Crystalcareai's picture
Upload folder using huggingface_hub
7a23527 verified
raw
history blame contribute delete
No virus
43.8 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.2879683234844167,
"eval_steps": 500,
"global_step": 1800,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 4.9999964908081455e-05,
"loss": 0.7285,
"step": 5
},
{
"epoch": 0.0,
"learning_rate": 4.999985963242432e-05,
"loss": 0.6712,
"step": 10
},
{
"epoch": 0.0,
"learning_rate": 4.999968417332415e-05,
"loss": 0.6081,
"step": 15
},
{
"epoch": 0.0,
"learning_rate": 4.999943853127351e-05,
"loss": 0.6383,
"step": 20
},
{
"epoch": 0.0,
"learning_rate": 4.999912270696202e-05,
"loss": 0.6456,
"step": 25
},
{
"epoch": 0.0,
"learning_rate": 4.9998736701276295e-05,
"loss": 0.6228,
"step": 30
},
{
"epoch": 0.01,
"learning_rate": 4.99982805153e-05,
"loss": 0.6134,
"step": 35
},
{
"epoch": 0.01,
"learning_rate": 4.9997754150313815e-05,
"loss": 0.5975,
"step": 40
},
{
"epoch": 0.01,
"learning_rate": 4.999715760779541e-05,
"loss": 0.6053,
"step": 45
},
{
"epoch": 0.01,
"learning_rate": 4.9996490889419514e-05,
"loss": 0.6064,
"step": 50
},
{
"epoch": 0.01,
"learning_rate": 4.999575399705783e-05,
"loss": 0.5947,
"step": 55
},
{
"epoch": 0.01,
"learning_rate": 4.999494693277907e-05,
"loss": 0.5839,
"step": 60
},
{
"epoch": 0.01,
"learning_rate": 4.999406969884897e-05,
"loss": 0.6106,
"step": 65
},
{
"epoch": 0.01,
"learning_rate": 4.999312229773022e-05,
"loss": 0.6146,
"step": 70
},
{
"epoch": 0.01,
"learning_rate": 4.99921047320825e-05,
"loss": 0.5659,
"step": 75
},
{
"epoch": 0.01,
"learning_rate": 4.9991017004762496e-05,
"loss": 0.5682,
"step": 80
},
{
"epoch": 0.01,
"learning_rate": 4.998985911882384e-05,
"loss": 0.6352,
"step": 85
},
{
"epoch": 0.01,
"learning_rate": 4.998863107751711e-05,
"loss": 0.6018,
"step": 90
},
{
"epoch": 0.02,
"learning_rate": 4.998733288428987e-05,
"loss": 0.6342,
"step": 95
},
{
"epoch": 0.02,
"learning_rate": 4.9985964542786614e-05,
"loss": 0.5886,
"step": 100
},
{
"epoch": 0.02,
"learning_rate": 4.998452605684874e-05,
"loss": 0.6097,
"step": 105
},
{
"epoch": 0.02,
"learning_rate": 4.998301743051459e-05,
"loss": 0.5687,
"step": 110
},
{
"epoch": 0.02,
"learning_rate": 4.998143866801942e-05,
"loss": 0.5866,
"step": 115
},
{
"epoch": 0.02,
"learning_rate": 4.997978977379536e-05,
"loss": 0.5612,
"step": 120
},
{
"epoch": 0.02,
"learning_rate": 4.997807075247146e-05,
"loss": 0.6221,
"step": 125
},
{
"epoch": 0.02,
"learning_rate": 4.997628160887361e-05,
"loss": 0.5728,
"step": 130
},
{
"epoch": 0.02,
"learning_rate": 4.997442234802456e-05,
"loss": 0.6105,
"step": 135
},
{
"epoch": 0.02,
"learning_rate": 4.997249297514394e-05,
"loss": 0.6161,
"step": 140
},
{
"epoch": 0.02,
"learning_rate": 4.997049349564814e-05,
"loss": 0.6511,
"step": 145
},
{
"epoch": 0.02,
"learning_rate": 4.996842391515044e-05,
"loss": 0.6108,
"step": 150
},
{
"epoch": 0.02,
"learning_rate": 4.996628423946087e-05,
"loss": 0.5664,
"step": 155
},
{
"epoch": 0.03,
"learning_rate": 4.996407447458626e-05,
"loss": 0.6127,
"step": 160
},
{
"epoch": 0.03,
"learning_rate": 4.99617946267302e-05,
"loss": 0.6213,
"step": 165
},
{
"epoch": 0.03,
"learning_rate": 4.995944470229302e-05,
"loss": 0.596,
"step": 170
},
{
"epoch": 0.03,
"learning_rate": 4.9957024707871806e-05,
"loss": 0.5731,
"step": 175
},
{
"epoch": 0.03,
"learning_rate": 4.995453465026032e-05,
"loss": 0.5704,
"step": 180
},
{
"epoch": 0.03,
"learning_rate": 4.995197453644905e-05,
"loss": 0.5767,
"step": 185
},
{
"epoch": 0.03,
"learning_rate": 4.994934437362513e-05,
"loss": 0.6134,
"step": 190
},
{
"epoch": 0.03,
"learning_rate": 4.9946644169172355e-05,
"loss": 0.5919,
"step": 195
},
{
"epoch": 0.03,
"learning_rate": 4.994387393067117e-05,
"loss": 0.6031,
"step": 200
},
{
"epoch": 0.03,
"learning_rate": 4.994103366589859e-05,
"loss": 0.6236,
"step": 205
},
{
"epoch": 0.03,
"learning_rate": 4.993812338282826e-05,
"loss": 0.6307,
"step": 210
},
{
"epoch": 0.03,
"learning_rate": 4.993514308963036e-05,
"loss": 0.5618,
"step": 215
},
{
"epoch": 0.04,
