Poro-34B-chat / trainer_state.json
jonabur
update chat version
5da6497
raw
history blame
No virus
43.5 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 500,
"global_step": 1746,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 1.142857142857143e-07,
"loss": 2.7168,
"step": 1
},
{
"epoch": 0.01,
"learning_rate": 5.714285714285715e-07,
"loss": 2.5728,
"step": 5
},
{
"epoch": 0.02,
"learning_rate": 1.142857142857143e-06,
"loss": 2.5422,
"step": 10
},
{
"epoch": 0.03,
"learning_rate": 1.7142857142857145e-06,
"loss": 2.3792,
"step": 15
},
{
"epoch": 0.03,
"learning_rate": 2.285714285714286e-06,
"loss": 2.2176,
"step": 20
},
{
"epoch": 0.04,
"learning_rate": 2.8571428571428573e-06,
"loss": 1.9282,
"step": 25
},
{
"epoch": 0.05,
"learning_rate": 3.428571428571429e-06,
"loss": 1.7601,
"step": 30
},
{
"epoch": 0.06,
"learning_rate": 4.000000000000001e-06,
"loss": 1.6887,
"step": 35
},
{
"epoch": 0.07,
"learning_rate": 4.571428571428572e-06,
"loss": 1.6597,
"step": 40
},
{
"epoch": 0.08,
"learning_rate": 5.142857142857142e-06,
"loss": 1.5152,
"step": 45
},
{
"epoch": 0.09,
"learning_rate": 5.7142857142857145e-06,
"loss": 1.5448,
"step": 50
},
{
"epoch": 0.09,
"learning_rate": 6.285714285714286e-06,
"loss": 1.5993,
"step": 55
},
{
"epoch": 0.1,
"learning_rate": 6.857142857142858e-06,
"loss": 1.5941,
"step": 60
},
{
"epoch": 0.11,
"learning_rate": 7.428571428571429e-06,
"loss": 1.5832,
"step": 65
},
{
"epoch": 0.12,
"learning_rate": 8.000000000000001e-06,
"loss": 1.5369,
"step": 70
},
{
"epoch": 0.13,
"learning_rate": 8.571428571428571e-06,
"loss": 1.4847,
"step": 75
},
{
"epoch": 0.14,
"learning_rate": 9.142857142857144e-06,
"loss": 1.544,
"step": 80
},
{
"epoch": 0.15,
"learning_rate": 9.714285714285715e-06,
"loss": 1.5631,
"step": 85
},
{
"epoch": 0.15,
"learning_rate": 1.0285714285714285e-05,
"loss": 1.5124,
"step": 90
},
{
"epoch": 0.16,
"learning_rate": 1.0857142857142858e-05,
"loss": 1.4762,
"step": 95
},
{
"epoch": 0.17,
"learning_rate": 1.1428571428571429e-05,
"loss": 1.5304,
"step": 100
},
{
"epoch": 0.18,
"learning_rate": 1.2e-05,
"loss": 1.5102,
"step": 105
},
{
"epoch": 0.19,
"learning_rate": 1.2571428571428572e-05,
"loss": 1.477,
"step": 110
},
{
"epoch": 0.2,
"learning_rate": 1.3142857142857145e-05,
"loss": 1.5082,
"step": 115
},
{
"epoch": 0.21,
"learning_rate": 1.3714285714285716e-05,
"loss": 1.4684,
"step": 120
},
{
"epoch": 0.21,
"learning_rate": 1.4285714285714287e-05,
"loss": 1.5267,
"step": 125
},
{
"epoch": 0.22,
"learning_rate": 1.4857142857142858e-05,
"loss": 1.4454,
"step": 130
},
{
"epoch": 0.23,
"learning_rate": 1.542857142857143e-05,
"loss": 1.4974,
"step": 135
},
{
"epoch": 0.24,
"learning_rate": 1.6000000000000003e-05,
"loss": 1.5087,
"step": 140
},
{
"epoch": 0.25,
"learning_rate": 1.6571428571428574e-05,
"loss": 1.5172,
"step": 145
},
{
"epoch": 0.26,
"learning_rate": 1.7142857142857142e-05,
"loss": 1.5034,
"step": 150
},
{
"epoch": 0.27,
"learning_rate": 1.7714285714285717e-05,
"loss": 1.4841,
"step": 155
},
{
"epoch": 0.27,
"learning_rate": 1.8285714285714288e-05,
"loss": 1.5138,
"step": 160
},
{
"epoch": 0.28,
"learning_rate": 1.885714285714286e-05,
"loss": 1.5664,
"step": 165
},
{
"epoch": 0.29,
"learning_rate": 1.942857142857143e-05,
"loss": 1.5134,
"step": 170
},
{
"epoch": 0.3,
"learning_rate": 2e-05,
"loss": 1.5214,
"step": 175
},
{
"epoch": 0.31,
"learning_rate": 1.9999500133801672e-05,
"loss": 1.502,
"step": 180
},
{
"epoch": 0.32,
"learning_rate": 1.9998000585179915e-05,
"loss": 1.4694,
"step": 185
},
{
"epoch": 0.33,
"learning_rate": 1.9995501504049474e-05,
"loss": 1.5153,
"step": 190
},
{
"epoch": 0.34,
"learning_rate": 1.9992003140251582e-05,
"loss": 1.5056,
"step": 195
},
{
"epoch": 0.34,
"learning_rate": 1.9987505843529004e-05,
"loss": 1.4324,
"step": 200
},
{
"epoch": 0.35,
"learning_rate": 1.998201006349106e-05,
"loss": 1.4889,
"step": 205
},
{
"epoch": 0.36,
"learning_rate": 1.997551634956868e-05,
"loss": 1.5285,
"step": 210
},
{
"epoch": 0.37,
"learning_rate": 1.9968025350959497e-05,
