opt-peter-2.7B / trainer_state.json
pszemraj's picture
add additional epoch checkpoint, better regularization
d23972a
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9992919995954284,
"global_step": 1235,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 5.0607287449392715e-08,
"loss": 1.0392,
"step": 5
},
{
"epoch": 0.01,
"learning_rate": 1.0121457489878543e-07,
"loss": 1.0115,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 1.5182186234817813e-07,
"loss": 0.99,
"step": 15
},
{
"epoch": 0.02,
"learning_rate": 2.0242914979757086e-07,
"loss": 1.0143,
"step": 20
},
{
"epoch": 0.02,
"learning_rate": 2.5303643724696356e-07,
"loss": 1.0301,
"step": 25
},
{
"epoch": 0.02,
"learning_rate": 3.0364372469635626e-07,
"loss": 0.9651,
"step": 30
},
{
"epoch": 0.03,
"learning_rate": 3.54251012145749e-07,
"loss": 0.9984,
"step": 35
},
{
"epoch": 0.03,
"learning_rate": 4.048582995951417e-07,
"loss": 0.9842,
"step": 40
},
{
"epoch": 0.04,
"learning_rate": 4.5546558704453447e-07,
"loss": 1.0033,
"step": 45
},
{
"epoch": 0.04,
"learning_rate": 5.060728744939271e-07,
"loss": 0.9764,
"step": 50
},
{
"epoch": 0.04,
"learning_rate": 5.566801619433199e-07,
"loss": 1.018,
"step": 55
},
{
"epoch": 0.05,
"learning_rate": 6.072874493927125e-07,
"loss": 0.9808,
"step": 60
},
{
"epoch": 0.05,
"learning_rate": 6.578947368421053e-07,
"loss": 0.9508,
"step": 65
},
{
"epoch": 0.06,
"learning_rate": 7.08502024291498e-07,
"loss": 0.9654,
"step": 70
},
{
"epoch": 0.06,
"learning_rate": 7.591093117408907e-07,
"loss": 0.9801,
"step": 75
},
{
"epoch": 0.06,
"learning_rate": 8.097165991902834e-07,
"loss": 0.9825,
"step": 80
},
{
"epoch": 0.07,
"learning_rate": 8.603238866396761e-07,
"loss": 1.0046,
"step": 85
},
{
"epoch": 0.07,
"learning_rate": 9.109311740890689e-07,
"loss": 0.9797,
"step": 90
},
{
"epoch": 0.08,
"learning_rate": 9.615384615384617e-07,
"loss": 0.9904,
"step": 95
},
{
"epoch": 0.08,
"learning_rate": 1.0121457489878542e-06,
"loss": 0.987,
"step": 100
},
{
"epoch": 0.08,
"learning_rate": 1.062753036437247e-06,
"loss": 0.9782,
"step": 105
},
{
"epoch": 0.09,
"learning_rate": 1.1133603238866398e-06,
"loss": 1.0131,
"step": 110
},
{
"epoch": 0.09,
"learning_rate": 1.1639676113360325e-06,
"loss": 0.9269,
"step": 115
},
{
"epoch": 0.1,
"learning_rate": 1.214574898785425e-06,
"loss": 0.9312,
"step": 120
},
{
"epoch": 0.1,
"learning_rate": 1.265182186234818e-06,
"loss": 1.0038,
"step": 125
},
{
"epoch": 0.11,
"learning_rate": 1.3157894736842106e-06,
"loss": 0.9896,
"step": 130
},
{
"epoch": 0.11,
"learning_rate": 1.3663967611336035e-06,
"loss": 0.9544,
"step": 135
},
{
"epoch": 0.11,
"learning_rate": 1.417004048582996e-06,
"loss": 0.9811,
"step": 140
},
{
"epoch": 0.12,
"learning_rate": 1.4676113360323888e-06,
"loss": 1.0079,
"step": 145
