ZhongJing-2-0_5b1 / checkpoint-1800 /trainer_state.json
CMLL's picture
Upload folder using huggingface_hub
30c199d verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.7217321571772254,
"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": 4.99999449047447e-05,
"loss": 2.7413,
"step": 5
},
{
"epoch": 0.0,
"learning_rate": 4.9999779619221645e-05,
"loss": 2.6684,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 4.999950414415935e-05,
"loss": 2.6511,
"step": 15
},
{
"epoch": 0.01,
"learning_rate": 4.999911848077199e-05,
"loss": 2.72,
"step": 20
},
{
"epoch": 0.01,
"learning_rate": 4.999862263075944e-05,
"loss": 2.7222,
"step": 25
},
{
"epoch": 0.01,
"learning_rate": 4.999801659630722e-05,
"loss": 2.7479,
"step": 30
},
{
"epoch": 0.01,
"learning_rate": 4.999730038008649e-05,
"loss": 2.6063,
"step": 35
},
{
"epoch": 0.02,
"learning_rate": 4.9996473985254055e-05,
"loss": 2.576,
"step": 40
},
{
"epoch": 0.02,
"learning_rate": 4.999553741545237e-05,
"loss": 2.579,
"step": 45
},
{
"epoch": 0.02,
"learning_rate": 4.999449067480945e-05,
"loss": 2.5114,
"step": 50
},
{
"epoch": 0.02,
"learning_rate": 4.9993333767938954e-05,
"loss": 2.6174,
"step": 55
},
{
"epoch": 0.02,
"learning_rate": 4.9992066699940085e-05,
"loss": 2.6581,
"step": 60
},
{
"epoch": 0.03,
"learning_rate": 4.9990689476397586e-05,
"loss": 2.586,
"step": 65
},
{
"epoch": 0.03,
"learning_rate": 4.998920210338175e-05,
"loss": 2.4642,
"step": 70
},
{
"epoch": 0.03,
"learning_rate": 4.9987604587448343e-05,
"loss": 2.6262,
"step": 75
},
{
"epoch": 0.03,
"learning_rate": 4.998589693563861e-05,
"loss": 2.5678,
"step": 80
},
{
"epoch": 0.03,
"learning_rate": 4.998407915547924e-05,
"loss": 2.5597,
"step": 85
},
{
"epoch": 0.04,
"learning_rate": 4.9982151254982304e-05,
"loss": 2.6578,
"step": 90
},
{
"epoch": 0.04,
"learning_rate": 4.998011324264527e-05,
"loss": 2.4825,
"step": 95
},
{
"epoch": 0.04,
"learning_rate": 4.997796512745091e-05,
"loss": 2.6197,
"step": 100
},
{
"epoch": 0.04,
"learning_rate": 4.997570691886732e-05,
"loss": 2.4921,
"step": 105
},
{
"epoch": 0.04,
"learning_rate": 4.99733386268478e-05,
"loss": 2.5126,
"step": 110
},
{
"epoch": 0.05,
"learning_rate": 4.99708602618309e-05,
"loss": 2.584,
"step": 115
},
{
"epoch": 0.05,
"learning_rate": 4.9968271834740305e-05,
"loss": 2.4991,
"step": 120
},
{
"epoch": 0.05,
"learning_rate": 4.996557335698482e-05,
"loss": 2.5242,
"step": 125
},
{
"epoch": 0.05,
"learning_rate": 4.996276484045832e-05,
"loss": 2.4506,
"step": 130
},
{
"epoch": 0.05,
"learning_rate": 4.995984629753967e-05,
"loss": 2.5479,
"step": 135
},
{
"epoch": 0.06,
"learning_rate": 4.9956817741092696e-05,
"loss": 2.5316,
"step": 140
},
{
"epoch": 0.06,
"learning_rate": 4.995367918446613e-05,
"loss": 2.6053,
"step": 145
},
{
"epoch": 0.06,
"learning_rate": 4.995043064149354e-05,
"loss": 2.4533,
"step": 150
},
{
"epoch": 0.06,
"learning_rate": 4.9947072126493276e-05,
"loss": 2.5279,
"step": 155
},
{
"epoch": 0.06,
"learning_rate": 4.994360365426839e-05,
"loss": 2.4994,
"step": 160
},
{
"epoch": 0.07,
"learning_rate": 4.994002524010659e-05,
"loss": 2.4675,
"step": 165
},
{
"epoch": 0.07,
"learning_rate": 4.9936336899780166e-05,
"loss": 2.5233,
"step": 170
},
{
"epoch": 0.07,
"learning_rate": 4.993253864954592e-05,
"loss": 2.4974,
"step": 175
},
{
"epoch": 0.07,
"learning_rate": 4.992863050614511e-05,
"loss": 2.6295,
"step": 180
},
{
"epoch": 0.07,
"learning_rate": 4.9924612486803346e-05,
"loss": 2.4744,
"step": 185
},
{
"epoch": 0.08,
"learning_rate": 4.992048460923052e-05,
"loss": 2.5248,
"step": 190
},
{
"epoch": 0.08,
"learning_rate": 4.991624689162076e-05,
"loss": 2.5727,
"step": 195
},
{
"epoch": 0.08,
"learning_rate": 4.991189935265231e-05,
"loss": 2.4845,
"step": 200
},
{
"epoch": 0.08,
"learning_rate": 4.990744201148748e-05,
"loss": 2.4544,
"step": 205
},
{
"epoch": 0.08,
"learning_rate": 4.990287488777253e-05,
"loss": 2.4383,
"step": 210
},
{
"epoch": 0.09,
"learning_rate": 4.989819800163761e-05,
"loss": 2.5263,
"step": 215
},
{
"epoch": 0.09,
"learning_rate": 4.989341137369666e-05,