"loss": 1.5191,
"step": 215
},
{
"epoch": 0.38,
"learning_rate": 1.9959537816562897e-05,
"loss": 1.5196,
"step": 220
},
{
"epoch": 0.39,
"learning_rate": 1.9950054594905196e-05,
"loss": 1.5304,
"step": 225
},
{
"epoch": 0.4,
"learning_rate": 1.9939576634054782e-05,
"loss": 1.4943,
"step": 230
},
{
"epoch": 0.4,
"learning_rate": 1.992810498152735e-05,
"loss": 1.5335,
"step": 235
},
{
"epoch": 0.41,
"learning_rate": 1.9915640784181163e-05,
"loss": 1.4391,
"step": 240
},
{
"epoch": 0.42,
"learning_rate": 1.990218528810242e-05,
"loss": 1.494,
"step": 245
},
{
"epoch": 0.43,
"learning_rate": 1.988773983848064e-05,
"loss": 1.4153,
"step": 250
},
{
"epoch": 0.44,
"learning_rate": 1.9872305879474234e-05,
"loss": 1.4412,
"step": 255
},
{
"epoch": 0.45,
"learning_rate": 1.9855884954066077e-05,
"loss": 1.4328,
"step": 260
},
{
"epoch": 0.46,
"learning_rate": 1.983847870390928e-05,
"loss": 1.4412,
"step": 265
},
{
"epoch": 0.46,
"learning_rate": 1.9820088869163066e-05,
"loss": 1.4981,
"step": 270
},
{
"epoch": 0.47,
"learning_rate": 1.9800717288318792e-05,
"loss": 1.4064,
"step": 275
},
{
"epoch": 0.48,
"learning_rate": 1.9780365898016147e-05,
"loss": 1.4006,
"step": 280
},
{
"epoch": 0.49,
"learning_rate": 1.9759036732849552e-05,
"loss": 1.4635,
"step": 285
},
{
"epoch": 0.5,
"learning_rate": 1.9736731925164755e-05,
"loss": 1.4569,
"step": 290
},
{
"epoch": 0.51,
"learning_rate": 1.971345370484563e-05,
"loss": 1.5035,
"step": 295
},
{
"epoch": 0.52,
"learning_rate": 1.9689204399091285e-05,
"loss": 1.3976,
"step": 300
},
{
"epoch": 0.52,
"learning_rate": 1.9663986432183374e-05,
"loss": 1.4406,
"step": 305
},
{
"epoch": 0.53,
"learning_rate": 1.963780232524374e-05,
"loss": 1.4725,
"step": 310
},
{
"epoch": 0.54,
"learning_rate": 1.961065469598239e-05,
"loss": 1.4824,
"step": 315
},
{
"epoch": 0.55,
"learning_rate": 1.958254625843577e-05,
"loss": 1.5003,
"step": 320
},
{
"epoch": 0.56,
"learning_rate": 1.9553479822695435e-05,
"loss": 1.4694,
"step": 325
},
{
"epoch": 0.57,
"learning_rate": 1.952345829462714e-05,
"loss": 1.481,
"step": 330
},
{
"epoch": 0.58,
"learning_rate": 1.9492484675580302e-05,
"loss": 1.4117,
"step": 335
},
{
"epoch": 0.58,
"learning_rate": 1.9460562062087963e-05,
"loss": 1.4311,
"step": 340
},
{
"epoch": 0.59,
"learning_rate": 1.942769364555721e-05,
"loss": 1.43,
"step": 345
},
{
"epoch": 0.6,
"learning_rate": 1.939388271195013e-05,
"loss": 1.5002,
"step": 350
},
{
"epoch": 0.61,
"learning_rate": 1.935913264145529e-05,
"loss": 1.4256,
"step": 355
},
{
"epoch": 0.62,
"learning_rate": 1.932344690814981e-05,
"loss": 1.4574,
"step": 360
},
{
"epoch": 0.63,
"learning_rate": 1.928682907965207e-05,
"loss": 1.4027,
"step": 365
},
{
"epoch": 0.64,
"learning_rate": 1.924928281676501e-05,
"loss": 1.3318,
"step": 370
},
{
"epoch": 0.64,
"learning_rate": 1.9210811873110164e-05,
"loss": 1.4903,
"step": 375
},
{
"epoch": 0.65,
"learning_rate": 1.9171420094752404e-05,
"loss": 1.4705,
"step": 380
},
{
"epoch": 0.66,
"learning_rate": 1.9131111419815428e-05,
"loss": 1.4515,
"step": 385
},
{
"epoch": 0.67,
"learning_rate": 1.9089889878088063e-05,
"loss": 1.3972,
"step": 390
},
{
"epoch": 0.68,
"learning_rate": 1.904775959062137e-05,
"loss": 1.4329,
"step": 395
},
{
"epoch": 0.69,
"learning_rate": 1.9004724769316682e-05,
"loss": 1.4771,
"step": 400
},
{
"epoch": 0.7,
"learning_rate": 1.8960789716504502e-05,
"loss": 1.4283,
"step": 405
},
{
"epoch": 0.7,
"learning_rate": 1.8915958824514388e-05,
"loss": 1.4044,
"step": 410
},
{
"epoch": 0.71,
"learning_rate": 1.887023657523586e-05,
"loss": 1.4577,
"step": 415
},
{
"epoch": 0.72,
"learning_rate": 1.8823627539670296e-05,
"loss": 1.4222,
"step": 420
},
{
"epoch": 0.73,
"learning_rate": 1.877613637747398e-05,
"loss": 1.4151,
"step": 425
},
{
"epoch": 0.74,
"learning_rate": 1.8727767836492256e-05,
"loss": 1.425,
"step": 430
},
{
"epoch": 0.75,
"learning_rate": 1.8678526752284857e-05,
"loss": 1.3253,
"step": 435
},
{
"epoch": 0.76,
"learning_rate": 1.8628418047642505e-05,
"loss": 1.3933,
"step": 440
