DeepLeffen-TSM_Leffen / trainer_state.json
Frikallo's picture
End of training
d8cfa72
raw
history blame
17.6 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"global_step": 711,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 0.0001362351617440225,
"loss": 4.199,
"step": 5
},
{
"epoch": 0.01,
"learning_rate": 0.000135270323488045,
"loss": 4.6198,
"step": 10
},
{
"epoch": 0.02,
"learning_rate": 0.0001343054852320675,
"loss": 4.3219,
"step": 15
},
{
"epoch": 0.03,
"learning_rate": 0.00013334064697609002,
"loss": 4.0312,
"step": 20
},
{
"epoch": 0.04,
"learning_rate": 0.00013237580872011253,
"loss": 4.3119,
"step": 25
},
{
"epoch": 0.04,
"learning_rate": 0.00013141097046413501,
"loss": 3.9227,
"step": 30
},
{
"epoch": 0.05,
"learning_rate": 0.00013044613220815753,
"loss": 4.1775,
"step": 35
},
{
"epoch": 0.06,
"learning_rate": 0.00012948129395218,
"loss": 4.3598,
"step": 40
},
{
"epoch": 0.06,
"learning_rate": 0.00012851645569620252,
"loss": 3.7573,
"step": 45
},
{
"epoch": 0.07,
"learning_rate": 0.00012755161744022503,
"loss": 3.011,
"step": 50
},
{
"epoch": 0.08,
"learning_rate": 0.00012658677918424754,
"loss": 3.3466,
"step": 55
},
{
"epoch": 0.08,
"learning_rate": 0.00012562194092827005,
"loss": 3.3757,
"step": 60
},
{
"epoch": 0.09,
"learning_rate": 0.00012465710267229254,
"loss": 3.5864,
"step": 65
},
{
"epoch": 0.1,
"learning_rate": 0.00012369226441631505,
"loss": 3.8094,
"step": 70
},
{
"epoch": 0.11,
"learning_rate": 0.00012272742616033753,
"loss": 3.2495,
"step": 75
},
{
"epoch": 0.11,
"learning_rate": 0.00012176258790436006,
"loss": 3.4377,
"step": 80
},
{
"epoch": 0.12,
"learning_rate": 0.00012079774964838257,
"loss": 3.2708,
"step": 85
},
{
"epoch": 0.13,
"learning_rate": 0.00011983291139240507,
"loss": 3.7736,
"step": 90
},
{
"epoch": 0.13,
"learning_rate": 0.00011886807313642758,
"loss": 2.9204,
"step": 95
},
{
"epoch": 0.14,
"learning_rate": 0.00011790323488045006,
"loss": 3.4391,
"step": 100
},
{
"epoch": 0.15,
"learning_rate": 0.00011693839662447257,
"loss": 2.9807,
"step": 105
},
{
"epoch": 0.15,
"learning_rate": 0.00011597355836849507,
"loss": 3.1689,
"step": 110
},
{
"epoch": 0.16,
"learning_rate": 0.00011500872011251758,
"loss": 3.3144,
"step": 115
},
{
"epoch": 0.17,
"learning_rate": 0.00011404388185654008,
"loss": 3.5561,
"step": 120
},
{
"epoch": 0.18,
"learning_rate": 0.00011307904360056259,
"loss": 3.6431,
"step": 125
},
{
"epoch": 0.18,
"learning_rate": 0.0001121142053445851,
"loss": 3.8902,
"step": 130
},
{
"epoch": 0.19,
"learning_rate": 0.00011114936708860759,
"loss": 3.0992,
"step": 135
},
{
"epoch": 0.2,
"learning_rate": 0.0001101845288326301,
"loss": 2.7877,
"step": 140
},
{
"epoch": 0.2,
"learning_rate": 0.0001092196905766526,
"loss": 3.9218,
"step": 145
},
{
"epoch": 0.21,
"learning_rate": 0.00010825485232067511,
"loss": 3.5637,
"step": 150
},
{
"epoch": 0.22,
"learning_rate": 0.0001072900140646976,
"loss": 3.1522,
"step": 155
},
{
"epoch": 0.23,
"learning_rate": 0.00010632517580872012,
"loss": 3.4419,
"step": 160
},
{
"epoch": 0.23,
"learning_rate": 0.00010536033755274261,
"loss": 3.0554,
"step": 165
},
{
"epoch": 0.24,
"learning_rate": 0.00010439549929676513,
"loss": 3.4052,
"step": 170
},
{
"epoch": 0.25,
"learning_rate": 0.00010343066104078762,
