coolshell-llm / trainer_state.json
zhaokun's picture
Add models
58d149a
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 25.0,
"eval_steps": 500,
"global_step": 1100,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.11,
"learning_rate": 0.001999898043009433,
"loss": 4.5094,
"step": 5
},
{
"epoch": 0.23,
"learning_rate": 0.0019995921928281893,
"loss": 3.8047,
"step": 10
},
{
"epoch": 0.34,
"learning_rate": 0.001999082511823396,
"loss": 3.8813,
"step": 15
},
{
"epoch": 0.45,
"learning_rate": 0.0019983691039261358,
"loss": 3.7188,
"step": 20
},
{
"epoch": 0.57,
"learning_rate": 0.0019974521146102534,
"loss": 3.6695,
"step": 25
},
{
"epoch": 0.68,
"learning_rate": 0.001996331730862691,
"loss": 3.7078,
"step": 30
},
{
"epoch": 0.8,
"learning_rate": 0.0019950081811453595,
"loss": 3.6844,
"step": 35
},
{
"epoch": 0.91,
"learning_rate": 0.0019934817353485504,
"loss": 3.6961,
"step": 40
},
{
"epoch": 1.02,
"learning_rate": 0.0019917527047359027,
"loss": 3.5758,
"step": 45
},
{
"epoch": 1.14,
"learning_rate": 0.001989821441880933,
"loss": 3.4102,
"step": 50
},
{
"epoch": 1.25,
"learning_rate": 0.0019876883405951376,
"loss": 3.3984,
"step": 55
},
{
"epoch": 1.36,
"learning_rate": 0.001985353835847693,
"loss": 3.3602,
"step": 60
},
{
"epoch": 1.48,
"learning_rate": 0.0019828184036767556,
"loss": 3.4461,
"step": 65
},
{
"epoch": 1.59,
"learning_rate": 0.0019800825610923932,
"loss": 3.3461,
"step": 70
},
{
"epoch": 1.7,
"learning_rate": 0.0019771468659711597,
"loss": 3.4172,
"step": 75
},
{
"epoch": 1.82,
"learning_rate": 0.0019740119169423336,
"loss": 3.4359,
"step": 80
},
{
"epoch": 1.93,
"learning_rate": 0.0019706783532658523,
"loss": 3.5141,
"step": 85
},
{
"epoch": 2.05,
"learning_rate": 0.001967146854701957,
"loss": 3.2242,
"step": 90
},
{
"epoch": 2.16,
"learning_rate": 0.0019634181413725788,
"loss": 3.0227,
"step": 95
},
{
"epoch": 2.27,
"learning_rate": 0.0019594929736144974,
"loss": 2.8984,
"step": 100
},
{
"epoch": 2.39,
"learning_rate": 0.001955372151824297,
"loss": 3.0781,
"step": 105
},
{
"epoch": 2.5,
"learning_rate": 0.0019510565162951536,
"loss": 3.1203,
"step": 110
},
{
"epoch": 2.61,
"learning_rate": 0.00194654694704549,
"loss": 3.1828,
"step": 115
},
{
"epoch": 2.73,
"learning_rate": 0.0019418443636395248,
"loss": 3.0531,
"step": 120
},
{
"epoch": 2.84,
"learning_rate": 0.001936949724999762,
"loss": 3.1523,
"step": 125
},
{
"epoch": 2.95,
"learning_rate": 0.0019318640292114524,
"loss": 3.1156,
"step": 130
},
{
"epoch": 3.07,
"learning_rate": 0.0019265883133190713,
"loss": 2.7844,
"step": 135
},
{
"epoch": 3.18,
"learning_rate": 0.0019211236531148502,
"loss": 2.6711,
"step": 140
},
{
"epoch": 3.3,
"learning_rate": 0.0019154711629194062,
"loss": 2.6609,
"step": 145
},
{
"epoch": 3.41,
"learning_rate": 0.0019096319953545184,
"loss": 2.7531,
"step": 150
},
{
"epoch": 3.52,
"learning_rate": 0.0019036073411080917,
