
|
"learning_rate": 5.202172541089284e-05,
|
|
"loss": 1.3406,
|
|
"step": 25430
|
|
},
|
|
{
|
|
"epoch": 7.91,
|
|
"learning_rate": 5.187260076382711e-05,
|
|
"loss": 1.3479,
|
|
"step": 25440
|
|
},
|
|
{
|
|
"epoch": 7.92,
|
|
"learning_rate": 5.172366541758541e-05,
|
|
"loss": 1.2073,
|
|
"step": 25450
|
|
},
|
|
{
|
|
"epoch": 7.92,
|
|
"learning_rate": 5.1574919514468105e-05,
|
|
"loss": 1.1773,
|
|
"step": 25460
|
|
},
|
|
{
|
|
"epoch": 7.92,
|
|
"learning_rate": 5.142636319659455e-05,
|
|
"loss": 1.31,
|
|
"step": 25470
|
|
},
|
|
{
|
|
"epoch": 7.93,
|
|
"learning_rate": 5.127799660590282e-05,
|
|
"loss": 1.2356,
|
|
"step": 25480
|
|
},
|
|
{
|
|
"epoch": 7.93,
|
|
"learning_rate": 5.1129819884149665e-05,
|
|
"loss": 1.3453,
|
|
"step": 25490
|
|
},
|
|
{
|
|
"epoch": 7.93,
|
|
"learning_rate": 5.0981833172910694e-05,
|
|
"loss": 1.1831,
|
|
"step": 25500
|
|
},
|
|
{
|
|
"epoch": 7.94,
|
|
"learning_rate": 5.083403661357966e-05,
|
|
"loss": 1.3291,
|
|
"step": 25510
|
|
},
|
|
{
|
|
"epoch": 7.94,
|
|
"learning_rate": 5.068643034736894e-05,
|
|
"loss": 1.1971,
|
|
"step": 25520
|
|
},
|
|
{
|
|
"epoch": 7.94,
|
|
"learning_rate": 5.053901451530879e-05,
|
|
"loss": 1.1947,
|
|
"step": 25530
|
|
},
|
|
{
|
|
"epoch": 7.95,
|
|
"learning_rate": 5.0391789258247834e-05,
|
|
"loss": 1.2912,
|
|
"step": 25540
|
|
},
|
|
{
|
|
"epoch": 7.95,
|
|
"learning_rate": 5.024475471685233e-05,
|
|
"loss": 1.2446,
|
|
"step": 25550
|
|
},
|
|
{
|
|
"epoch": 7.95,
|
|
"learning_rate": 5.009791103160641e-05,
|
|
"loss": 1.2377,
|
|
"step": 25560
|
|
},
|
|
{
|
|
"epoch": 7.96,
|
|
"learning_rate": 4.995125834281197e-05,
|
|
"loss": 1.1703,
|
|
"step": 25570
|
|
},
|
|
{
|
|
"epoch": 7.96,
|
|
"learning_rate": 4.980479679058822e-05,
|
|
"loss": 1.246,
|
|
"step": 25580
|
|
},
|
|
{
|
|
"epoch": 7.96,
|
|
"learning_rate": 4.965852651487196e-05,
|
|
"loss": 1.3223,
|
|
"step": 25590
|
|
},
|
|
{
|
|
"epoch": 7.96,
|
|
"learning_rate": 4.9512447655416984e-05,
|
|
"loss": 1.2885,
|
|
"step": 25600
|
|
},
|
|
{
|
|
"epoch": 7.97,
|
|
"learning_rate": 4.9366560351794514e-05,
|
|
"loss": 1.306,
|
|
"step": 25610
|
|
},
|
|
{
|
|
"epoch": 7.97,
|
|
"learning_rate": 4.9220864743392466e-05,
|
|
"loss": 1.3027,
|
|
"step": 25620
|
|
},
|
|
{
|
|
"epoch": 7.97,
|
|
"learning_rate": 4.907536096941565e-05,
|
|
"loss": 1.3333,
|
|
"step": 25630
|
|
},
|
|
{
|
|
"epoch": 7.98,
|
|
"learning_rate": 4.893004916888574e-05,
|
|
"loss": 1.2659,
|
|
"step": 25640
|
|
},
|
|
{
|
|
"epoch": 7.98,
|
|
"learning_rate": 4.8784929480640925e-05,
|
|
"loss": 1.278,
|
|
"step": 25650
|
|
},
|
|
{
|
|
"epoch": 7.98,
|
|
"learning_rate": 4.86400020433358e-05,
|
|
"loss": 1.2557,
|
|
"step": 25660
|
|
},
|
|
{
|
|
"epoch": 7.99,
|
|
"learning_rate": 4.849526699544116e-05,
|
|
"loss": 1.2945,
|
|
"step": 25670
|
|
},
|
|
{
|
|
"epoch": 7.99,
|
|
"learning_rate": 4.8350724475244244e-05,
|
|
"loss": 1.209,
|
|
"step": 25680
|
|
},
|
|
{
|
|
"epoch": 7.99,
|
|
"learning_rate": 4.8206374620848176e-05,
|
|
"loss": 1.3134,
|
|
"step": 25690
|
|
},
|
|
{
|
|
"epoch": 8.0,
|
|
"learning_rate": 4.8062217570171957e-05,
|
|
"loss": 1.2185,
|
|
"step": 25700
|
|
},
|
|
{
|
|
"epoch": 8.0,
|
|
"learning_rate": 4.791825346095047e-05,
|
|
"loss": 1.2873,
|
|
"step": 25710
|
|
},
|
|
{
|
|
"epoch": 8.0,
|
|
"learning_rate": 4.777448243073429e-05,
|
|
"loss": 1.2285,
|
|
"step": 25720
|
|
},
|
|
{
|
|
"epoch": 8.0,
|
|
"learning_rate": 4.763090461688943e-05,
|
|
"loss": 1.116,
|
|
"step": 25730
|
|
},
|
|
{
|
|
"epoch": 8.01,
|
|
"learning_rate": 4.748752015659721e-05,
|
|
"loss": 1.1283,
|
|
"step": 25740
|
|
},
|
|
{
|
|
"epoch": 8.01,
|
|
"learning_rate": 4.7344329186854465e-05,
|
|
"loss": 1.3022,
|
|
"step": 25750
|
|
},
|
|
{
|
|
"epoch": 8.01,
|
|
"learning_rate": 4.7201331844472925e-05,
|
|
"loss": 1.0838,
|
|
"step": 25760
|
|
},
|
|
{
|
|
"epoch": 8.02,
|
|
"learning_rate": 4.7058528266079314e-05,
|
|
"loss": 1.3028,
|
|
"step": 25770
|
|
},
|
|
{
|
|
"epoch": 8.02,
|
|
"learning_rate": 4.691591858811542e-05,
|
|
"loss": 1.2832,
|
|
"step": 25780
|
|
},
|
|
{
|
|
"epoch": 8.02,
|
|
"learning_rate": 4.6773502946837715e-05,
|
|
"loss": 1.2244,
|
|
"step": 25790
|
|
},
|
|
{
|
|
"epoch": 8.03,
|
|
"learning_rate": 4.6631281478317164e-05,
|
|
"loss": 1.2231,
|
|
"step": 25800
|
|
},
|
|
{
|
|
"epoch": 8.03,
|
|
"learning_rate": 4.648925431843917e-05,
|
|
"loss": 1.174,
|
|
"step": 25810
|
|
},
|
|
{
|
|
"epoch": 8.03,
|
|
"learning_rate": 4.634742160290373e-05,
|
|
"loss": 1.2347,
|
|
"step": 25820
|
|
},
|
|
{
|
|
"epoch": 8.04,
|
|
"learning_rate": 4.620578346722487e-05,
|
|
"loss": 1.2397,
|
|
"step": 25830
|
|
},
|
|
{
|
|
"epoch": 8.04,
|
|
"learning_rate": 4.60643400467306e-05,
|
|
"loss": 1.2421,
|
|
"step": 25840
|
|
},
|
|
{
|
|
"epoch": 8.04,
|
|
"learning_rate": 4.592309147656329e-05,
|
|
"loss": 1.1886,
|
|
"step": 25850
|
|
},
|
|
{
|
|
"epoch": 8.05,
|
|
"learning_rate": 4.578203789167876e-05,
|
|
"loss": 1.1591,
|
|
"step": 25860
|
|
},
|
|
{
|
|
"epoch": 8.05,
|
|
"learning_rate": 4.564117942684668e-05,
|
|
"loss": 1.196,
|
|
"step": 25870
|
|
},
|
|
{
|
|
"epoch": 8.05,
|
|
"learning_rate": 4.550051621665016e-05,
|
|
"loss": 1.3288,
|
|
"step": 25880
|
|
},
|
|
{
|
|
"epoch": 8.05,
|
|
"learning_rate": 4.536004839548602e-05,
|
|
"loss": 1.1246,
|
|
"step": 25890
|
|
},
|
|
{
|
|
"epoch": 8.06,
|
|
"learning_rate": 4.521977609756414e-05,
|
|
"loss": 1.2126,
|
|
"step": 25900
|
|
},
|
|
{
|
|
"epoch": 8.06,
|
|
"learning_rate": 4.507969945690771e-05,
|
|
"loss": 1.2405,
|
|
"step": 25910
|
|
},
|
|
{
|
|
"epoch": 8.06,
|
|
"learning_rate": 4.4939818607353024e-05,
|
|
"loss": 1.2421,
|
|
"step": 25920
|
|
},
|
|
{
|
|
"epoch": 8.07,
|
|
"learning_rate": 4.480013368254921e-05,
|
|
"loss": 1.2565,
|
|
"step": 25930
|
|
},
|
|
{
|
|
"epoch": 8.07,
|
|
"learning_rate": 4.466064481595813e-05,
|
|
"loss": 1.2512,
|
|
"step": 25940
|
|
},
|
|
{
|
|
"epoch": 8.07,
|
|
"learning_rate": 4.4521352140854565e-05,
|
|
"loss": 1.24,
|
|
"step": 25950
|
|
},
|
|
{
|
|
"epoch": 8.08,
|
|
"learning_rate": 4.438225579032562e-05,
|
|
"loss": 1.1318,
|
|
"step": 25960
|
|
},
|
|
{
|
|
"epoch": 8.08,
|
|
"learning_rate": 4.424335589727088e-05,
|
|
"loss": 1.207,
|
|
"step": 25970
|
|
},
|
|
{
|
|
"epoch": 8.08,
|
|
"learning_rate": 4.4104652594402274e-05,
|
|
"loss": 1.2392,
|
|
"step": 25980
|
|
},
|
|
{
|
|
"epoch": 8.09,
|
|
"learning_rate": 4.3966146014243955e-05,
|
|
"loss": 1.1614,
|
|
"step": 25990
|
|
},
|
|
{
|
|
"epoch": 8.09,
|
|
"learning_rate": 4.382783628913195e-05,
|
|
"loss": 1.215,
|
|
"step": 26000
|
|
},
|
|
{
|
|
"epoch": 8.09,
|
|
"learning_rate": 4.368972355121426e-05,
|
|
"loss": 1.2596,
|
|
"step": 26010
|
|
},
|
|
{
|
|
"epoch": 8.1,
|
|
"learning_rate": 4.355180793245081e-05,
|
|
"loss": 1.126,
|
|
"step": 26020
|
|
},
|
|
{
|
|
"epoch": 8.1,
|
|
"learning_rate": 4.341408956461293e-05,
|
|
"loss": 1.1813,
|
|
"step": 26030
|
|
},
|
|
{
|
|
"epoch": 8.1,
|
|
"learning_rate": 4.327656857928378e-05,
|
|
"loss": 1.2609,
|
|
"step": 26040
|
|
},
|
|
{
|
|
"epoch": 8.1,
|
|
"learning_rate": 4.3139245107857664e-05,
|
|
"loss": 1.205,
|
|
"step": 26050
|
|
},
|
|
{
|
|
"epoch": 8.11,
|
|
"learning_rate": 4.3002119281540434e-05,
|
|
"loss": 1.201,
|
|
"step": 26060
|
|
},
|
|
{
|
|
"epoch": 8.11,
|
|
"learning_rate": 4.2865191231348855e-05,
|
|
"loss": 1.1784,
|
|
"step": 26070
|
|
},
|
|
{
|
|
"epoch": 8.11,
|
|
"learning_rate": 4.2728461088110796e-05,
|
|
"loss": 1.1957,
|
|
"step": 26080
|
|
},
|
|
{
|
|
"epoch": 8.12,
|
|
"learning_rate": 4.259192898246519e-05,
|
|
"loss": 1.2488,
|
|
"step": 26090
|
|
},
|
|
{
|
|
"epoch": 8.12,
|
|
"learning_rate": 4.245559504486154e-05,
|
|
"loss": 1.1794,
|
|
"step": 26100
|
|
},
|
|
{
|
|
"epoch": 8.12,
|
|
"learning_rate": 4.23194594055602e-05,
|
|
"loss": 1.3415,
|
|
"step": 26110
|
|
},
|
|
{
|
|
"epoch": 8.13,
|
|
"learning_rate": 4.218352219463187e-05,
|
|
"loss": 1.1575,
|
|
"step": 26120
|
|
},
|
|
{
|
|
"epoch": 8.13,
|
|
"learning_rate": 4.2047783541957844e-05,
|
|
"loss": 1.1686,
|
|
"step": 26130
|
|
},
|
|
{
|
|
"epoch": 8.13,
|
|
"learning_rate": 4.191224357722959e-05,
|
|
"loss": 1.2913,
|
|
"step": 26140
|
|
},
|
|
{
|
|
"epoch": 8.14,
|
|
"learning_rate": 4.177690242994867e-05,
|
|
"loss": 1.1104,
|
|
"step": 26150
|
|
},
|
|
{
|
|
"epoch": 8.14,
|
|
"learning_rate": 4.164176022942689e-05,
|
|
"loss": 1.0203,
|
|
"step": 26160
|
|
},
|
|
{
|
|
"epoch": 8.14,
|
|
"learning_rate": 4.1506817104785904e-05,
|
|
"loss": 1.1409,
|
|
"step": 26170
|
|
},
|
|
{
|
|
"epoch": 8.14,
|
|
"learning_rate": 4.137207318495706e-05,
|
|
"loss": 1.3157,
|
|
"step": 26180
|
|
},
|
|
{
|
|
"epoch": 8.15,
|
|
"learning_rate": 4.123752859868138e-05,
|
|
"loss": 1.2495,
|
|
"step": 26190
|
|
},
|
|
{
|
|
"epoch": 8.15,
|
|
"learning_rate": 4.110318347450959e-05,
|
|
"loss": 1.1656,
|
|
"step": 26200
|
|
},
|
|
{
|
|
"epoch": 8.15,
|
|
"learning_rate": 4.096903794080173e-05,
|
|
"loss": 1.1549,
|
|
"step": 26210
|
|
},
|
|
{
|
|
"epoch": 8.16,
|
|
"learning_rate": 4.083509212572703e-05,
|
|
"loss": 1.258,
|
|
"step": 26220
|
|
},
|
|
{
|
|
"epoch": 8.16,
|
|
"learning_rate": 4.070134615726412e-05,
|
|
"loss": 1.2929,
|
|
"step": 26230
|
|
},
|
|
{
|
|
"epoch": 8.16,
|
|
"learning_rate": 4.056780016320061e-05,
|
|
"loss": 1.1343,
|
|
"step": 26240
|
|
},
|
|
{
|
|
"epoch": 8.17,
|
|
"learning_rate": 4.043445427113301e-05,
|
|
"loss": 1.1421,
|
|
"step": 26250
|
|
},
|
|
{
|
|
"epoch": 8.17,
|
|
"learning_rate": 4.030130860846653e-05,
|
|
"loss": 1.2031,
|
|
"step": 26260
|
|
},
|
|
{
|
|
"epoch": 8.17,
|
|
"learning_rate": 4.0168363302415386e-05,
|
|
"loss": 1.1315,