"loss": 2.9866,
"step": 175
},
{
"epoch": 0.25,
"learning_rate": 0.00010246582278481012,
"loss": 2.5035,
"step": 180
},
{
"epoch": 0.26,
"learning_rate": 0.00010150098452883263,
"loss": 3.7511,
"step": 185
},
{
"epoch": 0.27,
"learning_rate": 0.00010053614627285513,
"loss": 2.7323,
"step": 190
},
{
"epoch": 0.27,
"learning_rate": 9.957130801687764e-05,
"loss": 2.8699,
"step": 195
},
{
"epoch": 0.28,
"learning_rate": 9.860646976090014e-05,
"loss": 3.1837,
"step": 200
},
{
"epoch": 0.29,
"learning_rate": 9.764163150492265e-05,
"loss": 1.8443,
"step": 205
},
{
"epoch": 0.3,
"learning_rate": 9.667679324894516e-05,
"loss": 3.3378,
"step": 210
},
{
"epoch": 0.3,
"learning_rate": 9.571195499296765e-05,
"loss": 3.3139,
"step": 215
},
{
"epoch": 0.31,
"learning_rate": 9.474711673699016e-05,
"loss": 2.715,
"step": 220
},
{
"epoch": 0.32,
"learning_rate": 9.378227848101265e-05,
"loss": 2.2078,
"step": 225
},
{
"epoch": 0.32,
"learning_rate": 9.281744022503517e-05,
"loss": 3.6404,
"step": 230
},
{
"epoch": 0.33,
"learning_rate": 9.185260196905766e-05,
"loss": 2.7474,
"step": 235
},
{
"epoch": 0.34,
"learning_rate": 9.088776371308017e-05,
"loss": 2.7442,
"step": 240
},
{
"epoch": 0.34,
"learning_rate": 8.992292545710267e-05,
"loss": 2.7549,
"step": 245
},
{
"epoch": 0.35,
"learning_rate": 8.895808720112517e-05,
"loss": 3.1178,
"step": 250
},
{
"epoch": 0.36,
"learning_rate": 8.799324894514768e-05,
"loss": 3.5897,
"step": 255
},
{
"epoch": 0.37,
"learning_rate": 8.702841068917018e-05,
"loss": 3.613,
"step": 260
},
{
"epoch": 0.37,
"learning_rate": 8.606357243319269e-05,
"loss": 3.0409,
"step": 265
},
{
"epoch": 0.38,
"learning_rate": 8.509873417721519e-05,
"loss": 2.6512,
"step": 270
},
{
"epoch": 0.39,
"learning_rate": 8.41338959212377e-05,
"loss": 2.6139,
"step": 275
},
{
"epoch": 0.39,
"learning_rate": 8.31690576652602e-05,
"loss": 3.4506,
"step": 280
},
{
"epoch": 0.4,
"learning_rate": 8.220421940928271e-05,
"loss": 2.5725,
"step": 285
},
{
"epoch": 0.41,
"learning_rate": 8.123938115330519e-05,
"loss": 3.4395,
"step": 290
},
{
"epoch": 0.41,
"learning_rate": 8.02745428973277e-05,
"loss": 2.5777,
"step": 295
},
{
"epoch": 0.42,
"learning_rate": 7.930970464135022e-05,
"loss": 2.9152,
"step": 300
},
{
"epoch": 0.43,
"learning_rate": 7.834486638537271e-05,
"loss": 3.9138,
"step": 305
},
{
"epoch": 0.44,
"learning_rate": 7.738002812939522e-05,
"loss": 3.4747,
"step": 310
},
{
"epoch": 0.44,
"learning_rate": 7.641518987341772e-05,
"loss": 2.0438,
"step": 315
},
{
"epoch": 0.45,
"learning_rate": 7.545035161744023e-05,
"loss": 3.9241,
"step": 320
},
{
"epoch": 0.46,
"learning_rate": 7.448551336146272e-05,
"loss": 2.4667,
"step": 325
},
{
"epoch": 0.46,
"learning_rate": 7.352067510548523e-05,
"loss": 3.0487,
"step": 330
},
{
"epoch": 0.47,
"learning_rate": 7.255583684950774e-05,
"loss": 2.5293,
"step": 335
},
{
"epoch": 0.48,
"learning_rate": 7.159099859353024e-05,
"loss": 2.4645,
"step": 340
},
{
"epoch": 0.49,
"learning_rate": 7.062616033755275e-05,
"loss": 2.3263,
"step": 345
},
{
"epoch": 0.49,
"learning_rate": 6.966132208157525e-05,
"loss": 3.305,
"step": 350
},
{
"epoch": 0.5,
"learning_rate": 6.869648382559776e-05,
"loss": 2.4653,
"step": 355
},
{
"epoch": 0.51,
"learning_rate": 6.773164556962026e-05,
"loss": 1.8414,
