Files
tur_indomain_prepretraining…/checkpoint-4000/trainer_state.json
ModelHub XC d181db07e8 初始化项目,由ModelHub XC社区提供模型
Model: fpadovani/tur_indomain_prepretraining_seed21
Source: Original Platform
2026-05-23 01:25:36 +08:00

5634 lines
128 KiB
JSON

{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.5231151507225528,
"eval_steps": 500,
"global_step": 4000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.000653893938403191,
"grad_norm": 8.4375,
"learning_rate": 1e-05,
"loss": 10.9218,
"step": 5
},
{
"epoch": 0.001307787876806382,
"grad_norm": 8.5,
"learning_rate": 2e-05,
"loss": 10.86,
"step": 10
},
{
"epoch": 0.001961681815209573,
"grad_norm": 5.0625,
"learning_rate": 3e-05,
"loss": 10.6568,
"step": 15
},
{
"epoch": 0.002615575753612764,
"grad_norm": 3.4375,
"learning_rate": 4e-05,
"loss": 10.4622,
"step": 20
},
{
"epoch": 0.003269469692015955,
"grad_norm": 3.0625,
"learning_rate": 5e-05,
"loss": 10.2882,
"step": 25
},
{
"epoch": 0.003923363630419146,
"grad_norm": 3.09375,
"learning_rate": 6e-05,
"loss": 10.2014,
"step": 30
},
{
"epoch": 0.004577257568822337,
"grad_norm": 2.703125,
"learning_rate": 7.000000000000001e-05,
"loss": 10.0942,
"step": 35
},
{
"epoch": 0.005231151507225528,
"grad_norm": 2.984375,
"learning_rate": 8e-05,
"loss": 9.9471,
"step": 40
},
{
"epoch": 0.005885045445628719,
"grad_norm": 2.703125,
"learning_rate": 8.999999999999999e-05,
"loss": 9.7595,
"step": 45
},
{
"epoch": 0.00653893938403191,
"grad_norm": 2.46875,
"learning_rate": 0.0001,
"loss": 9.6038,
"step": 50
},
{
"epoch": 0.007192833322435101,
"grad_norm": 2.53125,
"learning_rate": 0.00011,
"loss": 9.3898,
"step": 55
},
{
"epoch": 0.007846727260838291,
"grad_norm": 2.125,
"learning_rate": 0.00012,
"loss": 9.2079,
"step": 60
},
{
"epoch": 0.008500621199241483,
"grad_norm": 1.8046875,
"learning_rate": 0.00013000000000000002,
"loss": 9.0458,
"step": 65
},
{
"epoch": 0.009154515137644674,
"grad_norm": 1.734375,
"learning_rate": 0.00014000000000000001,
"loss": 8.8588,
"step": 70
},
{
"epoch": 0.009808409076047865,
"grad_norm": 1.34375,
"learning_rate": 0.00015,
"loss": 8.7008,
"step": 75
},
{
"epoch": 0.010462303014451056,
"grad_norm": 1.109375,
"learning_rate": 0.00016,
"loss": 8.5939,
"step": 80
},
{
"epoch": 0.011116196952854247,
"grad_norm": 1.1640625,
"learning_rate": 0.00017,
"loss": 8.5616,
"step": 85
},
{
"epoch": 0.011770090891257438,
"grad_norm": 1.3984375,
"learning_rate": 0.00017999999999999998,
"loss": 8.4525,
"step": 90
},
{
"epoch": 0.01242398482966063,
"grad_norm": 1.109375,
"learning_rate": 0.00019,
"loss": 8.4594,
"step": 95
},
{
"epoch": 0.01307787876806382,
"grad_norm": 1.1640625,
"learning_rate": 0.0002,
"loss": 8.4348,
"step": 100
},
{
"epoch": 0.013731772706467011,
"grad_norm": 1.4375,
"learning_rate": 0.00021,
"loss": 8.4187,
"step": 105
},
{
"epoch": 0.014385666644870202,
"grad_norm": 1.78125,
"learning_rate": 0.00022,
"loss": 8.3887,
"step": 110
},
{
"epoch": 0.015039560583273394,
"grad_norm": 1.375,
"learning_rate": 0.00023,
"loss": 8.3935,
"step": 115
},
{
"epoch": 0.015693454521676583,
"grad_norm": 1.4453125,
"learning_rate": 0.00024,
"loss": 8.3468,
"step": 120
},
{
"epoch": 0.016347348460079774,
"grad_norm": 1.5859375,
"learning_rate": 0.00025,
"loss": 8.3648,
"step": 125
},
{
"epoch": 0.017001242398482965,
"grad_norm": 1.8046875,
"learning_rate": 0.00026000000000000003,
"loss": 8.3006,
"step": 130
},
{
"epoch": 0.017655136336886156,
"grad_norm": 1.421875,
"learning_rate": 0.00027,
"loss": 8.2614,
"step": 135
},
{
"epoch": 0.018309030275289347,
"grad_norm": 1.3828125,
"learning_rate": 0.00028000000000000003,
"loss": 8.25,
"step": 140
},
{
"epoch": 0.01896292421369254,
"grad_norm": 1.90625,
"learning_rate": 0.00029,
"loss": 8.2765,
"step": 145
},
{
"epoch": 0.01961681815209573,
"grad_norm": 1.4296875,
"learning_rate": 0.0003,
"loss": 8.2609,
"step": 150
},
{
"epoch": 0.02027071209049892,
"grad_norm": 1.703125,
"learning_rate": 0.00031,
"loss": 8.1702,
"step": 155
},
{
"epoch": 0.02092460602890211,
"grad_norm": 1.53125,
"learning_rate": 0.00032,
"loss": 8.1875,
"step": 160
},
{
"epoch": 0.021578499967305303,
"grad_norm": 1.5,
"learning_rate": 0.00033,
"loss": 8.1725,
"step": 165
},
{
"epoch": 0.022232393905708494,
"grad_norm": 1.9140625,
"learning_rate": 0.00034,
"loss": 8.1809,
"step": 170
},
{
"epoch": 0.022886287844111685,
"grad_norm": 1.5703125,
"learning_rate": 0.00035,
"loss": 8.1357,
"step": 175
},
{
"epoch": 0.023540181782514876,
"grad_norm": 1.453125,
"learning_rate": 0.00035999999999999997,
"loss": 8.1805,
"step": 180
},
{
"epoch": 0.024194075720918067,
"grad_norm": 1.84375,
"learning_rate": 0.00037,
"loss": 8.0948,
"step": 185
},
{
"epoch": 0.02484796965932126,
"grad_norm": 1.65625,
"learning_rate": 0.00038,
"loss": 8.0769,
"step": 190
},
{
"epoch": 0.02550186359772445,
"grad_norm": 1.4375,
"learning_rate": 0.00039000000000000005,
"loss": 8.0623,
"step": 195
},
{
"epoch": 0.02615575753612764,
"grad_norm": 1.375,
"learning_rate": 0.0004,
"loss": 8.0233,
"step": 200
},
{
"epoch": 0.02680965147453083,
"grad_norm": 1.65625,
"learning_rate": 0.00041,
"loss": 8.0448,
"step": 205
},
{
"epoch": 0.027463545412934023,
"grad_norm": 1.421875,
"learning_rate": 0.00042,
"loss": 7.9827,
"step": 210
},
{
"epoch": 0.028117439351337214,
"grad_norm": 1.8125,
"learning_rate": 0.00043,
"loss": 7.9879,
"step": 215
},
{
"epoch": 0.028771333289740405,
"grad_norm": 1.484375,
"learning_rate": 0.00044,
"loss": 7.9859,
"step": 220
},
{
"epoch": 0.029425227228143596,
"grad_norm": 1.40625,
"learning_rate": 0.00045000000000000004,
"loss": 7.9821,
"step": 225
},
{
"epoch": 0.030079121166546787,
"grad_norm": 1.421875,
"learning_rate": 0.00046,
"loss": 7.9357,
"step": 230
},
{
"epoch": 0.030733015104949978,
"grad_norm": 1.375,
"learning_rate": 0.00047,
"loss": 7.9613,
"step": 235
},
{
"epoch": 0.031386909043353166,
"grad_norm": 1.96875,
"learning_rate": 0.00048,
"loss": 7.8928,
"step": 240
},
{
"epoch": 0.03204080298175636,
"grad_norm": 1.5859375,
"learning_rate": 0.00049,
"loss": 7.9647,
"step": 245
},
{
"epoch": 0.03269469692015955,
"grad_norm": 1.6875,
"learning_rate": 0.0005,
"loss": 7.8866,
"step": 250
},
{
"epoch": 0.03334859085856274,
"grad_norm": 1.5703125,
"learning_rate": 0.00051,
"loss": 7.8719,
"step": 255
},
{
"epoch": 0.03400248479696593,
"grad_norm": 1.4609375,
"learning_rate": 0.0005200000000000001,
"loss": 7.8036,
"step": 260
},
{
"epoch": 0.03465637873536912,
"grad_norm": 1.53125,
"learning_rate": 0.0005300000000000001,
"loss": 7.8523,
"step": 265
},
{
"epoch": 0.03531027267377231,
"grad_norm": 1.46875,
"learning_rate": 0.00054,
"loss": 7.8359,
"step": 270
},
{
"epoch": 0.035964166612175504,
"grad_norm": 1.65625,
"learning_rate": 0.00055,
"loss": 7.8399,
"step": 275
},
{
"epoch": 0.036618060550578695,
"grad_norm": 1.65625,
"learning_rate": 0.0005600000000000001,
"loss": 7.8428,
"step": 280
},
{
"epoch": 0.037271954488981886,
"grad_norm": 1.7421875,
"learning_rate": 0.00057,
"loss": 7.7551,
"step": 285
},
{
"epoch": 0.03792584842738508,
"grad_norm": 1.4765625,
"learning_rate": 0.00058,
"loss": 7.7357,
"step": 290
},
{
"epoch": 0.03857974236578827,
"grad_norm": 1.375,
"learning_rate": 0.00059,
"loss": 7.7327,
"step": 295
},
{
"epoch": 0.03923363630419146,
"grad_norm": 1.5859375,
"learning_rate": 0.0006,
"loss": 7.6911,
"step": 300
},
{
"epoch": 0.03988753024259465,
"grad_norm": 1.3359375,
"learning_rate": 0.00061,
"loss": 7.6854,
"step": 305
},
{
"epoch": 0.04054142418099784,
"grad_norm": 1.4921875,
"learning_rate": 0.00062,
"loss": 7.7088,
"step": 310
},
{
"epoch": 0.04119531811940103,
"grad_norm": 1.59375,
"learning_rate": 0.00063,
"loss": 7.6666,
"step": 315
},
{
"epoch": 0.04184921205780422,
"grad_norm": 1.4921875,
"learning_rate": 0.00064,
"loss": 7.6758,
"step": 320
},
{
"epoch": 0.042503105996207415,
"grad_norm": 1.46875,
"learning_rate": 0.0006500000000000001,
"loss": 7.6554,
"step": 325
},
{
"epoch": 0.043156999934610606,
"grad_norm": 1.6328125,
"learning_rate": 0.00066,
"loss": 7.6471,
"step": 330
},
{
"epoch": 0.0438108938730138,
"grad_norm": 1.546875,
"learning_rate": 0.00067,
"loss": 7.612,
"step": 335
},
{
"epoch": 0.04446478781141699,
"grad_norm": 1.546875,
"learning_rate": 0.00068,
"loss": 7.6353,
"step": 340
},
{
"epoch": 0.04511868174982018,
"grad_norm": 1.5859375,
"learning_rate": 0.00069,
"loss": 7.6068,
"step": 345
},
{
"epoch": 0.04577257568822337,
"grad_norm": 1.640625,
"learning_rate": 0.0007,
"loss": 7.6507,
"step": 350
},
{
"epoch": 0.04642646962662656,
"grad_norm": 1.6328125,
"learning_rate": 0.00071,
"loss": 7.5806,
"step": 355
},
{
"epoch": 0.04708036356502975,
"grad_norm": 1.6328125,
"learning_rate": 0.0007199999999999999,
"loss": 7.5964,
"step": 360
},
{
"epoch": 0.04773425750343294,
"grad_norm": 1.484375,
"learning_rate": 0.00073,
"loss": 7.5817,
"step": 365
},
{
"epoch": 0.048388151441836134,
"grad_norm": 1.4375,
"learning_rate": 0.00074,
"loss": 7.5673,
"step": 370
},
{
"epoch": 0.049042045380239326,
"grad_norm": 1.6015625,
"learning_rate": 0.00075,
"loss": 7.5662,
"step": 375
},
{
"epoch": 0.04969593931864252,
"grad_norm": 1.5234375,
"learning_rate": 0.00076,
"loss": 7.5739,
"step": 380
},
{
"epoch": 0.05034983325704571,
"grad_norm": 1.6328125,
"learning_rate": 0.0007700000000000001,
"loss": 7.5809,
"step": 385
},
{
"epoch": 0.0510037271954489,
"grad_norm": 1.6328125,
"learning_rate": 0.0007800000000000001,
"loss": 7.584,
"step": 390
},
{
"epoch": 0.05165762113385209,
"grad_norm": 1.8671875,
"learning_rate": 0.00079,
"loss": 7.4952,
"step": 395
},
{
"epoch": 0.05231151507225528,
"grad_norm": 1.6328125,
"learning_rate": 0.0008,
"loss": 7.5619,
"step": 400
},
{
"epoch": 0.05296540901065847,
"grad_norm": 1.4609375,
"learning_rate": 0.0008100000000000001,
"loss": 7.5143,
"step": 405
},
{
"epoch": 0.05361930294906166,
"grad_norm": 1.59375,
"learning_rate": 0.00082,
"loss": 7.429,
"step": 410
},
{
"epoch": 0.054273196887464854,
"grad_norm": 1.5625,
"learning_rate": 0.00083,
"loss": 7.5304,
"step": 415
},
{
"epoch": 0.054927090825868045,
"grad_norm": 1.515625,
"learning_rate": 0.00084,
"loss": 7.4544,
"step": 420
},
{
"epoch": 0.055580984764271237,
"grad_norm": 1.5546875,
"learning_rate": 0.00085,
"loss": 7.4307,
"step": 425
},
{
"epoch": 0.05623487870267443,
"grad_norm": 1.5078125,
"learning_rate": 0.00086,
"loss": 7.4134,
"step": 430
},
{
"epoch": 0.05688877264107762,
"grad_norm": 1.4765625,
"learning_rate": 0.00087,
"loss": 7.5005,
"step": 435
},
{
"epoch": 0.05754266657948081,
"grad_norm": 1.421875,
"learning_rate": 0.00088,
"loss": 7.4401,
"step": 440
},
{
"epoch": 0.058196560517884,
"grad_norm": 1.671875,
"learning_rate": 0.0008900000000000001,
"loss": 7.4792,
"step": 445
},
{
"epoch": 0.05885045445628719,
"grad_norm": 1.5,
"learning_rate": 0.0009000000000000001,
"loss": 7.405,
"step": 450
},
{
"epoch": 0.05950434839469038,
"grad_norm": 1.5625,
"learning_rate": 0.00091,
"loss": 7.4043,
"step": 455
},
{
"epoch": 0.060158242333093574,
"grad_norm": 1.5,
"learning_rate": 0.00092,
"loss": 7.4356,
"step": 460
},
{
"epoch": 0.060812136271496765,
"grad_norm": 1.4453125,
"learning_rate": 0.00093,
"loss": 7.2855,
"step": 465
},
{
"epoch": 0.061466030209899956,
"grad_norm": 1.6015625,
"learning_rate": 0.00094,
"loss": 7.3614,
"step": 470
},
{
"epoch": 0.06211992414830315,
"grad_norm": 1.6171875,
"learning_rate": 0.00095,
"loss": 7.4136,
"step": 475
},
{
"epoch": 0.06277381808670633,
"grad_norm": 1.5546875,
"learning_rate": 0.00096,
"loss": 7.3571,
"step": 480
},
{
"epoch": 0.06342771202510952,
"grad_norm": 1.6015625,
"learning_rate": 0.0009699999999999999,
"loss": 7.3855,
"step": 485
},
{
"epoch": 0.06408160596351271,
"grad_norm": 1.6875,
"learning_rate": 0.00098,
"loss": 7.5011,
"step": 490
},
{
"epoch": 0.0647354999019159,
"grad_norm": 1.578125,
"learning_rate": 0.00099,
"loss": 7.3837,
"step": 495
},
{
"epoch": 0.0653893938403191,
"grad_norm": 1.5859375,
"learning_rate": 0.001,
"loss": 7.2856,
"step": 500
},
{
"epoch": 0.06604328777872229,
"grad_norm": 1.421875,
"learning_rate": 0.0009999954680464025,
"loss": 7.315,
"step": 505
},
{
"epoch": 0.06669718171712548,
"grad_norm": 1.4140625,
"learning_rate": 0.000999981872276892,
"loss": 7.3113,
"step": 510
},
{
"epoch": 0.06735107565552867,
"grad_norm": 1.6328125,
"learning_rate": 0.0009999592129653152,
"loss": 7.4444,
"step": 515
},
{
"epoch": 0.06800496959393186,
"grad_norm": 1.625,
"learning_rate": 0.0009999274905680762,
"loss": 7.3685,
"step": 520
},
{
"epoch": 0.06865886353233505,
"grad_norm": 1.453125,
"learning_rate": 0.000999886705724128,
"loss": 7.3539,
"step": 525
},
{
"epoch": 0.06931275747073824,
"grad_norm": 1.3671875,
"learning_rate": 0.0009998368592549595,