|
|
"step": 26270
|
|
},
|
|
{
|
|
"epoch": 8.18,
|
|
"learning_rate": 4.003561848000206e-05,
|
|
"loss": 1.1295,
|
|
"step": 26280
|
|
},
|
|
{
|
|
"epoch": 8.18,
|
|
"learning_rate": 3.990307426805756e-05,
|
|
"loss": 1.1715,
|
|
"step": 26290
|
|
},
|
|
{
|
|
"epoch": 8.18,
|
|
"learning_rate": 3.97707307932213e-05,
|
|
"loss": 1.213,
|
|
"step": 26300
|
|
},
|
|
{
|
|
"epoch": 8.19,
|
|
"learning_rate": 3.9638588181940886e-05,
|
|
"loss": 1.1529,
|
|
"step": 26310
|
|
},
|
|
{
|
|
"epoch": 8.19,
|
|
"learning_rate": 3.950664656047198e-05,
|
|
"loss": 1.2764,
|
|
"step": 26320
|
|
},
|
|
{
|
|
"epoch": 8.19,
|
|
"learning_rate": 3.937490605487809e-05,
|
|
"loss": 1.1942,
|
|
"step": 26330
|
|
},
|
|
{
|
|
"epoch": 8.19,
|
|
"learning_rate": 3.924336679103083e-05,
|
|
"loss": 1.2061,
|
|
"step": 26340
|
|
},
|
|
{
|
|
"epoch": 8.2,
|
|
"learning_rate": 3.9112028894609295e-05,
|
|
"loss": 1.1445,
|
|
"step": 26350
|
|
},
|
|
{
|
|
"epoch": 8.2,
|
|
"learning_rate": 3.898089249110029e-05,
|
|
"loss": 1.1187,
|
|
"step": 26360
|
|
},
|
|
{
|
|
"epoch": 8.2,
|
|
"learning_rate": 3.8849957705798075e-05,
|
|
"loss": 1.247,
|
|
"step": 26370
|
|
},
|
|
{
|
|
"epoch": 8.21,
|
|
"learning_rate": 3.87192246638044e-05,
|
|
"loss": 1.1888,
|
|
"step": 26380
|
|
},
|
|
{
|
|
"epoch": 8.21,
|
|
"learning_rate": 3.8588693490028055e-05,
|
|
"loss": 1.237,
|
|
"step": 26390
|
|
},
|
|
{
|
|
"epoch": 8.21,
|
|
"learning_rate": 3.845836430918501e-05,
|
|
"loss": 1.3085,
|
|
"step": 26400
|
|
},
|
|
{
|
|
"epoch": 8.22,
|
|
"learning_rate": 3.832823724579842e-05,
|
|
"loss": 1.3021,
|
|
"step": 26410
|
|
},
|
|
{
|
|
"epoch": 8.22,
|
|
"learning_rate": 3.8198312424198026e-05,
|
|
"loss": 1.1568,
|
|
"step": 26420
|
|
},
|
|
{
|
|
"epoch": 8.22,
|
|
"learning_rate": 3.806858996852067e-05,
|
|
"loss": 1.1489,
|
|
"step": 26430
|
|
},
|
|
{
|
|
"epoch": 8.23,
|
|
"learning_rate": 3.793907000270949e-05,
|
|
"loss": 1.1905,
|
|
"step": 26440
|
|
},
|
|
{
|
|
"epoch": 8.23,
|
|
"learning_rate": 3.780975265051451e-05,
|
|
"loss": 1.2468,
|
|
"step": 26450
|
|
},
|
|
{
|
|
"epoch": 8.23,
|
|
"learning_rate": 3.768063803549193e-05,
|
|
"loss": 1.2538,
|
|
"step": 26460
|
|
},
|
|
{
|
|
"epoch": 8.24,
|
|
"learning_rate": 3.75517262810042e-05,
|
|
"loss": 1.1685,
|
|
"step": 26470
|
|
},
|
|
{
|
|
"epoch": 8.24,
|
|
"learning_rate": 3.7423017510220234e-05,
|
|
"loss": 1.1518,
|
|
"step": 26480
|
|
},
|
|
{
|
|
"epoch": 8.24,
|
|
"learning_rate": 3.729451184611468e-05,
|
|
"loss": 1.1846,
|
|
"step": 26490
|
|
},
|
|
{
|
|
"epoch": 8.24,
|
|
"learning_rate": 3.716620941146834e-05,
|
|
"loss": 1.2859,
|
|
"step": 26500
|
|
},
|
|
{
|
|
"epoch": 8.25,
|
|
"learning_rate": 3.7038110328867834e-05,
|
|
"loss": 1.2388,
|
|
"step": 26510
|
|
},
|
|
{
|
|
"epoch": 8.25,
|
|
"learning_rate": 3.691021472070538e-05,
|
|
"loss": 1.2866,
|
|
"step": 26520
|
|
},
|
|
{
|
|
"epoch": 8.25,
|
|
"learning_rate": 3.678252270917884e-05,
|
|
"loss": 1.1959,
|
|
"step": 26530
|
|
},
|
|
{
|
|
"epoch": 8.26,
|
|
"learning_rate": 3.665503441629145e-05,
|
|
"loss": 1.2935,
|
|
"step": 26540
|
|
},
|
|
{
|
|
"epoch": 8.26,
|
|
"learning_rate": 3.6527749963852e-05,
|
|
"loss": 1.1165,
|
|
"step": 26550
|
|
},
|
|
{
|
|
"epoch": 8.26,
|
|
"learning_rate": 3.640066947347445e-05,
|
|
"loss": 1.2607,
|
|
"step": 26560
|
|
},
|
|
{
|
|
"epoch": 8.27,
|
|
"learning_rate": 3.627379306657777e-05,
|
|
"loss": 1.21,
|
|
"step": 26570
|
|
},
|
|
{
|
|
"epoch": 8.27,
|
|
"learning_rate": 3.6147120864386124e-05,
|
|
"loss": 1.2111,
|
|
"step": 26580
|
|
},
|
|
{
|
|
"epoch": 8.27,
|
|
"learning_rate": 3.6020652987928395e-05,
|
|
"loss": 1.1978,
|
|
"step": 26590
|
|
},
|
|
{
|
|
"epoch": 8.28,
|
|
"learning_rate": 3.589438955803828e-05,
|
|
"loss": 1.2486,
|
|
"step": 26600
|
|
},
|
|
{
|
|
"epoch": 8.28,
|
|
"learning_rate": 3.576833069535423e-05,
|
|
"loss": 1.1636,
|
|
"step": 26610
|
|
},
|
|
{
|
|
"epoch": 8.28,
|
|
"learning_rate": 3.564247652031921e-05,
|
|
"loss": 1.1559,
|
|
"step": 26620
|
|
},
|
|
{
|
|
"epoch": 8.28,
|
|
"learning_rate": 3.551682715318058e-05,
|
|
"loss": 1.2619,
|
|
"step": 26630
|
|
},
|
|
{
|
|
"epoch": 8.29,
|
|
"learning_rate": 3.539138271398995e-05,
|
|
"loss": 1.2425,
|
|
"step": 26640
|
|
},
|
|
{
|
|
"epoch": 8.29,
|
|
"learning_rate": 3.5266143322603335e-05,
|
|
"loss": 1.1854,
|
|
"step": 26650
|
|
},
|
|
{
|
|
"epoch": 8.29,
|
|
"learning_rate": 3.5141109098680625e-05,
|
|
"loss": 1.2256,
|
|
"step": 26660
|
|
},
|
|
{
|
|
"epoch": 8.3,
|
|
"learning_rate": 3.501628016168573e-05,
|
|
"loss": 1.1522,
|
|
"step": 26670
|
|
},
|
|
{
|
|
"epoch": 8.3,
|
|
"learning_rate": 3.4891656630886534e-05,
|
|
"loss": 1.1965,
|
|
"step": 26680
|
|
},
|
|
{
|
|
"epoch": 8.3,
|
|
"learning_rate": 3.476723862535464e-05,
|
|
"loss": 1.1913,
|
|
"step": 26690
|
|
},
|
|
{
|
|
"epoch": 8.31,
|
|
"learning_rate": 3.464302626396515e-05,
|
|
"loss": 1.2672,
|
|
"step": 26700
|
|
},
|
|
{
|
|
"epoch": 8.31,
|
|
"learning_rate": 3.4519019665396725e-05,
|
|
"loss": 1.2782,
|
|
"step": 26710
|
|
},
|
|
{
|
|
"epoch": 8.31,
|
|
"learning_rate": 3.4395218948131576e-05,
|
|
"loss": 1.2014,
|
|
"step": 26720
|
|
},
|
|
{
|
|
"epoch": 8.32,
|
|
"learning_rate": 3.4271624230455044e-05,
|
|
"loss": 1.1787,
|
|
"step": 26730
|
|
},
|
|
{
|
|
"epoch": 8.32,
|
|
"learning_rate": 3.414823563045566e-05,
|
|
"loss": 1.2184,
|
|
"step": 26740
|
|
},
|
|
{
|
|
"epoch": 8.32,
|
|
"learning_rate": 3.4025053266025116e-05,
|
|
"loss": 1.182,
|
|
"step": 26750
|
|
},
|
|
{
|
|
"epoch": 8.33,
|
|
"learning_rate": 3.390207725485806e-05,
|
|
"loss": 1.1807,
|
|
"step": 26760
|
|
},
|
|
{
|
|
"epoch": 8.33,
|
|
"learning_rate": 3.377930771445181e-05,
|
|
"loss": 1.1509,
|
|
"step": 26770
|
|
},
|
|
{
|
|
"epoch": 8.33,
|
|
"learning_rate": 3.3656744762106564e-05,
|
|
"loss": 1.1641,
|
|
"step": 26780
|
|
},
|
|
{
|
|
"epoch": 8.33,
|
|
"learning_rate": 3.353438851492513e-05,
|
|
"loss": 1.1854,
|
|
"step": 26790
|
|
},
|
|
{
|
|
"epoch": 8.34,
|
|
"learning_rate": 3.341223908981275e-05,
|
|
"loss": 1.224,
|
|
"step": 26800
|
|
},
|
|
{
|
|
"epoch": 8.34,
|
|
"learning_rate": 3.329029660347707e-05,
|
|
"loss": 1.1962,
|
|
"step": 26810
|
|
},
|
|
{
|
|
"epoch": 8.34,
|
|
"learning_rate": 3.316856117242806e-05,
|
|
"loss": 1.2083,
|
|
"step": 26820
|
|
},
|
|
{
|
|
"epoch": 8.35,
|
|
"learning_rate": 3.304703291297789e-05,
|
|
"loss": 1.2076,
|
|
"step": 26830
|
|
},
|
|
{
|
|
"epoch": 8.35,
|
|
"learning_rate": 3.2925711941240696e-05,
|
|
"loss": 1.2968,
|
|
"step": 26840
|
|
},
|
|
{
|
|
"epoch": 8.35,
|
|
"learning_rate": 3.2804598373132544e-05,
|
|
"loss": 1.1696,
|
|
"step": 26850
|
|
},
|
|
{
|
|
"epoch": 8.36,
|
|
"learning_rate": 3.2683692324371516e-05,
|
|
"loss": 1.2664,
|
|
"step": 26860
|
|
},
|
|
{
|
|
"epoch": 8.36,
|
|
"learning_rate": 3.256299391047715e-05,
|
|
"loss": 1.1414,
|
|
"step": 26870
|
|
},
|
|
{
|
|
"epoch": 8.36,
|
|
"learning_rate": 3.244250324677087e-05,
|
|
"loss": 1.2234,
|
|
"step": 26880
|
|
},
|
|
{
|
|
"epoch": 8.37,
|
|
"learning_rate": 3.232222044837541e-05,
|
|
"loss": 1.149,
|
|
"step": 26890
|
|
},
|
|
{
|
|
"epoch": 8.37,
|
|
"learning_rate": 3.220214563021501e-05,
|
|
"loss": 1.1674,
|
|
"step": 26900
|
|
},
|
|
{
|
|
"epoch": 8.37,
|
|
"learning_rate": 3.2082278907015175e-05,
|
|
"loss": 1.2362,
|
|
"step": 26910
|
|
},
|
|
{
|
|
"epoch": 8.38,
|
|
"learning_rate": 3.196262039330244e-05,
|
|
"loss": 1.1688,
|
|
"step": 26920
|
|
},
|
|
{
|
|
"epoch": 8.38,
|
|
"learning_rate": 3.184317020340469e-05,
|
|
"loss": 1.2818,
|
|
"step": 26930
|
|
},
|
|
{
|
|
"epoch": 8.38,
|
|
"learning_rate": 3.17239284514505e-05,
|
|
"loss": 1.2577,
|
|
"step": 26940
|
|
},
|
|
{
|
|
"epoch": 8.38,
|
|
"learning_rate": 3.1604895251369474e-05,
|
|
"loss": 1.1721,
|
|
"step": 26950
|
|
},
|
|
{
|
|
"epoch": 8.39,
|
|
"learning_rate": 3.1486070716891805e-05,
|
|
"loss": 1.2463,
|
|
"step": 26960
|
|
},
|
|
{
|
|
"epoch": 8.39,
|
|
"learning_rate": 3.1367454961548497e-05,
|
|
"loss": 1.282,
|
|
"step": 26970
|
|
},
|
|
{
|
|
"epoch": 8.39,
|
|
"learning_rate": 3.124904809867093e-05,
|
|
"loss": 1.1815,
|
|
"step": 26980
|
|
},
|
|
{
|
|
"epoch": 8.4,
|
|
"learning_rate": 3.1130850241390865e-05,
|
|
"loss": 1.2144,
|
|
"step": 26990
|
|
},
|
|
{
|
|
"epoch": 8.4,
|
|
"learning_rate": 3.1012861502640514e-05,
|
|
"loss": 1.2984,
|
|
"step": 27000
|
|
},
|
|
{
|
|
"epoch": 8.4,
|
|
"learning_rate": 3.089508199515229e-05,
|
|
"loss": 1.2722,
|
|
"step": 27010
|
|
},
|
|
{
|
|
"epoch": 8.41,
|
|
"learning_rate": 3.0777511831458523e-05,
|
|
"loss": 1.2372,
|
|
"step": 27020
|
|
},
|
|
{
|
|
"epoch": 8.41,
|
|
"learning_rate": 3.066015112389159e-05,
|
|
"loss": 1.1798,
|
|
"step": 27030
|
|
},
|
|
{
|
|
"epoch": 8.41,
|
|
"learning_rate": 3.05429999845839e-05,
|
|
"loss": 1.2324,
|
|
"step": 27040
|
|
},
|
|
{
|
|
"epoch": 8.42,
|
|
"learning_rate": 3.0426058525467455e-05,
|
|
"loss": 1.2168,
|
|
"step": 27050
|
|
},
|
|
{
|
|
"epoch": 8.42,
|
|
"learning_rate": 3.0309326858273924e-05,
|
|
"loss": 1.252,
|
|
"step": 27060
|
|
},
|
|
{
|
|
"epoch": 8.42,
|
|
"learning_rate": 3.0192805094534593e-05,
|
|
"loss": 1.3209,
|
|
"step": 27070
|
|
},
|
|
{
|
|
"epoch": 8.42,
|
|
"learning_rate": 3.0076493345580298e-05,
|
|
"loss": 1.2872,
|
|
"step": 27080
|
|
},
|
|
{
|
|
"epoch": 8.43,
|
|
"learning_rate": 2.996039172254092e-05,
|
|
"loss": 1.243,
|
|
"step": 27090
|
|
},
|
|
{
|
|
"epoch": 8.43,
|
|
"learning_rate": 2.984450033634592e-05,
|
|
"loss": 1.2822,
|
|
"step": 27100
|
|
},
|
|
{
|
|
"epoch": 8.43,
|
|
"learning_rate": 2.972881929772367e-05,
|
|
"loss": 1.1832,
|
|
"step": 27110
|
|
},
|
|
{
|
|
"epoch": 8.44,
|