"step": 360
},
{
"epoch": 0.51,
"learning_rate": 6.676680731364275e-05,
"loss": 2.8415,
"step": 365
},
{
"epoch": 0.52,
"learning_rate": 6.580196905766526e-05,
"loss": 2.773,
"step": 370
},
{
"epoch": 0.53,
"learning_rate": 6.483713080168776e-05,
"loss": 2.7577,
"step": 375
},
{
"epoch": 0.53,
"learning_rate": 6.387229254571027e-05,
"loss": 2.6964,
"step": 380
},
{
"epoch": 0.54,
"learning_rate": 6.290745428973277e-05,
"loss": 3.8508,
"step": 385
},
{
"epoch": 0.55,
"learning_rate": 6.194261603375527e-05,
"loss": 1.7801,
"step": 390
},
{
"epoch": 0.56,
"learning_rate": 6.097777777777777e-05,
"loss": 2.3334,
"step": 395
},
{
"epoch": 0.56,
"learning_rate": 6.0012939521800284e-05,
"loss": 1.3051,
"step": 400
},
{
"epoch": 0.57,
"learning_rate": 5.904810126582279e-05,
"loss": 2.7872,
"step": 405
},
{
"epoch": 0.58,
"learning_rate": 5.808326300984529e-05,
"loss": 2.2091,
"step": 410
},
{
"epoch": 0.58,
"learning_rate": 5.711842475386779e-05,
"loss": 2.1466,
"step": 415
},
{
"epoch": 0.59,
"learning_rate": 5.6153586497890295e-05,
"loss": 2.7545,
"step": 420
},
{
"epoch": 0.6,
"learning_rate": 5.51887482419128e-05,
"loss": 2.5816,
"step": 425
},
{
"epoch": 0.6,
"learning_rate": 5.42239099859353e-05,
"loss": 2.1573,
"step": 430
},
{
"epoch": 0.61,
"learning_rate": 5.32590717299578e-05,
"loss": 2.6483,
"step": 435
},
{
"epoch": 0.62,
"learning_rate": 5.229423347398031e-05,
"loss": 2.1141,
"step": 440
},
{
"epoch": 0.63,
"learning_rate": 5.132939521800282e-05,
"loss": 1.6248,
"step": 445
},
{
"epoch": 0.63,
"learning_rate": 5.0364556962025315e-05,
"loss": 2.6418,
"step": 450
},
{
"epoch": 0.64,
"learning_rate": 4.939971870604782e-05,
"loss": 2.7324,
"step": 455
},
{
"epoch": 0.65,
"learning_rate": 4.8434880450070324e-05,
"loss": 2.661,
"step": 460
},
{
"epoch": 0.65,
"learning_rate": 4.747004219409283e-05,
"loss": 2.1676,
"step": 465
},
{
"epoch": 0.66,
"learning_rate": 4.6505203938115326e-05,
"loss": 2.0641,
"step": 470
},
{
"epoch": 0.67,
"learning_rate": 4.554036568213783e-05,
"loss": 2.6073,
"step": 475
},
{
"epoch": 0.68,
"learning_rate": 4.4575527426160335e-05,
"loss": 3.2055,
"step": 480
},
{
"epoch": 0.68,
"learning_rate": 4.361068917018285e-05,
"loss": 1.5895,
"step": 485
},
{
"epoch": 0.69,
"learning_rate": 4.2645850914205344e-05,
"loss": 3.1821,
"step": 490
},
{
"epoch": 0.7,
"learning_rate": 4.168101265822785e-05,
"loss": 1.7399,
"step": 495
},
{
"epoch": 0.7,
"learning_rate": 4.071617440225035e-05,
"loss": 3.1152,
"step": 500
},
{
"epoch": 0.71,
"learning_rate": 3.975133614627286e-05,
"loss": 1.5188,
"step": 505
},
{
"epoch": 0.72,
"learning_rate": 3.8786497890295355e-05,
"loss": 2.0804,
"step": 510
},
{
"epoch": 0.72,
"learning_rate": 3.782165963431786e-05,
"loss": 2.0614,
"step": 515
},
{
"epoch": 0.73,
"learning_rate": 3.6856821378340364e-05,
"loss": 3.1566,
"step": 520
},
{
"epoch": 0.74,
"learning_rate": 3.5891983122362876e-05,
"loss": 2.0499,
"step": 525
},
{
"epoch": 0.75,
"learning_rate": 3.492714486638537e-05,
"loss": 2.0387,
"step": 530
},
{
"epoch": 0.75,
"learning_rate": 3.396230661040788e-05,
"loss": 2.0698,
"step": 535
},
{
"epoch": 0.76,
"learning_rate": 3.299746835443038e-05,
"loss": 2.5658,
"step": 540
},
{
"epoch": 0.77,
"learning_rate": 3.203263009845288e-05,