"loss": 7.2917,
"step": 530
},
{
"epoch": 0.06996665140914143,
"grad_norm": 1.46875,
"learning_rate": 0.0009997779521645793,
"loss": 7.2531,
"step": 535
},
{
"epoch": 0.07062054534754462,
"grad_norm": 1.390625,
"learning_rate": 0.0009997099856394946,
"loss": 7.2724,
"step": 540
},
{
"epoch": 0.07127443928594782,
"grad_norm": 1.4453125,
"learning_rate": 0.0009996329610486886,
"loss": 7.2601,
"step": 545
},
{
"epoch": 0.07192833322435101,
"grad_norm": 1.5390625,
"learning_rate": 0.0009995468799435915,
"loss": 7.2737,
"step": 550
},
{
"epoch": 0.0725822271627542,
"grad_norm": 1.3515625,
"learning_rate": 0.0009994517440580508,
"loss": 7.2841,
"step": 555
},
{
"epoch": 0.07323612110115739,
"grad_norm": 1.453125,
"learning_rate": 0.0009993475553082944,
"loss": 7.2297,
"step": 560
},
{
"epoch": 0.07389001503956058,
"grad_norm": 1.484375,
"learning_rate": 0.0009992343157928943,
"loss": 7.2323,
"step": 565
},
{
"epoch": 0.07454390897796377,
"grad_norm": 1.5625,
"learning_rate": 0.0009991120277927223,
"loss": 7.2182,
"step": 570
},
{
"epoch": 0.07519780291636696,
"grad_norm": 1.390625,
"learning_rate": 0.0009989806937709053,
"loss": 7.1595,
"step": 575
},
{
"epoch": 0.07585169685477015,
"grad_norm": 1.3671875,
"learning_rate": 0.0009988403163727754,
"loss": 7.2895,
"step": 580
},
{
"epoch": 0.07650559079317334,
"grad_norm": 1.4296875,
"learning_rate": 0.0009986908984258162,
"loss": 7.181,
"step": 585
},
{
"epoch": 0.07715948473157654,
"grad_norm": 1.375,
"learning_rate": 0.0009985324429396065,
"loss": 7.2096,
"step": 590
},
{
"epoch": 0.07781337866997973,
"grad_norm": 1.5390625,
"learning_rate": 0.0009983649531057593,
"loss": 7.1715,
"step": 595
},
{
"epoch": 0.07846727260838292,
"grad_norm": 1.40625,
"learning_rate": 0.0009981884322978576,
"loss": 7.1572,
"step": 600
},
{
"epoch": 0.07912116654678611,
"grad_norm": 1.5,
"learning_rate": 0.000998002884071386,
"loss": 7.2064,
"step": 605
},
{
"epoch": 0.0797750604851893,
"grad_norm": 1.3046875,
"learning_rate": 0.0009978083121636601,
"loss": 7.1608,
"step": 610
},
{
"epoch": 0.08042895442359249,
"grad_norm": 1.390625,
"learning_rate": 0.0009976047204937502,
"loss": 7.1221,
"step": 615
},
{
"epoch": 0.08108284836199568,
"grad_norm": 1.3828125,
"learning_rate": 0.0009973921131624032,
"loss": 7.191,
"step": 620
},
{
"epoch": 0.08173674230039887,
"grad_norm": 1.46875,
"learning_rate": 0.0009971704944519593,
"loss": 7.1432,
"step": 625
},
{
"epoch": 0.08239063623880206,
"grad_norm": 1.3046875,
"learning_rate": 0.0009969398688262658,
"loss": 7.094,
"step": 630
},
{
"epoch": 0.08304453017720526,
"grad_norm": 1.46875,
"learning_rate": 0.000996700240930588,
"loss": 7.0845,
"step": 635
},
{
"epoch": 0.08369842411560845,
"grad_norm": 1.5078125,
"learning_rate": 0.000996451615591515,
"loss": 7.0421,
"step": 640
},
{
"epoch": 0.08435231805401164,
"grad_norm": 2.453125,
"learning_rate": 0.000996193997816862,
"loss": 7.1952,
"step": 645
},
{
"epoch": 0.08500621199241483,
"grad_norm": 1.2890625,
"learning_rate": 0.0009959273927955706,
"loss": 7.0521,
"step": 650
},
{
"epoch": 0.08566010593081802,
"grad_norm": 1.46875,
"learning_rate": 0.0009956518058976034,
"loss": 7.0618,
"step": 655
},
{
"epoch": 0.08631399986922121,
"grad_norm": 1.421875,
"learning_rate": 0.0009953672426738357,
"loss": 7.1123,
"step": 660
},
{
"epoch": 0.0869678938076244,
"grad_norm": 1.4375,
"learning_rate": 0.000995073708855945,
"loss": 7.0862,
"step": 665
},
{
"epoch": 0.0876217877460276,
"grad_norm": 1.4375,
"learning_rate": 0.000994771210356294,
"loss": 7.0968,
"step": 670
},
{
"epoch": 0.08827568168443078,
"grad_norm": 1.4453125,
"learning_rate": 0.0009944597532678121,
"loss": 7.054,
"step": 675
},
{
"epoch": 0.08892957562283398,
"grad_norm": 1.296875,
"learning_rate": 0.0009941393438638731,
"loss": 7.052,
"step": 680
},
{
"epoch": 0.08958346956123717,
"grad_norm": 1.359375,
"learning_rate": 0.0009938099885981684,
"loss": 7.0878,
"step": 685
},
{
"epoch": 0.09023736349964036,
"grad_norm": 1.4609375,
"learning_rate": 0.000993471694104577,
"loss": 7.0524,
"step": 690
},
{
"epoch": 0.09089125743804355,
"grad_norm": 1.375,
"learning_rate": 0.0009931244671970319,
"loss": 7.0968,
"step": 695
},
{
"epoch": 0.09154515137644674,
"grad_norm": 1.390625,
"learning_rate": 0.0009927683148693834,
"loss": 7.0047,
"step": 700
},
{
"epoch": 0.09219904531484993,
"grad_norm": 1.390625,
"learning_rate": 0.0009924032442952568,
"loss": 7.0067,
"step": 705
},
{
"epoch": 0.09285293925325312,
"grad_norm": 1.40625,
"learning_rate": 0.00099202926282791,
"loss": 7.0746,
"step": 710
},
{
"epoch": 0.09350683319165631,
"grad_norm": 1.3828125,
"learning_rate": 0.0009916463780000832,
"loss": 6.9485,
"step": 715
},
{
"epoch": 0.0941607271300595,
"grad_norm": 1.2890625,
"learning_rate": 0.000991254597523849,
"loss": 7.0258,
"step": 720
},
{
"epoch": 0.0948146210684627,
"grad_norm": 1.2265625,
"learning_rate": 0.000990853929290456,
"loss": 6.9995,
"step": 725
},
{
"epoch": 0.09546851500686589,
"grad_norm": 1.3046875,
"learning_rate": 0.0009904443813701703,
"loss": 6.9946,
"step": 730
},
{
"epoch": 0.09612240894526908,
"grad_norm": 1.3984375,
"learning_rate": 0.0009900259620121122,
"loss": 6.992,
"step": 735
},
{
"epoch": 0.09677630288367227,
"grad_norm": 1.34375,
"learning_rate": 0.0009895986796440914,
"loss": 6.9776,
"step": 740
},
{
"epoch": 0.09743019682207546,
"grad_norm": 1.359375,
"learning_rate": 0.0009891625428724363,
"loss": 6.9604,
"step": 745
},
{
"epoch": 0.09808409076047865,
"grad_norm": 1.2109375,
"learning_rate": 0.0009887175604818205,
"loss": 7.0686,
"step": 750
},
{
"epoch": 0.09873798469888184,
"grad_norm": 1.1875,
"learning_rate": 0.0009882637414350868,
"loss": 7.0291,
"step": 755
},
{
"epoch": 0.09939187863728503,
"grad_norm": 1.34375,
"learning_rate": 0.0009878010948730653,
"loss": 6.9426,
"step": 760
},
{
"epoch": 0.10004577257568822,
"grad_norm": 1.3671875,
"learning_rate": 0.0009873296301143905,
"loss": 6.9343,
"step": 765
},
{
"epoch": 0.10069966651409142,
"grad_norm": 1.25,
"learning_rate": 0.000986849356655313,
"loss": 6.9432,
"step": 770
},
{
"epoch": 0.1013535604524946,
"grad_norm": 1.3125,
"learning_rate": 0.000986360284169509,
"loss": 6.9194,
"step": 775
},
{
"epoch": 0.1020074543908978,
"grad_norm": 1.2578125,
"learning_rate": 0.000985862422507884,
"loss": 6.9385,
"step": 780
},
{
"epoch": 0.10266134832930099,
"grad_norm": 1.2890625,
"learning_rate": 0.0009853557816983756,
"loss": 6.9232,
"step": 785
},
{
"epoch": 0.10331524226770418,
"grad_norm": 1.234375,
"learning_rate": 0.0009848403719457507,
"loss": 6.902,
"step": 790
},
{
"epoch": 0.10396913620610737,
"grad_norm": 1.328125,
"learning_rate": 0.0009843162036314015,
"loss": 6.8928,
"step": 795
},
{
"epoch": 0.10462303014451056,
"grad_norm": 1.3515625,
"learning_rate": 0.000983783287313134,
"loss": 6.8928,
"step": 800
},
{
"epoch": 0.10527692408291375,
"grad_norm": 1.28125,
"learning_rate": 0.0009832416337249574,
"loss": 6.9226,
"step": 805
},
{
"epoch": 0.10593081802131694,
"grad_norm": 1.4375,
"learning_rate": 0.000982691253776867,
"loss": 6.896,
"step": 810
},
{
"epoch": 0.10658471195972014,
"grad_norm": 1.3671875,
"learning_rate": 0.0009821321585546244,
"loss": 6.8955,
"step": 815
},
{
"epoch": 0.10723860589812333,
"grad_norm": 1.3046875,
"learning_rate": 0.0009815643593195345,
"loss": 6.8248,
"step": 820
},
{
"epoch": 0.10789249983652652,
"grad_norm": 1.21875,
"learning_rate": 0.0009809878675082187,
"loss": 6.9171,
"step": 825
},
{
"epoch": 0.10854639377492971,
"grad_norm": 1.171875,
"learning_rate": 0.0009804026947323843,
"loss": 6.888,
"step": 830
},
{
"epoch": 0.1092002877133329,
"grad_norm": 1.2265625,
"learning_rate": 0.0009798088527785903,
"loss": 6.828,
"step": 835
},
{
"epoch": 0.10985418165173609,
"grad_norm": 1.3984375,
"learning_rate": 0.0009792063536080114,
"loss": 6.7827,
"step": 840
},
{
"epoch": 0.11050807559013928,
"grad_norm": 1.3359375,
"learning_rate": 0.0009785952093561952,
"loss": 6.8547,
"step": 845
},
{
"epoch": 0.11116196952854247,
"grad_norm": 1.296875,
"learning_rate": 0.0009779754323328191,
"loss": 6.8897,
"step": 850
},
{
"epoch": 0.11181586346694566,
"grad_norm": 1.390625,
"learning_rate": 0.0009773470350214418,
"loss": 6.8768,
"step": 855
},
{
"epoch": 0.11246975740534886,
"grad_norm": 1.3515625,
"learning_rate": 0.0009767100300792518,
"loss": 6.841,
"step": 860
},
{
"epoch": 0.11312365134375205,
"grad_norm": 1.3046875,
"learning_rate": 0.0009760644303368132,
"loss": 6.8652,
"step": 865
},
{
"epoch": 0.11377754528215524,
"grad_norm": 1.2890625,
"learning_rate": 0.0009754102487978059,
"loss": 6.8508,
"step": 870
},
{
"epoch": 0.11443143922055843,
"grad_norm": 1.3984375,
"learning_rate": 0.0009747474986387655,
"loss": 6.8592,
"step": 875
},
{
"epoch": 0.11508533315896162,
"grad_norm": 1.2890625,
"learning_rate": 0.0009740761932088156,
"loss": 6.7444,
"step": 880
},
{
"epoch": 0.11573922709736481,
"grad_norm": 1.1875,
"learning_rate": 0.0009733963460294015,
"loss": 6.7886,
"step": 885
},
{
"epoch": 0.116393121035768,
"grad_norm": 1.265625,
"learning_rate": 0.0009727079707940157,
"loss": 6.8274,
"step": 890
},
{
"epoch": 0.11704701497417119,
"grad_norm": 1.3046875,
"learning_rate": 0.0009720110813679232,
"loss": 6.8312,
"step": 895
},
{
"epoch": 0.11770090891257438,
"grad_norm": 1.3984375,
"learning_rate": 0.0009713056917878818,
"loss": 6.7666,
"step": 900
},
{
"epoch": 0.11835480285097758,
"grad_norm": 1.3359375,
"learning_rate": 0.0009705918162618599,
"loss": 6.837,
"step": 905
},
{
"epoch": 0.11900869678938077,
"grad_norm": 1.25,
"learning_rate": 0.00096986946916875,
"loss": 6.7604,
"step": 910
},
{
"epoch": 0.11966259072778396,
"grad_norm": 1.3125,
"learning_rate": 0.0009691386650580782,
"loss": 6.823,
"step": 915
},
{
"epoch": 0.12031648466618715,
"grad_norm": 1.3984375,
"learning_rate": 0.0009683994186497132,
"loss": 6.7549,
"step": 920
},
{
"epoch": 0.12097037860459034,
"grad_norm": 1.2265625,
"learning_rate": 0.0009676517448335676,
"loss": 6.7826,
"step": 925
},
{
"epoch": 0.12162427254299353,
"grad_norm": 1.4140625,
"learning_rate": 0.0009668956586692994,
"loss": 6.7052,
"step": 930
},
{
"epoch": 0.12227816648139672,
"grad_norm": 1.28125,
"learning_rate": 0.0009661311753860083,
"loss": 6.7853,
"step": 935
},
{
"epoch": 0.12293206041979991,
"grad_norm": 1.390625,
"learning_rate": 0.0009653583103819289,
"loss": 6.756,
"step": 940
},
{
"epoch": 0.1235859543582031,
"grad_norm": 1.2734375,
"learning_rate": 0.0009645770792241201,
"loss": 6.8063,
"step": 945
},
{
"epoch": 0.1242398482966063,
"grad_norm": 1.203125,
"learning_rate": 0.0009637874976481528,
"loss": 6.7515,
"step": 950
},
{
"epoch": 0.12489374223500949,
"grad_norm": 1.3046875,
"learning_rate": 0.0009629895815577914,
"loss": 6.8032,
"step": 955
},
{
"epoch": 0.12554763617341266,
"grad_norm": 1.328125,
"learning_rate": 0.0009621833470246749,
"loss": 6.8087,
"step": 960
},
{
"epoch": 0.12620153011181587,
"grad_norm": 1.2578125,
"learning_rate": 0.000961368810287992,
"loss": 6.7568,
"step": 965
},
{
"epoch": 0.12685542405021905,
"grad_norm": 1.1875,
"learning_rate": 0.0009605459877541544,
"loss": 6.641,
"step": 970
},
{
"epoch": 0.12750931798862225,
"grad_norm": 1.375,
"learning_rate": 0.0009597148959964672,
"loss": 6.7308,
"step": 975
},
{
"epoch": 0.12816321192702543,
"grad_norm": 1.1875,
"learning_rate": 0.0009588755517547935,
"loss": 6.6694,
"step": 980
},
{
"epoch": 0.12881710586542863,
"grad_norm": 1.2890625,
"learning_rate": 0.0009580279719352186,
"loss": 6.7216,
"step": 985
},
{
"epoch": 0.1294709998038318,
"grad_norm": 1.296875,
"learning_rate": 0.0009571721736097089,
"loss": 6.7645,
"step": 990
},
{
"epoch": 0.13012489374223501,
"grad_norm": 1.3359375,
"learning_rate": 0.0009563081740157675,
"loss": 6.6517,
"step": 995
},
{
"epoch": 0.1307787876806382,
"grad_norm": 1.265625,
"learning_rate": 0.0009554359905560886,
"loss": 6.6533,
"step": 1000
},
{
"epoch": 0.1314326816190414,
"grad_norm": 1.40625,
"learning_rate": 0.0009545556407982051,
"loss": 6.6792,
"step": 1005
},
{
"epoch": 0.13208657555744457,
"grad_norm": 1.4609375,
"learning_rate": 0.0009536671424741358,
"loss": 6.7272,
"step": 1010
},
{
"epoch": 0.13274046949584778,
"grad_norm": 1.25,
"learning_rate": 0.0009527705134800284,
"loss": 6.7536,
"step": 1015
},
{
"epoch": 0.13339436343425096,
"grad_norm": 1.2734375,
"learning_rate": 0.0009518657718757985,
"loss": 6.6877,
"step": 1020
},
{
"epoch": 0.13404825737265416,
"grad_norm": 1.328125,
"learning_rate": 0.0009509529358847655,
"loss": 6.7513,
"step": 1025
},
{
"epoch": 0.13470215131105734,
"grad_norm": 1.390625,
"learning_rate": 0.0009500320238932869,
