2396 lines
47 KiB
JSON
2396 lines
47 KiB
JSON
{
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.9998720081914757,
|
|
"global_step": 3906,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"epoch": 0.0,
|
|
"learning_rate": 0.0,
|
|
"loss": 9.2076,
|
|
"step": 1
|
|
},
|
|
{
|
|
"epoch": 0.0,
|
|
"learning_rate": 2e-05,
|
|
"loss": 9.3403,
|
|
"step": 10
|
|
},
|
|
{
|
|
"epoch": 0.01,
|
|
"learning_rate": 4.5e-05,
|
|
"loss": 7.9144,
|
|
"step": 20
|
|
},
|
|
{
|
|
"epoch": 0.01,
|
|
"learning_rate": 7.500000000000001e-05,
|
|
"loss": 6.7554,
|
|
"step": 30
|
|
},
|
|
{
|
|
"epoch": 0.01,
|
|
"learning_rate": 0.00012,
|
|
"loss": 5.7716,
|
|
"step": 40
|
|
},
|
|
{
|
|
"epoch": 0.01,
|
|
"learning_rate": 0.00017,
|
|
"loss": 5.0089,
|
|
"step": 50
|
|
},
|
|
{
|
|
"epoch": 0.02,
|
|
"learning_rate": 0.00019999947171819797,
|
|
"loss": 4.383,
|
|
"step": 60
|
|
},
|
|
{
|
|
"epoch": 0.02,
|
|
"learning_rate": 0.00019999352861202634,
|
|
"loss": 4.1286,
|
|
"step": 70
|
|
},
|
|
{
|
|
"epoch": 0.02,
|
|
"learning_rate": 0.0001999809824411913,
|
|
"loss": 3.7428,
|
|
"step": 80
|
|
},
|
|
{
|
|
"epoch": 0.02,
|
|
"learning_rate": 0.0001999618340341782,
|
|
"loss": 3.4558,
|
|
"step": 90
|
|
},
|
|
{
|
|
"epoch": 0.03,
|
|
"learning_rate": 0.00019993608465545054,
|
|
"loss": 3.3284,
|
|
"step": 100
|
|
},
|
|
{
|
|
"epoch": 0.03,
|
|
"learning_rate": 0.00019990373600536657,
|
|
"loss": 3.202,
|
|
"step": 110
|
|
},
|
|
{
|
|
"epoch": 0.03,
|
|
"learning_rate": 0.00019986479022006677,
|
|
"loss": 3.1471,
|
|
"step": 120
|
|
},
|
|
{
|
|
"epoch": 0.03,
|
|
"learning_rate": 0.00019981924987133289,
|
|
"loss": 3.0477,
|
|
"step": 130
|
|
},
|
|
{
|
|
"epoch": 0.04,
|
|
"learning_rate": 0.00019976711796641832,
|
|
"loss": 2.9572,
|
|
"step": 140
|
|
},
|
|
{
|
|
"epoch": 0.04,
|
|
"learning_rate": 0.00019970839794784917,
|
|
"loss": 2.9283,
|
|
"step": 150
|
|
},
|
|
{
|
|
"epoch": 0.04,
|
|
"learning_rate": 0.00019964309369319722,
|
|
"loss": 2.882,
|
|
"step": 160
|
|
},
|
|
{
|
|
"epoch": 0.04,
|
|
"learning_rate": 0.00019957120951482363,
|
|
"loss": 2.799,
|
|
"step": 170
|
|
},
|
|
{
|
|
"epoch": 0.05,
|
|
"learning_rate": 0.00019949275015959442,
|
|
"loss": 2.7808,
|
|
"step": 180
|
|
},
|
|
{
|
|
"epoch": 0.05,
|
|
"learning_rate": 0.0001994077208085668,
|
|
"loss": 2.7251,
|
|
"step": 190
|
|
},
|
|
{
|
|
"epoch": 0.05,
|
|
"learning_rate": 0.0001993161270766472,
|
|
"loss": 2.6977,
|
|
"step": 200
|
|
},
|
|
{
|
|
"epoch": 0.05,
|
|
"learning_rate": 0.00019921797501222036,
|
|
"loss": 2.7366,
|
|
"step": 210
|
|
},
|
|
{
|
|
"epoch": 0.06,
|
|
"learning_rate": 0.00019911327109675003,
|
|
"loss": 2.7007,
|
|
"step": 220
|
|
},
|
|
{
|
|
"epoch": 0.06,
|
|
"learning_rate": 0.00019900202224435086,
|
|
"loss": 2.6237,
|
|
"step": 230
|
|
},
|
|
{
|
|
"epoch": 0.06,
|
|
"learning_rate": 0.00019888423580133194,
|
|
"loss": 2.4928,
|
|
"step": 240
|
|
},
|
|
{
|
|
"epoch": 0.06,
|
|
"learning_rate": 0.0001987599195457116,
|
|
"loss": 2.6081,
|
|
"step": 250
|
|
},
|
|
{
|
|
"epoch": 0.07,
|
|
"learning_rate": 0.00019862908168670384,
|
|
"loss": 2.59,
|
|
"step": 260
|
|
},
|
|
{
|
|
"epoch": 0.07,
|
|
"learning_rate": 0.00019849173086417622,
|
|
"loss": 2.5477,
|
|
"step": 270
|
|
},
|
|
{
|
|
"epoch": 0.07,
|
|
"learning_rate": 0.0001983478761480793,
|
|
"loss": 2.5678,
|
|
"step": 280
|
|
},
|
|
{
|
|
"epoch": 0.07,
|
|
"learning_rate": 0.00019819752703784777,
|
|
"loss": 2.4678,
|
|
"step": 290
|
|
},
|
|
{
|
|
"epoch": 0.08,
|
|
"learning_rate": 0.0001980406934617731,
|
|
"loss": 2.4486,
|
|
"step": 300
|
|
},
|
|
{
|
|
"epoch": 0.08,
|
|
"learning_rate": 0.00019787738577634794,
|
|
"loss": 2.5024,
|
|
"step": 310
|
|
},
|
|
{
|
|
"epoch": 0.08,
|
|
"learning_rate": 0.00019770761476558223,
|
|
"loss": 2.5042,
|
|
"step": 320
|
|
},
|
|
{
|
|
"epoch": 0.08,
|
|
"learning_rate": 0.00019753139164029108,
|
|
"loss": 2.4463,
|
|
"step": 330
|
|
},
|
|
{
|
|
"epoch": 0.09,
|
|
"learning_rate": 0.00019734872803735444,
|
|
"loss": 2.4035,
|
|
"step": 340
|
|
},
|
|
{
|
|
"epoch": 0.09,
|
|
"learning_rate": 0.0001971596360189488,
|
|
"loss": 2.4444,
|
|
"step": 350
|
|
},
|
|
{
|
|
"epoch": 0.09,
|
|
"learning_rate": 0.0001969641280717504,
|
|
"loss": 2.4404,
|
|
"step": 360
|
|
},
|
|
{
|
|
"epoch": 0.09,
|
|
"learning_rate": 0.00019676221710611093,
|
|
"loss": 2.4378,
|
|
"step": 370
|
|
},
|
|
{
|
|
"epoch": 0.1,
|
|
"learning_rate": 0.00019655391645520486,
|
|
"loss": 2.3842,
|
|
"step": 380
|
|
},
|
|
{
|
|
"epoch": 0.1,
|
|
"learning_rate": 0.000196339239874149,
|
|
"loss": 2.3743,
|
|
"step": 390
|
|
},
|
|
{
|
|
"epoch": 0.1,
|
|
"learning_rate": 0.00019611820153909418,
|
|
"loss": 2.3983,
|
|
"step": 400
|
|
},
|
|
{
|
|
"epoch": 0.1,
|
|
"learning_rate": 0.0001958908160462892,
|
|
"loss": 2.3224,
|
|
"step": 410
|
|
},
|
|
{
|
|
"epoch": 0.11,
|
|
"learning_rate": 0.0001956570984111169,
|
|
"loss": 2.3779,
|
|
"step": 420
|
|
},
|
|
{
|
|
"epoch": 0.11,
|
|
"learning_rate": 0.00019541706406710256,
|
|
"loss": 2.3706,
|
|
"step": 430
|
|
},
|
|
{
|
|
"epoch": 0.11,
|
|
"learning_rate": 0.000195170728864895,
|
|
"loss": 2.3213,
|
|
"step": 440
|
|
},
|
|
{
|
|
"epoch": 0.12,
|
|
"learning_rate": 0.0001949181090712195,
|
|
"loss": 2.3222,
|
|
"step": 450
|
|
},
|
|
{
|
|
"epoch": 0.12,
|
|
"learning_rate": 0.00019465922136780396,
|
|
"loss": 2.3018,
|
|
"step": 460
|
|
},
|
|
{
|
|
"epoch": 0.12,
|
|
"learning_rate": 0.00019439408285027717,
|
|
"loss": 2.3268,
|
|
"step": 470
|
|
},
|
|
{
|
|
"epoch": 0.12,
|
|
"learning_rate": 0.00019412271102703992,
|
|
"loss": 2.2956,
|
|
"step": 480
|
|
},
|
|
{
|
|
"epoch": 0.13,
|
|
"learning_rate": 0.00019384512381810887,
|
|
"loss": 2.2676,
|
|
"step": 490
|
|
},
|
|
{
|
|
"epoch": 0.13,
|
|
"learning_rate": 0.00019356133955393312,
|
|
"loss": 2.2877,
|
|
"step": 500
|
|
},
|
|
{
|
|
"epoch": 0.13,
|
|
"learning_rate": 0.0001932713769741839,
|
|
"loss": 2.3348,
|
|
"step": 510
|
|
},
|
|
{
|
|
"epoch": 0.13,
|
|
"learning_rate": 0.0001929752552265169,
|
|
"loss": 2.3026,
|
|
"step": 520
|
|
},
|
|
{
|
|
"epoch": 0.14,
|
|
"learning_rate": 0.00019267299386530813,
|
|
"loss": 2.3344,
|
|
"step": 530
|
|
},
|
|
{
|
|
"epoch": 0.14,
|
|
"learning_rate": 0.00019236461285036233,
|
|
"loss": 2.258,
|
|
"step": 540
|
|
},
|
|
{
|
|
"epoch": 0.14,
|
|
