{
"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": 133.26564025878906,
"learning_rate": 1.6000000000000001e-06,
"loss": 319.5714,
"step": 5
},
{
"epoch": 0.002,
"grad_norm": 116.60221099853516,
"learning_rate": 3.6e-06,
"loss": 321.6409,
"step": 10
},
{
"epoch": 0.003,
"grad_norm": 99.86441040039062,
"learning_rate": 5.600000000000001e-06,
"loss": 321.4713,
"step": 15
},
{
"epoch": 0.004,
"grad_norm": 120.4101333618164,
"learning_rate": 7.6e-06,
"loss": 326.6742,
"step": 20
},
{
"epoch": 0.005,
"grad_norm": 131.2949676513672,
"learning_rate": 9.600000000000001e-06,
"loss": 325.8993,
"step": 25
},
{
"epoch": 0.006,
"grad_norm": 109.72811889648438,
"learning_rate": 1.16e-05,
"loss": 313.0747,
"step": 30
},
{
"epoch": 0.007,
"grad_norm": 93.34612274169922,
"learning_rate": 1.3600000000000002e-05,
"loss": 315.1154,
"step": 35
},
{
"epoch": 0.008,
"grad_norm": 89.763427734375,
"learning_rate": 1.56e-05,
"loss": 307.5251,
"step": 40
},
{
"epoch": 0.009,
"grad_norm": 79.69110870361328,
"learning_rate": 1.76e-05,
"loss": 310.1657,
"step": 45
},
{
"epoch": 0.01,
"grad_norm": 83.45806121826172,
"learning_rate": 1.9600000000000002e-05,
"loss": 322.3456,
"step": 50
},
{
"epoch": 0.011,
"grad_norm": 83.1032943725586,
"learning_rate": 2.16e-05,
"loss": 307.5482,
"step": 55
},
{
"epoch": 0.012,
"grad_norm": 100.54994201660156,
"learning_rate": 2.36e-05,
"loss": 308.4983,
"step": 60
},
{
"epoch": 0.013,
"grad_norm": 74.47264099121094,
"learning_rate": 2.5600000000000002e-05,
"loss": 313.1681,
"step": 65
},
{
"epoch": 0.014,
"grad_norm": 85.1391372680664,
"learning_rate": 2.7600000000000003e-05,
"loss": 302.5862,
"step": 70
},
{
"epoch": 0.015,
"grad_norm": 86.149169921875,
"learning_rate": 2.96e-05,
"loss": 296.1115,
"step": 75
},
{
"epoch": 0.016,
"grad_norm": 82.54764556884766,
"learning_rate": 3.16e-05,
"loss": 299.7468,
"step": 80
},
{
"epoch": 0.017,
"grad_norm": 76.23515319824219,
"learning_rate": 3.3600000000000004e-05,
"loss": 314.8733,
"step": 85
},
{
"epoch": 0.018,
"grad_norm": 86.42366027832031,
"learning_rate": 3.56e-05,
"loss": 309.0613,
"step": 90
},
{
"epoch": 0.019,
"grad_norm": 79.41493225097656,
"learning_rate": 3.76e-05,
"loss": 311.0322,
"step": 95
},
{
"epoch": 0.02,
"grad_norm": 97.31949615478516,
"learning_rate": 3.960000000000001e-05,
"loss": 303.7566,
"step": 100
},
{
"epoch": 0.021,
"grad_norm": 91.24207305908203,
"learning_rate": 4.16e-05,
"loss": 307.9841,
"step": 105
},
{
"epoch": 0.022,
"grad_norm": 82.55218505859375,
"learning_rate": 4.36e-05,
"loss": 303.4123,
"step": 110
},
{
"epoch": 0.023,
"grad_norm": 98.32549285888672,
"learning_rate": 4.5600000000000004e-05,
"loss": 302.9958,
"step": 115
},
{
"epoch": 0.024,
"grad_norm": 90.6205062866211,
"learning_rate": 4.76e-05,
"loss": 306.3299,
"step": 120
},
{
"epoch": 0.025,
"grad_norm": 88.87057495117188,
"learning_rate": 4.96e-05,
"loss": 299.5162,
"step": 125
},
{
"epoch": 0.026,
"grad_norm": 84.20787048339844,
"learning_rate": 5.16e-05,
"loss": 302.7059,
"step": 130
},
{
"epoch": 0.027,
"grad_norm": 95.52533721923828,
"learning_rate": 5.360000000000001e-05,
"loss": 302.2274,
"step": 135
},
{
"epoch": 0.028,
"grad_norm": 117.1716537475586,
"learning_rate": 5.560000000000001e-05,
"loss": 299.0743,
"step": 140
},
{
"epoch": 0.029,
"grad_norm": 77.68347930908203,
"learning_rate": 5.76e-05,
"loss": 295.1787,
"step": 145
},
{
"epoch": 0.03,
"grad_norm": 76.69217681884766,
"learning_rate": 5.96e-05,
"loss": 303.3868,
"step": 150
},
{
"epoch": 0.031,
"grad_norm": 91.29154205322266,
"learning_rate": 6.16e-05,
"loss": 285.78,
"step": 155
},
{
"epoch": 0.032,
"grad_norm": 80.40809631347656,
"learning_rate": 6.36e-05,
"loss": 298.3949,
"step": 160
},
{
"epoch": 0.033,
"grad_norm": 91.36680603027344,
"learning_rate": 6.560000000000001e-05,
"loss": 304.5564,
"step": 165
},
{
"epoch": 0.034,
"grad_norm": 112.79888916015625,
"learning_rate": 6.76e-05,
"loss": 242.7879,
"step": 170
},
{
"epoch": 0.035,
"grad_norm": 98.3003158569336,
"learning_rate": 6.96e-05,
"loss": 239.308,
"step": 175
},
{
"epoch": 0.036,
"grad_norm": 88.80140686035156,
"learning_rate": 7.16e-05,
"loss": 280.2297,
"step": 180
},
{
"epoch": 0.037,
"grad_norm": 75.21417236328125,
"learning_rate": 7.36e-05,
"loss": 285.2648,
"step": 185
},
{
"epoch": 0.038,
"grad_norm": 76.6654052734375,
"learning_rate": 7.560000000000001e-05,
"loss": 297.0549,
"step": 190
},
{
"epoch": 0.039,
"grad_norm": 101.13793182373047,
"learning_rate": 7.76e-05,
"loss": 287.9887,
"step": 195
},
{
"epoch": 0.04,
"grad_norm": 79.47496032714844,
"learning_rate": 7.960000000000001e-05,
"loss": 267.6669,
"step": 200
},
{
"epoch": 0.041,
"grad_norm": 86.7893295288086,
"learning_rate": 8.16e-05,
"loss": 301.4663,
"step": 205
},
{
"epoch": 0.042,
"grad_norm": 98.68603515625,
"learning_rate": 8.36e-05,
"loss": 297.1799,
"step": 210
},
{
"epoch": 0.043,
"grad_norm": 69.82585144042969,
"learning_rate": 8.560000000000001e-05,
"loss": 284.9405,
"step": 215
},
{
"epoch": 0.044,
"grad_norm": 77.55110931396484,
"learning_rate": 8.76e-05,
"loss": 289.2016,
"step": 220
},
{
"epoch": 0.045,
"grad_norm": 67.33943176269531,
"learning_rate": 8.960000000000001e-05,
"loss": 289.2506,
"step": 225
},
{
"epoch": 0.046,
"grad_norm": 66.90230560302734,
"learning_rate": 9.16e-05,
"loss": 297.8193,
"step": 230
},
{
"epoch": 0.047,
"grad_norm": 280.9183044433594,
"learning_rate": 9.360000000000001e-05,
"loss": 299.363,
"step": 235
},
{
"epoch": 0.048,
"grad_norm": 87.29924011230469,
"learning_rate": 9.56e-05,
"loss": 285.1276,
"step": 240
},
{
"epoch": 0.049,
"grad_norm": 69.45281982421875,
"learning_rate": 9.76e-05,
"loss": 291.0465,
"step": 245
},
{
"epoch": 0.05,
"grad_norm": 95.85892486572266,
"learning_rate": 9.960000000000001e-05,
"loss": 253.5561,
"step": 250
},
{
"epoch": 0.051,
"grad_norm": 87.18708801269531,
"learning_rate": 0.0001016,
"loss": 278.3737,
"step": 255
},
{
"epoch": 0.052,
"grad_norm": 59.54637145996094,
"learning_rate": 0.00010360000000000001,
"loss": 284.0256,
"step": 260
},
{
"epoch": 0.053,
"grad_norm": 75.85100555419922,
"learning_rate": 0.0001056,
"loss": 288.8852,
"step": 265
},
{
"epoch": 0.054,
"grad_norm": 79.74699401855469,
"learning_rate": 0.00010760000000000001,
"loss": 235.3202,