"loss": 1.5012,
"step": 545
},
{
"epoch": 0.77,
"learning_rate": 3.1067791842475384e-05,
"loss": 1.978,
"step": 550
},
{
"epoch": 0.78,
"learning_rate": 3.0102953586497892e-05,
"loss": 3.0437,
"step": 555
},
{
"epoch": 0.79,
"learning_rate": 2.9138115330520393e-05,
"loss": 1.9812,
"step": 560
},
{
"epoch": 0.79,
"learning_rate": 2.8173277074542898e-05,
"loss": 1.9784,
"step": 565
},
{
"epoch": 0.8,
"learning_rate": 2.72084388185654e-05,
"loss": 1.9855,
"step": 570
},
{
"epoch": 0.81,
"learning_rate": 2.6243600562587903e-05,
"loss": 2.5896,
"step": 575
},
{
"epoch": 0.82,
"learning_rate": 2.5278762306610408e-05,
"loss": 2.4775,
"step": 580
},
{
"epoch": 0.82,
"learning_rate": 2.4313924050632912e-05,
"loss": 2.4693,
"step": 585
},
{
"epoch": 0.83,
"learning_rate": 2.3349085794655413e-05,
"loss": 1.9928,
"step": 590
},
{
"epoch": 0.84,
"learning_rate": 2.2384247538677918e-05,
"loss": 3.0532,
"step": 595
},
{
"epoch": 0.84,
"learning_rate": 2.1419409282700422e-05,
"loss": 2.4624,
"step": 600
},
{
"epoch": 0.85,
"learning_rate": 2.0454571026722927e-05,
"loss": 1.9622,
"step": 605
},
{
"epoch": 0.86,
"learning_rate": 1.9489732770745428e-05,
"loss": 1.9914,
"step": 610
},
{
"epoch": 0.86,
"learning_rate": 1.8524894514767932e-05,
"loss": 1.3641,
"step": 615
},
{
"epoch": 0.87,
"learning_rate": 1.7560056258790437e-05,
"loss": 2.8009,
"step": 620
},
{
"epoch": 0.88,
"learning_rate": 1.659521800281294e-05,
"loss": 3.0455,
"step": 625
},
{
"epoch": 0.89,
"learning_rate": 1.5630379746835442e-05,
"loss": 2.418,
"step": 630
},
{
"epoch": 0.89,
"learning_rate": 1.4665541490857947e-05,
"loss": 3.0566,
"step": 635
},
{
"epoch": 0.9,
"learning_rate": 1.370070323488045e-05,
"loss": 1.9132,
"step": 640
},
{
"epoch": 0.91,
"learning_rate": 1.2735864978902954e-05,
"loss": 2.4978,
"step": 645
},
{
"epoch": 0.91,
"learning_rate": 1.1771026722925457e-05,
"loss": 2.6473,
"step": 650
},
{
"epoch": 0.92,
"learning_rate": 1.0806188466947961e-05,
"loss": 2.4882,
"step": 655
},
{
"epoch": 0.93,
"learning_rate": 9.841350210970464e-06,
"loss": 3.1199,
"step": 660
},
{
"epoch": 0.94,
"learning_rate": 8.876511954992969e-06,
"loss": 3.0693,
"step": 665
},
{
"epoch": 0.94,
"learning_rate": 7.911673699015471e-06,
"loss": 2.4433,
"step": 670
},
{
"epoch": 0.95,
"learning_rate": 6.946835443037974e-06,
"loss": 2.4399,
"step": 675
},
{
"epoch": 0.96,
"learning_rate": 5.981997187060478e-06,
"loss": 2.5172,
"step": 680
},
{
"epoch": 0.96,
"learning_rate": 5.0171589310829815e-06,
"loss": 3.0587,
"step": 685
},
{
"epoch": 0.97,
"learning_rate": 4.052320675105485e-06,
"loss": 3.6936,
"step": 690
},
{
"epoch": 0.98,
"learning_rate": 3.0874824191279887e-06,
"loss": 1.8324,
"step": 695
},
{
"epoch": 0.98,
"learning_rate": 2.1226441631504924e-06,
"loss": 1.9274,
"step": 700
},
{
"epoch": 0.99,
"learning_rate": 1.1578059071729958e-06,
"loss": 2.505,
"step": 705
},
{
"epoch": 1.0,
"learning_rate": 1.929676511954993e-07,
"loss": 1.8712,
"step": 710
},
{
"epoch": 1.0,
"step": 711,
"total_flos": 371557269504000.0,
"train_loss": 2.8279777153299497,
"train_runtime": 196.8346,
"train_samples_per_second": 3.612,
"train_steps_per_second": 3.612
}
],
"max_steps": 711,
"num_train_epochs": 1,
"total_flos": 371557269504000.0,
"trial_name": null,
"trial_params": null
}