"learning_rate": 0.0001920501325455952,
|
|
"loss": 2.2424,
|
|
"step": 550
|
|
},
|
|
{
|
|
"epoch": 0.14,
|
|
"learning_rate": 0.00019172957371768848,
|
|
"loss": 2.2824,
|
|
"step": 560
|
|
},
|
|
{
|
|
"epoch": 0.15,
|
|
"learning_rate": 0.00019140295753471872,
|
|
"loss": 2.2618,
|
|
"step": 570
|
|
},
|
|
{
|
|
"epoch": 0.15,
|
|
"learning_rate": 0.0001910703055647595,
|
|
"loss": 2.243,
|
|
"step": 580
|
|
},
|
|
{
|
|
"epoch": 0.15,
|
|
"learning_rate": 0.00019073163977445696,
|
|
"loss": 2.2295,
|
|
"step": 590
|
|
},
|
|
{
|
|
"epoch": 0.15,
|
|
"learning_rate": 0.00019038698252757952,
|
|
"loss": 2.2533,
|
|
"step": 600
|
|
},
|
|
{
|
|
"epoch": 0.16,
|
|
"learning_rate": 0.00019003635658354094,
|
|
"loss": 2.2098,
|
|
"step": 610
|
|
},
|
|
{
|
|
"epoch": 0.16,
|
|
"learning_rate": 0.0001896797850958973,
|
|
"loss": 2.3026,
|
|
"step": 620
|
|
},
|
|
{
|
|
"epoch": 0.16,
|
|
"learning_rate": 0.00018931729161081835,
|
|
"loss": 2.19,
|
|
"step": 630
|
|
},
|
|
{
|
|
"epoch": 0.16,
|
|
"learning_rate": 0.00018894890006553237,
|
|
"loss": 2.1298,
|
|
"step": 640
|
|
},
|
|
{
|
|
"epoch": 0.17,
|
|
"learning_rate": 0.00018857463478674552,
|
|
"loss": 2.1882,
|
|
"step": 650
|
|
},
|
|
{
|
|
"epoch": 0.17,
|
|
"learning_rate": 0.00018819452048903561,
|
|
"loss": 2.1378,
|
|
"step": 660
|
|
},
|
|
{
|
|
"epoch": 0.17,
|
|
"learning_rate": 0.00018780858227321988,
|
|
"loss": 2.1886,
|
|
"step": 670
|
|
},
|
|
{
|
|
"epoch": 0.17,
|
|
"learning_rate": 0.0001874168456246975,
|
|
"loss": 2.1542,
|
|
"step": 680
|
|
},
|
|
{
|
|
"epoch": 0.18,
|
|
"learning_rate": 0.00018701933641176676,
|
|
"loss": 2.1299,
|
|
"step": 690
|
|
},
|
|
{
|
|
"epoch": 0.18,
|
|
"learning_rate": 0.00018661608088391671,
|
|
"loss": 2.164,
|
|
"step": 700
|
|
},
|
|
{
|
|
"epoch": 0.18,
|
|
"learning_rate": 0.0001862071056700939,
|
|
"loss": 2.1497,
|
|
"step": 710
|
|
},
|
|
{
|
|
"epoch": 0.18,
|
|
"learning_rate": 0.00018579243777694387,
|
|
"loss": 2.1869,
|
|
"step": 720
|
|
},
|
|
{
|
|
"epoch": 0.19,
|
|
"learning_rate": 0.00018537210458702773,
|
|
"loss": 2.1317,
|
|
"step": 730
|
|
},
|
|
{
|
|
"epoch": 0.19,
|
|
"learning_rate": 0.00018494613385701408,
|
|
"loss": 2.138,
|
|
"step": 740
|
|
},
|
|
{
|
|
"epoch": 0.19,
|
|
"learning_rate": 0.00018451455371584603,
|
|
"loss": 2.1337,
|
|
"step": 750
|
|
},
|
|
{
|
|
"epoch": 0.19,
|
|
"learning_rate": 0.00018407739266288365,
|
|
"loss": 2.1062,
|
|
"step": 760
|
|
},
|
|
{
|
|
"epoch": 0.2,
|
|
"learning_rate": 0.00018363467956602206,
|
|
"loss": 2.0968,
|
|
"step": 770
|
|
},
|
|
{
|
|
"epoch": 0.2,
|
|
"learning_rate": 0.0001831864436597853,
|
|
"loss": 2.095,
|
|
"step": 780
|
|
},
|
|
{
|
|
"epoch": 0.2,
|
|
"learning_rate": 0.00018273271454339552,
|
|
"loss": 2.1348,
|
|
"step": 790
|
|
},
|
|
{
|
|
"epoch": 0.2,
|
|
"learning_rate": 0.0001822735221788186,
|
|
"loss": 2.0977,
|
|
"step": 800
|
|
},
|
|
{
|
|
"epoch": 0.21,
|
|
"learning_rate": 0.0001818088968887857,
|
|
"loss": 2.1029,
|
|
"step": 810
|
|
},
|
|
{
|
|
"epoch": 0.21,
|
|
"learning_rate": 0.00018133886935479057,
|
|
"loss": 2.1493,
|
|
"step": 820
|
|
},
|
|
{
|
|
"epoch": 0.21,
|
|
"learning_rate": 0.0001808634706150639,
|
|
"loss": 2.088,
|
|
"step": 830
|
|
},
|
|
{
|
|
"epoch": 0.22,
|
|
"learning_rate": 0.0001803827320625234,
|
|
"loss": 2.1212,
|
|
"step": 840
|
|
},
|
|
{
|
|
"epoch": 0.22,
|
|
"learning_rate": 0.00017989668544270097,
|
|
"loss": 2.0288,
|
|
"step": 850
|
|
},
|
|
{
|
|
"epoch": 0.22,
|
|
"learning_rate": 0.0001794053628516462,
|
|
"loss": 2.0432,
|
|
"step": 860
|
|
},
|
|
{
|
|
"epoch": 0.22,
|
|
"learning_rate": 0.00017890879673380719,
|
|
"loss": 2.0355,
|
|
"step": 870
|
|
},
|
|
{
|
|
"epoch": 0.23,
|
|
"learning_rate": 0.00017840701987988772,
|
|
"loss": 2.0755,
|
|
"step": 880
|
|
},
|
|
{
|
|
"epoch": 0.23,
|
|
"learning_rate": 0.0001779000654246823,
|
|
"loss": 2.0453,
|
|
"step": 890
|
|
},
|
|
{
|
|
"epoch": 0.23,
|
|
"learning_rate": 0.00017738796684488772,
|
|
"loss": 2.0582,
|
|
"step": 900
|
|
},
|
|
{
|
|
"epoch": 0.23,
|
|
"learning_rate": 0.00017687075795689278,
|
|
"loss": 2.0768,
|
|
"step": 910
|
|
},
|
|
{
|
|
"epoch": 0.24,
|
|
"learning_rate": 0.00017634847291454503,
|
|
"loss": 2.091,
|
|
"step": 920
|
|
},
|
|
{
|
|
"epoch": 0.24,
|
|
"learning_rate": 0.0001758211462068955,
|
|
"loss": 2.0577,
|
|
"step": 930
|
|
},
|
|
{
|
|
"epoch": 0.24,
|
|
"learning_rate": 0.00017528881265592108,
|
|
"loss": 2.0704,
|
|
"step": 940
|
|
},
|
|
{
|
|
"epoch": 0.24,
|
|
"learning_rate": 0.00017475150741422528,
|
|
"loss": 2.0305,
|
|
"step": 950
|
|
},
|
|
{
|
|
"epoch": 0.25,
|
|
"learning_rate": 0.0001742092659627167,
|
|
"loss": 2.0256,
|
|
"step": 960
|
|
},
|
|
{
|
|
"epoch": 0.25,
|
|
"learning_rate": 0.0001736621241082663,
|
|
"loss": 2.0357,
|
|
"step": 970
|
|
},
|
|
{
|
|
"epoch": 0.25,
|
|
"learning_rate": 0.00017311011798134263,
|
|
"loss": 1.9873,
|
|
"step": 980
|
|
},
|
|
{
|
|
"epoch": 0.25,
|
|
"learning_rate": 0.00017255328403362606,
|
|
"loss": 2.0248,
|
|
"step": 990
|
|
},
|
|
{
|
|
"epoch": 0.26,
|
|
"learning_rate": 0.00017199165903560192,
|
|
"loss": 1.9927,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"epoch": 0.26,
|
|
"eval_loss": 1.7968560457229614,
|
|
"eval_runtime": 2.032,
|
|
"eval_samples_per_second": 49.213,
|
|
"eval_steps_per_second": 1.969,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"epoch": 0.26,
|
|
"learning_rate": 0.00017142528007413192,
|
|
"loss": 1.9916,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"epoch": 0.26,
|
|
"learning_rate": 0.00017085418455000553,
|
|
"loss": 2.0123,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"epoch": 0.26,
|
|
"learning_rate": 0.00017027841017546998,
|
|
"loss": 2.0141,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"epoch": 0.27,
|
|
"learning_rate": 0.00016969799497174005,
|
|
"loss": 1.976,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"epoch": 0.27,
|
|
"learning_rate": 0.0001691129772664873,
|
|
"loss": 1.9943,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"epoch": 0.27,
|
|
"learning_rate": 0.00016852339569130905,
|
|
"loss": 1.9607,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"epoch": 0.27,
|
|
"learning_rate": 0.00016792928917917755,
|
|
"loss": 1.9793,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"epoch": 0.28,
|
|