"step": 270
},
{
"epoch": 0.055,
"grad_norm": 93.92021942138672,
"learning_rate": 0.00010960000000000001,
"loss": 291.399,
"step": 275
},
{
"epoch": 0.056,
"grad_norm": 73.23931121826172,
"learning_rate": 0.00011160000000000002,
"loss": 297.0533,
"step": 280
},
{
"epoch": 0.057,
"grad_norm": 74.23943328857422,
"learning_rate": 0.0001136,
"loss": 301.6619,
"step": 285
},
{
"epoch": 0.058,
"grad_norm": 76.8428726196289,
"learning_rate": 0.00011559999999999999,
"loss": 297.2145,
"step": 290
},
{
"epoch": 0.059,
"grad_norm": 63.19135284423828,
"learning_rate": 0.0001176,
"loss": 259.2088,
"step": 295
},
{
"epoch": 0.06,
"grad_norm": 74.82901000976562,
"learning_rate": 0.00011960000000000001,
"loss": 269.6802,
"step": 300
},
{
"epoch": 0.061,
"grad_norm": 118.87765502929688,
"learning_rate": 0.0001216,
"loss": 254.0412,
"step": 305
},
{
"epoch": 0.062,
"grad_norm": 74.98046875,
"learning_rate": 0.0001236,
"loss": 294.7132,
"step": 310
},
{
"epoch": 0.063,
"grad_norm": 70.42806243896484,
"learning_rate": 0.00012560000000000002,
"loss": 256.933,
"step": 315
},
{
"epoch": 0.064,
"grad_norm": 86.4557113647461,
"learning_rate": 0.0001276,
"loss": 235.0536,
"step": 320
},
{
"epoch": 0.065,
"grad_norm": 62.878108978271484,
"learning_rate": 0.0001296,
"loss": 255.1298,
"step": 325
},
{
"epoch": 0.066,
"grad_norm": 62.64030838012695,
"learning_rate": 0.0001316,
"loss": 286.0793,
"step": 330
},
{
"epoch": 0.067,
"grad_norm": 82.25812530517578,
"learning_rate": 0.00013360000000000002,
"loss": 255.7905,
"step": 335
},
{
"epoch": 0.068,
"grad_norm": 67.82426452636719,
"learning_rate": 0.00013560000000000002,
"loss": 286.4674,
"step": 340
},
{
"epoch": 0.069,
"grad_norm": 69.97148132324219,
"learning_rate": 0.00013759999999999998,
"loss": 287.4435,
"step": 345
},
{
"epoch": 0.07,
"grad_norm": 127.98161315917969,
"learning_rate": 0.0001396,
"loss": 273.2139,
"step": 350
},
{
"epoch": 0.071,
"grad_norm": 92.13734436035156,
"learning_rate": 0.0001416,
"loss": 283.4005,
"step": 355
},
{
"epoch": 0.072,
"grad_norm": 142.50759887695312,
"learning_rate": 0.0001436,
"loss": 267.1752,
"step": 360
},
{
"epoch": 0.073,
"grad_norm": 110.20304107666016,
"learning_rate": 0.00014560000000000002,
"loss": 248.1763,
"step": 365
},
{
"epoch": 0.074,
"grad_norm": 76.13386535644531,
"learning_rate": 0.0001476,
"loss": 286.8581,
"step": 370
},
{
"epoch": 0.075,
"grad_norm": 169.9783172607422,
"learning_rate": 0.0001496,
"loss": 273.6802,
"step": 375
},
{
"epoch": 0.076,
"grad_norm": 88.17061614990234,
"learning_rate": 0.0001516,
"loss": 279.6191,
"step": 380
},
{
"epoch": 0.077,
"grad_norm": 85.39425659179688,
"learning_rate": 0.00015360000000000002,
"loss": 247.7376,
"step": 385
},
{
"epoch": 0.078,
"grad_norm": 71.32750701904297,
"learning_rate": 0.00015560000000000001,
"loss": 271.884,
"step": 390
},
{
"epoch": 0.079,
"grad_norm": 65.19810485839844,
"learning_rate": 0.0001576,
"loss": 277.6798,
"step": 395
},
{
"epoch": 0.08,
"grad_norm": 94.19916534423828,
"learning_rate": 0.0001596,
"loss": 276.7407,
"step": 400
},
{
"epoch": 0.081,
"grad_norm": 133.42376708984375,
"learning_rate": 0.00016160000000000002,
"loss": 230.0227,
"step": 405
},
{
"epoch": 0.082,
"grad_norm": 74.1983642578125,
"learning_rate": 0.0001636,
"loss": 254.8563,
"step": 410
},
{
"epoch": 0.083,
"grad_norm": 81.3104248046875,
"learning_rate": 0.0001656,
"loss": 266.7406,
"step": 415
},
{
"epoch": 0.084,
"grad_norm": 79.57012176513672,
"learning_rate": 0.0001676,
"loss": 250.5589,
"step": 420
},
{
"epoch": 0.085,
"grad_norm": 77.29656219482422,
"learning_rate": 0.0001696,
"loss": 282.2854,
"step": 425
},
{
"epoch": 0.086,
"grad_norm": 79.8593978881836,
"learning_rate": 0.0001716,
"loss": 252.3088,
"step": 430
},
{
"epoch": 0.087,
"grad_norm": 60.186832427978516,
"learning_rate": 0.00017360000000000002,
"loss": 286.7576,
"step": 435
},
{
"epoch": 0.088,
"grad_norm": 65.36947631835938,
"learning_rate": 0.0001756,
"loss": 281.5767,
"step": 440
},
{
"epoch": 0.089,
"grad_norm": 75.44194030761719,
"learning_rate": 0.0001776,
"loss": 278.4216,
"step": 445
},
{
"epoch": 0.09,
"grad_norm": 66.71389770507812,
"learning_rate": 0.0001796,
"loss": 270.1713,
"step": 450
},
{
"epoch": 0.091,
"grad_norm": 68.38360595703125,
"learning_rate": 0.00018160000000000002,
"loss": 275.1372,
"step": 455
},
{
"epoch": 0.092,
"grad_norm": 72.85200500488281,
"learning_rate": 0.00018360000000000002,
"loss": 281.6097,
"step": 460
},
{
"epoch": 0.093,
"grad_norm": 65.46351623535156,
"learning_rate": 0.0001856,
"loss": 285.4045,
"step": 465
},
{
"epoch": 0.094,
"grad_norm": 77.94449615478516,
"learning_rate": 0.0001876,
"loss": 275.6515,
"step": 470
},
{
"epoch": 0.095,
"grad_norm": 104.31855773925781,
"learning_rate": 0.0001896,
"loss": 252.4393,
"step": 475
},
{
"epoch": 0.096,
"grad_norm": 85.45411682128906,
"learning_rate": 0.0001916,
"loss": 260.0067,
"step": 480
},
{
"epoch": 0.097,
"grad_norm": 71.21846008300781,
"learning_rate": 0.00019360000000000002,
"loss": 282.9384,
"step": 485
},
{
"epoch": 0.098,
"grad_norm": 66.82077026367188,
"learning_rate": 0.0001956,
"loss": 268.286,
"step": 490
},
{
"epoch": 0.099,
"grad_norm": 66.0440673828125,
"learning_rate": 0.0001976,
"loss": 280.2809,
"step": 495
},
{
"epoch": 0.1,
"grad_norm": 65.30158996582031,
"learning_rate": 0.0001996,
"loss": 277.9199,
"step": 500
},
{
"epoch": 0.101,
"grad_norm": 69.67945098876953,
"learning_rate": 0.00019999961008995606,
"loss": 289.9011,
"step": 505
},
{
"epoch": 0.102,
"grad_norm": 67.6677474975586,
"learning_rate": 0.0001999980260856137,
"loss": 277.9196,
"step": 510
},
{
"epoch": 0.103,
"grad_norm": 74.7071762084961,
"learning_rate": 0.000199995223636881,
"loss": 262.7933,
"step": 515
},
{
"epoch": 0.104,
"grad_norm": 69.05998992919922,
"learning_rate": 0.00019999120277790477,
"loss": 287.7239,
"step": 520
},
{
"epoch": 0.105,
"grad_norm": 69.93698120117188,
"learning_rate": 0.00019998596355767805,
"loss": 275.5523,
"step": 525
},
{
"epoch": 0.106,
"grad_norm": 61.50294876098633,
"learning_rate": 0.000199979506040039,
"loss": 280.7647,
"step": 530
},
{
"epoch": 0.107,
"grad_norm": 68.64286041259766,
"learning_rate": 0.00019997183030367048,
"loss": 271.8449,
"step": 535
},
{
"epoch": 0.108,