"loss": 6.6554,
"step": 1030
},
{
"epoch": 0.13535604524946054,
"grad_norm": 1.1953125,
"learning_rate": 0.0009491030544503867,
"loss": 6.6413,
"step": 1035
},
{
"epoch": 0.13600993918786372,
"grad_norm": 1.2734375,
"learning_rate": 0.0009481660462673824,
"loss": 6.7161,
"step": 1040
},
{
"epoch": 0.13666383312626693,
"grad_norm": 1.3984375,
"learning_rate": 0.0009472210182175074,
"loss": 6.6721,
"step": 1045
},
{
"epoch": 0.1373177270646701,
"grad_norm": 1.3125,
"learning_rate": 0.0009462679893355321,
"loss": 6.6715,
"step": 1050
},
{
"epoch": 0.1379716210030733,
"grad_norm": 1.296875,
"learning_rate": 0.0009453069788173795,
"loss": 6.6908,
"step": 1055
},
{
"epoch": 0.13862551494147649,
"grad_norm": 1.359375,
"learning_rate": 0.0009443380060197386,
"loss": 6.7072,
"step": 1060
},
{
"epoch": 0.1392794088798797,
"grad_norm": 1.2890625,
"learning_rate": 0.0009433610904596752,
"loss": 6.6452,
"step": 1065
},
{
"epoch": 0.13993330281828287,
"grad_norm": 1.2578125,
"learning_rate": 0.0009423762518142381,
"loss": 6.6627,
"step": 1070
},
{
"epoch": 0.14058719675668607,
"grad_norm": 1.171875,
"learning_rate": 0.0009413835099200629,
"loss": 6.6257,
"step": 1075
},
{
"epoch": 0.14124109069508925,
"grad_norm": 1.2578125,
"learning_rate": 0.000940382884772973,
"loss": 6.661,
"step": 1080
},
{
"epoch": 0.14189498463349245,
"grad_norm": 1.296875,
"learning_rate": 0.0009393743965275757,
"loss": 6.6813,
"step": 1085
},
{
"epoch": 0.14254887857189563,
"grad_norm": 1.28125,
"learning_rate": 0.0009383580654968576,
"loss": 6.7009,
"step": 1090
},
{
"epoch": 0.14320277251029884,
"grad_norm": 1.3828125,
"learning_rate": 0.0009373339121517746,
"loss": 6.7083,
"step": 1095
},
{
"epoch": 0.14385666644870201,
"grad_norm": 1.1875,
"learning_rate": 0.0009363019571208398,
"loss": 6.6262,
"step": 1100
},
{
"epoch": 0.14451056038710522,
"grad_norm": 1.4140625,
"learning_rate": 0.0009352622211897077,
"loss": 6.7029,
"step": 1105
},
{
"epoch": 0.1451644543255084,
"grad_norm": 1.3515625,
"learning_rate": 0.0009342147253007562,
"loss": 6.6313,
"step": 1110
},
{
"epoch": 0.1458183482639116,
"grad_norm": 1.1953125,
"learning_rate": 0.0009331594905526644,
"loss": 6.5729,
"step": 1115
},
{
"epoch": 0.14647224220231478,
"grad_norm": 1.2421875,
"learning_rate": 0.0009320965381999872,
"loss": 6.544,
"step": 1120
},
{
"epoch": 0.14712613614071798,
"grad_norm": 1.3046875,
"learning_rate": 0.0009310258896527278,
"loss": 6.6008,
"step": 1125
},
{
"epoch": 0.14778003007912116,
"grad_norm": 1.265625,
"learning_rate": 0.0009299475664759069,
"loss": 6.6361,
"step": 1130
},
{
"epoch": 0.14843392401752437,
"grad_norm": 1.296875,
"learning_rate": 0.0009288615903891266,
"loss": 6.6924,
"step": 1135
},
{
"epoch": 0.14908781795592754,
"grad_norm": 1.3125,
"learning_rate": 0.0009277679832661348,
"loss": 6.6027,
"step": 1140
},
{
"epoch": 0.14974171189433075,
"grad_norm": 1.2734375,
"learning_rate": 0.0009266667671343836,
"loss": 6.6924,
"step": 1145
},
{
"epoch": 0.15039560583273393,
"grad_norm": 1.2421875,
"learning_rate": 0.0009255579641745861,
"loss": 6.5873,
"step": 1150
},
{
"epoch": 0.15104949977113713,
"grad_norm": 1.328125,
"learning_rate": 0.0009244415967202692,
"loss": 6.5781,
"step": 1155
},
{
"epoch": 0.1517033937095403,
"grad_norm": 1.2578125,
"learning_rate": 0.0009233176872573241,
"loss": 6.6017,
"step": 1160
},
{
"epoch": 0.1523572876479435,
"grad_norm": 1.2578125,
"learning_rate": 0.0009221862584235527,
"loss": 6.4452,
"step": 1165
},
{
"epoch": 0.1530111815863467,
"grad_norm": 1.2890625,
"learning_rate": 0.0009210473330082134,
"loss": 6.671,
"step": 1170
},
{
"epoch": 0.1536650755247499,
"grad_norm": 1.3125,
"learning_rate": 0.0009199009339515595,
"loss": 6.5906,
"step": 1175
},
{
"epoch": 0.15431896946315307,
"grad_norm": 1.203125,
"learning_rate": 0.0009187470843443794,
"loss": 6.5613,
"step": 1180
},
{
"epoch": 0.15497286340155628,
"grad_norm": 1.1796875,
"learning_rate": 0.0009175858074275303,
"loss": 6.5873,
"step": 1185
},
{
"epoch": 0.15562675733995945,
"grad_norm": 1.328125,
"learning_rate": 0.0009164171265914704,
"loss": 6.629,
"step": 1190
},
{
"epoch": 0.15628065127836266,
"grad_norm": 1.28125,
"learning_rate": 0.0009152410653757879,
"loss": 6.5664,
"step": 1195
},
{
"epoch": 0.15693454521676584,
"grad_norm": 1.3046875,
"learning_rate": 0.0009140576474687263,
"loss": 6.5779,
"step": 1200
},
{
"epoch": 0.15758843915516904,
"grad_norm": 1.296875,
"learning_rate": 0.0009128668967067084,
"loss": 6.5533,
"step": 1205
},
{
"epoch": 0.15824233309357222,
"grad_norm": 1.3203125,
"learning_rate": 0.0009116688370738549,
"loss": 6.5091,
"step": 1210
},
{
"epoch": 0.15889622703197542,
"grad_norm": 1.3671875,
"learning_rate": 0.0009104634927015022,
"loss": 6.5639,
"step": 1215
},
{
"epoch": 0.1595501209703786,
"grad_norm": 1.3046875,
"learning_rate": 0.0009092508878677157,
"loss": 6.528,
"step": 1220
},
{
"epoch": 0.1602040149087818,
"grad_norm": 1.3203125,
"learning_rate": 0.0009080310469968015,
"loss": 6.5639,
"step": 1225
},
{
"epoch": 0.16085790884718498,
"grad_norm": 1.3671875,
"learning_rate": 0.0009068039946588139,
"loss": 6.4909,
"step": 1230
},
{
"epoch": 0.1615118027855882,
"grad_norm": 1.34375,
"learning_rate": 0.0009055697555690607,
"loss": 6.5136,
"step": 1235
},
{
"epoch": 0.16216569672399136,
"grad_norm": 1.328125,
"learning_rate": 0.0009043283545876054,
"loss": 6.5411,
"step": 1240
},
{
"epoch": 0.16281959066239457,
"grad_norm": 1.390625,
"learning_rate": 0.0009030798167187664,
"loss": 6.4831,
"step": 1245
},
{
"epoch": 0.16347348460079775,
"grad_norm": 1.25,
"learning_rate": 0.0009018241671106134,
"loss": 6.5947,
"step": 1250
},
{
"epoch": 0.16412737853920095,
"grad_norm": 1.25,
"learning_rate": 0.000900561431054461,
"loss": 6.5163,
"step": 1255
},
{
"epoch": 0.16478127247760413,
"grad_norm": 1.3046875,
"learning_rate": 0.000899291633984359,
"loss": 6.5648,
"step": 1260
},
{
"epoch": 0.16543516641600733,
"grad_norm": 1.15625,
"learning_rate": 0.0008980148014765801,
"loss": 6.56,
"step": 1265
},
{
"epoch": 0.1660890603544105,
"grad_norm": 1.28125,
"learning_rate": 0.0008967309592491052,
"loss": 6.5537,
"step": 1270
},
{
"epoch": 0.16674295429281372,
"grad_norm": 1.21875,
"learning_rate": 0.000895440133161105,
"loss": 6.501,
"step": 1275
},
{
"epoch": 0.1673968482312169,
"grad_norm": 1.28125,
"learning_rate": 0.0008941423492124193,
"loss": 6.4513,
"step": 1280
},
{
"epoch": 0.1680507421696201,
"grad_norm": 1.1953125,
"learning_rate": 0.0008928376335430331,
"loss": 6.6408,
"step": 1285
},
{
"epoch": 0.16870463610802328,
"grad_norm": 1.1796875,
"learning_rate": 0.00089152601243255,
"loss": 6.5347,
"step": 1290
},
{
"epoch": 0.16935853004642648,
"grad_norm": 1.15625,
"learning_rate": 0.0008902075122996638,
"loss": 6.4901,
"step": 1295
},
{
"epoch": 0.17001242398482966,
"grad_norm": 1.2734375,
"learning_rate": 0.000888882159701625,
"loss": 6.4564,
"step": 1300
},
{
"epoch": 0.17066631792323286,
"grad_norm": 1.25,
"learning_rate": 0.0008875499813337067,
"loss": 6.5377,
"step": 1305
},
{
"epoch": 0.17132021186163604,
"grad_norm": 1.2109375,
"learning_rate": 0.0008862110040286674,
"loss": 6.5112,
"step": 1310
},
{
"epoch": 0.17197410580003925,
"grad_norm": 1.1875,
"learning_rate": 0.0008848652547562088,
"loss": 6.5023,
"step": 1315
},
{
"epoch": 0.17262799973844242,
"grad_norm": 1.2109375,
"learning_rate": 0.0008835127606224346,
"loss": 6.479,
"step": 1320
},
{
"epoch": 0.17328189367684563,
"grad_norm": 1.3671875,
"learning_rate": 0.0008821535488693033,
"loss": 6.5211,
"step": 1325
},
{
"epoch": 0.1739357876152488,
"grad_norm": 1.59375,
"learning_rate": 0.0008807876468740795,
"loss": 6.5395,
"step": 1330
},
{
"epoch": 0.174589681553652,
"grad_norm": 1.1328125,
"learning_rate": 0.0008794150821487834,
"loss": 6.537,
"step": 1335
},
{
"epoch": 0.1752435754920552,
"grad_norm": 1.359375,
"learning_rate": 0.0008780358823396352,
"loss": 6.4743,
"step": 1340
},
{
"epoch": 0.1758974694304584,
"grad_norm": 1.265625,
"learning_rate": 0.0008766500752264999,
"loss": 6.4797,
"step": 1345
},
{
"epoch": 0.17655136336886157,
"grad_norm": 1.3203125,
"learning_rate": 0.0008752576887223263,
"loss": 6.4782,
"step": 1350
},
{
"epoch": 0.17720525730726477,
"grad_norm": 1.3359375,
"learning_rate": 0.0008738587508725857,
"loss": 6.4511,
"step": 1355
},
{
"epoch": 0.17785915124566795,
"grad_norm": 1.296875,
"learning_rate": 0.0008724532898547066,
"loss": 6.4105,
"step": 1360
},
{
"epoch": 0.17851304518407116,
"grad_norm": 1.203125,
"learning_rate": 0.0008710413339775073,
"loss": 6.4949,
"step": 1365
},
{
"epoch": 0.17916693912247433,
"grad_norm": 1.296875,
"learning_rate": 0.0008696229116806256,
"loss": 6.4468,
"step": 1370
},
{
"epoch": 0.17982083306087754,
"grad_norm": 1.2421875,
"learning_rate": 0.0008681980515339464,
"loss": 6.4627,
"step": 1375
},
{
"epoch": 0.18047472699928072,
"grad_norm": 1.328125,
"learning_rate": 0.0008667667822370252,
"loss": 6.4464,
"step": 1380
},
{
"epoch": 0.18112862093768392,
"grad_norm": 1.21875,
"learning_rate": 0.0008653291326185112,
"loss": 6.5362,
"step": 1385
},
{
"epoch": 0.1817825148760871,
"grad_norm": 1.3671875,
"learning_rate": 0.0008638851316355662,
"loss": 6.5447,
"step": 1390
},
{
"epoch": 0.1824364088144903,
"grad_norm": 1.25,
"learning_rate": 0.0008624348083732806,
"loss": 6.4575,
"step": 1395
},
{
"epoch": 0.18309030275289348,
"grad_norm": 1.15625,
"learning_rate": 0.0008609781920440892,
"loss": 6.4726,
"step": 1400
},
{
"epoch": 0.18374419669129669,
"grad_norm": 1.359375,
"learning_rate": 0.000859515311987181,
"loss": 6.4314,
"step": 1405
},
{
"epoch": 0.18439809062969986,
"grad_norm": 1.2890625,
"learning_rate": 0.0008580461976679099,
"loss": 6.5269,
"step": 1410
},
{
"epoch": 0.18505198456810307,
"grad_norm": 1.96875,
"learning_rate": 0.0008565708786771999,
"loss": 6.4284,
"step": 1415
},
{
"epoch": 0.18570587850650624,
"grad_norm": 1.296875,
"learning_rate": 0.0008550893847309494,
"loss": 6.4655,
"step": 1420
},
{
"epoch": 0.18635977244490945,
"grad_norm": 1.3984375,
"learning_rate": 0.0008536017456694336,
"loss": 6.4113,
"step": 1425
},
{
"epoch": 0.18701366638331263,
"grad_norm": 1.25,
"learning_rate": 0.0008521079914567018,
"loss": 6.4303,
"step": 1430
},
{
"epoch": 0.1876675603217158,
"grad_norm": 1.234375,
"learning_rate": 0.0008506081521799755,
"loss": 6.4443,
"step": 1435
},
{
"epoch": 0.188321454260119,
"grad_norm": 1.2265625,
"learning_rate": 0.0008491022580490416,
"loss": 6.3961,
"step": 1440
},
{
"epoch": 0.1889753481985222,
"grad_norm": 1.2109375,
"learning_rate": 0.0008475903393956434,
"loss": 6.6002,
"step": 1445
},
{
"epoch": 0.1896292421369254,
"grad_norm": 1.1640625,
"learning_rate": 0.0008460724266728708,
"loss": 6.4222,
"step": 1450
},
{
"epoch": 0.19028313607532857,
"grad_norm": 1.2578125,
"learning_rate": 0.000844548550454546,
"loss": 6.445,
"step": 1455
},
{
"epoch": 0.19093703001373177,
"grad_norm": 1.234375,
"learning_rate": 0.0008430187414346081,
"loss": 6.4051,
"step": 1460
},
{
"epoch": 0.19159092395213495,
"grad_norm": 1.2265625,
"learning_rate": 0.000841483030426495,
"loss": 6.458,
"step": 1465
},
{
"epoch": 0.19224481789053816,
"grad_norm": 1.2734375,
"learning_rate": 0.0008399414483625225,
"loss": 6.4358,
"step": 1470
},
{
"epoch": 0.19289871182894133,
"grad_norm": 1.234375,
"learning_rate": 0.0008383940262932608,
"loss": 6.4806,
"step": 1475
},
{
"epoch": 0.19355260576734454,
"grad_norm": 1.2578125,
"learning_rate": 0.0008368407953869104,
"loss": 6.3711,
"step": 1480
},
{
"epoch": 0.19420649970574771,
"grad_norm": 1.21875,
"learning_rate": 0.0008352817869286727,
"loss": 6.4329,
"step": 1485
},
{
"epoch": 0.19486039364415092,
"grad_norm": 1.1171875,
"learning_rate": 0.0008337170323201212,
"loss": 6.3695,
"step": 1490
},
{
"epoch": 0.1955142875825541,
"grad_norm": 1.234375,
"learning_rate": 0.0008321465630785681,
"loss": 6.4027,
"step": 1495
},
{
"epoch": 0.1961681815209573,
"grad_norm": 1.203125,
"learning_rate": 0.0008305704108364302,
"loss": 6.4392,
"step": 1500
},
{
"epoch": 0.19682207545936048,
"grad_norm": 1.2578125,
"learning_rate": 0.0008289886073405908,
"loss": 6.3566,
"step": 1505
},
{
"epoch": 0.19747596939776368,
"grad_norm": 1.2578125,
"learning_rate": 0.0008274011844517614,
"loss": 6.4445,
"step": 1510
},
{
"epoch": 0.19812986333616686,
"grad_norm": 1.2734375,
"learning_rate": 0.0008258081741438395,
"loss": 6.1971,
"step": 1515
},
{
"epoch": 0.19878375727457007,
"grad_norm": 1.3515625,
"learning_rate": 0.0008242096085032637,
"loss": 6.4111,
"step": 1520
},
{
"epoch": 0.19943765121297324,
"grad_norm": 1.1640625,
"learning_rate": 0.000822605519728369,
"loss": 6.4553,
"step": 1525
},
{