"loss": 2.7977,
"step": 155
},
{
"epoch": 3.64,
"learning_rate": 0.0018973984286913585,
"loss": 2.7914,
"step": 160
},
{
"epoch": 3.75,
"learning_rate": 0.0018910065241883678,
"loss": 2.8188,
"step": 165
},
{
"epoch": 3.86,
"learning_rate": 0.0018844329309978143,
"loss": 2.8945,
"step": 170
},
{
"epoch": 3.98,
"learning_rate": 0.0018776789895672556,
"loss": 2.8883,
"step": 175
},
{
"epoch": 4.09,
"learning_rate": 0.0018707460771197773,
"loss": 2.4617,
"step": 180
},
{
"epoch": 4.2,
"learning_rate": 0.001863635607373157,
"loss": 2.4633,
"step": 185
},
{
"epoch": 4.32,
"learning_rate": 0.001856349030251589,
"loss": 2.5094,
"step": 190
},
{
"epoch": 4.43,
"learning_rate": 0.0018488878315900226,
"loss": 2.432,
"step": 195
},
{
"epoch": 4.55,
"learning_rate": 0.0018412535328311812,
"loss": 2.5648,
"step": 200
},
{
"epoch": 4.66,
"learning_rate": 0.0018334476907153176,
"loss": 2.4836,
"step": 205
},
{
"epoch": 4.77,
"learning_rate": 0.001825471896962774,
"loss": 2.6617,
"step": 210
},
{
"epoch": 4.89,
"learning_rate": 0.0018173277779494068,
"loss": 2.6734,
"step": 215
},
{
"epoch": 5.0,
"learning_rate": 0.0018090169943749475,
"loss": 2.6742,
"step": 220
},
{
"epoch": 5.11,
"learning_rate": 0.0018005412409243604,
"loss": 2.1379,
"step": 225
},
{
"epoch": 5.23,
"learning_rate": 0.0017919022459222751,
"loss": 2.1508,
"step": 230
},
{
"epoch": 5.34,
"learning_rate": 0.0017831017709805555,
"loss": 2.2582,
"step": 235
},
{
"epoch": 5.45,
"learning_rate": 0.0017741416106390826,
"loss": 2.2367,
"step": 240
},
{
"epoch": 5.57,
"learning_rate": 0.0017650235919998232,
"loss": 2.325,
"step": 245
},
{
"epoch": 5.68,
"learning_rate": 0.0017557495743542584,
"loss": 2.2703,
"step": 250
},
{
"epoch": 5.8,
"learning_rate": 0.0017463214488042471,
"loss": 2.3703,
"step": 255
},
{
"epoch": 5.91,
"learning_rate": 0.001736741137876405,
"loss": 2.4648,
"step": 260
},
{
"epoch": 6.02,
"learning_rate": 0.0017270105951300739,
"loss": 2.2734,
"step": 265
},
{
"epoch": 6.14,
"learning_rate": 0.0017171318047589637,
"loss": 1.9898,
"step": 270
},
{
"epoch": 6.25,
"learning_rate": 0.0017071067811865474,
"loss": 1.9816,
"step": 275
},
{
"epoch": 6.36,
"learning_rate": 0.0016969375686552938,
"loss": 1.9648,
"step": 280
},
{
"epoch": 6.48,
"learning_rate": 0.0016866262408098134,
"loss": 2.1672,
"step": 285
},
{
"epoch": 6.59,
"learning_rate": 0.0016761749002740195,
"loss": 2.0074,
"step": 290
},
{
"epoch": 6.7,
"learning_rate": 0.0016655856782223683,
"loss": 2.1598,
"step": 295
},
{
"epoch": 6.82,
"learning_rate": 0.0016548607339452852,
"loss": 2.0996,
"step": 300
},
{
"epoch": 6.93,
"learning_rate": 0.0016440022544088554,
"loss": 2.1434,
"step": 305
},
{
"epoch": 7.05,
"learning_rate": 0.0016330124538088703,
"loss": 2.0699,
"step": 310
},
{
"epoch": 7.16,
"learning_rate": 0.0016218935731193223,
"loss": 1.7312,
"step": 315
},
{
