ZhongJing-2-0_5b2 / checkpoint-1800 /trainer_state.json
CMLL's picture
Upload folder using huggingface_hub
5561d3a verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.7094994087504927,
"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": 1.999997870262096e-05,
"loss": 2.714,
"step": 5
},
{
"epoch": 0.0,
"learning_rate": 1.999991481057455e-05,
"loss": 2.7679,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 1.9999808324132915e-05,
"loss": 2.6887,
"step": 15
},
{
"epoch": 0.01,
"learning_rate": 1.999965924374964e-05,
"loss": 2.6986,
"step": 20
},
{
"epoch": 0.01,
"learning_rate": 1.999946757005972e-05,
"loss": 2.7536,
"step": 25
},
{
"epoch": 0.01,
"learning_rate": 1.9999233303879592e-05,
"loss": 2.7516,
"step": 30
},
{
"epoch": 0.01,
"learning_rate": 1.99989564462071e-05,
"loss": 2.6283,
"step": 35
},
{
"epoch": 0.02,
"learning_rate": 1.999863699822152e-05,
"loss": 2.708,
"step": 40
},
{
"epoch": 0.02,
"learning_rate": 1.9998274961283523e-05,
"loss": 2.6932,
"step": 45
},
{
"epoch": 0.02,
"learning_rate": 1.9997870336935207e-05,
"loss": 2.6321,
"step": 50
},
{
"epoch": 0.02,
"learning_rate": 1.9997423126900056e-05,
"loss": 2.7129,
"step": 55
},
{
"epoch": 0.02,
"learning_rate": 1.9996933333082945e-05,
"loss": 2.6179,
"step": 60
},
{
"epoch": 0.03,
"learning_rate": 1.9996400957570148e-05,
"loss": 2.6052,
"step": 65
},
{
"epoch": 0.03,
"learning_rate": 1.99958260026293e-05,
"loss": 2.7054,
"step": 70
},
{
"epoch": 0.03,
"learning_rate": 1.9995208470709405e-05,
"loss": 2.6568,
"step": 75
},
{
"epoch": 0.03,
"learning_rate": 1.9994548364440836e-05,
"loss": 2.6436,
"step": 80
},
{
"epoch": 0.03,
"learning_rate": 1.999384568663529e-05,
"loss": 2.7091,
"step": 85
},
{
"epoch": 0.04,
"learning_rate": 1.9993100440285805e-05,
"loss": 2.5557,
"step": 90
},
{
"epoch": 0.04,
"learning_rate": 1.999231262856675e-05,
"loss": 2.5945,
"step": 95
},
{
"epoch": 0.04,
"learning_rate": 1.999148225483378e-05,
"loss": 2.4729,
"step": 100
},
{
"epoch": 0.04,
"learning_rate": 1.9990609322623854e-05,
"loss": 2.6724,
"step": 105
},
{
"epoch": 0.04,
"learning_rate": 1.9989693835655205e-05,
"loss": 2.5272,
"step": 110
},
{
"epoch": 0.05,
"learning_rate": 1.9988735797827336e-05,
"loss": 2.6145,
"step": 115
},
{
"epoch": 0.05,
"learning_rate": 1.9987735213220975e-05,
"loss": 2.6772,
"step": 120
},
{
"epoch": 0.05,
"learning_rate": 1.9986692086098095e-05,
"loss": 2.6388,
"step": 125
},
{
"epoch": 0.05,
"learning_rate": 1.998560642090187e-05,
"loss": 2.4973,
"step": 130
},
{
"epoch": 0.05,
"learning_rate": 1.998447822225666e-05,
"loss": 2.5338,
"step": 135
},
{
"epoch": 0.06,
"learning_rate": 1.9983307494968e-05,
"loss": 2.6469,
"step": 140
},
{
"epoch": 0.06,
"learning_rate": 1.9982094244022582e-05,
"loss": 2.6008,
"step": 145
},
{
"epoch": 0.06,
"learning_rate": 1.9980838474588214e-05,
"loss": 2.5936,
"step": 150
},
{
"epoch": 0.06,
"learning_rate": 1.9979540192013814e-05,
"loss": 2.5862,
"step": 155
},
{
"epoch": 0.06,
"learning_rate": 1.997819940182939e-05,
"loss": 2.568,
"step": 160
},
{
"epoch": 0.07,
"learning_rate": 1.9976816109746e-05,
"loss": 2.5343,
"step": 165
},
{
"epoch": 0.07,
"learning_rate": 1.9975390321655745e-05,
"loss": 2.5575,
"step": 170
},
{
"epoch": 0.07,
"learning_rate": 1.9973922043631737e-05,
"loss": 2.5399,
"step": 175
},
{
"epoch": 0.07,
"learning_rate": 1.9972411281928068e-05,
"loss": 2.6394,
"step": 180
},
{
"epoch": 0.07,
"learning_rate": 1.9970858042979794e-05,
"loss": 2.5378,
"step": 185
},
{
"epoch": 0.07,
"learning_rate": 1.9969262333402893e-05,
"loss": 2.5373,
"step": 190
},
{
"epoch": 0.08,
"learning_rate": 1.9967624159994262e-05,
"loss": 2.5414,
"step": 195
},
{
"epoch": 0.08,
"learning_rate": 1.9965943529731646e-05,
"loss": 2.5606,
"step": 200
},
{
"epoch": 0.08,
"learning_rate": 1.9964220449773664e-05,
"loss": 2.5154,
"step": 205
},
{
"epoch": 0.08,
"learning_rate": 1.9962454927459723e-05,
"loss": 2.5468,
"step": 210
},
{
"epoch": 0.08,
"learning_rate": 1.9960646970310027e-05,
"loss": 2.5137,
"step": 215
},
{
"epoch": 0.09,
"learning_rate": 1.9958796586025527e-05,