"grad_norm": 63.09992980957031,
"learning_rate": 0.00019996293644209887,
"loss": 278.2004,
"step": 540
},
{
"epoch": 0.109,
"grad_norm": 71.78915405273438,
"learning_rate": 0.0001999528245636931,
"loss": 278.1076,
"step": 545
},
{
"epoch": 0.11,
"grad_norm": 119.38697052001953,
"learning_rate": 0.00019994149479166324,
"loss": 250.7288,
"step": 550
},
{
"epoch": 0.111,
"grad_norm": 68.61959075927734,
"learning_rate": 0.00019992894726405893,
"loss": 210.8162,
"step": 555
},
{
"epoch": 0.112,
"grad_norm": 76.88066864013672,
"learning_rate": 0.00019991518213376787,
"loss": 280.71,
"step": 560
},
{
"epoch": 0.113,
"grad_norm": 145.10508728027344,
"learning_rate": 0.00019990019956851382,
"loss": 267.4712,
"step": 565
},
{
"epoch": 0.114,
"grad_norm": 60.84817123413086,
"learning_rate": 0.0001998839997508546,
"loss": 271.589,
"step": 570
},
{
"epoch": 0.115,
"grad_norm": 68.52861785888672,
"learning_rate": 0.00019986658287817987,
"loss": 264.3261,
"step": 575
},
{
"epoch": 0.116,
"grad_norm": 74.1113052368164,
"learning_rate": 0.00019984794916270876,
"loss": 246.1759,
"step": 580
},
{
"epoch": 0.117,
"grad_norm": 72.84656524658203,
"learning_rate": 0.00019982809883148722,
"loss": 260.5045,
"step": 585
},
{
"epoch": 0.118,
"grad_norm": 70.28099822998047,
"learning_rate": 0.00019980703212638522,
"loss": 240.8895,
"step": 590
},
{
"epoch": 0.119,
"grad_norm": 72.57321166992188,
"learning_rate": 0.00019978474930409395,
"loss": 267.5912,
"step": 595
},
{
"epoch": 0.12,
"grad_norm": 82.38754272460938,
"learning_rate": 0.00019976125063612252,
"loss": 260.8692,
"step": 600
},
{
"epoch": 0.121,
"grad_norm": 62.69374084472656,
"learning_rate": 0.00019973653640879485,
"loss": 267.0439,
"step": 605
},
{
"epoch": 0.122,
"grad_norm": 183.09005737304688,
"learning_rate": 0.00019971060692324598,
"loss": 261.9547,
"step": 610
},
{
"epoch": 0.123,
"grad_norm": 77.94440460205078,
"learning_rate": 0.00019968346249541846,
"loss": 262.4955,
"step": 615
},
{
"epoch": 0.124,
"grad_norm": 303.3373107910156,
"learning_rate": 0.00019965510345605866,
"loss": 259.7711,
"step": 620
},
{
"epoch": 0.125,
"grad_norm": 74.0142822265625,
"learning_rate": 0.0001996255301507125,
"loss": 270.3866,
"step": 625
},
{
"epoch": 0.126,
"grad_norm": 71.14913177490234,
"learning_rate": 0.00019959474293972129,
"loss": 272.4547,
"step": 630
},
{
"epoch": 0.127,
"grad_norm": 135.9524688720703,
"learning_rate": 0.00019956274219821757,
"loss": 253.1282,
"step": 635
},
{
"epoch": 0.128,
"grad_norm": 66.36004638671875,
"learning_rate": 0.00019952952831612026,
"loss": 273.6564,
"step": 640
},
{
"epoch": 0.129,
"grad_norm": 70.32064056396484,
"learning_rate": 0.00019949510169813003,
"loss": 280.9516,
"step": 645
},
{
"epoch": 0.13,
"grad_norm": 59.25802993774414,
"learning_rate": 0.00019945946276372434,
"loss": 254.8434,
"step": 650
},
{
"epoch": 0.131,
"grad_norm": 70.53588104248047,
"learning_rate": 0.00019942261194715236,
"loss": 245.8175,
"step": 655
},
{
"epoch": 0.132,
"grad_norm": 69.76761627197266,
"learning_rate": 0.00019938454969742968,
"loss": 275.741,
"step": 660
},
{
"epoch": 0.133,
"grad_norm": 64.74825286865234,
"learning_rate": 0.00019934527647833276,
"loss": 266.5821,
"step": 665
},
{
"epoch": 0.134,
"grad_norm": 65.31316375732422,
"learning_rate": 0.00019930479276839344,
"loss": 275.6624,
"step": 670
},
{
"epoch": 0.135,
"grad_norm": 62.38485336303711,
"learning_rate": 0.0001992630990608929,
"loss": 261.4533,
"step": 675
},
{
"epoch": 0.136,
"grad_norm": 71.19464111328125,
"learning_rate": 0.00019922019586385585,
"loss": 262.5512,
"step": 680
},
{
"epoch": 0.137,
"grad_norm": 168.85684204101562,
"learning_rate": 0.00019917608370004417,
"loss": 234.3873,
"step": 685
},
{
"epoch": 0.138,
"grad_norm": 75.73576354980469,
"learning_rate": 0.00019913076310695068,
"loss": 231.9306,
"step": 690
},
{
"epoch": 0.139,
"grad_norm": 143.76568603515625,
"learning_rate": 0.00019908423463679248,
"loss": 264.1436,
"step": 695
},
{
"epoch": 0.14,
"grad_norm": 83.88737487792969,
"learning_rate": 0.0001990364988565043,
"loss": 281.3076,
"step": 700
},
{
"epoch": 0.141,
"grad_norm": 70.77721405029297,
"learning_rate": 0.00019898755634773158,
"loss": 268.7908,
"step": 705
},
{
"epoch": 0.142,
"grad_norm": 84.32762145996094,
"learning_rate": 0.00019893740770682335,
"loss": 269.243,
"step": 710
},
{
"epoch": 0.143,
"grad_norm": 60.8754768371582,
"learning_rate": 0.0001988860535448249,
"loss": 247.6113,
"step": 715
},
{
"epoch": 0.144,
"grad_norm": 72.7818603515625,
"learning_rate": 0.00019883349448747062,
"loss": 268.8609,
"step": 720
},
{
"epoch": 0.145,
"grad_norm": 88.45670318603516,
"learning_rate": 0.0001987797311751759,
"loss": 268.0048,
"step": 725
},
{
"epoch": 0.146,
"grad_norm": 72.0194320678711,
"learning_rate": 0.00019872476426302982,
"loss": 275.5222,
"step": 730
},
{
"epoch": 0.147,
"grad_norm": 62.675167083740234,
"learning_rate": 0.0001986685944207868,
"loss": 267.5268,
"step": 735
},
{
"epoch": 0.148,
"grad_norm": 82.43748474121094,
"learning_rate": 0.0001986112223328587,
"loss": 274.9757,
"step": 740
},
{
"epoch": 0.149,
"grad_norm": 71.96373748779297,
"learning_rate": 0.00019855264869830629,
"loss": 264.831,
"step": 745
},
{
"epoch": 0.15,
"grad_norm": 66.41895294189453,
"learning_rate": 0.00019849287423083078,
"loss": 263.1631,
"step": 750
},
{
"epoch": 0.151,
"grad_norm": 87.85332489013672,
"learning_rate": 0.00019843189965876526,
"loss": 260.5555,
"step": 755
},
{
"epoch": 0.152,
"grad_norm": 74.49442291259766,
"learning_rate": 0.00019836972572506557,
"loss": 275.7229,
"step": 760
},
{
"epoch": 0.153,
"grad_norm": 77.08104705810547,
"learning_rate": 0.00019830635318730154,
"loss": 256.9746,
"step": 765
},
{
"epoch": 0.154,
"grad_norm": 73.9883041381836,
"learning_rate": 0.00019824178281764753,
"loss": 276.2443,
"step": 770
},
{
"epoch": 0.155,
"grad_norm": 73.93590545654297,
"learning_rate": 0.00019817601540287306,
"loss": 254.5362,
"step": 775
},
{
"epoch": 0.156,
"grad_norm": 68.59113311767578,
"learning_rate": 0.0001981090517443334,
"loss": 262.6415,
"step": 780
},
{
"epoch": 0.157,
"grad_norm": 61.02271270751953,
"learning_rate": 0.0001980408926579596,
"loss": 252.363,
"step": 785
},
{
"epoch": 0.158,