"learning_rate": 0.00016733069696186868,
|
|
"loss": 1.988,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"epoch": 0.28,
|
|
"learning_rate": 0.00016672765856737178,
|
|
"loss": 1.9143,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"epoch": 0.28,
|
|
"learning_rate": 0.00016612021381727887,
|
|
"loss": 1.9971,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"epoch": 0.28,
|
|
"learning_rate": 0.0001655084028241555,
|
|
"loss": 1.9675,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"epoch": 0.29,
|
|
"learning_rate": 0.0001648922659888916,
|
|
"loss": 2.0046,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"epoch": 0.29,
|
|
"learning_rate": 0.00016427184399803383,
|
|
"loss": 2.018,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"epoch": 0.29,
|
|
"learning_rate": 0.0001636471778210988,
|
|
"loss": 1.999,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"epoch": 0.29,
|
|
"learning_rate": 0.00016301830870786742,
|
|
"loss": 1.9143,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"epoch": 0.3,
|
|
"learning_rate": 0.00016238527818566138,
|
|
"loss": 1.9324,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"epoch": 0.3,
|
|
"learning_rate": 0.0001617481280566005,
|
|
"loss": 1.9493,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"epoch": 0.3,
|
|
"learning_rate": 0.00016110690039484267,
|
|
"loss": 1.9507,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"epoch": 0.3,
|
|
"learning_rate": 0.00016046163754380514,
|
|
"loss": 1.9408,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"epoch": 0.31,
|
|
"learning_rate": 0.00015981238211336873,
|
|
"loss": 2.0009,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"epoch": 0.31,
|
|
"learning_rate": 0.00015915917697706386,
|
|
"loss": 1.9684,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"epoch": 0.31,
|
|
"learning_rate": 0.0001585020652692394,
|
|
"loss": 1.9373,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"epoch": 0.31,
|
|
"learning_rate": 0.0001578410903822145,
|
|
"loss": 1.9038,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"epoch": 0.32,
|
|
"learning_rate": 0.00015717629596341288,
|
|
"loss": 1.9065,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"epoch": 0.32,
|
|
"learning_rate": 0.00015650772591248085,
|
|
"loss": 1.9327,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"epoch": 0.32,
|
|
"learning_rate": 0.0001558354243783882,
|
|
"loss": 1.935,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"epoch": 0.33,
|
|
"learning_rate": 0.000155159435756513,
|
|
"loss": 1.9339,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"epoch": 0.33,
|
|
"learning_rate": 0.00015447980468570979,
|
|
"loss": 1.929,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"epoch": 0.33,
|
|
"learning_rate": 0.00015379657604536203,
|
|
"loss": 1.9184,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"epoch": 0.33,
|
|
"learning_rate": 0.00015310979495241825,
|
|
"loss": 1.9242,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"epoch": 0.34,
|
|
"learning_rate": 0.00015241950675841306,
|
|
"loss": 1.9133,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"epoch": 0.34,
|
|
"learning_rate": 0.0001517257570464721,
|
|
"loss": 1.9014,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"epoch": 0.34,
|
|
"learning_rate": 0.00015102859162830209,
|
|
"loss": 1.9283,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"epoch": 0.34,
|
|
"learning_rate": 0.00015032805654116566,
|
|
"loss": 1.8821,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"epoch": 0.35,
|
|
"learning_rate": 0.00014962419804484127,
|
|
"loss": 1.8956,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"epoch": 0.35,
|
|
"learning_rate": 0.00014891706261856844,
|
|
"loss": 1.9166,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"epoch": 0.35,
|
|
"learning_rate": 0.00014820669695797843,
|
|
"loss": 1.9385,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"epoch": 0.35,
|
|
"learning_rate": 0.00014749314797201084,
|
|
"loss": 1.9325,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"epoch": 0.36,
|
|
"learning_rate": 0.00014677646277981593,
|
|
"loss": 1.8642,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"epoch": 0.36,
|
|
"learning_rate": 0.00014605668870764293,
|
|
"loss": 1.8964,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"epoch": 0.36,
|
|
"learning_rate": 0.0001453338732857152,
|
|
"loss": 1.8727,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"epoch": 0.36,
|
|
"learning_rate": 0.00014460806424509132,
|
|
"loss": 1.8644,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"epoch": 0.37,
|
|
"learning_rate": 0.0001438793095145132,
|
|
"loss": 1.8591,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"epoch": 0.37,
|
|
"learning_rate": 0.00014314765721724118,
|
|
"loss": 1.8931,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"epoch": 0.37,
|
|
"learning_rate": 0.00014241315566787617,
|
|
"loss": 1.8953,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"epoch": 0.37,
|
|
"learning_rate": 0.00014167585336916926,
|
|
"loss": 1.8672,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"epoch": 0.38,
|
|
"learning_rate": 0.0001409357990088188,
|
|
"loss": 1.8414,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"epoch": 0.38,
|
|
"learning_rate": 0.00014019304145625517,
|
|
"loss": 1.8838,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"epoch": 0.38,
|
|
"learning_rate": 0.00013944762975941403,
|
|
"loss": 1.856,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"epoch": 0.38,
|
|
"learning_rate": 0.00013877453061830693,
|
|
"loss": 1.8715,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"epoch": 0.39,
|
|
"learning_rate": 0.00013802421179949775,
|
|
"loss": 1.8323,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"epoch": 0.39,
|
|
"learning_rate": 0.00013727138205490392,
|
|
"loss": 1.898,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"epoch": 0.39,
|
|
"learning_rate": 0.00013651609109757744,
|
|
"loss": 1.8455,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"epoch": 0.39,
|
|
"learning_rate": 0.00013575838880309623,
|
|
"loss": 1.8788,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"epoch": 0.4,
|
|
"learning_rate": 0.00013499832520627076,
|
|
"loss": 1.8881,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"epoch": 0.4,
|
|
