{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.4,
"eval_steps": 500,
"global_step": 2000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.001,
"grad_norm": 184.6030731201172,
"learning_rate": 1.6000000000000001e-06,
"loss": 319.5776,
"step": 5
},
{
"epoch": 0.002,
"grad_norm": 166.8455047607422,
"learning_rate": 3.6e-06,
"loss": 321.4675,
"step": 10
},
{
"epoch": 0.003,
"grad_norm": 138.33668518066406,
"learning_rate": 5.600000000000001e-06,
"loss": 321.0479,
"step": 15
},
{
"epoch": 0.004,
"grad_norm": 163.59259033203125,
"learning_rate": 7.6e-06,
"loss": 325.7438,
"step": 20
},
{
"epoch": 0.005,
"grad_norm": 162.9120330810547,
"learning_rate": 9.600000000000001e-06,
"loss": 323.9409,
"step": 25
},
{
"epoch": 0.006,
"grad_norm": 126.21514129638672,
"learning_rate": 1.16e-05,
"loss": 310.5008,
"step": 30
},
{
"epoch": 0.007,
"grad_norm": 104.5123062133789,
"learning_rate": 1.3600000000000002e-05,
"loss": 312.7666,
"step": 35
},
{
"epoch": 0.008,
"grad_norm": 101.64288330078125,
"learning_rate": 1.56e-05,
"loss": 305.1989,
"step": 40
},
{
"epoch": 0.009,
"grad_norm": 102.09917449951172,
"learning_rate": 1.76e-05,
"loss": 307.8038,
"step": 45
},
{
"epoch": 0.01,
"grad_norm": 104.21722412109375,
"learning_rate": 1.9600000000000002e-05,
"loss": 320.1353,
"step": 50
},
{
"epoch": 0.011,
"grad_norm": 93.92383575439453,
"learning_rate": 2.16e-05,
"loss": 304.7655,
"step": 55
},
{
"epoch": 0.012,
"grad_norm": 114.69617462158203,
"learning_rate": 2.36e-05,
"loss": 305.9618,
"step": 60
},
{
"epoch": 0.013,
"grad_norm": 93.69319915771484,
"learning_rate": 2.5600000000000002e-05,
"loss": 310.8797,
"step": 65
},
{
"epoch": 0.014,
"grad_norm": 109.1821060180664,
"learning_rate": 2.7600000000000003e-05,
"loss": 300.2823,
"step": 70
},
{
"epoch": 0.015,
"grad_norm": 103.80460357666016,
"learning_rate": 2.96e-05,
"loss": 293.9528,
"step": 75
},
{
"epoch": 0.016,
"grad_norm": 106.84497833251953,
"learning_rate": 3.16e-05,
"loss": 296.8524,
"step": 80
},
{
"epoch": 0.017,
"grad_norm": 97.91087341308594,
"learning_rate": 3.3600000000000004e-05,
"loss": 312.3261,
"step": 85
},
{
"epoch": 0.018,
"grad_norm": 111.58818817138672,
"learning_rate": 3.56e-05,
"loss": 306.8122,
"step": 90
},
{
"epoch": 0.019,
"grad_norm": 102.35470581054688,
"learning_rate": 3.76e-05,
"loss": 309.0235,
"step": 95
},
{
"epoch": 0.02,
"grad_norm": 117.13568115234375,
"learning_rate": 3.960000000000001e-05,
"loss": 301.4674,
"step": 100
},
{
"epoch": 0.021,
"grad_norm": 111.54915618896484,
"learning_rate": 4.16e-05,
"loss": 305.648,
"step": 105
},
{
"epoch": 0.022,
"grad_norm": 100.69993591308594,
"learning_rate": 4.36e-05,
"loss": 301.0534,
"step": 110
},
{
"epoch": 0.023,
"grad_norm": 118.74501037597656,
"learning_rate": 4.5600000000000004e-05,
"loss": 299.9809,
"step": 115
},
{
"epoch": 0.024,
"grad_norm": 108.8770980834961,
"learning_rate": 4.76e-05,
"loss": 303.6106,
"step": 120
},
{
"epoch": 0.025,
"grad_norm": 101.70016479492188,
"learning_rate": 4.96e-05,
"loss": 296.1799,
"step": 125
},
{
"epoch": 0.026,
"grad_norm": 100.83229064941406,
"learning_rate": 5.16e-05,
"loss": 299.5976,
"step": 130
},
{
"epoch": 0.027,
"grad_norm": 110.32823181152344,
"learning_rate": 5.360000000000001e-05,
"loss": 299.0243,
"step": 135
},
{
"epoch": 0.028,
"grad_norm": 132.75369262695312,
"learning_rate": 5.560000000000001e-05,
"loss": 296.0466,
"step": 140
},
{
"epoch": 0.029,
"grad_norm": 87.60545349121094,
"learning_rate": 5.76e-05,
"loss": 291.5091,
"step": 145
},
{
"epoch": 0.03,
"grad_norm": 86.51393127441406,
"learning_rate": 5.96e-05,
"loss": 299.5217,
"step": 150
},
{
"epoch": 0.031,
"grad_norm": 111.37022399902344,
"learning_rate": 6.16e-05,
"loss": 282.0177,
"step": 155
},
{
"epoch": 0.032,
"grad_norm": 87.67730712890625,
"learning_rate": 6.36e-05,
"loss": 294.2152,
"step": 160
},
{
"epoch": 0.033,
"grad_norm": 107.94450378417969,
"learning_rate": 6.560000000000001e-05,
"loss": 300.385,
"step": 165
},
{
"epoch": 0.034,
"grad_norm": 130.67694091796875,
"learning_rate": 6.76e-05,
"loss": 241.1595,
"step": 170
},
{
"epoch": 0.035,
"grad_norm": 108.5428695678711,
"learning_rate": 6.96e-05,
"loss": 236.5823,
"step": 175
},
{
"epoch": 0.036,
"grad_norm": 100.71643829345703,
"learning_rate": 7.16e-05,
"loss": 276.0929,
"step": 180
},
{
"epoch": 0.037,
"grad_norm": 85.25595092773438,
"learning_rate": 7.36e-05,
"loss": 281.2445,
"step": 185
},
{
"epoch": 0.038,
"grad_norm": 85.13512420654297,
"learning_rate": 7.560000000000001e-05,
"loss": 292.1499,
"step": 190
},
{
"epoch": 0.039,
"grad_norm": 116.6955795288086,
"learning_rate": 7.76e-05,
"loss": 282.8511,
"step": 195
},
{
"epoch": 0.04,
"grad_norm": 120.2426528930664,
"learning_rate": 7.960000000000001e-05,
"loss": 263.451,
"step": 200
},
{
"epoch": 0.041,
"grad_norm": 96.3780517578125,
"learning_rate": 8.16e-05,
"loss": 296.5316,
"step": 205
},
{
"epoch": 0.042,
"grad_norm": 111.3336410522461,
"learning_rate": 8.36e-05,
"loss": 292.5496,
"step": 210
},
{
"epoch": 0.043,
"grad_norm": 78.72579956054688,
"learning_rate": 8.560000000000001e-05,
"loss": 283.5232,
"step": 215
},
{
"epoch": 0.044,
"grad_norm": 90.24775695800781,
"learning_rate": 8.76e-05,
"loss": 284.9789,
"step": 220
},
{
"epoch": 0.045,
"grad_norm": 79.07009887695312,
"learning_rate": 8.960000000000001e-05,
"loss": 283.898,
"step": 225
},
{
"epoch": 0.046,
"grad_norm": 78.58618927001953,
"learning_rate": 9.16e-05,
"loss": 292.8704,
"step": 230
},
{
"epoch": 0.047,
"grad_norm": 290.9330749511719,
"learning_rate": 9.360000000000001e-05,
"loss": 294.0916,
"step": 235
},
{
"epoch": 0.048,
"grad_norm": 94.39144134521484,
"learning_rate": 9.56e-05,
"loss": 279.7254,
"step": 240
},
{
"epoch": 0.049,
"grad_norm": 77.19213104248047,
"learning_rate": 9.76e-05,
"loss": 285.9852,
"step": 245
},
{
"epoch": 0.05,
"grad_norm": 101.7437515258789,
"learning_rate": 9.960000000000001e-05,
"loss": 249.4468,
"step": 250
},
{
"epoch": 0.051,
"grad_norm": 93.58489990234375,
"learning_rate": 0.0001016,
"loss": 273.2887,
"step": 255
},
{
"epoch": 0.052,
"grad_norm": 72.4750747680664,
"learning_rate": 0.00010360000000000001,
"loss": 279.6227,
"step": 260
},
{
"epoch": 0.053,
"grad_norm": 82.14293670654297,
"learning_rate": 0.0001056,
"loss": 283.8576,
"step": 265
},
{
"epoch": 0.054,
"grad_norm": 89.74528503417969,
"learning_rate": 0.00010760000000000001,
"loss": 230.3749,