"epoch": 0.20009154515137645,
"grad_norm": 1.2109375,
"learning_rate": 0.000820995940128737,
"loss": 6.4275,
"step": 1530
},
{
"epoch": 0.20074543908977963,
"grad_norm": 1.3515625,
"learning_rate": 0.0008193809021245458,
"loss": 6.3271,
"step": 1535
},
{
"epoch": 0.20139933302818283,
"grad_norm": 1.3046875,
"learning_rate": 0.0008177604382459167,
"loss": 6.5117,
"step": 1540
},
{
"epoch": 0.202053226966586,
"grad_norm": 1.2109375,
"learning_rate": 0.000816134581132259,
"loss": 6.3986,
"step": 1545
},
{
"epoch": 0.2027071209049892,
"grad_norm": 1.1796875,
"learning_rate": 0.000814503363531613,
"loss": 6.4492,
"step": 1550
},
{
"epoch": 0.2033610148433924,
"grad_norm": 1.328125,
"learning_rate": 0.0008128668182999891,
"loss": 6.3814,
"step": 1555
},
{
"epoch": 0.2040149087817956,
"grad_norm": 1.1796875,
"learning_rate": 0.000811224978400708,
"loss": 6.3646,
"step": 1560
},
{
"epoch": 0.20466880272019877,
"grad_norm": 1.328125,
"learning_rate": 0.0008095778769037352,
"loss": 6.3298,
"step": 1565
},
{
"epoch": 0.20532269665860198,
"grad_norm": 1.203125,
"learning_rate": 0.000807925546985015,
"loss": 6.3736,
"step": 1570
},
{
"epoch": 0.20597659059700515,
"grad_norm": 1.2734375,
"learning_rate": 0.0008062680219258034,
"loss": 6.3592,
"step": 1575
},
{
"epoch": 0.20663048453540836,
"grad_norm": 1.203125,
"learning_rate": 0.0008046053351119965,
"loss": 6.36,
"step": 1580
},
{
"epoch": 0.20728437847381154,
"grad_norm": 1.2578125,
"learning_rate": 0.0008029375200334588,
"loss": 6.4186,
"step": 1585
},
{
"epoch": 0.20793827241221474,
"grad_norm": 1.25,
"learning_rate": 0.000801264610283348,
"loss": 6.3836,
"step": 1590
},
{
"epoch": 0.20859216635061792,
"grad_norm": 1.234375,
"learning_rate": 0.0007995866395574396,
"loss": 6.3369,
"step": 1595
},
{
"epoch": 0.20924606028902112,
"grad_norm": 1.2421875,
"learning_rate": 0.0007979036416534462,
"loss": 6.3349,
"step": 1600
},
{
"epoch": 0.2098999542274243,
"grad_norm": 1.4140625,
"learning_rate": 0.0007962156504703387,
"loss": 6.3643,
"step": 1605
},
{
"epoch": 0.2105538481658275,
"grad_norm": 1.171875,
"learning_rate": 0.0007945227000076627,
"loss": 6.3306,
"step": 1610
},
{
"epoch": 0.21120774210423068,
"grad_norm": 1.265625,
"learning_rate": 0.000792824824364853,
"loss": 6.3463,
"step": 1615
},
{
"epoch": 0.2118616360426339,
"grad_norm": 1.2734375,
"learning_rate": 0.0007911220577405485,
"loss": 6.3509,
"step": 1620
},
{
"epoch": 0.21251552998103707,
"grad_norm": 1.4140625,
"learning_rate": 0.0007894144344319014,
"loss": 6.4472,
"step": 1625
},
{
"epoch": 0.21316942391944027,
"grad_norm": 1.3203125,
"learning_rate": 0.0007877019888338881,
"loss": 6.4182,
"step": 1630
},
{
"epoch": 0.21382331785784345,
"grad_norm": 1.2734375,
"learning_rate": 0.0007859847554386145,
"loss": 6.3197,
"step": 1635
},
{
"epoch": 0.21447721179624665,
"grad_norm": 1.2734375,
"learning_rate": 0.0007842627688346239,
"loss": 6.2924,
"step": 1640
},
{
"epoch": 0.21513110573464983,
"grad_norm": 1.15625,
"learning_rate": 0.0007825360637061976,
"loss": 6.2979,
"step": 1645
},
{
"epoch": 0.21578499967305304,
"grad_norm": 1.3046875,
"learning_rate": 0.0007808046748326578,
"loss": 6.3048,
"step": 1650
},
{
"epoch": 0.2164388936114562,
"grad_norm": 1.28125,
"learning_rate": 0.0007790686370876671,
"loss": 6.3447,
"step": 1655
},
{
"epoch": 0.21709278754985942,
"grad_norm": 1.25,
"learning_rate": 0.0007773279854385256,
"loss": 6.3274,
"step": 1660
},
{
"epoch": 0.2177466814882626,
"grad_norm": 1.2578125,
"learning_rate": 0.0007755827549454663,
"loss": 6.2754,
"step": 1665
},
{
"epoch": 0.2184005754266658,
"grad_norm": 1.3125,
"learning_rate": 0.0007738329807609499,
"loss": 6.3975,
"step": 1670
},
{
"epoch": 0.21905446936506898,
"grad_norm": 1.3671875,
"learning_rate": 0.0007720786981289562,
"loss": 6.2348,
"step": 1675
},
{
"epoch": 0.21970836330347218,
"grad_norm": 1.21875,
"learning_rate": 0.0007703199423842736,
"loss": 6.3522,
"step": 1680
},
{
"epoch": 0.22036225724187536,
"grad_norm": 1.1484375,
"learning_rate": 0.0007685567489517887,
"loss": 6.387,
"step": 1685
},
{
"epoch": 0.22101615118027856,
"grad_norm": 1.1953125,
"learning_rate": 0.0007667891533457718,
"loss": 6.3233,
"step": 1690
},
{
"epoch": 0.22167004511868174,
"grad_norm": 1.1953125,
"learning_rate": 0.000765017191169162,
"loss": 6.3719,
"step": 1695
},
{
"epoch": 0.22232393905708495,
"grad_norm": 1.234375,
"learning_rate": 0.0007632408981128494,
"loss": 6.363,
"step": 1700
},
{
"epoch": 0.22297783299548812,
"grad_norm": 1.203125,
"learning_rate": 0.0007614603099549574,
"loss": 6.3034,
"step": 1705
},
{
"epoch": 0.22363172693389133,
"grad_norm": 1.234375,
"learning_rate": 0.0007596754625601211,
"loss": 6.3842,
"step": 1710
},
{
"epoch": 0.2242856208722945,
"grad_norm": 1.15625,
"learning_rate": 0.0007578863918787654,
"loss": 6.2461,
"step": 1715
},
{
"epoch": 0.2249395148106977,
"grad_norm": 1.21875,
"learning_rate": 0.0007560931339463805,
"loss": 6.3564,
"step": 1720
},
{
"epoch": 0.2255934087491009,
"grad_norm": 1.1640625,
"learning_rate": 0.000754295724882796,
"loss": 6.3975,
"step": 1725
},
{
"epoch": 0.2262473026875041,
"grad_norm": 1.34375,
"learning_rate": 0.0007524942008914544,
"loss": 6.354,
"step": 1730
},
{
"epoch": 0.22690119662590727,
"grad_norm": 1.1640625,
"learning_rate": 0.0007506885982586809,
"loss": 6.2258,
"step": 1735
},
{
"epoch": 0.22755509056431047,
"grad_norm": 1.28125,
"learning_rate": 0.000748878953352952,
"loss": 6.4151,
"step": 1740
},
{
"epoch": 0.22820898450271365,
"grad_norm": 1.2421875,
"learning_rate": 0.0007470653026241649,
"loss": 6.3751,
"step": 1745
},
{
"epoch": 0.22886287844111686,
"grad_norm": 1.2109375,
"learning_rate": 0.0007452476826029011,
"loss": 6.3588,
"step": 1750
},
{
"epoch": 0.22951677237952003,
"grad_norm": 1.2734375,
"learning_rate": 0.0007434261298996925,
"loss": 6.2568,
"step": 1755
},
{
"epoch": 0.23017066631792324,
"grad_norm": 1.234375,
"learning_rate": 0.0007416006812042827,
"loss": 6.2871,
"step": 1760
},
{
"epoch": 0.23082456025632642,
"grad_norm": 1.296875,
"learning_rate": 0.0007397713732848884,
"loss": 6.3105,
"step": 1765
},
{
"epoch": 0.23147845419472962,
"grad_norm": 1.265625,
"learning_rate": 0.000737938242987459,
"loss": 6.2848,
"step": 1770
},
{
"epoch": 0.2321323481331328,
"grad_norm": 1.2421875,
"learning_rate": 0.0007361013272349343,
"loss": 6.3153,
"step": 1775
},
{
"epoch": 0.232786242071536,
"grad_norm": 1.140625,
"learning_rate": 0.0007342606630265008,
"loss": 6.2578,
"step": 1780
},
{
"epoch": 0.23344013600993918,
"grad_norm": 1.2421875,
"learning_rate": 0.0007324162874368462,
"loss": 6.2395,
"step": 1785
},
{
"epoch": 0.23409402994834239,
"grad_norm": 1.1640625,
"learning_rate": 0.0007305682376154135,
"loss": 6.2165,
"step": 1790
},
{
"epoch": 0.23474792388674556,
"grad_norm": 1.2890625,
"learning_rate": 0.0007287165507856513,
"loss": 6.3059,
"step": 1795
},
{
"epoch": 0.23540181782514877,
"grad_norm": 1.28125,
"learning_rate": 0.0007268612642442657,
"loss": 6.2721,
"step": 1800
},
{
"epoch": 0.23605571176355195,
"grad_norm": 1.2578125,
"learning_rate": 0.0007250024153604678,
"loss": 6.2669,
"step": 1805
},
{
"epoch": 0.23670960570195515,
"grad_norm": 1.28125,
"learning_rate": 0.0007231400415752213,
"loss": 6.233,
"step": 1810
},
{
"epoch": 0.23736349964035833,
"grad_norm": 1.2578125,
"learning_rate": 0.0007212741804004889,
"loss": 6.2736,
"step": 1815
},
{
"epoch": 0.23801739357876153,
"grad_norm": 1.234375,
"learning_rate": 0.0007194048694184764,
"loss": 6.3255,
"step": 1820
},
{
"epoch": 0.2386712875171647,
"grad_norm": 1.2265625,
"learning_rate": 0.0007175321462808753,
"loss": 6.2782,
"step": 1825
},
{
"epoch": 0.23932518145556791,
"grad_norm": 1.21875,
"learning_rate": 0.0007156560487081052,
"loss": 6.2378,
"step": 1830
},
{
"epoch": 0.2399790753939711,
"grad_norm": 1.203125,
"learning_rate": 0.000713776614488553,
"loss": 6.2961,
"step": 1835
},
{
"epoch": 0.2406329693323743,
"grad_norm": 1.265625,
"learning_rate": 0.0007118938814778132,
"loss": 6.3067,
"step": 1840
},
{
"epoch": 0.24128686327077747,
"grad_norm": 1.2109375,
"learning_rate": 0.0007100078875979239,
"loss": 6.2744,
"step": 1845
},
{
"epoch": 0.24194075720918068,
"grad_norm": 1.296875,
"learning_rate": 0.0007081186708366044,
"loss": 6.2761,
"step": 1850
},
{
"epoch": 0.24259465114758386,
"grad_norm": 1.2265625,
"learning_rate": 0.0007062262692464884,
"loss": 6.2965,
"step": 1855
},
{
"epoch": 0.24324854508598706,
"grad_norm": 1.296875,
"learning_rate": 0.0007043307209443591,
"loss": 6.2799,
"step": 1860
},
{
"epoch": 0.24390243902439024,
"grad_norm": 1.203125,
"learning_rate": 0.0007024320641103812,
"loss": 6.2671,
"step": 1865
},
{
"epoch": 0.24455633296279344,
"grad_norm": 1.6875,
"learning_rate": 0.0007005303369873305,
"loss": 6.3632,
"step": 1870
},
{
"epoch": 0.24521022690119662,
"grad_norm": 1.25,
"learning_rate": 0.0006986255778798253,
"loss": 6.2364,
"step": 1875
},
{
"epoch": 0.24586412083959983,
"grad_norm": 1.28125,
"learning_rate": 0.0006967178251535539,
"loss": 6.2602,
"step": 1880
},
{
"epoch": 0.246518014778003,
"grad_norm": 1.265625,
"learning_rate": 0.0006948071172345022,
"loss": 6.2642,
"step": 1885
},
{
"epoch": 0.2471719087164062,
"grad_norm": 1.1953125,
"learning_rate": 0.00069289349260818,
"loss": 6.2373,
"step": 1890
},
{
"epoch": 0.24782580265480939,
"grad_norm": 1.2734375,
"learning_rate": 0.0006909769898188447,
"loss": 6.1669,
"step": 1895
},
{
"epoch": 0.2484796965932126,
"grad_norm": 1.4609375,
"learning_rate": 0.0006890576474687264,
"loss": 6.2295,
"step": 1900
},
{
"epoch": 0.24913359053161577,
"grad_norm": 1.2578125,
"learning_rate": 0.0006871355042172493,
"loss": 6.1861,
"step": 1905
},
{
"epoch": 0.24978748447001897,
"grad_norm": 1.1796875,
"learning_rate": 0.0006852105987802534,
"loss": 6.2793,
"step": 1910
},
{
"epoch": 0.2504413784084222,
"grad_norm": 1.1640625,
"learning_rate": 0.000683282969929215,
"loss": 6.2589,
"step": 1915
},
{
"epoch": 0.2510952723468253,
"grad_norm": 1.2109375,
"learning_rate": 0.000681352656490465,
"loss": 6.2614,
"step": 1920
},
{
"epoch": 0.25174916628522853,
"grad_norm": 1.1796875,
"learning_rate": 0.0006794196973444078,
"loss": 6.2263,
"step": 1925
},
{
"epoch": 0.25240306022363174,
"grad_norm": 1.296875,
"learning_rate": 0.0006774841314247372,
"loss": 6.1922,
"step": 1930
},
{
"epoch": 0.25305695416203494,
"grad_norm": 1.1484375,
"learning_rate": 0.0006755459977176532,
"loss": 6.3164,
"step": 1935
},
{
"epoch": 0.2537108481004381,
"grad_norm": 1.21875,
"learning_rate": 0.0006736053352610756,
"loss": 6.1636,
"step": 1940
},
{
"epoch": 0.2543647420388413,
"grad_norm": 1.25,
"learning_rate": 0.0006716621831438588,
"loss": 6.2248,
"step": 1945
},
{
"epoch": 0.2550186359772445,
"grad_norm": 1.2578125,
"learning_rate": 0.0006697165805050039,
"loss": 6.2169,
"step": 1950
},
{
"epoch": 0.2556725299156477,
"grad_norm": 1.140625,
"learning_rate": 0.0006677685665328701,
"loss": 6.1363,
"step": 1955
},
{
"epoch": 0.25632642385405086,
"grad_norm": 1.21875,
"learning_rate": 0.0006658181804643862,
"loss": 6.2463,
"step": 1960
},
{
"epoch": 0.25698031779245406,
"grad_norm": 1.25,
"learning_rate": 0.0006638654615842593,
"loss": 6.2385,
"step": 1965
},
{
"epoch": 0.25763421173085727,
"grad_norm": 1.2890625,
"learning_rate": 0.0006619104492241848,
"loss": 6.2521,
"step": 1970
},
{
"epoch": 0.25828810566926047,
"grad_norm": 1.15625,
"learning_rate": 0.0006599531827620523,
"loss": 6.2401,
"step": 1975
},
{
"epoch": 0.2589419996076636,
"grad_norm": 1.2421875,
"learning_rate": 0.0006579937016211547,
"loss": 6.3103,
"step": 1980
},
{
"epoch": 0.2595958935460668,
"grad_norm": 1.28125,
"learning_rate": 0.0006560320452693922,
"loss": 6.1594,
"step": 1985
},
{
"epoch": 0.26024978748447003,
"grad_norm": 1.3984375,
"learning_rate": 0.0006540682532184785,
"loss": 6.2207,
"step": 1990
},
{
"epoch": 0.26090368142287323,
"grad_norm": 1.28125,
"learning_rate": 0.0006521023650231444,
"loss": 6.0819,
"step": 1995
},
{
"epoch": 0.2615575753612764,
"grad_norm": 1.2265625,
"learning_rate": 0.0006501344202803415,
"loss": 6.1979,
"step": 2000
},
{
"epoch": 0.2622114692996796,
"grad_norm": 1.2890625,
"learning_rate": 0.0006481644586284442,
"loss": 6.1735,
"step": 2005
},
{
"epoch": 0.2628653632380828,
"grad_norm": 1.25,
"learning_rate": 0.0006461925197464516,
"loss": 6.2303,
"step": 2010
},
{
"epoch": 0.263519257176486,
"grad_norm": 1.1796875,
"learning_rate": 0.0006442186433531879,
"loss": 6.221,
"step": 2015
},
{
"epoch": 0.26417315111488915,
"grad_norm": 1.2578125,
"learning_rate": 0.0006422428692065038,
"loss": 6.2354,
"step": 2020
},
{
"epoch": 0.26482704505329235,
"grad_norm": 1.375,