},
{
"epoch": 0.12,
"learning_rate": 1.5182186234817814e-06,
"loss": 0.9216,
"step": 150
},
{
"epoch": 0.13,
"learning_rate": 1.5688259109311743e-06,
"loss": 0.9537,
"step": 155
},
{
"epoch": 0.13,
"learning_rate": 1.6194331983805669e-06,
"loss": 0.9364,
"step": 160
},
{
"epoch": 0.13,
"learning_rate": 1.6700404858299596e-06,
"loss": 0.9203,
"step": 165
},
{
"epoch": 0.14,
"learning_rate": 1.7206477732793522e-06,
"loss": 0.9639,
"step": 170
},
{
"epoch": 0.14,
"learning_rate": 1.7712550607287451e-06,
"loss": 0.9563,
"step": 175
},
{
"epoch": 0.15,
"learning_rate": 1.8218623481781379e-06,
"loss": 0.9413,
"step": 180
},
{
"epoch": 0.15,
"learning_rate": 1.8724696356275304e-06,
"loss": 0.9173,
"step": 185
},
{
"epoch": 0.15,
"learning_rate": 1.9230769230769234e-06,
"loss": 0.9208,
"step": 190
},
{
"epoch": 0.16,
"learning_rate": 1.973684210526316e-06,
"loss": 0.9382,
"step": 195
},
{
"epoch": 0.16,
"learning_rate": 2.0242914979757085e-06,
"loss": 0.8964,
"step": 200
},
{
"epoch": 0.17,
"learning_rate": 2.0748987854251012e-06,
"loss": 0.9241,
"step": 205
},
{
"epoch": 0.17,
"learning_rate": 2.125506072874494e-06,
"loss": 0.9458,
"step": 210
},
{
"epoch": 0.17,
"learning_rate": 2.1761133603238867e-06,
"loss": 0.93,
"step": 215
},
{
"epoch": 0.18,
"learning_rate": 2.2267206477732795e-06,
"loss": 0.9031,
"step": 220
},
{
"epoch": 0.18,
"learning_rate": 2.2773279352226723e-06,
"loss": 0.9207,
"step": 225
},
{
"epoch": 0.19,
"learning_rate": 2.327935222672065e-06,
"loss": 0.9123,
"step": 230
},
{
"epoch": 0.19,
"learning_rate": 2.3785425101214578e-06,
"loss": 0.9057,
"step": 235
},
{
"epoch": 0.19,
"learning_rate": 2.42914979757085e-06,
"loss": 0.8909,
"step": 240
},
{
"epoch": 0.2,
"learning_rate": 2.4797570850202433e-06,
"loss": 0.9171,
"step": 245
},
{
"epoch": 0.2,
"learning_rate": 2.530364372469636e-06,
"loss": 0.8959,
"step": 250
},
{
"epoch": 0.21,
"learning_rate": 2.5809716599190288e-06,
"loss": 0.946,
"step": 255
},
{
"epoch": 0.21,
"learning_rate": 2.631578947368421e-06,
"loss": 0.9071,
"step": 260
},
{
"epoch": 0.21,
"learning_rate": 2.682186234817814e-06,
"loss": 0.8789,
"step": 265
},
{
"epoch": 0.22,
"learning_rate": 2.732793522267207e-06,
"loss": 0.9864,
"step": 270
},
{
"epoch": 0.22,
"learning_rate": 2.7834008097165994e-06,
"loss": 0.8932,
"step": 275
},
{
"epoch": 0.23,
"learning_rate": 2.834008097165992e-06,
"loss": 0.9064,
"step": 280
},
{
"epoch": 0.23,
"learning_rate": 2.8846153846153845e-06,
"loss": 0.9127,
"step": 285
},
{
"epoch": 0.23,
"learning_rate": 2.9352226720647776e-06,
"loss": 0.914,
"step": 290
},
{
"epoch": 0.24,
"learning_rate": 2.9858299595141704e-06,
"loss": 0.9254,
"step": 295
},
{
"epoch": 0.24,
"learning_rate": 3.0364372469635627e-06,
"loss": 0.9396,
"step": 300
},
{
"epoch": 0.25,