"learning_rate": 0.00013423595049783974,
|
|
"loss": 1.8326,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"epoch": 0.4,
|
|
"learning_rate": 0.00013347131502115616,
|
|
"loss": 1.845,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"epoch": 0.4,
|
|
"learning_rate": 0.00013270446926886252,
|
|
"loss": 1.8768,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"epoch": 0.41,
|
|
"learning_rate": 0.00013193546387955672,
|
|
"loss": 1.8571,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"epoch": 0.41,
|
|
"learning_rate": 0.00013116434963444815,
|
|
"loss": 1.8596,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"epoch": 0.41,
|
|
"learning_rate": 0.00013039117745400426,
|
|
"loss": 1.8515,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"epoch": 0.41,
|
|
"learning_rate": 0.00012961599839458825,
|
|
"loss": 1.8281,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"epoch": 0.42,
|
|
"learning_rate": 0.00012883886364508718,
|
|
"loss": 1.7872,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"epoch": 0.42,
|
|
"learning_rate": 0.00012805982452353213,
|
|
"loss": 1.8333,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"epoch": 0.42,
|
|
"learning_rate": 0.00012727893247370918,
|
|
"loss": 1.7989,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"epoch": 0.42,
|
|
"learning_rate": 0.00012657458799214414,
|
|
"loss": 1.8662,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"epoch": 0.43,
|
|
"learning_rate": 0.00012579031754172398,
|
|
"loss": 1.8667,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"epoch": 0.43,
|
|
"learning_rate": 0.0001250043440297479,
|
|
"loss": 1.821,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"epoch": 0.43,
|
|
"learning_rate": 0.0001242167193579139,
|
|
"loss": 1.8333,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"epoch": 0.44,
|
|
"learning_rate": 0.00012342749553695423,
|
|
"loss": 1.8554,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"epoch": 0.44,
|
|
"learning_rate": 0.0001226367246832007,
|
|
"loss": 1.8308,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"epoch": 0.44,
|
|
"learning_rate": 0.00012184445901514343,
|
|
"loss": 1.8215,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"epoch": 0.44,
|
|
"learning_rate": 0.00012105075084998242,
|
|
"loss": 1.8347,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"epoch": 0.45,
|
|
"learning_rate": 0.00012025565260017291,
|
|
"loss": 1.7671,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"epoch": 0.45,
|
|
"learning_rate": 0.00011945921676996417,
|
|
"loss": 1.8035,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"epoch": 0.45,
|
|
"learning_rate": 0.00011866149595193254,
|
|
"loss": 1.8008,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"epoch": 0.45,
|
|
"learning_rate": 0.0001178625428235085,
|
|
"loss": 1.8057,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"epoch": 0.46,
|
|
"learning_rate": 0.00011706241014349788,
|
|
"loss": 1.8286,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"epoch": 0.46,
|
|
"learning_rate": 0.00011626115074859829,
|
|
"loss": 1.7838,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"epoch": 0.46,
|
|
"learning_rate": 0.00011545881754990972,
|
|
"loss": 1.7678,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"epoch": 0.46,
|
|
"learning_rate": 0.00011465546352944083,
|
|
"loss": 1.8015,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"epoch": 0.47,
|
|
"learning_rate": 0.00011385114173661003,
|
|
"loss": 1.773,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"epoch": 0.47,
|
|
"learning_rate": 0.00011304590528474257,
|
|
"loss": 1.7528,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"epoch": 0.47,
|
|
"learning_rate": 0.00011223980734756319,
|
|
"loss": 1.7651,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"epoch": 0.47,
|
|
"learning_rate": 0.00011143290115568473,
|
|
"loss": 1.7817,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"epoch": 0.48,
|
|
"learning_rate": 0.00011062523999309291,
|
|
"loss": 1.7699,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"epoch": 0.48,
|
|
"learning_rate": 0.00010981687719362807,
|
|
"loss": 1.7672,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"epoch": 0.48,
|
|
"learning_rate": 0.00010900786613746299,
|
|
"loss": 1.789,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"epoch": 0.48,
|
|
"learning_rate": 0.00010819826024757807,
|
|
"loss": 1.7622,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"epoch": 0.49,
|
|
"learning_rate": 0.00010738811298623348,
|
|
"loss": 1.7543,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"epoch": 0.49,
|
|
"learning_rate": 0.00010657747785143882,
|
|
"loss": 1.7432,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"epoch": 0.49,
|
|
"learning_rate": 0.00010576640837342036,
|
|
"loss": 1.7765,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"epoch": 0.49,
|
|
"learning_rate": 0.00010495495811108622,
|
|
"loss": 1.768,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"epoch": 0.5,
|
|
"learning_rate": 0.00010414318064848956,
|
|
"loss": 1.7852,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"epoch": 0.5,
|
|
"learning_rate": 0.0001033311295912902,
|
|
"loss": 1.7551,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"epoch": 0.5,
|
|
"learning_rate": 0.0001025188585632147,
|
|
"loss": 1.7474,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"epoch": 0.5,
|
|
"learning_rate": 0.00010186891940623151,
|
|
"loss": 1.7737,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"epoch": 0.51,
|
|
"learning_rate": 0.00010105638760647513,
|
|
"loss": 1.7802,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"epoch": 0.51,
|
|
"learning_rate": 0.00010024378604824765,
|
|
"loss": 1.7723,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"epoch": 0.51,
|
|
"learning_rate": 9.943116839162797e-05,
|
|
"loss": 1.7412,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"epoch": 0.51,
|
|
"eval_loss": 1.5315768718719482,
|
|
"eval_runtime": 2.0299,
|
|
"eval_samples_per_second": 49.264,
|
|
"eval_steps_per_second": 1.971,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"epoch": 0.51,
|
|
"learning_rate": 9.869984308751394e-05,
|
|
"loss": 1.7468,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"epoch": 0.52,
|
|
"learning_rate": 9.788734267841828e-05,
|
|