"learning_rate": 4.993209279467164e-05,
"loss": 0.6093,
"step": 220
},
{
"epoch": 0.04,
"learning_rate": 4.992897250651535e-05,
"loss": 0.5744,
"step": 225
},
{
"epoch": 0.04,
"learning_rate": 4.992578223392124e-05,
"loss": 0.5844,
"step": 230
},
{
"epoch": 0.04,
"learning_rate": 4.992252198584554e-05,
"loss": 0.5358,
"step": 235
},
{
"epoch": 0.04,
"learning_rate": 4.9919191771440905e-05,
"loss": 0.6067,
"step": 240
},
{
"epoch": 0.04,
"learning_rate": 4.991579160005644e-05,
"loss": 0.6147,
"step": 245
},
{
"epoch": 0.04,
"learning_rate": 4.991232148123761e-05,
"loss": 0.6185,
"step": 250
},
{
"epoch": 0.04,
"learning_rate": 4.990878142472628e-05,
"loss": 0.5797,
"step": 255
},
{
"epoch": 0.04,
"learning_rate": 4.990517144046064e-05,
"loss": 0.58,
"step": 260
},
{
"epoch": 0.04,
"learning_rate": 4.9901491538575185e-05,
"loss": 0.6051,
"step": 265
},
{
"epoch": 0.04,
"learning_rate": 4.9897741729400705e-05,
"loss": 0.6199,
"step": 270
},
{
"epoch": 0.04,
"learning_rate": 4.9893922023464236e-05,
"loss": 0.6173,
"step": 275
},
{
"epoch": 0.04,
"learning_rate": 4.989003243148904e-05,
"loss": 0.5907,
"step": 280
},
{
"epoch": 0.05,
"learning_rate": 4.988607296439458e-05,
"loss": 0.5818,
"step": 285
},
{
"epoch": 0.05,
"learning_rate": 4.988204363329648e-05,
"loss": 0.5767,
"step": 290
},
{
"epoch": 0.05,
"learning_rate": 4.987794444950651e-05,
"loss": 0.579,
"step": 295
},
{
"epoch": 0.05,
"learning_rate": 4.987377542453251e-05,
"loss": 0.6454,
"step": 300
},
{
"epoch": 0.05,
"learning_rate": 4.986953657007841e-05,
"loss": 0.5777,
"step": 305
},
{
"epoch": 0.05,
"learning_rate": 4.986522789804417e-05,
"loss": 0.532,
"step": 310
},
{
"epoch": 0.05,
"learning_rate": 4.9860849420525766e-05,
"loss": 0.56,
"step": 315
},
{
"epoch": 0.05,
"learning_rate": 4.9856401149815126e-05,
"loss": 0.5624,
"step": 320
},
{
"epoch": 0.05,
"learning_rate": 4.985188309840012e-05,
"loss": 0.6008,
"step": 325
},
{
"epoch": 0.05,
"learning_rate": 4.9847295278964514e-05,
"loss": 0.6425,
"step": 330
},
{
"epoch": 0.05,
"learning_rate": 4.984263770438793e-05,
"loss": 0.5907,
"step": 335
},
{
"epoch": 0.05,
"learning_rate": 4.9837910387745845e-05,
"loss": 0.5926,
"step": 340
},
{
"epoch": 0.06,
"learning_rate": 4.98331133423095e-05,
"loss": 0.6115,
"step": 345
},
{
"epoch": 0.06,
"learning_rate": 4.982824658154589e-05,
"loss": 0.5685,
"step": 350
},
{
"epoch": 0.06,
"learning_rate": 4.982331011911774e-05,
"loss": 0.5412,
"step": 355
},
{
"epoch": 0.06,
"learning_rate": 4.981830396888344e-05,
"loss": 0.6032,
"step": 360
},
{
"epoch": 0.06,
"learning_rate": 4.981322814489703e-05,
"loss": 0.568,
"step": 365
},
{
"epoch": 0.06,
"learning_rate": 4.980808266140813e-05,
"loss": 0.5835,
"step": 370
},
{
"epoch": 0.06,
"learning_rate": 4.980286753286195e-05,
"loss": 0.5633,
"step": 375
},
{
"epoch": 0.06,
"learning_rate": 4.979758277389919e-05,
"loss": 0.574,
"step": 380
},
{
"epoch": 0.06,
"learning_rate": 4.979222839935602e-05,
"loss": 0.5774,
"step": 385
},
{
"epoch": 0.06,
"learning_rate": 4.9786804424264085e-05,
"loss": 0.5608,
"step": 390
},
{
"epoch": 0.06,
"learning_rate": 4.9781310863850405e-05,
"loss": 0.5659,
"step": 395
},
{
"epoch": 0.06,
"learning_rate": 4.977574773353732e-05,
"loss": 0.6167,
"step": 400
},
{
"epoch": 0.06,
"learning_rate": 4.977011504894252e-05,
"loss": 0.5523,
"step": 405
},
{
"epoch": 0.07,
"learning_rate": 4.9764412825878943e-05,
"loss": 0.5804,
"step": 410
},
{
"epoch": 0.07,
"learning_rate": 4.975864108035474e-05,
"loss": 0.5811,
"step": 415
},
{
"epoch": 0.07,
"learning_rate": 4.975279982857324e-05,
"loss": 0.5832,
"step": 420
},
{
"epoch": 0.07,
"learning_rate": 4.9746889086932895e-05,
"loss": 0.6035,
"step": 425
},
{
"epoch": 0.07,
"learning_rate": 4.974090887202726e-05,
"loss": 0.6077,
"step": 430
},
{
"epoch": 0.07,
"learning_rate": 4.9734859200644905e-05,
"loss": 0.6147,
"step": 435
},
{
"epoch": 0.07,
"learning_rate": 4.97287400897694e-05,
"loss": 0.6825,
"step": 440
},
{
"epoch": 0.07,
"learning_rate": 4.972255155657925e-05,
"loss": 0.5573,
"step": 445
},