"learning_rate": 0.0006402652371024727,
"loss": 6.2178,
"step": 2025
},
{
"epoch": 0.26548093899169556,
"grad_norm": 1.1875,
"learning_rate": 0.0006382857868745929,
"loss": 6.335,
"step": 2030
},
{
"epoch": 0.26613483293009876,
"grad_norm": 1.1875,
"learning_rate": 0.000636304558392982,
"loss": 6.2241,
"step": 2035
},
{
"epoch": 0.2667887268685019,
"grad_norm": 1.328125,
"learning_rate": 0.0006343215915635762,
"loss": 6.1066,
"step": 2040
},
{
"epoch": 0.2674426208069051,
"grad_norm": 1.2578125,
"learning_rate": 0.0006323369263273246,
"loss": 6.2049,
"step": 2045
},
{
"epoch": 0.2680965147453083,
"grad_norm": 1.3046875,
"learning_rate": 0.0006303506026593865,
"loss": 6.1856,
"step": 2050
},
{
"epoch": 0.26875040868371153,
"grad_norm": 1.3203125,
"learning_rate": 0.0006283626605683249,
"loss": 6.2339,
"step": 2055
},
{
"epoch": 0.2694043026221147,
"grad_norm": 1.6484375,
"learning_rate": 0.000626373140095301,
"loss": 6.2062,
"step": 2060
},
{
"epoch": 0.2700581965605179,
"grad_norm": 1.2421875,
"learning_rate": 0.0006243820813132683,
"loss": 6.1619,
"step": 2065
},
{
"epoch": 0.2707120904989211,
"grad_norm": 1.1484375,
"learning_rate": 0.0006223895243261644,
"loss": 6.1684,
"step": 2070
},
{
"epoch": 0.2713659844373243,
"grad_norm": 1.1796875,
"learning_rate": 0.000620395509268104,
"loss": 6.2551,
"step": 2075
},
{
"epoch": 0.27201987837572744,
"grad_norm": 1.0859375,
"learning_rate": 0.0006184000763025703,
"loss": 6.1934,
"step": 2080
},
{
"epoch": 0.27267377231413065,
"grad_norm": 1.1875,
"learning_rate": 0.0006164032656216059,
"loss": 6.2045,
"step": 2085
},
{
"epoch": 0.27332766625253385,
"grad_norm": 1.203125,
"learning_rate": 0.0006144051174450039,
"loss": 6.1961,
"step": 2090
},
{
"epoch": 0.27398156019093706,
"grad_norm": 1.21875,
"learning_rate": 0.0006124056720194963,
"loss": 6.1617,
"step": 2095
},
{
"epoch": 0.2746354541293402,
"grad_norm": 1.1953125,
"learning_rate": 0.000610404969617945,
"loss": 6.0775,
"step": 2100
},
{
"epoch": 0.2752893480677434,
"grad_norm": 1.6640625,
"learning_rate": 0.0006084030505385298,
"loss": 6.1625,
"step": 2105
},
{
"epoch": 0.2759432420061466,
"grad_norm": 1.296875,
"learning_rate": 0.000606399955103937,
"loss": 6.1461,
"step": 2110
},
{
"epoch": 0.2765971359445498,
"grad_norm": 1.125,
"learning_rate": 0.0006043957236605465,
"loss": 6.1243,
"step": 2115
},
{
"epoch": 0.27725102988295297,
"grad_norm": 1.3125,
"learning_rate": 0.0006023903965776203,
"loss": 6.1387,
"step": 2120
},
{
"epoch": 0.2779049238213562,
"grad_norm": 1.078125,
"learning_rate": 0.0006003840142464886,
"loss": 6.1395,
"step": 2125
},
{
"epoch": 0.2785588177597594,
"grad_norm": 1.3359375,
"learning_rate": 0.0005983766170797363,
"loss": 6.1803,
"step": 2130
},
{
"epoch": 0.2792127116981626,
"grad_norm": 1.3046875,
"learning_rate": 0.0005963682455103892,
"loss": 6.219,
"step": 2135
},
{
"epoch": 0.27986660563656574,
"grad_norm": 1.1953125,
"learning_rate": 0.0005943589399910996,
"loss": 6.1649,
"step": 2140
},
{
"epoch": 0.28052049957496894,
"grad_norm": 1.140625,
"learning_rate": 0.0005923487409933316,
"loss": 6.1699,
"step": 2145
},
{
"epoch": 0.28117439351337215,
"grad_norm": 1.21875,
"learning_rate": 0.0005903376890065452,
"loss": 6.2105,
"step": 2150
},
{
"epoch": 0.2818282874517753,
"grad_norm": 1.4375,
"learning_rate": 0.0005883258245373818,
"loss": 6.117,
"step": 2155
},
{
"epoch": 0.2824821813901785,
"grad_norm": 1.1640625,
"learning_rate": 0.0005863131881088478,
"loss": 6.1877,
"step": 2160
},
{
"epoch": 0.2831360753285817,
"grad_norm": 1.3671875,
"learning_rate": 0.0005842998202594984,
"loss": 6.1556,
"step": 2165
},
{
"epoch": 0.2837899692669849,
"grad_norm": 1.171875,
"learning_rate": 0.0005822857615426207,
"loss": 6.1822,
"step": 2170
},
{
"epoch": 0.28444386320538806,
"grad_norm": 1.2421875,
"learning_rate": 0.0005802710525254179,
"loss": 6.2047,
"step": 2175
},
{
"epoch": 0.28509775714379126,
"grad_norm": 1.3203125,
"learning_rate": 0.0005782557337881911,
"loss": 6.1374,
"step": 2180
},
{
"epoch": 0.28575165108219447,
"grad_norm": 1.3828125,
"learning_rate": 0.0005762398459235225,
"loss": 6.1365,
"step": 2185
},
{
"epoch": 0.2864055450205977,
"grad_norm": 1.2421875,
"learning_rate": 0.0005742234295354577,
"loss": 6.0982,
"step": 2190
},
{
"epoch": 0.2870594389590008,
"grad_norm": 1.25,
"learning_rate": 0.0005722065252386881,
"loss": 6.2163,
"step": 2195
},
{
"epoch": 0.28771333289740403,
"grad_norm": 1.234375,
"learning_rate": 0.0005701891736577318,
"loss": 6.1441,
"step": 2200
},
{
"epoch": 0.28836722683580723,
"grad_norm": 1.2578125,
"learning_rate": 0.0005681714154261168,
"loss": 6.1118,
"step": 2205
},
{
"epoch": 0.28902112077421044,
"grad_norm": 1.2109375,
"learning_rate": 0.0005661532911855621,
"loss": 6.1684,
"step": 2210
},
{
"epoch": 0.2896750147126136,
"grad_norm": 1.1875,
"learning_rate": 0.0005641348415851577,
"loss": 6.2018,
"step": 2215
},
{
"epoch": 0.2903289086510168,
"grad_norm": 1.1953125,
"learning_rate": 0.0005621161072805483,
"loss": 6.2055,
"step": 2220
},
{
"epoch": 0.29098280258942,
"grad_norm": 1.296875,
"learning_rate": 0.0005600971289331123,
"loss": 6.0639,
"step": 2225
},
{
"epoch": 0.2916366965278232,
"grad_norm": 1.2421875,
"learning_rate": 0.0005580779472091438,
"loss": 6.1691,
"step": 2230
},
{
"epoch": 0.29229059046622635,
"grad_norm": 1.15625,
"learning_rate": 0.0005560586027790334,
"loss": 6.124,
"step": 2235
},
{
"epoch": 0.29294448440462956,
"grad_norm": 1.2734375,
"learning_rate": 0.0005540391363164491,
"loss": 6.224,
"step": 2240
},
{
"epoch": 0.29359837834303276,
"grad_norm": 1.234375,
"learning_rate": 0.0005520195884975165,
"loss": 6.1268,
"step": 2245
},
{
"epoch": 0.29425227228143597,
"grad_norm": 1.203125,
"learning_rate": 0.00055,
"loss": 6.1298,
"step": 2250
},
{
"epoch": 0.2949061662198391,
"grad_norm": 1.2734375,
"learning_rate": 0.0005479804115024836,
"loss": 6.1443,
"step": 2255
},
{
"epoch": 0.2955600601582423,
"grad_norm": 1.1328125,
"learning_rate": 0.000545960863683551,
"loss": 6.1012,
"step": 2260
},
{
"epoch": 0.2962139540966455,
"grad_norm": 1.265625,
"learning_rate": 0.0005439413972209664,
"loss": 6.1175,
"step": 2265
},
{
"epoch": 0.29686784803504873,
"grad_norm": 1.3046875,
"learning_rate": 0.0005419220527908563,
"loss": 6.1121,
"step": 2270
},
{
"epoch": 0.2975217419734519,
"grad_norm": 1.2890625,
"learning_rate": 0.0005399028710668879,
"loss": 6.1841,
"step": 2275
},
{
"epoch": 0.2981756359118551,
"grad_norm": 1.296875,
"learning_rate": 0.0005378838927194518,
"loss": 6.1723,
"step": 2280
},
{
"epoch": 0.2988295298502583,
"grad_norm": 1.2109375,
"learning_rate": 0.0005358651584148423,
"loss": 6.1083,
"step": 2285
},
{
"epoch": 0.2994834237886615,
"grad_norm": 1.171875,
"learning_rate": 0.000533846708814438,
"loss": 6.0644,
"step": 2290
},
{
"epoch": 0.30013731772706465,
"grad_norm": 1.28125,
"learning_rate": 0.0005318285845738831,
"loss": 6.1333,
"step": 2295
},
{
"epoch": 0.30079121166546785,
"grad_norm": 1.2265625,
"learning_rate": 0.0005298108263422685,
"loss": 6.1305,
"step": 2300
},
{
"epoch": 0.30144510560387106,
"grad_norm": 1.1875,
"learning_rate": 0.0005277934747613122,
"loss": 6.1627,
"step": 2305
},
{
"epoch": 0.30209899954227426,
"grad_norm": 1.1875,
"learning_rate": 0.0005257765704645423,
"loss": 6.0763,
"step": 2310
},
{
"epoch": 0.3027528934806774,
"grad_norm": 1.3671875,
"learning_rate": 0.0005237601540764777,
"loss": 6.1065,
"step": 2315
},
{
"epoch": 0.3034067874190806,
"grad_norm": 1.140625,
"learning_rate": 0.0005217442662118091,
"loss": 6.0723,
"step": 2320
},
{
"epoch": 0.3040606813574838,
"grad_norm": 1.171875,
"learning_rate": 0.0005197289474745822,
"loss": 6.2038,
"step": 2325
},
{
"epoch": 0.304714575295887,
"grad_norm": 1.1953125,
"learning_rate": 0.0005177142384573793,
"loss": 6.2002,
"step": 2330
},
{
"epoch": 0.3053684692342902,
"grad_norm": 1.28125,
"learning_rate": 0.0005157001797405019,
"loss": 6.0739,
"step": 2335
},
{
"epoch": 0.3060223631726934,
"grad_norm": 1.3125,
"learning_rate": 0.0005136868118911523,
"loss": 6.0938,
"step": 2340
},
{
"epoch": 0.3066762571110966,
"grad_norm": 1.234375,
"learning_rate": 0.0005116741754626184,
"loss": 6.144,
"step": 2345
},
{
"epoch": 0.3073301510494998,
"grad_norm": 1.375,
"learning_rate": 0.000509662310993455,
"loss": 6.1117,
"step": 2350
},
{
"epoch": 0.30798404498790294,
"grad_norm": 1.171875,
"learning_rate": 0.0005076512590066686,
"loss": 6.1018,
"step": 2355
},
{
"epoch": 0.30863793892630614,
"grad_norm": 1.2421875,
"learning_rate": 0.0005056410600089004,
"loss": 6.1043,
"step": 2360
},
{
"epoch": 0.30929183286470935,
"grad_norm": 1.2734375,
"learning_rate": 0.000503631754489611,
"loss": 6.1371,
"step": 2365
},
{
"epoch": 0.30994572680311255,
"grad_norm": 1.2109375,
"learning_rate": 0.0005016233829202638,
"loss": 6.0772,
"step": 2370
},
{
"epoch": 0.3105996207415157,
"grad_norm": 1.1484375,
"learning_rate": 0.0004996159857535115,
"loss": 6.1063,
"step": 2375
},
{
"epoch": 0.3112535146799189,
"grad_norm": 1.25,
"learning_rate": 0.0004976096034223799,
"loss": 6.0306,
"step": 2380
},
{
"epoch": 0.3119074086183221,
"grad_norm": 1.1328125,
"learning_rate": 0.0004956042763394536,
"loss": 6.0645,
"step": 2385
},
{
"epoch": 0.3125613025567253,
"grad_norm": 1.2421875,
"learning_rate": 0.0004936000448960631,
"loss": 6.0675,
"step": 2390
},
{
"epoch": 0.31321519649512847,
"grad_norm": 1.328125,
"learning_rate": 0.0004915969494614701,
"loss": 6.0552,
"step": 2395
},
{
"epoch": 0.3138690904335317,
"grad_norm": 1.2734375,
"learning_rate": 0.0004895950303820552,
"loss": 6.0857,
"step": 2400
},
{
"epoch": 0.3145229843719349,
"grad_norm": 1.6328125,
"learning_rate": 0.00048759432798050397,
"loss": 6.0189,
"step": 2405
},
{
"epoch": 0.3151768783103381,
"grad_norm": 1.28125,
"learning_rate": 0.00048559488255499626,
"loss": 6.0809,
"step": 2410
},
{
"epoch": 0.31583077224874123,
"grad_norm": 1.203125,
"learning_rate": 0.0004835967343783941,
"loss": 6.0609,
"step": 2415
},
{
"epoch": 0.31648466618714444,
"grad_norm": 1.3125,
"learning_rate": 0.0004815999236974298,
"loss": 6.0588,
"step": 2420
},
{
"epoch": 0.31713856012554764,
"grad_norm": 1.1875,
"learning_rate": 0.00047960449073189605,
"loss": 6.1468,
"step": 2425
},
{
"epoch": 0.31779245406395085,
"grad_norm": 1.15625,
"learning_rate": 0.0004776104756738359,
"loss": 6.1777,
"step": 2430
},
{
"epoch": 0.318446348002354,
"grad_norm": 1.25,
"learning_rate": 0.0004756179186867319,
"loss": 6.1324,
"step": 2435
},
{
"epoch": 0.3191002419407572,
"grad_norm": 1.2265625,
"learning_rate": 0.000473626859904699,
"loss": 6.1012,
"step": 2440
},
{
"epoch": 0.3197541358791604,
"grad_norm": 1.2734375,
"learning_rate": 0.0004716373394316752,
"loss": 6.1039,
"step": 2445
},
{
"epoch": 0.3204080298175636,
"grad_norm": 1.359375,
"learning_rate": 0.0004696493973406135,
"loss": 6.0409,
"step": 2450
},
{
"epoch": 0.32106192375596676,
"grad_norm": 1.1171875,
"learning_rate": 0.0004676630736726754,
"loss": 6.0591,
"step": 2455
},
{
"epoch": 0.32171581769436997,
"grad_norm": 1.234375,
"learning_rate": 0.00046567840843642387,
"loss": 6.0989,
"step": 2460
},
{
"epoch": 0.32236971163277317,
"grad_norm": 1.1953125,
"learning_rate": 0.00046369544160701807,
"loss": 6.1061,
"step": 2465
},
{
"epoch": 0.3230236055711764,
"grad_norm": 1.3125,
"learning_rate": 0.0004617142131254073,
"loss": 6.058,
"step": 2470
},
{
"epoch": 0.3236774995095795,
"grad_norm": 1.21875,
"learning_rate": 0.00045973476289752727,
"loss": 6.0669,
"step": 2475
},
{
"epoch": 0.32433139344798273,
"grad_norm": 1.234375,
"learning_rate": 0.00045775713079349636,
"loss": 6.0408,
"step": 2480
},
{
"epoch": 0.32498528738638593,
"grad_norm": 1.2890625,
"learning_rate": 0.00045578135664681196,
"loss": 6.0931,
"step": 2485
},
{
"epoch": 0.32563918132478914,
"grad_norm": 1.2578125,
"learning_rate": 0.00045380748025354844,
"loss": 6.0582,
"step": 2490
},
{
"epoch": 0.3262930752631923,
"grad_norm": 1.390625,
"learning_rate": 0.000451835541371556,
"loss": 6.1096,
"step": 2495
},
{
"epoch": 0.3269469692015955,
"grad_norm": 1.2421875,
"learning_rate": 0.0004498655797196586,
"loss": 6.0578,
"step": 2500
},
{
"epoch": 0.3276008631399987,
"grad_norm": 1.2578125,
"learning_rate": 0.00044789763497685565,
"loss": 6.0324,
"step": 2505
},
{
"epoch": 0.3282547570784019,
"grad_norm": 1.296875,
"learning_rate": 0.0004459317467815216,
"loss": 6.1035,
"step": 2510
},
{
"epoch": 0.32890865101680505,
"grad_norm": 1.2265625,
"learning_rate": 0.0004439679547306079,
"loss": 6.1331,
"step": 2515
},
{
"epoch": 0.32956254495520826,
"grad_norm": 1.1875,
"learning_rate": 0.00044200629837884534,
"loss": 6.053,
"step": 2520
},
{
"epoch": 0.33021643889361146,