},
{
"epoch": 0.76,
"learning_rate": 1.8577446732094732e-05,
"loss": 1.4658,
"step": 445
},
{
"epoch": 0.77,
"learning_rate": 1.8525617901409082e-05,
"loss": 1.4172,
"step": 450
},
{
"epoch": 0.78,
"learning_rate": 1.8472936737081673e-05,
"loss": 1.4866,
"step": 455
},
{
"epoch": 0.79,
"learning_rate": 1.841940850581917e-05,
"loss": 1.4293,
"step": 460
},
{
"epoch": 0.8,
"learning_rate": 1.8365038559012263e-05,
"loss": 1.4085,
"step": 465
},
{
"epoch": 0.81,
"learning_rate": 1.8309832332200677e-05,
"loss": 1.421,
"step": 470
},
{
"epoch": 0.82,
"learning_rate": 1.8253795344529758e-05,
"loss": 1.3329,
"step": 475
},
{
"epoch": 0.82,
"learning_rate": 1.81969331981987e-05,
"loss": 1.3832,
"step": 480
},
{
"epoch": 0.83,
"learning_rate": 1.813925157790049e-05,
"loss": 1.2692,
"step": 485
},
{
"epoch": 0.84,
"learning_rate": 1.8080756250253575e-05,
"loss": 1.4182,
"step": 490
},
{
"epoch": 0.85,
"learning_rate": 1.802145306322537e-05,
"loss": 1.3419,
"step": 495
},
{
"epoch": 0.86,
"learning_rate": 1.79613479455476e-05,
"loss": 1.356,
"step": 500
},
{
"epoch": 0.87,
"learning_rate": 1.7900446906123604e-05,
"loss": 1.3546,
"step": 505
},
{
"epoch": 0.88,
"learning_rate": 1.7838756033427585e-05,
"loss": 1.3617,
"step": 510
},
{
"epoch": 0.88,
"learning_rate": 1.7776281494895956e-05,
"loss": 1.3494,
"step": 515
},
{
"epoch": 0.89,
"learning_rate": 1.7713029536310722e-05,
"loss": 1.382,
"step": 520
},
{
"epoch": 0.9,
"learning_rate": 1.76490064811751e-05,
"loss": 1.3565,
"step": 525
},
{
"epoch": 0.91,
"learning_rate": 1.7584218730081325e-05,
"loss": 1.3842,
"step": 530
},
{
"epoch": 0.92,
"learning_rate": 1.7518672760070764e-05,
"loss": 1.369,
"step": 535
},
{
"epoch": 0.93,
"learning_rate": 1.7452375123986386e-05,
"loss": 1.3536,
"step": 540
},
{
"epoch": 0.94,
"learning_rate": 1.7385332449817655e-05,
"loss": 1.3606,
"step": 545
},
{
"epoch": 0.95,
"learning_rate": 1.73175514400379e-05,
"loss": 1.3455,
"step": 550
},
{
"epoch": 0.95,
"learning_rate": 1.7249038870934263e-05,
"loss": 1.3637,
"step": 555
},
{
"epoch": 0.96,
"learning_rate": 1.717980159193023e-05,
"loss": 1.3794,
"step": 560
},
{
"epoch": 0.97,
"learning_rate": 1.7109846524900885e-05,
"loss": 1.3189,
"step": 565
},
{
"epoch": 0.98,
"learning_rate": 1.7039180663480917e-05,
"loss": 1.3252,
"step": 570
},
{
"epoch": 0.99,
"learning_rate": 1.6967811072365423e-05,
"loss": 1.342,
"step": 575
},
{
"epoch": 1.0,
"learning_rate": 1.689574488660364e-05,
"loss": 1.3497,
"step": 580
},
{
"epoch": 1.0,
"eval_loss": 1.4483790397644043,
"eval_runtime": 133.8837,
"eval_samples_per_second": 10.18,
"eval_steps_per_second": 0.112,
"step": 582
},
{
"epoch": 1.01,
"learning_rate": 1.682298931088563e-05,
"loss": 1.2855,
"step": 585
},
{
"epoch": 1.01,
"learning_rate": 1.6749551618822006e-05,
"loss": 1.2097,
"step": 590
},
{
"epoch": 1.02,
"learning_rate": 1.6675439152216747e-05,
"loss": 1.3221,
"step": 595
},
{
"epoch": 1.03,
"learning_rate": 1.6600659320333247e-05,
"loss": 1.229,
"step": 600
},
{
"epoch": 1.04,
"learning_rate": 1.652521959915356e-05,
"loss": 1.1311,
"step": 605
},
{
"epoch": 1.05,
"learning_rate": 1.6449127530631005e-05,
"loss": 1.2322,
"step": 610
},
{
"epoch": 1.06,
"learning_rate": 1.6372390721936198e-05,
"loss": 1.2631,
"step": 615
},
{
"epoch": 1.07,
"learning_rate": 1.6295016844696494e-05,
"loss": 1.1868,
"step": 620
},
{
"epoch": 1.07,
"learning_rate": 1.621701363422907e-05,
"loss": 1.1462,
"step": 625
},
{
"epoch": 1.08,
"learning_rate": 1.6138388888767587e-05,
"loss": 1.0917,
"step": 630
},
{
"epoch": 1.09,
"learning_rate": 1.6059150468682558e-05,
"loss": 1.0819,
"step": 635
},
{
"epoch": 1.1,
"learning_rate": 1.5979306295695547e-05,
"loss": 1.1196,
"step": 640
},
{
"epoch": 1.11,
"learning_rate": 1.58988643520872e-05,
"loss": 1.0547,
"step": 645
},
{
"epoch": 1.12,
"learning_rate": 1.5817832679899222e-05,
"loss": 1.0307,
"step": 650
},
{
"epoch": 1.13,
"learning_rate": 1.5736219380130395e-05,
"loss": 0.9733,
"step": 655
},
{
"epoch": 1.13,
"learning_rate": 1.5654032611926698e-05,
