zephyr-7b-sft-full / trainer_state.json
lewtun's picture
lewtun HF staff
Model save
8104d49
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 1090,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 1.8348623853211012e-07,
"loss": 1.6972,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 9.174311926605506e-07,
"loss": 1.6464,
"step": 5
},
{
"epoch": 0.01,
"learning_rate": 1.8348623853211011e-06,
"loss": 1.3919,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 2.7522935779816517e-06,
"loss": 1.2141,
"step": 15
},
{
"epoch": 0.02,
"learning_rate": 3.6697247706422022e-06,
"loss": 1.17,
"step": 20
},
{
"epoch": 0.02,
"learning_rate": 4.587155963302753e-06,
"loss": 1.1172,
"step": 25
},
{
"epoch": 0.03,
"learning_rate": 5.504587155963303e-06,
"loss": 1.0704,
"step": 30
},
{
"epoch": 0.03,
"learning_rate": 6.422018348623854e-06,
"loss": 1.0576,
"step": 35
},
{
"epoch": 0.04,
"learning_rate": 7.3394495412844045e-06,
"loss": 1.052,
"step": 40
},
{
"epoch": 0.04,
"learning_rate": 8.256880733944956e-06,
"loss": 1.0469,
"step": 45
},
{
"epoch": 0.05,
"learning_rate": 9.174311926605506e-06,
"loss": 1.0308,
"step": 50
},
{
"epoch": 0.05,
"learning_rate": 1.0091743119266055e-05,
"loss": 1.0091,
"step": 55
},
{
"epoch": 0.06,
"learning_rate": 1.1009174311926607e-05,
"loss": 1.0356,
"step": 60
},
{
"epoch": 0.06,
"learning_rate": 1.1926605504587156e-05,
"loss": 1.0079,
"step": 65
},
{
"epoch": 0.06,
"learning_rate": 1.2844036697247708e-05,
"loss": 1.0001,
"step": 70
},
{
"epoch": 0.07,
"learning_rate": 1.3761467889908258e-05,
"loss": 1.0001,
"step": 75
},
{
"epoch": 0.07,
"learning_rate": 1.4678899082568809e-05,
"loss": 0.9918,
"step": 80
},
{
"epoch": 0.08,
"learning_rate": 1.559633027522936e-05,
"loss": 1.0148,
"step": 85
},
{
"epoch": 0.08,
"learning_rate": 1.6513761467889912e-05,
"loss": 0.9973,
"step": 90
},
{
"epoch": 0.09,
"learning_rate": 1.743119266055046e-05,
"loss": 1.0154,
"step": 95
},
{
"epoch": 0.09,
"learning_rate": 1.834862385321101e-05,
"loss": 1.0163,
"step": 100
},
{
"epoch": 0.1,
"learning_rate": 1.9266055045871563e-05,
"loss": 0.9872,
"step": 105
},
{
"epoch": 0.1,
"learning_rate": 1.999994872196626e-05,
"loss": 1.0056,
"step": 110
},
{
"epoch": 0.11,
"learning_rate": 1.9998154046002822e-05,
"loss": 1.0141,
"step": 115
},
{
"epoch": 0.11,
"learning_rate": 1.999379599421534e-05,
"loss": 1.0058,
"step": 120
},
{
"epoch": 0.11,
"learning_rate": 1.9986875683942535e-05,
"loss": 1.02,
"step": 125
},
{
"epoch": 0.12,
"learning_rate": 1.9977394889447526e-05,
"loss": 1.0237,
"step": 130
},
{
"epoch": 0.12,
"learning_rate": 1.9965356041462954e-05,
"loss": 1.0304,
"step": 135
},
{
"epoch": 0.13,
"learning_rate": 1.9950762226567783e-05,
"loss": 1.0284,
"step": 140
},
{
"epoch": 0.13,
"learning_rate": 1.9933617186395917e-05,
"loss": 1.0046,
"step": 145
},
{
"epoch": 0.14,
"learning_rate": 1.9913925316676946e-05,