|
"learning_rate": 2.9613348717201588e-05,
|
|
"loss": 1.1871,
|
|
"step": 27120
|
|
},
|
|
{
|
|
"epoch": 8.44,
|
|
"learning_rate": 2.9498088705105925e-05,
|
|
"loss": 1.166,
|
|
"step": 27130
|
|
},
|
|
{
|
|
"epoch": 8.44,
|
|
"learning_rate": 2.9383039371562115e-05,
|
|
"loss": 1.176,
|
|
"step": 27140
|
|
},
|
|
{
|
|
"epoch": 8.45,
|
|
"learning_rate": 2.9268200826493895e-05,
|
|
"loss": 1.3324,
|
|
"step": 27150
|
|
},
|
|
{
|
|
"epoch": 8.45,
|
|
"learning_rate": 2.915357317962375e-05,
|
|
"loss": 1.1437,
|
|
"step": 27160
|
|
},
|
|
{
|
|
"epoch": 8.45,
|
|
"learning_rate": 2.9039156540472704e-05,
|
|
"loss": 1.2128,
|
|
"step": 27170
|
|
},
|
|
{
|
|
"epoch": 8.46,
|
|
"learning_rate": 2.892495101836015e-05,
|
|
"loss": 1.1376,
|
|
"step": 27180
|
|
},
|
|
{
|
|
"epoch": 8.46,
|
|
"learning_rate": 2.8810956722403662e-05,
|
|
"loss": 1.2518,
|
|
"step": 27190
|
|
},
|
|
{
|
|
"epoch": 8.46,
|
|
"learning_rate": 2.8697173761519147e-05,
|
|
"loss": 1.1436,
|
|
"step": 27200
|
|
},
|
|
{
|
|
"epoch": 8.47,
|
|
"learning_rate": 2.858360224442061e-05,
|
|
"loss": 1.2999,
|
|
"step": 27210
|
|
},
|
|
{
|
|
"epoch": 8.47,
|
|
"learning_rate": 2.8470242279619862e-05,
|
|
"loss": 1.1885,
|
|
"step": 27220
|
|
},
|
|
{
|
|
"epoch": 8.47,
|
|
"learning_rate": 2.8357093975426683e-05,
|
|
"loss": 1.2592,
|
|
"step": 27230
|
|
},
|
|
{
|
|
"epoch": 8.47,
|
|
"learning_rate": 2.824415743994868e-05,
|
|
"loss": 1.3216,
|
|
"step": 27240
|
|
},
|
|
{
|
|
"epoch": 8.48,
|
|
"learning_rate": 2.8131432781091036e-05,
|
|
"loss": 1.2031,
|
|
"step": 27250
|
|
},
|
|
{
|
|
"epoch": 8.48,
|
|
"learning_rate": 2.801892010655649e-05,
|
|
"loss": 1.1938,
|
|
"step": 27260
|
|
},
|
|
{
|
|
"epoch": 8.48,
|
|
"learning_rate": 2.7906619523845294e-05,
|
|
"loss": 1.2011,
|
|
"step": 27270
|
|
},
|
|
{
|
|
"epoch": 8.49,
|
|
"learning_rate": 2.7794531140255098e-05,
|
|
"loss": 1.2266,
|
|
"step": 27280
|
|
},
|
|
{
|
|
"epoch": 8.49,
|
|
"learning_rate": 2.768265506288073e-05,
|
|
"loss": 1.2142,
|
|
"step": 27290
|
|
},
|
|
{
|
|
"epoch": 8.49,
|
|
"learning_rate": 2.7570991398614104e-05,
|
|
"loss": 1.1351,
|
|
"step": 27300
|
|
},
|
|
{
|
|
"epoch": 8.5,
|
|
"learning_rate": 2.745954025414438e-05,
|
|
"loss": 1.346,
|
|
"step": 27310
|
|
},
|
|
{
|
|
"epoch": 8.5,
|
|
"learning_rate": 2.734830173595748e-05,
|
|
"loss": 1.3261,
|
|
"step": 27320
|
|
},
|
|
{
|
|
"epoch": 8.5,
|
|
"learning_rate": 2.723727595033623e-05,
|
|
"loss": 1.1063,
|
|
"step": 27330
|
|
},
|
|
{
|
|
"epoch": 8.51,
|
|
"learning_rate": 2.7126463003360275e-05,
|
|
"loss": 1.2262,
|
|
"step": 27340
|
|
},
|
|
{
|
|
"epoch": 8.51,
|
|
"learning_rate": 2.701586300090586e-05,
|
|
"loss": 1.1925,
|
|
"step": 27350
|
|
},
|
|
{
|
|
"epoch": 8.51,
|
|
"learning_rate": 2.690547604864574e-05,
|
|
"loss": 1.2229,
|
|
"step": 27360
|
|
},
|
|
{
|
|
"epoch": 8.52,
|
|
"learning_rate": 2.679530225204907e-05,
|
|
"loss": 1.1618,
|
|
"step": 27370
|
|
},
|
|
{
|
|
"epoch": 8.52,
|
|
"learning_rate": 2.6685341716381485e-05,
|
|
"loss": 1.1575,
|
|
"step": 27380
|
|
},
|
|
{
|
|
"epoch": 8.52,
|
|
"learning_rate": 2.657559454670469e-05,
|
|
"loss": 1.3249,
|
|
"step": 27390
|
|
},
|
|
{
|
|
"epoch": 8.52,
|
|
"learning_rate": 2.646606084787673e-05,
|
|
"loss": 1.184,
|
|
"step": 27400
|
|
},
|
|
{
|
|
"epoch": 8.53,
|
|
"learning_rate": 2.6356740724551438e-05,
|
|
"loss": 1.2455,
|
|
"step": 27410
|
|
},
|
|
{
|
|
"epoch": 8.53,
|
|
"learning_rate": 2.6247634281178877e-05,
|
|
"loss": 1.2272,
|
|
"step": 27420
|
|
},
|
|
{
|
|
"epoch": 8.53,
|
|
"learning_rate": 2.6138741622004746e-05,
|
|
"loss": 1.2836,
|
|
"step": 27430
|
|
},
|
|
{
|
|
"epoch": 8.54,
|
|
"learning_rate": 2.6030062851070458e-05,
|
|
"loss": 1.2391,
|
|
"step": 27440
|
|
},
|
|
{
|
|
"epoch": 8.54,
|
|
"learning_rate": 2.5921598072213225e-05,
|
|
"loss": 1.2046,
|
|
"step": 27450
|
|
},
|
|
{
|
|
"epoch": 8.54,
|
|
"learning_rate": 2.5813347389065683e-05,
|
|
"loss": 1.2446,
|
|
"step": 27460
|
|
},
|
|
{
|
|
"epoch": 8.55,
|
|
"learning_rate": 2.5705310905056012e-05,
|
|
"loss": 1.2123,
|
|
"step": 27470
|
|
},
|
|
{
|
|
"epoch": 8.55,
|
|
"learning_rate": 2.5597488723407585e-05,
|
|
"loss": 1.1718,
|
|
"step": 27480
|
|
},
|
|
{
|
|
"epoch": 8.55,
|
|
"learning_rate": 2.5489880947139167e-05,
|
|
"loss": 1.3088,
|
|
"step": 27490
|
|
},
|
|
{
|
|
"epoch": 8.56,
|
|
"learning_rate": 2.538248767906462e-05,
|
|
"loss": 1.2234,
|
|
"step": 27500
|
|
},
|
|
{
|
|
"epoch": 8.56,
|
|
"learning_rate": 2.527530902179273e-05,
|
|
"loss": 1.2693,
|
|
"step": 27510
|
|
},
|
|
{
|
|
"epoch": 8.56,
|
|
"learning_rate": 2.5168345077727444e-05,
|
|
"loss": 1.2541,
|
|
"step": 27520
|
|
},
|
|
{
|
|
"epoch": 8.56,
|
|
"learning_rate": 2.5061595949067485e-05,
|
|
"loss": 1.2832,
|
|
"step": 27530
|
|
},
|
|
{
|
|
"epoch": 8.57,
|
|
"learning_rate": 2.495506173780626e-05,
|
|
"loss": 1.2014,
|
|
"step": 27540
|
|
},
|
|
{
|
|
"epoch": 8.57,
|
|
"learning_rate": 2.4848742545731828e-05,
|
|
"loss": 1.181,
|
|
"step": 27550
|
|
},
|
|
{
|
|
"epoch": 8.57,
|
|
"learning_rate": 2.4742638474426982e-05,
|
|
"loss": 1.2328,
|
|
"step": 27560
|
|
},
|
|
{
|
|
"epoch": 8.58,
|
|
"learning_rate": 2.4636749625268796e-05,
|
|
"loss": 1.1679,
|
|
"step": 27570
|
|
},
|
|
{
|
|
"epoch": 8.58,
|
|
"learning_rate": 2.453107609942873e-05,
|
|
"loss": 1.3425,
|
|
"step": 27580
|
|
},
|
|
{
|
|
"epoch": 8.58,
|
|
"learning_rate": 2.4425617997872573e-05,
|
|
"loss": 1.1599,
|
|
"step": 27590
|
|
},
|
|
{
|
|
"epoch": 8.59,
|
|
"learning_rate": 2.4320375421360368e-05,
|
|
"loss": 1.3119,
|
|
"step": 27600
|
|
},
|
|
{
|
|
"epoch": 8.59,
|
|
"learning_rate": 2.4215348470446042e-05,
|
|
"loss": 1.1603,
|
|
"step": 27610
|
|
},
|
|
{
|
|
"epoch": 8.59,
|
|
"learning_rate": 2.4110537245477572e-05,
|
|
"loss": 1.2863,
|
|
"step": 27620
|
|
},
|
|
{
|
|
"epoch": 8.6,
|
|
"learning_rate": 2.4005941846596907e-05,
|
|
"loss": 1.097,
|
|
"step": 27630
|
|
},
|
|
{
|
|
"epoch": 8.6,
|
|
"learning_rate": 2.3901562373739723e-05,
|
|
"loss": 1.1708,
|
|
"step": 27640
|
|
},
|
|
{
|
|
"epoch": 8.6,
|
|
"learning_rate": 2.3797398926635265e-05,
|
|
"loss": 1.0649,
|
|
"step": 27650
|
|
},
|
|
{
|
|
"epoch": 8.61,
|
|
"learning_rate": 2.3693451604806683e-05,
|
|
"loss": 1.2376,
|
|
"step": 27660
|
|
},
|
|
{
|
|
"epoch": 8.61,
|
|
"learning_rate": 2.3589720507570355e-05,
|
|
"loss": 1.0865,
|
|
"step": 27670
|
|
},
|
|
{
|
|
"epoch": 8.61,
|
|
"learning_rate": 2.348620573403615e-05,
|
|
"loss": 1.2635,
|
|
"step": 27680
|
|
},
|
|
{
|
|
"epoch": 8.61,
|
|
"learning_rate": 2.338290738310725e-05,
|
|
"loss": 1.3335,
|
|
"step": 27690
|
|
},
|
|
{
|
|
"epoch": 8.62,
|
|
"learning_rate": 2.32798255534801e-05,
|
|
"loss": 1.2465,
|
|
"step": 27700
|
|
},
|
|
{
|
|
"epoch": 8.62,
|
|
"learning_rate": 2.3176960343644247e-05,
|
|
"loss": 1.2607,
|
|
"step": 27710
|
|
},
|
|
{
|
|
"epoch": 8.62,
|
|
"learning_rate": 2.3074311851882106e-05,
|
|
"loss": 1.1826,
|
|
"step": 27720
|
|
},
|
|
{
|
|
"epoch": 8.63,
|
|
"learning_rate": 2.2971880176269418e-05,
|
|
"loss": 1.1832,
|
|
"step": 27730
|
|
},
|
|
{
|
|
"epoch": 8.63,
|
|
"learning_rate": 2.286966541467442e-05,
|
|
"loss": 1.185,
|
|
"step": 27740
|
|
},
|
|
{
|
|
"epoch": 8.63,
|
|
"learning_rate": 2.276766766475813e-05,
|
|
"loss": 1.2962,
|
|
"step": 27750
|
|
},
|
|
{
|
|
"epoch": 8.64,
|
|
"learning_rate": 2.26658870239744e-05,
|
|
"loss": 1.2776,
|
|
"step": 27760
|
|
},
|
|
{
|
|
"epoch": 8.64,
|
|
"learning_rate": 2.256432358956953e-05,
|
|
"loss": 1.1891,
|
|
"step": 27770
|
|
},
|
|
{
|
|
"epoch": 8.64,
|
|
"learning_rate": 2.2462977458582223e-05,
|
|
"loss": 1.2742,
|
|
"step": 27780
|
|
},
|
|
{
|
|
"epoch": 8.65,
|
|
"learning_rate": 2.236184872784372e-05,
|
|
"loss": 1.1812,
|
|
"step": 27790
|
|
},
|
|
{
|
|
"epoch": 8.65,
|
|
"learning_rate": 2.226093749397748e-05,
|
|
"loss": 1.261,
|
|
"step": 27800
|
|
},
|
|
{
|
|
"epoch": 8.65,
|
|
"learning_rate": 2.2160243853399097e-05,
|
|
"loss": 1.2753,
|
|
"step": 27810
|
|
},
|
|
{
|
|
"epoch": 8.66,
|
|
"learning_rate": 2.2059767902316285e-05,
|
|
"loss": 1.2784,
|
|
"step": 27820
|
|
},
|
|
{
|
|
"epoch": 8.66,
|
|
"learning_rate": 2.1959509736728888e-05,
|
|
"loss": 1.1125,
|
|
"step": 27830
|
|
},
|
|
{
|
|
"epoch": 8.66,
|
|
"learning_rate": 2.1859469452428505e-05,
|
|
"loss": 1.2023,
|
|
"step": 27840
|
|
},
|
|
{
|
|
"epoch": 8.66,
|
|
"learning_rate": 2.1759647144998562e-05,
|
|
"loss": 1.2293,
|
|
"step": 27850
|
|
},
|
|
{
|
|
"epoch": 8.67,
|
|
"learning_rate": 2.1660042909814383e-05,
|
|
"loss": 1.2806,
|
|
"step": 27860
|
|
},
|
|
{
|
|
"epoch": 8.67,
|
|
"learning_rate": 2.156065684204281e-05,
|
|
"loss": 1.2268,
|
|
"step": 27870
|
|
},
|
|
{
|
|
"epoch": 8.67,
|
|
"learning_rate": 2.14614890366423e-05,
|
|
"loss": 1.1363,
|
|
"step": 27880
|
|
},
|
|
{
|
|
"epoch": 8.68,
|
|
"learning_rate": 2.136253958836262e-05,
|
|
"loss": 1.186,
|
|
"step": 27890
|
|
},
|
|
{
|
|
"epoch": 8.68,
|
|
"learning_rate": 2.126380859174512e-05,
|
|
"loss": 1.313,
|
|
"step": 27900
|
|
},
|
|
{
|
|
"epoch": 8.68,
|
|
"learning_rate": 2.116529614112228e-05,
|
|
"loss": 1.3145,
|
|
"step": 27910
|
|
},
|
|
{
|
|
"epoch": 8.69,
|
|
"learning_rate": 2.1067002330617897e-05,
|
|
"loss": 1.2223,
|
|
"step": 27920
|
|
},
|
|
{
|
|
"epoch": 8.69,
|
|
"learning_rate": 2.0968927254146675e-05,
|
|
"loss": 1.2564,
|
|
"step": 27930
|
|
},
|
|
{
|
|
"epoch": 8.69,
|
|
"learning_rate": 2.0871071005414548e-05,
|
|
"loss": 1.2953,
|
|
"step": 27940
|
|
},
|
|
{
|
|
"epoch": 8.7,
|
|
"learning_rate": 2.077343367791823e-05,
|
|
"loss": 1.2393,
|
|
"step": 27950
|
|
},
|
|
{
|
|
"epoch": 8.7,
|
|
"learning_rate": 2.067601536494526e-05,