"grad_norm": 62.54066848754883,
"learning_rate": 0.00019797153897424852,
"loss": 268.4424,
"step": 790
},
{
"epoch": 0.159,
"grad_norm": 63.734649658203125,
"learning_rate": 0.000197900991538253,
"loss": 255.699,
"step": 795
},
{
"epoch": 0.16,
"grad_norm": 487.8463134765625,
"learning_rate": 0.00019782925120957124,
"loss": 268.1905,
"step": 800
},
{
"epoch": 0.161,
"grad_norm": 70.30332946777344,
"learning_rate": 0.00019775631886233654,
"loss": 260.2901,
"step": 805
},
{
"epoch": 0.162,
"grad_norm": 81.92864990234375,
"learning_rate": 0.0001976821953852065,
"loss": 257.2851,
"step": 810
},
{
"epoch": 0.163,
"grad_norm": 72.4359130859375,
"learning_rate": 0.00019760688168135232,
"loss": 258.2725,
"step": 815
},
{
"epoch": 0.164,
"grad_norm": 72.5333023071289,
"learning_rate": 0.00019753037866844771,
"loss": 245.3567,
"step": 820
},
{
"epoch": 0.165,
"grad_norm": 70.82955932617188,
"learning_rate": 0.00019745268727865774,
"loss": 247.9339,
"step": 825
},
{
"epoch": 0.166,
"grad_norm": 66.89386749267578,
"learning_rate": 0.00019737380845862745,
"loss": 267.3392,
"step": 830
},
{
"epoch": 0.167,
"grad_norm": 62.468936920166016,
"learning_rate": 0.0001972937431694704,
"loss": 249.5989,
"step": 835
},
{
"epoch": 0.168,
"grad_norm": 66.95137786865234,
"learning_rate": 0.00019721249238675688,
"loss": 256.6585,
"step": 840
},
{
"epoch": 0.169,
"grad_norm": 69.7963638305664,
"learning_rate": 0.000197130057100502,
"loss": 266.6019,
"step": 845
},
{
"epoch": 0.17,
"grad_norm": 64.68950653076172,
"learning_rate": 0.00019704643831515374,
"loss": 268.029,
"step": 850
},
{
"epoch": 0.171,
"grad_norm": 71.6061019897461,
"learning_rate": 0.0001969616370495806,
"loss": 261.1283,
"step": 855
},
{
"epoch": 0.172,
"grad_norm": 62.72983932495117,
"learning_rate": 0.00019687565433705926,
"loss": 267.8803,
"step": 860
},
{
"epoch": 0.173,
"grad_norm": 64.09201049804688,
"learning_rate": 0.00019678849122526187,
"loss": 243.9025,
"step": 865
},
{
"epoch": 0.174,
"grad_norm": 61.98489761352539,
"learning_rate": 0.00019670014877624353,
"loss": 241.4365,
"step": 870
},
{
"epoch": 0.175,
"grad_norm": 59.48838424682617,
"learning_rate": 0.00019661062806642903,
"loss": 250.3907,
"step": 875
},
{
"epoch": 0.176,
"grad_norm": 70.55399322509766,
"learning_rate": 0.0001965199301866,
"loss": 242.1836,
"step": 880
},
{
"epoch": 0.177,
"grad_norm": 63.19829177856445,
"learning_rate": 0.00019642805624188147,
"loss": 246.7926,
"step": 885
},
{
"epoch": 0.178,
"grad_norm": 70.59349060058594,
"learning_rate": 0.0001963350073517285,
"loss": 235.0772,
"step": 890
},
{
"epoch": 0.179,
"grad_norm": 70.43497467041016,
"learning_rate": 0.0001962407846499124,
"loss": 246.707,
"step": 895
},
{
"epoch": 0.18,
"grad_norm": 85.28739166259766,
"learning_rate": 0.0001961453892845071,
"loss": 240.7082,
"step": 900
},
{
"epoch": 0.181,
"grad_norm": 71.00152587890625,
"learning_rate": 0.00019604882241787498,
"loss": 241.3172,
"step": 905
},
{
"epoch": 0.182,
"grad_norm": 70.0228042602539,
"learning_rate": 0.0001959510852266529,
"loss": 259.7299,
"step": 910
},
{
"epoch": 0.183,
"grad_norm": 74.89047241210938,
"learning_rate": 0.0001958521789017376,
"loss": 258.1866,
"step": 915
},
{
"epoch": 0.184,
"grad_norm": 69.18814086914062,
"learning_rate": 0.00019575210464827149,
"loss": 270.8136,
"step": 920
},
{
"epoch": 0.185,
"grad_norm": 69.73190307617188,
"learning_rate": 0.0001956508636856278,
"loss": 258.3369,
"step": 925
},
{
"epoch": 0.186,
"grad_norm": 66.07145690917969,
"learning_rate": 0.00019554845724739566,
"loss": 251.0459,
"step": 930
},
{
"epoch": 0.187,
"grad_norm": 85.49530029296875,
"learning_rate": 0.00019544488658136523,
"loss": 266.0341,
"step": 935
},
{
"epoch": 0.188,
"grad_norm": 68.31378173828125,
"learning_rate": 0.00019534015294951233,
"loss": 264.6955,
"step": 940
},
{
"epoch": 0.189,
"grad_norm": 82.6740951538086,
"learning_rate": 0.00019523425762798329,
"loss": 266.1459,
"step": 945
},
{
"epoch": 0.19,
"grad_norm": 83.74392700195312,
"learning_rate": 0.00019512720190707913,
"loss": 247.1594,
"step": 950
},
{
"epoch": 0.191,
"grad_norm": 83.73538208007812,
"learning_rate": 0.00019501898709124008,
"loss": 260.7229,
"step": 955
},
{
"epoch": 0.192,
"grad_norm": 66.07109069824219,
"learning_rate": 0.00019490961449902946,
"loss": 263.6804,
"step": 960
},
{
"epoch": 0.193,
"grad_norm": 63.7003059387207,
"learning_rate": 0.00019479908546311781,
"loss": 264.5129,
"step": 965
},
{
"epoch": 0.194,
"grad_norm": 65.40355682373047,
"learning_rate": 0.0001946874013302666,
"loss": 260.6219,
"step": 970
},
{
"epoch": 0.195,
"grad_norm": 65.47498321533203,
"learning_rate": 0.0001945745634613117,
"loss": 263.1286,
"step": 975
},
{
"epoch": 0.196,
"grad_norm": 68.73960876464844,
"learning_rate": 0.0001944605732311469,
"loss": 265.6815,
"step": 980
},
{
"epoch": 0.197,
"grad_norm": 84.80562591552734,
"learning_rate": 0.00019434543202870725,
"loss": 253.9608,
"step": 985
},
{
"epoch": 0.198,
"grad_norm": 66.91242218017578,
"learning_rate": 0.0001942291412569519,
"loss": 262.0103,
"step": 990
},
{
"epoch": 0.199,
"grad_norm": 61.25504684448242,
"learning_rate": 0.00019411170233284727,
"loss": 269.1613,
"step": 995
},
{
"epoch": 0.2,
"grad_norm": 56.45645523071289,
"learning_rate": 0.00019399311668734956,
"loss": 264.6178,
"step": 1000
},
{
"epoch": 0.201,
"grad_norm": 63.47613525390625,
"learning_rate": 0.00019387338576538744,
"loss": 270.6375,
"step": 1005
},
{
"epoch": 0.202,
"grad_norm": 71.85877227783203,
"learning_rate": 0.0001937525110258444,
"loss": 259.4103,
"step": 1010
},
{
"epoch": 0.203,
"grad_norm": 70.76119995117188,
"learning_rate": 0.00019363049394154094,
"loss": 267.0952,
"step": 1015
},
{
"epoch": 0.204,
"grad_norm": 62.38040542602539,
"learning_rate": 0.00019350733599921683,
"loss": 251.4135,
"step": 1020
},
{
"epoch": 0.205,
"grad_norm": 72.8625259399414,
"learning_rate": 0.00019338303869951269,
"loss": 256.7074,
"step": 1025
},
{
"epoch": 0.206,
"grad_norm": 74.69538879394531,
"learning_rate": 0.00019325760355695188,
"loss": 267.8689,
"step": 1030
},
{
"epoch": 0.207,
"grad_norm": 71.6656723022461,
"learning_rate": 0.00019313103209992204,
"loss": 252.3839,
"step": 1035
},
{
"epoch": 0.208,
"grad_norm": 57.08998107910156,