"loss": 1.0215,
"step": 660
},
{
"epoch": 1.14,
"learning_rate": 1.5571280591765613e-05,
"loss": 0.9941,
"step": 665
},
{
"epoch": 1.15,
"learning_rate": 1.548797159263467e-05,
"loss": 0.9208,
"step": 670
},
{
"epoch": 1.16,
"learning_rate": 1.540411394320442e-05,
"loss": 0.9202,
"step": 675
},
{
"epoch": 1.17,
"learning_rate": 1.531971602699574e-05,
"loss": 0.9048,
"step": 680
},
{
"epoch": 1.18,
"learning_rate": 1.5234786281541736e-05,
"loss": 0.9502,
"step": 685
},
{
"epoch": 1.19,
"learning_rate": 1.5149333197544203e-05,
"loss": 0.8838,
"step": 690
},
{
"epoch": 1.19,
"learning_rate": 1.5063365318024791e-05,
"loss": 0.9124,
"step": 695
},
{
"epoch": 1.2,
"learning_rate": 1.497689123747092e-05,
"loss": 0.8446,
"step": 700
},
{
"epoch": 1.21,
"learning_rate": 1.4889919600976573e-05,
"loss": 0.8778,
"step": 705
},
{
"epoch": 1.22,
"learning_rate": 1.4802459103378008e-05,
"loss": 0.7858,
"step": 710
},
{
"epoch": 1.23,
"learning_rate": 1.4714518488384512e-05,
"loss": 0.8087,
"step": 715
},
{
"epoch": 1.24,
"learning_rate": 1.4626106547704262e-05,
"loss": 0.8072,
"step": 720
},
{
"epoch": 1.25,
"learning_rate": 1.4537232120165401e-05,
"loss": 0.7525,
"step": 725
},
{
"epoch": 1.25,
"learning_rate": 1.4447904090832366e-05,
"loss": 0.8278,
"step": 730
},
{
"epoch": 1.26,
"learning_rate": 1.4358131390117645e-05,
"loss": 0.8115,
"step": 735
},
{
"epoch": 1.27,
"learning_rate": 1.4267922992888961e-05,
"loss": 0.7743,
"step": 740
},
{
"epoch": 1.28,
"learning_rate": 1.4177287917572032e-05,
"loss": 0.8078,
"step": 745
},
{
"epoch": 1.29,
"learning_rate": 1.4086235225248966e-05,
"loss": 0.7173,
"step": 750
},
{
"epoch": 1.3,
"learning_rate": 1.3994774018752389e-05,
"loss": 0.7239,
"step": 755
},
{
"epoch": 1.31,
"learning_rate": 1.3902913441755422e-05,
"loss": 0.704,
"step": 760
},
{
"epoch": 1.31,
"learning_rate": 1.3810662677857548e-05,
"loss": 0.7421,
"step": 765
},
{
"epoch": 1.32,
"learning_rate": 1.3718030949666488e-05,
"loss": 0.7604,
"step": 770
},
{
"epoch": 1.33,
"learning_rate": 1.3625027517876216e-05,
"loss": 0.7587,
"step": 775
},
{
"epoch": 1.34,
"learning_rate": 1.3531661680341098e-05,
"loss": 0.7139,
"step": 780
},
{
"epoch": 1.35,
"learning_rate": 1.3437942771146388e-05,
"loss": 0.715,
"step": 785
},
{
"epoch": 1.36,
"learning_rate": 1.3343880159675062e-05,
"loss": 0.7455,
"step": 790
},
{
"epoch": 1.37,
"learning_rate": 1.3249483249671117e-05,
"loss": 0.7436,
"step": 795
},
{
"epoch": 1.37,
"learning_rate": 1.3154761478299461e-05,
"loss": 0.7172,
"step": 800
},
{
"epoch": 1.38,
"learning_rate": 1.3059724315202444e-05,
"loss": 0.741,
"step": 805
},
{
"epoch": 1.39,
"learning_rate": 1.296438126155315e-05,
"loss": 0.6807,
"step": 810
},
{
"epoch": 1.4,
"learning_rate": 1.286874184910553e-05,
"loss": 0.7379,
"step": 815
},
{
"epoch": 1.41,
"learning_rate": 1.2772815639241491e-05,
"loss": 0.7086,
"step": 820
},
{
"epoch": 1.42,
"learning_rate": 1.2676612222014999e-05,
"loss": 0.7675,
"step": 825
},
{
"epoch": 1.43,
"learning_rate": 1.258014121519334e-05,
"loss": 0.7193,
"step": 830
},
{
"epoch": 1.43,
"learning_rate": 1.2483412263295602e-05,
"loss": 0.6671,
"step": 835
},
{
"epoch": 1.44,
"learning_rate": 1.2386435036628474e-05,
"loss": 0.6785,
"step": 840
},
{
"epoch": 1.45,
"learning_rate": 1.228921923031948e-05,
"loss": 0.6683,
"step": 845
},
{
"epoch": 1.46,
"learning_rate": 1.2191774563347727e-05,
"loss": 0.7199,
"step": 850
},
{
"epoch": 1.47,
"learning_rate": 1.2094110777572257e-05,
"loss": 0.7024,
"step": 855
},
{
"epoch": 1.48,
"learning_rate": 1.1996237636758133e-05,
"loss": 0.6914,
"step": 860
},
{
"epoch": 1.49,
"learning_rate": 1.1898164925600316e-05,
"loss": 0.6947,
"step": 865
},
{
"epoch": 1.49,
"learning_rate": 1.1799902448745466e-05,
"loss": 0.6846,
"step": 870
},
{
"epoch": 1.5,
"learning_rate": 1.1701460029811733e-05,
"loss": 0.6788,
"step": 875
},
{
"epoch": 1.51,
"learning_rate": 1.1602847510406657e-05,
"loss": 0.6986,
"step": 880
},
{
"epoch": 1.52,
"learning_rate": 1.150407474914327e-05,