"loss": 2.5453,
"step": 220
},
{
"epoch": 0.09,
"learning_rate": 1.9956903782487885e-05,
"loss": 2.5325,
"step": 225
},
{
"epoch": 0.09,
"learning_rate": 1.9954968567759456e-05,
"loss": 2.5054,
"step": 230
},
{
"epoch": 0.09,
"learning_rate": 1.9952990950083236e-05,
"loss": 2.5139,
"step": 235
},
{
"epoch": 0.09,
"learning_rate": 1.995097093788285e-05,
"loss": 2.5097,
"step": 240
},
{
"epoch": 0.1,
"learning_rate": 1.994890853976248e-05,
"loss": 2.5546,
"step": 245
},
{
"epoch": 0.1,
"learning_rate": 1.994680376450686e-05,
"loss": 2.4609,
"step": 250
},
{
"epoch": 0.1,
"learning_rate": 1.994465662108124e-05,
"loss": 2.5063,
"step": 255
},
{
"epoch": 0.1,
"learning_rate": 1.9942467118631322e-05,
"loss": 2.5162,
"step": 260
},
{
"epoch": 0.1,
"learning_rate": 1.994023526648323e-05,
"loss": 2.5317,
"step": 265
},
{
"epoch": 0.11,
"learning_rate": 1.9937961074143492e-05,
"loss": 2.4621,
"step": 270
},
{
"epoch": 0.11,
"learning_rate": 1.9935644551298976e-05,
"loss": 2.5879,
"step": 275
},
{
"epoch": 0.11,
"learning_rate": 1.993328570781685e-05,
"loss": 2.4742,
"step": 280
},
{
"epoch": 0.11,
"learning_rate": 1.993088455374456e-05,
"loss": 2.4661,
"step": 285
},
{
"epoch": 0.11,
"learning_rate": 1.992844109930975e-05,
"loss": 2.4943,
"step": 290
},
{
"epoch": 0.12,
"learning_rate": 1.9925955354920265e-05,
"loss": 2.4322,
"step": 295
},
{
"epoch": 0.12,
"learning_rate": 1.9923427331164072e-05,
"loss": 2.484,
"step": 300
},
{
"epoch": 0.12,
"learning_rate": 1.9920857038809223e-05,
"loss": 2.5334,
"step": 305
},
{
"epoch": 0.12,
"learning_rate": 1.991824448880382e-05,
"loss": 2.6554,
"step": 310
},
{
"epoch": 0.12,
"learning_rate": 1.9915589692275955e-05,
"loss": 2.4749,
"step": 315
},
{
"epoch": 0.13,
"learning_rate": 1.991289266053367e-05,
"loss": 2.5076,
"step": 320
},
{
"epoch": 0.13,
"learning_rate": 1.9910153405064904e-05,
"loss": 2.4635,
"step": 325
},
{
"epoch": 0.13,
"learning_rate": 1.990737193753745e-05,
"loss": 2.5443,
"step": 330
},
{
"epoch": 0.13,
"learning_rate": 1.9904548269798906e-05,
"loss": 2.6012,
"step": 335
},
{
"epoch": 0.13,
"learning_rate": 1.990168241387662e-05,
"loss": 2.4818,
"step": 340
},
{
"epoch": 0.14,
"learning_rate": 1.9898774381977618e-05,
"loss": 2.4717,
"step": 345
},
{
"epoch": 0.14,
"learning_rate": 1.989582418648861e-05,
"loss": 2.4756,
"step": 350
},
{
"epoch": 0.14,
"learning_rate": 1.9892831839975874e-05,
"loss": 2.4868,
"step": 355
},
{
"epoch": 0.14,
"learning_rate": 1.9889797355185237e-05,
"loss": 2.5652,
"step": 360
},
{
"epoch": 0.14,
"learning_rate": 1.9886720745042017e-05,
"loss": 2.3907,
"step": 365
},
{
"epoch": 0.15,
"learning_rate": 1.988360202265096e-05,
"loss": 2.4984,
"step": 370
},
{
"epoch": 0.15,
"learning_rate": 1.9880441201296186e-05,
"loss": 2.5654,
"step": 375
},
{
"epoch": 0.15,
"learning_rate": 1.987723829444114e-05,
"loss": 2.581,
"step": 380
},
{
"epoch": 0.15,
"learning_rate": 1.9873993315728523e-05,
"loss": 2.5189,
"step": 385
},
{
"epoch": 0.15,
"learning_rate": 1.987070627898025e-05,
"loss": 2.491,
"step": 390
},
{
"epoch": 0.16,
"learning_rate": 1.9867377198197367e-05,
"loss": 2.4875,
"step": 395
},
{
"epoch": 0.16,
"learning_rate": 1.9864006087560016e-05,
"loss": 2.4828,
"step": 400
},
{
"epoch": 0.16,
"learning_rate": 1.9860592961427358e-05,
"loss": 2.5298,
"step": 405
},
{
"epoch": 0.16,
"learning_rate": 1.9857137834337527e-05,
"loss": 2.4873,
"step": 410
},
{
"epoch": 0.16,
"learning_rate": 1.985364072100755e-05,
"loss": 2.5371,
"step": 415
},
{
"epoch": 0.17,
"learning_rate": 1.98501016363333e-05,
"loss": 2.4167,
"step": 420
},
{
"epoch": 0.17,
"learning_rate": 1.9846520595389415e-05,
"loss": 2.4312,
"step": 425
},
{
"epoch": 0.17,
"learning_rate": 1.984289761342926e-05,
"loss": 2.4471,
"step": 430
},
{
"epoch": 0.17,
"learning_rate": 1.9839232705884836e-05,
"loss": 2.4971,
"step": 435
},
{
"epoch": 0.17,
"learning_rate": 1.9835525888366727e-05,
"loss": 2.5206,
"step": 440
},
{
"epoch": 0.18,
"learning_rate": 1.9831777176664035e-05,
"loss": 2.5067,
"step": 445
},
{
"epoch": 0.18,