"step": 270
},
{
"epoch": 0.055,
"grad_norm": 102.13854217529297,
"learning_rate": 0.00010960000000000001,
"loss": 286.7239,
"step": 275
},
{
"epoch": 0.056,
"grad_norm": 88.80033111572266,
"learning_rate": 0.00011160000000000002,
"loss": 292.9791,
"step": 280
},
{
"epoch": 0.057,
"grad_norm": 86.31920623779297,
"learning_rate": 0.0001136,
"loss": 297.6509,
"step": 285
},
{
"epoch": 0.058,
"grad_norm": 91.43080139160156,
"learning_rate": 0.00011559999999999999,
"loss": 292.7598,
"step": 290
},
{
"epoch": 0.059,
"grad_norm": 71.60067749023438,
"learning_rate": 0.0001176,
"loss": 256.386,
"step": 295
},
{
"epoch": 0.06,
"grad_norm": 92.36524963378906,
"learning_rate": 0.00011960000000000001,
"loss": 264.7678,
"step": 300
},
{
"epoch": 0.061,
"grad_norm": 128.7174530029297,
"learning_rate": 0.0001216,
"loss": 246.7081,
"step": 305
},
{
"epoch": 0.062,
"grad_norm": 88.78849792480469,
"learning_rate": 0.0001236,
"loss": 290.4893,
"step": 310
},
{
"epoch": 0.063,
"grad_norm": 81.30330657958984,
"learning_rate": 0.00012560000000000002,
"loss": 247.1457,
"step": 315
},
{
"epoch": 0.064,
"grad_norm": 101.5293197631836,
"learning_rate": 0.0001276,
"loss": 228.2218,
"step": 320
},
{
"epoch": 0.065,
"grad_norm": 74.30409240722656,
"learning_rate": 0.0001296,
"loss": 250.0866,
"step": 325
},
{
"epoch": 0.066,
"grad_norm": 72.12100982666016,
"learning_rate": 0.0001316,
"loss": 280.8592,
"step": 330
},
{
"epoch": 0.067,
"grad_norm": 98.41854095458984,
"learning_rate": 0.00013360000000000002,
"loss": 252.9652,
"step": 335
},
{
"epoch": 0.068,
"grad_norm": 93.92510986328125,
"learning_rate": 0.00013560000000000002,
"loss": 281.9821,
"step": 340
},
{
"epoch": 0.069,
"grad_norm": 85.45738220214844,
"learning_rate": 0.00013759999999999998,
"loss": 283.5235,
"step": 345
},
{
"epoch": 0.07,
"grad_norm": 162.42868041992188,
"learning_rate": 0.0001396,
"loss": 269.317,
"step": 350
},
{
"epoch": 0.071,
"grad_norm": 98.22898864746094,
"learning_rate": 0.0001416,
"loss": 278.7544,
"step": 355
},
{
"epoch": 0.072,
"grad_norm": 207.04397583007812,
"learning_rate": 0.0001436,
"loss": 263.1506,
"step": 360
},
{
"epoch": 0.073,
"grad_norm": 184.2711639404297,
"learning_rate": 0.00014560000000000002,
"loss": 248.193,
"step": 365
},
{
"epoch": 0.074,
"grad_norm": 91.50098419189453,
"learning_rate": 0.0001476,
"loss": 282.5412,
"step": 370
},
{
"epoch": 0.075,
"grad_norm": 84.67757415771484,
"learning_rate": 0.0001496,
"loss": 268.9463,
"step": 375
},
{
"epoch": 0.076,
"grad_norm": 96.04291534423828,
"learning_rate": 0.0001516,
"loss": 274.9769,
"step": 380
},
{
"epoch": 0.077,
"grad_norm": 105.64541625976562,
"learning_rate": 0.00015360000000000002,
"loss": 245.0583,
"step": 385
},
{
"epoch": 0.078,
"grad_norm": 81.34778594970703,
"learning_rate": 0.00015560000000000001,
"loss": 267.3725,
"step": 390
},
{
"epoch": 0.079,
"grad_norm": 81.13752746582031,
"learning_rate": 0.0001576,
"loss": 273.0711,
"step": 395
},
{
"epoch": 0.08,
"grad_norm": 122.15283966064453,
"learning_rate": 0.0001596,
"loss": 273.6886,
"step": 400
},
{
"epoch": 0.081,
"grad_norm": 170.748291015625,
"learning_rate": 0.00016160000000000002,
"loss": 227.4906,
"step": 405
},
{
"epoch": 0.082,
"grad_norm": 79.59201049804688,
"learning_rate": 0.0001636,
"loss": 251.662,
"step": 410
},
{
"epoch": 0.083,
"grad_norm": 107.14413452148438,
"learning_rate": 0.0001656,
"loss": 262.4159,
"step": 415
},
{
"epoch": 0.084,
"grad_norm": 88.18859100341797,
"learning_rate": 0.0001676,
"loss": 246.9784,
"step": 420
},
{
"epoch": 0.085,
"grad_norm": 86.94664764404297,
"learning_rate": 0.0001696,
"loss": 277.6558,
"step": 425
},
{
"epoch": 0.086,
"grad_norm": 94.17179107666016,
"learning_rate": 0.0001716,
"loss": 250.7233,
"step": 430
},
{
"epoch": 0.087,
"grad_norm": 76.1084213256836,
"learning_rate": 0.00017360000000000002,
"loss": 282.617,
"step": 435
},
{
"epoch": 0.088,
"grad_norm": 79.19873046875,
"learning_rate": 0.0001756,
"loss": 277.949,
"step": 440
},
{
"epoch": 0.089,
"grad_norm": 93.7997817993164,
"learning_rate": 0.0001776,
"loss": 274.2419,
"step": 445
},
{
"epoch": 0.09,
"grad_norm": 74.91171264648438,
"learning_rate": 0.0001796,
"loss": 265.3718,
"step": 450
},
{
"epoch": 0.091,
"grad_norm": 77.39509582519531,
"learning_rate": 0.00018160000000000002,
"loss": 270.7689,
"step": 455
},
{
"epoch": 0.092,
"grad_norm": 106.16510772705078,
"learning_rate": 0.00018360000000000002,
"loss": 277.0751,
"step": 460
},
{
"epoch": 0.093,
"grad_norm": 76.39285278320312,
"learning_rate": 0.0001856,
"loss": 280.0632,
"step": 465
},
{
"epoch": 0.094,
"grad_norm": 95.96058654785156,
"learning_rate": 0.0001876,
"loss": 270.5622,
"step": 470
},
{
"epoch": 0.095,
"grad_norm": 129.634033203125,
"learning_rate": 0.0001896,
"loss": 252.6396,
"step": 475
},
{
"epoch": 0.096,
"grad_norm": 103.3237533569336,
"learning_rate": 0.0001916,
"loss": 256.8568,
"step": 480
},
{
"epoch": 0.097,
"grad_norm": 85.59272003173828,
"learning_rate": 0.00019360000000000002,
"loss": 278.5041,
"step": 485
},
{
"epoch": 0.098,
"grad_norm": 81.82221221923828,
"learning_rate": 0.0001956,
"loss": 264.4953,
"step": 490
},
{
"epoch": 0.099,
"grad_norm": 86.00318908691406,
"learning_rate": 0.0001976,
"loss": 276.5557,
"step": 495
},
{
"epoch": 0.1,
"grad_norm": 76.62991333007812,
"learning_rate": 0.0001996,
"loss": 273.7858,
"step": 500
},
{
"epoch": 0.101,
"grad_norm": 82.21709442138672,
"learning_rate": 0.00019999961008995606,
"loss": 285.5494,
"step": 505
},
{
"epoch": 0.102,
"grad_norm": 81.89825439453125,
"learning_rate": 0.0001999980260856137,
"loss": 274.5959,
"step": 510
},
{
"epoch": 0.103,
"grad_norm": 97.47382354736328,
"learning_rate": 0.000199995223636881,
"loss": 259.881,
"step": 515
},
{
"epoch": 0.104,
"grad_norm": 85.02828216552734,
"learning_rate": 0.00019999120277790477,
"loss": 284.2157,
"step": 520
},
{
"epoch": 0.105,
"grad_norm": 81.77962493896484,
"learning_rate": 0.00019998596355767805,
"loss": 272.7059,
"step": 525
},
{
"epoch": 0.106,
"grad_norm": 75.69007110595703,
"learning_rate": 0.000199979506040039,
"loss": 277.5403,
"step": 530
},
{
"epoch": 0.107,
"grad_norm": 83.2806625366211,
"learning_rate": 0.00019997183030367048,
"loss": 268.087,
"step": 535
},
{
"epoch": 0.108,
"grad_norm": 72.27945709228516,
"learning_rate": 0.00019996293644209887,
"loss": 275.1966,
"step": 540
},
{
"epoch": 0.109,