"loss": 1.0026,
"step": 150
},
{
"epoch": 0.14,
"learning_rate": 1.9891691666109112e-05,
"loss": 1.0226,
"step": 155
},
{
"epoch": 0.15,
"learning_rate": 1.9866921935064907e-05,
"loss": 1.0136,
"step": 160
},
{
"epoch": 0.15,
"learning_rate": 1.9839622474129595e-05,
"loss": 1.016,
"step": 165
},
{
"epoch": 0.16,
"learning_rate": 1.9809800282473014e-05,
"loss": 0.9979,
"step": 170
},
{
"epoch": 0.16,
"learning_rate": 1.977746300605507e-05,
"loss": 1.0219,
"step": 175
},
{
"epoch": 0.17,
"learning_rate": 1.9742618935665478e-05,
"loss": 1.0086,
"step": 180
},
{
"epoch": 0.17,
"learning_rate": 1.9705277004798072e-05,
"loss": 0.9983,
"step": 185
},
{
"epoch": 0.17,
"learning_rate": 1.9665446787360444e-05,
"loss": 1.0106,
"step": 190
},
{
"epoch": 0.18,
"learning_rate": 1.9623138495219292e-05,
"loss": 1.0084,
"step": 195
},
{
"epoch": 0.18,
"learning_rate": 1.957836297558229e-05,
"loss": 1.0272,
"step": 200
},
{
"epoch": 0.19,
"learning_rate": 1.9531131708217005e-05,
"loss": 0.989,
"step": 205
},
{
"epoch": 0.19,
"learning_rate": 1.948145680250766e-05,
"loss": 1.0114,
"step": 210
},
{
"epoch": 0.2,
"learning_rate": 1.9429350994350483e-05,
"loss": 0.993,
"step": 215
},
{
"epoch": 0.2,
"learning_rate": 1.93748276428884e-05,
"loss": 1.0229,
"step": 220
},
{
"epoch": 0.21,
"learning_rate": 1.931790072708596e-05,
"loss": 1.0191,
"step": 225
},
{
"epoch": 0.21,
"learning_rate": 1.9258584842145342e-05,
"loss": 1.0016,
"step": 230
},
{
"epoch": 0.22,
"learning_rate": 1.9196895195764363e-05,
"loss": 0.9955,
"step": 235
},
{
"epoch": 0.22,
"learning_rate": 1.913284760423745e-05,
"loss": 1.0212,
"step": 240
},
{
"epoch": 0.22,
"learning_rate": 1.9066458488400586e-05,
"loss": 1.0258,
"step": 245
},
{
"epoch": 0.23,
"learning_rate": 1.8997744869421248e-05,
"loss": 1.0036,
"step": 250
},
{
"epoch": 0.23,
"learning_rate": 1.8926724364434447e-05,
"loss": 0.9951,
"step": 255
},
{
"epoch": 0.24,
"learning_rate": 1.8853415182025953e-05,
"loss": 1.0088,
"step": 260
},
{
"epoch": 0.24,
"learning_rate": 1.8777836117563894e-05,
"loss": 1.0197,
"step": 265
},
{
"epoch": 0.25,
"learning_rate": 1.8700006548379898e-05,
"loss": 0.9919,
"step": 270
},
{
"epoch": 0.25,
"learning_rate": 1.861994642880105e-05,
"loss": 1.0036,
"step": 275
},
{
"epoch": 0.26,
"learning_rate": 1.8537676285033886e-05,
"loss": 1.0064,
"step": 280
},
{
"epoch": 0.26,
"learning_rate": 1.845321720990181e-05,
"loss": 1.0098,
"step": 285
},
{
"epoch": 0.27,
"learning_rate": 1.8366590857437182e-05,
"loss": 1.0154,
"step": 290
},
{
"epoch": 0.27,
"learning_rate": 1.8277819437329577e-05,
"loss": 0.993,
"step": 295
},
{
"epoch": 0.28,
"learning_rate": 1.8186925709231534e-05,
"loss": 0.9877,
"step": 300
},
{
"epoch": 0.28,
"learning_rate": 1.809393297692334e-05,
"loss": 0.9892,
"step": 305
},
{
"epoch": 0.28,
"learning_rate": 1.799886508233829e-05,
"loss": 0.9869,