"learning_rate": 1.9827986586744302e-05,
"loss": 2.4903,
"step": 450
},
{
"epoch": 0.18,
"learning_rate": 1.982415413475346e-05,
"loss": 2.4391,
"step": 455
},
{
"epoch": 0.18,
"learning_rate": 1.9820279837015742e-05,
"loss": 2.4358,
"step": 460
},
{
"epoch": 0.18,
"learning_rate": 1.981636371003363e-05,
"loss": 2.4809,
"step": 465
},
{
"epoch": 0.19,
"learning_rate": 1.9812405770487763e-05,
"loss": 2.516,
"step": 470
},
{
"epoch": 0.19,
"learning_rate": 1.9808406035236897e-05,
"loss": 2.4091,
"step": 475
},
{
"epoch": 0.19,
"learning_rate": 1.9804364521317806e-05,
"loss": 2.5363,
"step": 480
},
{
"epoch": 0.19,
"learning_rate": 1.9800281245945217e-05,
"loss": 2.51,
"step": 485
},
{
"epoch": 0.19,
"learning_rate": 1.9796156226511747e-05,
"loss": 2.5049,
"step": 490
},
{
"epoch": 0.2,
"learning_rate": 1.9791989480587815e-05,
"loss": 2.4722,
"step": 495
},
{
"epoch": 0.2,
"learning_rate": 1.978778102592157e-05,
"loss": 2.4111,
"step": 500
},
{
"epoch": 0.2,
"learning_rate": 1.9783530880438832e-05,
"loss": 2.4078,
"step": 505
},
{
"epoch": 0.2,
"learning_rate": 1.9779239062242988e-05,
"loss": 2.3981,
"step": 510
},
{
"epoch": 0.2,
"learning_rate": 1.9774905589614935e-05,
"loss": 2.5459,
"step": 515
},
{
"epoch": 0.2,
"learning_rate": 1.977053048101299e-05,
"loss": 2.4432,
"step": 520
},
{
"epoch": 0.21,
"learning_rate": 1.976611375507283e-05,
"loss": 2.5329,
"step": 525
},
{
"epoch": 0.21,
"learning_rate": 1.9761655430607384e-05,
"loss": 2.5107,
"step": 530
},
{
"epoch": 0.21,
"learning_rate": 1.975715552660678e-05,
"loss": 2.4389,
"step": 535
},
{
"epoch": 0.21,
"learning_rate": 1.9752614062238256e-05,
"loss": 2.4939,
"step": 540
},
{
"epoch": 0.21,
"learning_rate": 1.974803105684606e-05,
"loss": 2.5349,
"step": 545
},
{
"epoch": 0.22,
"learning_rate": 1.9743406529951403e-05,
"loss": 2.5268,
"step": 550
},
{
"epoch": 0.22,
"learning_rate": 1.9738740501252337e-05,
"loss": 2.4477,
"step": 555
},
{
"epoch": 0.22,
"learning_rate": 1.9734032990623702e-05,
"loss": 2.4597,
"step": 560
},
{
"epoch": 0.22,
"learning_rate": 1.972928401811703e-05,
"loss": 2.4938,
"step": 565
},
{
"epoch": 0.22,
"learning_rate": 1.9724493603960443e-05,
"loss": 2.4756,
"step": 570
},
{
"epoch": 0.23,
"learning_rate": 1.9719661768558604e-05,
"loss": 2.3664,
"step": 575
},
{
"epoch": 0.23,
"learning_rate": 1.9714788532492595e-05,
"loss": 2.5166,
"step": 580
},
{
"epoch": 0.23,
"learning_rate": 1.9709873916519853e-05,
"loss": 2.4143,
"step": 585
},
{
"epoch": 0.23,
"learning_rate": 1.9704917941574053e-05,
"loss": 2.4666,
"step": 590
},
{
"epoch": 0.23,
"learning_rate": 1.9699920628765065e-05,
"loss": 2.4617,
"step": 595
},
{
"epoch": 0.24,
"learning_rate": 1.969488199937881e-05,
"loss": 2.4912,
"step": 600
},
{
"epoch": 0.24,
"learning_rate": 1.9689802074877216e-05,
"loss": 2.4386,
"step": 605
},
{
"epoch": 0.24,
"learning_rate": 1.9684680876898096e-05,
"loss": 2.5002,
"step": 610
},
{
"epoch": 0.24,
"learning_rate": 1.967951842725507e-05,
"loss": 2.5668,
"step": 615
},
{
"epoch": 0.24,
"learning_rate": 1.9674314747937462e-05,
"loss": 2.4955,
"step": 620
},
{
"epoch": 0.25,
"learning_rate": 1.9669069861110225e-05,
"loss": 2.5317,
"step": 625
},
{
"epoch": 0.25,
"learning_rate": 1.9663783789113827e-05,
"loss": 2.4709,
"step": 630
},
{
"epoch": 0.25,
"learning_rate": 1.9658456554464157e-05,
"loss": 2.4066,
"step": 635
},
{
"epoch": 0.25,
"learning_rate": 1.9653088179852448e-05,
"loss": 2.4462,
"step": 640
},
{
"epoch": 0.25,
"learning_rate": 1.9647678688145163e-05,
"loss": 2.5093,
"step": 645
},
{
"epoch": 0.26,
"learning_rate": 1.9642228102383894e-05,
"loss": 2.4634,
"step": 650
},
{
"epoch": 0.26,
"learning_rate": 1.9636736445785288e-05,
"loss": 2.424,
"step": 655
},
{
"epoch": 0.26,
"learning_rate": 1.963120374174092e-05,
"loss": 2.4968,
"step": 660
},
{
"epoch": 0.26,
"learning_rate": 1.9625630013817204e-05,
"loss": 2.3947,
"step": 665
},
{
"epoch": 0.26,
"learning_rate": 1.9620015285755306e-05,
"loss": 2.3954,
"step": 670
},
{
"epoch": 0.27,
"learning_rate": 1.961435958147102e-05,
"loss": 2.3764,
"step": 675
},
{