"learning_rate": 3.087044534412956e-06,
"loss": 0.9208,
"step": 305
},
{
"epoch": 0.25,
"learning_rate": 3.1376518218623487e-06,
"loss": 0.9242,
"step": 310
},
{
"epoch": 0.25,
"learning_rate": 3.188259109311741e-06,
"loss": 0.9057,
"step": 315
},
{
"epoch": 0.26,
"learning_rate": 3.2388663967611337e-06,
"loss": 0.9632,
"step": 320
},
{
"epoch": 0.26,
"learning_rate": 3.289473684210527e-06,
"loss": 0.9344,
"step": 325
},
{
"epoch": 0.27,
"learning_rate": 3.3400809716599193e-06,
"loss": 0.9578,
"step": 330
},
{
"epoch": 0.27,
"learning_rate": 3.390688259109312e-06,
"loss": 0.947,
"step": 335
},
{
"epoch": 0.28,
"learning_rate": 3.4412955465587043e-06,
"loss": 0.9344,
"step": 340
},
{
"epoch": 0.28,
"learning_rate": 3.4919028340080975e-06,
"loss": 0.9472,
"step": 345
},
{
"epoch": 0.28,
"learning_rate": 3.5425101214574903e-06,
"loss": 1.0034,
"step": 350
},
{
"epoch": 0.29,
"learning_rate": 3.5931174089068826e-06,
"loss": 0.9558,
"step": 355
},
{
"epoch": 0.29,
"learning_rate": 3.6437246963562758e-06,
"loss": 0.9274,
"step": 360
},
{
"epoch": 0.3,
"learning_rate": 3.6943319838056685e-06,
"loss": 0.968,
"step": 365
},
{
"epoch": 0.3,
"learning_rate": 3.744939271255061e-06,
"loss": 0.9543,
"step": 370
},
{
"epoch": 0.3,
"learning_rate": 3.7955465587044536e-06,
"loss": 1.0063,
"step": 375
},
{
"epoch": 0.31,
"learning_rate": 3.846153846153847e-06,
"loss": 0.9491,
"step": 380
},
{
"epoch": 0.31,
"learning_rate": 3.896761133603239e-06,
"loss": 0.8891,
"step": 385
},
{
"epoch": 0.32,
"learning_rate": 3.947368421052632e-06,
"loss": 0.9015,
"step": 390
},
{
"epoch": 0.32,
"learning_rate": 3.997975708502025e-06,
"loss": 0.9852,
"step": 395
},
{
"epoch": 0.32,
"learning_rate": 4.048582995951417e-06,
"loss": 0.9636,
"step": 400
},
{
"epoch": 0.33,
"learning_rate": 4.09919028340081e-06,
"loss": 0.9683,
"step": 405
},
{
"epoch": 0.33,
"learning_rate": 4.1497975708502025e-06,
"loss": 0.9127,
"step": 410
},
{
"epoch": 0.34,
"learning_rate": 4.200404858299596e-06,
"loss": 0.9229,
"step": 415
},
{
"epoch": 0.34,
"learning_rate": 4.251012145748988e-06,
"loss": 0.9329,
"step": 420
},
{
"epoch": 0.34,
"learning_rate": 4.30161943319838e-06,
"loss": 0.9864,
"step": 425
},
{
"epoch": 0.35,
"learning_rate": 4.3522267206477735e-06,
"loss": 0.9208,
"step": 430
},
{
"epoch": 0.35,
"learning_rate": 4.402834008097167e-06,
"loss": 0.959,
"step": 435
},
{
"epoch": 0.36,
"learning_rate": 4.453441295546559e-06,
"loss": 0.9411,
"step": 440
},
{
"epoch": 0.36,
"learning_rate": 4.504048582995952e-06,
"loss": 0.9695,
"step": 445
},
{
"epoch": 0.36,
"learning_rate": 4.5546558704453445e-06,
"loss": 0.9808,
"step": 450
},
{
"epoch": 0.37,
"learning_rate": 4.605263157894737e-06,
"loss": 0.8951,
"step": 455
},
{
"epoch": 0.37,
"learning_rate": 4.65587044534413e-06,