{
"epoch": 0.07,
"learning_rate": 4.971629361844785e-05,
"loss": 0.5691,
"step": 450
},
{
"epoch": 0.07,
"learning_rate": 4.9709966292943455e-05,
"loss": 0.5768,
"step": 455
},
{
"epoch": 0.07,
"learning_rate": 4.970356959782909e-05,
"loss": 0.5953,
"step": 460
},
{
"epoch": 0.07,
"learning_rate": 4.9697103551062556e-05,
"loss": 0.6207,
"step": 465
},
{
"epoch": 0.08,
"learning_rate": 4.969056817079633e-05,
"loss": 0.5845,
"step": 470
},
{
"epoch": 0.08,
"learning_rate": 4.968396347537751e-05,
"loss": 0.5719,
"step": 475
},
{
"epoch": 0.08,
"learning_rate": 4.967728948334784e-05,
"loss": 0.5889,
"step": 480
},
{
"epoch": 0.08,
"learning_rate": 4.967054621344356e-05,
"loss": 0.5574,
"step": 485
},
{
"epoch": 0.08,
"learning_rate": 4.966373368459541e-05,
"loss": 0.6037,
"step": 490
},
{
"epoch": 0.08,
"learning_rate": 4.965685191592859e-05,
"loss": 0.5707,
"step": 495
},
{
"epoch": 0.08,
"learning_rate": 4.964990092676263e-05,
"loss": 0.6586,
"step": 500
},
{
"epoch": 0.08,
"learning_rate": 4.964288073661142e-05,
"loss": 0.5559,
"step": 505
},
{
"epoch": 0.08,
"learning_rate": 4.963579136518312e-05,
"loss": 0.5609,
"step": 510
},
{
"epoch": 0.08,
"learning_rate": 4.96286328323801e-05,
"loss": 0.6081,
"step": 515
},
{
"epoch": 0.08,
"learning_rate": 4.96214051582989e-05,
"loss": 0.5724,
"step": 520
},
{
"epoch": 0.08,
"learning_rate": 4.9614108363230135e-05,
"loss": 0.5758,
"step": 525
},
{
"epoch": 0.08,
"learning_rate": 4.960674246765851e-05,
"loss": 0.6191,
"step": 530
},
{
"epoch": 0.09,
"learning_rate": 4.959930749226269e-05,
"loss": 0.5638,
"step": 535
},
{
"epoch": 0.09,
"learning_rate": 4.959180345791528e-05,
"loss": 0.5698,
"step": 540
},
{
"epoch": 0.09,
"learning_rate": 4.958423038568274e-05,
"loss": 0.5878,
"step": 545
},
{
"epoch": 0.09,
"learning_rate": 4.9576588296825386e-05,
"loss": 0.5734,
"step": 550
},
{
"epoch": 0.09,
"learning_rate": 4.956887721279726e-05,
"loss": 0.606,
"step": 555
},
{
"epoch": 0.09,
"learning_rate": 4.956109715524608e-05,
"loss": 0.5871,
"step": 560
},
{
"epoch": 0.09,
"learning_rate": 4.955324814601324e-05,
"loss": 0.6306,
"step": 565
},
{
"epoch": 0.09,
"learning_rate": 4.9545330207133664e-05,
"loss": 0.6231,
"step": 570
},
{
"epoch": 0.09,
"learning_rate": 4.953734336083583e-05,
"loss": 0.6278,
"step": 575
},
{
"epoch": 0.09,
"learning_rate": 4.952928762954161e-05,
"loss": 0.5551,
"step": 580
},
{
"epoch": 0.09,
"learning_rate": 4.952116303586631e-05,
"loss": 0.6441,
"step": 585
},
{
"epoch": 0.09,
"learning_rate": 4.951296960261853e-05,
"loss": 0.5753,
"step": 590
},
{
"epoch": 0.1,
"learning_rate": 4.9504707352800125e-05,
"loss": 0.5458,
"step": 595
},
{
"epoch": 0.1,
"learning_rate": 4.949637630960617e-05,
"loss": 0.5668,
"step": 600
},
{
"epoch": 0.1,
"learning_rate": 4.948797649642484e-05,
"loss": 0.5727,
"step": 605
},
{
"epoch": 0.1,
"learning_rate": 4.9479507936837364e-05,
"loss": 0.628,
"step": 610
},
{
"epoch": 0.1,
"learning_rate": 4.947097065461801e-05,
"loss": 0.5958,
"step": 615
},
{
"epoch": 0.1,
"learning_rate": 4.946236467373392e-05,
"loss": 0.6173,
"step": 620
},
{
"epoch": 0.1,
"learning_rate": 4.9453690018345144e-05,
"loss": 0.5473,
"step": 625
},
{
"epoch": 0.1,
"learning_rate": 4.9444946712804494e-05,
"loss": 0.6012,
"step": 630
},
{
"epoch": 0.1,
"learning_rate": 4.943613478165753e-05,
"loss": 0.6303,
"step": 635
},
{
"epoch": 0.1,
"learning_rate": 4.9427254249642444e-05,
"loss": 0.6188,
"step": 640
},
{
"epoch": 0.1,
"learning_rate": 4.941830514169004e-05,
"loss": 0.6079,
"step": 645
},
{
"epoch": 0.1,
"learning_rate": 4.940928748292363e-05,
"loss": 0.5589,
"step": 650
},
{
"epoch": 0.1,
"learning_rate": 4.940020129865895e-05,
"loss": 0.5652,
"step": 655
},
{
"epoch": 0.11,
"learning_rate": 4.939104661440415e-05,
"loss": 0.5415,
"step": 660
},
{
"epoch": 0.11,
"learning_rate": 4.938182345585966e-05,
"loss": 0.5657,
"step": 665
},
{
"epoch": 0.11,
"learning_rate": 4.9372531848918145e-05,
"loss": 0.6403,
"step": 670
},
{
"epoch": 0.11,
"learning_rate": 4.9363171819664434e-05,
"loss": 0.6198,
"step": 675