"epoch": 0.27,
"learning_rate": 1.9608662925054684e-05,
"loss": 2.386,
"step": 680
},
{
"epoch": 0.27,
"learning_rate": 1.960292534077107e-05,
"loss": 2.4218,
"step": 685
},
{
"epoch": 0.27,
"learning_rate": 1.9597146853059273e-05,
"loss": 2.4479,
"step": 690
},
{
"epoch": 0.27,
"learning_rate": 1.959132748653263e-05,
"loss": 2.4301,
"step": 695
},
{
"epoch": 0.28,
"learning_rate": 1.9585467265978585e-05,
"loss": 2.5069,
"step": 700
},
{
"epoch": 0.28,
"learning_rate": 1.957956621635861e-05,
"loss": 2.4144,
"step": 705
},
{
"epoch": 0.28,
"learning_rate": 1.9573624362808078e-05,
"loss": 2.4491,
"step": 710
},
{
"epoch": 0.28,
"learning_rate": 1.9567641730636174e-05,
"loss": 2.4723,
"step": 715
},
{
"epoch": 0.28,
"learning_rate": 1.956161834532578e-05,
"loss": 2.4839,
"step": 720
},
{
"epoch": 0.29,
"learning_rate": 1.955555423253335e-05,
"loss": 2.4881,
"step": 725
},
{
"epoch": 0.29,
"learning_rate": 1.9549449418088832e-05,
"loss": 2.5076,
"step": 730
},
{
"epoch": 0.29,
"learning_rate": 1.9543303927995536e-05,
"loss": 2.4704,
"step": 735
},
{
"epoch": 0.29,
"learning_rate": 1.9537117788430024e-05,
"loss": 2.3958,
"step": 740
},
{
"epoch": 0.29,
"learning_rate": 1.953089102574201e-05,
"loss": 2.5256,
"step": 745
},
{
"epoch": 0.3,
"learning_rate": 1.9524623666454243e-05,
"loss": 2.4658,
"step": 750
},
{
"epoch": 0.3,
"learning_rate": 1.951831573726238e-05,
"loss": 2.4636,
"step": 755
},
{
"epoch": 0.3,
"learning_rate": 1.9511967265034904e-05,
"loss": 2.4249,
"step": 760
},
{
"epoch": 0.3,
"learning_rate": 1.9505578276812964e-05,
"loss": 2.5412,
"step": 765
},
{
"epoch": 0.3,
"learning_rate": 1.9499148799810314e-05,
"loss": 2.4355,
"step": 770
},
{
"epoch": 0.31,
"learning_rate": 1.949267886141315e-05,
"loss": 2.5814,
"step": 775
},
{
"epoch": 0.31,
"learning_rate": 1.948616848918002e-05,
"loss": 2.5195,
"step": 780
},
{
"epoch": 0.31,
"learning_rate": 1.9479617710841693e-05,
"loss": 2.5177,
"step": 785
},
{
"epoch": 0.31,
"learning_rate": 1.9473026554301057e-05,
"loss": 2.4418,
"step": 790
},
{
"epoch": 0.31,
"learning_rate": 1.946639504763298e-05,
"loss": 2.5187,
"step": 795
},
{
"epoch": 0.32,
"learning_rate": 1.94597232190842e-05,
"loss": 2.479,
"step": 800
},
{
"epoch": 0.32,
"learning_rate": 1.9453011097073217e-05,
"loss": 2.4451,
"step": 805
},
{
"epoch": 0.32,
"learning_rate": 1.9446258710190152e-05,
"loss": 2.5426,
"step": 810
},
{
"epoch": 0.32,
"learning_rate": 1.9439466087196627e-05,
"loss": 2.4299,
"step": 815
},
{
"epoch": 0.32,
"learning_rate": 1.943263325702566e-05,
"loss": 2.5317,
"step": 820
},
{
"epoch": 0.33,
"learning_rate": 1.9425760248781525e-05,
"loss": 2.4384,
"step": 825
},
{
"epoch": 0.33,
"learning_rate": 1.9418847091739638e-05,
"loss": 2.4445,
"step": 830
},
{
"epoch": 0.33,
"learning_rate": 1.9411893815346418e-05,
"loss": 2.4872,
"step": 835
},
{
"epoch": 0.33,
"learning_rate": 1.9404900449219178e-05,
"loss": 2.5123,
"step": 840
},
{
"epoch": 0.33,
"learning_rate": 1.9397867023146e-05,
"loss": 2.3569,
"step": 845
},
{
"epoch": 0.34,
"learning_rate": 1.9390793567085585e-05,
"loss": 2.467,
"step": 850
},
{
"epoch": 0.34,
"learning_rate": 1.9383680111167146e-05,
"loss": 2.4097,
"step": 855
},
{
"epoch": 0.34,
"learning_rate": 1.937652668569028e-05,
"loss": 2.4653,
"step": 860
},
{
"epoch": 0.34,
"learning_rate": 1.9369333321124832e-05,
"loss": 2.4164,
"step": 865
},
{
"epoch": 0.34,
"learning_rate": 1.936210004811076e-05,
"loss": 2.3906,
"step": 870
},
{
"epoch": 0.34,
"learning_rate": 1.9354826897458016e-05,
"loss": 2.4433,
"step": 875
},
{
"epoch": 0.35,
"learning_rate": 1.9347513900146412e-05,
"loss": 2.42,
"step": 880
},
{
"epoch": 0.35,
"learning_rate": 1.9340161087325483e-05,
"loss": 2.4606,
"step": 885
},
{
"epoch": 0.35,
"learning_rate": 1.9332768490314354e-05,
"loss": 2.4242,
"step": 890
},
{
"epoch": 0.35,
"learning_rate": 1.9325336140601612e-05,
"loss": 2.461,
"step": 895
},
{
"epoch": 0.35,
"learning_rate": 1.931786406984518e-05,
"loss": 2.3949,
"step": 900
},
{
"epoch": 0.36,
"learning_rate": 1.9310352309872153e-05,
"loss": 2.4449,