|
|
"loss": 1.1905,
|
|
"step": 27960
|
|
},
|
|
{
|
|
"epoch": 8.7,
|
|
"learning_rate": 2.057881615957405e-05,
|
|
"loss": 1.2983,
|
|
"step": 27970
|
|
},
|
|
{
|
|
"epoch": 8.7,
|
|
"learning_rate": 2.0481836154673528e-05,
|
|
"loss": 1.2909,
|
|
"step": 27980
|
|
},
|
|
{
|
|
"epoch": 8.71,
|
|
"learning_rate": 2.0385075442903273e-05,
|
|
"loss": 1.2733,
|
|
"step": 27990
|
|
},
|
|
{
|
|
"epoch": 8.71,
|
|
"learning_rate": 2.0288534116713246e-05,
|
|
"loss": 1.1729,
|
|
"step": 28000
|
|
},
|
|
{
|
|
"epoch": 8.71,
|
|
"learning_rate": 2.0192212268343947e-05,
|
|
"loss": 1.2695,
|
|
"step": 28010
|
|
},
|
|
{
|
|
"epoch": 8.72,
|
|
"learning_rate": 2.009610998982603e-05,
|
|
"loss": 1.2311,
|
|
"step": 28020
|
|
},
|
|
{
|
|
"epoch": 8.72,
|
|
"learning_rate": 2.000022737298038e-05,
|
|
"loss": 1.2133,
|
|
"step": 28030
|
|
},
|
|
{
|
|
"epoch": 8.72,
|
|
"learning_rate": 1.9904564509418104e-05,
|
|
"loss": 1.2152,
|
|
"step": 28040
|
|
},
|
|
{
|
|
"epoch": 8.73,
|
|
"learning_rate": 1.9809121490540287e-05,
|
|
"loss": 1.2368,
|
|
"step": 28050
|
|
},
|
|
{
|
|
"epoch": 8.73,
|
|
"learning_rate": 1.9713898407537955e-05,
|
|
"loss": 1.2499,
|
|
"step": 28060
|
|
},
|
|
{
|
|
"epoch": 8.73,
|
|
"learning_rate": 1.961889535139197e-05,
|
|
"loss": 1.282,
|
|
"step": 28070
|
|
},
|
|
{
|
|
"epoch": 8.74,
|
|
"learning_rate": 1.9524112412873052e-05,
|
|
"loss": 1.1403,
|
|
"step": 28080
|
|
},
|
|
{
|
|
"epoch": 8.74,
|
|
"learning_rate": 1.9429549682541543e-05,
|
|
"loss": 1.1798,
|
|
"step": 28090
|
|
},
|
|
{
|
|
"epoch": 8.74,
|
|
"learning_rate": 1.9335207250747333e-05,
|
|
"loss": 1.2236,
|
|
"step": 28100
|
|
},
|
|
{
|
|
"epoch": 8.75,
|
|
"learning_rate": 1.9241085207629988e-05,
|
|
"loss": 1.2022,
|
|
"step": 28110
|
|
},
|
|
{
|
|
"epoch": 8.75,
|
|
"learning_rate": 1.9147183643118404e-05,
|
|
"loss": 1.1093,
|
|
"step": 28120
|
|
},
|
|
{
|
|
"epoch": 8.75,
|
|
"learning_rate": 1.9053502646930814e-05,
|
|
"loss": 1.0921,
|
|
"step": 28130
|
|
},
|
|
{
|
|
"epoch": 8.75,
|
|
"learning_rate": 1.8960042308574705e-05,
|
|
"loss": 1.2306,
|
|
"step": 28140
|
|
},
|
|
{
|
|
"epoch": 8.76,
|
|
"learning_rate": 1.8866802717346808e-05,
|
|
"loss": 1.1779,
|
|
"step": 28150
|
|
},
|
|
{
|
|
"epoch": 8.76,
|
|
"learning_rate": 1.877378396233284e-05,
|
|
"loss": 1.1962,
|
|
"step": 28160
|
|
},
|
|
{
|
|
"epoch": 8.76,
|
|
"learning_rate": 1.8680986132407568e-05,
|
|
"loss": 1.2263,
|
|
"step": 28170
|
|
},
|
|
{
|
|
"epoch": 8.77,
|
|
"learning_rate": 1.8588409316234707e-05,
|
|
"loss": 1.1683,
|
|
"step": 28180
|
|
},
|
|
{
|
|
"epoch": 8.77,
|
|
"learning_rate": 1.8496053602266804e-05,
|
|
"loss": 1.2723,
|
|
"step": 28190
|
|
},
|
|
{
|
|
"epoch": 8.77,
|
|
"learning_rate": 1.8403919078745086e-05,
|
|
"loss": 1.267,
|
|
"step": 28200
|
|
},
|
|
{
|
|
"epoch": 8.78,
|
|
"learning_rate": 1.8312005833699463e-05,
|
|
"loss": 1.177,
|
|
"step": 28210
|
|
},
|
|
{
|
|
"epoch": 8.78,
|
|
"learning_rate": 1.8220313954948497e-05,
|
|
"loss": 1.2544,
|
|
"step": 28220
|
|
},
|
|
{
|
|
"epoch": 8.78,
|
|
"learning_rate": 1.8128843530099164e-05,
|
|
"loss": 1.2226,
|
|
"step": 28230
|
|
},
|
|
{
|
|
"epoch": 8.79,
|
|
"learning_rate": 1.803759464654686e-05,
|
|
"loss": 1.0769,
|
|
"step": 28240
|
|
},
|
|
{
|
|
"epoch": 8.79,
|
|
"learning_rate": 1.7946567391475404e-05,
|
|
"loss": 1.2617,
|
|
"step": 28250
|
|
},
|
|
{
|
|
"epoch": 8.79,
|
|
"learning_rate": 1.785576185185675e-05,
|
|
"loss": 1.3089,
|
|
"step": 28260
|
|
},
|
|
{
|
|
"epoch": 8.8,
|
|
"learning_rate": 1.7765178114451024e-05,
|
|
"loss": 1.2182,
|
|
"step": 28270
|
|
},
|
|
{
|
|
"epoch": 8.8,
|
|
"learning_rate": 1.7674816265806443e-05,
|
|
"loss": 1.1728,
|
|
"step": 28280
|
|
},
|
|
{
|
|
"epoch": 8.8,
|
|
"learning_rate": 1.758467639225933e-05,
|
|
"loss": 1.2269,
|
|
"step": 28290
|
|
},
|
|
{
|
|
"epoch": 8.8,
|
|
"learning_rate": 1.749475857993371e-05,
|
|
"loss": 1.2223,
|
|
"step": 28300
|
|
},
|
|
{
|
|
"epoch": 8.81,
|
|
"learning_rate": 1.7405062914741617e-05,
|
|
"loss": 1.2342,
|
|
"step": 28310
|
|
},
|
|
{
|
|
"epoch": 8.81,
|
|
"learning_rate": 1.7315589482382794e-05,
|
|
"loss": 1.2853,
|
|
"step": 28320
|
|
},
|
|
{
|
|
"epoch": 8.81,
|
|
"learning_rate": 1.722633836834464e-05,
|
|
"loss": 1.0895,
|
|
"step": 28330
|
|
},
|
|
{
|
|
"epoch": 8.82,
|
|
"learning_rate": 1.7137309657902027e-05,
|
|
"loss": 1.1409,
|
|
"step": 28340
|
|
},
|
|
{
|
|
"epoch": 8.82,
|
|
"learning_rate": 1.704850343611758e-05,
|
|
"loss": 1.2917,
|
|
"step": 28350
|
|
},
|
|
{
|
|
"epoch": 8.82,
|
|
"learning_rate": 1.6959919787841088e-05,
|
|
"loss": 1.2595,
|
|
"step": 28360
|
|
},
|
|
{
|
|
"epoch": 8.83,
|
|
"learning_rate": 1.6871558797709878e-05,
|
|
"loss": 1.2935,
|
|
"step": 28370
|
|
},
|
|
{
|
|
"epoch": 8.83,
|
|
"learning_rate": 1.678342055014839e-05,
|
|
"loss": 1.1331,
|
|
"step": 28380
|
|
},
|
|
{
|
|
"epoch": 8.83,
|
|
"learning_rate": 1.6695505129368406e-05,
|
|
"loss": 1.1356,
|
|
"step": 28390
|
|
},
|
|
{
|
|
"epoch": 8.84,
|
|
"learning_rate": 1.660781261936864e-05,
|
|
"loss": 1.1413,
|
|
"step": 28400
|
|
},
|
|
{
|
|
"epoch": 8.84,
|
|
"learning_rate": 1.6520343103934882e-05,
|
|
"loss": 1.1793,
|
|
"step": 28410
|
|
},
|
|
{
|
|
"epoch": 8.84,
|
|
"learning_rate": 1.6433096666639947e-05,
|
|
"loss": 1.2312,
|
|
"step": 28420
|
|
},
|
|
{
|
|
"epoch": 8.84,
|
|
"learning_rate": 1.6346073390843376e-05,
|
|
"loss": 1.21,
|
|
"step": 28430
|
|
},
|
|
{
|
|
"epoch": 8.85,
|
|
"learning_rate": 1.6259273359691655e-05,
|
|
"loss": 1.2636,
|
|
"step": 28440
|
|
},
|
|
{
|
|
"epoch": 8.85,
|
|
"learning_rate": 1.617269665611776e-05,
|
|
"loss": 1.1876,
|
|
"step": 28450
|
|
},
|
|
{
|
|
"epoch": 8.85,
|
|
"learning_rate": 1.6086343362841484e-05,
|
|
"loss": 1.1262,
|
|
"step": 28460
|
|
},
|
|
{
|
|
"epoch": 8.86,
|
|
"learning_rate": 1.6000213562369082e-05,
|
|
"loss": 1.177,
|
|
"step": 28470
|
|
},
|
|
{
|
|
"epoch": 8.86,
|
|
"learning_rate": 1.59143073369932e-05,
|
|
"loss": 1.116,
|
|
"step": 28480
|
|
},
|
|
{
|
|
"epoch": 8.86,
|
|
"learning_rate": 1.582862476879296e-05,
|
|
"loss": 1.2329,
|
|
"step": 28490
|
|
},
|
|
{
|
|
"epoch": 8.87,
|
|
"learning_rate": 1.5743165939633875e-05,
|
|
"loss": 1.2121,
|
|
"step": 28500
|
|
},
|
|
{
|
|
"epoch": 8.87,
|
|
"learning_rate": 1.5657930931167463e-05,
|
|
"loss": 1.1678,
|
|
"step": 28510
|
|
},
|
|
{
|
|
"epoch": 8.87,
|
|
"learning_rate": 1.5572919824831556e-05,
|
|
"loss": 1.2715,
|
|
"step": 28520
|
|
},
|
|
{
|
|
"epoch": 8.88,
|
|
"learning_rate": 1.548813270185004e-05,
|
|
"loss": 1.2102,
|
|
"step": 28530
|
|
},
|
|
{
|
|
"epoch": 8.88,
|
|
"learning_rate": 1.5403569643232752e-05,
|
|
"loss": 1.208,
|
|
"step": 28540
|
|
},
|
|
{
|
|
"epoch": 8.88,
|
|
"learning_rate": 1.5319230729775425e-05,
|
|
"loss": 1.2258,
|
|
"step": 28550
|
|
},
|
|
{
|
|
"epoch": 8.89,
|
|
"learning_rate": 1.523511604205971e-05,
|
|
"loss": 1.1401,
|
|
"step": 28560
|
|
},
|
|
{
|
|
"epoch": 8.89,
|
|
"learning_rate": 1.5151225660453017e-05,
|
|
"loss": 1.2105,
|
|
"step": 28570
|
|
},
|
|
{
|
|
"epoch": 8.89,
|
|
"learning_rate": 1.5067559665108394e-05,
|
|
"loss": 1.206,
|
|
"step": 28580
|
|
},
|
|
{
|
|
"epoch": 8.89,
|
|
"learning_rate": 1.498411813596448e-05,
|
|
"loss": 1.2433,
|
|
"step": 28590
|
|
},
|
|
{
|
|
"epoch": 8.9,
|
|
"learning_rate": 1.4900901152745534e-05,
|
|
"loss": 1.2095,
|
|
"step": 28600
|
|
},
|
|
{
|
|
"epoch": 8.9,
|
|
"learning_rate": 1.4817908794961171e-05,
|
|
"loss": 1.0907,
|
|
"step": 28610
|
|
},
|
|
{
|
|
"epoch": 8.9,
|
|
"learning_rate": 1.4735141141906467e-05,
|
|
"loss": 1.0915,
|
|
"step": 28620
|
|
},
|
|
{
|
|
"epoch": 8.91,
|
|
"learning_rate": 1.4652598272661744e-05,
|
|
"loss": 1.3654,
|
|
"step": 28630
|
|
},
|
|
{
|
|
"epoch": 8.91,
|
|
"learning_rate": 1.4570280266092667e-05,
|
|
"loss": 1.2817,
|
|
"step": 28640
|
|
},
|
|
{
|
|
"epoch": 8.91,
|
|
"learning_rate": 1.4488187200849934e-05,
|
|
"loss": 1.216,
|
|
"step": 28650
|
|
},
|
|
{
|
|
"epoch": 8.92,
|
|
"learning_rate": 1.4406319155369329e-05,
|
|
"loss": 1.2821,
|
|
"step": 28660
|
|
},
|
|
{
|
|
"epoch": 8.92,
|
|
"learning_rate": 1.4324676207871729e-05,
|
|
"loss": 1.2041,
|
|
"step": 28670
|
|
},
|
|
{
|
|
"epoch": 8.92,
|
|
"learning_rate": 1.4243258436362872e-05,
|
|
"loss": 1.2131,
|
|
"step": 28680
|
|
},
|
|
{
|
|
"epoch": 8.93,
|
|
"learning_rate": 1.416206591863331e-05,
|
|
"loss": 1.1541,
|
|
"step": 28690
|
|
},
|
|
{
|
|
"epoch": 8.93,
|
|
"learning_rate": 1.408109873225849e-05,
|
|
"loss": 1.2402,
|
|
"step": 28700
|
|
},
|
|
{
|
|
"epoch": 8.93,
|
|
"learning_rate": 1.400035695459853e-05,
|
|
"loss": 1.207,
|
|
"step": 28710
|
|
},
|
|
{
|
|
"epoch": 8.94,
|
|
"learning_rate": 1.391984066279814e-05,
|
|
"loss": 1.2782,
|
|
"step": 28720
|
|
},
|
|
{
|
|
"epoch": 8.94,
|
|
"learning_rate": 1.3839549933786583e-05,
|
|
"loss": 1.2606,
|
|
"step": 28730
|
|
},
|
|
{
|
|
"epoch": 8.94,
|
|
"learning_rate": 1.3759484844277692e-05,
|
|
"loss": 1.2918,
|
|
"step": 28740
|
|
},
|
|
{
|
|
"epoch": 8.94,
|
|
"learning_rate": 1.367964547076958e-05,
|
|
"loss": 1.2393,
|
|
"step": 28750
|
|
},
|
|
{
|
|
"epoch": 8.95,
|
|
"learning_rate": 1.3600031889544867e-05,
|
|
"loss": 1.1877,
|
|
"step": 28760
|
|
},
|
|
{
|
|
"epoch": 8.95,
|
|
"learning_rate": 1.352064417667026e-05,
|
|
"loss": 1.2315,
|
|
"step": 28770
|
|
},
|
|
{
|
|
"epoch": 8.95,
|
|
"learning_rate": 1.3441482407996835e-05,
|
|
"loss": 1.2762,
|
|
"step": 28780
|
|
},
|
|
{
|
|
"epoch": 8.96,
|
|
"learning_rate": 1.3362546659159675e-05,
|
|
"loss": 1.1775,
|
|
"step": 28790
|
|
},
|
|
{
|
|
"epoch": 8.96,
|
|
"learning_rate": 1.3291697794504565e-05,
|
|
