emilykang's picture
Training in progress, epoch 0
0a9013f verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 9.986282578875171,
"eval_steps": 500,
"global_step": 3640,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.027434842249657063,
"grad_norm": 9.328125,
"learning_rate": 0.00019999627553166294,
"loss": 2.6306,
"step": 10
},
{
"epoch": 0.05486968449931413,
"grad_norm": 5.1328125,
"learning_rate": 0.00019998510240408496,
"loss": 2.4194,
"step": 20
},
{
"epoch": 0.0823045267489712,
"grad_norm": 5.58203125,
"learning_rate": 0.0001999664814495453,
"loss": 2.336,
"step": 30
},
{
"epoch": 0.10973936899862825,
"grad_norm": 3.78515625,
"learning_rate": 0.00019994041405510705,
"loss": 2.4327,
"step": 40
},
{
"epoch": 0.13717421124828533,
"grad_norm": 3.041015625,
"learning_rate": 0.00019990690216251396,
"loss": 2.3063,
"step": 50
},
{
"epoch": 0.1646090534979424,
"grad_norm": 3.302734375,
"learning_rate": 0.0001998659482680456,
"loss": 2.3151,
"step": 60
},
{
"epoch": 0.19204389574759945,
"grad_norm": 3.869140625,
"learning_rate": 0.00019981755542233177,
"loss": 2.3566,
"step": 70
},
{
"epoch": 0.2194787379972565,
"grad_norm": 5.70703125,
"learning_rate": 0.0001997617272301248,
"loss": 2.3368,
"step": 80
},
{
"epoch": 0.24691358024691357,
"grad_norm": 4.81640625,
"learning_rate": 0.00019969846785003134,
"loss": 2.3303,
"step": 90
},
{
"epoch": 0.27434842249657065,
"grad_norm": 4.6015625,
"learning_rate": 0.00019962778199420265,
"loss": 2.4144,
"step": 100
},
{
"epoch": 0.3017832647462277,
"grad_norm": 4.52734375,
"learning_rate": 0.00019954967492798333,
"loss": 2.4014,
"step": 110
},
{
"epoch": 0.3292181069958848,
"grad_norm": 4.68359375,
"learning_rate": 0.0001994641524695193,
"loss": 2.4312,
"step": 120
},
{
"epoch": 0.35665294924554186,
"grad_norm": 3.36328125,
"learning_rate": 0.00019937122098932428,
"loss": 2.3563,
"step": 130
},
{
"epoch": 0.3840877914951989,
"grad_norm": 3.3984375,
"learning_rate": 0.0001992708874098054,
"loss": 2.351,
"step": 140
},
{
"epoch": 0.411522633744856,
"grad_norm": 3.103515625,
"learning_rate": 0.0001991631592047475,
"loss": 2.2869,
"step": 150
},
{
"epoch": 0.438957475994513,
"grad_norm": 2.904296875,
"learning_rate": 0.00019904804439875633,
"loss": 2.364,
"step": 160
},
{
"epoch": 0.4663923182441701,
"grad_norm": 4.171875,
"learning_rate": 0.00019892555156666089,
"loss": 2.362,
"step": 170
},
{
"epoch": 0.49382716049382713,
"grad_norm": 3.611328125,
"learning_rate": 0.00019879568983287467,
"loss": 2.2994,
"step": 180
},
{
"epoch": 0.5212620027434842,
"grad_norm": 2.470703125,
"learning_rate": 0.00019865846887071596,
"loss": 2.2469,
"step": 190
},
{
"epoch": 0.5486968449931413,
"grad_norm": 2.314453125,
"learning_rate": 0.0001985138989016874,
"loss": 2.2429,
"step": 200
},
{
"epoch": 0.5761316872427984,
"grad_norm": 2.720703125,
"learning_rate": 0.00019836199069471437,
"loss": 2.3157,
"step": 210
},
{
"epoch": 0.6035665294924554,
"grad_norm": 2.998046875,
"learning_rate": 0.00019820275556534304,
"loss": 2.2214,
"step": 220
},
{
"epoch": 0.6310013717421125,
"grad_norm": 3.96484375,
"learning_rate": 0.00019803620537489736,
"loss": 2.3018,
"step": 230
},
{
"epoch": 0.6584362139917695,
"grad_norm": 2.982421875,
"learning_rate": 0.00019786235252959553,
"loss": 2.2603,
"step": 240
},
{
"epoch": 0.6858710562414266,
"grad_norm": 2.01953125,
"learning_rate": 0.00019768120997962592,
"loss": 2.3007,
"step": 250
},
{
"epoch": 0.7133058984910837,
"grad_norm": 2.552734375,
"learning_rate": 0.00019749279121818235,
"loss": 2.281,
"step": 260
},
{
"epoch": 0.7407407407407407,
"grad_norm": 2.98046875,
"learning_rate": 0.00019729711028045909,
"loss": 2.2611,
"step": 270
},
{
"epoch": 0.7681755829903978,
"grad_norm": 2.716796875,
"learning_rate": 0.0001970941817426052,
"loss": 2.1961,
"step": 280
},
{
"epoch": 0.7956104252400549,
"grad_norm": 2.318359375,
"learning_rate": 0.00019688402072063903,
"loss": 2.2652,
"step": 290
},
{
"epoch": 0.823045267489712,
"grad_norm": 2.53515625,
"learning_rate": 0.00019666664286932198,
"loss": 2.1895,
"step": 300
},
{
"epoch": 0.850480109739369,
"grad_norm": 2.451171875,
"learning_rate": 0.0001964420643809925,
"loss": 2.252,
"step": 310
},
{
"epoch": 0.877914951989026,
"grad_norm": 1.8544921875,
"learning_rate": 0.00019621030198436006,
"loss": 2.1616,
"step": 320
},
{
"epoch": 0.9053497942386831,
"grad_norm": 2.611328125,
"learning_rate": 0.00019597137294325877,
"loss": 2.1698,
"step": 330
},
{
"epoch": 0.9327846364883402,
"grad_norm": 2.349609375,
"learning_rate": 0.0001957252950553616,
"loss": 2.2043,
"step": 340
},
{
"epoch": 0.9602194787379973,
"grad_norm": 2.169921875,
"learning_rate": 0.00019547208665085457,
"loss": 2.1506,
"step": 350
},
{
"epoch": 0.9876543209876543,
"grad_norm": 1.8349609375,
"learning_rate": 0.00019521176659107142,
"loss": 2.1987,
"step": 360
},
{
"epoch": 1.0150891632373114,
"grad_norm": 1.9765625,
"learning_rate": 0.00019494435426708855,
"loss": 2.1909,
"step": 370
},
{
"epoch": 1.0425240054869684,
"grad_norm": 1.65234375,
"learning_rate": 0.0001946698695982806,
"loss": 2.1928,
"step": 380
},
{
"epoch": 1.0699588477366255,
"grad_norm": 1.677734375,
"learning_rate": 0.00019438833303083678,
"loss": 2.1761,
"step": 390
},
{
"epoch": 1.0973936899862826,
"grad_norm": 1.94140625,
"learning_rate": 0.00019409976553623766,
"loss": 2.1634,
"step": 400
},
{
"epoch": 1.1248285322359397,
"grad_norm": 1.8623046875,
"learning_rate": 0.00019380418860969322,
"loss": 2.2044,
"step": 410
},
{
"epoch": 1.1522633744855968,
"grad_norm": 1.7763671875,
"learning_rate": 0.0001935016242685415,
"loss": 2.1264,
"step": 420
},
{
"epoch": 1.1796982167352539,
"grad_norm": 2.4609375,
"learning_rate": 0.0001931920950506087,
"loss": 2.1819,
"step": 430
},
{
"epoch": 1.2071330589849107,
"grad_norm": 2.990234375,
"learning_rate": 0.00019287562401253022,
"loss": 2.1799,
"step": 440
},
{
"epoch": 1.2345679012345678,
"grad_norm": 4.86328125,