"grad_norm": 90.93228149414062,
"learning_rate": 0.0001999528245636931,
"loss": 274.347,
"step": 545
},
{
"epoch": 0.11,
"grad_norm": 154.7509002685547,
"learning_rate": 0.00019994149479166324,
"loss": 248.1377,
"step": 550
},
{
"epoch": 0.111,
"grad_norm": 83.35163879394531,
"learning_rate": 0.00019992894726405893,
"loss": 208.5353,
"step": 555
},
{
"epoch": 0.112,
"grad_norm": 92.43716430664062,
"learning_rate": 0.00019991518213376787,
"loss": 277.7712,
"step": 560
},
{
"epoch": 0.113,
"grad_norm": 290.52801513671875,
"learning_rate": 0.00019990019956851382,
"loss": 267.6006,
"step": 565
},
{
"epoch": 0.114,
"grad_norm": 76.6048355102539,
"learning_rate": 0.0001998839997508546,
"loss": 268.9107,
"step": 570
},
{
"epoch": 0.115,
"grad_norm": 87.27433013916016,
"learning_rate": 0.00019986658287817987,
"loss": 261.1261,
"step": 575
},
{
"epoch": 0.116,
"grad_norm": 99.33406066894531,
"learning_rate": 0.00019984794916270876,
"loss": 246.2465,
"step": 580
},
{
"epoch": 0.117,
"grad_norm": 106.19979095458984,
"learning_rate": 0.00019982809883148722,
"loss": 257.5928,
"step": 585
},
{
"epoch": 0.118,
"grad_norm": 104.18225860595703,
"learning_rate": 0.00019980703212638522,
"loss": 246.5048,
"step": 590
},
{
"epoch": 0.119,
"grad_norm": 87.01223754882812,
"learning_rate": 0.00019978474930409395,
"loss": 265.1268,
"step": 595
},
{
"epoch": 0.12,
"grad_norm": 100.94159698486328,
"learning_rate": 0.00019976125063612252,
"loss": 257.2071,
"step": 600
},
{
"epoch": 0.121,
"grad_norm": 80.6121597290039,
"learning_rate": 0.00019973653640879485,
"loss": 264.2997,
"step": 605
},
{
"epoch": 0.122,
"grad_norm": 177.31259155273438,
"learning_rate": 0.00019971060692324598,
"loss": 259.3418,
"step": 610
},
{
"epoch": 0.123,
"grad_norm": 86.36884307861328,
"learning_rate": 0.00019968346249541846,
"loss": 260.3142,
"step": 615
},
{
"epoch": 0.124,
"grad_norm": 234.34327697753906,
"learning_rate": 0.00019965510345605866,
"loss": 255.819,
"step": 620
},
{
"epoch": 0.125,
"grad_norm": 80.11038208007812,
"learning_rate": 0.0001996255301507125,
"loss": 266.1089,
"step": 625
},
{
"epoch": 0.126,
"grad_norm": 83.22906494140625,
"learning_rate": 0.00019959474293972129,
"loss": 269.0696,
"step": 630
},
{
"epoch": 0.127,
"grad_norm": 141.25596618652344,
"learning_rate": 0.00019956274219821757,
"loss": 250.2724,
"step": 635
},
{
"epoch": 0.128,
"grad_norm": 89.66653442382812,
"learning_rate": 0.00019952952831612026,
"loss": 270.7056,
"step": 640
},
{
"epoch": 0.129,
"grad_norm": 86.98383331298828,
"learning_rate": 0.00019949510169813003,
"loss": 277.2881,
"step": 645
},
{
"epoch": 0.13,
"grad_norm": 75.34684753417969,
"learning_rate": 0.00019945946276372434,
"loss": 252.0289,
"step": 650
},
{
"epoch": 0.131,
"grad_norm": 103.57421112060547,
"learning_rate": 0.00019942261194715236,
"loss": 243.6953,
"step": 655
},
{
"epoch": 0.132,
"grad_norm": 85.66519927978516,
"learning_rate": 0.00019938454969742968,
"loss": 272.2591,
"step": 660
},
{
"epoch": 0.133,
"grad_norm": 83.34697723388672,
"learning_rate": 0.00019934527647833276,
"loss": 262.9014,
"step": 665
},
{
"epoch": 0.134,
"grad_norm": 83.82205963134766,
"learning_rate": 0.00019930479276839344,
"loss": 271.9406,
"step": 670
},
{
"epoch": 0.135,
"grad_norm": 79.8653564453125,
"learning_rate": 0.0001992630990608929,
"loss": 257.5353,
"step": 675
},
{
"epoch": 0.136,
"grad_norm": 93.54436492919922,
"learning_rate": 0.00019922019586385585,
"loss": 259.1287,
"step": 680
},
{
"epoch": 0.137,
"grad_norm": 130.45753479003906,
"learning_rate": 0.00019917608370004417,
"loss": 230.2193,
"step": 685
},
{
"epoch": 0.138,
"grad_norm": 97.64761352539062,
"learning_rate": 0.00019913076310695068,
"loss": 229.156,
"step": 690
},
{
"epoch": 0.139,
"grad_norm": 88.8829574584961,
"learning_rate": 0.00019908423463679248,
"loss": 261.6211,
"step": 695
},
{
"epoch": 0.14,
"grad_norm": 91.44242095947266,
"learning_rate": 0.0001990364988565043,
"loss": 277.4674,
"step": 700
},
{
"epoch": 0.141,
"grad_norm": 99.95320129394531,
"learning_rate": 0.00019898755634773158,
"loss": 265.9647,
"step": 705
},
{
"epoch": 0.142,
"grad_norm": 92.32852935791016,
"learning_rate": 0.00019893740770682335,
"loss": 265.5265,
"step": 710
},
{
"epoch": 0.143,
"grad_norm": 75.08499908447266,
"learning_rate": 0.0001988860535448249,
"loss": 244.9103,
"step": 715
},
{
"epoch": 0.144,
"grad_norm": 95.38877868652344,
"learning_rate": 0.00019883349448747062,
"loss": 266.2588,
"step": 720
},
{
"epoch": 0.145,
"grad_norm": 95.82470703125,
"learning_rate": 0.0001987797311751759,
"loss": 264.3755,
"step": 725
},
{
"epoch": 0.146,
"grad_norm": 92.83106994628906,
"learning_rate": 0.00019872476426302982,
"loss": 273.0378,
"step": 730
},
{
"epoch": 0.147,
"grad_norm": 80.2651596069336,
"learning_rate": 0.0001986685944207868,
"loss": 264.7744,
"step": 735
},
{
"epoch": 0.148,
"grad_norm": 102.18953704833984,
"learning_rate": 0.0001986112223328587,
"loss": 272.8693,
"step": 740
},
{
"epoch": 0.149,
"grad_norm": 82.0627670288086,
"learning_rate": 0.00019855264869830629,
"loss": 260.8485,
"step": 745
},
{
"epoch": 0.15,
"grad_norm": 82.57454681396484,
"learning_rate": 0.00019849287423083078,
"loss": 259.2679,
"step": 750
},
{
"epoch": 0.151,
"grad_norm": 114.72159576416016,
"learning_rate": 0.00019843189965876526,
"loss": 257.4495,
"step": 755
},
{
"epoch": 0.152,
"grad_norm": 93.50579833984375,
"learning_rate": 0.00019836972572506557,
"loss": 272.7271,
"step": 760
},
{
"epoch": 0.153,
"grad_norm": 98.9693603515625,
"learning_rate": 0.00019830635318730154,
"loss": 254.5802,
"step": 765
},
{
"epoch": 0.154,
"grad_norm": 97.73676300048828,
"learning_rate": 0.00019824178281764753,
"loss": 272.8733,
"step": 770
},
{
"epoch": 0.155,
"grad_norm": 91.14765930175781,
"learning_rate": 0.00019817601540287306,
"loss": 251.6327,
"step": 775
},
{
"epoch": 0.156,
"grad_norm": 85.48234558105469,
"learning_rate": 0.0001981090517443334,
"loss": 260.2286,
"step": 780
},
{
"epoch": 0.157,
"grad_norm": 77.91681671142578,
"learning_rate": 0.0001980408926579596,
"loss": 249.5181,
"step": 785
},
{
"epoch": 0.158,
"grad_norm": 81.32903289794922,
"learning_rate": 0.00019797153897424852,
"loss": 266.2003,
"step": 790
},
{
"epoch": 0.159,
"grad_norm": 83.8577880859375,
"learning_rate": 0.000197900991538253,
"loss": 252.6153,
"step": 795
},
{
"epoch": 0.16,
"grad_norm": 95.97789764404297,