"learning_rate": 0.0001930033258706564,
"loss": 257.3785,
"step": 1040
},
{
"epoch": 0.209,
"grad_norm": 75.07803344726562,
"learning_rate": 0.00019287448642521513,
"loss": 267.4957,
"step": 1045
},
{
"epoch": 0.21,
"grad_norm": 79.76412963867188,
"learning_rate": 0.00019274451533346615,
"loss": 261.6118,
"step": 1050
},
{
"epoch": 0.211,
"grad_norm": 81.56097412109375,
"learning_rate": 0.00019261341417906621,
"loss": 265.8841,
"step": 1055
},
{
"epoch": 0.212,
"grad_norm": 70.84222412109375,
"learning_rate": 0.0001924811845594415,
"loss": 250.3418,
"step": 1060
},
{
"epoch": 0.213,
"grad_norm": 67.82208251953125,
"learning_rate": 0.00019234782808576824,
"loss": 263.8429,
"step": 1065
},
{
"epoch": 0.214,
"grad_norm": 72.11970520019531,
"learning_rate": 0.00019221334638295294,
"loss": 250.9662,
"step": 1070
},
{
"epoch": 0.215,
"grad_norm": 74.35679626464844,
"learning_rate": 0.00019207774108961272,
"loss": 259.2442,
"step": 1075
},
{
"epoch": 0.216,
"grad_norm": 69.58717346191406,
"learning_rate": 0.0001919410138580553,
"loss": 258.0087,
"step": 1080
},
{
"epoch": 0.217,
"grad_norm": 71.62444305419922,
"learning_rate": 0.0001918031663542588,
"loss": 253.524,
"step": 1085
},
{
"epoch": 0.218,
"grad_norm": 64.11453247070312,
"learning_rate": 0.00019166420025785164,
"loss": 263.3739,
"step": 1090
},
{
"epoch": 0.219,
"grad_norm": 67.0963134765625,
"learning_rate": 0.00019152411726209176,
"loss": 264.8893,
"step": 1095
},
{
"epoch": 0.22,
"grad_norm": 70.35098266601562,
"learning_rate": 0.0001913829190738463,
"loss": 237.8675,
"step": 1100
},
{
"epoch": 0.221,
"grad_norm": 70.07389831542969,
"learning_rate": 0.00019124060741357063,
"loss": 265.9235,
"step": 1105
},
{
"epoch": 0.222,
"grad_norm": 70.8550796508789,
"learning_rate": 0.0001910971840152874,
"loss": 260.5005,
"step": 1110
},
{
"epoch": 0.223,
"grad_norm": 93.7171630859375,
"learning_rate": 0.00019095265062656544,
"loss": 254.5492,
"step": 1115
},
{
"epoch": 0.224,
"grad_norm": 151.48504638671875,
"learning_rate": 0.00019080700900849851,
"loss": 253.4584,
"step": 1120
},
{
"epoch": 0.225,
"grad_norm": 72.2385482788086,
"learning_rate": 0.00019066026093568378,
"loss": 259.241,
"step": 1125
},
{
"epoch": 0.226,
"grad_norm": 60.79322814941406,
"learning_rate": 0.00019051240819620014,
"loss": 259.5886,
"step": 1130
},
{
"epoch": 0.227,
"grad_norm": 65.25270080566406,
"learning_rate": 0.00019036345259158667,
"loss": 260.1056,
"step": 1135
},
{
"epoch": 0.228,
"grad_norm": 60.94587707519531,
"learning_rate": 0.00019021339593682028,
"loss": 257.8644,
"step": 1140
},
{
"epoch": 0.229,
"grad_norm": 84.38846588134766,
"learning_rate": 0.00019006224006029406,
"loss": 244.2875,
"step": 1145
},
{
"epoch": 0.23,
"grad_norm": 69.91790771484375,
"learning_rate": 0.00018990998680379456,
"loss": 258.3608,
"step": 1150
},
{
"epoch": 0.231,
"grad_norm": 81.54023742675781,
"learning_rate": 0.00018975663802247976,
"loss": 272.5109,
"step": 1155
},
{
"epoch": 0.232,
"grad_norm": 69.9112319946289,
"learning_rate": 0.0001896021955848561,
"loss": 255.1114,
"step": 1160
},
{
"epoch": 0.233,
"grad_norm": 78.4234619140625,
"learning_rate": 0.000189446661372756,
"loss": 259.7902,
"step": 1165
},
{
"epoch": 0.234,
"grad_norm": 59.534034729003906,
"learning_rate": 0.0001892900372813147,
"loss": 265.1972,
"step": 1170
},
{
"epoch": 0.235,
"grad_norm": 67.2402114868164,
"learning_rate": 0.00018913232521894732,
"loss": 257.1966,
"step": 1175
},
{
"epoch": 0.236,
"grad_norm": 64.15892028808594,
"learning_rate": 0.00018897352710732564,
"loss": 256.5153,
"step": 1180
},
{
"epoch": 0.237,
"grad_norm": 106.17436981201172,
"learning_rate": 0.00018881364488135448,
"loss": 267.3872,
"step": 1185
},
{
"epoch": 0.238,
"grad_norm": 68.61872100830078,
"learning_rate": 0.00018865268048914828,
"loss": 253.5069,
"step": 1190
},
{
"epoch": 0.239,
"grad_norm": 68.29266357421875,
"learning_rate": 0.00018849063589200743,
"loss": 260.4851,
"step": 1195
},
{
"epoch": 0.24,
"grad_norm": 69.44786834716797,
"learning_rate": 0.00018832751306439418,
"loss": 252.4921,
"step": 1200
},
{
"epoch": 0.241,
"grad_norm": 70.99056243896484,
"learning_rate": 0.0001881633139939087,
"loss": 262.0189,
"step": 1205
},
{
"epoch": 0.242,
"grad_norm": 60.21652603149414,
"learning_rate": 0.00018799804068126485,
"loss": 253.4937,
"step": 1210
},
{
"epoch": 0.243,
"grad_norm": 66.3786392211914,
"learning_rate": 0.00018783169514026578,
"loss": 255.9939,
"step": 1215
},
{
"epoch": 0.244,
"grad_norm": 68.00920104980469,
"learning_rate": 0.00018766427939777945,
"loss": 257.3594,
"step": 1220
},
{
"epoch": 0.245,
"grad_norm": 65.09504699707031,
"learning_rate": 0.0001874957954937138,
"loss": 260.6237,
"step": 1225
},
{
"epoch": 0.246,
"grad_norm": 60.35883331298828,
"learning_rate": 0.00018732624548099204,
"loss": 257.7881,
"step": 1230
},
{
"epoch": 0.247,
"grad_norm": 117.36902618408203,
"learning_rate": 0.00018715563142552758,
"loss": 256.1025,
"step": 1235
},
{
"epoch": 0.248,
"grad_norm": 61.20811080932617,
"learning_rate": 0.0001869839554061988,
"loss": 255.0857,
"step": 1240
},
{
"epoch": 0.249,
"grad_norm": 78.92390441894531,
"learning_rate": 0.00018681121951482393,
"loss": 259.8825,
"step": 1245
},
{
"epoch": 0.25,
"grad_norm": 62.366363525390625,
"learning_rate": 0.00018663742585613518,
"loss": 258.528,
"step": 1250
},
{
"epoch": 0.251,
"grad_norm": 61.07777786254883,
"learning_rate": 0.0001864625765477535,
"loss": 259.0611,
"step": 1255
},
{
"epoch": 0.252,
"grad_norm": 62.74348449707031,
"learning_rate": 0.0001862866737201625,
"loss": 256.3734,
"step": 1260
},
{
"epoch": 0.253,
"grad_norm": 63.42617416381836,
"learning_rate": 0.00018610971951668265,
"loss": 269.0647,
"step": 1265
},
{
"epoch": 0.254,
"grad_norm": 67.448974609375,
"learning_rate": 0.00018593171609344503,
"loss": 250.4642,
"step": 1270
},
{
"epoch": 0.255,
"grad_norm": 61.498104095458984,
"learning_rate": 0.00018575266561936523,
"loss": 259.9946,
"step": 1275
},
{
"epoch": 0.256,
"grad_norm": 61.68122100830078,
"learning_rate": 0.00018557257027611675,
"loss": 257.0583,
"step": 1280
},
{
"epoch": 0.257,
"grad_norm": 62.55679702758789,
"learning_rate": 0.0001853914322581045,
"loss": 256.0573,
"step": 1285
},
{
"epoch": 0.258,