"learning_rate": 0.00019255223472803334,
"loss": 2.1497,
"step": 450
},
{
"epoch": 1.262002743484225,
"grad_norm": 2.998046875,
"learning_rate": 0.00019222195128618106,
"loss": 2.0783,
"step": 460
},
{
"epoch": 1.289437585733882,
"grad_norm": 2.033203125,
"learning_rate": 0.00019188479828957772,
"loss": 2.1195,
"step": 470
},
{
"epoch": 1.316872427983539,
"grad_norm": 1.9560546875,
"learning_rate": 0.00019154080085253666,
"loss": 2.0549,
"step": 480
},
{
"epoch": 1.3443072702331962,
"grad_norm": 2.150390625,
"learning_rate": 0.00019118998459920902,
"loss": 2.2041,
"step": 490
},
{
"epoch": 1.3717421124828533,
"grad_norm": 1.9931640625,
"learning_rate": 0.0001908323756616754,
"loss": 2.1735,
"step": 500
},
{
"epoch": 1.3991769547325104,
"grad_norm": 1.732421875,
"learning_rate": 0.0001904680006779991,
"loss": 2.1329,
"step": 510
},
{
"epoch": 1.4266117969821672,
"grad_norm": 1.703125,
"learning_rate": 0.0001900968867902419,
"loss": 2.075,
"step": 520
},
{
"epoch": 1.4540466392318243,
"grad_norm": 2.724609375,
"learning_rate": 0.00018971906164244232,
"loss": 2.1452,
"step": 530
},
{
"epoch": 1.4814814814814814,
"grad_norm": 3.53125,
"learning_rate": 0.00018933455337855632,
"loss": 2.081,
"step": 540
},
{
"epoch": 1.5089163237311385,
"grad_norm": 2.15234375,
"learning_rate": 0.000188943390640361,
"loss": 2.1311,
"step": 550
},
{
"epoch": 1.5363511659807956,
"grad_norm": 2.5078125,
"learning_rate": 0.000188545602565321,
"loss": 2.1465,
"step": 560
},
{
"epoch": 1.5637860082304527,
"grad_norm": 2.421875,
"learning_rate": 0.00018814121878441814,
"loss": 2.242,
"step": 570
},
{
"epoch": 1.5912208504801097,
"grad_norm": 2.095703125,
"learning_rate": 0.0001877302694199442,
"loss": 2.1339,
"step": 580
},
{
"epoch": 1.6186556927297668,
"grad_norm": 1.5791015625,
"learning_rate": 0.00018731278508325708,
"loss": 2.1318,
"step": 590
},
{
"epoch": 1.646090534979424,
"grad_norm": 1.8525390625,
"learning_rate": 0.00018688879687250067,
"loss": 2.108,
"step": 600
},
{
"epoch": 1.673525377229081,
"grad_norm": 1.310546875,
"learning_rate": 0.00018645833637028825,
"loss": 2.2039,
"step": 610
},
{
"epoch": 1.700960219478738,
"grad_norm": 1.50390625,
"learning_rate": 0.0001860214356413501,
"loss": 2.1096,
"step": 620
},
{
"epoch": 1.7283950617283952,
"grad_norm": 1.6025390625,
"learning_rate": 0.00018557812723014476,
"loss": 2.0806,
"step": 630
},
{
"epoch": 1.7558299039780523,
"grad_norm": 2.197265625,
"learning_rate": 0.00018512844415843514,
"loss": 2.0545,
"step": 640
},
{
"epoch": 1.7832647462277091,
"grad_norm": 1.8056640625,
"learning_rate": 0.00018467241992282843,
"loss": 2.0552,
"step": 650
},
{
"epoch": 1.8106995884773662,
"grad_norm": 1.40234375,
"learning_rate": 0.00018421008849228118,
"loss": 2.0906,
"step": 660
},
{
"epoch": 1.8381344307270233,
"grad_norm": 1.7080078125,
"learning_rate": 0.0001837414843055689,
"loss": 2.0512,
"step": 670
},
{
"epoch": 1.8655692729766804,
"grad_norm": 1.6162109375,
"learning_rate": 0.00018326664226872065,
"loss": 2.0945,
"step": 680
},
{
"epoch": 1.8930041152263375,
"grad_norm": 1.603515625,
"learning_rate": 0.0001827855977524191,
"loss": 2.0553,
"step": 690
},
{
"epoch": 1.9204389574759944,
"grad_norm": 1.5771484375,
"learning_rate": 0.00018229838658936564,
"loss": 2.0876,
"step": 700
},
{
"epoch": 1.9478737997256514,
"grad_norm": 1.400390625,
"learning_rate": 0.0001818050450716113,
"loss": 2.0565,
"step": 710
},
{
"epoch": 1.9753086419753085,
"grad_norm": 2.265625,
"learning_rate": 0.00018130560994785325,
"loss": 2.0883,
"step": 720
},
{
"epoch": 2.0027434842249656,
"grad_norm": 3.23046875,
"learning_rate": 0.00018080011842069765,
"loss": 2.0904,
"step": 730
},
{
"epoch": 2.0301783264746227,
"grad_norm": 1.611328125,
"learning_rate": 0.00018028860814388827,
"loss": 1.9926,
"step": 740
},
{
"epoch": 2.05761316872428,
"grad_norm": 1.638671875,
"learning_rate": 0.00017977111721950164,
"loss": 1.9994,
"step": 750
},
{
"epoch": 2.085048010973937,
"grad_norm": 1.7724609375,
"learning_rate": 0.00017924768419510904,
"loss": 2.0709,
"step": 760
},
{
"epoch": 2.112482853223594,
"grad_norm": 1.9208984375,
"learning_rate": 0.00017871834806090501,
"loss": 1.9618,
"step": 770
},
{
"epoch": 2.139917695473251,
"grad_norm": 2.603515625,
"learning_rate": 0.000178183148246803,
"loss": 1.9531,
"step": 780
},
{
"epoch": 2.167352537722908,
"grad_norm": 2.236328125,
"learning_rate": 0.0001776421246194982,
"loss": 2.0776,
"step": 790
},
{
"epoch": 2.1947873799725652,
"grad_norm": 2.79296875,
"learning_rate": 0.00017709531747949796,
"loss": 2.0563,
"step": 800
},
{
"epoch": 2.2222222222222223,
"grad_norm": 2.55078125,
"learning_rate": 0.00017654276755811997,
"loss": 2.052,
"step": 810
},
{
"epoch": 2.2496570644718794,
"grad_norm": 2.2421875,
"learning_rate": 0.0001759845160144579,
"loss": 2.0051,
"step": 820
},
{
"epoch": 2.2770919067215365,
"grad_norm": 2.35546875,
"learning_rate": 0.00017542060443231572,
"loss": 2.0448,
"step": 830
},
{
"epoch": 2.3045267489711936,
"grad_norm": 1.953125,
"learning_rate": 0.00017485107481711012,
"loss": 2.068,
"step": 840
},
{
"epoch": 2.3319615912208507,
"grad_norm": 1.9912109375,
"learning_rate": 0.00017427596959274143,
"loss": 2.0173,
"step": 850
},
{
"epoch": 2.3593964334705078,
"grad_norm": 1.841796875,
"learning_rate": 0.00017369533159843369,
"loss": 1.9539,
"step": 860
},
{
"epoch": 2.386831275720165,
"grad_norm": 1.9970703125,
"learning_rate": 0.00017310920408554332,
"loss": 1.9894,
"step": 870
},
{
"epoch": 2.4142661179698215,
"grad_norm": 1.80078125,
"learning_rate": 0.00017251763071433765,
"loss": 2.0438,
"step": 880
},
{
"epoch": 2.4417009602194786,
"grad_norm": 1.8701171875,
"learning_rate": 0.00017192065555074245,
"loss": 2.0079,
"step": 890
},
{
"epoch": 2.4691358024691357,
"grad_norm": 1.9775390625,
"learning_rate": 0.00017131832306305965,
"loss": 2.0738,
"step": 900
},
{
"epoch": 2.4965706447187928,
"grad_norm": 2.087890625,