"loss": 2.5219,
"step": 220
},
{
"epoch": 0.09,
"learning_rate": 4.9888515025047316e-05,
"loss": 2.4512,
"step": 225
},
{
"epoch": 0.09,
"learning_rate": 4.988350897727083e-05,
"loss": 2.491,
"step": 230
},
{
"epoch": 0.09,
"learning_rate": 4.9878393252431953e-05,
"loss": 2.5404,
"step": 235
},
{
"epoch": 0.1,
"learning_rate": 4.987316787307888e-05,
"loss": 2.4777,
"step": 240
},
{
"epoch": 0.1,
"learning_rate": 4.9867832862243055e-05,
"loss": 2.4498,
"step": 245
},
{
"epoch": 0.1,
"learning_rate": 4.986238824343923e-05,
"loss": 2.4174,
"step": 250
},
{
"epoch": 0.1,
"learning_rate": 4.985683404066519e-05,
"loss": 2.4589,
"step": 255
},
{
"epoch": 0.1,
"learning_rate": 4.985117027840175e-05,
"loss": 2.5029,
"step": 260
},
{
"epoch": 0.11,
"learning_rate": 4.984539698161264e-05,
"loss": 2.4376,
"step": 265
},
{
"epoch": 0.11,
"learning_rate": 4.983951417574436e-05,
"loss": 2.526,
"step": 270
},
{
"epoch": 0.11,
"learning_rate": 4.983352188672608e-05,
"loss": 2.5214,
"step": 275
},
{
"epoch": 0.11,
"learning_rate": 4.982742014096952e-05,
"loss": 2.5188,
"step": 280
},
{
"epoch": 0.11,
"learning_rate": 4.982120896536888e-05,
"loss": 2.4175,
"step": 285
},
{
"epoch": 0.12,
"learning_rate": 4.981488838730066e-05,
"loss": 2.5346,
"step": 290
},
{
"epoch": 0.12,
"learning_rate": 4.980845843462357e-05,
"loss": 2.496,
"step": 295
},
{
"epoch": 0.12,
"learning_rate": 4.98019191356784e-05,
"loss": 2.477,
"step": 300
},
{
"epoch": 0.12,
"learning_rate": 4.9795270519287886e-05,
"loss": 2.4205,
"step": 305
},
{
"epoch": 0.12,
"learning_rate": 4.9788512614756624e-05,
"loss": 2.4621,
"step": 310
},
{
"epoch": 0.13,
"learning_rate": 4.9781645451870875e-05,
"loss": 2.5098,
"step": 315
},
{
"epoch": 0.13,
"learning_rate": 4.9774669060898496e-05,
"loss": 2.4847,
"step": 320
},
{
"epoch": 0.13,
"learning_rate": 4.976758347258877e-05,
"loss": 2.4873,
"step": 325
},
{
"epoch": 0.13,
"learning_rate": 4.976038871817228e-05,
"loss": 2.4462,
"step": 330
},
{
"epoch": 0.13,
"learning_rate": 4.9753084829360776e-05,
"loss": 2.4994,
"step": 335
},
{
"epoch": 0.14,
"learning_rate": 4.974567183834702e-05,
"loss": 2.4994,
"step": 340
},
{
"epoch": 0.14,
"learning_rate": 4.9738149777804665e-05,
"loss": 2.4584,
"step": 345
},
{
"epoch": 0.14,
"learning_rate": 4.97305186808881e-05,
"loss": 2.4294,
"step": 350
},
{
"epoch": 0.14,
"learning_rate": 4.9722778581232305e-05,
"loss": 2.4499,
"step": 355
},
{
"epoch": 0.14,
"learning_rate": 4.9714929512952704e-05,
"loss": 2.5851,
"step": 360
},
{
"epoch": 0.15,
"learning_rate": 4.9706971510645e-05,
"loss": 2.4746,
"step": 365
},
{
"epoch": 0.15,
"learning_rate": 4.969890460938505e-05,
"loss": 2.4184,
"step": 370
},
{
"epoch": 0.15,
"learning_rate": 4.9690728844728704e-05,
"loss": 2.4716,
"step": 375
},
{
"epoch": 0.15,
"learning_rate": 4.968244425271161e-05,
"loss": 2.4477,
"step": 380
},
{
"epoch": 0.15,
"learning_rate": 4.9674050869849124e-05,
"loss": 2.4563,
"step": 385
},
{
"epoch": 0.16,
"learning_rate": 4.966554873313608e-05,
"loss": 2.3708,
"step": 390
},
{
"epoch": 0.16,
"learning_rate": 4.9656937880046676e-05,
"loss": 2.4351,
"step": 395
},
{
"epoch": 0.16,
"learning_rate": 4.9648218348534284e-05,
"loss": 2.3933,
"step": 400
},
{
"epoch": 0.16,
"learning_rate": 4.963939017703128e-05,
"loss": 2.5871,
"step": 405
},
{
"epoch": 0.16,
"learning_rate": 4.9630453404448905e-05,
"loss": 2.3965,
"step": 410
},
{
"epoch": 0.17,
"learning_rate": 4.962140807017705e-05,
"loss": 2.372,
"step": 415
},
{
"epoch": 0.17,
"learning_rate": 4.961225421408412e-05,
"loss": 2.4847,
"step": 420
},
{
"epoch": 0.17,
"learning_rate": 4.960299187651684e-05,
"loss": 2.4046,
"step": 425
},
{
"epoch": 0.17,
"learning_rate": 4.959362109830007e-05,
"loss": 2.3912,
"step": 430
},
{
"epoch": 0.17,
"learning_rate": 4.9584141920736656e-05,
"loss": 2.4732,
"step": 435
},
{
"epoch": 0.18,
"learning_rate": 4.957455438560721e-05,
"loss": 2.4854,
"step": 440
},
{
"epoch": 0.18,
"learning_rate": 4.956485853516993e-05,
"loss": 2.3736,
"step": 445
},
{
"epoch": 0.18,