"learning_rate": 0.00019782925120957124,
"loss": 264.6659,
"step": 800
},
{
"epoch": 0.161,
"grad_norm": 87.8358383178711,
"learning_rate": 0.00019775631886233654,
"loss": 257.1771,
"step": 805
},
{
"epoch": 0.162,
"grad_norm": 100.98839569091797,
"learning_rate": 0.0001976821953852065,
"loss": 254.5719,
"step": 810
},
{
"epoch": 0.163,
"grad_norm": 81.7477035522461,
"learning_rate": 0.00019760688168135232,
"loss": 255.831,
"step": 815
},
{
"epoch": 0.164,
"grad_norm": 86.37773895263672,
"learning_rate": 0.00019753037866844771,
"loss": 242.8062,
"step": 820
},
{
"epoch": 0.165,
"grad_norm": 94.87779235839844,
"learning_rate": 0.00019745268727865774,
"loss": 243.8499,
"step": 825
},
{
"epoch": 0.166,
"grad_norm": 89.45201110839844,
"learning_rate": 0.00019737380845862745,
"loss": 265.0962,
"step": 830
},
{
"epoch": 0.167,
"grad_norm": 74.38033294677734,
"learning_rate": 0.0001972937431694704,
"loss": 246.3535,
"step": 835
},
{
"epoch": 0.168,
"grad_norm": 81.76091766357422,
"learning_rate": 0.00019721249238675688,
"loss": 254.2162,
"step": 840
},
{
"epoch": 0.169,
"grad_norm": 83.09095764160156,
"learning_rate": 0.000197130057100502,
"loss": 263.6743,
"step": 845
},
{
"epoch": 0.17,
"grad_norm": 85.52371978759766,
"learning_rate": 0.00019704643831515374,
"loss": 264.9698,
"step": 850
},
{
"epoch": 0.171,
"grad_norm": 87.44183349609375,
"learning_rate": 0.0001969616370495806,
"loss": 258.4468,
"step": 855
},
{
"epoch": 0.172,
"grad_norm": 79.76492309570312,
"learning_rate": 0.00019687565433705926,
"loss": 265.5098,
"step": 860
},
{
"epoch": 0.173,
"grad_norm": 79.6773452758789,
"learning_rate": 0.00019678849122526187,
"loss": 240.6995,
"step": 865
},
{
"epoch": 0.174,
"grad_norm": 78.79090118408203,
"learning_rate": 0.00019670014877624353,
"loss": 237.9277,
"step": 870
},
{
"epoch": 0.175,
"grad_norm": 72.39372253417969,
"learning_rate": 0.00019661062806642903,
"loss": 247.0791,
"step": 875
},
{
"epoch": 0.176,
"grad_norm": 85.30286407470703,
"learning_rate": 0.0001965199301866,
"loss": 239.022,
"step": 880
},
{
"epoch": 0.177,
"grad_norm": 88.13388061523438,
"learning_rate": 0.00019642805624188147,
"loss": 246.1704,
"step": 885
},
{
"epoch": 0.178,
"grad_norm": 85.502685546875,
"learning_rate": 0.0001963350073517285,
"loss": 232.5218,
"step": 890
},
{
"epoch": 0.179,
"grad_norm": 92.60126495361328,
"learning_rate": 0.0001962407846499124,
"loss": 244.6306,
"step": 895
},
{
"epoch": 0.18,
"grad_norm": 116.27145385742188,
"learning_rate": 0.0001961453892845071,
"loss": 238.3904,
"step": 900
},
{
"epoch": 0.181,
"grad_norm": 88.1554946899414,
"learning_rate": 0.00019604882241787498,
"loss": 238.8139,
"step": 905
},
{
"epoch": 0.182,
"grad_norm": 90.355224609375,
"learning_rate": 0.0001959510852266529,
"loss": 256.3098,
"step": 910
},
{
"epoch": 0.183,
"grad_norm": 99.56891632080078,
"learning_rate": 0.0001958521789017376,
"loss": 255.7037,
"step": 915
},
{
"epoch": 0.184,
"grad_norm": 80.60883331298828,
"learning_rate": 0.00019575210464827149,
"loss": 267.9918,
"step": 920
},
{
"epoch": 0.185,
"grad_norm": 92.05183410644531,
"learning_rate": 0.0001956508636856278,
"loss": 255.4713,
"step": 925
},
{
"epoch": 0.186,
"grad_norm": 81.51905059814453,
"learning_rate": 0.00019554845724739566,
"loss": 248.0809,
"step": 930
},
{
"epoch": 0.187,
"grad_norm": 195.4979248046875,
"learning_rate": 0.00019544488658136523,
"loss": 263.204,
"step": 935
},
{
"epoch": 0.188,
"grad_norm": 85.58273315429688,
"learning_rate": 0.00019534015294951233,
"loss": 262.0167,
"step": 940
},
{
"epoch": 0.189,
"grad_norm": 119.53018188476562,
"learning_rate": 0.00019523425762798329,
"loss": 263.1468,
"step": 945
},
{
"epoch": 0.19,
"grad_norm": 108.07363891601562,
"learning_rate": 0.00019512720190707913,
"loss": 244.3173,
"step": 950
},
{
"epoch": 0.191,
"grad_norm": 93.44219970703125,
"learning_rate": 0.00019501898709124008,
"loss": 256.8474,
"step": 955
},
{
"epoch": 0.192,
"grad_norm": 80.76904296875,
"learning_rate": 0.00019490961449902946,
"loss": 260.2707,
"step": 960
},
{
"epoch": 0.193,
"grad_norm": 84.2000503540039,
"learning_rate": 0.00019479908546311781,
"loss": 262.6882,
"step": 965
},
{
"epoch": 0.194,
"grad_norm": 94.77296447753906,
"learning_rate": 0.0001946874013302666,
"loss": 257.7969,
"step": 970
},
{
"epoch": 0.195,
"grad_norm": 80.09429168701172,
"learning_rate": 0.0001945745634613117,
"loss": 260.404,
"step": 975
},
{
"epoch": 0.196,
"grad_norm": 85.663818359375,
"learning_rate": 0.0001944605732311469,
"loss": 262.7288,
"step": 980
},
{
"epoch": 0.197,
"grad_norm": 101.31607818603516,
"learning_rate": 0.00019434543202870725,
"loss": 250.8562,
"step": 985
},
{
"epoch": 0.198,
"grad_norm": 85.12718200683594,
"learning_rate": 0.0001942291412569519,
"loss": 259.1356,
"step": 990
},
{
"epoch": 0.199,
"grad_norm": 78.0478744506836,
"learning_rate": 0.00019411170233284727,
"loss": 266.376,
"step": 995
},
{
"epoch": 0.2,
"grad_norm": 68.81765747070312,
"learning_rate": 0.00019399311668734956,
"loss": 261.6669,
"step": 1000
},
{
"epoch": 0.201,
"grad_norm": 83.69310760498047,
"learning_rate": 0.00019387338576538744,
"loss": 266.8398,
"step": 1005
},
{
"epoch": 0.202,
"grad_norm": 95.58879852294922,
"learning_rate": 0.0001937525110258444,
"loss": 255.4197,
"step": 1010
},
{
"epoch": 0.203,
"grad_norm": 98.04708099365234,
"learning_rate": 0.00019363049394154094,
"loss": 264.1991,
"step": 1015
},
{
"epoch": 0.204,
"grad_norm": 79.52462768554688,
"learning_rate": 0.00019350733599921683,
"loss": 248.4136,
"step": 1020
},
{
"epoch": 0.205,
"grad_norm": 91.26261901855469,
"learning_rate": 0.00019338303869951269,
"loss": 253.9279,
"step": 1025
},
{
"epoch": 0.206,
"grad_norm": 93.99327850341797,
"learning_rate": 0.00019325760355695188,
"loss": 265.3703,
"step": 1030
},
{
"epoch": 0.207,
"grad_norm": 184.60055541992188,
"learning_rate": 0.00019313103209992204,
"loss": 248.6289,
"step": 1035
},
{
"epoch": 0.208,
"grad_norm": 73.1077651977539,
"learning_rate": 0.0001930033258706564,
"loss": 253.6411,
"step": 1040
},
{
"epoch": 0.209,
"grad_norm": 91.29564666748047,
"learning_rate": 0.00019287448642521513,
"loss": 265.2475,
"step": 1045
},
{
"epoch": 0.21,
"grad_norm": 88.97148895263672,
"learning_rate": 0.00019274451533346615,
"loss": 258.7835,
"step": 1050
},
{
"epoch": 0.211,
"grad_norm": 95.8347396850586,
"learning_rate": 0.00019261341417906621,
"loss": 263.1405,