"loss": 0.9815,
"step": 460
},
{
"epoch": 0.38,
"learning_rate": 4.706477732793522e-06,
"loss": 0.9565,
"step": 465
},
{
"epoch": 0.38,
"learning_rate": 4.7570850202429155e-06,
"loss": 0.9335,
"step": 470
},
{
"epoch": 0.38,
"learning_rate": 4.807692307692308e-06,
"loss": 0.9409,
"step": 475
},
{
"epoch": 0.39,
"learning_rate": 4.8582995951417e-06,
"loss": 0.9057,
"step": 480
},
{
"epoch": 0.39,
"learning_rate": 4.908906882591093e-06,
"loss": 0.9125,
"step": 485
},
{
"epoch": 0.4,
"learning_rate": 4.9595141700404865e-06,
"loss": 0.9485,
"step": 490
},
{
"epoch": 0.4,
"learning_rate": 4.9999993758760865e-06,
"loss": 0.9827,
"step": 495
},
{
"epoch": 0.4,
"learning_rate": 4.999977531571805e-06,
"loss": 0.9135,
"step": 500
},
{
"epoch": 0.41,
"learning_rate": 4.999924481383433e-06,
"loss": 0.9547,
"step": 505
},
{
"epoch": 0.41,
"learning_rate": 4.9998402259731634e-06,
"loss": 0.9506,
"step": 510
},
{
"epoch": 0.42,
"learning_rate": 4.999724766392715e-06,
"loss": 0.9281,
"step": 515
},
{
"epoch": 0.42,
"learning_rate": 4.999578104083307e-06,
"loss": 0.925,
"step": 520
},
{
"epoch": 0.42,
"learning_rate": 4.999400240875647e-06,
"loss": 0.9808,
"step": 525
},
{
"epoch": 0.43,
"learning_rate": 4.999191178989905e-06,
"loss": 0.963,
"step": 530
},
{
"epoch": 0.43,
"learning_rate": 4.998950921035691e-06,
"loss": 0.9125,
"step": 535
},
{
"epoch": 0.44,
"learning_rate": 4.998679470012015e-06,
"loss": 0.9833,
"step": 540
},
{
"epoch": 0.44,
"learning_rate": 4.998376829307255e-06,
"loss": 0.949,
"step": 545
},
{
"epoch": 0.45,
"learning_rate": 4.998043002699114e-06,
"loss": 0.9539,
"step": 550
},
{
"epoch": 0.45,
"learning_rate": 4.997677994354573e-06,
"loss": 0.9612,
"step": 555
},
{
"epoch": 0.45,
"learning_rate": 4.997281808829833e-06,
"loss": 0.962,
"step": 560
},
{
"epoch": 0.46,
"learning_rate": 4.996854451070267e-06,
"loss": 0.9467,
"step": 565
},
{
"epoch": 0.46,
"learning_rate": 4.996395926410354e-06,
"loss": 0.9273,
"step": 570
},
{
"epoch": 0.47,
"learning_rate": 4.995906240573615e-06,
"loss": 0.9213,
"step": 575
},
{
"epoch": 0.47,
"learning_rate": 4.995385399672532e-06,
"loss": 0.9405,
"step": 580
},
{
"epoch": 0.47,
"learning_rate": 4.994833410208487e-06,
"loss": 0.9448,
"step": 585
},
{
"epoch": 0.48,
"learning_rate": 4.994250279071669e-06,
"loss": 0.9146,
"step": 590
},
{
"epoch": 0.48,
"learning_rate": 4.9936360135409915e-06,
"loss": 0.9891,
"step": 595
},
{
"epoch": 0.49,
"learning_rate": 4.992990621284004e-06,
"loss": 0.9444,
"step": 600
},
{
"epoch": 0.49,
"learning_rate": 4.992314110356793e-06,
"loss": 0.9599,
"step": 605
},
{
"epoch": 0.49,
"learning_rate": 4.991606489203883e-06,
"loss": 1.0091,
"step": 610
},
{
"epoch": 0.5,
"learning_rate": 4.99086776665813e-06,
"loss": 0.9725,
"step": 615
},
{