"learning_rate": 4.9555054412160476e-05,
"loss": 2.4222,
"step": 450
},
{
"epoch": 0.18,
"learning_rate": 4.9545142059791686e-05,
"loss": 2.4498,
"step": 455
},
{
"epoch": 0.18,
"learning_rate": 4.9535121521753434e-05,
"loss": 2.4172,
"step": 460
},
{
"epoch": 0.19,
"learning_rate": 4.952499284221247e-05,
"loss": 2.4742,
"step": 465
},
{
"epoch": 0.19,
"learning_rate": 4.951475606581215e-05,
"loss": 2.4008,
"step": 470
},
{
"epoch": 0.19,
"learning_rate": 4.950441123767231e-05,
"loss": 2.4278,
"step": 475
},
{
"epoch": 0.19,
"learning_rate": 4.949395840338903e-05,
"loss": 2.5041,
"step": 480
},
{
"epoch": 0.19,
"learning_rate": 4.948339760903442e-05,
"loss": 2.4088,
"step": 485
},
{
"epoch": 0.2,
"learning_rate": 4.947272890115647e-05,
"loss": 2.466,
"step": 490
},
{
"epoch": 0.2,
"learning_rate": 4.946195232677878e-05,
"loss": 2.4404,
"step": 495
},
{
"epoch": 0.2,
"learning_rate": 4.9451067933400406e-05,
"loss": 2.3658,
"step": 500
},
{
"epoch": 0.2,
"learning_rate": 4.9440075768995625e-05,
"loss": 2.4247,
"step": 505
},
{
"epoch": 0.2,
"learning_rate": 4.942897588201372e-05,
"loss": 2.5082,
"step": 510
},
{
"epoch": 0.21,
"learning_rate": 4.941776832137879e-05,
"loss": 2.5545,
"step": 515
},
{
"epoch": 0.21,
"learning_rate": 4.940645313648949e-05,
"loss": 2.4665,
"step": 520
},
{
"epoch": 0.21,
"learning_rate": 4.939503037721888e-05,
"loss": 2.4195,
"step": 525
},
{
"epoch": 0.21,
"learning_rate": 4.938350009391413e-05,
"loss": 2.4908,
"step": 530
},
{
"epoch": 0.21,
"learning_rate": 4.937186233739637e-05,
"loss": 2.4093,
"step": 535
},
{
"epoch": 0.22,
"learning_rate": 4.93601171589604e-05,
"loss": 2.44,
"step": 540
},
{
"epoch": 0.22,
"learning_rate": 4.9348264610374494e-05,
"loss": 2.4989,
"step": 545
},
{
"epoch": 0.22,
"learning_rate": 4.9336304743880226e-05,
"loss": 2.3786,
"step": 550
},
{
"epoch": 0.22,
"learning_rate": 4.932423761219211e-05,
"loss": 2.4305,
"step": 555
},
{
"epoch": 0.22,
"learning_rate": 4.931206326849751e-05,
"loss": 2.4012,
"step": 560
},
{
"epoch": 0.23,
"learning_rate": 4.92997817664563e-05,
"loss": 2.4263,
"step": 565
},
{
"epoch": 0.23,
"learning_rate": 4.9287393160200676e-05,
"loss": 2.4749,
"step": 570
},
{
"epoch": 0.23,
"learning_rate": 4.927489750433492e-05,
"loss": 2.5083,
"step": 575
},
{
"epoch": 0.23,
"learning_rate": 4.926229485393513e-05,
"loss": 2.5228,
"step": 580
},
{
"epoch": 0.23,
"learning_rate": 4.924958526454902e-05,
"loss": 2.4623,
"step": 585
},
{
"epoch": 0.24,
"learning_rate": 4.923676879219562e-05,
"loss": 2.4199,
"step": 590
},
{
"epoch": 0.24,
"learning_rate": 4.9223845493365085e-05,
"loss": 2.2906,
"step": 595
},
{
"epoch": 0.24,
"learning_rate": 4.9210815425018406e-05,
"loss": 2.5539,
"step": 600
},
{
"epoch": 0.24,
"learning_rate": 4.919767864458718e-05,
"loss": 2.3456,
"step": 605
},
{
"epoch": 0.24,
"learning_rate": 4.9184435209973354e-05,
"loss": 2.4328,
"step": 610
},
{
"epoch": 0.25,
"learning_rate": 4.917108517954895e-05,
"loss": 2.3412,
"step": 615
},
{
"epoch": 0.25,
"learning_rate": 4.9157628612155836e-05,
"loss": 2.604,
"step": 620
},
{
"epoch": 0.25,
"learning_rate": 4.9144065567105465e-05,
"loss": 2.4007,
"step": 625
},
{
"epoch": 0.25,
"learning_rate": 4.913039610417859e-05,
"loss": 2.437,
"step": 630
},
{
"epoch": 0.25,
"learning_rate": 4.9116620283624996e-05,
"loss": 2.5004,
"step": 635
},
{
"epoch": 0.26,
"learning_rate": 4.91027381661633e-05,
"loss": 2.5045,
"step": 640
},
{
"epoch": 0.26,
"learning_rate": 4.908874981298057e-05,
"loss": 2.3794,
"step": 645
},
{
"epoch": 0.26,
"learning_rate": 4.9074655285732196e-05,
"loss": 2.4621,
"step": 650
},
{
"epoch": 0.26,
"learning_rate": 4.906045464654148e-05,
"loss": 2.549,
"step": 655
},
{
"epoch": 0.26,
"learning_rate": 4.9046147957999454e-05,
"loss": 2.4567,
"step": 660
},
{
"epoch": 0.27,
"learning_rate": 4.9031735283164574e-05,
"loss": 2.3243,
"step": 665
},
{
"epoch": 0.27,
"learning_rate": 4.901721668556244e-05,
"loss": 2.4758,
"step": 670
},
{
"epoch": 0.27,
"learning_rate": 4.9002592229185515e-05,
"loss": 2.5083,
"step": 675
},
{