"loss": 0.7083,
"step": 885
},
{
"epoch": 1.53,
"learning_rate": 1.1405151620654513e-05,
"loss": 0.6188,
"step": 890
},
{
"epoch": 1.54,
"learning_rate": 1.1306088014606018e-05,
"loss": 0.7138,
"step": 895
},
{
"epoch": 1.55,
"learning_rate": 1.1206893834707415e-05,
"loss": 0.6972,
"step": 900
},
{
"epoch": 1.55,
"learning_rate": 1.110757899772222e-05,
"loss": 0.7069,
"step": 905
},
{
"epoch": 1.56,
"learning_rate": 1.1008153432476436e-05,
"loss": 0.7038,
"step": 910
},
{
"epoch": 1.57,
"learning_rate": 1.0908627078865928e-05,
"loss": 0.6523,
"step": 915
},
{
"epoch": 1.58,
"learning_rate": 1.0809009886862695e-05,
"loss": 0.6411,
"step": 920
},
{
"epoch": 1.59,
"learning_rate": 1.0709311815520151e-05,
"loss": 0.6691,
"step": 925
},
{
"epoch": 1.6,
"learning_rate": 1.0609542831977478e-05,
"loss": 0.6952,
"step": 930
},
{
"epoch": 1.61,
"learning_rate": 1.0509712910463175e-05,
"loss": 0.7437,
"step": 935
},
{
"epoch": 1.62,
"learning_rate": 1.0409832031297912e-05,
"loss": 0.7274,
"step": 940
},
{
"epoch": 1.62,
"learning_rate": 1.0309910179896762e-05,
"loss": 0.6345,
"step": 945
},
{
"epoch": 1.63,
"learning_rate": 1.0209957345770924e-05,
"loss": 0.6331,
"step": 950
},
{
"epoch": 1.64,
"learning_rate": 1.0109983521529036e-05,
"loss": 0.6683,
"step": 955
},
{
"epoch": 1.65,
"learning_rate": 1.000999870187819e-05,
"loss": 0.6999,
"step": 960
},
{
"epoch": 1.66,
"learning_rate": 9.910012882624726e-06,
"loss": 0.6881,
"step": 965
},
{
"epoch": 1.67,
"learning_rate": 9.810036059674914e-06,
"loss": 0.6735,
"step": 970
},
{
"epoch": 1.68,
"learning_rate": 9.710078228035635e-06,
"loss": 0.6506,
"step": 975
},
{
"epoch": 1.68,
"learning_rate": 9.610149380815148e-06,
"loss": 0.6896,
"step": 980
},
{
"epoch": 1.69,
"learning_rate": 9.510259508224052e-06,
"loss": 0.6672,
"step": 985
},
{
"epoch": 1.7,
"learning_rate": 9.41041859657651e-06,
"loss": 0.6851,
"step": 990
},
{
"epoch": 1.71,
"learning_rate": 9.310636627291915e-06,
"loss": 0.6618,
"step": 995
},
{
"epoch": 1.72,
"learning_rate": 9.210923575897001e-06,
"loss": 0.6249,
"step": 1000
},
{
"epoch": 1.73,
"learning_rate": 9.111289411028545e-06,
"loss": 0.631,
"step": 1005
},
{
"epoch": 1.74,
"learning_rate": 9.0117440934368e-06,
"loss": 0.6352,
"step": 1010
},
{
"epoch": 1.74,
"learning_rate": 8.912297574989649e-06,
"loss": 0.6613,
"step": 1015
},
{
"epoch": 1.75,
"learning_rate": 8.812959797677718e-06,
"loss": 0.6452,
"step": 1020
},
{
"epoch": 1.76,
"learning_rate": 8.713740692620432e-06,
"loss": 0.6671,
"step": 1025
},
{
"epoch": 1.77,
"learning_rate": 8.614650179073152e-06,
"loss": 0.6833,
"step": 1030
},
{
"epoch": 1.78,
"learning_rate": 8.515698163435542e-06,
"loss": 0.7135,
"step": 1035
},
{
"epoch": 1.79,
"learning_rate": 8.41689453826118e-06,
"loss": 0.6784,
"step": 1040
},
{
"epoch": 1.8,
"learning_rate": 8.318249181268556e-06,
"loss": 0.6886,
"step": 1045
},
{
"epoch": 1.8,
"learning_rate": 8.219771954353597e-06,
"loss": 0.6221,
"step": 1050
},
{
"epoch": 1.81,
"learning_rate": 8.121472702603703e-06,
"loss": 0.677,
"step": 1055
},
{
"epoch": 1.82,
"learning_rate": 8.023361253313533e-06,
"loss": 0.631,
"step": 1060
},
{
"epoch": 1.83,
"learning_rate": 7.925447415002523e-06,
"loss": 0.5897,
"step": 1065
},
{
"epoch": 1.84,
"learning_rate": 7.827740976434287e-06,
"loss": 0.6003,
"step": 1070
},
{
"epoch": 1.85,
"learning_rate": 7.730251705638034e-06,
"loss": 0.6457,
"step": 1075
},
{
"epoch": 1.86,
"learning_rate": 7.632989348931993e-06,
"loss": 0.6322,
"step": 1080
},
{
"epoch": 1.86,
"learning_rate": 7.535963629949071e-06,
"loss": 0.5849,
"step": 1085
},
{
"epoch": 1.87,
"learning_rate": 7.439184248664713e-06,
"loss": 0.6439,
"step": 1090
},
{
"epoch": 1.88,
"learning_rate": 7.34266088042721e-06,
"loss": 0.641,
"step": 1095
},
{
"epoch": 1.89,
"learning_rate": 7.246403174990379e-06,
"loss": 0.6496,
"step": 1100
},
{
"epoch": 1.9,
"learning_rate": 7.15042075554888e-06,
"loss": 0.6245,
"step": 1105
},
{
"epoch": 1.91,
"learning_rate": 7.054723217776138e-06,
"loss": 0.6483,