"loss": 1.7681,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"epoch": 0.52,
|
|
"learning_rate": 9.707498177847988e-05,
|
|
"loss": 1.8109,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"epoch": 0.52,
|
|
"learning_rate": 9.626281403188578e-05,
|
|
"loss": 1.72,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"epoch": 0.52,
|
|
"learning_rate": 9.545089307006811e-05,
|
|
"loss": 1.703,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"epoch": 0.53,
|
|
"learning_rate": 9.463927250816272e-05,
|
|
"loss": 1.7624,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"epoch": 0.53,
|
|
"learning_rate": 9.382800594146841e-05,
|
|
"loss": 1.7587,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"epoch": 0.53,
|
|
"learning_rate": 9.301714694190808e-05,
|
|
"loss": 1.7375,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"epoch": 0.54,
|
|
"learning_rate": 9.220674905449091e-05,
|
|
"loss": 1.7579,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"epoch": 0.54,
|
|
"learning_rate": 9.139686579377649e-05,
|
|
"loss": 1.7396,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"epoch": 0.54,
|
|
"learning_rate": 9.058755064034127e-05,
|
|
"loss": 1.6666,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"epoch": 0.54,
|
|
"learning_rate": 8.977885703724658e-05,
|
|
"loss": 1.7319,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"epoch": 0.55,
|
|
"learning_rate": 8.897083838650984e-05,
|
|
"loss": 1.7387,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"epoch": 0.55,
|
|
"learning_rate": 8.816354804557807e-05,
|
|
"loss": 1.7204,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"epoch": 0.55,
|
|
"learning_rate": 8.743765350485347e-05,
|
|
"loss": 1.7183,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"epoch": 0.55,
|
|
"learning_rate": 8.671243090320367e-05,
|
|
"loss": 1.7173,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"epoch": 0.56,
|
|
"learning_rate": 8.590746326848647e-05,
|
|
"loss": 1.7185,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"epoch": 0.56,
|
|
"learning_rate": 8.510342623330503e-05,
|
|
"loss": 1.7228,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"epoch": 0.56,
|
|
"learning_rate": 8.430037289218072e-05,
|
|
"loss": 1.7542,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"epoch": 0.56,
|
|
"learning_rate": 8.349835627467664e-05,
|
|
"loss": 1.7005,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"epoch": 0.57,
|
|
"learning_rate": 8.269742934189604e-05,
|
|
"loss": 1.7211,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"epoch": 0.57,
|
|
"learning_rate": 8.189764498298483e-05,
|
|
"loss": 1.7455,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"epoch": 0.57,
|
|
"learning_rate": 8.109905601163912e-05,
|
|
"loss": 1.6729,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"epoch": 0.57,
|
|
"learning_rate": 8.030171516261782e-05,
|
|
"loss": 1.7341,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"epoch": 0.58,
|
|
"learning_rate": 7.950567508826012e-05,
|
|
"loss": 1.7286,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"epoch": 0.58,
|
|
"learning_rate": 7.871098835500859e-05,
|
|
"loss": 1.7079,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"epoch": 0.58,
|
|
"learning_rate": 7.791770743993817e-05,
|
|
"loss": 1.7001,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"epoch": 0.58,
|
|
"learning_rate": 7.712588472729058e-05,
|
|
"loss": 1.7239,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"epoch": 0.59,
|
|
"learning_rate": 7.633557250501531e-05,
|
|
"loss": 1.7032,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"epoch": 0.59,
|
|
"learning_rate": 7.55468229613168e-05,
|
|
"loss": 1.6624,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"epoch": 0.59,
|
|
"learning_rate": 7.475968818120798e-05,
|
|
"loss": 1.7258,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"epoch": 0.59,
|
|
"learning_rate": 7.405269046437083e-05,
|
|
"loss": 1.6995,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"epoch": 0.6,
|
|
"learning_rate": 7.342541200785587e-05,
|
|
"loss": 1.6715,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"epoch": 0.6,
|
|
"learning_rate": 7.26428964082281e-05,
|
|
"loss": 1.7005,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"epoch": 0.6,
|
|
"learning_rate": 7.186218733274769e-05,
|
|
"loss": 1.6575,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"epoch": 0.6,
|
|
"learning_rate": 7.1083336335476e-05,
|
|
"loss": 1.7001,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"epoch": 0.61,
|
|
"learning_rate": 7.030639484777641e-05,
|
|
"loss": 1.6679,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"epoch": 0.61,
|
|
"learning_rate": 6.953141417491781e-05,
|
|
"loss": 1.7034,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"epoch": 0.61,
|
|
"learning_rate": 6.875844549268706e-05,
|
|
"loss": 1.6804,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"epoch": 0.61,
|
|
"learning_rate": 6.798753984400916e-05,
|
|
"loss": 1.6844,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"epoch": 0.62,
|
|
"learning_rate": 6.721874813557699e-05,
|
|
"loss": 1.7038,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"epoch": 0.62,
|
|
"learning_rate": 6.645212113448953e-05,
|
|
"loss": 1.6728,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"epoch": 0.62,
|
|
"learning_rate": 6.568770946489948e-05,
|
|
"loss": 1.682,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"epoch": 0.62,
|
|
"learning_rate": 6.492556360467025e-05,
|
|
"loss": 1.6799,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"epoch": 0.63,
|
|
"learning_rate": 6.416573388204282e-05,
|
|
"loss": 1.66,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"epoch": 0.63,
|
|
"learning_rate": 6.340827047231211e-05,
|
|
"loss": 1.6806,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"epoch": 0.63,
|
|
"learning_rate": 6.265322339451376e-05,
|
|
"loss": 1.6661,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"epoch": 0.63,
|
|
"learning_rate": 6.190064250812124e-05,
|
|
"loss": 1.6696,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"epoch": 0.64,
|
|
"learning_rate": 6.115057750975312e-05,
|
|
"loss": 1.6153,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"epoch": 0.64,
|
|
"learning_rate": 6.040307792989157e-05,
|
|
"loss": 1.6824,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"epoch": 0.64,