"step": 310
},
{
"epoch": 0.29,
"learning_rate": 1.790174639944997e-05,
"loss": 0.9894,
"step": 315
},
{
"epoch": 0.29,
"learning_rate": 1.780260182802314e-05,
"loss": 0.9984,
"step": 320
},
{
"epoch": 0.3,
"learning_rate": 1.7701456787229805e-05,
"loss": 0.9878,
"step": 325
},
{
"epoch": 0.3,
"learning_rate": 1.7598337209132142e-05,
"loss": 1.0103,
"step": 330
},
{
"epoch": 0.31,
"learning_rate": 1.7493269532033882e-05,
"loss": 0.994,
"step": 335
},
{
"epoch": 0.31,
"learning_rate": 1.738628069370195e-05,
"loss": 0.9978,
"step": 340
},
{
"epoch": 0.32,
"learning_rate": 1.7277398124460022e-05,
"loss": 1.0071,
"step": 345
},
{
"epoch": 0.32,
"learning_rate": 1.71666497401558e-05,
"loss": 0.9925,
"step": 350
},
{
"epoch": 0.33,
"learning_rate": 1.7054063935003813e-05,
"loss": 0.9971,
"step": 355
},
{
"epoch": 0.33,
"learning_rate": 1.6939669574305565e-05,
"loss": 1.0069,
"step": 360
},
{
"epoch": 0.33,
"learning_rate": 1.6823495987048922e-05,
"loss": 0.9703,
"step": 365
},
{
"epoch": 0.34,
"learning_rate": 1.6705572958388576e-05,
"loss": 0.9989,
"step": 370
},
{
"epoch": 0.34,
"learning_rate": 1.6585930722009602e-05,
"loss": 0.9951,
"step": 375
},
{
"epoch": 0.35,
"learning_rate": 1.6464599952375998e-05,
"loss": 0.9971,
"step": 380
},
{
"epoch": 0.35,
"learning_rate": 1.63416117568662e-05,
"loss": 0.9811,
"step": 385
},
{
"epoch": 0.36,
"learning_rate": 1.621699766779763e-05,
"loss": 1.009,
"step": 390
},
{
"epoch": 0.36,
"learning_rate": 1.6090789634342278e-05,
"loss": 1.0029,
"step": 395
},
{
"epoch": 0.37,
"learning_rate": 1.5963020014335437e-05,
"loss": 0.9934,
"step": 400
},
{
"epoch": 0.37,
"learning_rate": 1.583372156597961e-05,
"loss": 0.9753,
"step": 405
},
{
"epoch": 0.38,
"learning_rate": 1.570292743944583e-05,
"loss": 1.009,
"step": 410
},
{
"epoch": 0.38,
"learning_rate": 1.557067116837444e-05,
"loss": 0.968,
"step": 415
},
{
"epoch": 0.39,
"learning_rate": 1.5436986661277578e-05,
"loss": 0.9961,
"step": 420
},
{
"epoch": 0.39,
"learning_rate": 1.530190819284555e-05,
"loss": 1.0131,
"step": 425
},
{
"epoch": 0.39,
"learning_rate": 1.5165470395159314e-05,
"loss": 0.9881,
"step": 430
},
{
"epoch": 0.4,
"learning_rate": 1.5027708248811331e-05,
"loss": 0.9887,
"step": 435
},
{
"epoch": 0.4,
"learning_rate": 1.4888657073937077e-05,
"loss": 0.9793,
"step": 440
},
{
"epoch": 0.41,
"learning_rate": 1.4748352521159492e-05,
"loss": 0.9766,
"step": 445
},
{
"epoch": 0.41,
"learning_rate": 1.4606830562448692e-05,
"loss": 0.9877,
"step": 450
},
{
"epoch": 0.42,
"learning_rate": 1.4464127481899312e-05,
"loss": 0.9998,
"step": 455
},
{
"epoch": 0.42,
"learning_rate": 1.4320279866427798e-05,
"loss": 0.9789,
"step": 460
},
{
"epoch": 0.43,
"learning_rate": 1.4175324596392075e-05,
"loss": 0.9832,
"step": 465
},
{
"epoch": 0.43,
"learning_rate": 1.402929883613599e-05,
"loss": 0.9766,
"step": 470
},
{
"epoch": 0.44,