"learning_rate": 0.00017071067811865476,
"loss": 2.0805,
"step": 910
},
{
"epoch": 2.52400548696845,
"grad_norm": 2.212890625,
"learning_rate": 0.00017009776598061495,
"loss": 2.0563,
"step": 920
},
{
"epoch": 2.551440329218107,
"grad_norm": 2.291015625,
"learning_rate": 0.00016947963230437725,
"loss": 2.0289,
"step": 930
},
{
"epoch": 2.578875171467764,
"grad_norm": 2.0625,
"learning_rate": 0.0001688563231343277,
"loss": 2.0648,
"step": 940
},
{
"epoch": 2.606310013717421,
"grad_norm": 2.197265625,
"learning_rate": 0.00016822788490037177,
"loss": 1.9541,
"step": 950
},
{
"epoch": 2.633744855967078,
"grad_norm": 1.5,
"learning_rate": 0.00016759436441447545,
"loss": 2.0415,
"step": 960
},
{
"epoch": 2.6611796982167353,
"grad_norm": 1.7353515625,
"learning_rate": 0.00016695580886717858,
"loss": 2.0242,
"step": 970
},
{
"epoch": 2.6886145404663924,
"grad_norm": 2.115234375,
"learning_rate": 0.00016631226582407952,
"loss": 2.0,
"step": 980
},
{
"epoch": 2.7160493827160495,
"grad_norm": 1.78515625,
"learning_rate": 0.00016566378322229204,
"loss": 2.0559,
"step": 990
},
{
"epoch": 2.7434842249657065,
"grad_norm": 1.6708984375,
"learning_rate": 0.00016501040936687443,
"loss": 2.0658,
"step": 1000
},
{
"epoch": 2.7709190672153636,
"grad_norm": 2.06640625,
"learning_rate": 0.00016435219292723147,
"loss": 2.0381,
"step": 1010
},
{
"epoch": 2.7983539094650207,
"grad_norm": 1.99609375,
"learning_rate": 0.00016368918293348892,
"loss": 1.9942,
"step": 1020
},
{
"epoch": 2.825788751714678,
"grad_norm": 2.3125,
"learning_rate": 0.00016302142877284138,
"loss": 2.0459,
"step": 1030
},
{
"epoch": 2.8532235939643344,
"grad_norm": 2.109375,
"learning_rate": 0.00016234898018587337,
"loss": 1.9964,
"step": 1040
},
{
"epoch": 2.8806584362139915,
"grad_norm": 1.828125,
"learning_rate": 0.00016167188726285434,
"loss": 1.9702,
"step": 1050
},
{
"epoch": 2.9080932784636486,
"grad_norm": 1.609375,
"learning_rate": 0.00016099020044000727,
"loss": 1.971,
"step": 1060
},
{
"epoch": 2.9355281207133057,
"grad_norm": 1.662109375,
"learning_rate": 0.00016030397049575203,
"loss": 2.0445,
"step": 1070
},
{
"epoch": 2.962962962962963,
"grad_norm": 2.14453125,
"learning_rate": 0.00015961324854692254,
"loss": 1.9905,
"step": 1080
},
{
"epoch": 2.99039780521262,
"grad_norm": 1.71875,
"learning_rate": 0.00015891808604495938,
"loss": 2.0048,
"step": 1090
},
{
"epoch": 3.017832647462277,
"grad_norm": 1.599609375,
"learning_rate": 0.00015821853477207708,
"loss": 2.0107,
"step": 1100
},
{
"epoch": 3.045267489711934,
"grad_norm": 2.4765625,
"learning_rate": 0.00015751464683740697,
"loss": 1.9425,
"step": 1110
},
{
"epoch": 3.072702331961591,
"grad_norm": 3.009765625,
"learning_rate": 0.00015680647467311557,
"loss": 1.9891,
"step": 1120
},
{
"epoch": 3.1001371742112482,
"grad_norm": 2.1328125,
"learning_rate": 0.00015609407103049896,
"loss": 1.9283,
"step": 1130
},
{
"epoch": 3.1275720164609053,
"grad_norm": 3.130859375,
"learning_rate": 0.0001553774889760533,
"loss": 1.9353,
"step": 1140
},
{
"epoch": 3.1550068587105624,
"grad_norm": 2.798828125,
"learning_rate": 0.0001546567818875221,
"loss": 1.9945,
"step": 1150
},
{
"epoch": 3.1824417009602195,
"grad_norm": 2.287109375,
"learning_rate": 0.00015393200344991995,
"loss": 1.9199,
"step": 1160
},
{
"epoch": 3.2098765432098766,
"grad_norm": 2.748046875,
"learning_rate": 0.00015320320765153367,
"loss": 1.9415,
"step": 1170
},
{
"epoch": 3.2373113854595337,
"grad_norm": 2.10546875,
"learning_rate": 0.0001524704487799008,
"loss": 1.9417,
"step": 1180
},
{
"epoch": 3.2647462277091908,
"grad_norm": 2.1015625,
"learning_rate": 0.00015173378141776568,
"loss": 1.9477,
"step": 1190
},
{
"epoch": 3.292181069958848,
"grad_norm": 1.8896484375,
"learning_rate": 0.0001509932604390136,
"loss": 1.8957,
"step": 1200
},
{
"epoch": 3.319615912208505,
"grad_norm": 2.36328125,
"learning_rate": 0.0001502489410045833,
"loss": 1.9313,
"step": 1210
},
{
"epoch": 3.347050754458162,
"grad_norm": 2.107421875,
"learning_rate": 0.00014950087855835815,
"loss": 1.902,
"step": 1220
},
{
"epoch": 3.374485596707819,
"grad_norm": 1.919921875,
"learning_rate": 0.000148749128823036,
"loss": 1.8492,
"step": 1230
},
{
"epoch": 3.401920438957476,
"grad_norm": 2.07421875,
"learning_rate": 0.00014799374779597867,
"loss": 1.9576,
"step": 1240
},
{
"epoch": 3.4293552812071333,
"grad_norm": 2.115234375,
"learning_rate": 0.00014723479174504037,
"loss": 1.9472,
"step": 1250
},
{
"epoch": 3.45679012345679,
"grad_norm": 2.748046875,
"learning_rate": 0.00014647231720437686,
"loss": 1.969,
"step": 1260
},
{
"epoch": 3.484224965706447,
"grad_norm": 2.20703125,
"learning_rate": 0.0001457063809702338,
"loss": 1.9607,
"step": 1270
},
{
"epoch": 3.511659807956104,
"grad_norm": 1.8447265625,
"learning_rate": 0.00014493704009671613,
"loss": 1.9347,
"step": 1280
},
{
"epoch": 3.539094650205761,
"grad_norm": 1.857421875,
"learning_rate": 0.00014416435189153846,
"loss": 1.9848,
"step": 1290
},
{
"epoch": 3.5665294924554183,
"grad_norm": 2.009765625,
"learning_rate": 0.00014338837391175582,
"loss": 1.9784,
"step": 1300
},
{
"epoch": 3.5939643347050754,
"grad_norm": 2.373046875,
"learning_rate": 0.00014260916395947656,
"loss": 1.9356,
"step": 1310
},
{
"epoch": 3.6213991769547325,
"grad_norm": 2.474609375,
"learning_rate": 0.0001418267800775565,
"loss": 1.9703,
"step": 1320
},
{
"epoch": 3.6488340192043895,
"grad_norm": 1.7783203125,
"learning_rate": 0.0001410412805452757,
"loss": 1.9149,
"step": 1330
},
{
"epoch": 3.6762688614540466,
"grad_norm": 2.7421875,
"learning_rate": 0.00014025272387399674,
"loss": 1.948,
"step": 1340
},
{
"epoch": 3.7037037037037037,
"grad_norm": 2.64453125,
"learning_rate": 0.00013946116880280681,
"loss": 1.9427,
"step": 1350
},
{
"epoch": 3.731138545953361,
"grad_norm": 3.169921875,
"learning_rate": 0.0001386666742941419,
"loss": 1.8966,
"step": 1360
},
{
"epoch": 3.758573388203018,
"grad_norm": 2.00390625,