|
|
"learning_rate": 5.9658193129611604e-05,
|
|
"loss": 1.6886,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"epoch": 0.65,
|
|
"learning_rate": 5.891597229732135e-05,
|
|
"loss": 1.6358,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"epoch": 0.65,
|
|
"learning_rate": 5.8176464445514166e-05,
|
|
"loss": 1.6462,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"epoch": 0.65,
|
|
"learning_rate": 5.7439718407531906e-05,
|
|
"loss": 1.6434,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"epoch": 0.65,
|
|
"learning_rate": 5.670578283434016e-05,
|
|
"loss": 1.6459,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"epoch": 0.66,
|
|
"learning_rate": 5.5974706191315884e-05,
|
|
"loss": 1.6705,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"epoch": 0.66,
|
|
"learning_rate": 5.5246536755046706e-05,
|
|
"loss": 1.6638,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"epoch": 0.66,
|
|
"learning_rate": 5.452132261014304e-05,
|
|
"loss": 1.6656,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"epoch": 0.66,
|
|
"learning_rate": 5.379911164606304e-05,
|
|
"loss": 1.6572,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"epoch": 0.67,
|
|
"learning_rate": 5.315172891887351e-05,
|
|
"loss": 1.643,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"epoch": 0.67,
|
|
"learning_rate": 5.2435355221012797e-05,
|
|
"loss": 1.6544,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"epoch": 0.67,
|
|
"learning_rate": 5.172212245066537e-05,
|
|
"loss": 1.628,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"epoch": 0.67,
|
|
"learning_rate": 5.1012077706100125e-05,
|
|
"loss": 1.6378,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"epoch": 0.68,
|
|
"learning_rate": 5.0305267875065087e-05,
|
|
"loss": 1.6475,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"epoch": 0.68,
|
|
"learning_rate": 4.9601739631690836e-05,
|
|
"loss": 1.5959,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"epoch": 0.68,
|
|
"learning_rate": 4.897140837169796e-05,
|
|
"loss": 1.657,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"epoch": 0.68,
|
|
"learning_rate": 4.827424295352793e-05,
|
|
"loss": 1.6716,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"epoch": 0.69,
|
|
"learning_rate": 4.758049324158693e-05,
|
|
"loss": 1.59,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"epoch": 0.69,
|
|
"learning_rate": 4.6890205047581745e-05,
|
|
"loss": 1.6442,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"epoch": 0.69,
|
|
"learning_rate": 4.6203423954637995e-05,
|
|
"loss": 1.6152,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"epoch": 0.69,
|
|
"learning_rate": 4.552019531429019e-05,
|
|
"loss": 1.6446,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"epoch": 0.7,
|
|
"learning_rate": 4.484056424348703e-05,
|
|
"loss": 1.6216,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"epoch": 0.7,
|
|
"learning_rate": 4.416457562161184e-05,
|
|
"loss": 1.6534,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"epoch": 0.7,
|
|
"learning_rate": 4.349227408751919e-05,
|
|
"loss": 1.6474,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"epoch": 0.7,
|
|
"learning_rate": 4.282370403658717e-05,
|
|
"loss": 1.6338,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"epoch": 0.71,
|
|
"learning_rate": 4.2158909617785525e-05,
|
|
"loss": 1.6473,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"epoch": 0.71,
|
|
"learning_rate": 4.149793473076058e-05,
|
|
"loss": 1.6315,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"epoch": 0.71,
|
|
"learning_rate": 4.084082302293617e-05,
|
|
"loss": 1.6516,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"epoch": 0.71,
|
|
"learning_rate": 4.018761788663127e-05,
|
|
"loss": 1.6112,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"epoch": 0.72,
|
|
"learning_rate": 3.953836245619488e-05,
|
|
"loss": 1.6077,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"epoch": 0.72,
|
|
"learning_rate": 3.889309960515738e-05,
|
|
"loss": 1.6182,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"epoch": 0.72,
|
|
"learning_rate": 3.82518719433995e-05,
|
|
"loss": 1.6072,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"epoch": 0.72,
|
|
"learning_rate": 3.761472181433865e-05,
|
|
"loss": 1.6062,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"epoch": 0.73,
|
|
"learning_rate": 3.6981691292132604e-05,
|
|
"loss": 1.6332,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"epoch": 0.73,
|
|
"learning_rate": 3.6352822178901235e-05,
|
|
"loss": 1.6393,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"epoch": 0.73,
|
|
"learning_rate": 3.5728156001966154e-05,
|
|
"loss": 1.6401,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"epoch": 0.73,
|
|
"learning_rate": 3.5169584051980575e-05,
|
|
"loss": 1.6234,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"epoch": 0.74,
|
|
"learning_rate": 3.461447977339909e-05,
|
|
"loss": 1.5814,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"epoch": 0.74,
|
|
"learning_rate": 3.4001800370596834e-05,
|
|
"loss": 1.6018,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"epoch": 0.74,
|
|
"learning_rate": 3.339347915362796e-05,
|
|
"loss": 1.6172,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"epoch": 0.74,
|
|
"learning_rate": 3.278955629293534e-05,
|
|
"loss": 1.6042,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"epoch": 0.75,
|
|
"learning_rate": 3.219007166851673e-05,
|
|
"loss": 1.6119,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"epoch": 0.75,
|
|
"learning_rate": 3.1595064867291394e-05,
|
|
"loss": 1.621,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"epoch": 0.75,
|
|
"learning_rate": 3.1004575180485885e-05,
|
|
"loss": 1.6046,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"epoch": 0.76,
|
|
"learning_rate": 3.0418641601039366e-05,
|
|
"loss": 1.5811,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"epoch": 0.76,
|
|
"learning_rate": 2.9837302821028956e-05,
|
|
"loss": 1.5635,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"epoch": 0.76,
|
|
"learning_rate": 2.926059722911447e-05,
|
|
"loss": 1.6193,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"epoch": 0.76,
|
|
"learning_rate": 2.86885629080035e-05,
|
|
"loss": 1.6067,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"epoch": 0.77,