},
{
"epoch": 0.11,
"learning_rate": 4.935374339437543e-05,
"loss": 0.5685,
"step": 680
},
{
"epoch": 0.11,
"learning_rate": 4.934424659952006e-05,
"loss": 0.5737,
"step": 685
},
{
"epoch": 0.11,
"learning_rate": 4.933468146175918e-05,
"loss": 0.5975,
"step": 690
},
{
"epoch": 0.11,
"learning_rate": 4.9325048007945526e-05,
"loss": 0.6033,
"step": 695
},
{
"epoch": 0.11,
"learning_rate": 4.9315346265123594e-05,
"loss": 0.6587,
"step": 700
},
{
"epoch": 0.11,
"learning_rate": 4.9305576260529607e-05,
"loss": 0.5903,
"step": 705
},
{
"epoch": 0.11,
"learning_rate": 4.929573802159143e-05,
"loss": 0.5883,
"step": 710
},
{
"epoch": 0.11,
"learning_rate": 4.9285831575928465e-05,
"loss": 0.6151,
"step": 715
},
{
"epoch": 0.12,
"learning_rate": 4.927585695135162e-05,
"loss": 0.5687,
"step": 720
},
{
"epoch": 0.12,
"learning_rate": 4.9265814175863186e-05,
"loss": 0.6008,
"step": 725
},
{
"epoch": 0.12,
"learning_rate": 4.925570327765678e-05,
"loss": 0.6045,
"step": 730
},
{
"epoch": 0.12,
"learning_rate": 4.9245524285117274e-05,
"loss": 0.5439,
"step": 735
},
{
"epoch": 0.12,
"learning_rate": 4.9235277226820695e-05,
"loss": 0.61,
"step": 740
},
{
"epoch": 0.12,
"learning_rate": 4.922496213153416e-05,
"loss": 0.5913,
"step": 745
},
{
"epoch": 0.12,
"learning_rate": 4.9214579028215776e-05,
"loss": 0.6255,
"step": 750
},
{
"epoch": 0.12,
"learning_rate": 4.920412794601461e-05,
"loss": 0.5834,
"step": 755
},
{
"epoch": 0.12,
"learning_rate": 4.9193608914270515e-05,
"loss": 0.6102,
"step": 760
},
{
"epoch": 0.12,
"learning_rate": 4.918302196251415e-05,
"loss": 0.5591,
"step": 765
},
{
"epoch": 0.12,
"learning_rate": 4.917236712046682e-05,
"loss": 0.556,
"step": 770
},
{
"epoch": 0.12,
"learning_rate": 4.916164441804044e-05,
"loss": 0.5774,
"step": 775
},
{
"epoch": 0.12,
"learning_rate": 4.9150853885337426e-05,
"loss": 0.6256,
"step": 780
},
{
"epoch": 0.13,
"learning_rate": 4.913999555265062e-05,
"loss": 0.6505,
"step": 785
},
{
"epoch": 0.13,
"learning_rate": 4.9129069450463186e-05,
"loss": 0.6012,
"step": 790
},
{
"epoch": 0.13,
"learning_rate": 4.911807560944858e-05,
"loss": 0.5913,
"step": 795
},
{
"epoch": 0.13,
"learning_rate": 4.910701406047037e-05,
"loss": 0.6963,
"step": 800
},
{
"epoch": 0.13,
"learning_rate": 4.909588483458225e-05,
"loss": 0.5588,
"step": 805
},
{
"epoch": 0.13,
"learning_rate": 4.9084687963027894e-05,
"loss": 0.6078,
"step": 810
},
{
"epoch": 0.13,
"learning_rate": 4.907342347724087e-05,
"loss": 0.5816,
"step": 815
},
{
"epoch": 0.13,
"learning_rate": 4.906209140884459e-05,
"loss": 0.5989,
"step": 820
},
{
"epoch": 0.13,
"learning_rate": 4.905069178965215e-05,
"loss": 0.5568,
"step": 825
},
{
"epoch": 0.13,
"learning_rate": 4.9039224651666325e-05,
"loss": 0.6021,
"step": 830
},
{
"epoch": 0.13,
"learning_rate": 4.902769002707942e-05,
"loss": 0.6009,
"step": 835
},
{
"epoch": 0.13,
"learning_rate": 4.90160879482732e-05,
"loss": 0.5801,
"step": 840
},
{
"epoch": 0.14,
"learning_rate": 4.9004418447818815e-05,
"loss": 0.5939,
"step": 845
},
{
"epoch": 0.14,
"learning_rate": 4.899268155847667e-05,
"loss": 0.6027,
"step": 850
},
{
"epoch": 0.14,
"learning_rate": 4.898087731319636e-05,
"loss": 0.5416,
"step": 855
},
{
"epoch": 0.14,
"learning_rate": 4.896900574511657e-05,
"loss": 0.5596,
"step": 860
},
{
"epoch": 0.14,
"learning_rate": 4.8957066887565e-05,
"loss": 0.6187,
"step": 865
},
{
"epoch": 0.14,
"learning_rate": 4.894506077405824e-05,
"loss": 0.5733,
"step": 870
},
{
"epoch": 0.14,
"learning_rate": 4.893298743830168e-05,
"loss": 0.5862,
"step": 875
},
{
"epoch": 0.14,
"learning_rate": 4.892084691418947e-05,
"loss": 0.6191,
"step": 880
},
{
"epoch": 0.14,
"learning_rate": 4.8908639235804324e-05,
"loss": 0.6258,
"step": 885
},
{
"epoch": 0.14,
"learning_rate": 4.889636443741752e-05,
"loss": 0.5504,
"step": 890
},
{
"epoch": 0.14,
"learning_rate": 4.888402255348876e-05,
"loss": 0.6241,
"step": 895
},
{
"epoch": 0.14,
"learning_rate": 4.887161361866608e-05,
"loss": 0.5839,
"step": 900
},
{
"epoch": 0.14,
"learning_rate": 4.8859137667785735e-05,