"learning_rate": 0.00013786929952939477,
"loss": 1.9682,
"step": 1370
},
{
"epoch": 3.786008230452675,
"grad_norm": 1.7138671875,
"learning_rate": 0.00013706910390450677,
"loss": 1.9255,
"step": 1380
},
{
"epoch": 3.813443072702332,
"grad_norm": 1.9404296875,
"learning_rate": 0.0001362661470255432,
"loss": 1.8883,
"step": 1390
},
{
"epoch": 3.840877914951989,
"grad_norm": 2.662109375,
"learning_rate": 0.00013546048870425356,
"loss": 1.9409,
"step": 1400
},
{
"epoch": 3.8683127572016462,
"grad_norm": 1.763671875,
"learning_rate": 0.000134652188953616,
"loss": 1.9766,
"step": 1410
},
{
"epoch": 3.895747599451303,
"grad_norm": 1.7626953125,
"learning_rate": 0.00013384130798336705,
"loss": 1.9428,
"step": 1420
},
{
"epoch": 3.92318244170096,
"grad_norm": 1.8583984375,
"learning_rate": 0.00013302790619551674,
"loss": 1.9664,
"step": 1430
},
{
"epoch": 3.950617283950617,
"grad_norm": 1.7919921875,
"learning_rate": 0.00013221204417984908,
"loss": 1.9387,
"step": 1440
},
{
"epoch": 3.978052126200274,
"grad_norm": 2.16015625,
"learning_rate": 0.000131393782709409,
"loss": 1.8872,
"step": 1450
},
{
"epoch": 4.005486968449931,
"grad_norm": 1.833984375,
"learning_rate": 0.0001305731827359753,
"loss": 1.9299,
"step": 1460
},
{
"epoch": 4.032921810699588,
"grad_norm": 2.3359375,
"learning_rate": 0.00012975030538552032,
"loss": 1.8399,
"step": 1470
},
{
"epoch": 4.060356652949245,
"grad_norm": 1.4580078125,
"learning_rate": 0.00012892521195365678,
"loss": 1.9137,
"step": 1480
},
{
"epoch": 4.0877914951989025,
"grad_norm": 1.7353515625,
"learning_rate": 0.00012809796390107195,
"loss": 1.8806,
"step": 1490
},
{
"epoch": 4.11522633744856,
"grad_norm": 2.189453125,
"learning_rate": 0.00012726862284894938,
"loss": 1.9019,
"step": 1500
},
{
"epoch": 4.142661179698217,
"grad_norm": 1.490234375,
"learning_rate": 0.0001264372505743789,
"loss": 1.8454,
"step": 1510
},
{
"epoch": 4.170096021947874,
"grad_norm": 1.6123046875,
"learning_rate": 0.0001256039090057547,
"loss": 1.9057,
"step": 1520
},
{
"epoch": 4.197530864197531,
"grad_norm": 1.3447265625,
"learning_rate": 0.0001247686602181626,
"loss": 1.8994,
"step": 1530
},
{
"epoch": 4.224965706447188,
"grad_norm": 1.7265625,
"learning_rate": 0.0001239315664287558,
"loss": 1.8779,
"step": 1540
},
{
"epoch": 4.252400548696845,
"grad_norm": 2.07421875,
"learning_rate": 0.0001230926899921206,
"loss": 1.8386,
"step": 1550
},
{
"epoch": 4.279835390946502,
"grad_norm": 1.7724609375,
"learning_rate": 0.00012225209339563145,
"loss": 1.8646,
"step": 1560
},
{
"epoch": 4.307270233196159,
"grad_norm": 1.8017578125,
"learning_rate": 0.00012140983925479662,
"loss": 1.8488,
"step": 1570
},
{
"epoch": 4.334705075445816,
"grad_norm": 2.1171875,
"learning_rate": 0.00012056599030859366,
"loss": 1.8531,
"step": 1580
},
{
"epoch": 4.362139917695473,
"grad_norm": 1.9462890625,
"learning_rate": 0.00011972060941479621,
"loss": 1.8437,
"step": 1590
},
{
"epoch": 4.3895747599451305,
"grad_norm": 1.5908203125,
"learning_rate": 0.00011887375954529168,
"loss": 1.8201,
"step": 1600
},
{
"epoch": 4.4170096021947876,
"grad_norm": 5.125,
"learning_rate": 0.0001180255037813906,
"loss": 1.865,
"step": 1610
},
{
"epoch": 4.444444444444445,
"grad_norm": 1.919921875,
"learning_rate": 0.00011717590530912763,
"loss": 1.8605,
"step": 1620
},
{
"epoch": 4.471879286694102,
"grad_norm": 1.666015625,
"learning_rate": 0.00011632502741455496,
"loss": 1.8294,
"step": 1630
},
{
"epoch": 4.499314128943759,
"grad_norm": 1.6572265625,
"learning_rate": 0.00011547293347902812,
"loss": 1.8254,
"step": 1640
},
{
"epoch": 4.526748971193416,
"grad_norm": 1.4775390625,
"learning_rate": 0.00011461968697448485,
"loss": 1.8534,
"step": 1650
},
{
"epoch": 4.554183813443073,
"grad_norm": 1.791015625,
"learning_rate": 0.00011376535145871684,
"loss": 1.8151,
"step": 1660
},
{
"epoch": 4.58161865569273,
"grad_norm": 1.9013671875,
"learning_rate": 0.00011290999057063569,
"loss": 1.875,
"step": 1670
},
{
"epoch": 4.609053497942387,
"grad_norm": 2.322265625,
"learning_rate": 0.0001120536680255323,
"loss": 1.9154,
"step": 1680
},
{
"epoch": 4.636488340192044,
"grad_norm": 1.814453125,
"learning_rate": 0.00011119644761033078,
"loss": 1.898,
"step": 1690
},
{
"epoch": 4.663923182441701,
"grad_norm": 2.25390625,
"learning_rate": 0.00011033839317883701,
"loss": 1.852,
"step": 1700
},
{
"epoch": 4.6913580246913575,
"grad_norm": 2.240234375,
"learning_rate": 0.00010947956864698223,
"loss": 1.8394,
"step": 1710
},
{
"epoch": 4.7187928669410155,
"grad_norm": 2.544921875,
"learning_rate": 0.00010862003798806196,
"loss": 1.84,
"step": 1720
},
{
"epoch": 4.746227709190672,
"grad_norm": 1.7255859375,
"learning_rate": 0.00010775986522797063,
"loss": 1.8682,
"step": 1730
},
{
"epoch": 4.77366255144033,
"grad_norm": 2.705078125,
"learning_rate": 0.00010689911444043248,
"loss": 1.8197,
"step": 1740
},
{
"epoch": 4.801097393689986,
"grad_norm": 1.7275390625,
"learning_rate": 0.00010603784974222861,
"loss": 1.868,
"step": 1750
},
{
"epoch": 4.828532235939643,
"grad_norm": 1.7900390625,
"learning_rate": 0.00010517613528842097,
"loss": 1.8828,
"step": 1760
},
{
"epoch": 4.8559670781893,
"grad_norm": 1.603515625,
"learning_rate": 0.00010431403526757347,
"loss": 1.8683,
"step": 1770
},
{
"epoch": 4.883401920438957,
"grad_norm": 1.958984375,
"learning_rate": 0.00010345161389697082,
"loss": 1.8725,
"step": 1780
},
{
"epoch": 4.910836762688614,
"grad_norm": 1.857421875,
"learning_rate": 0.00010258893541783476,
"loss": 1.8893,
"step": 1790
},
{
"epoch": 4.938271604938271,
"grad_norm": 1.755859375,
"learning_rate": 0.00010172606409053886,
"loss": 1.892,
"step": 1800
},
{
"epoch": 4.965706447187928,
"grad_norm": 1.76171875,
"learning_rate": 0.0001008630641898219,
"loss": 1.8952,
"step": 1810
},
{
"epoch": 4.9931412894375855,
"grad_norm": 1.767578125,
"learning_rate": 0.0001,
"loss": 1.8623,
"step": 1820
},
{
"epoch": 5.020576131687243,
"grad_norm": 2.0234375,