"epoch": 0.27,
"learning_rate": 4.898786197849285e-05,
"loss": 2.4428,
"step": 680
},
{
"epoch": 0.27,
"learning_rate": 4.897302599840981e-05,
"loss": 2.4403,
"step": 685
},
{
"epoch": 0.28,
"learning_rate": 4.895808435432776e-05,
"loss": 2.4401,
"step": 690
},
{
"epoch": 0.28,
"learning_rate": 4.8943037112103784e-05,
"loss": 2.3789,
"step": 695
},
{
"epoch": 0.28,
"learning_rate": 4.892788433806042e-05,
"loss": 2.3945,
"step": 700
},
{
"epoch": 0.28,
"learning_rate": 4.8912626098985355e-05,
"loss": 2.4758,
"step": 705
},
{
"epoch": 0.28,
"learning_rate": 4.88972624621311e-05,
"loss": 2.4646,
"step": 710
},
{
"epoch": 0.29,
"learning_rate": 4.888179349521475e-05,
"loss": 2.4225,
"step": 715
},
{
"epoch": 0.29,
"learning_rate": 4.886621926641762e-05,
"loss": 2.4074,
"step": 720
},
{
"epoch": 0.29,
"learning_rate": 4.8850539844385017e-05,
"loss": 2.4438,
"step": 725
},
{
"epoch": 0.29,
"learning_rate": 4.883475529822587e-05,
"loss": 2.3666,
"step": 730
},
{
"epoch": 0.29,
"learning_rate": 4.881886569751248e-05,
"loss": 2.3782,
"step": 735
},
{
"epoch": 0.3,
"learning_rate": 4.880287111228016e-05,
"loss": 2.4916,
"step": 740
},
{
"epoch": 0.3,
"learning_rate": 4.878677161302698e-05,
"loss": 2.3639,
"step": 745
},
{
"epoch": 0.3,
"learning_rate": 4.877056727071342e-05,
"loss": 2.4333,
"step": 750
},
{
"epoch": 0.3,
"learning_rate": 4.8754258156762075e-05,
"loss": 2.3907,
"step": 755
},
{
"epoch": 0.3,
"learning_rate": 4.8737844343057315e-05,
"loss": 2.433,
"step": 760
},
{
"epoch": 0.31,
"learning_rate": 4.8721325901945015e-05,
"loss": 2.3849,
"step": 765
},
{
"epoch": 0.31,
"learning_rate": 4.870470290623218e-05,
"loss": 2.419,
"step": 770
},
{
"epoch": 0.31,
"learning_rate": 4.8687975429186685e-05,
"loss": 2.3694,
"step": 775
},
{
"epoch": 0.31,
"learning_rate": 4.867114354453688e-05,
"loss": 2.4335,
"step": 780
},
{
"epoch": 0.31,
"learning_rate": 4.865420732647133e-05,
"loss": 2.4168,
"step": 785
},
{
"epoch": 0.32,
"learning_rate": 4.863716684963846e-05,
"loss": 2.419,
"step": 790
},
{
"epoch": 0.32,
"learning_rate": 4.862002218914622e-05,
"loss": 2.335,
"step": 795
},
{
"epoch": 0.32,
"learning_rate": 4.860277342056176e-05,
"loss": 2.4059,
"step": 800
},
{
"epoch": 0.32,
"learning_rate": 4.858542061991112e-05,
"loss": 2.3423,
"step": 805
},
{
"epoch": 0.32,
"learning_rate": 4.856796386367884e-05,
"loss": 2.4135,
"step": 810
},
{
"epoch": 0.33,
"learning_rate": 4.855040322880769e-05,
"loss": 2.3652,
"step": 815
},
{
"epoch": 0.33,
"learning_rate": 4.853273879269827e-05,
"loss": 2.3511,
"step": 820
},
{
"epoch": 0.33,
"learning_rate": 4.8514970633208726e-05,
"loss": 2.413,
"step": 825
},
{
"epoch": 0.33,
"learning_rate": 4.849709882865435e-05,
"loss": 2.4445,
"step": 830
},
{
"epoch": 0.33,
"learning_rate": 4.847912345780727e-05,
"loss": 2.4221,
"step": 835
},
{
"epoch": 0.34,
"learning_rate": 4.846104459989611e-05,
"loss": 2.4992,
"step": 840
},
{
"epoch": 0.34,
"learning_rate": 4.84428623346056e-05,
"loss": 2.3923,
"step": 845
},
{
"epoch": 0.34,
"learning_rate": 4.842457674207627e-05,
"loss": 2.3666,
"step": 850
},
{
"epoch": 0.34,
"learning_rate": 4.8406187902904076e-05,
"loss": 2.4329,
"step": 855
},
{
"epoch": 0.34,
"learning_rate": 4.8387695898140026e-05,
"loss": 2.3429,
"step": 860
},
{
"epoch": 0.35,
"learning_rate": 4.836910080928987e-05,
"loss": 2.4428,
"step": 865
},
{
"epoch": 0.35,
"learning_rate": 4.83504027183137e-05,
"loss": 2.3842,
"step": 870
},
{
"epoch": 0.35,
"learning_rate": 4.833160170762561e-05,
"loss": 2.4064,
"step": 875
},
{
"epoch": 0.35,
"learning_rate": 4.8312697860093295e-05,
"loss": 2.3705,
"step": 880
},
{
"epoch": 0.35,
"learning_rate": 4.829369125903776e-05,
"loss": 2.4151,
"step": 885
},
{
"epoch": 0.36,
"learning_rate": 4.8274581988232894e-05,
"loss": 2.4219,
"step": 890
},
{
"epoch": 0.36,
"learning_rate": 4.825537013190509e-05,
"loss": 2.4042,
"step": 895
},
{
"epoch": 0.36,
"learning_rate": 4.823605577473293e-05,
"loss": 2.4509,
"step": 900
},
{
"epoch": 0.36,
"learning_rate": 4.8216639001846764e-05,
"loss": 2.4255,