"step": 905
},
{
"epoch": 0.36,
"learning_rate": 1.9302800892678693e-05,
"loss": 2.4864,
"step": 910
},
{
"epoch": 0.36,
"learning_rate": 1.9295209850429884e-05,
"loss": 2.5432,
"step": 915
},
{
"epoch": 0.36,
"learning_rate": 1.9287579215459585e-05,
"loss": 2.4357,
"step": 920
},
{
"epoch": 0.36,
"learning_rate": 1.9279909020270294e-05,
"loss": 2.4625,
"step": 925
},
{
"epoch": 0.37,
"learning_rate": 1.9272199297533027e-05,
"loss": 2.3937,
"step": 930
},
{
"epoch": 0.37,
"learning_rate": 1.9264450080087163e-05,
"loss": 2.5051,
"step": 935
},
{
"epoch": 0.37,
"learning_rate": 1.9256661400940303e-05,
"loss": 2.4894,
"step": 940
},
{
"epoch": 0.37,
"learning_rate": 1.9248833293268144e-05,
"loss": 2.4117,
"step": 945
},
{
"epoch": 0.37,
"learning_rate": 1.9240965790414312e-05,
"loss": 2.4892,
"step": 950
},
{
"epoch": 0.38,
"learning_rate": 1.923305892589025e-05,
"loss": 2.4059,
"step": 955
},
{
"epoch": 0.38,
"learning_rate": 1.9225112733375057e-05,
"loss": 2.3975,
"step": 960
},
{
"epoch": 0.38,
"learning_rate": 1.9217127246715344e-05,
"loss": 2.4867,
"step": 965
},
{
"epoch": 0.38,
"learning_rate": 1.92091024999251e-05,
"loss": 2.4757,
"step": 970
},
{
"epoch": 0.38,
"learning_rate": 1.9201038527185546e-05,
"loss": 2.4164,
"step": 975
},
{
"epoch": 0.39,
"learning_rate": 1.919293536284497e-05,
"loss": 2.4024,
"step": 980
},
{
"epoch": 0.39,
"learning_rate": 1.9184793041418607e-05,
"loss": 2.4706,
"step": 985
},
{
"epoch": 0.39,
"learning_rate": 1.917661159758848e-05,
"loss": 2.465,
"step": 990
},
{
"epoch": 0.39,
"learning_rate": 1.9168391066203248e-05,
"loss": 2.555,
"step": 995
},
{
"epoch": 0.39,
"learning_rate": 1.9160131482278068e-05,
"loss": 2.4465,
"step": 1000
},
{
"epoch": 0.4,
"learning_rate": 1.9151832880994438e-05,
"loss": 2.4014,
"step": 1005
},
{
"epoch": 0.4,
"learning_rate": 1.914349529770005e-05,
"loss": 2.4358,
"step": 1010
},
{
"epoch": 0.4,
"learning_rate": 1.9135118767908637e-05,
"loss": 2.402,
"step": 1015
},
{
"epoch": 0.4,
"learning_rate": 1.9126703327299822e-05,
"loss": 2.3952,
"step": 1020
},
{
"epoch": 0.4,
"learning_rate": 1.9118249011718975e-05,
"loss": 2.4051,
"step": 1025
},
{
"epoch": 0.41,
"learning_rate": 1.9109755857177053e-05,
"loss": 2.4198,
"step": 1030
},
{
"epoch": 0.41,
"learning_rate": 1.910122389985043e-05,
"loss": 2.4414,
"step": 1035
},
{
"epoch": 0.41,
"learning_rate": 1.909265317608078e-05,
"loss": 2.4688,
"step": 1040
},
{
"epoch": 0.41,
"learning_rate": 1.9084043722374895e-05,
"loss": 2.3766,
"step": 1045
},
{
"epoch": 0.41,
"learning_rate": 1.907539557540453e-05,
"loss": 2.3966,
"step": 1050
},
{
"epoch": 0.42,
"learning_rate": 1.9066708772006262e-05,
"loss": 2.5027,
"step": 1055
},
{
"epoch": 0.42,
"learning_rate": 1.9057983349181316e-05,
"loss": 2.4904,
"step": 1060
},
{
"epoch": 0.42,
"learning_rate": 1.904921934409542e-05,
"loss": 2.4296,
"step": 1065
},
{
"epoch": 0.42,
"learning_rate": 1.9040416794078648e-05,
"loss": 2.4294,
"step": 1070
},
{
"epoch": 0.42,
"learning_rate": 1.903157573662524e-05,
"loss": 2.4442,
"step": 1075
},
{
"epoch": 0.43,
"learning_rate": 1.902269620939347e-05,
"loss": 2.382,
"step": 1080
},
{
"epoch": 0.43,
"learning_rate": 1.901377825020547e-05,
"loss": 2.5004,
"step": 1085
},
{
"epoch": 0.43,
"learning_rate": 1.9004821897047067e-05,
"loss": 2.3837,
"step": 1090
},
{
"epoch": 0.43,
"learning_rate": 1.899582718806764e-05,
"loss": 2.3654,
"step": 1095
},
{
"epoch": 0.43,
"learning_rate": 1.8986794161579927e-05,
"loss": 2.4624,
"step": 1100
},
{
"epoch": 0.44,
"learning_rate": 1.8977722856059886e-05,
"loss": 2.4875,
"step": 1105
},
{
"epoch": 0.44,
"learning_rate": 1.8968613310146527e-05,
"loss": 2.4575,
"step": 1110
},
{
"epoch": 0.44,
"learning_rate": 1.8959465562641738e-05,
"loss": 2.337,
"step": 1115
},
{
"epoch": 0.44,
"learning_rate": 1.895027965251013e-05,
"loss": 2.4485,
"step": 1120
},
{
"epoch": 0.44,
"learning_rate": 1.8941055618878864e-05,
"loss": 2.5231,
"step": 1125
},
{
"epoch": 0.45,
"learning_rate": 1.8931793501037483e-05,
"loss": 2.3996,
"step": 1130
},
{
"epoch": 0.45,