"learning_rate": 9.913693581017812e-05,
"loss": 1.7838,
"step": 1830
},
{
"epoch": 5.0480109739369,
"grad_norm": 1.9765625,
"learning_rate": 9.827393590946116e-05,
"loss": 1.7935,
"step": 1840
},
{
"epoch": 5.075445816186557,
"grad_norm": 2.12109375,
"learning_rate": 9.741106458216528e-05,
"loss": 1.838,
"step": 1850
},
{
"epoch": 5.102880658436214,
"grad_norm": 1.63671875,
"learning_rate": 9.654838610302923e-05,
"loss": 1.8097,
"step": 1860
},
{
"epoch": 5.130315500685871,
"grad_norm": 2.62109375,
"learning_rate": 9.568596473242654e-05,
"loss": 1.7773,
"step": 1870
},
{
"epoch": 5.157750342935528,
"grad_norm": 2.1015625,
"learning_rate": 9.482386471157904e-05,
"loss": 1.8083,
"step": 1880
},
{
"epoch": 5.185185185185185,
"grad_norm": 1.8603515625,
"learning_rate": 9.396215025777139e-05,
"loss": 1.7376,
"step": 1890
},
{
"epoch": 5.212620027434842,
"grad_norm": 1.7890625,
"learning_rate": 9.31008855595675e-05,
"loss": 1.8674,
"step": 1900
},
{
"epoch": 5.240054869684499,
"grad_norm": 2.1796875,
"learning_rate": 9.224013477202939e-05,
"loss": 1.8239,
"step": 1910
},
{
"epoch": 5.267489711934156,
"grad_norm": 2.208984375,
"learning_rate": 9.137996201193805e-05,
"loss": 1.811,
"step": 1920
},
{
"epoch": 5.2949245541838135,
"grad_norm": 2.001953125,
"learning_rate": 9.052043135301779e-05,
"loss": 1.7938,
"step": 1930
},
{
"epoch": 5.322359396433471,
"grad_norm": 2.083984375,
"learning_rate": 8.9661606821163e-05,
"loss": 1.8577,
"step": 1940
},
{
"epoch": 5.349794238683128,
"grad_norm": 1.939453125,
"learning_rate": 8.880355238966923e-05,
"loss": 1.8207,
"step": 1950
},
{
"epoch": 5.377229080932785,
"grad_norm": 1.873046875,
"learning_rate": 8.79463319744677e-05,
"loss": 1.7565,
"step": 1960
},
{
"epoch": 5.404663923182442,
"grad_norm": 1.646484375,
"learning_rate": 8.709000942936433e-05,
"loss": 1.8572,
"step": 1970
},
{
"epoch": 5.432098765432099,
"grad_norm": 1.5400390625,
"learning_rate": 8.62346485412832e-05,
"loss": 1.8169,
"step": 1980
},
{
"epoch": 5.459533607681756,
"grad_norm": 1.8388671875,
"learning_rate": 8.538031302551522e-05,
"loss": 1.8642,
"step": 1990
},
{
"epoch": 5.486968449931413,
"grad_norm": 2.240234375,
"learning_rate": 8.452706652097186e-05,
"loss": 1.7803,
"step": 2000
},
{
"epoch": 5.51440329218107,
"grad_norm": 1.8984375,
"learning_rate": 8.367497258544507e-05,
"loss": 1.7859,
"step": 2010
},
{
"epoch": 5.541838134430727,
"grad_norm": 1.880859375,
"learning_rate": 8.282409469087239e-05,
"loss": 1.8381,
"step": 2020
},
{
"epoch": 5.569272976680384,
"grad_norm": 1.865234375,
"learning_rate": 8.197449621860943e-05,
"loss": 1.7921,
"step": 2030
},
{
"epoch": 5.596707818930041,
"grad_norm": 1.671875,
"learning_rate": 8.112624045470835e-05,
"loss": 1.781,
"step": 2040
},
{
"epoch": 5.6241426611796985,
"grad_norm": 1.7802734375,
"learning_rate": 8.027939058520381e-05,
"loss": 1.7988,
"step": 2050
},
{
"epoch": 5.651577503429356,
"grad_norm": 1.72265625,
"learning_rate": 7.943400969140635e-05,
"loss": 1.7888,
"step": 2060
},
{
"epoch": 5.679012345679013,
"grad_norm": 1.8701171875,
"learning_rate": 7.85901607452034e-05,
"loss": 1.7995,
"step": 2070
},
{
"epoch": 5.70644718792867,
"grad_norm": 1.9873046875,
"learning_rate": 7.774790660436858e-05,
"loss": 1.7753,
"step": 2080
},
{
"epoch": 5.733882030178327,
"grad_norm": 2.19921875,
"learning_rate": 7.690731000787948e-05,
"loss": 1.7387,
"step": 2090
},
{
"epoch": 5.761316872427983,
"grad_norm": 1.85546875,
"learning_rate": 7.606843357124426e-05,
"loss": 1.8478,
"step": 2100
},
{
"epoch": 5.788751714677641,
"grad_norm": 1.8662109375,
"learning_rate": 7.52313397818374e-05,
"loss": 1.8373,
"step": 2110
},
{
"epoch": 5.816186556927297,
"grad_norm": 1.8505859375,
"learning_rate": 7.43960909942453e-05,
"loss": 1.8703,
"step": 2120
},
{
"epoch": 5.843621399176955,
"grad_norm": 1.591796875,
"learning_rate": 7.356274942562111e-05,
"loss": 1.7647,
"step": 2130
},
{
"epoch": 5.871056241426611,
"grad_norm": 1.8681640625,
"learning_rate": 7.273137715105063e-05,
"loss": 1.7957,
"step": 2140
},
{
"epoch": 5.8984910836762685,
"grad_norm": 1.7666015625,
"learning_rate": 7.190203609892808e-05,
"loss": 1.7988,
"step": 2150
},
{
"epoch": 5.925925925925926,
"grad_norm": 1.6123046875,
"learning_rate": 7.107478804634325e-05,
"loss": 1.7388,
"step": 2160
},
{
"epoch": 5.953360768175583,
"grad_norm": 1.7646484375,
"learning_rate": 7.024969461447972e-05,
"loss": 1.7994,
"step": 2170
},
{
"epoch": 5.98079561042524,
"grad_norm": 1.96484375,
"learning_rate": 6.942681726402473e-05,
"loss": 1.7937,
"step": 2180
},
{
"epoch": 6.008230452674897,
"grad_norm": 2.099609375,
"learning_rate": 6.8606217290591e-05,
"loss": 1.7915,
"step": 2190
},
{
"epoch": 6.035665294924554,
"grad_norm": 1.8466796875,
"learning_rate": 6.778795582015097e-05,
"loss": 1.8106,
"step": 2200
},
{
"epoch": 6.063100137174211,
"grad_norm": 1.9228515625,
"learning_rate": 6.697209380448333e-05,
"loss": 1.7836,
"step": 2210
},
{
"epoch": 6.090534979423868,
"grad_norm": 2.74609375,
"learning_rate": 6.615869201663296e-05,
"loss": 1.7202,
"step": 2220
},
{
"epoch": 6.117969821673525,
"grad_norm": 1.708984375,
"learning_rate": 6.534781104638399e-05,
"loss": 1.7432,
"step": 2230
},
{
"epoch": 6.145404663923182,
"grad_norm": 1.921875,
"learning_rate": 6.453951129574644e-05,
"loss": 1.719,
"step": 2240
},
{
"epoch": 6.172839506172839,
"grad_norm": 1.7333984375,
"learning_rate": 6.37338529744568e-05,
"loss": 1.778,
"step": 2250
},
{
"epoch": 6.2002743484224965,
"grad_norm": 1.7802734375,
"learning_rate": 6.293089609549325e-05,
"loss": 1.7294,
"step": 2260
},
{
"epoch": 6.227709190672154,
"grad_norm": 2.220703125,
"learning_rate": 6.213070047060524e-05,
"loss": 1.6875,
"step": 2270
},
{
"epoch": 6.255144032921811,
"grad_norm": 1.8193359375,
"learning_rate": 6.133332570585812e-05,
"loss": 1.8336,
"step": 2280
},
{
"epoch": 6.282578875171468,
"grad_norm": 1.9384765625,
"learning_rate": 6.05388311971932e-05,