"step": 905
},
{
"epoch": 0.36,
"learning_rate": 4.8197119898828367e-05,
"loss": 2.4928,
"step": 910
},
{
"epoch": 0.37,
"learning_rate": 4.817749855171052e-05,
"loss": 2.4044,
"step": 915
},
{
"epoch": 0.37,
"learning_rate": 4.8157775046976684e-05,
"loss": 2.4085,
"step": 920
},
{
"epoch": 0.37,
"learning_rate": 4.813794947156058e-05,
"loss": 2.3941,
"step": 925
},
{
"epoch": 0.37,
"learning_rate": 4.8118021912845815e-05,
"loss": 2.3493,
"step": 930
},
{
"epoch": 0.37,
"learning_rate": 4.8097992458665506e-05,
"loss": 2.3367,
"step": 935
},
{
"epoch": 0.38,
"learning_rate": 4.807786119730189e-05,
"loss": 2.3865,
"step": 940
},
{
"epoch": 0.38,
"learning_rate": 4.8057628217485916e-05,
"loss": 2.3885,
"step": 945
},
{
"epoch": 0.38,
"learning_rate": 4.803729360839688e-05,
"loss": 2.4296,
"step": 950
},
{
"epoch": 0.38,
"learning_rate": 4.801685745966203e-05,
"loss": 2.3856,
"step": 955
},
{
"epoch": 0.38,
"learning_rate": 4.799631986135615e-05,
"loss": 2.3631,
"step": 960
},
{
"epoch": 0.39,
"learning_rate": 4.797568090400117e-05,
"loss": 2.3882,
"step": 965
},
{
"epoch": 0.39,
"learning_rate": 4.7954940678565785e-05,
"loss": 2.3396,
"step": 970
},
{
"epoch": 0.39,
"learning_rate": 4.793409927646504e-05,
"loss": 2.3548,
"step": 975
},
{
"epoch": 0.39,
"learning_rate": 4.791315678955991e-05,
"loss": 2.4576,
"step": 980
},
{
"epoch": 0.39,
"learning_rate": 4.789211331015695e-05,
"loss": 2.4523,
"step": 985
},
{
"epoch": 0.4,
"learning_rate": 4.787096893100781e-05,
"loss": 2.2542,
"step": 990
},
{
"epoch": 0.4,
"learning_rate": 4.784972374530889e-05,
"loss": 2.4385,
"step": 995
},
{
"epoch": 0.4,
"learning_rate": 4.7828377846700925e-05,
"loss": 2.3266,
"step": 1000
},
{
"epoch": 0.4,
"learning_rate": 4.780693132926851e-05,
"loss": 2.3301,
"step": 1005
},
{
"epoch": 0.4,
"learning_rate": 4.7785384287539755e-05,
"loss": 2.3554,
"step": 1010
},
{
"epoch": 0.41,
"learning_rate": 4.776373681648586e-05,
"loss": 2.3838,
"step": 1015
},
{
"epoch": 0.41,
"learning_rate": 4.7741989011520645e-05,
"loss": 2.3361,
"step": 1020
},
{
"epoch": 0.41,
"learning_rate": 4.772014096850018e-05,
"loss": 2.2864,
"step": 1025
},
{
"epoch": 0.41,
"learning_rate": 4.769819278372235e-05,
"loss": 2.3955,
"step": 1030
},
{
"epoch": 0.41,
"learning_rate": 4.7676144553926414e-05,
"loss": 2.3802,
"step": 1035
},
{
"epoch": 0.42,
"learning_rate": 4.765399637629262e-05,
"loss": 2.2856,
"step": 1040
},
{
"epoch": 0.42,
"learning_rate": 4.7631748348441705e-05,
"loss": 2.3698,
"step": 1045
},
{
"epoch": 0.42,
"learning_rate": 4.760940056843454e-05,
"loss": 2.3305,
"step": 1050
},
{
"epoch": 0.42,
"learning_rate": 4.758695313477166e-05,
"loss": 2.4944,
"step": 1055
},
{
"epoch": 0.43,
"learning_rate": 4.756440614639283e-05,
"loss": 2.4622,
"step": 1060
},
{
"epoch": 0.43,
"learning_rate": 4.754175970267661e-05,
"loss": 2.3995,
"step": 1065
},
{
"epoch": 0.43,
"learning_rate": 4.751901390343995e-05,
"loss": 2.343,
"step": 1070
},
{
"epoch": 0.43,
"learning_rate": 4.7496168848937674e-05,
"loss": 2.4388,
"step": 1075
},
{
"epoch": 0.43,
"learning_rate": 4.7473224639862116e-05,
"loss": 2.3694,
"step": 1080
},
{
"epoch": 0.44,
"learning_rate": 4.745018137734264e-05,
"loss": 2.3485,
"step": 1085
},
{
"epoch": 0.44,
"learning_rate": 4.742703916294521e-05,
"loss": 2.46,
"step": 1090
},
{
"epoch": 0.44,
"learning_rate": 4.740379809867193e-05,
"loss": 2.3138,
"step": 1095
},
{
"epoch": 0.44,
"learning_rate": 4.738045828696056e-05,
"loss": 2.4117,
"step": 1100
},
{
"epoch": 0.44,
"learning_rate": 4.735701983068416e-05,
"loss": 2.3506,
"step": 1105
},
{
"epoch": 0.45,
"learning_rate": 4.7333482833150525e-05,
"loss": 2.3711,
"step": 1110
},
{
"epoch": 0.45,
"learning_rate": 4.730984739810183e-05,
"loss": 2.2639,
"step": 1115
},
{
"epoch": 0.45,
"learning_rate": 4.728611362971408e-05,
"loss": 2.3749,
"step": 1120
},
{
"epoch": 0.45,
"learning_rate": 4.726228163259673e-05,
"loss": 2.4556,
"step": 1125
},
{
"epoch": 0.45,
"learning_rate": 4.7238351511792165e-05,
"loss": 2.4233,
"step": 1130
},
{
"epoch": 0.46,