"epoch": 7.27,
"learning_rate": 0.0016106478796354383,
"loss": 1.7799,
"step": 320
},
{
"epoch": 7.39,
"learning_rate": 0.0015992776665113468,
"loss": 1.7008,
"step": 325
},
{
"epoch": 7.5,
"learning_rate": 0.0015877852522924731,
"loss": 1.8969,
"step": 330
},
{
"epoch": 7.61,
"learning_rate": 0.0015761729804427528,
"loss": 1.8156,
"step": 335
},
{
"epoch": 7.73,
"learning_rate": 0.0015644432188667695,
"loss": 1.9336,
"step": 340
},
{
"epoch": 7.84,
"learning_rate": 0.0015525983594269026,
"loss": 1.9918,
"step": 345
},
{
"epoch": 7.95,
"learning_rate": 0.0015406408174555976,
"loss": 2.0055,
"step": 350
},
{
"epoch": 8.07,
"learning_rate": 0.0015285730312628418,
"loss": 1.7168,
"step": 355
},
{
"epoch": 8.18,
"learning_rate": 0.001516397461638962,
"loss": 1.5531,
"step": 360
},
{
"epoch": 8.3,
"learning_rate": 0.001504116591352832,
"loss": 1.5922,
"step": 365
},
{
"epoch": 8.41,
"learning_rate": 0.001491732924645604,
"loss": 1.618,
"step": 370
},
{
"epoch": 8.52,
"learning_rate": 0.0014792489867200569,
"loss": 1.6738,
"step": 375
},
{
"epoch": 8.64,
"learning_rate": 0.0014666673232256737,
"loss": 1.7461,
"step": 380
},
{
"epoch": 8.75,
"learning_rate": 0.0014539904997395467,
"loss": 1.6746,
"step": 385
},
{
"epoch": 8.86,
"learning_rate": 0.0014412211012432212,
"loss": 1.7711,
"step": 390
},
{
"epoch": 8.98,
"learning_rate": 0.0014283617315955814,
"loss": 1.8387,
"step": 395
},
{
"epoch": 9.09,
"learning_rate": 0.0014154150130018866,
"loss": 1.475,
"step": 400
},
{
"epoch": 9.2,
"learning_rate": 0.001402383585479068,
"loss": 1.4523,
"step": 405
},
{
"epoch": 9.32,
"learning_rate": 0.0013892701063173917,
"loss": 1.4812,
"step": 410
},
{
"epoch": 9.43,
"learning_rate": 0.0013760772495385997,
"loss": 1.525,
"step": 415
},
{
"epoch": 9.55,
"learning_rate": 0.001362807705350641,
"loss": 1.398,
"step": 420
},
{
"epoch": 9.66,
"learning_rate": 0.0013494641795990985,
"loss": 1.4477,
"step": 425
},
{
"epoch": 9.77,
"learning_rate": 0.00133604939321543,
"loss": 1.5801,
"step": 430
},
{
"epoch": 9.89,
"learning_rate": 0.0013225660816621341,
"loss": 1.6422,
"step": 435
},
{
"epoch": 10.0,
"learning_rate": 0.0013090169943749475,
"loss": 1.5535,
"step": 440
},
{
"epoch": 10.11,
"learning_rate": 0.0012954048942022001,
"loss": 1.2324,
"step": 445
},
{
"epoch": 10.23,
"learning_rate": 0.0012817325568414298,
"loss": 1.2613,
"step": 450
},
{
"epoch": 10.34,
"learning_rate": 0.001268002770273379,
"loss": 1.3293,
"step": 455
},
{
"epoch": 10.45,
"learning_rate": 0.0012542183341934872,
"loss": 1.2852,
"step": 460
},
{
"epoch": 10.57,
"learning_rate": 0.0012403820594409924,
"loss": 1.3295,
"step": 465
},
{
"epoch": 10.68,
"learning_rate": 0.0012264967674257645,
"loss": 1.3287,
"step": 470
},
{
"epoch": 10.8,
"learning_rate": 0.0012125652895529767,
"loss": 1.3566,
"step": 475
},
{
"epoch": 10.91,
"learning_rate": 0.0011985904666457455,