"loss": 1.7279,
"step": 2290
},
{
"epoch": 6.310013717421125,
"grad_norm": 2.046875,
"learning_rate": 5.9747276126003257e-05,
"loss": 1.753,
"step": 2300
},
{
"epoch": 6.337448559670782,
"grad_norm": 1.7490234375,
"learning_rate": 5.8958719454724346e-05,
"loss": 1.7593,
"step": 2310
},
{
"epoch": 6.364883401920439,
"grad_norm": 1.9990234375,
"learning_rate": 5.817321992244351e-05,
"loss": 1.7361,
"step": 2320
},
{
"epoch": 6.392318244170096,
"grad_norm": 2.55078125,
"learning_rate": 5.739083604052351e-05,
"loss": 1.7527,
"step": 2330
},
{
"epoch": 6.419753086419753,
"grad_norm": 1.8408203125,
"learning_rate": 5.6611626088244194e-05,
"loss": 1.7893,
"step": 2340
},
{
"epoch": 6.44718792866941,
"grad_norm": 1.8388671875,
"learning_rate": 5.583564810846157e-05,
"loss": 1.744,
"step": 2350
},
{
"epoch": 6.474622770919067,
"grad_norm": 1.947265625,
"learning_rate": 5.506295990328385e-05,
"loss": 1.7609,
"step": 2360
},
{
"epoch": 6.502057613168724,
"grad_norm": 1.947265625,
"learning_rate": 5.429361902976624e-05,
"loss": 1.7273,
"step": 2370
},
{
"epoch": 6.5294924554183815,
"grad_norm": 1.9033203125,
"learning_rate": 5.3527682795623146e-05,
"loss": 1.7782,
"step": 2380
},
{
"epoch": 6.556927297668039,
"grad_norm": 1.75390625,
"learning_rate": 5.276520825495963e-05,
"loss": 1.7612,
"step": 2390
},
{
"epoch": 6.584362139917696,
"grad_norm": 1.8037109375,
"learning_rate": 5.200625220402139e-05,
"loss": 1.7672,
"step": 2400
},
{
"epoch": 6.611796982167353,
"grad_norm": 1.7421875,
"learning_rate": 5.1250871176964036e-05,
"loss": 1.7832,
"step": 2410
},
{
"epoch": 6.63923182441701,
"grad_norm": 1.609375,
"learning_rate": 5.0499121441641864e-05,
"loss": 1.7438,
"step": 2420
},
{
"epoch": 6.666666666666667,
"grad_norm": 1.865234375,
"learning_rate": 4.975105899541671e-05,
"loss": 1.7172,
"step": 2430
},
{
"epoch": 6.694101508916324,
"grad_norm": 1.8056640625,
"learning_rate": 4.900673956098644e-05,
"loss": 1.7476,
"step": 2440
},
{
"epoch": 6.721536351165981,
"grad_norm": 1.75390625,
"learning_rate": 4.826621858223431e-05,
"loss": 1.7547,
"step": 2450
},
{
"epoch": 6.748971193415638,
"grad_norm": 1.841796875,
"learning_rate": 4.75295512200992e-05,
"loss": 1.7363,
"step": 2460
},
{
"epoch": 6.776406035665294,
"grad_norm": 1.8349609375,
"learning_rate": 4.6796792348466356e-05,
"loss": 1.7725,
"step": 2470
},
{
"epoch": 6.803840877914952,
"grad_norm": 1.7373046875,
"learning_rate": 4.606799655008009e-05,
"loss": 1.6962,
"step": 2480
},
{
"epoch": 6.831275720164609,
"grad_norm": 2.0234375,
"learning_rate": 4.5343218112477904e-05,
"loss": 1.6918,
"step": 2490
},
{
"epoch": 6.858710562414267,
"grad_norm": 1.73828125,
"learning_rate": 4.462251102394669e-05,
"loss": 1.7336,
"step": 2500
},
{
"epoch": 6.886145404663923,
"grad_norm": 1.974609375,
"learning_rate": 4.3905928969501056e-05,
"loss": 1.7502,
"step": 2510
},
{
"epoch": 6.91358024691358,
"grad_norm": 1.8828125,
"learning_rate": 4.3193525326884435e-05,
"loss": 1.8341,
"step": 2520
},
{
"epoch": 6.941015089163237,
"grad_norm": 1.7939453125,
"learning_rate": 4.248535316259305e-05,
"loss": 1.7671,
"step": 2530
},
{
"epoch": 6.968449931412894,
"grad_norm": 1.5888671875,
"learning_rate": 4.1781465227922957e-05,
"loss": 1.7457,
"step": 2540
},
{
"epoch": 6.995884773662551,
"grad_norm": 1.7177734375,
"learning_rate": 4.108191395504064e-05,
"loss": 1.7736,
"step": 2550
},
{
"epoch": 7.023319615912208,
"grad_norm": 1.5703125,
"learning_rate": 4.038675145307747e-05,
"loss": 1.6925,
"step": 2560
},
{
"epoch": 7.050754458161865,
"grad_norm": 2.091796875,
"learning_rate": 3.9696029504247956e-05,
"loss": 1.7176,
"step": 2570
},
{
"epoch": 7.078189300411522,
"grad_norm": 1.919921875,
"learning_rate": 3.900979955999271e-05,
"loss": 1.7825,
"step": 2580
},
{
"epoch": 7.1056241426611795,
"grad_norm": 1.943359375,
"learning_rate": 3.832811273714569e-05,
"loss": 1.7257,
"step": 2590
},
{
"epoch": 7.133058984910837,
"grad_norm": 2.052734375,
"learning_rate": 3.7651019814126654e-05,
"loss": 1.7665,
"step": 2600
},
{
"epoch": 7.160493827160494,
"grad_norm": 1.6552734375,
"learning_rate": 3.697857122715865e-05,
"loss": 1.7373,
"step": 2610
},
{
"epoch": 7.187928669410151,
"grad_norm": 1.8623046875,
"learning_rate": 3.6310817066511105e-05,
"loss": 1.6965,
"step": 2620
},
{
"epoch": 7.215363511659808,
"grad_norm": 1.48828125,
"learning_rate": 3.5647807072768526e-05,
"loss": 1.7009,
"step": 2630
},
{
"epoch": 7.242798353909465,
"grad_norm": 1.5126953125,
"learning_rate": 3.498959063312558e-05,
"loss": 1.7086,
"step": 2640
},
{
"epoch": 7.270233196159122,
"grad_norm": 1.6748046875,
"learning_rate": 3.4336216777708e-05,
"loss": 1.6847,
"step": 2650
},
{
"epoch": 7.297668038408779,
"grad_norm": 1.4794921875,
"learning_rate": 3.36877341759205e-05,
"loss": 1.756,
"step": 2660
},
{
"epoch": 7.325102880658436,
"grad_norm": 1.6240234375,
"learning_rate": 3.3044191132821454e-05,
"loss": 1.6819,
"step": 2670
},
{
"epoch": 7.352537722908093,
"grad_norm": 1.623046875,
"learning_rate": 3.2405635585524565e-05,
"loss": 1.7719,
"step": 2680
},
{
"epoch": 7.37997256515775,
"grad_norm": 1.775390625,
"learning_rate": 3.177211509962826e-05,
"loss": 1.7437,
"step": 2690
},
{
"epoch": 7.407407407407407,
"grad_norm": 1.880859375,
"learning_rate": 3.114367686567228e-05,
"loss": 1.702,
"step": 2700
},
{
"epoch": 7.4348422496570645,
"grad_norm": 1.6015625,
"learning_rate": 3.052036769562276e-05,
"loss": 1.6124,
"step": 2710
},
{
"epoch": 7.462277091906722,
"grad_norm": 1.8525390625,
"learning_rate": 2.9902234019385057e-05,
"loss": 1.6915,
"step": 2720
},
{
"epoch": 7.489711934156379,
"grad_norm": 1.998046875,
"learning_rate": 2.9289321881345254e-05,
"loss": 1.7637,
"step": 2730
},
{
"epoch": 7.517146776406036,
"grad_norm": 1.744140625,
"learning_rate": 2.8681676936940393e-05,
"loss": 1.7212,
"step": 2740
},
{
"epoch": 7.544581618655693,
"grad_norm": 1.486328125,
"learning_rate": 2.8079344449257572e-05,