"loss": 0.5797,
"step": 905
},
{
"epoch": 0.15,
"learning_rate": 4.884659473587213e-05,
"loss": 0.6189,
"step": 910
},
{
"epoch": 0.15,
"learning_rate": 4.8833984858137715e-05,
"loss": 0.6194,
"step": 915
},
{
"epoch": 0.15,
"learning_rate": 4.8821308069982867e-05,
"loss": 0.585,
"step": 920
},
{
"epoch": 0.15,
"learning_rate": 4.880856440699582e-05,
"loss": 0.582,
"step": 925
},
{
"epoch": 0.15,
"learning_rate": 4.8795753904952534e-05,
"loss": 0.5789,
"step": 930
},
{
"epoch": 0.15,
"learning_rate": 4.878287659981662e-05,
"loss": 0.6236,
"step": 935
},
{
"epoch": 0.15,
"learning_rate": 4.8769932527739225e-05,
"loss": 0.5614,
"step": 940
},
{
"epoch": 0.15,
"learning_rate": 4.8756921725058934e-05,
"loss": 0.5972,
"step": 945
},
{
"epoch": 0.15,
"learning_rate": 4.874384422830167e-05,
"loss": 0.5682,
"step": 950
},
{
"epoch": 0.15,
"learning_rate": 4.873070007418059e-05,
"loss": 0.6327,
"step": 955
},
{
"epoch": 0.15,
"learning_rate": 4.871748929959598e-05,
"loss": 0.5577,
"step": 960
},
{
"epoch": 0.15,
"learning_rate": 4.870421194163515e-05,
"loss": 0.56,
"step": 965
},
{
"epoch": 0.16,
"learning_rate": 4.8690868037572346e-05,
"loss": 0.6324,
"step": 970
},
{
"epoch": 0.16,
"learning_rate": 4.867745762486861e-05,
"loss": 0.5764,
"step": 975
},
{
"epoch": 0.16,
"learning_rate": 4.8663980741171724e-05,
"loss": 0.564,
"step": 980
},
{
"epoch": 0.16,
"learning_rate": 4.865043742431605e-05,
"loss": 0.5534,
"step": 985
},
{
"epoch": 0.16,
"learning_rate": 4.863682771232248e-05,
"loss": 0.5953,
"step": 990
},
{
"epoch": 0.16,
"learning_rate": 4.862315164339829e-05,
"loss": 0.4992,
"step": 995
},
{
"epoch": 0.16,
"learning_rate": 4.860940925593703e-05,
"loss": 0.6061,
"step": 1000
},
{
"epoch": 0.16,
"learning_rate": 4.859560058851844e-05,
"loss": 0.5429,
"step": 1005
},
{
"epoch": 0.16,
"learning_rate": 4.8581725679908317e-05,
"loss": 0.6121,
"step": 1010
},
{
"epoch": 0.16,
"learning_rate": 4.856778456905846e-05,
"loss": 0.5678,
"step": 1015
},
{
"epoch": 0.16,
"learning_rate": 4.855377729510648e-05,
"loss": 0.633,
"step": 1020
},
{
"epoch": 0.16,
"learning_rate": 4.8539703897375755e-05,
"loss": 0.6405,
"step": 1025
},
{
"epoch": 0.16,
"learning_rate": 4.852556441537528e-05,
"loss": 0.5485,
"step": 1030
},
{
"epoch": 0.17,
"learning_rate": 4.851135888879958e-05,
"loss": 0.5974,
"step": 1035
},
{
"epoch": 0.17,
"learning_rate": 4.849708735752859e-05,
"loss": 0.582,
"step": 1040
},
{
"epoch": 0.17,
"learning_rate": 4.848274986162754e-05,
"loss": 0.5806,
"step": 1045
},
{
"epoch": 0.17,
"learning_rate": 4.846834644134686e-05,
"loss": 0.6104,
"step": 1050
},
{
"epoch": 0.17,
"learning_rate": 4.845387713712203e-05,
"loss": 0.6216,
"step": 1055
},
{
"epoch": 0.17,
"learning_rate": 4.84393419895735e-05,
"loss": 0.612,
"step": 1060
},
{
"epoch": 0.17,
"learning_rate": 4.8424741039506575e-05,
"loss": 0.6155,
"step": 1065
},
{
"epoch": 0.17,
"learning_rate": 4.841007432791129e-05,
"loss": 0.5703,
"step": 1070
},
{
"epoch": 0.17,
"learning_rate": 4.839534189596228e-05,
"loss": 0.6044,
"step": 1075
},
{
"epoch": 0.17,
"learning_rate": 4.8380543785018677e-05,
"loss": 0.5819,
"step": 1080
},
{
"epoch": 0.17,
"learning_rate": 4.8365680036624026e-05,
"loss": 0.617,
"step": 1085
},
{
"epoch": 0.17,
"learning_rate": 4.835075069250613e-05,
"loss": 0.5707,
"step": 1090
},
{
"epoch": 0.18,
"learning_rate": 4.833575579457691e-05,
"loss": 0.6348,
"step": 1095
},
{
"epoch": 0.18,
"learning_rate": 4.832069538493237e-05,
"loss": 0.6339,
"step": 1100
},
{
"epoch": 0.18,
"learning_rate": 4.830556950585238e-05,
"loss": 0.5982,
"step": 1105
},
{
"epoch": 0.18,
"learning_rate": 4.829037819980065e-05,
"loss": 0.6028,
"step": 1110
},
{
"epoch": 0.18,
"learning_rate": 4.827512150942454e-05,
"loss": 0.5936,
"step": 1115
},
{
"epoch": 0.18,
"learning_rate": 4.8259799477554965e-05,
"loss": 0.5548,
"step": 1120
},
{
"epoch": 0.18,
"learning_rate": 4.8244412147206284e-05,
"loss": 0.5489,
"step": 1125
},
{
"epoch": 0.18,
"learning_rate": 4.822895956157619e-05,
"loss": 0.5788,
"step": 1130
},
{
"epoch": 0.18,