"loss": 1.4414,
"step": 480
},
{
"epoch": 11.02,
"learning_rate": 0.0011845751483658454,
"loss": 1.3695,
"step": 485
},
{
"epoch": 11.14,
"learning_rate": 0.0011705221926326238,
"loss": 1.1363,
"step": 490
},
{
"epoch": 11.25,
"learning_rate": 0.001156434465040231,
"loss": 1.1354,
"step": 495
},
{
"epoch": 11.36,
"learning_rate": 0.0011423148382732854,
"loss": 1.0725,
"step": 500
},
{
"epoch": 11.48,
"learning_rate": 0.001128166191521093,
"loss": 1.1754,
"step": 505
},
{
"epoch": 11.59,
"learning_rate": 0.0011139914098905405,
"loss": 1.1848,
"step": 510
},
{
"epoch": 11.7,
"learning_rate": 0.0010997933838177826,
"loss": 1.2354,
"step": 515
},
{
"epoch": 11.82,
"learning_rate": 0.0010855750084788399,
"loss": 1.1984,
"step": 520
},
{
"epoch": 11.93,
"learning_rate": 0.0010713391831992322,
"loss": 1.2666,
"step": 525
},
{
"epoch": 12.05,
"learning_rate": 0.001057088810862768,
"loss": 1.1408,
"step": 530
},
{
"epoch": 12.16,
"learning_rate": 0.0010428267973196027,
"loss": 0.9385,
"step": 535
},
{
"epoch": 12.27,
"learning_rate": 0.0010285560507936962,
"loss": 1.0158,
"step": 540
},
{
"epoch": 12.39,
"learning_rate": 0.0010142794812897874,
"loss": 0.9936,
"step": 545
},
{
"epoch": 12.5,
"learning_rate": 0.001,
"loss": 0.9891,
"step": 550
},
{
"epoch": 12.61,
"learning_rate": 0.000985720518710213,
"loss": 1.0684,
"step": 555
},
{
"epoch": 12.73,
"learning_rate": 0.0009714439492063038,
"loss": 1.076,
"step": 560
},
{
"epoch": 12.84,
"learning_rate": 0.0009571732026803976,
"loss": 1.0609,
"step": 565
},
{
"epoch": 12.95,
"learning_rate": 0.000942911189137232,
"loss": 1.1297,
"step": 570
},
{
"epoch": 13.07,
"learning_rate": 0.0009286608168007677,
"loss": 0.9342,
"step": 575
},
{
"epoch": 13.18,
"learning_rate": 0.0009144249915211606,
"loss": 0.8511,
"step": 580
},
{
"epoch": 13.3,
"learning_rate": 0.0009002066161822172,
"loss": 0.8336,
"step": 585
},
{
"epoch": 13.41,
"learning_rate": 0.0008860085901094594,
"loss": 0.8652,
"step": 590
},
{
"epoch": 13.52,
"learning_rate": 0.0008718338084789072,
"loss": 0.9744,
"step": 595
},
{
"epoch": 13.64,
"learning_rate": 0.000857685161726715,
"loss": 0.9006,
"step": 600
},
{
"epoch": 13.75,
"learning_rate": 0.000843565534959769,
"loss": 0.9619,
"step": 605
},
{
"epoch": 13.86,
"learning_rate": 0.0008294778073673762,
"loss": 0.9123,
"step": 610
},
{
"epoch": 13.98,
"learning_rate": 0.0008154248516341547,
"loss": 0.9959,
"step": 615
},
{
"epoch": 14.09,
"learning_rate": 0.0008014095333542549,
"loss": 0.7503,
"step": 620
},
{
"epoch": 14.2,
"learning_rate": 0.0007874347104470233,
"loss": 0.7357,
"step": 625
},
{
"epoch": 14.32,
"learning_rate": 0.0007735032325742355,
"loss": 0.7477,
"step": 630
},
{
"epoch": 14.43,
"learning_rate": 0.0007596179405590076,
"loss": 0.8088,
"step": 635
},
{
"epoch": 14.55,
"learning_rate": 0.0007457816658065133,
"loss": 0.7652,
"step": 640
},
{