"learning_rate": 1.3882240024460928e-05,
"loss": 0.986,
"step": 475
},
{
"epoch": 0.44,
"learning_rate": 1.3734185865027061e-05,
"loss": 0.9834,
"step": 480
},
{
"epoch": 0.44,
"learning_rate": 1.358517431668672e-05,
"loss": 0.9832,
"step": 485
},
{
"epoch": 0.45,
"learning_rate": 1.3435243583752294e-05,
"loss": 0.9749,
"step": 490
},
{
"epoch": 0.45,
"learning_rate": 1.3284432106201233e-05,
"loss": 0.9799,
"step": 495
},
{
"epoch": 0.46,
"learning_rate": 1.313277854982062e-05,
"loss": 0.9585,
"step": 500
},
{
"epoch": 0.46,
"learning_rate": 1.2980321796293838e-05,
"loss": 0.9886,
"step": 505
},
{
"epoch": 0.47,
"learning_rate": 1.2827100933231904e-05,
"loss": 0.9694,
"step": 510
},
{
"epoch": 0.47,
"learning_rate": 1.2673155244151985e-05,
"loss": 0.9797,
"step": 515
},
{
"epoch": 0.48,
"learning_rate": 1.2518524198405699e-05,
"loss": 0.9662,
"step": 520
},
{
"epoch": 0.48,
"learning_rate": 1.2363247441059775e-05,
"loss": 0.9711,
"step": 525
},
{
"epoch": 0.49,
"learning_rate": 1.2207364782731657e-05,
"loss": 0.9798,
"step": 530
},
{
"epoch": 0.49,
"learning_rate": 1.2050916189382646e-05,
"loss": 0.9638,
"step": 535
},
{
"epoch": 0.5,
"learning_rate": 1.189394177207125e-05,
"loss": 0.9826,
"step": 540
},
{
"epoch": 0.5,
"learning_rate": 1.1736481776669307e-05,
"loss": 0.9816,
"step": 545
},
{
"epoch": 0.5,
"learning_rate": 1.1578576573543541e-05,
"loss": 0.9614,
"step": 550
},
{
"epoch": 0.51,
"learning_rate": 1.1420266647205232e-05,
"loss": 0.9689,
"step": 555
},
{
"epoch": 0.51,
"learning_rate": 1.1261592585930576e-05,
"loss": 0.9876,
"step": 560
},
{
"epoch": 0.52,
"learning_rate": 1.1102595071354471e-05,
"loss": 0.9447,
"step": 565
},
{
"epoch": 0.52,
"learning_rate": 1.0943314868040365e-05,
"loss": 0.9584,
"step": 570
},
{
"epoch": 0.53,
"learning_rate": 1.0783792813028828e-05,
"loss": 0.9776,
"step": 575
},
{
"epoch": 0.53,
"learning_rate": 1.0624069805367558e-05,
"loss": 0.9402,
"step": 580
},
{
"epoch": 0.54,
"learning_rate": 1.0464186795625481e-05,
"loss": 0.9637,
"step": 585
},
{
"epoch": 0.54,
"learning_rate": 1.0304184775393642e-05,
"loss": 0.9573,
"step": 590
},
{
"epoch": 0.55,
"learning_rate": 1.0144104766775574e-05,
"loss": 0.9694,
"step": 595
},
{
"epoch": 0.55,
"learning_rate": 9.983987811869863e-06,
"loss": 0.967,
"step": 600
},
{
"epoch": 0.56,
"learning_rate": 9.823874962247565e-06,
"loss": 0.9652,
"step": 605
},
{
"epoch": 0.56,
"learning_rate": 9.663807268427197e-06,
"loss": 0.951,
"step": 610
},
{
"epoch": 0.56,
"learning_rate": 9.503825769350016e-06,
"loss": 0.9735,
"step": 615
},
{
"epoch": 0.57,
"learning_rate": 9.343971481858246e-06,
"loss": 0.9491,
"step": 620
},
{
"epoch": 0.57,
"learning_rate": 9.184285390178978e-06,
"loss": 0.9637,
"step": 625
},
{
"epoch": 0.58,
"learning_rate": 9.024808435416435e-06,
"loss": 0.9434,
"step": 630
},
{
"epoch": 0.58,
"learning_rate": 8.865581505055292e-06,