"step": 1110
},
{
"epoch": 1.92,
"learning_rate": 6.959320128865026e-06,
"loss": 0.6532,
"step": 1115
},
{
"epoch": 1.92,
"learning_rate": 6.86422102657142e-06,
"loss": 0.6116,
"step": 1120
},
{
"epoch": 1.93,
"learning_rate": 6.76943541826067e-06,
"loss": 0.5523,
"step": 1125
},
{
"epoch": 1.94,
"learning_rate": 6.6749727799571016e-06,
"loss": 0.6321,
"step": 1130
},
{
"epoch": 1.95,
"learning_rate": 6.580842555396706e-06,
"loss": 0.6502,
"step": 1135
},
{
"epoch": 1.96,
"learning_rate": 6.487054155082973e-06,
"loss": 0.6254,
"step": 1140
},
{
"epoch": 1.97,
"learning_rate": 6.393616955346129e-06,
"loss": 0.6547,
"step": 1145
},
{
"epoch": 1.98,
"learning_rate": 6.3005402974057415e-06,
"loss": 0.6172,
"step": 1150
},
{
"epoch": 1.98,
"learning_rate": 6.207833486436832e-06,
"loss": 0.6557,
"step": 1155
},
{
"epoch": 1.99,
"learning_rate": 6.115505790639642e-06,
"loss": 0.6709,
"step": 1160
},
{
"epoch": 2.0,
"eval_loss": 1.5766805410385132,
"eval_runtime": 133.3882,
"eval_samples_per_second": 10.218,
"eval_steps_per_second": 0.112,
"step": 1164
},
{
"epoch": 2.0,
"learning_rate": 6.023566440313023e-06,
"loss": 0.559,
"step": 1165
},
{
"epoch": 2.01,
"learning_rate": 5.932024626931689e-06,
"loss": 0.5316,
"step": 1170
},
{
"epoch": 2.02,
"learning_rate": 5.840889502227285e-06,
"loss": 0.6037,
"step": 1175
},
{
"epoch": 2.03,
"learning_rate": 5.750170177273471e-06,
"loss": 0.5708,
"step": 1180
},
{
"epoch": 2.04,
"learning_rate": 5.659875721575065e-06,
"loss": 0.5343,
"step": 1185
},
{
"epoch": 2.04,
"learning_rate": 5.570015162161331e-06,
"loss": 0.5318,
"step": 1190
},
{
"epoch": 2.05,
"learning_rate": 5.480597482683507e-06,
"loss": 0.5536,
"step": 1195
},
{
"epoch": 2.06,
"learning_rate": 5.391631622516697e-06,
"loss": 0.5613,
"step": 1200
},
{
"epoch": 2.07,
"learning_rate": 5.3031264758661595e-06,
"loss": 0.5205,
"step": 1205
},
{
"epoch": 2.08,
"learning_rate": 5.2150908908781335e-06,
"loss": 0.5141,
"step": 1210
},
{
"epoch": 2.09,
"learning_rate": 5.1275336687552554e-06,
"loss": 0.4753,
"step": 1215
},
{
"epoch": 2.1,
"learning_rate": 5.040463562876678e-06,
"loss": 0.5046,
"step": 1220
},
{
"epoch": 2.1,
"learning_rate": 4.9538892779229645e-06,
"loss": 0.509,
"step": 1225
},
{
"epoch": 2.11,
"learning_rate": 4.867819469005851e-06,
"loss": 0.4434,
"step": 1230
},
{
"epoch": 2.12,
"learning_rate": 4.782262740802975e-06,
"loss": 0.4493,
"step": 1235
},
{
"epoch": 2.13,
"learning_rate": 4.697227646697627e-06,
"loss": 0.4474,
"step": 1240
},
{
"epoch": 2.14,
"learning_rate": 4.612722687923658e-06,
"loss": 0.4455,
"step": 1245
},
{
"epoch": 2.15,
"learning_rate": 4.5287563127155545e-06,
"loss": 0.43,
"step": 1250
},
{
"epoch": 2.16,
"learning_rate": 4.445336915463874e-06,
"loss": 0.4147,
"step": 1255
},
{
"epoch": 2.16,
"learning_rate": 4.362472835876011e-06,
"loss": 0.3961,
"step": 1260
},
{
"epoch": 2.17,
"learning_rate": 4.280172358142448e-06,
"loss": 0.4416,
"step": 1265
},
{
"epoch": 2.18,
"learning_rate": 4.198443710108583e-06,
"loss": 0.3929,
"step": 1270
},
{
"epoch": 2.19,
"learning_rate": 4.117295062452122e-06,
"loss": 0.4044,
"step": 1275
},
{
"epoch": 2.2,
"learning_rate": 4.036734527866266e-06,
"loss": 0.4289,
"step": 1280
},
{
"epoch": 2.21,
"learning_rate": 3.956770160248658e-06,
"loss": 0.383,
"step": 1285
},
{
"epoch": 2.22,
"learning_rate": 3.8774099538961705e-06,
"loss": 0.391,
"step": 1290
},
{
"epoch": 2.23,
"learning_rate": 3.79866184270575e-06,
"loss": 0.3592,
"step": 1295
},
{
"epoch": 2.23,
"learning_rate": 3.720533699381177e-06,
"loss": 0.3803,
"step": 1300
},
{
"epoch": 2.24,
"learning_rate": 3.64303333464605e-06,
"loss": 0.3274,
"step": 1305
},
{
"epoch": 2.25,
"learning_rate": 3.5661684964629174e-06,
"loss": 0.3652,
"step": 1310
},
{
"epoch": 2.26,
"learning_rate": 3.4899468692586537e-06,
"loss": 0.3681,
"step": 1315
},
{
"epoch": 2.27,
"learning_rate": 3.414376073156275e-06,
"loss": 0.3589,
"step": 1320
},
{
"epoch": 2.28,
"learning_rate": 3.3394636632130893e-06,
"loss": 0.3431,
"step": 1325
},
{