"learning_rate": 4.721432337277529e-05,
"loss": 2.3544,
"step": 1135
},
{
"epoch": 0.46,
"learning_rate": 4.7190197321453014e-05,
"loss": 2.3654,
"step": 1140
},
{
"epoch": 0.46,
"learning_rate": 4.716597346416382e-05,
"loss": 2.3356,
"step": 1145
},
{
"epoch": 0.46,
"learning_rate": 4.7141651907677256e-05,
"loss": 2.4522,
"step": 1150
},
{
"epoch": 0.46,
"learning_rate": 4.7117232759193534e-05,
"loss": 2.3104,
"step": 1155
},
{
"epoch": 0.47,
"learning_rate": 4.709271612634298e-05,
"loss": 2.4492,
"step": 1160
},
{
"epoch": 0.47,
"learning_rate": 4.706810211718561e-05,
"loss": 2.4437,
"step": 1165
},
{
"epoch": 0.47,
"learning_rate": 4.7043390840210636e-05,
"loss": 2.3099,
"step": 1170
},
{
"epoch": 0.47,
"learning_rate": 4.701858240433597e-05,
"loss": 2.351,
"step": 1175
},
{
"epoch": 0.47,
"learning_rate": 4.6993676918907804e-05,
"loss": 2.4756,
"step": 1180
},
{
"epoch": 0.48,
"learning_rate": 4.696867449370005e-05,
"loss": 2.418,
"step": 1185
},
{
"epoch": 0.48,
"learning_rate": 4.6943575238913904e-05,
"loss": 2.5026,
"step": 1190
},
{
"epoch": 0.48,
"learning_rate": 4.691837926517737e-05,
"loss": 2.4096,
"step": 1195
},
{
"epoch": 0.48,
"learning_rate": 4.689308668354473e-05,
"loss": 2.4101,
"step": 1200
},
{
"epoch": 0.48,
"learning_rate": 4.686769760549607e-05,
"loss": 2.4533,
"step": 1205
},
{
"epoch": 0.49,
"learning_rate": 4.684221214293683e-05,
"loss": 2.2988,
"step": 1210
},
{
"epoch": 0.49,
"learning_rate": 4.681663040819724e-05,
"loss": 2.3937,
"step": 1215
},
{
"epoch": 0.49,
"learning_rate": 4.679095251403189e-05,
"loss": 2.3954,
"step": 1220
},
{
"epoch": 0.49,
"learning_rate": 4.676517857361917e-05,
"loss": 2.3275,
"step": 1225
},
{
"epoch": 0.49,
"learning_rate": 4.673930870056085e-05,
"loss": 2.4748,
"step": 1230
},
{
"epoch": 0.5,
"learning_rate": 4.67133430088815e-05,
"loss": 2.2496,
"step": 1235
},
{
"epoch": 0.5,
"learning_rate": 4.668728161302803e-05,
"loss": 2.3226,
"step": 1240
},
{
"epoch": 0.5,
"learning_rate": 4.666112462786919e-05,
"loss": 2.4655,
"step": 1245
},
{
"epoch": 0.5,
"learning_rate": 4.663487216869502e-05,
"loss": 2.3751,
"step": 1250
},
{
"epoch": 0.5,
"learning_rate": 4.660852435121642e-05,
"loss": 2.4136,
"step": 1255
},
{
"epoch": 0.51,
"learning_rate": 4.658208129156456e-05,
"loss": 2.3612,
"step": 1260
},
{
"epoch": 0.51,
"learning_rate": 4.655554310629041e-05,
"loss": 2.3675,
"step": 1265
},
{
"epoch": 0.51,
"learning_rate": 4.652890991236421e-05,
"loss": 2.2831,
"step": 1270
},
{
"epoch": 0.51,
"learning_rate": 4.650218182717498e-05,
"loss": 2.3958,
"step": 1275
},
{
"epoch": 0.51,
"learning_rate": 4.647535896852997e-05,
"loss": 2.3236,
"step": 1280
},
{
"epoch": 0.52,
"learning_rate": 4.6448441454654156e-05,
"loss": 2.3904,
"step": 1285
},
{
"epoch": 0.52,
"learning_rate": 4.642142940418973e-05,
"loss": 2.3565,
"step": 1290
},
{
"epoch": 0.52,
"learning_rate": 4.6394322936195556e-05,
"loss": 2.5229,
"step": 1295
},
{
"epoch": 0.52,
"learning_rate": 4.636712217014665e-05,
"loss": 2.369,
"step": 1300
},
{
"epoch": 0.52,
"learning_rate": 4.6339827225933665e-05,
"loss": 2.3444,
"step": 1305
},
{
"epoch": 0.53,
"learning_rate": 4.6312438223862356e-05,
"loss": 2.3387,
"step": 1310
},
{
"epoch": 0.53,
"learning_rate": 4.628495528465305e-05,
"loss": 2.3589,
"step": 1315
},
{
"epoch": 0.53,
"learning_rate": 4.625737852944011e-05,
"loss": 2.4779,
"step": 1320
},
{
"epoch": 0.53,
"learning_rate": 4.62297080797714e-05,
"loss": 2.4398,
"step": 1325
},
{
"epoch": 0.53,
"learning_rate": 4.620194405760777e-05,
"loss": 2.383,
"step": 1330
},
{
"epoch": 0.54,
"learning_rate": 4.6174086585322485e-05,
"loss": 2.424,
"step": 1335
},
{
"epoch": 0.54,
"learning_rate": 4.6146135785700705e-05,
"loss": 2.4289,
"step": 1340
},
{
"epoch": 0.54,
"learning_rate": 4.611809178193896e-05,
"loss": 2.225,
"step": 1345
},
{
"epoch": 0.54,
"learning_rate": 4.608995469764455e-05,
"loss": 2.3643,
"step": 1350
},
{
"epoch": 0.54,
"learning_rate": 4.606172465683508e-05,
"loss": 2.4278,
"step": 1355
},
{
"epoch": 0.55,
"learning_rate": 4.6033401783937844e-05,