"learning_rate": 1.8922493338437765e-05,
"loss": 2.4486,
"step": 1135
},
{
"epoch": 0.45,
"learning_rate": 1.8913155170693514e-05,
"loss": 2.5302,
"step": 1140
},
{
"epoch": 0.45,
"learning_rate": 1.8903779037580442e-05,
"loss": 2.4209,
"step": 1145
},
{
"epoch": 0.45,
"learning_rate": 1.8894364979035956e-05,
"loss": 2.3894,
"step": 1150
},
{
"epoch": 0.46,
"learning_rate": 1.8884913035159008e-05,
"loss": 2.3971,
"step": 1155
},
{
"epoch": 0.46,
"learning_rate": 1.8875423246209928e-05,
"loss": 2.3819,
"step": 1160
},
{
"epoch": 0.46,
"learning_rate": 1.8865895652610244e-05,
"loss": 2.4543,
"step": 1165
},
{
"epoch": 0.46,
"learning_rate": 1.8856330294942506e-05,
"loss": 2.4273,
"step": 1170
},
{
"epoch": 0.46,
"learning_rate": 1.8846727213950125e-05,
"loss": 2.4266,
"step": 1175
},
{
"epoch": 0.47,
"learning_rate": 1.8837086450537195e-05,
"loss": 2.4436,
"step": 1180
},
{
"epoch": 0.47,
"learning_rate": 1.8827408045768308e-05,
"loss": 2.5767,
"step": 1185
},
{
"epoch": 0.47,
"learning_rate": 1.8817692040868404e-05,
"loss": 2.3555,
"step": 1190
},
{
"epoch": 0.47,
"learning_rate": 1.880793847722256e-05,
"loss": 2.4157,
"step": 1195
},
{
"epoch": 0.47,
"learning_rate": 1.8798147396375855e-05,
"loss": 2.4256,
"step": 1200
},
{
"epoch": 0.47,
"learning_rate": 1.8788318840033155e-05,
"loss": 2.529,
"step": 1205
},
{
"epoch": 0.48,
"learning_rate": 1.8778452850058957e-05,
"loss": 2.4668,
"step": 1210
},
{
"epoch": 0.48,
"learning_rate": 1.8768549468477212e-05,
"loss": 2.4191,
"step": 1215
},
{
"epoch": 0.48,
"learning_rate": 1.875860873747113e-05,
"loss": 2.3992,
"step": 1220
},
{
"epoch": 0.48,
"learning_rate": 1.8748630699383016e-05,
"loss": 2.4485,
"step": 1225
},
{
"epoch": 0.48,
"learning_rate": 1.8738615396714083e-05,
"loss": 2.3803,
"step": 1230
},
{
"epoch": 0.49,
"learning_rate": 1.8728562872124264e-05,
"loss": 2.428,
"step": 1235
},
{
"epoch": 0.49,
"learning_rate": 1.8718473168432054e-05,
"loss": 2.4404,
"step": 1240
},
{
"epoch": 0.49,
"learning_rate": 1.8708346328614297e-05,
"loss": 2.5451,
"step": 1245
},
{
"epoch": 0.49,
"learning_rate": 1.869818239580602e-05,
"loss": 2.4906,
"step": 1250
},
{
"epoch": 0.49,
"learning_rate": 1.8687981413300246e-05,
"loss": 2.4486,
"step": 1255
},
{
"epoch": 0.5,
"learning_rate": 1.8677743424547824e-05,
"loss": 2.4106,
"step": 1260
},
{
"epoch": 0.5,
"learning_rate": 1.8667468473157212e-05,
"loss": 2.3316,
"step": 1265
},
{
"epoch": 0.5,
"learning_rate": 1.865715660289432e-05,
"loss": 2.4518,
"step": 1270
},
{
"epoch": 0.5,
"learning_rate": 1.8646807857682308e-05,
"loss": 2.4549,
"step": 1275
},
{
"epoch": 0.5,
"learning_rate": 1.8636422281601406e-05,
"loss": 2.4411,
"step": 1280
},
{
"epoch": 0.51,
"learning_rate": 1.8625999918888726e-05,
"loss": 2.509,
"step": 1285
},
{
"epoch": 0.51,
"learning_rate": 1.8615540813938063e-05,
"loss": 2.4455,
"step": 1290
},
{
"epoch": 0.51,
"learning_rate": 1.860504501129973e-05,
"loss": 2.5486,
"step": 1295
},
{
"epoch": 0.51,
"learning_rate": 1.8594512555680338e-05,
"loss": 2.4134,
"step": 1300
},
{
"epoch": 0.51,
"learning_rate": 1.8583943491942635e-05,
"loss": 2.483,
"step": 1305
},
{
"epoch": 0.52,
"learning_rate": 1.8573337865105285e-05,
"loss": 2.4329,
"step": 1310
},
{
"epoch": 0.52,
"learning_rate": 1.8562695720342704e-05,
"loss": 2.3614,
"step": 1315
},
{
"epoch": 0.52,
"learning_rate": 1.8552017102984842e-05,
"loss": 2.4119,
"step": 1320
},
{
"epoch": 0.52,
"learning_rate": 1.854130205851702e-05,
"loss": 2.4654,
"step": 1325
},
{
"epoch": 0.52,
"learning_rate": 1.853055063257971e-05,
"loss": 2.3784,
"step": 1330
},
{
"epoch": 0.53,
"learning_rate": 1.8519762870968344e-05,
"loss": 2.4059,
"step": 1335
},
{
"epoch": 0.53,
"learning_rate": 1.8508938819633138e-05,
"loss": 2.3768,
"step": 1340
},
{
"epoch": 0.53,
"learning_rate": 1.8498078524678874e-05,
"loss": 2.3345,
"step": 1345
},
{
"epoch": 0.53,
"learning_rate": 1.8487182032364714e-05,
"loss": 2.4273,
"step": 1350
},
{
"epoch": 0.53,
"learning_rate": 1.8476249389104007e-05,
"loss": 2.3947,
"step": 1355
},
{
"epoch": 0.54,
"learning_rate": 1.8465280641464085e-05,