"epoch": 2.29,
"learning_rate": 3.2652171286654032e-06,
"loss": 0.3458,
"step": 1330
},
{
"epoch": 2.29,
"learning_rate": 3.191643892179821e-06,
"loss": 0.3163,
"step": 1335
},
{
"epoch": 2.3,
"learning_rate": 3.1187513091111345e-06,
"loss": 0.2961,
"step": 1340
},
{
"epoch": 2.31,
"learning_rate": 3.0465466667670286e-06,
"loss": 0.3045,
"step": 1345
},
{
"epoch": 2.32,
"learning_rate": 2.975037183679519e-06,
"loss": 0.3366,
"step": 1350
},
{
"epoch": 2.33,
"learning_rate": 2.9042300088832877e-06,
"loss": 0.3511,
"step": 1355
},
{
"epoch": 2.34,
"learning_rate": 2.834132221200998e-06,
"loss": 0.3254,
"step": 1360
},
{
"epoch": 2.35,
"learning_rate": 2.7647508285355774e-06,
"loss": 0.3208,
"step": 1365
},
{
"epoch": 2.35,
"learning_rate": 2.6960927671696213e-06,
"loss": 0.3209,
"step": 1370
},
{
"epoch": 2.36,
"learning_rate": 2.6281649010719577e-06,
"loss": 0.3605,
"step": 1375
},
{
"epoch": 2.37,
"learning_rate": 2.5609740212114154e-06,
"loss": 0.3405,
"step": 1380
},
{
"epoch": 2.38,
"learning_rate": 2.494526844877938e-06,
"loss": 0.3352,
"step": 1385
},
{
"epoch": 2.39,
"learning_rate": 2.4288300150110077e-06,
"loss": 0.307,
"step": 1390
},
{
"epoch": 2.4,
"learning_rate": 2.3638900995355418e-06,
"loss": 0.3171,
"step": 1395
},
{
"epoch": 2.41,
"learning_rate": 2.299713590705275e-06,
"loss": 0.3189,
"step": 1400
},
{
"epoch": 2.41,
"learning_rate": 2.2363069044537044e-06,
"loss": 0.3225,
"step": 1405
},
{
"epoch": 2.42,
"learning_rate": 2.173676379752672e-06,
"loss": 0.3645,
"step": 1410
},
{
"epoch": 2.43,
"learning_rate": 2.1118282779786325e-06,
"loss": 0.3216,
"step": 1415
},
{
"epoch": 2.44,
"learning_rate": 2.0507687822866897e-06,
"loss": 0.3094,
"step": 1420
},
{
"epoch": 2.45,
"learning_rate": 1.9905039969924388e-06,
"loss": 0.3119,
"step": 1425
},
{
"epoch": 2.46,
"learning_rate": 1.9310399469617048e-06,
"loss": 0.3193,
"step": 1430
},
{
"epoch": 2.47,
"learning_rate": 1.8723825770082116e-06,
"loss": 0.3117,
"step": 1435
},
{
"epoch": 2.47,
"learning_rate": 1.8145377512992646e-06,
"loss": 0.3199,
"step": 1440
},
{
"epoch": 2.48,
"learning_rate": 1.7575112527694871e-06,
"loss": 0.2935,
"step": 1445
},
{
"epoch": 2.49,
"learning_rate": 1.7013087825426855e-06,
"loss": 0.3258,
"step": 1450
},
{
"epoch": 2.5,
"learning_rate": 1.645935959361884e-06,
"loss": 0.3007,
"step": 1455
},
{
"epoch": 2.51,
"learning_rate": 1.591398319027605e-06,
"loss": 0.3276,
"step": 1460
},
{
"epoch": 2.52,
"learning_rate": 1.5377013138444386e-06,
"loss": 0.3204,
"step": 1465
},
{
"epoch": 2.53,
"learning_rate": 1.4848503120759527e-06,
"loss": 0.3157,
"step": 1470
},
{
"epoch": 2.53,
"learning_rate": 1.432850597408012e-06,
"loss": 0.2953,
"step": 1475
},
{
"epoch": 2.54,
"learning_rate": 1.3817073684205562e-06,
"loss": 0.2959,
"step": 1480
},
{
"epoch": 2.55,
"learning_rate": 1.331425738067872e-06,
"loss": 0.3428,
"step": 1485
},
{
"epoch": 2.56,
"learning_rate": 1.2820107331674426e-06,
"loss": 0.3364,
"step": 1490
},
{
"epoch": 2.57,
"learning_rate": 1.2334672938973958e-06,
"loss": 0.3162,
"step": 1495
},
{
"epoch": 2.58,
"learning_rate": 1.1858002733026196e-06,
"loss": 0.2815,
"step": 1500
},
{
"epoch": 2.59,
"learning_rate": 1.139014436809589e-06,
"loss": 0.3064,
"step": 1505
},
{
"epoch": 2.59,
"learning_rate": 1.093114461749948e-06,
"loss": 0.3043,
"step": 1510
},
{
"epoch": 2.6,
"learning_rate": 1.048104936892902e-06,
"loss": 0.3775,
"step": 1515
},
{
"epoch": 2.61,
"learning_rate": 1.003990361986472e-06,
"loss": 0.3461,
"step": 1520
},
{
"epoch": 2.62,
"learning_rate": 9.607751473076232e-07,
"loss": 0.3095,
"step": 1525
},
{
"epoch": 2.63,
"learning_rate": 9.18463613221372e-07,
"loss": 0.2902,
"step": 1530
},
{
"epoch": 2.64,
"learning_rate": 8.770599897488563e-07,
"loss": 0.3263,
"step": 1535
},
{
"epoch": 2.65,
"learning_rate": 8.365684161444454e-07,
"loss": 0.3094,
"step": 1540
},
{
"epoch": 2.65,
"learning_rate": 7.969929404819377e-07,
"loss": 0.3099,
"step": 1545
},
{
"epoch": 2.66,
"learning_rate": 7.583375192498422e-07,
"loss": 0.3441,