"loss": 2.4464,
"step": 1360
},
{
"epoch": 0.55,
"learning_rate": 4.600498620378932e-05,
"loss": 2.3639,
"step": 1365
},
{
"epoch": 0.55,
"learning_rate": 4.597647804163461e-05,
"loss": 2.3595,
"step": 1370
},
{
"epoch": 0.55,
"learning_rate": 4.5947877423126864e-05,
"loss": 2.3569,
"step": 1375
},
{
"epoch": 0.55,
"learning_rate": 4.591918447432675e-05,
"loss": 2.4167,
"step": 1380
},
{
"epoch": 0.56,
"learning_rate": 4.589039932170188e-05,
"loss": 2.3959,
"step": 1385
},
{
"epoch": 0.56,
"learning_rate": 4.5861522092126313e-05,
"loss": 2.3629,
"step": 1390
},
{
"epoch": 0.56,
"learning_rate": 4.5832552912879894e-05,
"loss": 2.3978,
"step": 1395
},
{
"epoch": 0.56,
"learning_rate": 4.580349191164777e-05,
"loss": 2.4372,
"step": 1400
},
{
"epoch": 0.56,
"learning_rate": 4.5774339216519815e-05,
"loss": 2.4422,
"step": 1405
},
{
"epoch": 0.57,
"learning_rate": 4.574509495599003e-05,
"loss": 2.3786,
"step": 1410
},
{
"epoch": 0.57,
"learning_rate": 4.5715759258956025e-05,
"loss": 2.3467,
"step": 1415
},
{
"epoch": 0.57,
"learning_rate": 4.568633225471841e-05,
"loss": 2.371,
"step": 1420
},
{
"epoch": 0.57,
"learning_rate": 4.565681407298026e-05,
"loss": 2.3776,
"step": 1425
},
{
"epoch": 0.57,
"learning_rate": 4.5627204843846504e-05,
"loss": 2.3036,
"step": 1430
},
{
"epoch": 0.58,
"learning_rate": 4.559750469782339e-05,
"loss": 2.446,
"step": 1435
},
{
"epoch": 0.58,
"learning_rate": 4.5567713765817886e-05,
"loss": 2.3521,
"step": 1440
},
{
"epoch": 0.58,
"learning_rate": 4.553783217913712e-05,
"loss": 2.3322,
"step": 1445
},
{
"epoch": 0.58,
"learning_rate": 4.550786006948777e-05,
"loss": 2.3966,
"step": 1450
},
{
"epoch": 0.58,
"learning_rate": 4.547779756897554e-05,
"loss": 2.35,
"step": 1455
},
{
"epoch": 0.59,
"learning_rate": 4.544764481010451e-05,
"loss": 2.3739,
"step": 1460
},
{
"epoch": 0.59,
"learning_rate": 4.541740192577658e-05,
"loss": 2.4817,
"step": 1465
},
{
"epoch": 0.59,
"learning_rate": 4.538706904929092e-05,
"loss": 2.3857,
"step": 1470
},
{
"epoch": 0.59,
"learning_rate": 4.5356646314343344e-05,
"loss": 2.3453,
"step": 1475
},
{
"epoch": 0.59,
"learning_rate": 4.532613385502571e-05,
"loss": 2.2916,
"step": 1480
},
{
"epoch": 0.6,
"learning_rate": 4.5295531805825355e-05,
"loss": 2.338,
"step": 1485
},
{
"epoch": 0.6,
"learning_rate": 4.526484030162449e-05,
"loss": 2.2829,
"step": 1490
},
{
"epoch": 0.6,
"learning_rate": 4.5234059477699635e-05,
"loss": 2.3761,
"step": 1495
},
{
"epoch": 0.6,
"learning_rate": 4.520318946972097e-05,
"loss": 2.4692,
"step": 1500
},
{
"epoch": 0.6,
"learning_rate": 4.517223041375176e-05,
"loss": 2.3689,
"step": 1505
},
{
"epoch": 0.61,
"learning_rate": 4.514118244624779e-05,
"loss": 2.4082,
"step": 1510
},
{
"epoch": 0.61,
"learning_rate": 4.51100457040567e-05,
"loss": 2.4152,
"step": 1515
},
{
"epoch": 0.61,
"learning_rate": 4.507882032441745e-05,
"loss": 2.389,
"step": 1520
},
{
"epoch": 0.61,
"learning_rate": 4.504750644495965e-05,
"loss": 2.4914,
"step": 1525
},
{
"epoch": 0.61,
"learning_rate": 4.501610420370298e-05,
"loss": 2.4066,
"step": 1530
},
{
"epoch": 0.62,
"learning_rate": 4.4984613739056635e-05,
"loss": 2.3664,
"step": 1535
},
{
"epoch": 0.62,
"learning_rate": 4.4953035189818597e-05,
"loss": 2.2608,
"step": 1540
},
{
"epoch": 0.62,
"learning_rate": 4.4921368695175145e-05,
"loss": 2.3886,
"step": 1545
},
{
"epoch": 0.62,
"learning_rate": 4.488961439470015e-05,
"loss": 2.3459,
"step": 1550
},
{
"epoch": 0.62,
"learning_rate": 4.4857772428354536e-05,
"loss": 2.3653,
"step": 1555
},
{
"epoch": 0.63,
"learning_rate": 4.4825842936485585e-05,
"loss": 2.3518,
"step": 1560
},
{
"epoch": 0.63,
"learning_rate": 4.4793826059826394e-05,
"loss": 2.5581,
"step": 1565
},
{
"epoch": 0.63,
"learning_rate": 4.4761721939495185e-05,
"loss": 2.4307,
"step": 1570
},
{
"epoch": 0.63,
"learning_rate": 4.472953071699475e-05,
"loss": 2.4616,
"step": 1575
},
{
"epoch": 0.63,
"learning_rate": 4.469725253421177e-05,
"loss": 2.4261,
"step": 1580
},
{
"epoch": 0.64,
"learning_rate": 4.466488753341623e-05,
"loss": 2.404,