"learning_rate": 4.821344176404554e-05,
"loss": 0.582,
"step": 1135
},
{
"epoch": 0.18,
"learning_rate": 4.819785879817827e-05,
"loss": 0.5842,
"step": 1140
},
{
"epoch": 0.18,
"learning_rate": 4.8182210707721284e-05,
"loss": 0.6084,
"step": 1145
},
{
"epoch": 0.18,
"learning_rate": 4.81664975366043e-05,
"loss": 0.5531,
"step": 1150
},
{
"epoch": 0.18,
"learning_rate": 4.8150719328939755e-05,
"loss": 0.6259,
"step": 1155
},
{
"epoch": 0.19,
"learning_rate": 4.813487612902264e-05,
"loss": 0.5519,
"step": 1160
},
{
"epoch": 0.19,
"learning_rate": 4.811896798133042e-05,
"loss": 0.6005,
"step": 1165
},
{
"epoch": 0.19,
"learning_rate": 4.810299493052289e-05,
"loss": 0.5513,
"step": 1170
},
{
"epoch": 0.19,
"learning_rate": 4.808695702144206e-05,
"loss": 0.5715,
"step": 1175
},
{
"epoch": 0.19,
"learning_rate": 4.8070854299111994e-05,
"loss": 0.6532,
"step": 1180
},
{
"epoch": 0.19,
"learning_rate": 4.805468680873874e-05,
"loss": 0.5866,
"step": 1185
},
{
"epoch": 0.19,
"learning_rate": 4.803845459571014e-05,
"loss": 0.6018,
"step": 1190
},
{
"epoch": 0.19,
"learning_rate": 4.802215770559577e-05,
"loss": 0.6073,
"step": 1195
},
{
"epoch": 0.19,
"learning_rate": 4.800579618414676e-05,
"loss": 0.5287,
"step": 1200
},
{
"epoch": 0.19,
"learning_rate": 4.798937007729568e-05,
"loss": 0.5423,
"step": 1205
},
{
"epoch": 0.19,
"learning_rate": 4.797287943115641e-05,
"loss": 0.6094,
"step": 1210
},
{
"epoch": 0.19,
"learning_rate": 4.795632429202405e-05,
"loss": 0.5528,
"step": 1215
},
{
"epoch": 0.2,
"learning_rate": 4.793970470637469e-05,
"loss": 0.5419,
"step": 1220
},
{
"epoch": 0.2,
"learning_rate": 4.7923020720865414e-05,
"loss": 0.5872,
"step": 1225
},
{
"epoch": 0.2,
"learning_rate": 4.790627238233405e-05,
"loss": 0.6098,
"step": 1230
},
{
"epoch": 0.2,
"learning_rate": 4.78894597377991e-05,
"loss": 0.5886,
"step": 1235
},
{
"epoch": 0.2,
"learning_rate": 4.787258283445962e-05,
"loss": 0.5771,
"step": 1240
},
{
"epoch": 0.2,
"learning_rate": 4.7855641719695023e-05,
"loss": 0.5927,
"step": 1245
},
{
"epoch": 0.2,
"learning_rate": 4.783863644106502e-05,
"loss": 0.6261,
"step": 1250
},
{
"epoch": 0.2,
"learning_rate": 4.782156704630944e-05,
"loss": 0.5632,
"step": 1255
},
{
"epoch": 0.2,
"learning_rate": 4.78044335833481e-05,
"loss": 0.5792,
"step": 1260
},
{
"epoch": 0.2,
"learning_rate": 4.7787236100280685e-05,
"loss": 0.5769,
"step": 1265
},
{
"epoch": 0.2,
"learning_rate": 4.776997464538662e-05,
"loss": 0.5745,
"step": 1270
},
{
"epoch": 0.2,
"learning_rate": 4.775264926712489e-05,
"loss": 0.6351,
"step": 1275
},
{
"epoch": 0.2,
"learning_rate": 4.7735260014133986e-05,
"loss": 0.579,
"step": 1280
},
{
"epoch": 0.21,
"learning_rate": 4.7717806935231665e-05,
"loss": 0.5666,
"step": 1285
},
{
"epoch": 0.21,
"learning_rate": 4.7700290079414896e-05,
"loss": 0.6307,
"step": 1290
},
{
"epoch": 0.21,
"learning_rate": 4.768270949585968e-05,
"loss": 0.5851,
"step": 1295
},
{
"epoch": 0.21,
"learning_rate": 4.7665065233920945e-05,
"loss": 0.5708,
"step": 1300
},
{
"epoch": 0.21,
"learning_rate": 4.764735734313236e-05,
"loss": 0.5636,
"step": 1305
},
{
"epoch": 0.21,
"learning_rate": 4.7629585873206226e-05,
"loss": 0.5088,
"step": 1310
},
{
"epoch": 0.21,
"learning_rate": 4.7611750874033356e-05,
"loss": 0.5499,
"step": 1315
},
{
"epoch": 0.21,
"learning_rate": 4.759385239568289e-05,
"loss": 0.6735,
"step": 1320
},
{
"epoch": 0.21,
"learning_rate": 4.7575890488402185e-05,
"loss": 0.5632,
"step": 1325
},
{
"epoch": 0.21,
"learning_rate": 4.7557865202616656e-05,
"loss": 0.6031,
"step": 1330
},
{
"epoch": 0.21,
"learning_rate": 4.753977658892967e-05,
"loss": 0.6018,
"step": 1335
},
{
"epoch": 0.21,
"learning_rate": 4.752162469812234e-05,
"loss": 0.6149,
"step": 1340
},
{
"epoch": 0.22,
"learning_rate": 4.750340958115346e-05,
"loss": 0.5546,
"step": 1345
},
{
"epoch": 0.22,
"learning_rate": 4.7485131289159276e-05,
"loss": 0.5916,
"step": 1350
},
{
"epoch": 0.22,
"learning_rate": 4.7466789873453444e-05,
"loss": 0.5895,
"step": 1355
},
{
"epoch": 0.22,
"learning_rate": 4.744838538552677e-05,