"step": 1055
},
{
"epoch": 0.212,
"grad_norm": 104.48005676269531,
"learning_rate": 0.0001924811845594415,
"loss": 247.2216,
"step": 1060
},
{
"epoch": 0.213,
"grad_norm": 87.70344543457031,
"learning_rate": 0.00019234782808576824,
"loss": 260.89,
"step": 1065
},
{
"epoch": 0.214,
"grad_norm": 91.71766662597656,
"learning_rate": 0.00019221334638295294,
"loss": 247.5774,
"step": 1070
},
{
"epoch": 0.215,
"grad_norm": 88.97634887695312,
"learning_rate": 0.00019207774108961272,
"loss": 256.1988,
"step": 1075
},
{
"epoch": 0.216,
"grad_norm": 87.39369201660156,
"learning_rate": 0.0001919410138580553,
"loss": 254.3752,
"step": 1080
},
{
"epoch": 0.217,
"grad_norm": 90.25965881347656,
"learning_rate": 0.0001918031663542588,
"loss": 250.2446,
"step": 1085
},
{
"epoch": 0.218,
"grad_norm": 77.0758285522461,
"learning_rate": 0.00019166420025785164,
"loss": 260.8915,
"step": 1090
},
{
"epoch": 0.219,
"grad_norm": 80.48272705078125,
"learning_rate": 0.00019152411726209176,
"loss": 262.41,
"step": 1095
},
{
"epoch": 0.22,
"grad_norm": 88.65518951416016,
"learning_rate": 0.0001913829190738463,
"loss": 234.2297,
"step": 1100
},
{
"epoch": 0.221,
"grad_norm": 82.69694519042969,
"learning_rate": 0.00019124060741357063,
"loss": 262.6193,
"step": 1105
},
{
"epoch": 0.222,
"grad_norm": 101.18913269042969,
"learning_rate": 0.0001910971840152874,
"loss": 258.0365,
"step": 1110
},
{
"epoch": 0.223,
"grad_norm": 110.60680389404297,
"learning_rate": 0.00019095265062656544,
"loss": 252.7982,
"step": 1115
},
{
"epoch": 0.224,
"grad_norm": 177.97744750976562,
"learning_rate": 0.00019080700900849851,
"loss": 251.2411,
"step": 1120
},
{
"epoch": 0.225,
"grad_norm": 94.00029754638672,
"learning_rate": 0.00019066026093568378,
"loss": 257.0166,
"step": 1125
},
{
"epoch": 0.226,
"grad_norm": 71.40478515625,
"learning_rate": 0.00019051240819620014,
"loss": 256.7753,
"step": 1130
},
{
"epoch": 0.227,
"grad_norm": 80.93846130371094,
"learning_rate": 0.00019036345259158667,
"loss": 256.8576,
"step": 1135
},
{
"epoch": 0.228,
"grad_norm": 73.30122375488281,
"learning_rate": 0.00019021339593682028,
"loss": 255.052,
"step": 1140
},
{
"epoch": 0.229,
"grad_norm": 331.486083984375,
"learning_rate": 0.00019006224006029406,
"loss": 245.7577,
"step": 1145
},
{
"epoch": 0.23,
"grad_norm": 87.33750915527344,
"learning_rate": 0.00018990998680379456,
"loss": 258.0097,
"step": 1150
},
{
"epoch": 0.231,
"grad_norm": 102.74681854248047,
"learning_rate": 0.00018975663802247976,
"loss": 270.2411,
"step": 1155
},
{
"epoch": 0.232,
"grad_norm": 84.14704895019531,
"learning_rate": 0.0001896021955848561,
"loss": 251.5429,
"step": 1160
},
{
"epoch": 0.233,
"grad_norm": 94.87269592285156,
"learning_rate": 0.000189446661372756,
"loss": 258.4201,
"step": 1165
},
{
"epoch": 0.234,
"grad_norm": 77.7106704711914,
"learning_rate": 0.0001892900372813147,
"loss": 262.1626,
"step": 1170
},
{
"epoch": 0.235,
"grad_norm": 94.38058471679688,
"learning_rate": 0.00018913232521894732,
"loss": 254.3043,
"step": 1175
},
{
"epoch": 0.236,
"grad_norm": 81.66893768310547,
"learning_rate": 0.00018897352710732564,
"loss": 253.6277,
"step": 1180
},
{
"epoch": 0.237,
"grad_norm": 116.28044128417969,
"learning_rate": 0.00018881364488135448,
"loss": 264.6382,
"step": 1185
},
{
"epoch": 0.238,
"grad_norm": 98.0597152709961,
"learning_rate": 0.00018865268048914828,
"loss": 250.4016,
"step": 1190
},
{
"epoch": 0.239,
"grad_norm": 88.63140106201172,
"learning_rate": 0.00018849063589200743,
"loss": 257.5875,
"step": 1195
},
{
"epoch": 0.24,
"grad_norm": 111.06546020507812,
"learning_rate": 0.00018832751306439418,
"loss": 250.4046,
"step": 1200
},
{
"epoch": 0.241,
"grad_norm": 90.88837432861328,
"learning_rate": 0.0001881633139939087,
"loss": 258.8658,
"step": 1205
},
{
"epoch": 0.242,
"grad_norm": 83.42932891845703,
"learning_rate": 0.00018799804068126485,
"loss": 250.3608,
"step": 1210
},
{
"epoch": 0.243,
"grad_norm": 85.38086700439453,
"learning_rate": 0.00018783169514026578,
"loss": 253.0209,
"step": 1215
},
{
"epoch": 0.244,
"grad_norm": 83.19639587402344,
"learning_rate": 0.00018766427939777945,
"loss": 254.4578,
"step": 1220
},
{
"epoch": 0.245,
"grad_norm": 80.1951675415039,
"learning_rate": 0.0001874957954937138,
"loss": 257.0948,
"step": 1225
},
{
"epoch": 0.246,
"grad_norm": 73.29708099365234,
"learning_rate": 0.00018732624548099204,
"loss": 254.6324,
"step": 1230
},
{
"epoch": 0.247,
"grad_norm": 140.17010498046875,
"learning_rate": 0.00018715563142552758,
"loss": 252.8294,
"step": 1235
},
{
"epoch": 0.248,
"grad_norm": 75.43911743164062,
"learning_rate": 0.0001869839554061988,
"loss": 251.5451,
"step": 1240
},
{
"epoch": 0.249,
"grad_norm": 81.71854400634766,
"learning_rate": 0.00018681121951482393,
"loss": 256.574,
"step": 1245
},
{
"epoch": 0.25,
"grad_norm": 76.11139678955078,
"learning_rate": 0.00018663742585613518,
"loss": 254.9934,
"step": 1250
},
{
"epoch": 0.251,
"grad_norm": 78.11524200439453,
"learning_rate": 0.0001864625765477535,
"loss": 255.929,
"step": 1255
},
{
"epoch": 0.252,
"grad_norm": 85.76427459716797,
"learning_rate": 0.0001862866737201625,
"loss": 253.5611,
"step": 1260
},
{
"epoch": 0.253,
"grad_norm": 74.26799011230469,
"learning_rate": 0.00018610971951668265,
"loss": 266.0749,
"step": 1265
},
{
"epoch": 0.254,
"grad_norm": 91.27781677246094,
"learning_rate": 0.00018593171609344503,
"loss": 247.3766,
"step": 1270
},
{
"epoch": 0.255,
"grad_norm": 76.1453857421875,
"learning_rate": 0.00018575266561936523,
"loss": 256.995,
"step": 1275
},
{
"epoch": 0.256,
"grad_norm": 79.24016571044922,
"learning_rate": 0.00018557257027611675,
"loss": 253.1588,
"step": 1280
},
{
"epoch": 0.257,
"grad_norm": 74.36415100097656,
"learning_rate": 0.0001853914322581045,
"loss": 252.7699,
"step": 1285
},
{
"epoch": 0.258,
"grad_norm": 135.46632385253906,
"learning_rate": 0.0001852092537724381,
"loss": 241.3478,
"step": 1290
},
{
"epoch": 0.259,
"grad_norm": 85.78771209716797,
"learning_rate": 0.00018502603703890488,
"loss": 247.3219,
"step": 1295
},
{
"epoch": 0.26,
"grad_norm": 91.77862548828125,
"learning_rate": 0.0001848417842899429,
"loss": 256.2093,
"step": 1300
},
{
"epoch": 0.261,
"grad_norm": 91.4501953125,
"learning_rate": 0.0001846564977706138,
"loss": 247.4523,
"step": 1305
},
{
"epoch": 0.262,
"grad_norm": 79.59305572509766,
"learning_rate": 0.00018447017973857532,
"loss": 245.7698,