"loss": 1.7415,
"step": 2750
},
{
"epoch": 7.57201646090535,
"grad_norm": 2.044921875,
"learning_rate": 2.7482369285662378e-05,
"loss": 1.7262,
"step": 2760
},
{
"epoch": 7.599451303155007,
"grad_norm": 1.6982421875,
"learning_rate": 2.6890795914456678e-05,
"loss": 1.6766,
"step": 2770
},
{
"epoch": 7.626886145404664,
"grad_norm": 1.8671875,
"learning_rate": 2.6304668401566335e-05,
"loss": 1.7522,
"step": 2780
},
{
"epoch": 7.654320987654321,
"grad_norm": 1.8017578125,
"learning_rate": 2.572403040725855e-05,
"loss": 1.7095,
"step": 2790
},
{
"epoch": 7.681755829903978,
"grad_norm": 2.005859375,
"learning_rate": 2.514892518288988e-05,
"loss": 1.7196,
"step": 2800
},
{
"epoch": 7.709190672153635,
"grad_norm": 1.7734375,
"learning_rate": 2.4579395567684283e-05,
"loss": 1.7174,
"step": 2810
},
{
"epoch": 7.7366255144032925,
"grad_norm": 2.1015625,
"learning_rate": 2.401548398554213e-05,
"loss": 1.745,
"step": 2820
},
{
"epoch": 7.76406035665295,
"grad_norm": 1.7236328125,
"learning_rate": 2.345723244188006e-05,
"loss": 1.7127,
"step": 2830
},
{
"epoch": 7.791495198902607,
"grad_norm": 2.4296875,
"learning_rate": 2.290468252050204e-05,
"loss": 1.6945,
"step": 2840
},
{
"epoch": 7.818930041152264,
"grad_norm": 1.67578125,
"learning_rate": 2.2357875380501836e-05,
"loss": 1.7206,
"step": 2850
},
{
"epoch": 7.84636488340192,
"grad_norm": 2.359375,
"learning_rate": 2.181685175319702e-05,
"loss": 1.683,
"step": 2860
},
{
"epoch": 7.873799725651578,
"grad_norm": 1.7236328125,
"learning_rate": 2.1281651939094992e-05,
"loss": 1.7218,
"step": 2870
},
{
"epoch": 7.901234567901234,
"grad_norm": 1.82421875,
"learning_rate": 2.0752315804890977e-05,
"loss": 1.7274,
"step": 2880
},
{
"epoch": 7.928669410150892,
"grad_norm": 3.5078125,
"learning_rate": 2.0228882780498404e-05,
"loss": 1.6874,
"step": 2890
},
{
"epoch": 7.956104252400548,
"grad_norm": 2.08984375,
"learning_rate": 1.971139185611176e-05,
"loss": 1.7064,
"step": 2900
},
{
"epoch": 7.983539094650205,
"grad_norm": 2.240234375,
"learning_rate": 1.919988157930236e-05,
"loss": 1.6922,
"step": 2910
},
{
"epoch": 8.010973936899862,
"grad_norm": 2.25,
"learning_rate": 1.8694390052146737e-05,
"loss": 1.73,
"step": 2920
},
{
"epoch": 8.03840877914952,
"grad_norm": 1.62890625,
"learning_rate": 1.819495492838872e-05,
"loss": 1.6912,
"step": 2930
},
{
"epoch": 8.065843621399177,
"grad_norm": 1.755859375,
"learning_rate": 1.7701613410634365e-05,
"loss": 1.6858,
"step": 2940
},
{
"epoch": 8.093278463648835,
"grad_norm": 1.5791015625,
"learning_rate": 1.7214402247580918e-05,
"loss": 1.6634,
"step": 2950
},
{
"epoch": 8.12071330589849,
"grad_norm": 1.63671875,
"learning_rate": 1.6733357731279377e-05,
"loss": 1.6908,
"step": 2960
},
{
"epoch": 8.148148148148149,
"grad_norm": 1.8701171875,
"learning_rate": 1.6258515694431144e-05,
"loss": 1.7138,
"step": 2970
},
{
"epoch": 8.175582990397805,
"grad_norm": 1.6357421875,
"learning_rate": 1.5789911507718826e-05,
"loss": 1.7258,
"step": 2980
},
{
"epoch": 8.203017832647463,
"grad_norm": 1.734375,
"learning_rate": 1.5327580077171587e-05,
"loss": 1.7178,
"step": 2990
},
{
"epoch": 8.23045267489712,
"grad_norm": 1.787109375,
"learning_rate": 1.4871555841564887e-05,
"loss": 1.6809,
"step": 3000
},
{
"epoch": 8.257887517146777,
"grad_norm": 1.7177734375,
"learning_rate": 1.442187276985526e-05,
"loss": 1.6501,
"step": 3010
},
{
"epoch": 8.285322359396433,
"grad_norm": 1.822265625,
"learning_rate": 1.3978564358649927e-05,
"loss": 1.7259,
"step": 3020
},
{
"epoch": 8.312757201646091,
"grad_norm": 1.7109375,
"learning_rate": 1.3541663629711766e-05,
"loss": 1.752,
"step": 3030
},
{
"epoch": 8.340192043895748,
"grad_norm": 1.7744140625,
"learning_rate": 1.311120312749935e-05,
"loss": 1.6563,
"step": 3040
},
{
"epoch": 8.367626886145406,
"grad_norm": 1.8427734375,
"learning_rate": 1.2687214916742918e-05,
"loss": 1.7103,
"step": 3050
},
{
"epoch": 8.395061728395062,
"grad_norm": 2.611328125,
"learning_rate": 1.2269730580055805e-05,
"loss": 1.6951,
"step": 3060
},
{
"epoch": 8.422496570644718,
"grad_norm": 1.763671875,
"learning_rate": 1.185878121558186e-05,
"loss": 1.6747,
"step": 3070
},
{
"epoch": 8.449931412894376,
"grad_norm": 1.7568359375,
"learning_rate": 1.1454397434679021e-05,
"loss": 1.7284,
"step": 3080
},
{
"epoch": 8.477366255144032,
"grad_norm": 1.8837890625,
"learning_rate": 1.1056609359639025e-05,
"loss": 1.6907,
"step": 3090
},
{
"epoch": 8.50480109739369,
"grad_norm": 1.677734375,
"learning_rate": 1.0665446621443708e-05,
"loss": 1.652,
"step": 3100
},
{
"epoch": 8.532235939643346,
"grad_norm": 1.7236328125,
"learning_rate": 1.028093835755769e-05,
"loss": 1.6751,
"step": 3110
},
{
"epoch": 8.559670781893004,
"grad_norm": 1.716796875,
"learning_rate": 9.903113209758096e-06,
"loss": 1.6465,
"step": 3120
},
{
"epoch": 8.58710562414266,
"grad_norm": 1.6328125,
"learning_rate": 9.531999322000885e-06,
"loss": 1.7407,
"step": 3130
},
{
"epoch": 8.614540466392318,
"grad_norm": 1.681640625,
"learning_rate": 9.1676243383246e-06,
"loss": 1.7061,
"step": 3140
},
{
"epoch": 8.641975308641975,
"grad_norm": 2.072265625,
"learning_rate": 8.810015400790994e-06,
"loss": 1.6604,
"step": 3150
},
{
"epoch": 8.669410150891633,
"grad_norm": 1.7685546875,
"learning_rate": 8.45919914746337e-06,
"loss": 1.7301,
"step": 3160
},
{
"epoch": 8.696844993141289,
"grad_norm": 2.193359375,
"learning_rate": 8.115201710422282e-06,
"loss": 1.6973,
"step": 3170
},
{
"epoch": 8.724279835390947,
"grad_norm": 1.677734375,
"learning_rate": 7.778048713818975e-06,
"loss": 1.7165,
"step": 3180
},
{
"epoch": 8.751714677640603,
"grad_norm": 2.1171875,
"learning_rate": 7.447765271966656e-06,
"loss": 1.6841,
"step": 3190
},
{
"epoch": 8.779149519890261,
"grad_norm": 1.6279296875,
"learning_rate": 7.124375987469767e-06,
"loss": 1.7142,
"step": 3200
},
{
"epoch": 8.806584362139917,
"grad_norm": 1.93359375,
"learning_rate": 6.80790494939132e-06,
"loss": 1.7619,