"loss": 0.5661,
"step": 1360
},
{
"epoch": 0.22,
"learning_rate": 4.742991787704719e-05,
"loss": 0.6178,
"step": 1365
},
{
"epoch": 0.22,
"learning_rate": 4.741138739985951e-05,
"loss": 0.5959,
"step": 1370
},
{
"epoch": 0.22,
"learning_rate": 4.7392794005985326e-05,
"loss": 0.616,
"step": 1375
},
{
"epoch": 0.22,
"learning_rate": 4.737413774762287e-05,
"loss": 0.5876,
"step": 1380
},
{
"epoch": 0.22,
"learning_rate": 4.735541867714687e-05,
"loss": 0.5682,
"step": 1385
},
{
"epoch": 0.22,
"learning_rate": 4.733663684710835e-05,
"loss": 0.5658,
"step": 1390
},
{
"epoch": 0.22,
"learning_rate": 4.731779231023456e-05,
"loss": 0.5918,
"step": 1395
},
{
"epoch": 0.22,
"learning_rate": 4.7298885119428773e-05,
"loss": 0.6711,
"step": 1400
},
{
"epoch": 0.22,
"learning_rate": 4.7279915327770155e-05,
"loss": 0.5422,
"step": 1405
},
{
"epoch": 0.23,
"learning_rate": 4.7260882988513624e-05,
"loss": 0.6287,
"step": 1410
},
{
"epoch": 0.23,
"learning_rate": 4.724178815508967e-05,
"loss": 0.5955,
"step": 1415
},
{
"epoch": 0.23,
"learning_rate": 4.722263088110426e-05,
"loss": 0.6084,
"step": 1420
},
{
"epoch": 0.23,
"learning_rate": 4.720341122033862e-05,
"loss": 0.6089,
"step": 1425
},
{
"epoch": 0.23,
"learning_rate": 4.718412922674913e-05,
"loss": 0.6556,
"step": 1430
},
{
"epoch": 0.23,
"learning_rate": 4.7164784954467166e-05,
"loss": 0.5925,
"step": 1435
},
{
"epoch": 0.23,
"learning_rate": 4.714537845779894e-05,
"loss": 0.5911,
"step": 1440
},
{
"epoch": 0.23,
"learning_rate": 4.712590979122534e-05,
"loss": 0.5733,
"step": 1445
},
{
"epoch": 0.23,
"learning_rate": 4.710637900940181e-05,
"loss": 0.5898,
"step": 1450
},
{
"epoch": 0.23,
"learning_rate": 4.708678616715815e-05,
"loss": 0.5964,
"step": 1455
},
{
"epoch": 0.23,
"learning_rate": 4.706713131949839e-05,
"loss": 0.5852,
"step": 1460
},
{
"epoch": 0.23,
"learning_rate": 4.7047414521600644e-05,
"loss": 0.5726,
"step": 1465
},
{
"epoch": 0.24,
"learning_rate": 4.702763582881692e-05,
"loss": 0.5815,
"step": 1470
},
{
"epoch": 0.24,
"learning_rate": 4.7007795296673006e-05,
"loss": 0.5841,
"step": 1475
},
{
"epoch": 0.24,
"learning_rate": 4.6987892980868296e-05,
"loss": 0.5809,
"step": 1480
},
{
"epoch": 0.24,
"learning_rate": 4.696792893727562e-05,
"loss": 0.6363,
"step": 1485
},
{
"epoch": 0.24,
"learning_rate": 4.694790322194111e-05,
"loss": 0.5972,
"step": 1490
},
{
"epoch": 0.24,
"learning_rate": 4.692781589108402e-05,
"loss": 0.5575,
"step": 1495
},
{
"epoch": 0.24,
"learning_rate": 4.690766700109659e-05,
"loss": 0.5728,
"step": 1500
},
{
"epoch": 0.24,
"learning_rate": 4.688745660854388e-05,
"loss": 0.5417,
"step": 1505
},
{
"epoch": 0.24,
"learning_rate": 4.686718477016361e-05,
"loss": 0.6384,
"step": 1510
},
{
"epoch": 0.24,
"learning_rate": 4.684685154286599e-05,
"loss": 0.5762,
"step": 1515
},
{
"epoch": 0.24,
"learning_rate": 4.682645698373357e-05,
"loss": 0.5872,
"step": 1520
},
{
"epoch": 0.24,
"learning_rate": 4.68060011500211e-05,
"loss": 0.5602,
"step": 1525
},
{
"epoch": 0.24,
"learning_rate": 4.678548409915532e-05,
"loss": 0.5751,
"step": 1530
},
{
"epoch": 0.25,
"learning_rate": 4.676490588873486e-05,
"loss": 0.6352,
"step": 1535
},
{
"epoch": 0.25,
"learning_rate": 4.674426657653003e-05,
"loss": 0.587,
"step": 1540
},
{
"epoch": 0.25,
"learning_rate": 4.6723566220482664e-05,
"loss": 0.5306,
"step": 1545
},
{
"epoch": 0.25,
"learning_rate": 4.670280487870598e-05,
"loss": 0.5265,
"step": 1550
},
{
"epoch": 0.25,
"learning_rate": 4.6681982609484416e-05,
"loss": 0.5383,
"step": 1555
},
{
"epoch": 0.25,
"learning_rate": 4.666109947127343e-05,
"loss": 0.55,
"step": 1560
},
{
"epoch": 0.25,
"learning_rate": 4.6640155522699374e-05,
"loss": 0.5342,
"step": 1565
},
{
"epoch": 0.25,
"learning_rate": 4.661915082255932e-05,
"loss": 0.5897,
"step": 1570
},
{
"epoch": 0.25,
"learning_rate": 4.659808542982088e-05,
"loss": 0.5637,
"step": 1575
},
{
"epoch": 0.25,
"learning_rate": 4.657695940362207e-05,
"loss": 0.5857,
"step": 1580
},
{
"epoch": 0.25,
"learning_rate": 4.65557728032711e-05,
"loss": 0.5664,