"step": 1310
},
{
"epoch": 0.263,
"grad_norm": 73.08914184570312,
"learning_rate": 0.0001842828324640539,
"loss": 259.9312,
"step": 1315
},
{
"epoch": 0.264,
"grad_norm": 81.13728332519531,
"learning_rate": 0.00018409445822981693,
"loss": 253.4056,
"step": 1320
},
{
"epoch": 0.265,
"grad_norm": 139.3446807861328,
"learning_rate": 0.000183905059331145,
"loss": 251.4864,
"step": 1325
},
{
"epoch": 0.266,
"grad_norm": 101.48133087158203,
"learning_rate": 0.000183714638075804,
"loss": 250.6866,
"step": 1330
},
{
"epoch": 0.267,
"grad_norm": 89.03541564941406,
"learning_rate": 0.00018352319678401676,
"loss": 251.1165,
"step": 1335
},
{
"epoch": 0.268,
"grad_norm": 93.85267639160156,
"learning_rate": 0.000183330737788435,
"loss": 256.7002,
"step": 1340
},
{
"epoch": 0.269,
"grad_norm": 91.65203857421875,
"learning_rate": 0.00018313726343411086,
"loss": 250.5626,
"step": 1345
},
{
"epoch": 0.27,
"grad_norm": 89.79359436035156,
"learning_rate": 0.00018294277607846832,
"loss": 244.0624,
"step": 1350
},
{
"epoch": 0.271,
"grad_norm": 73.13269805908203,
"learning_rate": 0.00018274727809127438,
"loss": 244.0502,
"step": 1355
},
{
"epoch": 0.272,
"grad_norm": 80.32412719726562,
"learning_rate": 0.00018255077185461038,
"loss": 240.6928,
"step": 1360
},
{
"epoch": 0.273,
"grad_norm": 75.30445861816406,
"learning_rate": 0.00018235325976284275,
"loss": 240.0284,
"step": 1365
},
{
"epoch": 0.274,
"grad_norm": 72.1701431274414,
"learning_rate": 0.00018215474422259402,
"loss": 238.0993,
"step": 1370
},
{
"epoch": 0.275,
"grad_norm": 104.5904541015625,
"learning_rate": 0.0001819552276527134,
"loss": 239.107,
"step": 1375
},
{
"epoch": 0.276,
"grad_norm": 71.6397476196289,
"learning_rate": 0.0001817547124842473,
"loss": 250.2575,
"step": 1380
},
{
"epoch": 0.277,
"grad_norm": 86.97512817382812,
"learning_rate": 0.00018155320116040982,
"loss": 256.1841,
"step": 1385
},
{
"epoch": 0.278,
"grad_norm": 92.31695556640625,
"learning_rate": 0.0001813506961365528,
"loss": 246.5565,
"step": 1390
},
{
"epoch": 0.279,
"grad_norm": 74.40515899658203,
"learning_rate": 0.00018114719988013612,
"loss": 251.1006,
"step": 1395
},
{
"epoch": 0.28,
"grad_norm": 76.02753448486328,
"learning_rate": 0.00018094271487069735,
"loss": 258.7795,
"step": 1400
},
{
"epoch": 0.281,
"grad_norm": 71.08653259277344,
"learning_rate": 0.00018073724359982186,
"loss": 260.5511,
"step": 1405
},
{
"epoch": 0.282,
"grad_norm": 114.62284088134766,
"learning_rate": 0.0001805307885711122,
"loss": 256.3787,
"step": 1410
},
{
"epoch": 0.283,
"grad_norm": 83.6667709350586,
"learning_rate": 0.0001803233523001578,
"loss": 235.6527,
"step": 1415
},
{
"epoch": 0.284,
"grad_norm": 74.15666198730469,
"learning_rate": 0.00018011493731450413,
"loss": 249.9664,
"step": 1420
},
{
"epoch": 0.285,
"grad_norm": 71.5533447265625,
"learning_rate": 0.00017990554615362198,
"loss": 267.4946,
"step": 1425
},
{
"epoch": 0.286,
"grad_norm": 86.5447769165039,
"learning_rate": 0.00017969518136887663,
"loss": 250.8832,
"step": 1430
},
{
"epoch": 0.287,
"grad_norm": 85.03717041015625,
"learning_rate": 0.00017948384552349657,
"loss": 247.4606,
"step": 1435
},
{
"epoch": 0.288,
"grad_norm": 93.62215423583984,
"learning_rate": 0.00017927154119254236,
"loss": 232.7314,
"step": 1440
},
{
"epoch": 0.289,
"grad_norm": 75.2215576171875,
"learning_rate": 0.0001790582709628753,
"loss": 239.9004,
"step": 1445
},
{
"epoch": 0.29,
"grad_norm": 95.10070037841797,
"learning_rate": 0.00017884403743312582,
"loss": 249.9664,
"step": 1450
},
{
"epoch": 0.291,
"grad_norm": 94.75016784667969,
"learning_rate": 0.00017862884321366188,
"loss": 243.8475,
"step": 1455
},
{
"epoch": 0.292,
"grad_norm": 101.73164367675781,
"learning_rate": 0.00017841269092655715,
"loss": 239.0752,
"step": 1460
},
{
"epoch": 0.293,
"grad_norm": 96.95437622070312,
"learning_rate": 0.000178195583205559,
"loss": 230.2006,
"step": 1465
},
{
"epoch": 0.294,
"grad_norm": 65.30355072021484,
"learning_rate": 0.00017797752269605653,
"loss": 230.9965,
"step": 1470
},
{
"epoch": 0.295,
"grad_norm": 81.79991912841797,
"learning_rate": 0.0001777585120550482,
"loss": 247.2642,
"step": 1475
},
{
"epoch": 0.296,
"grad_norm": 98.32083129882812,
"learning_rate": 0.0001775385539511096,
"loss": 224.2117,
"step": 1480
},
{
"epoch": 0.297,
"grad_norm": 112.95418548583984,
"learning_rate": 0.00017731765106436073,
"loss": 230.1915,
"step": 1485
},
{
"epoch": 0.298,
"grad_norm": 81.77294158935547,
"learning_rate": 0.00017709580608643363,
"loss": 231.3808,
"step": 1490
},
{
"epoch": 0.299,
"grad_norm": 74.13616943359375,
"learning_rate": 0.00017687302172043933,
"loss": 233.7812,
"step": 1495
},
{
"epoch": 0.3,
"grad_norm": 72.692138671875,
"learning_rate": 0.00017664930068093498,
"loss": 241.5683,
"step": 1500
},
{
"epoch": 0.301,
"grad_norm": 167.48928833007812,
"learning_rate": 0.0001764246456938909,
"loss": 256.6586,
"step": 1505
},
{
"epoch": 0.302,
"grad_norm": 80.04060363769531,
"learning_rate": 0.0001761990594966572,
"loss": 261.3019,
"step": 1510
},
{
"epoch": 0.303,
"grad_norm": 77.33476257324219,
"learning_rate": 0.00017597254483793048,
"loss": 247.5956,
"step": 1515
},
{
"epoch": 0.304,
"grad_norm": 82.19470977783203,
"learning_rate": 0.00017574510447772039,
"loss": 251.6137,
"step": 1520
},
{
"epoch": 0.305,
"grad_norm": 90.15569305419922,
"learning_rate": 0.00017551674118731591,
"loss": 248.6482,
"step": 1525
},
{
"epoch": 0.306,
"grad_norm": 75.81546783447266,
"learning_rate": 0.00017528745774925172,
"loss": 244.635,
"step": 1530
},
{
"epoch": 0.307,
"grad_norm": 87.06208801269531,
"learning_rate": 0.00017505725695727412,
"loss": 247.6758,
"step": 1535
},
{
"epoch": 0.308,
"grad_norm": 71.23653411865234,
"learning_rate": 0.00017482614161630714,
"loss": 257.1815,
"step": 1540
},
{
"epoch": 0.309,
"grad_norm": 77.80252075195312,
"learning_rate": 0.00017459411454241822,
"loss": 264.111,
"step": 1545
},
{
"epoch": 0.31,
"grad_norm": 76.55634307861328,
"learning_rate": 0.0001743611785627841,
"loss": 241.7567,
"step": 1550
},
{
"epoch": 0.311,
"grad_norm": 244.104736328125,
"learning_rate": 0.0001741273365156561,
"loss": 251.3267,
"step": 1555
},
{
"epoch": 0.312,
"grad_norm": 76.95161437988281,
"learning_rate": 0.0001738925912503259,
"loss": 252.9643,
"step": 1560
},
{
"epoch": 0.313,
"grad_norm": 135.49423217773438,
"learning_rate": 0.00017365694562709034,