"step": 1550
},
{
"epoch": 2.67,
"learning_rate": 7.206060169558482e-07,
"loss": 0.3085,
"step": 1555
},
{
"epoch": 2.68,
"learning_rate": 6.838022057404848e-07,
"loss": 0.2788,
"step": 1560
},
{
"epoch": 2.69,
"learning_rate": 6.479297649999839e-07,
"loss": 0.3381,
"step": 1565
},
{
"epoch": 2.7,
"learning_rate": 6.129922810184663e-07,
"loss": 0.3003,
"step": 1570
},
{
"epoch": 2.71,
"learning_rate": 5.789932466093884e-07,
"loss": 0.3267,
"step": 1575
},
{
"epoch": 2.71,
"learning_rate": 5.459360607663644e-07,
"loss": 0.3103,
"step": 1580
},
{
"epoch": 2.72,
"learning_rate": 5.138240283233631e-07,
"loss": 0.2711,
"step": 1585
},
{
"epoch": 2.73,
"learning_rate": 4.826603596242918e-07,
"loss": 0.3007,
"step": 1590
},
{
"epoch": 2.74,
"learning_rate": 4.5244817020207775e-07,
"loss": 0.3087,
"step": 1595
},
{
"epoch": 2.75,
"learning_rate": 4.231904804671727e-07,
"loss": 0.3132,
"step": 1600
},
{
"epoch": 2.76,
"learning_rate": 3.9489021540560114e-07,
"loss": 0.3119,
"step": 1605
},
{
"epoch": 2.77,
"learning_rate": 3.6755020428654974e-07,
"loss": 0.2992,
"step": 1610
},
{
"epoch": 2.77,
"learning_rate": 3.411731803794982e-07,
"loss": 0.3365,
"step": 1615
},
{
"epoch": 2.78,
"learning_rate": 3.1576178068098205e-07,
"loss": 0.3505,
"step": 1620
},
{
"epoch": 2.79,
"learning_rate": 2.913185456509537e-07,
"loss": 0.3634,
"step": 1625
},
{
"epoch": 2.8,
"learning_rate": 2.678459189588045e-07,
"loss": 0.3027,
"step": 1630
},
{
"epoch": 2.81,
"learning_rate": 2.453462472390711e-07,
"loss": 0.3239,
"step": 1635
},
{
"epoch": 2.82,
"learning_rate": 2.238217798568254e-07,
"loss": 0.3222,
"step": 1640
},
{
"epoch": 2.83,
"learning_rate": 2.0327466868280354e-07,
"loss": 0.3058,
"step": 1645
},
{
"epoch": 2.84,
"learning_rate": 1.8370696787827658e-07,
"loss": 0.3013,
"step": 1650
},
{
"epoch": 2.84,
"learning_rate": 1.6512063368968488e-07,
"loss": 0.2995,
"step": 1655
},
{
"epoch": 2.85,
"learning_rate": 1.4751752425307243e-07,
"loss": 0.325,
"step": 1660
},
{
"epoch": 2.86,
"learning_rate": 1.3089939940831854e-07,
"loss": 0.3107,
"step": 1665
},
{
"epoch": 2.87,
"learning_rate": 1.1526792052319769e-07,
"loss": 0.3109,
"step": 1670
},
{
"epoch": 2.88,
"learning_rate": 1.0062465032729896e-07,
"loss": 0.3114,
"step": 1675
},
{
"epoch": 2.89,
"learning_rate": 8.697105275577989e-08,
"loss": 0.3613,
"step": 1680
},
{
"epoch": 2.9,
"learning_rate": 7.430849280302465e-08,
"loss": 0.3221,
"step": 1685
},
{
"epoch": 2.9,
"learning_rate": 6.263823638617328e-08,
"loss": 0.286,
"step": 1690
},
{
"epoch": 2.91,
"learning_rate": 5.196145021856836e-08,
"loss": 0.3689,
"step": 1695
},
{
"epoch": 2.92,
"learning_rate": 4.2279201693110615e-08,
"loss": 0.3032,
"step": 1700
},
{
"epoch": 2.93,
"learning_rate": 3.359245877555428e-08,
"loss": 0.3079,
"step": 1705
},
{
"epoch": 2.94,
"learning_rate": 2.5902089907730022e-08,
"loss": 0.3242,
"step": 1710
},
{
"epoch": 2.95,
"learning_rate": 1.920886392072885e-08,
"loss": 0.3382,
"step": 1715
},
{
"epoch": 2.96,
"learning_rate": 1.3513449958034718e-08,
"loss": 0.329,
"step": 1720
},
{
"epoch": 2.96,
"learning_rate": 8.816417408634704e-09,
"loss": 0.3636,
"step": 1725
},
{
"epoch": 2.97,
"learning_rate": 5.11823585008675e-09,
"loss": 0.3181,
"step": 1730
},
{
"epoch": 2.98,
"learning_rate": 2.4192750015850088e-09,
"loss": 0.3656,
"step": 1735
},
{
"epoch": 2.99,
"learning_rate": 7.198046869882902e-10,
"loss": 0.3502,
"step": 1740
},
{
"epoch": 3.0,
"learning_rate": 1.999480784942165e-11,
"loss": 0.3156,
"step": 1745
},
{
"epoch": 3.0,
"eval_loss": 1.7387598752975464,
"eval_runtime": 133.3136,
"eval_samples_per_second": 10.224,
"eval_steps_per_second": 0.113,
"step": 1746
},
{
"epoch": 3.0,
"step": 1746,
"total_flos": 1230956927057920.0,
"train_loss": 0.872046828952715,
"train_runtime": 30104.3205,
"train_samples_per_second": 2.783,
"train_steps_per_second": 0.058
}
],
"logging_steps": 5,
"max_steps": 1746,
"num_train_epochs": 3,
"save_steps": 500,
"total_flos": 1230956927057920.0,
"trial_name": null,
"trial_params": null
}