"step": 3210
},
{
"epoch": 8.834019204389575,
"grad_norm": 2.171875,
"learning_rate": 6.498375731458528e-06,
"loss": 1.7146,
"step": 3220
},
{
"epoch": 8.861454046639231,
"grad_norm": 1.59765625,
"learning_rate": 6.195811390306816e-06,
"loss": 1.6753,
"step": 3230
},
{
"epoch": 8.88888888888889,
"grad_norm": 1.6484375,
"learning_rate": 5.900234463762366e-06,
"loss": 1.662,
"step": 3240
},
{
"epoch": 8.916323731138545,
"grad_norm": 1.70703125,
"learning_rate": 5.611666969163243e-06,
"loss": 1.6781,
"step": 3250
},
{
"epoch": 8.943758573388203,
"grad_norm": 1.8642578125,
"learning_rate": 5.3301304017194135e-06,
"loss": 1.6446,
"step": 3260
},
{
"epoch": 8.97119341563786,
"grad_norm": 1.96484375,
"learning_rate": 5.055645732911462e-06,
"loss": 1.6632,
"step": 3270
},
{
"epoch": 8.998628257887518,
"grad_norm": 2.181640625,
"learning_rate": 4.788233408928589e-06,
"loss": 1.707,
"step": 3280
},
{
"epoch": 9.026063100137174,
"grad_norm": 1.75390625,
"learning_rate": 4.527913349145441e-06,
"loss": 1.7361,
"step": 3290
},
{
"epoch": 9.053497942386832,
"grad_norm": 2.705078125,
"learning_rate": 4.27470494463843e-06,
"loss": 1.7412,
"step": 3300
},
{
"epoch": 9.080932784636488,
"grad_norm": 2.5,
"learning_rate": 4.028627056741252e-06,
"loss": 1.6508,
"step": 3310
},
{
"epoch": 9.108367626886146,
"grad_norm": 1.7490234375,
"learning_rate": 3.789698015639953e-06,
"loss": 1.7095,
"step": 3320
},
{
"epoch": 9.135802469135802,
"grad_norm": 1.7919921875,
"learning_rate": 3.5579356190074907e-06,
"loss": 1.6629,
"step": 3330
},
{
"epoch": 9.16323731138546,
"grad_norm": 1.662109375,
"learning_rate": 3.3333571306780497e-06,
"loss": 1.6755,
"step": 3340
},
{
"epoch": 9.190672153635116,
"grad_norm": 5.0703125,
"learning_rate": 3.115979279360992e-06,
"loss": 1.6963,
"step": 3350
},
{
"epoch": 9.218106995884774,
"grad_norm": 1.662109375,
"learning_rate": 2.905818257394799e-06,
"loss": 1.694,
"step": 3360
},
{
"epoch": 9.24554183813443,
"grad_norm": 1.55078125,
"learning_rate": 2.702889719540924e-06,
"loss": 1.6488,
"step": 3370
},
{
"epoch": 9.272976680384089,
"grad_norm": 2.107421875,
"learning_rate": 2.5072087818176382e-06,
"loss": 1.6729,
"step": 3380
},
{
"epoch": 9.300411522633745,
"grad_norm": 1.5791015625,
"learning_rate": 2.3187900203740844e-06,
"loss": 1.6518,
"step": 3390
},
{
"epoch": 9.327846364883403,
"grad_norm": 2.0234375,
"learning_rate": 2.137647470404469e-06,
"loss": 1.7342,
"step": 3400
},
{
"epoch": 9.355281207133059,
"grad_norm": 1.9423828125,
"learning_rate": 1.963794625102655e-06,
"loss": 1.7223,
"step": 3410
},
{
"epoch": 9.382716049382717,
"grad_norm": 2.234375,
"learning_rate": 1.797244434656975e-06,
"loss": 1.7224,
"step": 3420
},
{
"epoch": 9.410150891632373,
"grad_norm": 1.6806640625,
"learning_rate": 1.6380093052856483e-06,
"loss": 1.6956,
"step": 3430
},
{
"epoch": 9.437585733882031,
"grad_norm": 1.693359375,
"learning_rate": 1.48610109831262e-06,
"loss": 1.6918,
"step": 3440
},
{
"epoch": 9.465020576131687,
"grad_norm": 1.7080078125,
"learning_rate": 1.341531129284046e-06,
"loss": 1.6376,
"step": 3450
},
{
"epoch": 9.492455418381343,
"grad_norm": 2.220703125,
"learning_rate": 1.2043101671253554e-06,
"loss": 1.6831,
"step": 3460
},
{
"epoch": 9.519890260631001,
"grad_norm": 2.203125,
"learning_rate": 1.0744484333391368e-06,
"loss": 1.6559,
"step": 3470
},
{
"epoch": 9.547325102880658,
"grad_norm": 1.982421875,
"learning_rate": 9.519556012436815e-07,
"loss": 1.6864,
"step": 3480
},
{
"epoch": 9.574759945130316,
"grad_norm": 2.025390625,
"learning_rate": 8.368407952525026e-07,
"loss": 1.6973,
"step": 3490
},
{
"epoch": 9.602194787379972,
"grad_norm": 1.6865234375,
"learning_rate": 7.291125901946027e-07,
"loss": 1.7048,
"step": 3500
},
{
"epoch": 9.62962962962963,
"grad_norm": 1.9140625,
"learning_rate": 6.287790106757396e-07,
"loss": 1.6939,
"step": 3510
},
{
"epoch": 9.657064471879286,
"grad_norm": 1.5322265625,
"learning_rate": 5.358475304807375e-07,
"loss": 1.7541,
"step": 3520
},
{
"epoch": 9.684499314128944,
"grad_norm": 2.29296875,
"learning_rate": 4.503250720166774e-07,
"loss": 1.6679,
"step": 3530
},
{
"epoch": 9.7119341563786,
"grad_norm": 1.5634765625,
"learning_rate": 3.7221800579735346e-07,
"loss": 1.685,
"step": 3540
},
{
"epoch": 9.739368998628258,
"grad_norm": 1.6884765625,
"learning_rate": 3.0153214996866406e-07,
"loss": 1.6628,
"step": 3550
},
{
"epoch": 9.766803840877914,
"grad_norm": 1.8408203125,
"learning_rate": 2.382727698752474e-07,
"loss": 1.6632,
"step": 3560
},
{
"epoch": 9.794238683127572,
"grad_norm": 1.9072265625,
"learning_rate": 1.824445776682504e-07,
"loss": 1.7231,
"step": 3570
},
{
"epoch": 9.821673525377228,
"grad_norm": 1.791015625,
"learning_rate": 1.340517319543877e-07,
"loss": 1.6758,
"step": 3580
},
{
"epoch": 9.849108367626886,
"grad_norm": 1.7236328125,
"learning_rate": 9.309783748606693e-08,
"loss": 1.6677,
"step": 3590
},
{
"epoch": 9.876543209876543,
"grad_norm": 1.5498046875,
"learning_rate": 5.958594489295921e-08,
"loss": 1.6355,
"step": 3600
},
{
"epoch": 9.9039780521262,
"grad_norm": 1.802734375,
"learning_rate": 3.351855045471419e-08,
"loss": 1.6854,
"step": 3610
},
{
"epoch": 9.931412894375857,
"grad_norm": 1.9306640625,
"learning_rate": 1.4897595915053242e-08,
"loss": 1.6643,
"step": 3620
},
{
"epoch": 9.958847736625515,
"grad_norm": 1.8544921875,
"learning_rate": 3.724468337085174e-09,
"loss": 1.7076,
"step": 3630
},
{
"epoch": 9.986282578875171,
"grad_norm": 2.060546875,
"learning_rate": 0.0,
"loss": 1.6734,
"step": 3640
},
{
"epoch": 9.986282578875171,
"step": 3640,
"total_flos": 2.39046462799872e+17,
"train_loss": 1.891263527398581,
"train_runtime": 3639.5664,
"train_samples_per_second": 4.006,
"train_steps_per_second": 1.0
}
],
"logging_steps": 10,
"max_steps": 3640,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"save_steps": 500,
"total_flos": 2.39046462799872e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}