"loss": 2.4527,
"step": 1360
},
{
"epoch": 0.54,
"learning_rate": 1.8454275836166052e-05,
"loss": 2.3342,
"step": 1365
},
{
"epoch": 0.54,
"learning_rate": 1.8443235020084624e-05,
"loss": 2.4361,
"step": 1370
},
{
"epoch": 0.54,
"learning_rate": 1.843215824024788e-05,
"loss": 2.502,
"step": 1375
},
{
"epoch": 0.54,
"learning_rate": 1.84210455438371e-05,
"loss": 2.4718,
"step": 1380
},
{
"epoch": 0.55,
"learning_rate": 1.8409896978186547e-05,
"loss": 2.428,
"step": 1385
},
{
"epoch": 0.55,
"learning_rate": 1.8398712590783258e-05,
"loss": 2.4213,
"step": 1390
},
{
"epoch": 0.55,
"learning_rate": 1.838749242926687e-05,
"loss": 2.3812,
"step": 1395
},
{
"epoch": 0.55,
"learning_rate": 1.8376236541429386e-05,
"loss": 2.4458,
"step": 1400
},
{
"epoch": 0.55,
"learning_rate": 1.836494497521499e-05,
"loss": 2.4359,
"step": 1405
},
{
"epoch": 0.56,
"learning_rate": 1.835361777871983e-05,
"loss": 2.3377,
"step": 1410
},
{
"epoch": 0.56,
"learning_rate": 1.8342255000191832e-05,
"loss": 2.414,
"step": 1415
},
{
"epoch": 0.56,
"learning_rate": 1.8330856688030474e-05,
"loss": 2.4517,
"step": 1420
},
{
"epoch": 0.56,
"learning_rate": 1.8319422890786586e-05,
"loss": 2.375,
"step": 1425
},
{
"epoch": 0.56,
"learning_rate": 1.830795365716216e-05,
"loss": 2.3515,
"step": 1430
},
{
"epoch": 0.57,
"learning_rate": 1.829644903601011e-05,
"loss": 2.4428,
"step": 1435
},
{
"epoch": 0.57,
"learning_rate": 1.8284909076334094e-05,
"loss": 2.4186,
"step": 1440
},
{
"epoch": 0.57,
"learning_rate": 1.8273333827288294e-05,
"loss": 2.4604,
"step": 1445
},
{
"epoch": 0.57,
"learning_rate": 1.8261723338177204e-05,
"loss": 2.4712,
"step": 1450
},
{
"epoch": 0.57,
"learning_rate": 1.825007765845542e-05,
"loss": 2.4355,
"step": 1455
},
{
"epoch": 0.58,
"learning_rate": 1.823839683772743e-05,
"loss": 2.4399,
"step": 1460
},
{
"epoch": 0.58,
"learning_rate": 1.822668092574741e-05,
"loss": 2.4747,
"step": 1465
},
{
"epoch": 0.58,
"learning_rate": 1.8214929972419004e-05,
"loss": 2.3503,
"step": 1470
},
{
"epoch": 0.58,
"learning_rate": 1.820314402779511e-05,
"loss": 2.42,
"step": 1475
},
{
"epoch": 0.58,
"learning_rate": 1.819132314207768e-05,
"loss": 2.3705,
"step": 1480
},
{
"epoch": 0.59,
"learning_rate": 1.8179467365617486e-05,
"loss": 2.3828,
"step": 1485
},
{
"epoch": 0.59,
"learning_rate": 1.816757674891392e-05,
"loss": 2.4663,
"step": 1490
},
{
"epoch": 0.59,
"learning_rate": 1.8155651342614784e-05,
"loss": 2.4991,
"step": 1495
},
{
"epoch": 0.59,
"learning_rate": 1.8143691197516048e-05,
"loss": 2.3769,
"step": 1500
},
{
"epoch": 0.59,
"learning_rate": 1.813169636456167e-05,
"loss": 2.4001,
"step": 1505
},
{
"epoch": 0.6,
"learning_rate": 1.811966689484334e-05,
"loss": 2.4054,
"step": 1510
},
{
"epoch": 0.6,
"learning_rate": 1.8107602839600306e-05,
"loss": 2.4524,
"step": 1515
},
{
"epoch": 0.6,
"learning_rate": 1.8095504250219103e-05,
"loss": 2.423,
"step": 1520
},
{
"epoch": 0.6,
"learning_rate": 1.80833711782334e-05,
"loss": 2.5138,
"step": 1525
},
{
"epoch": 0.6,
"learning_rate": 1.8071203675323708e-05,
"loss": 2.3669,
"step": 1530
},
{
"epoch": 0.61,
"learning_rate": 1.8059001793317215e-05,
"loss": 2.3542,
"step": 1535
},
{
"epoch": 0.61,
"learning_rate": 1.8046765584187544e-05,
"loss": 2.3358,
"step": 1540
},
{
"epoch": 0.61,
"learning_rate": 1.803449510005453e-05,
"loss": 2.3739,
"step": 1545
},
{
"epoch": 0.61,
"learning_rate": 1.8022190393184008e-05,
"loss": 2.4784,
"step": 1550
},
{
"epoch": 0.61,
"learning_rate": 1.8009851515987573e-05,
"loss": 2.3919,
"step": 1555
},
{
"epoch": 0.61,
"learning_rate": 1.7997478521022378e-05,
"loss": 2.4998,
"step": 1560
},
{
"epoch": 0.62,
"learning_rate": 1.7985071460990894e-05,
"loss": 2.4079,
"step": 1565
},
{
"epoch": 0.62,
"learning_rate": 1.7972630388740696e-05,
"loss": 2.3714,
"step": 1570
},
{
"epoch": 0.62,
"learning_rate": 1.7960155357264224e-05,
"loss": 2.4316,
"step": 1575
},
{
"epoch": 0.62,
"learning_rate": 1.7947646419698578e-05,
"loss": 2.3991,
"step": 1580
},
{
"epoch": 0.62,
"learning_rate": 1.793510362932527e-05,
"loss": 2.4027,