"epoch": 0.5,
"learning_rate": 4.9900979519406154e-06,
"loss": 0.9283,
"step": 620
},
{
"epoch": 0.51,
"learning_rate": 4.9892970546605226e-06,
"loss": 0.9856,
"step": 625
},
{
"epoch": 0.51,
"learning_rate": 4.988465084815026e-06,
"loss": 0.9866,
"step": 630
},
{
"epoch": 0.51,
"learning_rate": 4.987602052789159e-06,
"loss": 0.8948,
"step": 635
},
{
"epoch": 0.52,
"learning_rate": 4.986707969355692e-06,
"loss": 0.9727,
"step": 640
},
{
"epoch": 0.52,
"learning_rate": 4.985782845674988e-06,
"loss": 0.9579,
"step": 645
},
{
"epoch": 0.53,
"learning_rate": 4.9848266932948745e-06,
"loss": 0.9343,
"step": 650
},
{
"epoch": 0.53,
"learning_rate": 4.983839524150489e-06,
"loss": 0.9872,
"step": 655
},
{
"epoch": 0.53,
"learning_rate": 4.982821350564136e-06,
"loss": 0.9586,
"step": 660
},
{
"epoch": 0.54,
"learning_rate": 4.981772185245135e-06,
"loss": 0.9687,
"step": 665
},
{
"epoch": 0.54,
"learning_rate": 4.9806920412896555e-06,
"loss": 0.9365,
"step": 670
},
{
"epoch": 0.55,
"learning_rate": 4.979580932180556e-06,
"loss": 0.9754,
"step": 675
},
{
"epoch": 0.55,
"learning_rate": 4.978438871787219e-06,
"loss": 0.9456,
"step": 680
},
{
"epoch": 0.55,
"learning_rate": 4.977265874365374e-06,
"loss": 0.9345,
"step": 685
},
{
"epoch": 0.56,
"learning_rate": 4.976061954556921e-06,
"loss": 0.9384,
"step": 690
},
{
"epoch": 0.56,
"learning_rate": 4.9748271273897495e-06,
"loss": 0.9121,
"step": 695
},
{
"epoch": 0.57,
"learning_rate": 4.9735614082775455e-06,
"loss": 0.9196,
"step": 700
},
{
"epoch": 0.57,
"learning_rate": 4.972264813019605e-06,
"loss": 0.9427,
"step": 705
},
{
"epoch": 0.57,
"learning_rate": 4.970937357800635e-06,
"loss": 0.9248,
"step": 710
},
{
"epoch": 0.58,
"learning_rate": 4.969579059190549e-06,
"loss": 0.924,
"step": 715
},
{
"epoch": 0.58,
"learning_rate": 4.968189934144263e-06,
"loss": 0.9705,
"step": 720
},
{
"epoch": 0.59,
"learning_rate": 4.966770000001483e-06,
"loss": 0.992,
"step": 725
},
{
"epoch": 0.59,
"learning_rate": 4.965319274486488e-06,
"loss": 0.9164,
"step": 730
},
{
"epoch": 0.59,
"learning_rate": 4.963837775707911e-06,
"loss": 0.9343,
"step": 735
},
{
"epoch": 0.6,
"learning_rate": 4.962325522158509e-06,
"loss": 0.9485,
"step": 740
},
{
"epoch": 0.6,
"learning_rate": 4.960782532714934e-06,
"loss": 0.9483,
"step": 745
},
{
"epoch": 0.61,
"learning_rate": 4.959208826637502e-06,
"loss": 0.959,
"step": 750
},
{
"epoch": 0.61,
"learning_rate": 4.957604423569942e-06,
"loss": 0.9819,
"step": 755
},
{
"epoch": 0.61,
"learning_rate": 4.955969343539162e-06,
"loss": 0.9399,
"step": 760
},
{
"epoch": 0.62,
"learning_rate": 4.954303606954993e-06,
"loss": 0.8887,
"step": 765
},
{
"epoch": 0.62,
"learning_rate": 4.952607234609935e-06,
"loss": 0.989,
"step": 770
},
{
"epoch": 0.63,
"learning_rate": 4.950880247678897e-06,