"epoch": 14.66,
"learning_rate": 0.0007319972297266214,
"loss": 0.7847,
"step": 645
},
{
"epoch": 14.77,
"learning_rate": 0.0007182674431585703,
"loss": 0.7984,
"step": 650
},
{
"epoch": 14.89,
"learning_rate": 0.0007045951057978,
"loss": 0.8732,
"step": 655
},
{
"epoch": 15.0,
"learning_rate": 0.0006909830056250527,
"loss": 0.8258,
"step": 660
},
{
"epoch": 15.11,
"learning_rate": 0.0006774339183378663,
"loss": 0.6311,
"step": 665
},
{
"epoch": 15.23,
"learning_rate": 0.0006639506067845697,
"loss": 0.6543,
"step": 670
},
{
"epoch": 15.34,
"learning_rate": 0.0006505358204009018,
"loss": 0.6421,
"step": 675
},
{
"epoch": 15.45,
"learning_rate": 0.0006371922946493591,
"loss": 0.6937,
"step": 680
},
{
"epoch": 15.57,
"learning_rate": 0.0006239227504614003,
"loss": 0.6887,
"step": 685
},
{
"epoch": 15.68,
"learning_rate": 0.0006107298936826086,
"loss": 0.7097,
"step": 690
},
{
"epoch": 15.8,
"learning_rate": 0.0005976164145209322,
"loss": 0.6778,
"step": 695
},
{
"epoch": 15.91,
"learning_rate": 0.0005845849869981136,
"loss": 0.7124,
"step": 700
},
{
"epoch": 16.02,
"learning_rate": 0.000571638268404419,
"loss": 0.7053,
"step": 705
},
{
"epoch": 16.14,
"learning_rate": 0.0005587788987567784,
"loss": 0.5863,
"step": 710
},
{
"epoch": 16.25,
"learning_rate": 0.0005460095002604533,
"loss": 0.5588,
"step": 715
},
{
"epoch": 16.36,
"learning_rate": 0.0005333326767743263,
"loss": 0.5363,
"step": 720
},
{
"epoch": 16.48,
"learning_rate": 0.0005207510132799435,
"loss": 0.6137,
"step": 725
},
{
"epoch": 16.59,
"learning_rate": 0.0005082670753543961,
"loss": 0.5606,
"step": 730
},
{
"epoch": 16.7,
"learning_rate": 0.0004958834086471683,
"loss": 0.629,
"step": 735
},
{
"epoch": 16.82,
"learning_rate": 0.00048360253836103817,
"loss": 0.5754,
"step": 740
},
{
"epoch": 16.93,
"learning_rate": 0.0004714269687371581,
"loss": 0.6239,
"step": 745
},
{
"epoch": 17.05,
"learning_rate": 0.0004593591825444028,
"loss": 0.5807,
"step": 750
},
{
"epoch": 17.16,
"learning_rate": 0.0004474016405730973,
"loss": 0.465,
"step": 755
},
{
"epoch": 17.27,
"learning_rate": 0.00043555678113323104,
"loss": 0.4871,
"step": 760
},
{
"epoch": 17.39,
"learning_rate": 0.00042382701955724725,
"loss": 0.4623,
"step": 765
},
{
"epoch": 17.5,
"learning_rate": 0.00041221474770752696,
"loss": 0.5059,
"step": 770
},
{
"epoch": 17.61,
"learning_rate": 0.00040072233348865304,
"loss": 0.5021,
"step": 775
},
{
"epoch": 17.73,
"learning_rate": 0.0003893521203645618,
"loss": 0.5138,
"step": 780
},
{
"epoch": 17.84,
"learning_rate": 0.00037810642688067796,
"loss": 0.5212,
"step": 785
},
{
"epoch": 17.95,
"learning_rate": 0.00036698754619112975,
"loss": 0.5611,
"step": 790
},
{
"epoch": 18.07,
"learning_rate": 0.00035599774559114475,
"loss": 0.4956,
"step": 795
},
{
"epoch": 18.18,
"learning_rate": 0.000345139266054715,
"loss": 0.4243,
"step": 800
},
{
"epoch": 18.3,