"step": 1585
},
{
"epoch": 0.63,
"learning_rate": 1.7922527039570022e-05,
"loss": 2.443,
"step": 1590
},
{
"epoch": 0.63,
"learning_rate": 1.7909916704002506e-05,
"loss": 2.3988,
"step": 1595
},
{
"epoch": 0.63,
"learning_rate": 1.7897272676336143e-05,
"loss": 2.5286,
"step": 1600
},
{
"epoch": 0.63,
"learning_rate": 1.788459501042786e-05,
"loss": 2.4104,
"step": 1605
},
{
"epoch": 0.63,
"learning_rate": 1.7871883760277872e-05,
"loss": 2.3934,
"step": 1610
},
{
"epoch": 0.64,
"learning_rate": 1.785913898002944e-05,
"loss": 2.4028,
"step": 1615
},
{
"epoch": 0.64,
"learning_rate": 1.784636072396865e-05,
"loss": 2.3815,
"step": 1620
},
{
"epoch": 0.64,
"learning_rate": 1.783354904652417e-05,
"loss": 2.3652,
"step": 1625
},
{
"epoch": 0.64,
"learning_rate": 1.7820704002267034e-05,
"loss": 2.4487,
"step": 1630
},
{
"epoch": 0.64,
"learning_rate": 1.7807825645910396e-05,
"loss": 2.5422,
"step": 1635
},
{
"epoch": 0.65,
"learning_rate": 1.77949140323093e-05,
"loss": 2.3982,
"step": 1640
},
{
"epoch": 0.65,
"learning_rate": 1.7781969216460458e-05,
"loss": 2.3603,
"step": 1645
},
{
"epoch": 0.65,
"learning_rate": 1.7768991253501993e-05,
"loss": 2.3725,
"step": 1650
},
{
"epoch": 0.65,
"learning_rate": 1.775598019871323e-05,
"loss": 2.4896,
"step": 1655
},
{
"epoch": 0.65,
"learning_rate": 1.7742936107514442e-05,
"loss": 2.4789,
"step": 1660
},
{
"epoch": 0.66,
"learning_rate": 1.7729859035466617e-05,
"loss": 2.4811,
"step": 1665
},
{
"epoch": 0.66,
"learning_rate": 1.7716749038271225e-05,
"loss": 2.4251,
"step": 1670
},
{
"epoch": 0.66,
"learning_rate": 1.770360617176999e-05,
"loss": 2.4285,
"step": 1675
},
{
"epoch": 0.66,
"learning_rate": 1.7690430491944625e-05,
"loss": 2.4722,
"step": 1680
},
{
"epoch": 0.66,
"learning_rate": 1.7677222054916627e-05,
"loss": 2.384,
"step": 1685
},
{
"epoch": 0.67,
"learning_rate": 1.7663980916947007e-05,
"loss": 2.3686,
"step": 1690
},
{
"epoch": 0.67,
"learning_rate": 1.7650707134436075e-05,
"loss": 2.4773,
"step": 1695
},
{
"epoch": 0.67,
"learning_rate": 1.7637400763923187e-05,
"loss": 2.3632,
"step": 1700
},
{
"epoch": 0.67,
"learning_rate": 1.7624061862086508e-05,
"loss": 2.3542,
"step": 1705
},
{
"epoch": 0.67,
"learning_rate": 1.7610690485742763e-05,
"loss": 2.3659,
"step": 1710
},
{
"epoch": 0.68,
"learning_rate": 1.759728669184701e-05,
"loss": 2.5581,
"step": 1715
},
{
"epoch": 0.68,
"learning_rate": 1.7583850537492386e-05,
"loss": 2.3999,
"step": 1720
},
{
"epoch": 0.68,
"learning_rate": 1.757038207990986e-05,
"loss": 2.3789,
"step": 1725
},
{
"epoch": 0.68,
"learning_rate": 1.7556881376468004e-05,
"loss": 2.4012,
"step": 1730
},
{
"epoch": 0.68,
"learning_rate": 1.754334848467274e-05,
"loss": 2.3385,
"step": 1735
},
{
"epoch": 0.69,
"learning_rate": 1.7529783462167088e-05,
"loss": 2.4043,
"step": 1740
},
{
"epoch": 0.69,
"learning_rate": 1.751618636673094e-05,
"loss": 2.3214,
"step": 1745
},
{
"epoch": 0.69,
"learning_rate": 1.7502557256280792e-05,
"loss": 2.3812,
"step": 1750
},
{
"epoch": 0.69,
"learning_rate": 1.7488896188869503e-05,
"loss": 2.3469,
"step": 1755
},
{
"epoch": 0.69,
"learning_rate": 1.7475203222686073e-05,
"loss": 2.3821,
"step": 1760
},
{
"epoch": 0.7,
"learning_rate": 1.7461478416055352e-05,
"loss": 2.4155,
"step": 1765
},
{
"epoch": 0.7,
"learning_rate": 1.744772182743782e-05,
"loss": 2.3077,
"step": 1770
},
{
"epoch": 0.7,
"learning_rate": 1.7433933515429336e-05,
"loss": 2.4099,
"step": 1775
},
{
"epoch": 0.7,
"learning_rate": 1.7420113538760885e-05,
"loss": 2.4284,
"step": 1780
},
{
"epoch": 0.7,
"learning_rate": 1.7406261956298317e-05,
"loss": 2.383,
"step": 1785
},
{
"epoch": 0.71,
"learning_rate": 1.739237882704212e-05,
"loss": 2.4171,
"step": 1790
},
{
"epoch": 0.71,
"learning_rate": 1.737846421012714e-05,
"loss": 2.5326,
"step": 1795
},
{
"epoch": 0.71,
"learning_rate": 1.736451816482235e-05,
"loss": 2.2905,
"step": 1800
}
],
"logging_steps": 5,
"max_steps": 7611,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 100,
"total_flos": 2.431059902595072e+16,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}