"loss": 239.5739,
"step": 1565
},
{
"epoch": 0.314,
"grad_norm": 81.2066421508789,
"learning_rate": 0.00017342040251721702,
"loss": 251.5922,
"step": 1570
},
{
"epoch": 0.315,
"grad_norm": 85.94026184082031,
"learning_rate": 0.0001731829648029091,
"loss": 257.0892,
"step": 1575
},
{
"epoch": 0.316,
"grad_norm": 76.92382049560547,
"learning_rate": 0.00017294463537727024,
"loss": 250.3904,
"step": 1580
},
{
"epoch": 0.317,
"grad_norm": 92.71879577636719,
"learning_rate": 0.0001727054171442692,
"loss": 246.7984,
"step": 1585
},
{
"epoch": 0.318,
"grad_norm": 87.52629852294922,
"learning_rate": 0.0001724653130187047,
"loss": 225.4233,
"step": 1590
},
{
"epoch": 0.319,
"grad_norm": 71.92736053466797,
"learning_rate": 0.0001722243259261697,
"loss": 238.1165,
"step": 1595
},
{
"epoch": 0.32,
"grad_norm": 90.79645538330078,
"learning_rate": 0.0001719824588030159,
"loss": 243.6571,
"step": 1600
},
{
"epoch": 0.321,
"grad_norm": 84.94625091552734,
"learning_rate": 0.00017173971459631787,
"loss": 244.2219,
"step": 1605
},
{
"epoch": 0.322,
"grad_norm": 83.68124389648438,
"learning_rate": 0.00017149609626383717,
"loss": 256.8372,
"step": 1610
},
{
"epoch": 0.323,
"grad_norm": 77.1388168334961,
"learning_rate": 0.00017125160677398626,
"loss": 252.5201,
"step": 1615
},
{
"epoch": 0.324,
"grad_norm": 79.63390350341797,
"learning_rate": 0.0001710062491057925,
"loss": 249.4397,
"step": 1620
},
{
"epoch": 0.325,
"grad_norm": 107.53591918945312,
"learning_rate": 0.00017076002624886154,
"loss": 249.4407,
"step": 1625
},
{
"epoch": 0.326,
"grad_norm": 103.15985870361328,
"learning_rate": 0.00017051294120334125,
"loss": 240.4534,
"step": 1630
},
{
"epoch": 0.327,
"grad_norm": 73.01668548583984,
"learning_rate": 0.00017026499697988493,
"loss": 246.4568,
"step": 1635
},
{
"epoch": 0.328,
"grad_norm": 90.87763214111328,
"learning_rate": 0.00017001619659961467,
"loss": 237.5934,
"step": 1640
},
{
"epoch": 0.329,
"grad_norm": 85.4532241821289,
"learning_rate": 0.00016976654309408464,
"loss": 225.092,
"step": 1645
},
{
"epoch": 0.33,
"grad_norm": 113.58480072021484,
"learning_rate": 0.000169516039505244,
"loss": 243.6423,
"step": 1650
},
{
"epoch": 0.331,
"grad_norm": 91.1771011352539,
"learning_rate": 0.0001692646888853999,
"loss": 249.4315,
"step": 1655
},
{
"epoch": 0.332,
"grad_norm": 98.73737335205078,
"learning_rate": 0.00016901249429718032,
"loss": 236.1908,
"step": 1660
},
{
"epoch": 0.333,
"grad_norm": 88.62642669677734,
"learning_rate": 0.00016875945881349676,
"loss": 237.7242,
"step": 1665
},
{
"epoch": 0.334,
"grad_norm": 84.36568450927734,
"learning_rate": 0.0001685055855175067,
"loss": 225.9177,
"step": 1670
},
{
"epoch": 0.335,
"grad_norm": 110.53504180908203,
"learning_rate": 0.0001682508775025762,
"loss": 257.375,
"step": 1675
},
{
"epoch": 0.336,
"grad_norm": 81.43233489990234,
"learning_rate": 0.00016799533787224192,
"loss": 248.0211,
"step": 1680
},
{
"epoch": 0.337,
"grad_norm": 80.1913070678711,
"learning_rate": 0.00016773896974017373,
"loss": 243.9539,
"step": 1685
},
{
"epoch": 0.338,
"grad_norm": 82.59772491455078,
"learning_rate": 0.00016748177623013638,
"loss": 234.4935,
"step": 1690
},
{
"epoch": 0.339,
"grad_norm": 84.051513671875,
"learning_rate": 0.00016722376047595164,
"loss": 239.1631,
"step": 1695
},
{
"epoch": 0.34,
"grad_norm": 75.9992904663086,
"learning_rate": 0.00016696492562145996,
"loss": 242.8416,
"step": 1700
},
{
"epoch": 0.341,
"grad_norm": 78.23426818847656,
"learning_rate": 0.00016670527482048246,
"loss": 242.5307,
"step": 1705
},
{
"epoch": 0.342,
"grad_norm": 83.70015716552734,
"learning_rate": 0.00016644481123678217,
"loss": 232.6412,
"step": 1710
},
{
"epoch": 0.343,
"grad_norm": 118.21031951904297,
"learning_rate": 0.00016618353804402568,
"loss": 228.0151,
"step": 1715
},
{
"epoch": 0.344,
"grad_norm": 87.50984954833984,
"learning_rate": 0.00016592145842574433,
"loss": 238.7696,
"step": 1720
},
{
"epoch": 0.345,
"grad_norm": 70.18067932128906,
"learning_rate": 0.00016565857557529566,
"loss": 256.9798,
"step": 1725
},
{
"epoch": 0.346,
"grad_norm": 69.41463470458984,
"learning_rate": 0.00016539489269582416,
"loss": 248.7863,
"step": 1730
},
{
"epoch": 0.347,
"grad_norm": 87.95372772216797,
"learning_rate": 0.00016513041300022255,
"loss": 242.2556,
"step": 1735
},
{
"epoch": 0.348,
"grad_norm": 88.49801635742188,
"learning_rate": 0.00016486513971109243,
"loss": 251.6068,
"step": 1740
},
{
"epoch": 0.349,
"grad_norm": 74.05671691894531,
"learning_rate": 0.0001645990760607051,
"loss": 234.2199,
"step": 1745
},
{
"epoch": 0.35,
"grad_norm": 82.08663940429688,
"learning_rate": 0.0001643322252909622,
"loss": 248.5648,
"step": 1750
},
{
"epoch": 0.351,
"grad_norm": 71.9901351928711,
"learning_rate": 0.00016406459065335615,
"loss": 226.4082,
"step": 1755
},
{
"epoch": 0.352,
"grad_norm": 84.0577163696289,
"learning_rate": 0.00016379617540893056,
"loss": 229.734,
"step": 1760
},
{
"epoch": 0.353,
"grad_norm": 74.11405181884766,
"learning_rate": 0.00016352698282824044,
"loss": 234.9073,
"step": 1765
},
{
"epoch": 0.354,
"grad_norm": 81.10983276367188,
"learning_rate": 0.00016325701619131246,
"loss": 241.5879,
"step": 1770
},
{
"epoch": 0.355,
"grad_norm": 74.09709930419922,
"learning_rate": 0.00016298627878760487,
"loss": 230.4069,
"step": 1775
},
{
"epoch": 0.356,
"grad_norm": 75.3198013305664,
"learning_rate": 0.00016271477391596753,
"loss": 248.3652,
"step": 1780
},
{
"epoch": 0.357,
"grad_norm": 78.23440551757812,
"learning_rate": 0.00016244250488460158,
"loss": 246.4592,
"step": 1785
},
{
"epoch": 0.358,
"grad_norm": 82.37088012695312,
"learning_rate": 0.0001621694750110193,
"loss": 242.9515,
"step": 1790
},
{
"epoch": 0.359,
"grad_norm": 80.58068084716797,
"learning_rate": 0.00016189568762200348,
"loss": 235.8862,
"step": 1795
},
{
"epoch": 0.36,
"grad_norm": 174.61636352539062,
"learning_rate": 0.00016162114605356703,
"loss": 237.8045,
"step": 1800
},
{
"epoch": 0.361,
"grad_norm": 78.84001159667969,
"learning_rate": 0.00016134585365091243,
"loss": 237.9397,
"step": 1805
},
{
"epoch": 0.362,
"grad_norm": 87.54006958007812,
"learning_rate": 0.00016106981376839066,
"loss": 232.272,
"step": 1810
},
{
"epoch": 0.363,
"grad_norm": 75.18827819824219,
"learning_rate": 0.00016079302976946055,
"loss": 238.5237,
"step": 1815
},
{
"epoch": 0.364,
"grad_norm": 205.7169189453125,
"learning_rate": 0.0001605155050266478,