"loss": 0.9501,
"step": 635
},
{
"epoch": 0.59,
"learning_rate": 8.706645422477739e-06,
"loss": 0.9619,
"step": 640
},
{
"epoch": 0.59,
"learning_rate": 8.548040936496989e-06,
"loss": 0.9455,
"step": 645
},
{
"epoch": 0.6,
"learning_rate": 8.389808710909881e-06,
"loss": 0.9741,
"step": 650
},
{
"epoch": 0.6,
"learning_rate": 8.231989314071318e-06,
"loss": 0.9608,
"step": 655
},
{
"epoch": 0.61,
"learning_rate": 8.07462320849313e-06,
"loss": 0.9602,
"step": 660
},
{
"epoch": 0.61,
"learning_rate": 7.917750740470116e-06,
"loss": 0.9696,
"step": 665
},
{
"epoch": 0.61,
"learning_rate": 7.761412129735853e-06,
"loss": 0.9628,
"step": 670
},
{
"epoch": 0.62,
"learning_rate": 7.605647459150961e-06,
"loss": 0.9485,
"step": 675
},
{
"epoch": 0.62,
"learning_rate": 7.4504966644264775e-06,
"loss": 0.9485,
"step": 680
},
{
"epoch": 0.63,
"learning_rate": 7.295999523884921e-06,
"loss": 0.9424,
"step": 685
},
{
"epoch": 0.63,
"learning_rate": 7.142195648261747e-06,
"loss": 0.9648,
"step": 690
},
{
"epoch": 0.64,
"learning_rate": 6.989124470549746e-06,
"loss": 0.9602,
"step": 695
},
{
"epoch": 0.64,
"learning_rate": 6.83682523588902e-06,
"loss": 0.944,
"step": 700
},
{
"epoch": 0.65,
"learning_rate": 6.685336991505122e-06,
"loss": 0.9575,
"step": 705
},
{
"epoch": 0.65,
"learning_rate": 6.5346985766979384e-06,
"loss": 0.9498,
"step": 710
},
{
"epoch": 0.66,
"learning_rate": 6.384948612883872e-06,
"loss": 0.9475,
"step": 715
},
{
"epoch": 0.66,
"learning_rate": 6.2361254936939e-06,
"loss": 0.9385,
"step": 720
},
{
"epoch": 0.67,
"learning_rate": 6.0882673751300235e-06,
"loss": 0.9501,
"step": 725
},
{
"epoch": 0.67,
"learning_rate": 5.941412165782645e-06,
"loss": 0.9485,
"step": 730
},
{
"epoch": 0.67,
"learning_rate": 5.79559751711138e-06,
"loss": 0.9352,
"step": 735
},
{
"epoch": 0.68,
"learning_rate": 5.650860813791786e-06,
"loss": 0.9446,
"step": 740
},
{
"epoch": 0.68,
"learning_rate": 5.507239164130501e-06,
"loss": 0.9523,
"step": 745
},
{
"epoch": 0.69,
"learning_rate": 5.364769390551225e-06,
"loss": 0.9508,
"step": 750
},
{
"epoch": 0.69,
"learning_rate": 5.223488020154028e-06,
"loss": 0.946,
"step": 755
},
{
"epoch": 0.7,
"learning_rate": 5.083431275350312e-06,
"loss": 0.9396,
"step": 760
},
{
"epoch": 0.7,
"learning_rate": 4.9446350645759885e-06,
"loss": 0.9467,
"step": 765
},
{
"epoch": 0.71,
"learning_rate": 4.807134973085036e-06,
"loss": 0.9438,
"step": 770
},
{
"epoch": 0.71,
"learning_rate": 4.670966253826027e-06,
"loss": 0.9502,
"step": 775
},
{
"epoch": 0.72,
"learning_rate": 4.53616381840377e-06,
"loss": 0.9336,
"step": 780
},
{
"epoch": 0.72,
"learning_rate": 4.402762228128531e-06,
"loss": 0.9408,
"step": 785
},
{
"epoch": 0.72,
"learning_rate": 4.270795685155001e-06,
"loss": 0.9482,
"step": 790
},
{
"epoch": 0.73,
"learning_rate": 4.140298023713416e-06,
"loss": 0.9288,
"step": 795
},
{
"epoch": 0.73,