"grad_norm": 112.78436279296875,
"learning_rate": 0.0001852092537724381,
"loss": 244.0424,
"step": 1290
},
{
"epoch": 0.259,
"grad_norm": 79.3133544921875,
"learning_rate": 0.00018502603703890488,
"loss": 250.8328,
"step": 1295
},
{
"epoch": 0.26,
"grad_norm": 70.6105728149414,
"learning_rate": 0.0001848417842899429,
"loss": 258.7902,
"step": 1300
},
{
"epoch": 0.261,
"grad_norm": 68.15289306640625,
"learning_rate": 0.0001846564977706138,
"loss": 250.6485,
"step": 1305
},
{
"epoch": 0.262,
"grad_norm": 65.69000244140625,
"learning_rate": 0.00018447017973857532,
"loss": 248.6376,
"step": 1310
},
{
"epoch": 0.263,
"grad_norm": 58.19040298461914,
"learning_rate": 0.0001842828324640539,
"loss": 263.3102,
"step": 1315
},
{
"epoch": 0.264,
"grad_norm": 64.97654724121094,
"learning_rate": 0.00018409445822981693,
"loss": 256.339,
"step": 1320
},
{
"epoch": 0.265,
"grad_norm": 450.18511962890625,
"learning_rate": 0.000183905059331145,
"loss": 254.6749,
"step": 1325
},
{
"epoch": 0.266,
"grad_norm": 82.3821029663086,
"learning_rate": 0.000183714638075804,
"loss": 254.4249,
"step": 1330
},
{
"epoch": 0.267,
"grad_norm": 75.35969543457031,
"learning_rate": 0.00018352319678401676,
"loss": 254.6711,
"step": 1335
},
{
"epoch": 0.268,
"grad_norm": 64.18514251708984,
"learning_rate": 0.000183330737788435,
"loss": 259.8325,
"step": 1340
},
{
"epoch": 0.269,
"grad_norm": 66.32669830322266,
"learning_rate": 0.00018313726343411086,
"loss": 253.2079,
"step": 1345
},
{
"epoch": 0.27,
"grad_norm": 74.89440155029297,
"learning_rate": 0.00018294277607846832,
"loss": 246.6619,
"step": 1350
},
{
"epoch": 0.271,
"grad_norm": 62.38987731933594,
"learning_rate": 0.00018274727809127438,
"loss": 247.1976,
"step": 1355
},
{
"epoch": 0.272,
"grad_norm": 69.08052062988281,
"learning_rate": 0.00018255077185461038,
"loss": 244.9568,
"step": 1360
},
{
"epoch": 0.273,
"grad_norm": 62.61387634277344,
"learning_rate": 0.00018235325976284275,
"loss": 243.8006,
"step": 1365
},
{
"epoch": 0.274,
"grad_norm": 60.06017303466797,
"learning_rate": 0.00018215474422259402,
"loss": 241.652,
"step": 1370
},
{
"epoch": 0.275,
"grad_norm": 74.84953308105469,
"learning_rate": 0.0001819552276527134,
"loss": 243.0105,
"step": 1375
},
{
"epoch": 0.276,
"grad_norm": 61.174224853515625,
"learning_rate": 0.0001817547124842473,
"loss": 252.2928,
"step": 1380
},
{
"epoch": 0.277,
"grad_norm": 73.44465637207031,
"learning_rate": 0.00018155320116040982,
"loss": 259.0343,
"step": 1385
},
{
"epoch": 0.278,
"grad_norm": 72.30426788330078,
"learning_rate": 0.0001813506961365528,
"loss": 249.5622,
"step": 1390
},
{
"epoch": 0.279,
"grad_norm": 61.13508987426758,
"learning_rate": 0.00018114719988013612,
"loss": 254.7038,
"step": 1395
},
{
"epoch": 0.28,
"grad_norm": 60.89707946777344,
"learning_rate": 0.00018094271487069735,
"loss": 261.7343,
"step": 1400
},
{
"epoch": 0.281,
"grad_norm": 60.29357147216797,
"learning_rate": 0.00018073724359982186,
"loss": 263.7504,
"step": 1405
},
{
"epoch": 0.282,
"grad_norm": 64.27754974365234,
"learning_rate": 0.0001805307885711122,
"loss": 259.5201,
"step": 1410
},
{
"epoch": 0.283,
"grad_norm": 66.30209350585938,
"learning_rate": 0.0001803233523001578,
"loss": 239.3289,
"step": 1415
},
{
"epoch": 0.284,
"grad_norm": 59.92820358276367,
"learning_rate": 0.00018011493731450413,
"loss": 252.4354,
"step": 1420
},
{
"epoch": 0.285,
"grad_norm": 61.41872024536133,
"learning_rate": 0.00017990554615362198,
"loss": 270.7561,
"step": 1425
},
{
"epoch": 0.286,
"grad_norm": 58.28062438964844,
"learning_rate": 0.00017969518136887663,
"loss": 254.5627,
"step": 1430
},
{
"epoch": 0.287,
"grad_norm": 69.97006225585938,
"learning_rate": 0.00017948384552349657,
"loss": 250.7488,
"step": 1435
},
{
"epoch": 0.288,
"grad_norm": 64.22581481933594,
"learning_rate": 0.00017927154119254236,
"loss": 236.5071,
"step": 1440
},
{
"epoch": 0.289,
"grad_norm": 62.77339172363281,
"learning_rate": 0.0001790582709628753,
"loss": 243.0065,
"step": 1445
},
{
"epoch": 0.29,
"grad_norm": 72.30258178710938,
"learning_rate": 0.00017884403743312582,
"loss": 252.5576,
"step": 1450
},
{
"epoch": 0.291,
"grad_norm": 68.7700424194336,
"learning_rate": 0.00017862884321366188,
"loss": 246.0682,
"step": 1455
},
{
"epoch": 0.292,
"grad_norm": 101.85023498535156,
"learning_rate": 0.00017841269092655715,
"loss": 241.2078,
"step": 1460
},
{
"epoch": 0.293,
"grad_norm": 70.41748046875,
"learning_rate": 0.000178195583205559,
"loss": 232.2595,
"step": 1465
},
{
"epoch": 0.294,
"grad_norm": 56.64640426635742,
"learning_rate": 0.00017797752269605653,
"loss": 234.7589,
"step": 1470
},
{
"epoch": 0.295,
"grad_norm": 73.50944519042969,
"learning_rate": 0.0001777585120550482,
"loss": 250.9359,
"step": 1475
},
{
"epoch": 0.296,
"grad_norm": 82.7099609375,
"learning_rate": 0.0001775385539511096,
"loss": 227.0061,
"step": 1480
},
{
"epoch": 0.297,
"grad_norm": 96.73185729980469,
"learning_rate": 0.00017731765106436073,
"loss": 233.9576,
"step": 1485
},
{
"epoch": 0.298,
"grad_norm": 65.25926971435547,
"learning_rate": 0.00017709580608643363,
"loss": 235.6743,
"step": 1490
},
{
"epoch": 0.299,
"grad_norm": 61.761226654052734,
"learning_rate": 0.00017687302172043933,
"loss": 237.7806,
"step": 1495
},
{
"epoch": 0.3,
"grad_norm": 59.79208755493164,
"learning_rate": 0.00017664930068093498,
"loss": 244.9097,
"step": 1500
},
{
"epoch": 0.301,
"grad_norm": 75.16264343261719,
"learning_rate": 0.0001764246456938909,
"loss": 258.5652,
"step": 1505
},
{
"epoch": 0.302,
"grad_norm": 68.61026763916016,
"learning_rate": 0.0001761990594966572,
"loss": 264.604,
"step": 1510
},
{
"epoch": 0.303,
"grad_norm": 64.94346618652344,
"learning_rate": 0.00017597254483793048,
"loss": 251.489,
"step": 1515
},
{
"epoch": 0.304,
"grad_norm": 66.63980102539062,
"learning_rate": 0.00017574510447772039,
"loss": 255.6003,
"step": 1520
},
{
"epoch": 0.305,
"grad_norm": 72.99297332763672,
"learning_rate": 0.00017551674118731591,
"loss": 252.4185,
"step": 1525
},
{
"epoch": 0.306,
"grad_norm": 59.50336837768555,
"learning_rate": 0.00017528745774925172,
"loss": 247.8548,
"step": 1530
},
{
"epoch": 0.307,
"grad_norm": 66.31355285644531,
"learning_rate": 0.00017505725695727412,
"loss": 250.6218,
"step": 1535
},
{