"loss": 232.3343,
"step": 1820
},
{
"epoch": 0.365,
"grad_norm": 125.63472747802734,
"learning_rate": 0.00016023724292150385,
"loss": 236.4608,
"step": 1825
},
{
"epoch": 0.366,
"grad_norm": 75.56720733642578,
"learning_rate": 0.00015995824684456465,
"loss": 238.7022,
"step": 1830
},
{
"epoch": 0.367,
"grad_norm": 69.14988708496094,
"learning_rate": 0.00015967852019530926,
"loss": 246.5549,
"step": 1835
},
{
"epoch": 0.368,
"grad_norm": 72.42176818847656,
"learning_rate": 0.0001593980663821187,
"loss": 234.5464,
"step": 1840
},
{
"epoch": 0.369,
"grad_norm": 73.17369842529297,
"learning_rate": 0.0001591168888222342,
"loss": 240.6741,
"step": 1845
},
{
"epoch": 0.37,
"grad_norm": 93.2841567993164,
"learning_rate": 0.00015883499094171554,
"loss": 257.3144,
"step": 1850
},
{
"epoch": 0.371,
"grad_norm": 80.9893569946289,
"learning_rate": 0.0001585523761753994,
"loss": 237.1559,
"step": 1855
},
{
"epoch": 0.372,
"grad_norm": 70.33050537109375,
"learning_rate": 0.00015826904796685762,
"loss": 245.048,
"step": 1860
},
{
"epoch": 0.373,
"grad_norm": 103.5679702758789,
"learning_rate": 0.00015798500976835493,
"loss": 252.7692,
"step": 1865
},
{
"epoch": 0.374,
"grad_norm": 92.79717254638672,
"learning_rate": 0.00015770026504080718,
"loss": 244.0553,
"step": 1870
},
{
"epoch": 0.375,
"grad_norm": 83.82243347167969,
"learning_rate": 0.000157414817253739,
"loss": 233.3511,
"step": 1875
},
{
"epoch": 0.376,
"grad_norm": 90.47740936279297,
"learning_rate": 0.00015712866988524155,
"loss": 243.2532,
"step": 1880
},
{
"epoch": 0.377,
"grad_norm": 75.07630920410156,
"learning_rate": 0.0001568418264219303,
"loss": 232.785,
"step": 1885
},
{
"epoch": 0.378,
"grad_norm": 75.14298248291016,
"learning_rate": 0.0001565542903589023,
"loss": 211.9168,
"step": 1890
},
{
"epoch": 0.379,
"grad_norm": 108.48497772216797,
"learning_rate": 0.0001562660651996937,
"loss": 246.3054,
"step": 1895
},
{
"epoch": 0.38,
"grad_norm": 72.64405822753906,
"learning_rate": 0.00015597715445623712,
"loss": 238.2015,
"step": 1900
},
{
"epoch": 0.381,
"grad_norm": 78.86182403564453,
"learning_rate": 0.00015568756164881882,
"loss": 234.4326,
"step": 1905
},
{
"epoch": 0.382,
"grad_norm": 87.01496887207031,
"learning_rate": 0.00015539729030603574,
"loss": 231.1099,
"step": 1910
},
{
"epoch": 0.383,
"grad_norm": 76.23607635498047,
"learning_rate": 0.0001551063439647526,
"loss": 230.9525,
"step": 1915
},
{
"epoch": 0.384,
"grad_norm": 74.71236419677734,
"learning_rate": 0.00015481472617005876,
"loss": 232.652,
"step": 1920
},
{
"epoch": 0.385,
"grad_norm": 67.2276382446289,
"learning_rate": 0.00015452244047522502,
"loss": 229.7848,
"step": 1925
},
{
"epoch": 0.386,
"grad_norm": 86.58885192871094,
"learning_rate": 0.0001542294904416603,
"loss": 234.9773,
"step": 1930
},
{
"epoch": 0.387,
"grad_norm": 77.24354553222656,
"learning_rate": 0.00015393587963886835,
"loss": 226.631,
"step": 1935
},
{
"epoch": 0.388,
"grad_norm": 82.13939666748047,
"learning_rate": 0.0001536416116444041,
"loss": 244.9443,
"step": 1940
},
{
"epoch": 0.389,
"grad_norm": 86.08671569824219,
"learning_rate": 0.0001533466900438303,
"loss": 256.5951,
"step": 1945
},
{
"epoch": 0.39,
"grad_norm": 73.70137786865234,
"learning_rate": 0.0001530511184306734,
"loss": 251.7685,
"step": 1950
},
{
"epoch": 0.391,
"grad_norm": 89.96126556396484,
"learning_rate": 0.00015275490040638038,
"loss": 245.1215,
"step": 1955
},
{
"epoch": 0.392,
"grad_norm": 114.27163696289062,
"learning_rate": 0.00015245803958027434,
"loss": 232.9975,
"step": 1960
},
{
"epoch": 0.393,
"grad_norm": 78.34809875488281,
"learning_rate": 0.0001521605395695108,
"loss": 238.7876,
"step": 1965
},
{
"epoch": 0.394,
"grad_norm": 80.78251647949219,
"learning_rate": 0.00015186240399903342,
"loss": 244.877,
"step": 1970
},
{
"epoch": 0.395,
"grad_norm": 141.69923400878906,
"learning_rate": 0.00015156363650153012,
"loss": 248.5323,
"step": 1975
},
{
"epoch": 0.396,
"grad_norm": 85.24002838134766,
"learning_rate": 0.0001512642407173885,
"loss": 245.1147,
"step": 1980
},
{
"epoch": 0.397,
"grad_norm": 89.3248519897461,
"learning_rate": 0.00015096422029465178,
"loss": 240.5737,
"step": 1985
},
{
"epoch": 0.398,
"grad_norm": 77.96577453613281,
"learning_rate": 0.0001506635788889741,
"loss": 217.3196,
"step": 1990
},
{
"epoch": 0.399,
"grad_norm": 94.5428695678711,
"learning_rate": 0.0001503623201635761,
"loss": 244.0163,
"step": 1995
},
{
"epoch": 0.4,
"grad_norm": 99.44204711914062,
"learning_rate": 0.0001500604477892003,
"loss": 242.3106,
"step": 2000
}
],
"logging_steps": 5,
"max_steps": 5000,
"num_input_tokens_seen": 0,
"num_train_epochs": 9223372036854775807,
"save_steps": 1000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 9.7757951950848e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.4,
"eval_steps": 500,
"global_step": 2000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.001,
"grad_norm": 184.6030731201172,
"learning_rate": 1.6000000000000001e-06,
"loss": 319.5776,
"step": 5
},
{
"epoch": 0.002,
"grad_norm": 166.8455047607422,
"learning_rate": 3.6e-06,
"loss": 321.4675,
"step": 10
},
{
"epoch": 0.003,
"grad_norm": 138.33668518066406,
"learning_rate": 5.600000000000001e-06,
"loss": 321.0479,
"step": 15
},
{
"epoch": 0.004,
"grad_norm": 163.59259033203125,
"learning_rate": 7.6e-06,
"loss": 325.7438,
"step": 20
},
{
"epoch": 0.005,
"grad_norm": 162.9120330810547,
"learning_rate": 9.600000000000001e-06,
"loss": 323.9409,
"step": 25
},
{
"epoch": 0.006,
"grad_norm": 126.21514129638672,
"learning_rate": 1.16e-05,
"loss": 310.5008,
"step": 30
},
{
"epoch": 0.007,
"grad_norm": 104.5123062133789,
"learning_rate": 1.3600000000000002e-05,
"loss": 312.7666,
"step": 35
},
{
"epoch": 0.008,
"grad_norm": 101.64288330078125,
"learning_rate": 1.56e-05,
"loss": 305.1989,
"step": 40
},
{
"epoch": 0.009,
"grad_norm": 102.09917449951172,
"learning_rate": 1.76e-05,
"loss": 307.8038,
"step": 45
},
{
"epoch": 0.01,
"grad_norm": 104.21722412109375,
"learning_rate": 1.9600000000000002e-05,
"loss": 320.1353,
"step": 50
},
{
"epoch": 0.011,
"grad_norm": 93.92383575439453,
"learning_rate": 2.16e-05,
"loss": 304.7655,
"step": 55
},
{
"epoch": 0.012,
"grad_norm": 114.69617462158203,
"learning_rate": 2.36e-05,
"loss": 305.9618,
"step": 60
},
{
"epoch": 0.013,
"grad_norm": 93.69319915771484,
"learning_rate": 2.5600000000000002e-05,
"loss": 310.8797,