"loss": 1.0908,
|
|
"step": 28800
|
|
},
|
|
{
|
|
"epoch": 8.96,
|
|
"learning_rate": 1.3213191690957526e-05,
|
|
"loss": 1.2062,
|
|
"step": 28810
|
|
},
|
|
{
|
|
"epoch": 8.97,
|
|
"learning_rate": 1.313491182536708e-05,
|
|
"loss": 1.216,
|
|
"step": 28820
|
|
},
|
|
{
|
|
"epoch": 8.97,
|
|
"learning_rate": 1.3056858272525785e-05,
|
|
"loss": 1.1802,
|
|
"step": 28830
|
|
},
|
|
{
|
|
"epoch": 8.97,
|
|
"learning_rate": 1.297903110700982e-05,
|
|
"loss": 1.2987,
|
|
"step": 28840
|
|
},
|
|
{
|
|
"epoch": 8.98,
|
|
"learning_rate": 1.2901430403179231e-05,
|
|
"loss": 1.2611,
|
|
"step": 28850
|
|
},
|
|
{
|
|
"epoch": 8.98,
|
|
"learning_rate": 1.2824056235177572e-05,
|
|
"loss": 1.172,
|
|
"step": 28860
|
|
},
|
|
{
|
|
"epoch": 8.98,
|
|
"learning_rate": 1.274690867693204e-05,
|
|
"loss": 1.2729,
|
|
"step": 28870
|
|
},
|
|
{
|
|
"epoch": 8.98,
|
|
"learning_rate": 1.2669987802153227e-05,
|
|
"loss": 1.1432,
|
|
"step": 28880
|
|
},
|
|
{
|
|
"epoch": 8.99,
|
|
"learning_rate": 1.259329368433515e-05,
|
|
"loss": 1.1722,
|
|
"step": 28890
|
|
},
|
|
{
|
|
"epoch": 8.99,
|
|
"learning_rate": 1.2516826396755304e-05,
|
|
"loss": 1.1917,
|
|
"step": 28900
|
|
},
|
|
{
|
|
"epoch": 8.99,
|
|
"learning_rate": 1.2440586012474248e-05,
|
|
"loss": 1.2766,
|
|
"step": 28910
|
|
},
|
|
{
|
|
"epoch": 9.0,
|
|
"learning_rate": 1.2364572604335933e-05,
|
|
"loss": 1.1424,
|
|
"step": 28920
|
|
},
|
|
{
|
|
"epoch": 9.0,
|
|
"learning_rate": 1.228878624496732e-05,
|
|
"loss": 1.3367,
|
|
"step": 28930
|
|
},
|
|
{
|
|
"epoch": 9.0,
|
|
"learning_rate": 1.2213227006778543e-05,
|
|
"loss": 1.1228,
|
|
"step": 28940
|
|
},
|
|
{
|
|
"epoch": 9.01,
|
|
"learning_rate": 1.2137894961962658e-05,
|
|
"loss": 1.1171,
|
|
"step": 28950
|
|
},
|
|
{
|
|
"epoch": 9.01,
|
|
"learning_rate": 1.206279018249562e-05,
|
|
"loss": 1.23,
|
|
"step": 28960
|
|
},
|
|
{
|
|
"epoch": 9.01,
|
|
"learning_rate": 1.1987912740136304e-05,
|
|
"loss": 1.1787,
|
|
"step": 28970
|
|
},
|
|
{
|
|
"epoch": 9.02,
|
|
"learning_rate": 1.1913262706426426e-05,
|
|
"loss": 1.184,
|
|
"step": 28980
|
|
},
|
|
{
|
|
"epoch": 9.02,
|
|
"learning_rate": 1.1838840152690322e-05,
|
|
"loss": 1.1006,
|
|
"step": 28990
|
|
},
|
|
{
|
|
"epoch": 9.02,
|
|
"learning_rate": 1.1764645150035002e-05,
|
|
"loss": 1.1795,
|
|
"step": 29000
|
|
},
|
|
{
|
|
"epoch": 9.03,
|
|
"learning_rate": 1.1690677769350123e-05,
|
|
"loss": 1.12,
|
|
"step": 29010
|
|
},
|
|
{
|
|
"epoch": 9.03,
|
|
"learning_rate": 1.161693808130776e-05,
|
|
"loss": 1.1544,
|
|
"step": 29020
|
|
},
|
|
{
|
|
"epoch": 9.03,
|
|
"learning_rate": 1.1543426156362529e-05,
|
|
"loss": 1.1889,
|
|
"step": 29030
|
|
},
|
|
{
|
|
"epoch": 9.03,
|
|
"learning_rate": 1.1470142064751415e-05,
|
|
"loss": 1.2401,
|
|
"step": 29040
|
|
},
|
|
{
|
|
"epoch": 9.04,
|
|
"learning_rate": 1.1397085876493685e-05,
|
|
"loss": 1.21,
|
|
"step": 29050
|
|
},
|
|
{
|
|
"epoch": 9.04,
|
|
"learning_rate": 1.133153022212438e-05,
|
|
"loss": 1.1611,
|
|
"step": 29060
|
|
},
|
|
{
|
|
"epoch": 9.04,
|
|
"learning_rate": 1.1258907242361282e-05,
|
|
"loss": 1.1863,
|
|
"step": 29070
|
|
},
|
|
{
|
|
"epoch": 9.05,
|
|
"learning_rate": 1.1186512367775903e-05,
|
|
"loss": 1.2517,
|
|
"step": 29080
|
|
},
|
|
{
|
|
"epoch": 9.05,
|
|
"learning_rate": 1.1114345667537912e-05,
|
|
"loss": 1.2082,
|
|
"step": 29090
|
|
},
|
|
{
|
|
"epoch": 9.05,
|
|
"learning_rate": 1.1042407210598986e-05,
|
|
"loss": 1.2119,
|
|
"step": 29100
|
|
},
|
|
{
|
|
"epoch": 9.06,
|
|
"learning_rate": 1.0970697065692702e-05,
|
|
"loss": 1.1863,
|
|
"step": 29110
|
|
},
|
|
{
|
|
"epoch": 9.06,
|
|
"learning_rate": 1.089921530133453e-05,
|
|
"loss": 1.0615,
|
|
"step": 29120
|
|
},
|
|
{
|
|
"epoch": 9.06,
|
|
"learning_rate": 1.0827961985821727e-05,
|
|
"loss": 1.1918,
|
|
"step": 29130
|
|
},
|
|
{
|
|
"epoch": 9.07,
|
|
"learning_rate": 1.0756937187233279e-05,
|
|
"loss": 1.1809,
|
|
"step": 29140
|
|
},
|
|
{
|
|
"epoch": 9.07,
|
|
"learning_rate": 1.068614097342982e-05,
|
|
"loss": 1.3039,
|
|
"step": 29150
|
|
},
|
|
{
|
|
"epoch": 9.07,
|
|
"learning_rate": 1.0615573412053575e-05,
|
|
"loss": 1.2112,
|
|
"step": 29160
|
|
},
|
|
{
|
|
"epoch": 9.08,
|
|
"learning_rate": 1.054523457052839e-05,
|
|
"loss": 1.2129,
|
|
"step": 29170
|
|
},
|
|
{
|
|
"epoch": 9.08,
|
|
"learning_rate": 1.0475124516059448e-05,
|
|
"loss": 1.2184,
|
|
"step": 29180
|
|
},
|
|
{
|
|
"epoch": 9.08,
|
|
"learning_rate": 1.0405243315633361e-05,
|
|
"loss": 1.2067,
|
|
"step": 29190
|
|
},
|
|
{
|
|
"epoch": 9.08,
|
|
"learning_rate": 1.0335591036018221e-05,
|
|
"loss": 1.0685,
|
|
"step": 29200
|
|
},
|
|
{
|
|
"epoch": 9.09,
|
|
"learning_rate": 1.0266167743763239e-05,
|
|
"loss": 1.2973,
|
|
"step": 29210
|
|
},
|
|
{
|
|
"epoch": 9.09,
|
|
"learning_rate": 1.0196973505198936e-05,
|
|
"loss": 1.0948,
|
|
"step": 29220
|
|
},
|
|
{
|
|
"epoch": 9.09,
|
|
"learning_rate": 1.0128008386436904e-05,
|
|
"loss": 1.1637,
|
|
"step": 29230
|
|
},
|
|
{
|
|
"epoch": 9.1,
|
|
"learning_rate": 1.0059272453369905e-05,
|
|
"loss": 1.2132,
|
|
"step": 29240
|
|
},
|
|
{
|
|
"epoch": 9.1,
|
|
"learning_rate": 9.990765771671684e-06,
|
|
"loss": 1.1717,
|
|
"step": 29250
|
|
},
|
|
{
|
|
"epoch": 9.1,
|
|
"learning_rate": 9.922488406796854e-06,
|
|
"loss": 1.1765,
|
|
"step": 29260
|
|
},
|
|
{
|
|
"epoch": 9.11,
|
|
"learning_rate": 9.854440423981176e-06,
|
|
"loss": 1.1572,
|
|
"step": 29270
|
|
},
|
|
{
|
|
"epoch": 9.11,
|
|
"learning_rate": 9.786621888241005e-06,
|
|
"loss": 1.2231,
|
|
"step": 29280
|
|
},
|
|
{
|
|
"epoch": 9.11,
|
|
"learning_rate": 9.719032864373562e-06,
|
|
"loss": 1.1899,
|
|
"step": 29290
|
|
},
|
|
{
|
|
"epoch": 9.12,
|
|
"learning_rate": 9.651673416956858e-06,
|
|
"loss": 1.2378,
|
|
"step": 29300
|
|
},
|
|
{
|
|
"epoch": 9.12,
|
|
"learning_rate": 9.584543610349384e-06,
|
|
"loss": 1.2623,
|
|
"step": 29310
|
|
},
|
|
{
|
|
"epoch": 9.12,
|
|
"learning_rate": 9.51764350869036e-06,
|
|
"loss": 1.2141,
|
|
"step": 29320
|
|
},
|
|
{
|
|
"epoch": 9.12,
|
|
"learning_rate": 9.450973175899408e-06,
|
|
"loss": 1.2573,
|
|
"step": 29330
|
|
},
|
|
{
|
|
"epoch": 9.13,
|
|
"learning_rate": 9.38453267567682e-06,
|
|
"loss": 1.1727,
|
|
"step": 29340
|
|
},
|
|
{
|
|
"epoch": 9.13,
|
|
"learning_rate": 9.318322071503127e-06,
|
|
"loss": 1.1548,
|
|
"step": 29350
|
|
},
|
|
{
|
|
"epoch": 9.13,
|
|
"learning_rate": 9.252341426639222e-06,
|
|
"loss": 1.1289,
|
|
"step": 29360
|
|
},
|
|
{
|
|
"epoch": 9.14,
|
|
"learning_rate": 9.186590804126343e-06,
|
|
"loss": 1.2141,
|
|
"step": 29370
|
|
},
|
|
{
|
|
"epoch": 9.14,
|
|
"learning_rate": 9.121070266785908e-06,
|
|
"loss": 1.1553,
|
|
"step": 29380
|
|
},
|
|
{
|
|
"epoch": 9.14,
|
|
"learning_rate": 9.055779877219506e-06,
|
|
"loss": 1.2458,
|
|
"step": 29390
|
|
},
|
|
{
|
|
"epoch": 9.15,
|
|
"learning_rate": 8.990719697808846e-06,
|
|
"loss": 1.1309,
|
|
"step": 29400
|
|
},
|
|
{
|
|
"epoch": 9.15,
|
|
"learning_rate": 8.925889790715707e-06,
|
|
"loss": 1.1961,
|
|
"step": 29410
|
|
},
|
|
{
|
|
"epoch": 9.15,
|
|
"learning_rate": 8.86129021788179e-06,
|
|
"loss": 1.208,
|
|
"step": 29420
|
|
},
|
|
{
|
|
"epoch": 9.16,
|
|
"learning_rate": 8.796921041028749e-06,
|
|
"loss": 1.1462,
|
|
"step": 29430
|
|
},
|
|
{
|
|
"epoch": 9.16,
|
|
"learning_rate": 8.732782321658168e-06,
|
|
"loss": 1.1959,
|
|
"step": 29440
|
|
},
|
|
{
|
|
"epoch": 9.16,
|
|
"learning_rate": 8.668874121051328e-06,
|
|
"loss": 1.2102,
|
|
"step": 29450
|
|
},
|
|
{
|
|
"epoch": 9.17,
|
|
"learning_rate": 8.605196500269335e-06,
|
|
"loss": 1.2409,
|
|
"step": 29460
|
|
},
|
|
{
|
|
"epoch": 9.17,
|
|
"learning_rate": 8.541749520152991e-06,
|
|
"loss": 1.0692,
|
|
"step": 29470
|
|
},
|
|
{
|
|
"epoch": 9.17,
|
|
"learning_rate": 8.478533241322694e-06,
|
|
"loss": 1.2288,
|
|
"step": 29480
|
|
},
|
|
{
|
|
"epoch": 9.17,
|
|
"learning_rate": 8.415547724178463e-06,
|
|
"loss": 1.1857,
|
|
"step": 29490
|
|
},
|
|
{
|
|
"epoch": 9.18,
|
|
"learning_rate": 8.352793028899741e-06,
|
|
"loss": 1.2012,
|
|
"step": 29500
|
|
},
|
|
{
|
|
"epoch": 9.18,
|
|
"learning_rate": 8.290269215445623e-06,
|
|
"loss": 1.3485,
|
|
"step": 29510
|
|
},
|
|
{
|
|
"epoch": 9.18,
|
|
"learning_rate": 8.22797634355435e-06,
|
|
"loss": 1.1623,
|
|
"step": 29520
|
|
},
|
|
{
|
|
"epoch": 9.19,
|
|
"learning_rate": 8.165914472743758e-06,
|
|
"loss": 1.1712,
|
|
"step": 29530
|
|
},
|
|
{
|
|
"epoch": 9.19,
|
|
"learning_rate": 8.104083662310773e-06,
|
|
"loss": 1.0819,
|
|
"step": 29540
|
|
},
|
|
{
|
|
"epoch": 9.19,
|
|
"learning_rate": 8.042483971331727e-06,
|
|
"loss": 1.2898,
|
|
"step": 29550
|
|
},
|
|
{
|
|
"epoch": 9.2,
|
|
"learning_rate": 7.981115458662008e-06,
|
|
"loss": 1.1774,
|
|
"step": 29560
|
|
},
|
|
{
|
|
"epoch": 9.2,
|
|
"learning_rate": 7.919978182936133e-06,
|
|
"loss": 1.228,
|
|
"step": 29570
|
|
},
|
|
{
|
|
"epoch": 9.2,
|
|
"learning_rate": 7.859072202567735e-06,
|
|
"loss": 1.2271,
|
|
"step": 29580
|
|
},
|
|
{
|
|
"epoch": 9.21,
|
|
"learning_rate": 7.798397575749461e-06,
|
|
"loss": 1.2731,
|
|
"step": 29590
|
|
},
|
|
{
|
|
"epoch": 9.21,
|
|
"learning_rate": 7.737954360452853e-06,
|
|
"loss": 1.1712,
|
|
"step": 29600
|
|
},
|
|
{
|
|
"epoch": 9.21,
|
|
"learning_rate": 7.677742614428356e-06,
|
|
"loss": 1.2787,
|
|
"step": 29610
|
|
},
|
|
{
|
|
"epoch": 9.22,
|
|
"learning_rate": 7.617762395205341e-06,
|
|
"loss": 1.1044,
|
|
"step": 29620
|
|
},
|
|
{
|
|
"epoch": 9.22,
|
|
"learning_rate": 7.5580137600918805e-06,
|
|
"loss": 1.1737,
|
|
"step": 29630
|
|
},
|
|
{
|
|
"epoch": 9.22,
|
|
"learning_rate": 7.498496766174784e-06,
|
|
"loss": 1.1148,
|
|
"step": 29640
|
|
},
|
|
{
|
|