|
|
"learning_rate": 2.823432416081132e-05,
|
|
"loss": 1.5795,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"epoch": 0.77,
|
|
"learning_rate": 2.7670793109350358e-05,
|
|
"loss": 1.5891,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.77,
|
|
"eval_loss": 1.3908636569976807,
|
|
"eval_runtime": 2.0291,
|
|
"eval_samples_per_second": 49.282,
|
|
"eval_steps_per_second": 1.971,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.77,
|
|
"learning_rate": 2.7112038311280828e-05,
|
|
"loss": 1.599,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"epoch": 0.77,
|
|
"learning_rate": 2.655809666393112e-05,
|
|
"loss": 1.5877,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"epoch": 0.78,
|
|
"learning_rate": 2.600900474679364e-05,
|
|
"loss": 1.6096,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"epoch": 0.78,
|
|
"learning_rate": 2.546479881910918e-05,
|
|
"loss": 1.6317,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"epoch": 0.78,
|
|
"learning_rate": 2.4925514817472618e-05,
|
|
"loss": 1.5218,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"epoch": 0.78,
|
|
"learning_rate": 2.4391188353459925e-05,
|
|
"loss": 1.5526,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"epoch": 0.79,
|
|
"learning_rate": 2.3861854711276378e-05,
|
|
"loss": 1.5753,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"epoch": 0.79,
|
|
"learning_rate": 2.333754884542667e-05,
|
|
"loss": 1.6214,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"epoch": 0.79,
|
|
"learning_rate": 2.281830537840678e-05,
|
|
"loss": 1.591,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"epoch": 0.79,
|
|
"learning_rate": 2.2355342955230186e-05,
|
|
"loss": 1.5578,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"epoch": 0.8,
|
|
"learning_rate": 2.189653361595686e-05,
|
|
"loss": 1.5684,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"epoch": 0.8,
|
|
"learning_rate": 2.1391646203159456e-05,
|
|
"loss": 1.5654,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"epoch": 0.8,
|
|
"learning_rate": 2.089194968671713e-05,
|
|
"loss": 1.5803,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"epoch": 0.8,
|
|
"learning_rate": 2.039747706404943e-05,
|
|
"loss": 1.5737,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"epoch": 0.81,
|
|
"learning_rate": 1.99082609876164e-05,
|
|
"loss": 1.5444,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"epoch": 0.81,
|
|
"learning_rate": 1.9472487573431274e-05,
|
|
"loss": 1.5995,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"epoch": 0.81,
|
|
"learning_rate": 1.8993347647457706e-05,
|
|
"loss": 1.5803,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"epoch": 0.81,
|
|
"learning_rate": 1.8519556989292508e-05,
|
|
"loss": 1.5892,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"epoch": 0.82,
|
|
"learning_rate": 1.8051146885663938e-05,
|
|
"loss": 1.6006,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"epoch": 0.82,
|
|
"learning_rate": 1.7588148267995695e-05,
|
|
"loss": 1.567,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"epoch": 0.82,
|
|
"learning_rate": 1.7130591710364486e-05,
|
|
"loss": 1.5557,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"epoch": 0.82,
|
|
"learning_rate": 1.6678507427480983e-05,
|
|
"loss": 1.5794,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"epoch": 0.83,
|
|
"learning_rate": 1.6231925272694615e-05,
|
|
"loss": 1.5858,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"epoch": 0.83,
|
|
"learning_rate": 1.5790874736022287e-05,
|
|
"loss": 1.5791,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"epoch": 0.83,
|
|
"learning_rate": 1.535538494220089e-05,
|
|
"loss": 1.5721,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"epoch": 0.83,
|
|
"learning_rate": 1.4925484648764131e-05,
|
|
"loss": 1.5537,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"epoch": 0.84,
|
|
"learning_rate": 1.450120224414352e-05,
|
|
"loss": 1.5698,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"epoch": 0.84,
|
|
"learning_rate": 1.4082565745793686e-05,
|
|
"loss": 1.5529,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"epoch": 0.84,
|
|
"learning_rate": 1.3669602798342296e-05,
|
|
"loss": 1.5702,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"epoch": 0.84,
|
|
"learning_rate": 1.3262340671764584e-05,
|
|
"loss": 1.5273,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"epoch": 0.85,
|
|
"learning_rate": 1.2860806259582492e-05,
|
|
"loss": 1.5401,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"epoch": 0.85,
|
|
"learning_rate": 1.2504344407159785e-05,
|
|
"loss": 1.5753,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"epoch": 0.85,
|
|
"learning_rate": 1.2113765387943211e-05,
|
|
"loss": 1.5564,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"epoch": 0.85,
|
|
"learning_rate": 1.172898992919923e-05,
|
|
"loss": 1.5189,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"epoch": 0.86,
|
|
"learning_rate": 1.1350043439544521e-05,
|
|
"loss": 1.5607,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"epoch": 0.86,
|
|
"learning_rate": 1.0976950942680197e-05,
|
|
"loss": 1.539,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"epoch": 0.86,
|
|
"learning_rate": 1.0609737075739412e-05,
|
|
"loss": 1.5593,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"epoch": 0.87,
|
|
"learning_rate": 1.0248426087660557e-05,
|
|
"loss": 1.5345,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"epoch": 0.87,
|
|
"learning_rate": 9.89304183758577e-06,
|
|
"loss": 1.5988,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"epoch": 0.87,
|
|
"learning_rate": 9.543607793285626e-06,
|
|
"loss": 1.5306,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"epoch": 0.87,
|
|
"learning_rate": 9.200147029609264e-06,
|
|
"loss": 1.5702,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"epoch": 0.88,
|
|
"learning_rate": 8.896158250762244e-06,
|
|
"loss": 1.5378,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"epoch": 0.88,
|
|
"learning_rate": 8.59704246528129e-06,
|
|
"loss": 1.5693,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"epoch": 0.88,
|
|
"learning_rate": 8.270426282311539e-06,
|
|
"loss": 1.5517,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"epoch": 0.88,
|
|
"learning_rate": 7.949867454404824e-06,
|
|