"loss": 0.9565,
"step": 775
},
{
"epoch": 0.63,
"learning_rate": 4.949122667718935e-06,
"loss": 0.9373,
"step": 780
},
{
"epoch": 0.64,
"learning_rate": 4.947334516668981e-06,
"loss": 0.8964,
"step": 785
},
{
"epoch": 0.64,
"learning_rate": 4.945515816849567e-06,
"loss": 0.9158,
"step": 790
},
{
"epoch": 0.64,
"learning_rate": 4.9436665909625555e-06,
"loss": 0.9352,
"step": 795
},
{
"epoch": 0.65,
"learning_rate": 4.941786862090842e-06,
"loss": 0.9417,
"step": 800
},
{
"epoch": 0.65,
"learning_rate": 4.9398766536980795e-06,
"loss": 1.0072,
"step": 805
},
{
"epoch": 0.66,
"learning_rate": 4.937935989628377e-06,
"loss": 0.9596,
"step": 810
},
{
"epoch": 0.66,
"learning_rate": 4.935964894106011e-06,
"loss": 0.9452,
"step": 815
},
{
"epoch": 0.66,
"learning_rate": 4.933963391735111e-06,
"loss": 0.9791,
"step": 820
},
{
"epoch": 0.67,
"learning_rate": 4.9319315074993626e-06,
"loss": 0.9491,
"step": 825
},
{
"epoch": 0.67,
"learning_rate": 4.929869266761692e-06,
"loss": 0.9722,
"step": 830
},
{
"epoch": 0.68,
"learning_rate": 4.9277766952639485e-06,
"loss": 0.9667,
"step": 835
},
{
"epoch": 0.68,
"learning_rate": 4.9256538191265836e-06,
"loss": 0.9705,
"step": 840
},
{
"epoch": 0.68,
"learning_rate": 4.923500664848327e-06,
"loss": 0.9772,
"step": 845
},
{
"epoch": 0.69,
"learning_rate": 4.921317259305852e-06,
"loss": 1.0082,
"step": 850
},
{
"epoch": 0.69,
"learning_rate": 4.9191036297534455e-06,
"loss": 0.957,
"step": 855
},
{
"epoch": 0.7,
"learning_rate": 4.916859803822662e-06,
"loss": 0.9832,
"step": 860
},
{
"epoch": 0.7,
"learning_rate": 4.914585809521982e-06,
"loss": 0.9521,
"step": 865
},
{
"epoch": 0.7,
"learning_rate": 4.912281675236461e-06,
"loss": 0.9631,
"step": 870
},
{
"epoch": 0.71,
"learning_rate": 4.909947429727378e-06,
"loss": 0.9403,
"step": 875
},
{
"epoch": 0.71,
"learning_rate": 4.907583102131871e-06,
"loss": 1.0201,
"step": 880
},
{
"epoch": 0.72,
"learning_rate": 4.905188721962579e-06,
"loss": 0.9873,
"step": 885
},
{
"epoch": 0.72,
"learning_rate": 4.902764319107271e-06,
"loss": 0.9681,
"step": 890
},
{
"epoch": 0.72,
"learning_rate": 4.900309923828474e-06,
"loss": 0.9125,
"step": 895
},
{
"epoch": 0.73,
"learning_rate": 4.89782556676309e-06,
"loss": 0.9349,
"step": 900
},
{
"epoch": 0.73,
"learning_rate": 4.895311278922023e-06,
"loss": 0.9779,
"step": 905
},
{
"epoch": 0.74,
"learning_rate": 4.892767091689786e-06,
"loss": 0.9427,
"step": 910
},
{
"epoch": 0.74,
"learning_rate": 4.890193036824107e-06,
"loss": 0.9845,
"step": 915
},
{
"epoch": 0.74,
"learning_rate": 4.88758914645554e-06,
"loss": 0.9601,
"step": 920
},
{
"epoch": 0.75,
"learning_rate": 4.884955453087056e-06,
"loss": 0.9894,
"step": 925
},
{
"epoch": 0.75,
"learning_rate": 4.882291989593644e-06,
"loss": 1.0139,
"step": 930