"epoch": 9.22,
|
|
"learning_rate": 7.43921147031959e-06,
|
|
"loss": 1.1434,
|
|
"step": 29650
|
|
},
|
|
{
|
|
"epoch": 9.23,
|
|
"learning_rate": 7.380157929170461e-06,
|
|
"loss": 1.1337,
|
|
"step": 29660
|
|
},
|
|
{
|
|
"epoch": 9.23,
|
|
"learning_rate": 7.321336199150069e-06,
|
|
"loss": 1.1695,
|
|
"step": 29670
|
|
},
|
|
{
|
|
"epoch": 9.23,
|
|
"learning_rate": 7.262746336459625e-06,
|
|
"loss": 1.2047,
|
|
"step": 29680
|
|
},
|
|
{
|
|
"epoch": 9.24,
|
|
"learning_rate": 7.204388397078848e-06,
|
|
"loss": 1.1573,
|
|
"step": 29690
|
|
},
|
|
{
|
|
"epoch": 9.24,
|
|
"learning_rate": 7.146262436765804e-06,
|
|
"loss": 1.1595,
|
|
"step": 29700
|
|
},
|
|
{
|
|
"epoch": 9.24,
|
|
"learning_rate": 7.08836851105693e-06,
|
|
"loss": 1.195,
|
|
"step": 29710
|
|
},
|
|
{
|
|
"epoch": 9.25,
|
|
"learning_rate": 7.030706675267007e-06,
|
|
"loss": 1.2981,
|
|
"step": 29720
|
|
},
|
|
{
|
|
"epoch": 9.25,
|
|
"learning_rate": 6.9732769844890465e-06,
|
|
"loss": 1.2578,
|
|
"step": 29730
|
|
},
|
|
{
|
|
"epoch": 9.25,
|
|
"learning_rate": 6.916079493594241e-06,
|
|
"loss": 1.2478,
|
|
"step": 29740
|
|
},
|
|
{
|
|
"epoch": 9.26,
|
|
"learning_rate": 6.859114257231874e-06,
|
|
"loss": 1.1102,
|
|
"step": 29750
|
|
},
|
|
{
|
|
"epoch": 9.26,
|
|
"learning_rate": 6.802381329829465e-06,
|
|
"loss": 1.2225,
|
|
"step": 29760
|
|
},
|
|
{
|
|
"epoch": 9.26,
|
|
"learning_rate": 6.74588076559246e-06,
|
|
"loss": 1.1948,
|
|
"step": 29770
|
|
},
|
|
{
|
|
"epoch": 9.26,
|
|
"learning_rate": 6.689612618504259e-06,
|
|
"loss": 1.1639,
|
|
"step": 29780
|
|
},
|
|
{
|
|
"epoch": 9.27,
|
|
"learning_rate": 6.633576942326358e-06,
|
|
"loss": 1.1969,
|
|
"step": 29790
|
|
},
|
|
{
|
|
"epoch": 9.27,
|
|
"learning_rate": 6.577773790598013e-06,
|
|
"loss": 1.3071,
|
|
"step": 29800
|
|
},
|
|
{
|
|
"epoch": 9.27,
|
|
"learning_rate": 6.522203216636324e-06,
|
|
"loss": 1.0859,
|
|
"step": 29810
|
|
},
|
|
{
|
|
"epoch": 9.28,
|
|
"learning_rate": 6.4668652735362095e-06,
|
|
"loss": 1.157,
|
|
"step": 29820
|
|
},
|
|
{
|
|
"epoch": 9.28,
|
|
"learning_rate": 6.41176001417032e-06,
|
|
"loss": 1.2226,
|
|
"step": 29830
|
|
},
|
|
{
|
|
"epoch": 9.28,
|
|
"learning_rate": 6.356887491188929e-06,
|
|
"loss": 1.2654,
|
|
"step": 29840
|
|
},
|
|
{
|
|
"epoch": 9.29,
|
|
"learning_rate": 6.302247757020041e-06,
|
|
"loss": 1.164,
|
|
"step": 29850
|
|
},
|
|
{
|
|
"epoch": 9.29,
|
|
"learning_rate": 6.2478408638691755e-06,
|
|
"loss": 1.2115,
|
|
"step": 29860
|
|
},
|
|
{
|
|
"epoch": 9.29,
|
|
"learning_rate": 6.193666863719416e-06,
|
|
"loss": 1.1508,
|
|
"step": 29870
|
|
},
|
|
{
|
|
"epoch": 9.3,
|
|
"learning_rate": 6.139725808331248e-06,
|
|
"loss": 1.2145,
|
|
"step": 29880
|
|
},
|
|
{
|
|
"epoch": 9.3,
|
|
"learning_rate": 6.086017749242723e-06,
|
|
"loss": 1.0907,
|
|
"step": 29890
|
|
},
|
|
{
|
|
"epoch": 9.3,
|
|
"learning_rate": 6.032542737769181e-06,
|
|
"loss": 1.1656,
|
|
"step": 29900
|
|
},
|
|
{
|
|
"epoch": 9.31,
|
|
"learning_rate": 5.979300825003309e-06,
|
|
"loss": 1.1899,
|
|
"step": 29910
|
|
},
|
|
{
|
|
"epoch": 9.31,
|
|
"learning_rate": 5.9262920618150806e-06,
|
|
"loss": 1.2284,
|
|
"step": 29920
|
|
},
|
|
{
|
|
"epoch": 9.31,
|
|
"learning_rate": 5.873516498851788e-06,
|
|
"loss": 1.212,
|
|
"step": 29930
|
|
},
|
|
{
|
|
"epoch": 9.31,
|
|
"learning_rate": 5.820974186537792e-06,
|
|
"loss": 1.1827,
|
|
"step": 29940
|
|
},
|
|
{
|
|
"epoch": 9.32,
|
|
"learning_rate": 5.7686651750746e-06,
|
|
"loss": 1.1114,
|
|
"step": 29950
|
|
},
|
|
{
|
|
"epoch": 9.32,
|
|
"learning_rate": 5.716589514440956e-06,
|
|
"loss": 1.0912,
|
|
"step": 29960
|
|
},
|
|
{
|
|
"epoch": 9.32,
|
|
"learning_rate": 5.664747254392477e-06,
|
|
"loss": 1.2093,
|
|
"step": 29970
|
|
},
|
|
{
|
|
"epoch": 9.33,
|
|
"learning_rate": 5.613138444461874e-06,
|
|
"loss": 1.1575,
|
|
"step": 29980
|
|
},
|
|
{
|
|
"epoch": 9.33,
|
|
"learning_rate": 5.561763133958786e-06,
|
|
"loss": 1.2593,
|
|
"step": 29990
|
|
},
|
|
{
|
|
"epoch": 9.33,
|
|
"learning_rate": 5.510621371969754e-06,
|
|
"loss": 1.1518,
|
|
"step": 30000
|
|
},
|
|
{
|
|
"epoch": 9.34,
|
|
"learning_rate": 5.459713207358191e-06,
|
|
"loss": 1.1686,
|
|
"step": 30010
|
|
},
|
|
{
|
|
"epoch": 9.34,
|
|
"learning_rate": 5.409038688764273e-06,
|
|
"loss": 1.1483,
|
|
"step": 30020
|
|
},
|
|
{
|
|
"epoch": 9.34,
|
|
"learning_rate": 5.358597864604964e-06,
|
|
"loss": 1.1439,
|
|
"step": 30030
|
|
},
|
|
{
|
|
"epoch": 9.35,
|
|
"learning_rate": 5.308390783073963e-06,
|
|
"loss": 1.2297,
|
|
"step": 30040
|
|
},
|
|
{
|
|
"epoch": 9.35,
|
|
"learning_rate": 5.258417492141676e-06,
|
|
"loss": 1.1704,
|
|
"step": 30050
|
|
},
|
|
{
|
|
"epoch": 9.35,
|
|
"learning_rate": 5.208678039554992e-06,
|
|
"loss": 1.1348,
|
|
"step": 30060
|
|
},
|
|
{
|
|
"epoch": 9.36,
|
|
"learning_rate": 5.159172472837537e-06,
|
|
"loss": 1.1424,
|
|
"step": 30070
|
|
},
|
|
{
|
|
"epoch": 9.36,
|
|
"learning_rate": 5.109900839289389e-06,
|
|
"loss": 1.2477,
|
|
"step": 30080
|
|
},
|
|
{
|
|
"epoch": 9.36,
|
|
"learning_rate": 5.0608631859870855e-06,
|
|
"loss": 1.197,
|
|
"step": 30090
|
|
},
|
|
{
|
|
"epoch": 9.36,
|
|
"learning_rate": 5.012059559783705e-06,
|
|
"loss": 1.2528,
|
|
"step": 30100
|
|
},
|
|
{
|
|
"epoch": 9.37,
|
|
"learning_rate": 4.963490007308697e-06,
|
|
"loss": 1.2296,
|
|
"step": 30110
|
|
},
|
|
{
|
|
"epoch": 9.37,
|
|
"learning_rate": 4.915154574967801e-06,
|
|
"loss": 1.2328,
|
|
"step": 30120
|
|
},
|
|
{
|
|
"epoch": 9.37,
|
|
"learning_rate": 4.8670533089430755e-06,
|
|
"loss": 1.1509,
|
|
"step": 30130
|
|
},
|
|
{
|
|
"epoch": 9.38,
|
|
"learning_rate": 4.8191862551929255e-06,
|
|
"loss": 1.1929,
|
|
"step": 30140
|
|
},
|
|
{
|
|
"epoch": 9.38,
|
|
"learning_rate": 4.771553459451905e-06,
|
|
"loss": 1.1877,
|
|
"step": 30150
|
|
},
|
|
{
|
|
"epoch": 9.38,
|
|
"learning_rate": 4.724154967230776e-06,
|
|
"loss": 1.223,
|
|
"step": 30160
|
|
},
|
|
{
|
|
"epoch": 9.39,
|
|
"learning_rate": 4.6769908238164234e-06,
|
|
"loss": 1.2286,
|
|
"step": 30170
|
|
},
|
|
{
|
|
"epoch": 9.39,
|
|
"learning_rate": 4.63006107427183e-06,
|
|
"loss": 1.2325,
|
|
"step": 30180
|
|
},
|
|
{
|
|
"epoch": 9.39,
|
|
"learning_rate": 4.583365763436043e-06,
|
|
"loss": 1.1422,
|
|
"step": 30190
|
|
},
|
|
{
|
|
"epoch": 9.4,
|
|
"learning_rate": 4.536904935924069e-06,
|
|
"loss": 1.1907,
|
|
"step": 30200
|
|
},
|
|
{
|
|
"epoch": 9.4,
|
|
"learning_rate": 4.490678636126927e-06,
|
|
"loss": 1.1622,
|
|
"step": 30210
|
|
},
|
|
{
|
|
"epoch": 9.4,
|
|
"learning_rate": 4.4446869082115096e-06,
|
|
"loss": 1.2119,
|
|
"step": 30220
|
|
},
|
|
{
|
|
"epoch": 9.4,
|
|
"learning_rate": 4.398929796120637e-06,
|
|
"loss": 1.1501,
|
|
"step": 30230
|
|
},
|
|
{
|
|
"epoch": 9.41,
|
|
"learning_rate": 4.353407343572896e-06,
|
|
"loss": 1.2206,
|
|
"step": 30240
|
|
},
|
|
{
|
|
"epoch": 9.41,
|
|
"learning_rate": 4.308119594062798e-06,
|
|
"loss": 1.1479,
|
|
"step": 30250
|
|
},
|
|
{
|
|
"epoch": 9.41,
|
|
"learning_rate": 4.263066590860481e-06,
|
|
"loss": 1.0786,
|
|
"step": 30260
|
|
},
|
|
{
|
|
"epoch": 9.42,
|
|
"learning_rate": 4.218248377011819e-06,
|
|
"loss": 1.2888,
|
|
"step": 30270
|
|
},
|
|
{
|
|
"epoch": 9.42,
|
|
"learning_rate": 4.1736649953383885e-06,
|
|
"loss": 1.1979,
|
|
"step": 30280
|
|
},
|
|
{
|
|
"epoch": 9.42,
|
|
"learning_rate": 4.129316488437396e-06,
|
|
"loss": 1.0657,
|
|
"step": 30290
|
|
},
|
|
{
|
|
"epoch": 9.43,
|
|
"learning_rate": 4.085202898681583e-06,
|
|
"loss": 1.1811,
|
|
"step": 30300
|
|
},
|
|
{
|
|
"epoch": 9.43,
|
|
"learning_rate": 4.041324268219293e-06,
|
|
"loss": 1.2437,
|
|
"step": 30310
|
|
},
|
|
{
|
|
"epoch": 9.43,
|
|
"learning_rate": 3.997680638974433e-06,
|
|
"loss": 1.12,
|
|
"step": 30320
|
|
},
|
|
{
|
|
"epoch": 9.44,
|
|
"learning_rate": 3.954272052646202e-06,
|
|
"loss": 1.0504,
|
|
"step": 30330
|
|
},
|
|
{
|
|
"epoch": 9.44,
|
|
"learning_rate": 3.911098550709397e-06,
|
|
"loss": 1.1848,
|
|
"step": 30340
|
|
},
|
|
{
|
|
"epoch": 9.44,
|
|
"learning_rate": 3.868160174414132e-06,
|
|
"loss": 1.1917,
|
|
"step": 30350
|
|
},
|
|
{
|
|
"epoch": 9.45,
|
|
"learning_rate": 3.825456964785867e-06,
|
|
"loss": 1.1855,
|
|
"step": 30360
|
|
},
|
|
{
|
|
"epoch": 9.45,
|
|
"learning_rate": 3.782988962625383e-06,
|
|
"loss": 1.1265,
|
|
"step": 30370
|
|
},
|
|
{
|
|
"epoch": 9.45,
|
|
"learning_rate": 3.74075620850875e-06,
|
|
"loss": 1.2597,
|
|
"step": 30380
|
|
},
|
|
{
|
|
"epoch": 9.45,
|
|
"learning_rate": 3.698758742787245e-06,
|
|
"loss": 1.2106,
|
|
"step": 30390
|
|
},
|
|
{
|
|
"epoch": 9.46,
|
|
"learning_rate": 3.656996605587354e-06,
|
|
"loss": 1.2925,
|
|
"step": 30400
|
|
},
|
|
{
|
|
"epoch": 9.46,
|
|
"learning_rate": 3.6154698368106866e-06,
|
|
"loss": 1.1006,
|
|
"step": 30410
|
|
},
|
|
{
|
|
"epoch": 9.46,
|
|
"learning_rate": 3.5741784761340047e-06,
|
|
"loss": 1.1918,
|
|
"step": 30420
|
|
},
|
|
{
|
|
"epoch": 9.47,
|
|
"learning_rate": 3.533122563009139e-06,
|
|
"loss": 1.0635,
|
|
"step": 30430
|
|
},
|
|
{
|
|
"epoch": 9.47,
|
|
"learning_rate": 3.4923021366629893e-06,
|
|
"loss": 1.21,
|
|
"step": 30440
|
|
},
|
|
{
|
|
"epoch": 9.47,
|
|
"learning_rate": 3.451717236097385e-06,
|
|
"loss": 1.2024,
|
|
"step": 30450
|
|
},
|
|
{
|
|
"epoch": 9.48,
|
|
"learning_rate": 3.411367900089224e-06,
|
|
"loss": 1.1921,
|
|
"step": 30460
|
|
},
|
|
{
|
|
"epoch": 9.48,
|
|
"learning_rate": 3.3712541671902242e-06,
|
|
"loss": 1.1499,
|
|
"step": 30470
|
|
},
|
|
{
|
|
"epoch": 9.48,
|
|
"learning_rate": 3.3313760757270885e-06,
|
|
"loss": 1.1342,
|
|
"step": 30480
|
|
},
|
|
{
|
|
"epoch": 9.49,
|
|
"learning_rate": 3.2917336638013105e-06,
|
|