"grad_norm": 1.21875,
"learning_rate": 0.0004400468172379476,
"loss": 6.0992,
"step": 2525
},
{
"epoch": 0.33087033283201467,
"grad_norm": 1.2265625,
"learning_rate": 0.0004380895507758155,
"loss": 6.061,
"step": 2530
},
{
"epoch": 0.3315242267704178,
"grad_norm": 1.3359375,
"learning_rate": 0.0004361345384157408,
"loss": 6.0071,
"step": 2535
},
{
"epoch": 0.332178120708821,
"grad_norm": 1.2578125,
"learning_rate": 0.0004341818195356141,
"loss": 5.9888,
"step": 2540
},
{
"epoch": 0.33283201464722423,
"grad_norm": 1.203125,
"learning_rate": 0.00043223143346713,
"loss": 6.0574,
"step": 2545
},
{
"epoch": 0.33348590858562743,
"grad_norm": 1.2421875,
"learning_rate": 0.00043028341949499625,
"loss": 6.0241,
"step": 2550
},
{
"epoch": 0.3341398025240306,
"grad_norm": 1.328125,
"learning_rate": 0.00042833781685614115,
"loss": 6.105,
"step": 2555
},
{
"epoch": 0.3347936964624338,
"grad_norm": 1.265625,
"learning_rate": 0.0004263946647389245,
"loss": 6.0046,
"step": 2560
},
{
"epoch": 0.335447590400837,
"grad_norm": 1.1796875,
"learning_rate": 0.0004244540022823469,
"loss": 6.0276,
"step": 2565
},
{
"epoch": 0.3361014843392402,
"grad_norm": 1.234375,
"learning_rate": 0.0004225158685752629,
"loss": 6.0544,
"step": 2570
},
{
"epoch": 0.33675537827764335,
"grad_norm": 1.484375,
"learning_rate": 0.0004205803026555923,
"loss": 6.0594,
"step": 2575
},
{
"epoch": 0.33740927221604655,
"grad_norm": 1.25,
"learning_rate": 0.000418647343509535,
"loss": 6.0191,
"step": 2580
},
{
"epoch": 0.33806316615444976,
"grad_norm": 1.2578125,
"learning_rate": 0.0004167170300707851,
"loss": 5.9642,
"step": 2585
},
{
"epoch": 0.33871706009285296,
"grad_norm": 1.2421875,
"learning_rate": 0.0004147894012197466,
"loss": 6.0204,
"step": 2590
},
{
"epoch": 0.3393709540312561,
"grad_norm": 1.2265625,
"learning_rate": 0.000412864495782751,
"loss": 6.0704,
"step": 2595
},
{
"epoch": 0.3400248479696593,
"grad_norm": 1.2421875,
"learning_rate": 0.0004109423525312738,
"loss": 6.0715,
"step": 2600
},
{
"epoch": 0.3406787419080625,
"grad_norm": 1.21875,
"learning_rate": 0.0004090230101811554,
"loss": 6.0644,
"step": 2605
},
{
"epoch": 0.3413326358464657,
"grad_norm": 1.359375,
"learning_rate": 0.0004071065073918201,
"loss": 6.0276,
"step": 2610
},
{
"epoch": 0.3419865297848689,
"grad_norm": 1.1953125,
"learning_rate": 0.0004051928827654977,
"loss": 6.0337,
"step": 2615
},
{
"epoch": 0.3426404237232721,
"grad_norm": 1.40625,
"learning_rate": 0.0004032821748464463,
"loss": 6.0298,
"step": 2620
},
{
"epoch": 0.3432943176616753,
"grad_norm": 1.203125,
"learning_rate": 0.00040137442212017494,
"loss": 6.0832,
"step": 2625
},
{
"epoch": 0.3439482116000785,
"grad_norm": 1.2109375,
"learning_rate": 0.0003994696630126696,
"loss": 6.0048,
"step": 2630
},
{
"epoch": 0.34460210553848164,
"grad_norm": 1.2265625,
"learning_rate": 0.00039756793588961893,
"loss": 6.0598,
"step": 2635
},
{
"epoch": 0.34525599947688485,
"grad_norm": 1.15625,
"learning_rate": 0.00039566927905564087,
"loss": 6.0864,
"step": 2640
},
{
"epoch": 0.34590989341528805,
"grad_norm": 1.125,
"learning_rate": 0.0003937737307535117,
"loss": 6.0621,
"step": 2645
},
{
"epoch": 0.34656378735369125,
"grad_norm": 1.2890625,
"learning_rate": 0.0003918813291633958,
"loss": 6.0506,
"step": 2650
},
{
"epoch": 0.3472176812920944,
"grad_norm": 1.2265625,
"learning_rate": 0.0003899921124020761,
"loss": 5.9977,
"step": 2655
},
{
"epoch": 0.3478715752304976,
"grad_norm": 1.28125,
"learning_rate": 0.000388106118522187,
"loss": 5.9824,
"step": 2660
},
{
"epoch": 0.3485254691689008,
"grad_norm": 1.296875,
"learning_rate": 0.0003862233855114471,
"loss": 6.0342,
"step": 2665
},
{
"epoch": 0.349179363107304,
"grad_norm": 1.21875,
"learning_rate": 0.0003843439512918949,
"loss": 6.0025,
"step": 2670
},
{
"epoch": 0.34983325704570717,
"grad_norm": 1.2109375,
"learning_rate": 0.00038246785371912474,
"loss": 6.0821,
"step": 2675
},
{
"epoch": 0.3504871509841104,
"grad_norm": 1.1484375,
"learning_rate": 0.00038059513058152363,
"loss": 6.0068,
"step": 2680
},
{
"epoch": 0.3511410449225136,
"grad_norm": 1.25,
"learning_rate": 0.00037872581959951115,
"loss": 5.9847,
"step": 2685
},
{
"epoch": 0.3517949388609168,
"grad_norm": 1.25,
"learning_rate": 0.00037685995842477884,
"loss": 6.1195,
"step": 2690
},
{
"epoch": 0.35244883279931993,
"grad_norm": 1.25,
"learning_rate": 0.0003749975846395325,
"loss": 6.0077,
"step": 2695
},
{
"epoch": 0.35310272673772314,
"grad_norm": 1.2265625,
"learning_rate": 0.0003731387357557344,
"loss": 6.0799,
"step": 2700
},
{
"epoch": 0.35375662067612634,
"grad_norm": 1.328125,
"learning_rate": 0.00037128344921434875,
"loss": 6.0137,
"step": 2705
},
{
"epoch": 0.35441051461452955,
"grad_norm": 1.28125,
"learning_rate": 0.00036943176238458665,
"loss": 5.9969,
"step": 2710
},
{
"epoch": 0.3550644085529327,
"grad_norm": 1.453125,
"learning_rate": 0.0003675837125631538,
"loss": 6.1131,
"step": 2715
},
{
"epoch": 0.3557183024913359,
"grad_norm": 1.2890625,
"learning_rate": 0.00036573933697349936,
"loss": 6.0157,
"step": 2720
},
{
"epoch": 0.3563721964297391,
"grad_norm": 1.3828125,
"learning_rate": 0.00036389867276506586,
"loss": 5.9917,
"step": 2725
},
{
"epoch": 0.3570260903681423,
"grad_norm": 1.296875,
"learning_rate": 0.0003620617570125411,
"loss": 6.0519,
"step": 2730
},
{
"epoch": 0.35767998430654546,
"grad_norm": 1.3046875,
"learning_rate": 0.0003602286267151117,
"loss": 6.0774,
"step": 2735
},
{
"epoch": 0.35833387824494867,
"grad_norm": 1.21875,
"learning_rate": 0.0003583993187957173,
"loss": 6.0401,
"step": 2740
},
{
"epoch": 0.35898777218335187,
"grad_norm": 1.171875,
"learning_rate": 0.0003565738701003074,
"loss": 5.9721,
"step": 2745
},
{
"epoch": 0.3596416661217551,
"grad_norm": 1.40625,
"learning_rate": 0.0003547523173970989,
"loss": 6.0046,
"step": 2750
},
{
"epoch": 0.3602955600601582,
"grad_norm": 1.234375,
"learning_rate": 0.00035293469737583525,
"loss": 6.0032,
"step": 2755
},
{
"epoch": 0.36094945399856143,
"grad_norm": 1.2734375,
"learning_rate": 0.0003511210466470481,
"loss": 6.0029,
"step": 2760
},
{
"epoch": 0.36160334793696464,
"grad_norm": 1.59375,
"learning_rate": 0.00034931140174131913,
"loss": 6.0457,
"step": 2765
},
{
"epoch": 0.36225724187536784,
"grad_norm": 1.1328125,
"learning_rate": 0.0003475057991085455,
"loss": 6.0271,
"step": 2770
},
{
"epoch": 0.362911135813771,
"grad_norm": 1.1484375,
"learning_rate": 0.000345704275117204,
"loss": 6.0467,
"step": 2775
},
{
"epoch": 0.3635650297521742,
"grad_norm": 1.203125,
"learning_rate": 0.0003439068660536197,
"loss": 6.0158,
"step": 2780
},
{
"epoch": 0.3642189236905774,
"grad_norm": 1.21875,
"learning_rate": 0.0003421136081212347,
"loss": 6.0005,
"step": 2785
},
{
"epoch": 0.3648728176289806,
"grad_norm": 1.359375,
"learning_rate": 0.00034032453743987903,
"loss": 5.9828,
"step": 2790
},
{
"epoch": 0.36552671156738376,
"grad_norm": 1.2578125,
"learning_rate": 0.0003385396900450426,
"loss": 6.0036,
"step": 2795
},
{
"epoch": 0.36618060550578696,
"grad_norm": 1.1796875,
"learning_rate": 0.00033675910188715063,
"loss": 6.0571,
"step": 2800
},
{
"epoch": 0.36683449944419017,
"grad_norm": 1.2109375,
"learning_rate": 0.0003349828088308382,
"loss": 5.9794,
"step": 2805
},
{
"epoch": 0.36748839338259337,
"grad_norm": 1.296875,
"learning_rate": 0.0003332108466542281,
"loss": 5.9179,
"step": 2810
},
{
"epoch": 0.3681422873209965,
"grad_norm": 1.2109375,
"learning_rate": 0.00033144325104821125,
"loss": 6.0386,
"step": 2815
},
{
"epoch": 0.3687961812593997,
"grad_norm": 1.1953125,
"learning_rate": 0.0003296800576157266,
"loss": 6.0303,
"step": 2820
},
{
"epoch": 0.36945007519780293,
"grad_norm": 1.28125,
"learning_rate": 0.00032792130187104396,
"loss": 5.9665,
"step": 2825
},
{
"epoch": 0.37010396913620613,
"grad_norm": 1.2109375,
"learning_rate": 0.00032616701923905017,
"loss": 6.0108,
"step": 2830
},
{
"epoch": 0.3707578630746093,
"grad_norm": 1.234375,
"learning_rate": 0.00032441724505453387,
"loss": 5.9921,
"step": 2835
},
{
"epoch": 0.3714117570130125,
"grad_norm": 1.171875,
"learning_rate": 0.00032267201456147456,
"loss": 5.9639,
"step": 2840
},
{
"epoch": 0.3720656509514157,
"grad_norm": 1.21875,
"learning_rate": 0.00032093136291233294,
"loss": 6.0043,
"step": 2845
},
{
"epoch": 0.3727195448898189,
"grad_norm": 1.421875,
"learning_rate": 0.0003191953251673423,
"loss": 6.0208,
"step": 2850
},
{
"epoch": 0.37337343882822205,
"grad_norm": 1.2421875,
"learning_rate": 0.0003174639362938026,
"loss": 5.9572,
"step": 2855
},
{
"epoch": 0.37402733276662525,
"grad_norm": 1.328125,
"learning_rate": 0.0003157372311653763,
"loss": 5.9954,
"step": 2860
},
{
"epoch": 0.37468122670502846,
"grad_norm": 1.3046875,
"learning_rate": 0.0003140152445613854,
"loss": 6.0061,
"step": 2865
},
{
"epoch": 0.3753351206434316,
"grad_norm": 1.1953125,
"learning_rate": 0.00031229801116611206,
"loss": 6.0016,
"step": 2870
},
{
"epoch": 0.3759890145818348,
"grad_norm": 1.21875,
"learning_rate": 0.0003105855655680986,
"loss": 5.946,
"step": 2875
},
{
"epoch": 0.376642908520238,
"grad_norm": 1.2265625,
"learning_rate": 0.00030887794225945144,
"loss": 6.0011,
"step": 2880
},
{
"epoch": 0.3772968024586412,
"grad_norm": 1.265625,
"learning_rate": 0.0003071751756351471,
"loss": 6.0071,
"step": 2885
},
{
"epoch": 0.3779506963970444,
"grad_norm": 1.171875,
"learning_rate": 0.0003054772999923376,
"loss": 5.9815,
"step": 2890
},
{
"epoch": 0.3786045903354476,
"grad_norm": 1.1875,
"learning_rate": 0.0003037843495296613,
"loss": 6.0234,
"step": 2895
},
{
"epoch": 0.3792584842738508,
"grad_norm": 1.1171875,
"learning_rate": 0.0003020963583465539,
"loss": 5.9862,
"step": 2900
},
{
"epoch": 0.379912378212254,
"grad_norm": 1.3203125,
"learning_rate": 0.0003004133604425606,
"loss": 5.9259,
"step": 2905
},
{
"epoch": 0.38056627215065714,
"grad_norm": 1.15625,
"learning_rate": 0.0002987353897166518,
"loss": 6.0624,
"step": 2910
},
{
"epoch": 0.38122016608906034,
"grad_norm": 1.2890625,
"learning_rate": 0.00029706247996654135,
"loss": 5.9947,
"step": 2915
},
{
"epoch": 0.38187406002746355,
"grad_norm": 1.203125,
"learning_rate": 0.00029539466488800347,
"loss": 5.9619,
"step": 2920
},
{
"epoch": 0.38252795396586675,
"grad_norm": 1.2890625,
"learning_rate": 0.0002937319780741966,
"loss": 5.9979,
"step": 2925
},
{
"epoch": 0.3831818479042699,
"grad_norm": 1.171875,
"learning_rate": 0.00029207445301498503,
"loss": 5.9849,
"step": 2930
},
{
"epoch": 0.3838357418426731,
"grad_norm": 1.3359375,
"learning_rate": 0.0002904221230962648,
"loss": 6.0669,
"step": 2935
},
{
"epoch": 0.3844896357810763,
"grad_norm": 1.09375,
"learning_rate": 0.0002887750215992919,
"loss": 6.0018,
"step": 2940
},
{
"epoch": 0.3851435297194795,
"grad_norm": 1.1875,
"learning_rate": 0.0002871331817000109,
"loss": 5.9798,
"step": 2945
},
{
"epoch": 0.38579742365788267,
"grad_norm": 1.1640625,
"learning_rate": 0.0002854966364683872,
"loss": 5.9072,
"step": 2950
},
{
"epoch": 0.38645131759628587,
"grad_norm": 1.2578125,
"learning_rate": 0.00028386541886774096,
"loss": 6.0124,
"step": 2955
},
{
"epoch": 0.3871052115346891,
"grad_norm": 1.3671875,
"learning_rate": 0.0002822395617540834,
"loss": 5.9465,
"step": 2960
},
{
"epoch": 0.3877591054730923,
"grad_norm": 1.3359375,
"learning_rate": 0.0002806190978754541,
"loss": 5.9195,
"step": 2965
},
{
"epoch": 0.38841299941149543,
"grad_norm": 1.25,
"learning_rate": 0.000279004059871263,
"loss": 5.9989,
"step": 2970
},
{
"epoch": 0.38906689334989863,
"grad_norm": 1.1328125,
"learning_rate": 0.0002773944802716311,
"loss": 6.0261,
"step": 2975
},
{
"epoch": 0.38972078728830184,
"grad_norm": 1.1796875,
"learning_rate": 0.0002757903914967364,
"loss": 6.0452,
"step": 2980
},
{
"epoch": 0.39037468122670504,
"grad_norm": 1.2265625,
"learning_rate": 0.0002741918258561607,
"loss": 5.9528,
"step": 2985
},
{
"epoch": 0.3910285751651082,
"grad_norm": 1.2578125,
"learning_rate": 0.0002725988155482386,
"loss": 5.9283,
"step": 2990
},
{
"epoch": 0.3916824691035114,
"grad_norm": 1.2265625,
"learning_rate": 0.0002710113926594092,
"loss": 5.9506,
"step": 2995
},
{
"epoch": 0.3923363630419146,
"grad_norm": 1.265625,
"learning_rate": 0.00026942958916356994,
"loss": 5.9272,
"step": 3000
},
{
"epoch": 0.3929902569803178,
"grad_norm": 1.1796875,
"learning_rate": 0.00026785343692143195,
"loss": 5.9715,
"step": 3005
},
{
"epoch": 0.39364415091872096,
"grad_norm": 1.1796875,
"learning_rate": 0.00026628296767987873,
"loss": 5.9852,
"step": 3010
},
{
"epoch": 0.39429804485712416,
"grad_norm": 1.15625,
"learning_rate": 0.0002647182130713274,
"loss": 5.9364,
"step": 3015
},
{
"epoch": 0.39495193879552737,
"grad_norm": 1.3671875,