},
{
"epoch": 0.76,
"learning_rate": 4.879598789221893e-06,
"loss": 0.9599,
"step": 935
},
{
"epoch": 0.76,
"learning_rate": 4.876875885589589e-06,
"loss": 0.9855,
"step": 940
},
{
"epoch": 0.76,
"learning_rate": 4.87412331268528e-06,
"loss": 0.9763,
"step": 945
},
{
"epoch": 0.77,
"learning_rate": 4.8713411048678635e-06,
"loss": 0.946,
"step": 950
},
{
"epoch": 0.77,
"learning_rate": 4.868529296866156e-06,
"loss": 0.9446,
"step": 955
},
{
"epoch": 0.78,
"learning_rate": 4.865687923778452e-06,
"loss": 0.9792,
"step": 960
},
{
"epoch": 0.78,
"learning_rate": 4.862817021072096e-06,
"loss": 0.9644,
"step": 965
},
{
"epoch": 0.78,
"learning_rate": 4.8599166245830306e-06,
"loss": 0.9269,
"step": 970
},
{
"epoch": 0.79,
"learning_rate": 4.856986770515358e-06,
"loss": 0.9846,
"step": 975
},
{
"epoch": 0.79,
"learning_rate": 4.854027495440881e-06,
"loss": 0.9325,
"step": 980
},
{
"epoch": 0.8,
"learning_rate": 4.851038836298649e-06,
"loss": 0.968,
"step": 985
},
{
"epoch": 0.8,
"learning_rate": 4.848020830394498e-06,
"loss": 1.0115,
"step": 990
},
{
"epoch": 0.81,
"learning_rate": 4.844973515400584e-06,
"loss": 1.0004,
"step": 995
},
{
"epoch": 0.81,
"learning_rate": 4.8418969293549106e-06,
"loss": 0.9422,
"step": 1000
},
{
"epoch": 0.81,
"learning_rate": 4.83879111066086e-06,
"loss": 0.9617,
"step": 1005
},
{
"epoch": 0.82,
"learning_rate": 4.8356560980867064e-06,
"loss": 1.0238,
"step": 1010
},
{
"epoch": 0.82,
"learning_rate": 4.832491930765137e-06,
"loss": 0.9467,
"step": 1015
},
{
"epoch": 0.83,
"learning_rate": 4.829298648192763e-06,
"loss": 0.9567,
"step": 1020
},
{
"epoch": 0.83,
"learning_rate": 4.826076290229625e-06,
"loss": 0.9723,
"step": 1025
},
{
"epoch": 0.83,
"learning_rate": 4.822824897098697e-06,
"loss": 0.9852,
"step": 1030
},
{
"epoch": 0.84,
"learning_rate": 4.819544509385381e-06,
"loss": 0.9636,
"step": 1035
},
{
"epoch": 0.84,
"learning_rate": 4.8162351680370046e-06,
"loss": 0.9497,
"step": 1040
},
{
"epoch": 0.85,
"learning_rate": 4.81289691436231e-06,
"loss": 1.0008,
"step": 1045
},
{
"epoch": 0.85,
"learning_rate": 4.809529790030931e-06,
"loss": 1.0033,
"step": 1050
},
{
"epoch": 0.85,
"learning_rate": 4.806133837072886e-06,
"loss": 1.0142,
"step": 1055
},
{
"epoch": 0.86,
"learning_rate": 4.802709097878039e-06,
"loss": 0.9727,
"step": 1060
},
{
"epoch": 0.86,
"learning_rate": 4.799255615195582e-06,
"loss": 0.9863,
"step": 1065
},
{
"epoch": 0.87,
"learning_rate": 4.795773432133492e-06,
"loss": 0.984,
"step": 1070
},
{
"epoch": 0.87,
"learning_rate": 4.792262592158002e-06,
"loss": 0.9521,
"step": 1075
},
{
"epoch": 0.87,
"learning_rate": 4.788723139093051e-06,
"loss": 0.9497,
"step": 1080
},
{
"epoch": 0.88,
"learning_rate": 4.785155117119742e-06,
"loss": 1.0392,
"step": 1085
},
{
"epoch": 0.88,