"learning_rate": 4.0113027014349374e-06,
"loss": 0.9438,
"step": 800
},
{
"epoch": 0.74,
"learning_rate": 3.883842790773647e-06,
"loss": 0.9325,
"step": 805
},
{
"epoch": 0.74,
"learning_rate": 3.757950970527249e-06,
"loss": 0.9366,
"step": 810
},
{
"epoch": 0.75,
"learning_rate": 3.633659517458736e-06,
"loss": 0.931,
"step": 815
},
{
"epoch": 0.75,
"learning_rate": 3.511000298021098e-06,
"loss": 0.9497,
"step": 820
},
{
"epoch": 0.76,
"learning_rate": 3.39000476018726e-06,
"loss": 0.9438,
"step": 825
},
{
"epoch": 0.76,
"learning_rate": 3.2707039253872796e-06,
"loss": 0.9353,
"step": 830
},
{
"epoch": 0.77,
"learning_rate": 3.153128380554941e-06,
"loss": 0.9419,
"step": 835
},
{
"epoch": 0.77,
"learning_rate": 3.037308270285709e-06,
"loss": 0.9201,
"step": 840
},
{
"epoch": 0.78,
"learning_rate": 2.923273289108115e-06,
"loss": 0.9461,
"step": 845
},
{
"epoch": 0.78,
"learning_rate": 2.8110526738705345e-06,
"loss": 0.937,
"step": 850
},
{
"epoch": 0.78,
"learning_rate": 2.700675196245288e-06,
"loss": 0.9465,
"step": 855
},
{
"epoch": 0.79,
"learning_rate": 2.592169155352031e-06,
"loss": 0.9157,
"step": 860
},
{
"epoch": 0.79,
"learning_rate": 2.485562370502279e-06,
"loss": 0.9282,
"step": 865
},
{
"epoch": 0.8,
"learning_rate": 2.3808821740669608e-06,
"loss": 0.9293,
"step": 870
},
{
"epoch": 0.8,
"learning_rate": 2.2781554044688015e-06,
"loss": 0.9402,
"step": 875
},
{
"epoch": 0.81,
"learning_rate": 2.1774083993013715e-06,
"loss": 0.9362,
"step": 880
},
{
"epoch": 0.81,
"learning_rate": 2.0786669885765044e-06,
"loss": 0.9342,
"step": 885
},
{
"epoch": 0.82,
"learning_rate": 1.981956488101898e-06,
"loss": 0.9245,
"step": 890
},
{
"epoch": 0.82,
"learning_rate": 1.8873016929904942e-06,
"loss": 0.9338,
"step": 895
},
{
"epoch": 0.83,
"learning_rate": 1.7947268713034128e-06,
"loss": 0.9483,
"step": 900
},
{
"epoch": 0.83,
"learning_rate": 1.704255757827963e-06,
"loss": 0.9351,
"step": 905
},
{
"epoch": 0.83,
"learning_rate": 1.6159115479924259e-06,
"loss": 0.9239,
"step": 910
},
{
"epoch": 0.84,
"learning_rate": 1.529716891919074e-06,
"loss": 0.9212,
"step": 915
},
{
"epoch": 0.84,
"learning_rate": 1.4456938886170413e-06,
"loss": 0.9379,
"step": 920
},
{
"epoch": 0.85,
"learning_rate": 1.3638640803164516e-06,
"loss": 0.9246,
"step": 925
},
{
"epoch": 0.85,
"learning_rate": 1.2842484469453365e-06,
"loss": 0.9156,
"step": 930
},
{
"epoch": 0.86,
"learning_rate": 1.2068674007506787e-06,
"loss": 0.9285,
"step": 935
},
{
"epoch": 0.86,
"learning_rate": 1.1317407810650372e-06,
"loss": 0.9214,
"step": 940
},
{
"epoch": 0.87,
"learning_rate": 1.0588878492200261e-06,
"loss": 0.9344,
"step": 945
},
{
"epoch": 0.87,
"learning_rate": 9.883272836080116e-07,
"loss": 0.9293,
"step": 950
},
{
"epoch": 0.88,
"learning_rate": 9.200771748932513e-07,
"loss": 0.9416,
"step": 955
},
{
"epoch": 0.88,
"learning_rate": 8.541550213737171e-07,