"loss": 1.3532,
|
|
"step": 30490
|
|
},
|
|
{
|
|
"epoch": 9.49,
|
|
"learning_rate": 3.2523269692892597e-06,
|
|
"loss": 1.0919,
|
|
"step": 30500
|
|
},
|
|
{
|
|
"epoch": 9.49,
|
|
"learning_rate": 3.21315602984204e-06,
|
|
"loss": 1.1575,
|
|
"step": 30510
|
|
},
|
|
{
|
|
"epoch": 9.5,
|
|
"learning_rate": 3.1742208828855757e-06,
|
|
"loss": 1.2692,
|
|
"step": 30520
|
|
},
|
|
{
|
|
"epoch": 9.5,
|
|
"learning_rate": 3.135521565620386e-06,
|
|
"loss": 1.1699,
|
|
"step": 30530
|
|
},
|
|
{
|
|
"epoch": 9.5,
|
|
"learning_rate": 3.0970581150217558e-06,
|
|
"loss": 1.2698,
|
|
"step": 30540
|
|
},
|
|
{
|
|
"epoch": 9.5,
|
|
"learning_rate": 3.0588305678396213e-06,
|
|
"loss": 1.1721,
|
|
"step": 30550
|
|
},
|
|
{
|
|
"epoch": 9.51,
|
|
"learning_rate": 3.02083896059846e-06,
|
|
"loss": 1.2556,
|
|
"step": 30560
|
|
},
|
|
{
|
|
"epoch": 9.51,
|
|
"learning_rate": 2.983083329597347e-06,
|
|
"loss": 1.2286,
|
|
"step": 30570
|
|
},
|
|
{
|
|
"epoch": 9.51,
|
|
"learning_rate": 2.9455637109099265e-06,
|
|
"loss": 1.215,
|
|
"step": 30580
|
|
},
|
|
{
|
|
"epoch": 9.52,
|
|
"learning_rate": 2.9082801403843007e-06,
|
|
"loss": 1.1914,
|
|
"step": 30590
|
|
},
|
|
{
|
|
"epoch": 9.52,
|
|
"learning_rate": 2.8712326536430855e-06,
|
|
"loss": 1.1969,
|
|
"step": 30600
|
|
},
|
|
{
|
|
"epoch": 9.52,
|
|
"learning_rate": 2.834421286083244e-06,
|
|
"loss": 1.1871,
|
|
"step": 30610
|
|
},
|
|
{
|
|
"epoch": 9.53,
|
|
"learning_rate": 2.7978460728762255e-06,
|
|
"loss": 1.159,
|
|
"step": 30620
|
|
},
|
|
{
|
|
"epoch": 9.53,
|
|
"learning_rate": 2.761507048967854e-06,
|
|
"loss": 1.0978,
|
|
"step": 30630
|
|
},
|
|
{
|
|
"epoch": 9.53,
|
|
"learning_rate": 2.725404249078217e-06,
|
|
"loss": 1.123,
|
|
"step": 30640
|
|
},
|
|
{
|
|
"epoch": 9.54,
|
|
"learning_rate": 2.6895377077017222e-06,
|
|
"loss": 1.3251,
|
|
"step": 30650
|
|
},
|
|
{
|
|
"epoch": 9.54,
|
|
"learning_rate": 2.6539074591070965e-06,
|
|
"loss": 1.1685,
|
|
"step": 30660
|
|
},
|
|
{
|
|
"epoch": 9.54,
|
|
"learning_rate": 2.6185135373372194e-06,
|
|
"loss": 1.2025,
|
|
"step": 30670
|
|
},
|
|
{
|
|
"epoch": 9.54,
|
|
"learning_rate": 2.583355976209234e-06,
|
|
"loss": 1.1877,
|
|
"step": 30680
|
|
},
|
|
{
|
|
"epoch": 9.55,
|
|
"learning_rate": 2.5484348093144372e-06,
|
|
"loss": 1.305,
|
|
"step": 30690
|
|
},
|
|
{
|
|
"epoch": 9.55,
|
|
"learning_rate": 2.5137500700182505e-06,
|
|
"loss": 1.12,
|
|
"step": 30700
|
|
},
|
|
{
|
|
"epoch": 9.55,
|
|
"learning_rate": 2.479301791460192e-06,
|
|
"loss": 1.1463,
|
|
"step": 30710
|
|
},
|
|
{
|
|
"epoch": 9.56,
|
|
"learning_rate": 2.4450900065538796e-06,
|
|
"loss": 1.2273,
|
|
"step": 30720
|
|
},
|
|
{
|
|
"epoch": 9.56,
|
|
"learning_rate": 2.411114747986998e-06,
|
|
"loss": 1.2517,
|
|
"step": 30730
|
|
},
|
|
{
|
|
"epoch": 9.56,
|
|
"learning_rate": 2.3773760482211635e-06,
|
|
"loss": 1.183,
|
|
"step": 30740
|
|
},
|
|
{
|
|
"epoch": 9.57,
|
|
"learning_rate": 2.343873939492036e-06,
|
|
"loss": 1.1584,
|
|
"step": 30750
|
|
},
|
|
{
|
|
"epoch": 9.57,
|
|
"learning_rate": 2.3106084538091765e-06,
|
|
"loss": 1.2679,
|
|
"step": 30760
|
|
},
|
|
{
|
|
"epoch": 9.57,
|
|
"learning_rate": 2.277579622956161e-06,
|
|
"loss": 1.1019,
|
|
"step": 30770
|
|
},
|
|
{
|
|
"epoch": 9.58,
|
|
"learning_rate": 2.244787478490329e-06,
|
|
"loss": 1.1944,
|
|
"step": 30780
|
|
},
|
|
{
|
|
"epoch": 9.58,
|
|
"learning_rate": 2.212232051742924e-06,
|
|
"loss": 1.1415,
|
|
"step": 30790
|
|
},
|
|
{
|
|
"epoch": 9.58,
|
|
"learning_rate": 2.1799133738190925e-06,
|
|
"loss": 1.2445,
|
|
"step": 30800
|
|
},
|
|
{
|
|
"epoch": 9.59,
|
|
"learning_rate": 2.1478314755976613e-06,
|
|
"loss": 1.1842,
|
|
"step": 30810
|
|
},
|
|
{
|
|
"epoch": 9.59,
|
|
"learning_rate": 2.115986387731278e-06,
|
|
"loss": 1.2065,
|
|
"step": 30820
|
|
},
|
|
{
|
|
"epoch": 9.59,
|
|
"learning_rate": 2.0843781406463812e-06,
|
|
"loss": 1.2011,
|
|
"step": 30830
|
|
},
|
|
{
|
|
"epoch": 9.59,
|
|
"learning_rate": 2.0530067645430083e-06,
|
|
"loss": 1.2883,
|
|
"step": 30840
|
|
},
|
|
{
|
|
"epoch": 9.6,
|
|
"learning_rate": 2.0218722893950158e-06,
|
|
"loss": 1.3885,
|
|
"step": 30850
|
|
},
|
|
{
|
|
"epoch": 9.6,
|
|
"learning_rate": 1.9909747449497475e-06,
|
|
"loss": 1.3189,
|
|
"step": 30860
|
|
},
|
|
{
|
|
"epoch": 9.6,
|
|
"learning_rate": 1.960314160728338e-06,
|
|
"loss": 1.2231,
|
|
"step": 30870
|
|
},
|
|
{
|
|
"epoch": 9.61,
|
|
"learning_rate": 1.929890566025383e-06,
|
|
"loss": 1.2658,
|
|
"step": 30880
|
|
},
|
|
{
|
|
"epoch": 9.61,
|
|
"learning_rate": 1.8997039899091573e-06,
|
|
"loss": 1.2487,
|
|
"step": 30890
|
|
},
|
|
{
|
|
"epoch": 9.61,
|
|
"learning_rate": 1.8697544612214235e-06,
|
|
"loss": 1.2269,
|
|
"step": 30900
|
|
},
|
|
{
|
|
"epoch": 9.62,
|
|
"learning_rate": 1.8400420085774028e-06,
|
|
"loss": 1.1372,
|
|
"step": 30910
|
|
},
|
|
{
|
|
"epoch": 9.62,
|
|
"learning_rate": 1.810566660365942e-06,
|
|
"loss": 1.1241,
|
|
"step": 30920
|
|
},
|
|
{
|
|
"epoch": 9.62,
|
|
"learning_rate": 1.7813284447491528e-06,
|
|
"loss": 1.252,
|
|
"step": 30930
|
|
},
|
|
{
|
|
"epoch": 9.63,
|
|
"learning_rate": 1.7523273896628e-06,
|
|
"loss": 1.2294,
|
|
"step": 30940
|
|
},
|
|
{
|
|
"epoch": 9.63,
|
|
"learning_rate": 1.7235635228158851e-06,
|
|
"loss": 1.1998,
|
|
"step": 30950
|
|
},
|
|
{
|
|
"epoch": 9.63,
|
|
"learning_rate": 1.6950368716908414e-06,
|
|
"loss": 1.1879,
|
|
"step": 30960
|
|
},
|
|
{
|
|
"epoch": 9.64,
|
|
"learning_rate": 1.6667474635434777e-06,
|
|
"loss": 1.2471,
|
|
"step": 30970
|
|
},
|
|
{
|
|
"epoch": 9.64,
|
|
"learning_rate": 1.6386953254028948e-06,
|
|
"loss": 1.2933,
|
|
"step": 30980
|
|
},
|
|
{
|
|
"epoch": 9.64,
|
|
"learning_rate": 1.6108804840715142e-06,
|
|
"loss": 1.1662,
|
|
"step": 30990
|
|
},
|
|
{
|
|
"epoch": 9.64,
|
|
"learning_rate": 1.583302966125022e-06,
|
|
"loss": 1.1734,
|
|
"step": 31000
|
|
},
|
|
{
|
|
"epoch": 9.65,
|
|
"learning_rate": 1.555962797912369e-06,
|
|
"loss": 1.1516,
|
|
"step": 31010
|
|
},
|
|
{
|
|
"epoch": 9.65,
|
|
"learning_rate": 1.5288600055557156e-06,
|
|
"loss": 1.1383,
|
|
"step": 31020
|
|
},
|
|
{
|
|
"epoch": 9.65,
|
|
"learning_rate": 1.5019946149504027e-06,
|
|
"loss": 1.1997,
|
|
"step": 31030
|
|
},
|
|
{
|
|
"epoch": 9.66,
|
|
"learning_rate": 1.4753666517650087e-06,
|
|
"loss": 1.2049,
|
|
"step": 31040
|
|
},
|
|
{
|
|
"epoch": 9.66,
|
|
"learning_rate": 1.4489761414411828e-06,
|
|
"loss": 1.1319,
|
|
"step": 31050
|
|
},
|
|
{
|
|
"epoch": 9.66,
|
|
"learning_rate": 1.422823109193755e-06,
|
|
"loss": 1.1418,
|
|
"step": 31060
|
|
},
|
|
{
|
|
"epoch": 9.67,
|
|
"learning_rate": 1.3969075800106257e-06,
|
|
"loss": 1.2015,
|
|
"step": 31070
|
|
},
|
|
{
|
|
"epoch": 9.67,
|
|
"learning_rate": 1.3712295786528217e-06,
|
|
"loss": 1.2032,
|
|
"step": 31080
|
|
},
|
|
{
|
|
"epoch": 9.67,
|
|
"learning_rate": 1.3457891296543846e-06,
|
|
"loss": 1.1138,
|
|
"step": 31090
|
|
},
|
|
{
|
|
"epoch": 9.68,
|
|
"learning_rate": 1.3205862573223425e-06,
|
|
"loss": 1.1906,
|
|
"step": 31100
|
|
},
|
|
{
|
|
"epoch": 9.68,
|
|
"learning_rate": 1.2956209857368229e-06,
|
|
"loss": 1.1991,
|
|
"step": 31110
|
|
},
|
|
{
|
|
"epoch": 9.68,
|
|
"learning_rate": 1.2708933387509114e-06,
|
|
"loss": 1.1002,
|
|
"step": 31120
|
|
},
|
|
{
|
|
"epoch": 9.68,
|
|
"learning_rate": 1.2464033399905705e-06,
|
|
"loss": 1.2285,
|
|
"step": 31130
|
|
},
|
|
{
|
|
"epoch": 9.69,
|
|
"learning_rate": 1.2221510128548052e-06,
|
|
"loss": 1.1895,
|
|
"step": 31140
|
|
},
|
|
{
|
|
"epoch": 9.69,
|
|
"learning_rate": 1.1981363805155522e-06,
|
|
"loss": 1.1852,
|
|
"step": 31150
|
|
},
|
|
{
|
|
"epoch": 9.69,
|
|
"learning_rate": 1.1743594659175128e-06,
|
|
"loss": 1.1156,
|
|
"step": 31160
|
|
},
|
|
{
|
|
"epoch": 9.7,
|
|
"learning_rate": 1.1508202917783761e-06,
|
|
"loss": 1.2219,
|
|
"step": 31170
|
|
},
|
|
{
|
|
"epoch": 9.7,
|
|
"learning_rate": 1.1275188805886516e-06,
|
|
"loss": 1.1318,
|
|
"step": 31180
|
|
},
|
|
{
|
|
"epoch": 9.7,
|
|
"learning_rate": 1.1044552546116692e-06,
|
|
"loss": 1.185,
|
|
"step": 31190
|
|
},
|
|
{
|
|
"epoch": 9.71,
|
|
"learning_rate": 1.081629435883552e-06,
|
|
"loss": 1.2301,
|
|
"step": 31200
|
|
},
|
|
{
|
|
"epoch": 9.71,
|
|
"learning_rate": 1.0590414462132437e-06,
|
|
"loss": 1.029,
|
|
"step": 31210
|
|
},
|
|
{
|
|
"epoch": 9.71,
|
|
"learning_rate": 1.0366913071824525e-06,
|
|
"loss": 1.2582,
|
|
"step": 31220
|
|
},
|
|
{
|
|
"epoch": 9.72,
|
|
"learning_rate": 1.0145790401455967e-06,
|
|
"loss": 1.105,
|
|
"step": 31230
|
|
},
|
|
{
|
|
"epoch": 9.72,
|
|
"learning_rate": 9.927046662298323e-07,
|
|
"loss": 1.249,
|
|
"step": 31240
|
|
},
|
|
{
|
|
"epoch": 9.72,
|
|
"learning_rate": 9.710682063350517e-07,
|
|
"loss": 1.249,
|
|
"step": 31250
|
|
},
|
|
{
|
|
"epoch": 9.73,
|
|
"learning_rate": 9.496696811338302e-07,
|
|
"loss": 1.1982,
|
|
"step": 31260
|
|
},
|
|
{
|
|
"epoch": 9.73,
|
|
"learning_rate": 9.285091110713406e-07,
|
|
"loss": 1.1172,
|
|
"step": 31270
|
|
},
|
|
{
|
|
"epoch": 9.73,
|
|
"learning_rate": 9.07586516365494e-07,
|
|
"loss": 1.1946,
|
|
"step": 31280
|
|
},
|
|
{
|
|
"epoch": 9.73,
|
|
"learning_rate": 8.869019170067439e-07,
|
|
"loss": 1.2528,
|
|
"step": 31290
|
|
},
|
|
{
|
|
"epoch": 9.74,
|
|
"learning_rate": 8.664553327582258e-07,
|
|
"loss": 1.2566,
|
|
"step": 31300
|
|
},
|
|
{
|
|
"epoch": 9.74,
|
|
"learning_rate": 8.462467831555909e-07,
|
|
"loss": 1.1967,
|
|
"step": 31310
|
|
},
|
|
{
|
|
"epoch": 9.74,
|
|
"learning_rate": 8.262762875071439e-07,
|
|
"loss": 1.134,
|
|
"step": 31320
|
|
},
|
|
{
|
|
"epoch": 9.75,
|
|
"learning_rate": 8.065438648936496e-07,
|
|
"loss": 1.2224,
|
|
"step": 31330
|
|
},
|