"epoch": 0.308,
"grad_norm": 58.865623474121094,
"learning_rate": 0.00017482614161630714,
"loss": 260.7944,
"step": 1540
},
{
"epoch": 0.309,
"grad_norm": 63.617034912109375,
"learning_rate": 0.00017459411454241822,
"loss": 267.0334,
"step": 1545
},
{
"epoch": 0.31,
"grad_norm": 62.7519645690918,
"learning_rate": 0.0001743611785627841,
"loss": 245.0342,
"step": 1550
},
{
"epoch": 0.311,
"grad_norm": 85.38328552246094,
"learning_rate": 0.0001741273365156561,
"loss": 254.2524,
"step": 1555
},
{
"epoch": 0.312,
"grad_norm": 67.7838363647461,
"learning_rate": 0.0001738925912503259,
"loss": 256.7063,
"step": 1560
},
{
"epoch": 0.313,
"grad_norm": 110.21266174316406,
"learning_rate": 0.00017365694562709034,
"loss": 243.5006,
"step": 1565
},
{
"epoch": 0.314,
"grad_norm": 69.58531188964844,
"learning_rate": 0.00017342040251721702,
"loss": 254.3385,
"step": 1570
},
{
"epoch": 0.315,
"grad_norm": 65.52213287353516,
"learning_rate": 0.0001731829648029091,
"loss": 260.2927,
"step": 1575
},
{
"epoch": 0.316,
"grad_norm": 62.20018768310547,
"learning_rate": 0.00017294463537727024,
"loss": 253.9355,
"step": 1580
},
{
"epoch": 0.317,
"grad_norm": 72.21735382080078,
"learning_rate": 0.0001727054171442692,
"loss": 248.7483,
"step": 1585
},
{
"epoch": 0.318,
"grad_norm": 63.43247604370117,
"learning_rate": 0.0001724653130187047,
"loss": 229.2525,
"step": 1590
},
{
"epoch": 0.319,
"grad_norm": 58.46535873413086,
"learning_rate": 0.0001722243259261697,
"loss": 241.5975,
"step": 1595
},
{
"epoch": 0.32,
"grad_norm": 71.36355590820312,
"learning_rate": 0.0001719824588030159,
"loss": 246.6689,
"step": 1600
},
{
"epoch": 0.321,
"grad_norm": 77.30906677246094,
"learning_rate": 0.00017173971459631787,
"loss": 247.9697,
"step": 1605
},
{
"epoch": 0.322,
"grad_norm": 63.93739318847656,
"learning_rate": 0.00017149609626383717,
"loss": 260.0547,
"step": 1610
},
{
"epoch": 0.323,
"grad_norm": 63.72947311401367,
"learning_rate": 0.00017125160677398626,
"loss": 255.5164,
"step": 1615
},
{
"epoch": 0.324,
"grad_norm": 64.98088073730469,
"learning_rate": 0.0001710062491057925,
"loss": 251.8339,
"step": 1620
},
{
"epoch": 0.325,
"grad_norm": 78.54566192626953,
"learning_rate": 0.00017076002624886154,
"loss": 248.8351,
"step": 1625
},
{
"epoch": 0.326,
"grad_norm": 76.1285629272461,
"learning_rate": 0.00017051294120334125,
"loss": 242.5996,
"step": 1630
},
{
"epoch": 0.327,
"grad_norm": 59.719017028808594,
"learning_rate": 0.00017026499697988493,
"loss": 249.7222,
"step": 1635
},
{
"epoch": 0.328,
"grad_norm": 68.43321990966797,
"learning_rate": 0.00017001619659961467,
"loss": 240.5313,
"step": 1640
},
{
"epoch": 0.329,
"grad_norm": 69.43534088134766,
"learning_rate": 0.00016976654309408464,
"loss": 227.6783,
"step": 1645
},
{
"epoch": 0.33,
"grad_norm": 91.16776275634766,
"learning_rate": 0.000169516039505244,
"loss": 246.3205,
"step": 1650
},
{
"epoch": 0.331,
"grad_norm": 76.1478500366211,
"learning_rate": 0.0001692646888853999,
"loss": 252.1556,
"step": 1655
},
{
"epoch": 0.332,
"grad_norm": 136.00778198242188,
"learning_rate": 0.00016901249429718032,
"loss": 239.3608,
"step": 1660
},
{
"epoch": 0.333,
"grad_norm": 71.8016128540039,
"learning_rate": 0.00016875945881349676,
"loss": 240.7788,
"step": 1665
},
{
"epoch": 0.334,
"grad_norm": 66.53947448730469,
"learning_rate": 0.0001685055855175067,
"loss": 228.5486,
"step": 1670
},
{
"epoch": 0.335,
"grad_norm": 66.0619888305664,
"learning_rate": 0.0001682508775025762,
"loss": 259.8584,
"step": 1675
},
{
"epoch": 0.336,
"grad_norm": 66.97184753417969,
"learning_rate": 0.00016799533787224192,
"loss": 250.809,
"step": 1680
},
{
"epoch": 0.337,
"grad_norm": 64.1236801147461,
"learning_rate": 0.00016773896974017373,
"loss": 247.3749,
"step": 1685
},
{
"epoch": 0.338,
"grad_norm": 65.39366149902344,
"learning_rate": 0.00016748177623013638,
"loss": 237.2529,
"step": 1690
},
{
"epoch": 0.339,
"grad_norm": 65.25891876220703,
"learning_rate": 0.00016722376047595164,
"loss": 242.7048,
"step": 1695
},
{
"epoch": 0.34,
"grad_norm": 62.32688522338867,
"learning_rate": 0.00016696492562145996,
"loss": 246.5424,
"step": 1700
},
{
"epoch": 0.341,
"grad_norm": 62.54330825805664,
"learning_rate": 0.00016670527482048246,
"loss": 244.564,
"step": 1705
},
{
"epoch": 0.342,
"grad_norm": 69.17015838623047,
"learning_rate": 0.00016644481123678217,
"loss": 236.5604,
"step": 1710
},
{
"epoch": 0.343,
"grad_norm": 94.22887420654297,
"learning_rate": 0.00016618353804402568,
"loss": 231.0441,
"step": 1715
},
{
"epoch": 0.344,
"grad_norm": 69.00772857666016,
"learning_rate": 0.00016592145842574433,
"loss": 241.5581,
"step": 1720
},
{
"epoch": 0.345,
"grad_norm": 56.885257720947266,
"learning_rate": 0.00016565857557529566,
"loss": 259.9843,
"step": 1725
},
{
"epoch": 0.346,
"grad_norm": 55.5030632019043,
"learning_rate": 0.00016539489269582416,
"loss": 252.2137,
"step": 1730
},
{
"epoch": 0.347,
"grad_norm": 68.91424560546875,
"learning_rate": 0.00016513041300022255,
"loss": 245.8943,
"step": 1735
},
{
"epoch": 0.348,
"grad_norm": 70.65258026123047,
"learning_rate": 0.00016486513971109243,
"loss": 255.4661,
"step": 1740
},
{
"epoch": 0.349,
"grad_norm": 58.84693908691406,
"learning_rate": 0.0001645990760607051,
"loss": 237.8968,
"step": 1745
},
{
"epoch": 0.35,
"grad_norm": 64.97807312011719,
"learning_rate": 0.0001643322252909622,
"loss": 251.2854,
"step": 1750
},
{
"epoch": 0.351,
"grad_norm": 62.77329635620117,
"learning_rate": 0.00016406459065335615,
"loss": 230.4382,
"step": 1755
},
{
"epoch": 0.352,
"grad_norm": 64.9175033569336,
"learning_rate": 0.00016379617540893056,
"loss": 233.1863,
"step": 1760
},
{
"epoch": 0.353,
"grad_norm": 61.643211364746094,
"learning_rate": 0.00016352698282824044,
"loss": 238.2037,
"step": 1765
},
{
"epoch": 0.354,
"grad_norm": 63.59113311767578,
"learning_rate": 0.00016325701619131246,
"loss": 244.5164,
"step": 1770
},
{
"epoch": 0.355,
"grad_norm": 58.9718017578125,
"learning_rate": 0.00016298627878760487,
"loss": 234.3176,
"step": 1775
},
{
"epoch": 0.356,
"grad_norm": 61.498809814453125,
"learning_rate": 0.00016271477391596753,
"loss": 251.9608,
"step": 1780
},
{
"epoch": 0.357,
"grad_norm": 61.9296989440918,
"learning_rate": 0.00016244250488460158,
"loss": 249.1438,