"learning_rate": 0.0002631592046130896,
"loss": 6.0256,
"step": 3020
},
{
"epoch": 0.3956058327339306,
"grad_norm": 1.2734375,
"learning_rate": 0.00026160597370673914,
"loss": 5.9274,
"step": 3025
},
{
"epoch": 0.3962597266723337,
"grad_norm": 1.21875,
"learning_rate": 0.0002600585516374776,
"loss": 5.8797,
"step": 3030
},
{
"epoch": 0.39691362061073693,
"grad_norm": 1.15625,
"learning_rate": 0.0002585169695735049,
"loss": 5.9591,
"step": 3035
},
{
"epoch": 0.39756751454914013,
"grad_norm": 1.2109375,
"learning_rate": 0.0002569812585653919,
"loss": 5.8988,
"step": 3040
},
{
"epoch": 0.39822140848754334,
"grad_norm": 1.2421875,
"learning_rate": 0.0002554514495454543,
"loss": 6.0227,
"step": 3045
},
{
"epoch": 0.3988753024259465,
"grad_norm": 1.2265625,
"learning_rate": 0.00025392757332712935,
"loss": 5.8842,
"step": 3050
},
{
"epoch": 0.3995291963643497,
"grad_norm": 1.2421875,
"learning_rate": 0.0002524096606043568,
"loss": 5.9514,
"step": 3055
},
{
"epoch": 0.4001830903027529,
"grad_norm": 1.171875,
"learning_rate": 0.0002508977419509586,
"loss": 5.9149,
"step": 3060
},
{
"epoch": 0.4008369842411561,
"grad_norm": 1.2421875,
"learning_rate": 0.00024939184782002443,
"loss": 6.0804,
"step": 3065
},
{
"epoch": 0.40149087817955925,
"grad_norm": 1.2734375,
"learning_rate": 0.0002478920085432982,
"loss": 5.9113,
"step": 3070
},
{
"epoch": 0.40214477211796246,
"grad_norm": 1.2734375,
"learning_rate": 0.0002463982543305666,
"loss": 5.9224,
"step": 3075
},
{
"epoch": 0.40279866605636566,
"grad_norm": 1.3203125,
"learning_rate": 0.00024491061526905075,
"loss": 5.9271,
"step": 3080
},
{
"epoch": 0.40345255999476887,
"grad_norm": 1.34375,
"learning_rate": 0.0002434291213228003,
"loss": 6.0283,
"step": 3085
},
{
"epoch": 0.404106453933172,
"grad_norm": 1.2578125,
"learning_rate": 0.00024195380233209008,
"loss": 5.8895,
"step": 3090
},
{
"epoch": 0.4047603478715752,
"grad_norm": 1.2265625,
"learning_rate": 0.00024048468801281895,
"loss": 5.9462,
"step": 3095
},
{
"epoch": 0.4054142418099784,
"grad_norm": 1.2578125,
"learning_rate": 0.0002390218079559109,
"loss": 5.937,
"step": 3100
},
{
"epoch": 0.40606813574838163,
"grad_norm": 1.2265625,
"learning_rate": 0.00023756519162671937,
"loss": 5.9899,
"step": 3105
},
{
"epoch": 0.4067220296867848,
"grad_norm": 1.1484375,
"learning_rate": 0.00023611486836443404,
"loss": 6.0421,
"step": 3110
},
{
"epoch": 0.407375923625188,
"grad_norm": 1.28125,
"learning_rate": 0.0002346708673814889,
"loss": 5.9629,
"step": 3115
},
{
"epoch": 0.4080298175635912,
"grad_norm": 1.1640625,
"learning_rate": 0.0002332332177629748,
"loss": 6.0724,
"step": 3120
},
{
"epoch": 0.4086837115019944,
"grad_norm": 1.328125,
"learning_rate": 0.00023180194846605365,
"loss": 5.9444,
"step": 3125
},
{
"epoch": 0.40933760544039755,
"grad_norm": 1.21875,
"learning_rate": 0.0002303770883193744,
"loss": 6.0158,
"step": 3130
},
{
"epoch": 0.40999149937880075,
"grad_norm": 1.328125,
"learning_rate": 0.00022895866602249274,
"loss": 6.0312,
"step": 3135
},
{
"epoch": 0.41064539331720395,
"grad_norm": 1.2734375,
"learning_rate": 0.0002275467101452935,
"loss": 5.9407,
"step": 3140
},
{
"epoch": 0.41129928725560716,
"grad_norm": 1.296875,
"learning_rate": 0.0002261412491274146,
"loss": 5.9993,
"step": 3145
},
{
"epoch": 0.4119531811940103,
"grad_norm": 1.203125,
"learning_rate": 0.00022474231127767385,
"loss": 6.0375,
"step": 3150
},
{
"epoch": 0.4126070751324135,
"grad_norm": 1.2421875,
"learning_rate": 0.00022334992477350028,
"loss": 5.9187,
"step": 3155
},
{
"epoch": 0.4132609690708167,
"grad_norm": 1.2109375,
"learning_rate": 0.00022196411766036488,
"loss": 5.937,
"step": 3160
},
{
"epoch": 0.4139148630092199,
"grad_norm": 1.2265625,
"learning_rate": 0.0002205849178512167,
"loss": 5.9587,
"step": 3165
},
{
"epoch": 0.4145687569476231,
"grad_norm": 1.296875,
"learning_rate": 0.00021921235312592047,
"loss": 5.8824,
"step": 3170
},
{
"epoch": 0.4152226508860263,
"grad_norm": 1.2109375,
"learning_rate": 0.00021784645113069677,
"loss": 6.024,
"step": 3175
},
{
"epoch": 0.4158765448244295,
"grad_norm": 1.203125,
"learning_rate": 0.00021648723937756542,
"loss": 5.9667,
"step": 3180
},
{
"epoch": 0.4165304387628327,
"grad_norm": 1.21875,
"learning_rate": 0.00021513474524379126,
"loss": 6.0237,
"step": 3185
},
{
"epoch": 0.41718433270123584,
"grad_norm": 1.171875,
"learning_rate": 0.00021378899597133266,
"loss": 5.9058,
"step": 3190
},
{
"epoch": 0.41783822663963904,
"grad_norm": 1.046875,
"learning_rate": 0.00021245001866629322,
"loss": 6.0313,
"step": 3195
},
{
"epoch": 0.41849212057804225,
"grad_norm": 1.1640625,
"learning_rate": 0.0002111178402983751,
"loss": 5.9804,
"step": 3200
},
{
"epoch": 0.41914601451644545,
"grad_norm": 1.2578125,
"learning_rate": 0.0002097924877003362,
"loss": 5.8738,
"step": 3205
},
{
"epoch": 0.4197999084548486,
"grad_norm": 1.2578125,
"learning_rate": 0.00020847398756745005,
"loss": 5.9223,
"step": 3210
},
{
"epoch": 0.4204538023932518,
"grad_norm": 1.3515625,
"learning_rate": 0.0002071623664569671,
"loss": 5.985,
"step": 3215
},
{
"epoch": 0.421107696331655,
"grad_norm": 1.21875,
"learning_rate": 0.00020585765078758072,
"loss": 5.9831,
"step": 3220
},
{
"epoch": 0.4217615902700582,
"grad_norm": 1.6953125,
"learning_rate": 0.00020455986683889498,
"loss": 5.9639,
"step": 3225
},
{
"epoch": 0.42241548420846137,
"grad_norm": 1.21875,
"learning_rate": 0.0002032690407508949,
"loss": 5.995,
"step": 3230
},
{
"epoch": 0.42306937814686457,
"grad_norm": 1.1953125,
"learning_rate": 0.00020198519852341996,
"loss": 5.8706,
"step": 3235
},
{
"epoch": 0.4237232720852678,
"grad_norm": 1.3125,
"learning_rate": 0.00020070836601564123,
"loss": 6.0156,
"step": 3240
},
{
"epoch": 0.424377166023671,
"grad_norm": 1.265625,
"learning_rate": 0.00019943856894553906,
"loss": 5.9168,
"step": 3245
},
{
"epoch": 0.42503105996207413,
"grad_norm": 1.28125,
"learning_rate": 0.00019817583288938662,
"loss": 5.8642,
"step": 3250
},
{
"epoch": 0.42568495390047734,
"grad_norm": 1.3203125,
"learning_rate": 0.0001969201832812337,
"loss": 5.9422,
"step": 3255
},
{
"epoch": 0.42633884783888054,
"grad_norm": 1.21875,
"learning_rate": 0.0001956716454123946,
"loss": 6.0222,
"step": 3260
},
{
"epoch": 0.42699274177728375,
"grad_norm": 1.25,
"learning_rate": 0.00019443024443093932,
"loss": 5.9175,
"step": 3265
},
{
"epoch": 0.4276466357156869,
"grad_norm": 1.2421875,
"learning_rate": 0.00019319600534118615,
"loss": 5.866,
"step": 3270
},
{
"epoch": 0.4283005296540901,
"grad_norm": 1.3671875,
"learning_rate": 0.00019196895300319862,
"loss": 5.9764,
"step": 3275
},
{
"epoch": 0.4289544235924933,
"grad_norm": 1.3046875,
"learning_rate": 0.0001907491121322844,
"loss": 5.9223,
"step": 3280
},
{
"epoch": 0.4296083175308965,
"grad_norm": 1.2734375,
"learning_rate": 0.00018953650729849796,
"loss": 5.969,
"step": 3285
},
{
"epoch": 0.43026221146929966,
"grad_norm": 1.2265625,
"learning_rate": 0.00018833116292614507,
"loss": 5.8853,
"step": 3290
},
{
"epoch": 0.43091610540770287,
"grad_norm": 1.1953125,
"learning_rate": 0.0001871331032932916,
"loss": 5.9664,
"step": 3295
},
{
"epoch": 0.43156999934610607,
"grad_norm": 1.2421875,
"learning_rate": 0.00018594235253127373,
"loss": 5.9315,
"step": 3300
},
{
"epoch": 0.4322238932845093,
"grad_norm": 1.265625,
"learning_rate": 0.0001847589346242123,
"loss": 5.8507,
"step": 3305
},
{
"epoch": 0.4328777872229124,
"grad_norm": 1.2265625,
"learning_rate": 0.0001835828734085297,
"loss": 5.8807,
"step": 3310
},
{
"epoch": 0.43353168116131563,
"grad_norm": 1.296875,
"learning_rate": 0.00018241419257246987,
"loss": 5.934,
"step": 3315
},
{
"epoch": 0.43418557509971883,
"grad_norm": 1.28125,
"learning_rate": 0.00018125291565562065,
"loss": 6.0495,
"step": 3320
},
{
"epoch": 0.43483946903812204,
"grad_norm": 1.3046875,
"learning_rate": 0.00018009906604844059,
"loss": 5.992,
"step": 3325
},
{
"epoch": 0.4354933629765252,
"grad_norm": 1.265625,
"learning_rate": 0.00017895266699178674,
"loss": 5.9047,
"step": 3330
},
{
"epoch": 0.4361472569149284,
"grad_norm": 1.25,
"learning_rate": 0.00017781374157644714,
"loss": 5.9345,
"step": 3335
},
{
"epoch": 0.4368011508533316,
"grad_norm": 1.3203125,
"learning_rate": 0.0001766823127426761,
"loss": 5.963,
"step": 3340
},
{
"epoch": 0.4374550447917348,
"grad_norm": 1.234375,
"learning_rate": 0.00017555840327973077,
"loss": 5.9402,
"step": 3345
},
{
"epoch": 0.43810893873013795,
"grad_norm": 1.234375,
"learning_rate": 0.0001744420358254138,
"loss": 5.9138,
"step": 3350
},
{
"epoch": 0.43876283266854116,
"grad_norm": 1.1796875,
"learning_rate": 0.00017333323286561643,
"loss": 5.8638,
"step": 3355
},
{
"epoch": 0.43941672660694436,
"grad_norm": 1.2890625,
"learning_rate": 0.00017223201673386524,
"loss": 5.954,
"step": 3360
},
{
"epoch": 0.44007062054534757,
"grad_norm": 1.171875,
"learning_rate": 0.00017113840961087353,
"loss": 5.9336,
"step": 3365
},
{
"epoch": 0.4407245144837507,
"grad_norm": 1.2890625,
"learning_rate": 0.00017005243352409332,
"loss": 5.9056,
"step": 3370
},
{
"epoch": 0.4413784084221539,
"grad_norm": 1.3828125,
"learning_rate": 0.00016897411034727216,
"loss": 5.9029,
"step": 3375
},
{
"epoch": 0.44203230236055713,
"grad_norm": 1.25,
"learning_rate": 0.00016790346180001292,
"loss": 5.9735,
"step": 3380
},
{
"epoch": 0.44268619629896033,
"grad_norm": 1.3203125,
"learning_rate": 0.00016684050944733577,
"loss": 5.9242,
"step": 3385
},
{
"epoch": 0.4433400902373635,
"grad_norm": 1.2421875,
"learning_rate": 0.00016578527469924374,
"loss": 5.9295,
"step": 3390
},
{
"epoch": 0.4439939841757667,
"grad_norm": 1.15625,
"learning_rate": 0.0001647377788102923,
"loss": 5.8523,
"step": 3395
},
{
"epoch": 0.4446478781141699,
"grad_norm": 1.234375,
"learning_rate": 0.00016369804287916026,
"loss": 5.9583,
"step": 3400
},
{
"epoch": 0.4453017720525731,
"grad_norm": 1.2890625,
"learning_rate": 0.00016266608784822542,
"loss": 5.8399,
"step": 3405
},
{
"epoch": 0.44595566599097625,
"grad_norm": 1.2109375,
"learning_rate": 0.00016164193450314242,
"loss": 5.975,
"step": 3410
},
{
"epoch": 0.44660955992937945,
"grad_norm": 1.2578125,
"learning_rate": 0.00016062560347242434,
"loss": 5.9339,
"step": 3415
},
{
"epoch": 0.44726345386778266,
"grad_norm": 1.2890625,
"learning_rate": 0.0001596171152270271,
"loss": 5.9264,
"step": 3420
},
{
"epoch": 0.44791734780618586,
"grad_norm": 1.34375,
"learning_rate": 0.00015861649007993712,
"loss": 5.8358,
"step": 3425
},
{
"epoch": 0.448571241744589,
"grad_norm": 1.1796875,
"learning_rate": 0.00015762374818576187,
"loss": 5.7856,
"step": 3430
},
{
"epoch": 0.4492251356829922,
"grad_norm": 1.265625,
"learning_rate": 0.00015663890954032485,
"loss": 5.8397,
"step": 3435
},
{
"epoch": 0.4498790296213954,
"grad_norm": 1.203125,
"learning_rate": 0.0001556619939802615,
"loss": 5.9512,
"step": 3440
},
{
"epoch": 0.4505329235597986,
"grad_norm": 1.5078125,
"learning_rate": 0.00015469302118262056,
"loss": 5.9691,
"step": 3445
},
{
"epoch": 0.4511868174982018,
"grad_norm": 1.1171875,
"learning_rate": 0.0001537320106644679,
"loss": 6.0215,
"step": 3450
},
{
"epoch": 0.451840711436605,
"grad_norm": 1.21875,
"learning_rate": 0.00015277898178249266,
"loss": 5.9671,
"step": 3455
},
{
"epoch": 0.4524946053750082,
"grad_norm": 1.2109375,
"learning_rate": 0.00015183395373261768,
"loss": 5.9521,
"step": 3460
},
{
"epoch": 0.4531484993134114,
"grad_norm": 1.296875,
"learning_rate": 0.00015089694554961322,
"loss": 5.983,
"step": 3465
},
{
"epoch": 0.45380239325181454,
"grad_norm": 1.1640625,
"learning_rate": 0.0001499679761067131,
"loss": 5.9697,
"step": 3470
},
{
"epoch": 0.45445628719021774,
"grad_norm": 1.1796875,
"learning_rate": 0.0001490470641152345,
"loss": 5.9389,
"step": 3475
},
{
"epoch": 0.45511018112862095,
"grad_norm": 1.2890625,
"learning_rate": 0.00014813422812420162,
"loss": 5.9026,
"step": 3480
},
{
"epoch": 0.45576407506702415,
"grad_norm": 1.171875,
"learning_rate": 0.00014722948651997158,
"loss": 5.8682,
"step": 3485
},
{
"epoch": 0.4564179690054273,
"grad_norm": 1.2578125,
"learning_rate": 0.00014633285752586411,
"loss": 5.9187,
"step": 3490
},
{
"epoch": 0.4570718629438305,
"grad_norm": 1.21875,
"learning_rate": 0.0001454443592017949,
"loss": 5.9503,
"step": 3495
},
{
"epoch": 0.4577257568822337,
"grad_norm": 1.2734375,
"learning_rate": 0.00014456400944391147,
"loss": 5.9215,
"step": 3500
},
{
"epoch": 0.4583796508206369,
"grad_norm": 1.171875,
"learning_rate": 0.00014369182598423247,
"loss": 6.0538,
"step": 3505
},
{
"epoch": 0.45903354475904007,
"grad_norm": 1.1953125,
"learning_rate": 0.0001428278263902913,
"loss": 5.9739,
"step": 3510
},
{
"epoch": 0.4596874386974433,