"step": 1585
},
{
"epoch": 0.64,
"learning_rate": 4.4632435857260754e-05,
"loss": 2.374,
"step": 1590
},
{
"epoch": 0.64,
"learning_rate": 4.459989764878004e-05,
"loss": 2.3282,
"step": 1595
},
{
"epoch": 0.64,
"learning_rate": 4.456727305139013e-05,
"loss": 2.3896,
"step": 1600
},
{
"epoch": 0.64,
"learning_rate": 4.453456220888788e-05,
"loss": 2.5145,
"step": 1605
},
{
"epoch": 0.65,
"learning_rate": 4.4501765265450265e-05,
"loss": 2.4032,
"step": 1610
},
{
"epoch": 0.65,
"learning_rate": 4.446888236563377e-05,
"loss": 2.3513,
"step": 1615
},
{
"epoch": 0.65,
"learning_rate": 4.4435913654373726e-05,
"loss": 2.2915,
"step": 1620
},
{
"epoch": 0.65,
"learning_rate": 4.44028592769837e-05,
"loss": 2.3697,
"step": 1625
},
{
"epoch": 0.65,
"learning_rate": 4.4369719379154846e-05,
"loss": 2.2917,
"step": 1630
},
{
"epoch": 0.66,
"learning_rate": 4.433649410695525e-05,
"loss": 2.3396,
"step": 1635
},
{
"epoch": 0.66,
"learning_rate": 4.4303183606829304e-05,
"loss": 2.3729,
"step": 1640
},
{
"epoch": 0.66,
"learning_rate": 4.426978802559704e-05,
"loss": 2.3824,
"step": 1645
},
{
"epoch": 0.66,
"learning_rate": 4.423630751045351e-05,
"loss": 2.3842,
"step": 1650
},
{
"epoch": 0.66,
"learning_rate": 4.4202742208968115e-05,
"loss": 2.333,
"step": 1655
},
{
"epoch": 0.67,
"learning_rate": 4.416909226908398e-05,
"loss": 2.3321,
"step": 1660
},
{
"epoch": 0.67,
"learning_rate": 4.4135357839117235e-05,
"loss": 2.2699,
"step": 1665
},
{
"epoch": 0.67,
"learning_rate": 4.410153906775647e-05,
"loss": 2.3899,
"step": 1670
},
{
"epoch": 0.67,
"learning_rate": 4.406763610406197e-05,
"loss": 2.3605,
"step": 1675
},
{
"epoch": 0.67,
"learning_rate": 4.403364909746516e-05,
"loss": 2.3266,
"step": 1680
},
{
"epoch": 0.68,
"learning_rate": 4.399957819776783e-05,
"loss": 2.4621,
"step": 1685
},
{
"epoch": 0.68,
"learning_rate": 4.396542355514159e-05,
"loss": 2.4612,
"step": 1690
},
{
"epoch": 0.68,
"learning_rate": 4.3931185320127154e-05,
"loss": 2.4084,
"step": 1695
},
{
"epoch": 0.68,
"learning_rate": 4.389686364363365e-05,
"loss": 2.3852,
"step": 1700
},
{
"epoch": 0.68,
"learning_rate": 4.386245867693799e-05,
"loss": 2.3827,
"step": 1705
},
{
"epoch": 0.69,
"learning_rate": 4.3827970571684226e-05,
"loss": 2.2558,
"step": 1710
},
{
"epoch": 0.69,
"learning_rate": 4.3793399479882834e-05,
"loss": 2.3745,
"step": 1715
},
{
"epoch": 0.69,
"learning_rate": 4.375874555391006e-05,
"loss": 2.3762,
"step": 1720
},
{
"epoch": 0.69,
"learning_rate": 4.3724008946507255e-05,
"loss": 2.3857,
"step": 1725
},
{
"epoch": 0.69,
"learning_rate": 4.368918981078019e-05,
"loss": 2.3628,
"step": 1730
},
{
"epoch": 0.7,
"learning_rate": 4.3654288300198424e-05,
"loss": 2.4098,
"step": 1735
},
{
"epoch": 0.7,
"learning_rate": 4.361930456859455e-05,
"loss": 2.4795,
"step": 1740
},
{
"epoch": 0.7,
"learning_rate": 4.3584238770163575e-05,
"loss": 2.2823,
"step": 1745
},
{
"epoch": 0.7,
"learning_rate": 4.354909105946223e-05,
"loss": 2.4052,
"step": 1750
},
{
"epoch": 0.7,
"learning_rate": 4.35138615914083e-05,
"loss": 2.453,
"step": 1755
},
{
"epoch": 0.71,
"learning_rate": 4.347855052127988e-05,
"loss": 2.3922,
"step": 1760
},
{
"epoch": 0.71,
"learning_rate": 4.344315800471479e-05,
"loss": 2.3853,
"step": 1765
},
{
"epoch": 0.71,
"learning_rate": 4.340768419770979e-05,
"loss": 2.4103,
"step": 1770
},
{
"epoch": 0.71,
"learning_rate": 4.3372129256619965e-05,
"loss": 2.4206,
"step": 1775
},
{
"epoch": 0.71,
"learning_rate": 4.3336493338158004e-05,
"loss": 2.3072,
"step": 1780
},
{
"epoch": 0.72,
"learning_rate": 4.330077659939349e-05,
"loss": 2.4468,
"step": 1785
},
{
"epoch": 0.72,
"learning_rate": 4.326497919775228e-05,
"loss": 2.2803,
"step": 1790
},
{
"epoch": 0.72,
"learning_rate": 4.32291012910157e-05,
"loss": 2.3762,
"step": 1795
},
{
"epoch": 0.72,
"learning_rate": 4.319314303731997e-05,
"loss": 2.3452,
"step": 1800
}
],
"logging_steps": 5,
"max_steps": 7482,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 100,
"total_flos": 2.402932859142144e+16,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}