"learning_rate": 0.0003344143217776319,
"loss": 0.4391,
"step": 805
},
{
"epoch": 18.41,
"learning_rate": 0.00032382509972598086,
"loss": 0.4627,
"step": 810
},
{
"epoch": 18.52,
"learning_rate": 0.0003133737591901864,
"loss": 0.4208,
"step": 815
},
{
"epoch": 18.64,
"learning_rate": 0.0003030624313447067,
"loss": 0.45,
"step": 820
},
{
"epoch": 18.75,
"learning_rate": 0.00029289321881345256,
"loss": 0.44,
"step": 825
},
{
"epoch": 18.86,
"learning_rate": 0.0002828681952410366,
"loss": 0.4451,
"step": 830
},
{
"epoch": 18.98,
"learning_rate": 0.0002729894048699265,
"loss": 0.4494,
"step": 835
},
{
"epoch": 19.09,
"learning_rate": 0.00026325886212359495,
"loss": 0.3839,
"step": 840
},
{
"epoch": 19.2,
"learning_rate": 0.0002536785511957531,
"loss": 0.3728,
"step": 845
},
{
"epoch": 19.32,
"learning_rate": 0.00024425042564574185,
"loss": 0.4126,
"step": 850
},
{
"epoch": 19.43,
"learning_rate": 0.00023497640800017682,
"loss": 0.4183,
"step": 855
},
{
"epoch": 19.55,
"learning_rate": 0.0002258583893609175,
"loss": 0.3778,
"step": 860
},
{
"epoch": 19.66,
"learning_rate": 0.00021689822901944456,
"loss": 0.3758,
"step": 865
},
{
"epoch": 19.77,
"learning_rate": 0.000208097754077725,
"loss": 0.4034,
"step": 870
},
{
"epoch": 19.89,
"learning_rate": 0.0001994587590756397,
"loss": 0.4085,
"step": 875
},
{
"epoch": 20.0,
"learning_rate": 0.00019098300562505265,
"loss": 0.3673,
"step": 880
},
{
"epoch": 20.11,
"learning_rate": 0.0001826722220505931,
"loss": 0.363,
"step": 885
},
{
"epoch": 20.23,
"learning_rate": 0.000174528103037226,
"loss": 0.3707,
"step": 890
},
{
"epoch": 20.34,
"learning_rate": 0.00016655230928468257,
"loss": 0.369,
"step": 895
},
{
"epoch": 20.45,
"learning_rate": 0.00015874646716881869,
"loss": 0.3528,
"step": 900
},
{
"epoch": 20.57,
"learning_rate": 0.00015111216840997744,
"loss": 0.3581,
"step": 905
},
{
"epoch": 20.68,
"learning_rate": 0.00014365096974841107,
"loss": 0.3466,
"step": 910
},
{
"epoch": 20.8,
"learning_rate": 0.00013636439262684297,
"loss": 0.3274,
"step": 915
},
{
"epoch": 20.91,
"learning_rate": 0.00012925392288022297,
"loss": 0.3401,
"step": 920
},
{
"epoch": 21.02,
"learning_rate": 0.00012232101043274435,
"loss": 0.3435,
"step": 925
},
{
"epoch": 21.14,
"learning_rate": 0.00011556706900218572,
"loss": 0.2972,
"step": 930
},
{
"epoch": 21.25,
"learning_rate": 0.00010899347581163222,
"loss": 0.3153,
"step": 935
},
{
"epoch": 21.36,
"learning_rate": 0.00010260157130864178,
"loss": 0.3315,
"step": 940
},
{
"epoch": 21.48,
"learning_rate": 9.639265889190829e-05,
"loss": 0.3264,
"step": 945
},
{
"epoch": 21.59,
"learning_rate": 9.036800464548156e-05,
"loss": 0.3427,
"step": 950
},
{
"epoch": 21.7,
"learning_rate": 8.4528837080594e-05,
"loss": 0.3415,
"step": 955
},
{
"epoch": 21.82,
"learning_rate": 7.887634688515e-05,
"loss": 0.323,
"step": 960
},
{
"epoch": 21.93,