"loss": 1.5576,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"epoch": 0.89,
|
|
"learning_rate": 7.635387149637685e-06,
|
|
"loss": 1.5763,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"epoch": 0.89,
|
|
"learning_rate": 7.327006134691883e-06,
|
|
"loss": 1.5768,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"epoch": 0.89,
|
|
"learning_rate": 7.024744773483105e-06,
|
|
"loss": 1.5393,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"epoch": 0.89,
|
|
"learning_rate": 6.7286230258161385e-06,
|
|
"loss": 1.5617,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"epoch": 0.9,
|
|
"learning_rate": 6.438660446066891e-06,
|
|
"loss": 1.5404,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"epoch": 0.9,
|
|
"learning_rate": 6.154876181891145e-06,
|
|
"loss": 1.5765,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"epoch": 0.9,
|
|
"learning_rate": 5.877288972960071e-06,
|
|
"loss": 1.5942,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"epoch": 0.9,
|
|
"learning_rate": 5.632774125747675e-06,
|
|
"loss": 1.5557,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"epoch": 0.91,
|
|
"learning_rate": 5.367011482971008e-06,
|
|
"loss": 1.5438,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"epoch": 0.91,
|
|
"learning_rate": 5.107497922021364e-06,
|
|
"loss": 1.5351,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"epoch": 0.91,
|
|
"learning_rate": 4.854250579856034e-06,
|
|
"loss": 1.5304,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"epoch": 0.91,
|
|
"learning_rate": 4.6072861796429665e-06,
|
|
"loss": 1.554,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"epoch": 0.92,
|
|
"learning_rate": 4.366621029656582e-06,
|
|
"loss": 1.5185,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"epoch": 0.92,
|
|
"learning_rate": 4.1322710222008065e-06,
|
|
"loss": 1.5746,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"epoch": 0.92,
|
|
"learning_rate": 3.904251632559652e-06,
|
|
"loss": 1.5413,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"epoch": 0.92,
|
|
"learning_rate": 3.6825779179752716e-06,
|
|
"loss": 1.5533,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"epoch": 0.93,
|
|
"learning_rate": 3.467264516653668e-06,
|
|
"loss": 1.5432,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"epoch": 0.93,
|
|
"learning_rate": 3.2583256467980773e-06,
|
|
"loss": 1.5869,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"epoch": 0.93,
|
|
"learning_rate": 3.055775105670056e-06,
|
|
"loss": 1.5374,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"epoch": 0.93,
|
|
"learning_rate": 2.8596262686783837e-06,
|
|
"loss": 1.5425,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"epoch": 0.94,
|
|
"learning_rate": 2.6698920884958177e-06,
|
|
"loss": 1.5906,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"epoch": 0.94,
|
|
"learning_rate": 2.486585094203786e-06,
|
|
"loss": 1.5787,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"epoch": 0.94,
|
|
"learning_rate": 2.309717390464983e-06,
|
|
"loss": 1.5579,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"epoch": 0.94,
|
|
"learning_rate": 2.1393006567240635e-06,
|
|
"loss": 1.5391,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"epoch": 0.95,
|
|
"learning_rate": 1.9753461464364408e-06,
|
|
"loss": 1.5478,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"epoch": 0.95,
|
|
"learning_rate": 1.8178646863250548e-06,
|
|
"loss": 1.5777,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"epoch": 0.95,
|
|
"learning_rate": 1.6668666756655572e-06,
|
|
"loss": 1.5239,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"epoch": 0.95,
|
|
"learning_rate": 1.5365200653588708e-06,
|
|
"loss": 1.4992,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"epoch": 0.96,
|
|
"learning_rate": 1.397867724769042e-06,
|
|
"loss": 1.5272,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"epoch": 0.96,
|
|
"learning_rate": 1.2657265680968589e-06,
|
|
"loss": 1.541,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"epoch": 0.96,
|
|
"learning_rate": 1.1523738102167225e-06,
|
|
"loss": 1.5219,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"epoch": 0.97,
|
|
"learning_rate": 1.044308247886483e-06,
|
|
"loss": 1.5524,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"epoch": 0.97,
|
|
"learning_rate": 9.30443453495422e-07,
|
|
"loss": 1.5508,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"epoch": 0.97,
|
|
"learning_rate": 8.231207093463699e-07,
|
|
"loss": 1.5758,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"epoch": 0.97,
|
|
"learning_rate": 7.223471024881412e-07,
|
|
"loss": 1.5658,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"epoch": 0.98,
|
|
"learning_rate": 6.281292874978029e-07,
|
|
"loss": 1.5232,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"epoch": 0.98,
|
|
"learning_rate": 5.404734860412375e-07,
|
|
"loss": 1.5646,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"epoch": 0.98,
|
|
"learning_rate": 4.5938548646227154e-07,
|
|
"loss": 1.5771,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"epoch": 0.98,
|
|
"learning_rate": 3.8487064340047006e-07,
|
|
"loss": 1.5611,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"epoch": 0.99,
|
|
"learning_rate": 3.16933877437553e-07,
|
|
"loss": 1.6229,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"epoch": 0.99,
|
|
"learning_rate": 2.555796747724104e-07,
|
|
"loss": 1.5496,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"epoch": 0.99,
|
|
"learning_rate": 2.0081208692490638e-07,
|
|
"loss": 1.5312,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"epoch": 0.99,
|
|
"learning_rate": 1.5263473046833732e-07,
|
|
"loss": 1.5681,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"epoch": 1.0,
|
|
"learning_rate": 1.1105078679056747e-07,
|
|
"loss": 1.5128,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"epoch": 1.0,
|
|
"learning_rate": 7.606300188400805e-08,
|
|
"loss": 1.5764,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"epoch": 1.0,
|
|
"step": 3906,
|
|
"total_flos": 331952415375360.0,
|
|
"train_loss": 1.9416432221974707,
|
|
"train_runtime": 74872.2082,
|
|
"train_samples_per_second": 6.678,
|
|
"train_steps_per_second": 0.052
|
|
}
|
|
],
|
|
"max_steps": 3906,
|
|
"num_train_epochs": 1,
|
|
"total_flos": 331952415375360.0,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|