|
{
|
|
"epoch": 9.75,
|
|
"learning_rate": 7.870495341684992e-07,
|
|
"loss": 1.0997,
|
|
"step": 31340
|
|
},
|
|
{
|
|
"epoch": 9.75,
|
|
"learning_rate": 7.677933139574877e-07,
|
|
"loss": 1.1421,
|
|
"step": 31350
|
|
},
|
|
{
|
|
"epoch": 9.76,
|
|
"learning_rate": 7.487752226590372e-07,
|
|
"loss": 1.2268,
|
|
"step": 31360
|
|
},
|
|
{
|
|
"epoch": 9.76,
|
|
"learning_rate": 7.299952784439457e-07,
|
|
"loss": 1.2888,
|
|
"step": 31370
|
|
},
|
|
{
|
|
"epoch": 9.76,
|
|
"learning_rate": 7.114534992554989e-07,
|
|
"loss": 1.1756,
|
|
"step": 31380
|
|
},
|
|
{
|
|
"epoch": 9.77,
|
|
"learning_rate": 6.931499028094979e-07,
|
|
"loss": 1.1313,
|
|
"step": 31390
|
|
},
|
|
{
|
|
"epoch": 9.77,
|
|
"learning_rate": 6.750845065940369e-07,
|
|
"loss": 1.1306,
|
|
"step": 31400
|
|
},
|
|
{
|
|
"epoch": 9.77,
|
|
"learning_rate": 6.572573278697536e-07,
|
|
"loss": 1.2048,
|
|
"step": 31410
|
|
},
|
|
{
|
|
"epoch": 9.78,
|
|
"learning_rate": 6.39668383669606e-07,
|
|
"loss": 1.2262,
|
|
"step": 31420
|
|
},
|
|
{
|
|
"epoch": 9.78,
|
|
"learning_rate": 6.223176907989848e-07,
|
|
"loss": 1.1818,
|
|
"step": 31430
|
|
},
|
|
{
|
|
"epoch": 9.78,
|
|
"learning_rate": 6.052052658355456e-07,
|
|
"loss": 1.2494,
|
|
"step": 31440
|
|
},
|
|
{
|
|
"epoch": 9.78,
|
|
"learning_rate": 5.883311251294044e-07,
|
|
"loss": 1.1695,
|
|
"step": 31450
|
|
},
|
|
{
|
|
"epoch": 9.79,
|
|
"learning_rate": 5.716952848029144e-07,
|
|
"loss": 1.1375,
|
|
"step": 31460
|
|
},
|
|
{
|
|
"epoch": 9.79,
|
|
"learning_rate": 5.552977607508614e-07,
|
|
"loss": 1.1142,
|
|
"step": 31470
|
|
},
|
|
{
|
|
"epoch": 9.79,
|
|
"learning_rate": 5.391385686401851e-07,
|
|
"loss": 1.1214,
|
|
"step": 31480
|
|
},
|
|
{
|
|
"epoch": 9.8,
|
|
"learning_rate": 5.232177239102298e-07,
|
|
"loss": 1.1413,
|
|
"step": 31490
|
|
},
|
|
{
|
|
"epoch": 9.8,
|
|
"learning_rate": 5.075352417725498e-07,
|
|
"loss": 1.092,
|
|
"step": 31500
|
|
},
|
|
{
|
|
"epoch": 9.8,
|
|
"learning_rate": 4.920911372109648e-07,
|
|
"loss": 1.1093,
|
|
"step": 31510
|
|
},
|
|
{
|
|
"epoch": 9.81,
|
|
"learning_rate": 4.768854249815602e-07,
|
|
"loss": 1.1527,
|
|
"step": 31520
|
|
},
|
|
{
|
|
"epoch": 9.81,
|
|
"learning_rate": 4.619181196126587e-07,
|
|
"loss": 1.133,
|
|
"step": 31530
|
|
},
|
|
{
|
|
"epoch": 9.81,
|
|
"learning_rate": 4.471892354047102e-07,
|
|
"loss": 1.2003,
|
|
"step": 31540
|
|
},
|
|
{
|
|
"epoch": 9.82,
|
|
"learning_rate": 4.3269878643048543e-07,
|
|
"loss": 1.1356,
|
|
"step": 31550
|
|
},
|
|
{
|
|
"epoch": 9.82,
|
|
"learning_rate": 4.1844678653482627e-07,
|
|
"loss": 1.1493,
|
|
"step": 31560
|
|
},
|
|
{
|
|
"epoch": 9.82,
|
|
"learning_rate": 4.044332493348679e-07,
|
|
"loss": 1.3289,
|
|
"step": 31570
|
|
},
|
|
{
|
|
"epoch": 9.82,
|
|
"learning_rate": 3.906581882198168e-07,
|
|
"loss": 1.0953,
|
|
"step": 31580
|
|
},
|
|
{
|
|
"epoch": 9.83,
|
|
"learning_rate": 3.771216163510338e-07,
|
|
"loss": 1.1691,
|
|
"step": 31590
|
|
},
|
|
{
|
|
"epoch": 9.83,
|
|
"learning_rate": 3.6382354666206206e-07,
|
|
"loss": 1.2197,
|
|
"step": 31600
|
|
},
|
|
{
|
|
"epoch": 9.83,
|
|
"learning_rate": 3.5076399185854367e-07,
|
|
"loss": 1.1742,
|
|
"step": 31610
|
|
},
|
|
{
|
|
"epoch": 9.84,
|
|
"learning_rate": 3.379429644182197e-07,
|
|
"loss": 1.1238,
|
|
"step": 31620
|
|
},
|
|
{
|
|
"epoch": 9.84,
|
|
"learning_rate": 3.253604765909579e-07,
|
|
"loss": 1.2155,
|
|
"step": 31630
|
|
},
|
|
{
|
|
"epoch": 9.84,
|
|
"learning_rate": 3.1301654039866953e-07,
|
|
"loss": 1.1554,
|
|
"step": 31640
|
|
},
|
|
{
|
|
"epoch": 9.85,
|
|
"learning_rate": 3.009111676353926e-07,
|
|
"loss": 1.0947,
|
|
"step": 31650
|
|
},
|
|
{
|
|
"epoch": 9.85,
|
|
"learning_rate": 2.8904436986718076e-07,
|
|
"loss": 1.1241,
|
|
"step": 31660
|
|
},
|
|
{
|
|
"epoch": 9.85,
|
|
"learning_rate": 2.774161584321866e-07,
|
|
"loss": 1.2505,
|
|
"step": 31670
|
|
},
|
|
{
|
|
"epoch": 9.86,
|
|
"learning_rate": 2.660265444405785e-07,
|
|
"loss": 1.2546,
|
|
"step": 31680
|
|
},
|
|
{
|
|
"epoch": 9.86,
|
|
"learning_rate": 2.548755387745405e-07,
|
|
"loss": 1.2128,
|
|
"step": 31690
|
|
},
|
|
{
|
|
"epoch": 9.86,
|
|
"learning_rate": 2.439631520883556e-07,
|
|
"loss": 1.0928,
|
|
"step": 31700
|
|
},
|
|
{
|
|
"epoch": 9.87,
|
|
"learning_rate": 2.3328939480821154e-07,
|
|
"loss": 1.2041,
|
|
"step": 31710
|
|
},
|
|
{
|
|
"epoch": 9.87,
|
|
"learning_rate": 2.2285427713236718e-07,
|
|
"loss": 1.1355,
|
|
"step": 31720
|
|
},
|
|
{
|
|
"epoch": 9.87,
|
|
"learning_rate": 2.1265780903106935e-07,
|
|
"loss": 1.1673,
|
|
"step": 31730
|
|
},
|
|
{
|
|
"epoch": 9.87,
|
|
"learning_rate": 2.0270000024652514e-07,
|
|
"loss": 1.1581,
|
|
"step": 31740
|
|
},
|
|
{
|
|
"epoch": 9.88,
|
|
"learning_rate": 1.929808602929295e-07,
|
|
"loss": 1.2051,
|
|
"step": 31750
|
|
},
|
|
{
|
|
"epoch": 9.88,
|
|
"learning_rate": 1.8350039845640987e-07,
|
|
"loss": 1.2173,
|
|
"step": 31760
|
|
},
|
|
{
|
|
"epoch": 9.88,
|
|
"learning_rate": 1.7425862379508162e-07,
|
|
"loss": 1.2161,
|
|
"step": 31770
|
|
},
|
|
{
|
|
"epoch": 9.89,
|
|
"learning_rate": 1.652555451390203e-07,
|
|
"loss": 1.2893,
|
|
"step": 31780
|
|
},
|
|
{
|
|
"epoch": 9.89,
|
|
"learning_rate": 1.5649117109020616e-07,
|
|
"loss": 1.1465,
|
|
"step": 31790
|
|
},
|
|
{
|
|
"epoch": 9.89,
|
|
"learning_rate": 1.4796551002252413e-07,
|
|
"loss": 1.058,
|
|
"step": 31800
|
|
},
|
|
{
|
|
"epoch": 9.9,
|
|
"learning_rate": 1.3967857008187478e-07,
|
|
"loss": 1.1995,
|
|
"step": 31810
|
|
},
|
|
{
|
|
"epoch": 9.9,
|
|
"learning_rate": 1.3163035918600796e-07,
|
|
"loss": 1.1405,
|
|
"step": 31820
|
|
},
|
|
{
|
|
"epoch": 9.9,
|
|
"learning_rate": 1.2382088502455036e-07,
|
|
"loss": 1.2344,
|
|
"step": 31830
|
|
},
|
|
{
|
|
"epoch": 9.91,
|
|
"learning_rate": 1.1625015505908886e-07,
|
|
"loss": 1.0996,
|
|
"step": 31840
|
|
},
|
|
{
|
|
"epoch": 9.91,
|
|
"learning_rate": 1.0891817652305957e-07,
|
|
"loss": 1.0903,
|
|
"step": 31850
|
|
},
|
|
{
|
|
"epoch": 9.91,
|
|
"learning_rate": 1.0182495642180323e-07,
|
|
"loss": 1.1789,
|
|
"step": 31860
|
|
},
|
|
{
|
|
"epoch": 9.92,
|
|
"learning_rate": 9.497050153256526e-08,
|
|
"loss": 1.1783,
|
|
"step": 31870
|
|
},
|
|
{
|
|
"epoch": 9.92,
|
|
"learning_rate": 8.835481840441251e-08,
|
|
"loss": 1.1084,
|
|
"step": 31880
|
|
},
|
|
{
|
|
"epoch": 9.92,
|
|
"learning_rate": 8.19779133583165e-08,
|
|
"loss": 1.1603,
|
|
"step": 31890
|
|
},
|
|
{
|
|
"epoch": 9.92,
|
|
"learning_rate": 7.583979248707019e-08,
|
|
"loss": 1.2076,
|
|
"step": 31900
|
|
},
|
|
{
|
|
"epoch": 9.93,
|
|
"learning_rate": 6.99404616553434e-08,
|
|
"loss": 1.1093,
|
|
"step": 31910
|
|
},
|
|
{
|
|
"epoch": 9.93,
|
|
"learning_rate": 6.427992649965519e-08,
|
|
"loss": 1.2011,
|
|
"step": 31920
|
|
},
|
|
{
|
|
"epoch": 9.93,
|
|
"learning_rate": 5.8858192428373756e-08,
|
|
"loss": 1.2571,
|
|
"step": 31930
|
|
},
|
|
{
|
|
"epoch": 9.94,
|
|
"learning_rate": 5.36752646216887e-08,
|
|
"loss": 1.0986,
|
|
"step": 31940
|
|
},
|
|
{
|
|
"epoch": 9.94,
|
|
"learning_rate": 4.873114803161105e-08,
|
|
"loss": 1.219,
|
|
"step": 31950
|
|
},
|
|
{
|
|
"epoch": 9.94,
|
|
"learning_rate": 4.402584738202875e-08,
|
|
"loss": 1.207,
|
|
"step": 31960
|
|
},
|
|
{
|
|
"epoch": 9.95,
|
|
"learning_rate": 3.955936716859565e-08,
|
|
"loss": 1.2416,
|
|
"step": 31970
|
|
},
|
|
{
|
|
"epoch": 9.95,
|
|
"learning_rate": 3.533171165881477e-08,
|
|
"loss": 1.161,
|
|
"step": 31980
|
|
},
|
|
{
|
|
"epoch": 9.95,
|
|
"learning_rate": 3.134288489203829e-08,
|
|
"loss": 1.266,
|
|
"step": 31990
|
|
},
|
|
{
|
|
"epoch": 9.96,
|
|
"learning_rate": 2.7592890679328797e-08,
|
|
"loss": 1.2322,
|
|
"step": 32000
|
|
},
|
|
{
|
|
"epoch": 9.96,
|
|
"learning_rate": 2.408173260365354e-08,
|
|
"loss": 1.1172,
|
|
"step": 32010
|
|
},
|
|
{
|
|
"epoch": 9.96,
|
|
"learning_rate": 2.0809414019745676e-08,
|
|
"loss": 1.1202,
|
|
"step": 32020
|
|
},
|
|
{
|
|
"epoch": 9.96,
|
|
"learning_rate": 1.7775938054132023e-08,
|
|
"loss": 1.1035,
|
|
"step": 32030
|
|
},
|
|
{
|
|
"epoch": 9.97,
|
|
"learning_rate": 1.4981307605133055e-08,
|
|
"loss": 1.2232,
|
|
"step": 32040
|
|
},
|
|
{
|
|
"epoch": 9.97,
|
|
"learning_rate": 1.2425525342918409e-08,
|
|
"loss": 1.2755,
|
|
"step": 32050
|
|
},
|
|
{
|
|
"epoch": 9.97,
|
|
"learning_rate": 1.0108593709395874e-08,
|
|
"loss": 1.1698,
|
|
"step": 32060
|
|
},
|
|
{
|
|
"epoch": 9.98,
|
|
"learning_rate": 8.030514918266896e-09,
|
|
"loss": 1.0476,
|
|
"step": 32070
|
|
},
|
|
{
|
|
"epoch": 9.98,
|
|
"learning_rate": 6.19129095505433e-09,
|
|
"loss": 1.2533,
|
|
"step": 32080
|
|
},
|
|
{
|
|
"epoch": 9.98,
|
|
"learning_rate": 4.590923576991424e-09,
|
|
"loss": 1.2108,
|
|
"step": 32090
|
|
},
|
|
{
|
|
"epoch": 9.99,
|
|
"learning_rate": 3.229414313216106e-09,
|
|
"loss": 1.0883,
|
|
"step": 32100
|
|
},
|
|
{
|
|
"epoch": 9.99,
|
|
"learning_rate": 2.1067644645489382e-09,
|
|
"loss": 1.2424,
|
|
"step": 32110
|
|
},
|
|
{
|
|
"epoch": 9.99,
|
|
"learning_rate": 1.2229751036041402e-09,
|
|
"loss": 1.0899,
|
|
"step": 32120
|
|
},
|
|
{
|
|
"epoch": 10.0,
|
|
"learning_rate": 5.780470748451006e-10,
|
|
"loss": 1.2211,
|
|
"step": 32130
|
|
},
|
|
{
|
|
"epoch": 10.0,
|
|
"learning_rate": 1.7198099444559744e-10,
|
|
"loss": 1.1344,
|
|
"step": 32140
|
|
},
|
|
{
|
|
"epoch": 10.0,
|
|
"step": 32140,
|
|
"total_flos": 3.665445991098163e+18,
|
|
"train_loss": 1.4525756712203153,
|
|
"train_runtime": 38277.4982,
|
|
"train_samples_per_second": 13.435,
|
|
"train_steps_per_second": 0.84
|
|
}
|
|
],
|
|
"max_steps": 32140,
|
|
"num_train_epochs": 10,
|
|
"total_flos": 3.665445991098163e+18,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|