"loss": 0.9241,
"step": 960
},
{
"epoch": 0.89,
"learning_rate": 7.905777244947954e-07,
"loss": 0.9194,
"step": 965
},
{
"epoch": 0.89,
"learning_rate": 7.293615845160196e-07,
"loss": 0.9124,
"step": 970
},
{
"epoch": 0.89,
"learning_rate": 6.705222963319191e-07,
"loss": 0.9281,
"step": 975
},
{
"epoch": 0.9,
"learning_rate": 6.140749454480932e-07,
"loss": 0.9382,
"step": 980
},
{
"epoch": 0.9,
"learning_rate": 5.600340041135133e-07,
"loss": 0.9257,
"step": 985
},
{
"epoch": 0.91,
"learning_rate": 5.0841332761005e-07,
"loss": 0.9277,
"step": 990
},
{
"epoch": 0.91,
"learning_rate": 4.592261507001994e-07,
"loss": 0.9249,
"step": 995
},
{
"epoch": 0.92,
"learning_rate": 4.124850842338779e-07,
"loss": 0.9249,
"step": 1000
},
{
"epoch": 0.92,
"learning_rate": 3.6820211191520127e-07,
"loss": 0.9233,
"step": 1005
},
{
"epoch": 0.93,
"learning_rate": 3.263885872300343e-07,
"loss": 0.9086,
"step": 1010
},
{
"epoch": 0.93,
"learning_rate": 2.870552305351382e-07,
"loss": 0.929,
"step": 1015
},
{
"epoch": 0.94,
"learning_rate": 2.5021212630962246e-07,
"loss": 0.9328,
"step": 1020
},
{
"epoch": 0.94,
"learning_rate": 2.158687205694443e-07,
"loss": 0.9213,
"step": 1025
},
{
"epoch": 0.94,
"learning_rate": 1.840338184455881e-07,
"loss": 0.9144,
"step": 1030
},
{
"epoch": 0.95,
"learning_rate": 1.5471558192656776e-07,
"loss": 0.923,
"step": 1035
},
{
"epoch": 0.95,
"learning_rate": 1.279215277658097e-07,
"loss": 0.9124,
"step": 1040
},
{
"epoch": 0.96,
"learning_rate": 1.0365852555447642e-07,
"loss": 0.9406,
"step": 1045
},
{
"epoch": 0.96,
"learning_rate": 8.19327959602012e-08,
"loss": 0.9343,
"step": 1050
},
{
"epoch": 0.97,
"learning_rate": 6.274990913221035e-08,
"loss": 0.92,
"step": 1055
},
{
"epoch": 0.97,
"learning_rate": 4.6114783273213395e-08,
"loss": 0.9212,
"step": 1060
},
{
"epoch": 0.98,
"learning_rate": 3.203168337845508e-08,
"loss": 0.9127,
"step": 1065
},
{
"epoch": 0.98,
"learning_rate": 2.05042201422323e-08,
"loss": 0.9267,
"step": 1070
},
{
"epoch": 0.99,
"learning_rate": 1.1535349032167908e-08,
"loss": 0.9248,
"step": 1075
},
{
"epoch": 0.99,
"learning_rate": 5.127369531473525e-09,
"loss": 0.9453,
"step": 1080
},
{
"epoch": 1.0,
"learning_rate": 1.2819245493955746e-09,
"loss": 0.9159,
"step": 1085
},
{
"epoch": 1.0,
"learning_rate": 0.0,
"loss": 0.9075,
"step": 1090
},
{
"epoch": 1.0,
"eval_loss": 0.9353461265563965,
"eval_runtime": 142.6393,
"eval_samples_per_second": 108.182,
"eval_steps_per_second": 1.697,
"step": 1090
},
{
"epoch": 1.0,
"step": 1090,
"total_flos": 456447649382400.0,
"train_loss": 0.9776473476252424,
"train_runtime": 5608.2856,
"train_samples_per_second": 24.861,
"train_steps_per_second": 0.194
}
],
"logging_steps": 5,
"max_steps": 1090,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 100,
"total_flos": 456447649382400.0,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}