"grad_norm": 1.2109375,
"learning_rate": 0.0001419720280647814,
"loss": 5.9492,
"step": 3515
},
{
"epoch": 0.4603413326358465,
"grad_norm": 1.25,
"learning_rate": 0.00014112444824520648,
"loss": 5.8897,
"step": 3520
},
{
"epoch": 0.4609952265742497,
"grad_norm": 1.265625,
"learning_rate": 0.00014028510400353287,
"loss": 5.8429,
"step": 3525
},
{
"epoch": 0.46164912051265283,
"grad_norm": 1.1328125,
"learning_rate": 0.00013945401224584546,
"loss": 5.9574,
"step": 3530
},
{
"epoch": 0.46230301445105604,
"grad_norm": 1.1875,
"learning_rate": 0.00013863118971200813,
"loss": 5.9376,
"step": 3535
},
{
"epoch": 0.46295690838945924,
"grad_norm": 1.1484375,
"learning_rate": 0.00013781665297532512,
"loss": 5.9652,
"step": 3540
},
{
"epoch": 0.46361080232786245,
"grad_norm": 1.59375,
"learning_rate": 0.0001370104184422085,
"loss": 5.926,
"step": 3545
},
{
"epoch": 0.4642646962662656,
"grad_norm": 1.1953125,
"learning_rate": 0.00013621250235184727,
"loss": 6.0264,
"step": 3550
},
{
"epoch": 0.4649185902046688,
"grad_norm": 1.3203125,
"learning_rate": 0.00013542292077587995,
"loss": 5.866,
"step": 3555
},
{
"epoch": 0.465572484143072,
"grad_norm": 1.2734375,
"learning_rate": 0.0001346416896180712,
"loss": 5.9559,
"step": 3560
},
{
"epoch": 0.4662263780814752,
"grad_norm": 1.2265625,
"learning_rate": 0.0001338688246139918,
"loss": 5.8429,
"step": 3565
},
{
"epoch": 0.46688027201987836,
"grad_norm": 1.28125,
"learning_rate": 0.00013310434133070065,
"loss": 5.961,
"step": 3570
},
{
"epoch": 0.46753416595828157,
"grad_norm": 1.265625,
"learning_rate": 0.00013234825516643254,
"loss": 5.9198,
"step": 3575
},
{
"epoch": 0.46818805989668477,
"grad_norm": 1.2734375,
"learning_rate": 0.00013160058135028692,
"loss": 5.9682,
"step": 3580
},
{
"epoch": 0.4688419538350879,
"grad_norm": 1.15625,
"learning_rate": 0.00013086133494192174,
"loss": 5.9185,
"step": 3585
},
{
"epoch": 0.4694958477734911,
"grad_norm": 1.2578125,
"learning_rate": 0.00013013053083125013,
"loss": 5.9181,
"step": 3590
},
{
"epoch": 0.47014974171189433,
"grad_norm": 1.2890625,
"learning_rate": 0.00012940818373814012,
"loss": 5.9342,
"step": 3595
},
{
"epoch": 0.47080363565029754,
"grad_norm": 1.2734375,
"learning_rate": 0.0001286943082121183,
"loss": 6.0114,
"step": 3600
},
{
"epoch": 0.4714575295887007,
"grad_norm": 1.1875,
"learning_rate": 0.000127988918632077,
"loss": 5.9554,
"step": 3605
},
{
"epoch": 0.4721114235271039,
"grad_norm": 1.3125,
"learning_rate": 0.0001272920292059845,
"loss": 5.9866,
"step": 3610
},
{
"epoch": 0.4727653174655071,
"grad_norm": 1.1875,
"learning_rate": 0.00012660365397059855,
"loss": 5.9026,
"step": 3615
},
{
"epoch": 0.4734192114039103,
"grad_norm": 1.2578125,
"learning_rate": 0.00012592380679118438,
"loss": 5.9458,
"step": 3620
},
{
"epoch": 0.47407310534231345,
"grad_norm": 1.1953125,
"learning_rate": 0.00012525250136123458,
"loss": 5.9151,
"step": 3625
},
{
"epoch": 0.47472699928071665,
"grad_norm": 1.1875,
"learning_rate": 0.00012458975120219402,
"loss": 6.0135,
"step": 3630
},
{
"epoch": 0.47538089321911986,
"grad_norm": 1.234375,
"learning_rate": 0.00012393556966318691,
"loss": 5.8727,
"step": 3635
},
{
"epoch": 0.47603478715752306,
"grad_norm": 1.1796875,
"learning_rate": 0.0001232899699207481,
"loss": 5.8746,
"step": 3640
},
{
"epoch": 0.4766886810959262,
"grad_norm": 1.2265625,
"learning_rate": 0.00012265296497855827,
"loss": 5.8976,
"step": 3645
},
{
"epoch": 0.4773425750343294,
"grad_norm": 1.390625,
"learning_rate": 0.00012202456766718093,
"loss": 6.0284,
"step": 3650
},
{
"epoch": 0.4779964689727326,
"grad_norm": 1.3125,
"learning_rate": 0.00012140479064380477,
"loss": 5.9292,
"step": 3655
},
{
"epoch": 0.47865036291113583,
"grad_norm": 1.2578125,
"learning_rate": 0.00012079364639198862,
"loss": 5.8886,
"step": 3660
},
{
"epoch": 0.479304256849539,
"grad_norm": 1.25,
"learning_rate": 0.00012019114722140965,
"loss": 5.9441,
"step": 3665
},
{
"epoch": 0.4799581507879422,
"grad_norm": 1.3046875,
"learning_rate": 0.00011959730526761583,
"loss": 5.9149,
"step": 3670
},
{
"epoch": 0.4806120447263454,
"grad_norm": 1.3671875,
"learning_rate": 0.0001190121324917813,
"loss": 5.9622,
"step": 3675
},
{
"epoch": 0.4812659386647486,
"grad_norm": 1.2265625,
"learning_rate": 0.0001184356406804655,
"loss": 5.8466,
"step": 3680
},
{
"epoch": 0.48191983260315174,
"grad_norm": 1.2890625,
"learning_rate": 0.00011786784144537563,
"loss": 5.9519,
"step": 3685
},
{
"epoch": 0.48257372654155495,
"grad_norm": 1.2890625,
"learning_rate": 0.00011730874622313302,
"loss": 5.8682,
"step": 3690
},
{
"epoch": 0.48322762047995815,
"grad_norm": 1.296875,
"learning_rate": 0.00011675836627504263,
"loss": 5.9235,
"step": 3695
},
{
"epoch": 0.48388151441836136,
"grad_norm": 1.234375,
"learning_rate": 0.00011621671268686605,
"loss": 5.9482,
"step": 3700
},
{
"epoch": 0.4845354083567645,
"grad_norm": 1.2265625,
"learning_rate": 0.0001156837963685986,
"loss": 5.8796,
"step": 3705
},
{
"epoch": 0.4851893022951677,
"grad_norm": 1.3359375,
"learning_rate": 0.00011515962805424926,
"loss": 5.9607,
"step": 3710
},
{
"epoch": 0.4858431962335709,
"grad_norm": 1.28125,
"learning_rate": 0.0001146442183016245,
"loss": 5.8856,
"step": 3715
},
{
"epoch": 0.4864970901719741,
"grad_norm": 1.1875,
"learning_rate": 0.00011413757749211603,
"loss": 5.9737,
"step": 3720
},
{
"epoch": 0.48715098411037727,
"grad_norm": 1.2109375,
"learning_rate": 0.00011363971583049091,
"loss": 5.8906,
"step": 3725
},
{
"epoch": 0.4878048780487805,
"grad_norm": 1.234375,
"learning_rate": 0.00011315064334468685,
"loss": 5.9051,
"step": 3730
},
{
"epoch": 0.4884587719871837,
"grad_norm": 1.2265625,
"learning_rate": 0.00011267036988560957,
"loss": 5.9951,
"step": 3735
},
{
"epoch": 0.4891126659255869,
"grad_norm": 1.234375,
"learning_rate": 0.00011219890512693479,
"loss": 5.9118,
"step": 3740
},
{
"epoch": 0.48976655986399004,
"grad_norm": 1.359375,
"learning_rate": 0.00011173625856491323,
"loss": 5.9421,
"step": 3745
},
{
"epoch": 0.49042045380239324,
"grad_norm": 1.21875,
"learning_rate": 0.00011128243951817938,
"loss": 5.9842,
"step": 3750
},
{
"epoch": 0.49107434774079645,
"grad_norm": 1.25,
"learning_rate": 0.00011083745712756366,
"loss": 5.8857,
"step": 3755
},
{
"epoch": 0.49172824167919965,
"grad_norm": 1.21875,
"learning_rate": 0.0001104013203559086,
"loss": 5.8274,
"step": 3760
},
{
"epoch": 0.4923821356176028,
"grad_norm": 1.2734375,
"learning_rate": 0.00010997403798788789,
"loss": 5.9559,
"step": 3765
},
{
"epoch": 0.493036029556006,
"grad_norm": 1.2421875,
"learning_rate": 0.00010955561862982986,
"loss": 5.9266,
"step": 3770
},
{
"epoch": 0.4936899234944092,
"grad_norm": 1.1875,
"learning_rate": 0.00010914607070954404,
"loss": 5.9572,
"step": 3775
},
{
"epoch": 0.4943438174328124,
"grad_norm": 1.2578125,
"learning_rate": 0.000108745402476151,
"loss": 5.9317,
"step": 3780
},
{
"epoch": 0.49499771137121557,
"grad_norm": 1.2421875,
"learning_rate": 0.00010835362199991681,
"loss": 5.932,
"step": 3785
},
{
"epoch": 0.49565160530961877,
"grad_norm": 1.4375,
"learning_rate": 0.00010797073717209013,
"loss": 5.8616,
"step": 3790
},
{
"epoch": 0.496305499248022,
"grad_norm": 1.3125,
"learning_rate": 0.00010759675570474315,
"loss": 5.8934,
"step": 3795
},
{
"epoch": 0.4969593931864252,
"grad_norm": 1.265625,
"learning_rate": 0.00010723168513061665,
"loss": 5.9575,
"step": 3800
},
{
"epoch": 0.49761328712482833,
"grad_norm": 1.3203125,
"learning_rate": 0.00010687553280296799,
"loss": 5.8958,
"step": 3805
},
{
"epoch": 0.49826718106323153,
"grad_norm": 1.25,
"learning_rate": 0.000106528305895423,
"loss": 5.9284,
"step": 3810
},
{
"epoch": 0.49892107500163474,
"grad_norm": 1.21875,
"learning_rate": 0.00010619001140183163,
"loss": 5.9427,
"step": 3815
},
{
"epoch": 0.49957496894003794,
"grad_norm": 1.171875,
"learning_rate": 0.00010586065613612695,
"loss": 5.9246,
"step": 3820
},
{
"epoch": 0.5002288628784411,
"grad_norm": 1.171875,
"learning_rate": 0.00010554024673218806,
"loss": 5.8101,
"step": 3825
},
{
"epoch": 0.5008827568168444,
"grad_norm": 1.28125,
"learning_rate": 0.0001052287896437062,
"loss": 5.9353,
"step": 3830
},
{
"epoch": 0.5015366507552474,
"grad_norm": 1.265625,
"learning_rate": 0.00010492629114405506,
"loss": 5.9345,
"step": 3835
},
{
"epoch": 0.5021905446936507,
"grad_norm": 1.2265625,
"learning_rate": 0.00010463275732616432,
"loss": 5.9345,
"step": 3840
},
{
"epoch": 0.5028444386320539,
"grad_norm": 1.2734375,
"learning_rate": 0.00010434819410239672,
"loss": 5.9252,
"step": 3845
},
{
"epoch": 0.5034983325704571,
"grad_norm": 1.203125,
"learning_rate": 0.00010407260720442939,
"loss": 5.9419,
"step": 3850
},
{
"epoch": 0.5041522265088603,
"grad_norm": 1.3359375,
"learning_rate": 0.00010380600218313794,
"loss": 5.9057,
"step": 3855
},
{
"epoch": 0.5048061204472635,
"grad_norm": 1.3671875,
"learning_rate": 0.00010354838440848502,
"loss": 5.9136,
"step": 3860
},
{
"epoch": 0.5054600143856667,
"grad_norm": 1.1875,
"learning_rate": 0.00010329975906941192,
"loss": 5.9535,
"step": 3865
},
{
"epoch": 0.5061139083240699,
"grad_norm": 1.203125,
"learning_rate": 0.0001030601311737342,
"loss": 5.8979,
"step": 3870
},
{
"epoch": 0.506767802262473,
"grad_norm": 1.2734375,
"learning_rate": 0.00010282950554804084,
"loss": 5.876,
"step": 3875
},
{
"epoch": 0.5074216962008762,
"grad_norm": 1.3515625,
"learning_rate": 0.00010260788683759686,
"loss": 5.8516,
"step": 3880
},
{
"epoch": 0.5080755901392794,
"grad_norm": 1.34375,
"learning_rate": 0.00010239527950624975,
"loss": 5.8997,
"step": 3885
},
{
"epoch": 0.5087294840776826,
"grad_norm": 1.234375,
"learning_rate": 0.00010219168783633997,
"loss": 5.9395,
"step": 3890
},
{
"epoch": 0.5093833780160858,
"grad_norm": 1.2265625,
"learning_rate": 0.000101997115928614,
"loss": 5.9722,
"step": 3895
},
{
"epoch": 0.510037271954489,
"grad_norm": 1.2578125,
"learning_rate": 0.00010181156770214242,
"loss": 5.8886,
"step": 3900
},
{
"epoch": 0.5106911658928922,
"grad_norm": 1.328125,
"learning_rate": 0.00010163504689424062,
"loss": 5.8754,
"step": 3905
},
{
"epoch": 0.5113450598312954,
"grad_norm": 1.3203125,
"learning_rate": 0.00010146755706039344,
"loss": 5.9246,
"step": 3910
},
{
"epoch": 0.5119989537696985,
"grad_norm": 1.2734375,
"learning_rate": 0.0001013091015741838,
"loss": 5.8788,
"step": 3915
},
{
"epoch": 0.5126528477081017,
"grad_norm": 1.171875,
"learning_rate": 0.00010115968362722469,
"loss": 5.9029,
"step": 3920
},
{
"epoch": 0.5133067416465049,
"grad_norm": 1.2109375,
"learning_rate": 0.00010101930622909478,
"loss": 5.9025,
"step": 3925
},
{
"epoch": 0.5139606355849081,
"grad_norm": 1.2265625,
"learning_rate": 0.0001008879722072778,
"loss": 5.9398,
"step": 3930
},
{
"epoch": 0.5146145295233113,
"grad_norm": 1.359375,
"learning_rate": 0.0001007656842071058,
"loss": 5.8907,
"step": 3935
},
{
"epoch": 0.5152684234617145,
"grad_norm": 1.2890625,
"learning_rate": 0.00010065244469170559,
"loss": 5.9414,
"step": 3940
},
{
"epoch": 0.5159223174001177,
"grad_norm": 1.15625,
"learning_rate": 0.00010054825594194929,
"loss": 5.926,
"step": 3945
},
{
"epoch": 0.5165762113385209,
"grad_norm": 1.2109375,
"learning_rate": 0.00010045312005640844,
"loss": 5.9548,
"step": 3950
},
{
"epoch": 0.517230105276924,
"grad_norm": 1.2265625,
"learning_rate": 0.00010036703895131144,
"loss": 5.9586,
"step": 3955
},
{
"epoch": 0.5178839992153272,
"grad_norm": 1.2890625,
"learning_rate": 0.00010029001436050538,
"loss": 6.0724,
"step": 3960
},
{
"epoch": 0.5185378931537304,
"grad_norm": 1.234375,
"learning_rate": 0.00010022204783542078,
"loss": 5.9234,
"step": 3965
},
{
"epoch": 0.5191917870921336,
"grad_norm": 1.2265625,
"learning_rate": 0.0001001631407450405,
"loss": 5.8681,
"step": 3970
},
{
"epoch": 0.5198456810305369,
"grad_norm": 1.25,
"learning_rate": 0.00010011329427587207,
"loss": 5.9682,
"step": 3975
},
{
"epoch": 0.5204995749689401,
"grad_norm": 1.3359375,
"learning_rate": 0.00010007250943192382,
"loss": 5.8965,
"step": 3980
},
{
"epoch": 0.5211534689073433,
"grad_norm": 1.2734375,
"learning_rate": 0.00010004078703468479,
"loss": 5.8735,
"step": 3985
},
{
"epoch": 0.5218073628457465,
"grad_norm": 1.2109375,
"learning_rate": 0.00010001812772310801,
"loss": 5.9093,
"step": 3990
},
{
"epoch": 0.5224612567841496,
"grad_norm": 1.2890625,
"learning_rate": 0.00010000453195359765,
"loss": 5.8683,
"step": 3995
},
{
"epoch": 0.5231151507225528,
"grad_norm": 1.25,
"learning_rate": 0.0001,
"loss": 5.9889,
"step": 4000
}
],
"logging_steps": 5,
"max_steps": 4000,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 5305221834670080.0,
"train_batch_size": 32,
"trial_name": null,
"trial_params": null
}