"learning_rate": 4.781558570775787e-06,
"loss": 0.9197,
"step": 1090
},
{
"epoch": 0.89,
"learning_rate": 4.777933544954951e-06,
"loss": 1.0343,
"step": 1095
},
{
"epoch": 0.89,
"learning_rate": 4.774280084906498e-06,
"loss": 1.0113,
"step": 1100
},
{
"epoch": 0.89,
"learning_rate": 4.770598236234617e-06,
"loss": 0.9948,
"step": 1105
},
{
"epoch": 0.9,
"learning_rate": 4.766888044897856e-06,
"loss": 0.9312,
"step": 1110
},
{
"epoch": 0.9,
"learning_rate": 4.763149557208554e-06,
"loss": 0.9207,
"step": 1115
},
{
"epoch": 0.91,
"learning_rate": 4.759382819832256e-06,
"loss": 0.9621,
"step": 1120
},
{
"epoch": 0.91,
"learning_rate": 4.755587879787131e-06,
"loss": 1.0067,
"step": 1125
},
{
"epoch": 0.91,
"learning_rate": 4.75176478444339e-06,
"loss": 0.9758,
"step": 1130
},
{
"epoch": 0.92,
"learning_rate": 4.747913581522689e-06,
"loss": 0.9287,
"step": 1135
},
{
"epoch": 0.92,
"learning_rate": 4.744034319097536e-06,
"loss": 0.9803,
"step": 1140
},
{
"epoch": 0.93,
"learning_rate": 4.740127045590692e-06,
"loss": 1.0133,
"step": 1145
},
{
"epoch": 0.93,
"learning_rate": 4.736191809774567e-06,
"loss": 0.9588,
"step": 1150
},
{
"epoch": 0.93,
"learning_rate": 4.7322286607706056e-06,
"loss": 0.9763,
"step": 1155
},
{
"epoch": 0.94,
"learning_rate": 4.72823764804868e-06,
"loss": 0.9944,
"step": 1160
},
{
"epoch": 0.94,
"learning_rate": 4.724218821426472e-06,
"loss": 0.9897,
"step": 1165
},
{
"epoch": 0.95,
"learning_rate": 4.720172231068845e-06,
"loss": 0.9902,
"step": 1170
},
{
"epoch": 0.95,
"learning_rate": 4.716097927487225e-06,
"loss": 0.969,
"step": 1175
},
{
"epoch": 0.95,
"learning_rate": 4.711995961538969e-06,
"loss": 0.9458,
"step": 1180
},
{
"epoch": 0.96,
"learning_rate": 4.7078663844267245e-06,
"loss": 0.9782,
"step": 1185
},
{
"epoch": 0.96,
"learning_rate": 4.7037092476978e-06,
"loss": 0.9987,
"step": 1190
},
{
"epoch": 0.97,
"learning_rate": 4.699524603243509e-06,
"loss": 1.0171,
"step": 1195
},
{
"epoch": 0.97,
"learning_rate": 4.695312503298535e-06,
"loss": 0.9727,
"step": 1200
},
{
"epoch": 0.98,
"learning_rate": 4.69107300044027e-06,
"loss": 0.969,
"step": 1205
},
{
"epoch": 0.98,
"learning_rate": 4.686806147588166e-06,
"loss": 0.977,
"step": 1210
},
{
"epoch": 0.98,
"learning_rate": 4.6825119980030664e-06,
"loss": 0.9552,
"step": 1215
},
{
"epoch": 0.99,
"learning_rate": 4.678190605286546e-06,
"loss": 0.9912,
"step": 1220
},
{
"epoch": 0.99,
"learning_rate": 4.673842023380243e-06,
"loss": 0.9702,
"step": 1225
},
{
"epoch": 1.0,
"learning_rate": 4.669466306565181e-06,
"loss": 0.9792,
"step": 1230
},
{
"epoch": 1.0,
"learning_rate": 4.665063509461098e-06,
"loss": 1.0204,
"step": 1235
}
],
"max_steps": 4940,
"num_train_epochs": 4,
"total_flos": 6.117066158416855e+17,
"trial_name": null,
"trial_params": null
}