"step": 1585
},
{
"epoch": 0.25,
"learning_rate": 4.653452568824625e-05,
"loss": 0.5778,
"step": 1590
},
{
"epoch": 0.26,
"learning_rate": 4.651321811819568e-05,
"loss": 0.5741,
"step": 1595
},
{
"epoch": 0.26,
"learning_rate": 4.649185015293728e-05,
"loss": 0.5822,
"step": 1600
},
{
"epoch": 0.26,
"learning_rate": 4.647042185245847e-05,
"loss": 0.5923,
"step": 1605
},
{
"epoch": 0.26,
"learning_rate": 4.6448933276916076e-05,
"loss": 0.5621,
"step": 1610
},
{
"epoch": 0.26,
"learning_rate": 4.6427384486636113e-05,
"loss": 0.5731,
"step": 1615
},
{
"epoch": 0.26,
"learning_rate": 4.640577554211366e-05,
"loss": 0.5662,
"step": 1620
},
{
"epoch": 0.26,
"learning_rate": 4.638410650401267e-05,
"loss": 0.5628,
"step": 1625
},
{
"epoch": 0.26,
"learning_rate": 4.636237743316578e-05,
"loss": 0.5775,
"step": 1630
},
{
"epoch": 0.26,
"learning_rate": 4.634058839057417e-05,
"loss": 0.5749,
"step": 1635
},
{
"epoch": 0.26,
"learning_rate": 4.63187394374074e-05,
"loss": 0.6108,
"step": 1640
},
{
"epoch": 0.26,
"learning_rate": 4.629683063500319e-05,
"loss": 0.5746,
"step": 1645
},
{
"epoch": 0.26,
"learning_rate": 4.6274862044867304e-05,
"loss": 0.579,
"step": 1650
},
{
"epoch": 0.26,
"learning_rate": 4.625283372867333e-05,
"loss": 0.566,
"step": 1655
},
{
"epoch": 0.27,
"learning_rate": 4.623074574826254e-05,
"loss": 0.6109,
"step": 1660
},
{
"epoch": 0.27,
"learning_rate": 4.6208598165643715e-05,
"loss": 0.5497,
"step": 1665
},
{
"epoch": 0.27,
"learning_rate": 4.618639104299294e-05,
"loss": 0.5226,
"step": 1670
},
{
"epoch": 0.27,
"learning_rate": 4.616412444265345e-05,
"loss": 0.5861,
"step": 1675
},
{
"epoch": 0.27,
"learning_rate": 4.614179842713547e-05,
"loss": 0.6045,
"step": 1680
},
{
"epoch": 0.27,
"learning_rate": 4.611941305911602e-05,
"loss": 0.5793,
"step": 1685
},
{
"epoch": 0.27,
"learning_rate": 4.6096968401438745e-05,
"loss": 0.5975,
"step": 1690
},
{
"epoch": 0.27,
"learning_rate": 4.607446451711372e-05,
"loss": 0.5727,
"step": 1695
},
{
"epoch": 0.27,
"learning_rate": 4.605190146931731e-05,
"loss": 0.5874,
"step": 1700
},
{
"epoch": 0.27,
"learning_rate": 4.602927932139197e-05,
"loss": 0.5785,
"step": 1705
},
{
"epoch": 0.27,
"learning_rate": 4.6006598136846056e-05,
"loss": 0.5767,
"step": 1710
},
{
"epoch": 0.27,
"learning_rate": 4.598385797935368e-05,
"loss": 0.5695,
"step": 1715
},
{
"epoch": 0.28,
"learning_rate": 4.596105891275449e-05,
"loss": 0.6196,
"step": 1720
},
{
"epoch": 0.28,
"learning_rate": 4.593820100105355e-05,
"loss": 0.6025,
"step": 1725
},
{
"epoch": 0.28,
"learning_rate": 4.591528430842107e-05,
"loss": 0.5807,
"step": 1730
},
{
"epoch": 0.28,
"learning_rate": 4.589230889919232e-05,
"loss": 0.4916,
"step": 1735
},
{
"epoch": 0.28,
"learning_rate": 4.5869274837867394e-05,
"loss": 0.595,
"step": 1740
},
{
"epoch": 0.28,
"learning_rate": 4.5846182189111035e-05,
"loss": 0.5592,
"step": 1745
},
{
"epoch": 0.28,
"learning_rate": 4.5823031017752485e-05,
"loss": 0.5677,
"step": 1750
},
{
"epoch": 0.28,
"learning_rate": 4.579982138878527e-05,
"loss": 0.5988,
"step": 1755
},
{
"epoch": 0.28,
"learning_rate": 4.5776553367367e-05,
"loss": 0.5468,
"step": 1760
},
{
"epoch": 0.28,
"learning_rate": 4.575322701881926e-05,
"loss": 0.6078,
"step": 1765
},
{
"epoch": 0.28,
"learning_rate": 4.5729842408627334e-05,
"loss": 0.5498,
"step": 1770
},
{
"epoch": 0.28,
"learning_rate": 4.5706399602440106e-05,
"loss": 0.6135,
"step": 1775
},
{
"epoch": 0.28,
"learning_rate": 4.568289866606981e-05,
"loss": 0.568,
"step": 1780
},
{
"epoch": 0.29,
"learning_rate": 4.565933966549189e-05,
"loss": 0.6276,
"step": 1785
},
{
"epoch": 0.29,
"learning_rate": 4.5635722666844775e-05,
"loss": 0.5823,
"step": 1790
},
{
"epoch": 0.29,
"learning_rate": 4.561204773642974e-05,
"loss": 0.6211,
"step": 1795
},
{
"epoch": 0.29,
"learning_rate": 4.558831494071069e-05,
"loss": 0.584,
"step": 1800
}
],
"logging_steps": 5,
"max_steps": 9375,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 100,
"total_flos": 4.147591830287155e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}