"learning_rate": 7.341168668092857e-05,
"loss": 0.2961,
"step": 965
},
{
"epoch": 22.05,
"learning_rate": 6.813597078854772e-05,
"loss": 0.3276,
"step": 970
},
{
"epoch": 22.16,
"learning_rate": 6.305027500023842e-05,
"loss": 0.3045,
"step": 975
},
{
"epoch": 22.27,
"learning_rate": 5.8155636360475384e-05,
"loss": 0.3167,
"step": 980
},
{
"epoch": 22.39,
"learning_rate": 5.345305295450997e-05,
"loss": 0.319,
"step": 985
},
{
"epoch": 22.5,
"learning_rate": 4.894348370484647e-05,
"loss": 0.2852,
"step": 990
},
{
"epoch": 22.61,
"learning_rate": 4.4627848175703315e-05,
"loss": 0.3034,
"step": 995
},
{
"epoch": 22.73,
"learning_rate": 4.050702638550274e-05,
"loss": 0.2845,
"step": 1000
},
{
"epoch": 22.84,
"learning_rate": 3.658185862742103e-05,
"loss": 0.3136,
"step": 1005
},
{
"epoch": 22.95,
"learning_rate": 3.285314529804295e-05,
"loss": 0.3187,
"step": 1010
},
{
"epoch": 23.07,
"learning_rate": 2.93216467341475e-05,
"loss": 0.2907,
"step": 1015
},
{
"epoch": 23.18,
"learning_rate": 2.5988083057666535e-05,
"loss": 0.2955,
"step": 1020
},
{
"epoch": 23.3,
"learning_rate": 2.2853134028840594e-05,
"loss": 0.2785,
"step": 1025
},
{
"epoch": 23.41,
"learning_rate": 1.9917438907606554e-05,
"loss": 0.3369,
"step": 1030
},
{
"epoch": 23.52,
"learning_rate": 1.7181596323244453e-05,
"loss": 0.2837,
"step": 1035
},
{
"epoch": 23.64,
"learning_rate": 1.4646164152307017e-05,
"loss": 0.3002,
"step": 1040
},
{
"epoch": 23.75,
"learning_rate": 1.231165940486234e-05,
"loss": 0.3062,
"step": 1045
},
{
"epoch": 23.86,
"learning_rate": 1.0178558119067316e-05,
"loss": 0.2859,
"step": 1050
},
{
"epoch": 23.98,
"learning_rate": 8.247295264097288e-06,
"loss": 0.284,
"step": 1055
},
{
"epoch": 24.09,
"learning_rate": 6.518264651449779e-06,
"loss": 0.2607,
"step": 1060
},
{
"epoch": 24.2,
"learning_rate": 4.991818854640395e-06,
"loss": 0.3164,
"step": 1065
},
{
"epoch": 24.32,
"learning_rate": 3.6682691373086663e-06,
"loss": 0.2597,
"step": 1070
},
{
"epoch": 24.43,
"learning_rate": 2.5478853897464847e-06,
"loss": 0.2907,
"step": 1075
},
{
"epoch": 24.55,
"learning_rate": 1.630896073864352e-06,
"loss": 0.3033,
"step": 1080
},
{
"epoch": 24.66,
"learning_rate": 9.174881766043087e-07,
"loss": 0.3089,
"step": 1085
},
{
"epoch": 24.77,
"learning_rate": 4.078071718107701e-07,
"loss": 0.2964,
"step": 1090
},
{
"epoch": 24.89,
"learning_rate": 1.0195699056669839e-07,
"loss": 0.2995,
"step": 1095
},
{
"epoch": 25.0,
"learning_rate": 0.0,
"loss": 0.2936,
"step": 1100
},
{
"epoch": 25.0,
"step": 1100,
"total_flos": 5.602696856046797e+17,
"train_loss": 1.3768115234375,
"train_runtime": 24197.7873,
"train_samples_per_second": 0.724,
"train_steps_per_second": 0.045
}
],
"logging_steps": 5,
"max_steps": 1100,
"num_input_tokens_seen": 0,
"num_train_epochs": 25,
"save_steps": 100,
"total_flos": 5.602696856046797e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}