"step": 1785
},
{
"epoch": 0.358,
"grad_norm": 73.51992797851562,
"learning_rate": 0.0001621694750110193,
"loss": 246.7759,
"step": 1790
},
{
"epoch": 0.359,
"grad_norm": 59.58364486694336,
"learning_rate": 0.00016189568762200348,
"loss": 237.6455,
"step": 1795
},
{
"epoch": 0.36,
"grad_norm": 139.42498779296875,
"learning_rate": 0.00016162114605356703,
"loss": 240.8839,
"step": 1800
},
{
"epoch": 0.361,
"grad_norm": 61.32443618774414,
"learning_rate": 0.00016134585365091243,
"loss": 240.3019,
"step": 1805
},
{
"epoch": 0.362,
"grad_norm": 66.80059051513672,
"learning_rate": 0.00016106981376839066,
"loss": 235.7607,
"step": 1810
},
{
"epoch": 0.363,
"grad_norm": 96.10183715820312,
"learning_rate": 0.00016079302976946055,
"loss": 241.8637,
"step": 1815
},
{
"epoch": 0.364,
"grad_norm": 174.83294677734375,
"learning_rate": 0.0001605155050266478,
"loss": 235.3204,
"step": 1820
},
{
"epoch": 0.365,
"grad_norm": 83.66526794433594,
"learning_rate": 0.00016023724292150385,
"loss": 239.0025,
"step": 1825
},
{
"epoch": 0.366,
"grad_norm": 62.8675651550293,
"learning_rate": 0.00015995824684456465,
"loss": 241.9004,
"step": 1830
},
{
"epoch": 0.367,
"grad_norm": 57.88111877441406,
"learning_rate": 0.00015967852019530926,
"loss": 250.5243,
"step": 1835
},
{
"epoch": 0.368,
"grad_norm": 60.821659088134766,
"learning_rate": 0.0001593980663821187,
"loss": 238.8469,
"step": 1840
},
{
"epoch": 0.369,
"grad_norm": 60.44630813598633,
"learning_rate": 0.0001591168888222342,
"loss": 244.9853,
"step": 1845
},
{
"epoch": 0.37,
"grad_norm": 68.4105224609375,
"learning_rate": 0.00015883499094171554,
"loss": 260.3014,
"step": 1850
},
{
"epoch": 0.371,
"grad_norm": 64.6832275390625,
"learning_rate": 0.0001585523761753994,
"loss": 239.2754,
"step": 1855
},
{
"epoch": 0.372,
"grad_norm": 58.168155670166016,
"learning_rate": 0.00015826904796685762,
"loss": 248.5865,
"step": 1860
},
{
"epoch": 0.373,
"grad_norm": 83.49576568603516,
"learning_rate": 0.00015798500976835493,
"loss": 255.9171,
"step": 1865
},
{
"epoch": 0.374,
"grad_norm": 101.22307586669922,
"learning_rate": 0.00015770026504080718,
"loss": 248.0609,
"step": 1870
},
{
"epoch": 0.375,
"grad_norm": 68.59806060791016,
"learning_rate": 0.000157414817253739,
"loss": 236.3886,
"step": 1875
},
{
"epoch": 0.376,
"grad_norm": 71.27215576171875,
"learning_rate": 0.00015712866988524155,
"loss": 247.2733,
"step": 1880
},
{
"epoch": 0.377,
"grad_norm": 65.266357421875,
"learning_rate": 0.0001568418264219303,
"loss": 236.9641,
"step": 1885
},
{
"epoch": 0.378,
"grad_norm": 59.90776824951172,
"learning_rate": 0.0001565542903589023,
"loss": 215.6263,
"step": 1890
},
{
"epoch": 0.379,
"grad_norm": 61.711795806884766,
"learning_rate": 0.0001562660651996937,
"loss": 249.6925,
"step": 1895
},
{
"epoch": 0.38,
"grad_norm": 57.719783782958984,
"learning_rate": 0.00015597715445623712,
"loss": 241.6331,
"step": 1900
},
{
"epoch": 0.381,
"grad_norm": 60.528297424316406,
"learning_rate": 0.00015568756164881882,
"loss": 237.7176,
"step": 1905
},
{
"epoch": 0.382,
"grad_norm": 69.33570098876953,
"learning_rate": 0.00015539729030603574,
"loss": 235.1876,
"step": 1910
},
{
"epoch": 0.383,
"grad_norm": 64.02123260498047,
"learning_rate": 0.0001551063439647526,
"loss": 234.8362,
"step": 1915
},
{
"epoch": 0.384,
"grad_norm": 57.75348663330078,
"learning_rate": 0.00015481472617005876,
"loss": 236.5208,
"step": 1920
},
{
"epoch": 0.385,
"grad_norm": 53.08407974243164,
"learning_rate": 0.00015452244047522502,
"loss": 233.4317,
"step": 1925
},
{
"epoch": 0.386,
"grad_norm": 73.68172454833984,
"learning_rate": 0.0001542294904416603,
"loss": 238.0298,
"step": 1930
},
{
"epoch": 0.387,
"grad_norm": 57.79017639160156,
"learning_rate": 0.00015393587963886835,
"loss": 230.5418,
"step": 1935
},
{
"epoch": 0.388,
"grad_norm": 65.8370590209961,
"learning_rate": 0.0001536416116444041,
"loss": 247.8104,
"step": 1940
},
{
"epoch": 0.389,
"grad_norm": 67.43762969970703,
"learning_rate": 0.0001533466900438303,
"loss": 258.8561,
"step": 1945
},
{
"epoch": 0.39,
"grad_norm": 57.806129455566406,
"learning_rate": 0.0001530511184306734,
"loss": 254.9089,
"step": 1950
},
{
"epoch": 0.391,
"grad_norm": 69.66842651367188,
"learning_rate": 0.00015275490040638038,
"loss": 248.4691,
"step": 1955
},
{
"epoch": 0.392,
"grad_norm": 84.50879669189453,
"learning_rate": 0.00015245803958027434,
"loss": 237.1378,
"step": 1960
},
{
"epoch": 0.393,
"grad_norm": 65.10584259033203,
"learning_rate": 0.0001521605395695108,
"loss": 242.4159,
"step": 1965
},
{
"epoch": 0.394,
"grad_norm": 66.4300537109375,
"learning_rate": 0.00015186240399903342,
"loss": 245.825,
"step": 1970
},
{
"epoch": 0.395,
"grad_norm": 109.91886901855469,
"learning_rate": 0.00015156363650153012,
"loss": 250.4606,
"step": 1975
},
{
"epoch": 0.396,
"grad_norm": 72.5931396484375,
"learning_rate": 0.0001512642407173885,
"loss": 248.6551,
"step": 1980
},
{
"epoch": 0.397,
"grad_norm": 73.90507507324219,
"learning_rate": 0.00015096422029465178,
"loss": 244.256,
"step": 1985
},
{
"epoch": 0.398,
"grad_norm": 65.20423126220703,
"learning_rate": 0.0001506635788889741,
"loss": 220.3735,
"step": 1990
},
{
"epoch": 0.399,
"grad_norm": 71.23815155029297,
"learning_rate": 0.0001503623201635761,
"loss": 247.7928,
"step": 1995
},
{
"epoch": 0.4,
"grad_norm": 76.0530014038086,
"learning_rate": 0.0001500604477892003,
"loss": 245.9678,
"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": 9.6711053672448e+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": 133.26564025878906,
"learning_rate": 1.6000000000000001e-06,
"loss": 319.5714,
"step": 5
},
{
"epoch": 0.002,
"grad_norm": 116.60221099853516,
"learning_rate": 3.6e-06,
"loss": 321.6409,
"step": 10
},
{
"epoch": 0.003,
"grad_norm": 99.86441040039062,
"learning_rate": 5.600000000000001e-06,
"loss": 321.4713,
"step": 15
},
{
"epoch": 0.004,
"grad_norm": 120.4101333618164,
"learning_rate": 7.6e-06,
"loss": 326.6742,
"step": 20
},
{
"epoch": 0.005,
"grad_norm": 131.2949676513672,
"learning_rate": 9.600000000000001e-06,
"loss": 325.8993,
"step": 25
},
{
"epoch": 0.006,
"grad_norm": 109.72811889648438,
"learning_rate": 1.16e-05,
"loss": 313.0747,
"step": 30
},
{
"epoch": 0.007,
"grad_norm": 93.34612274169922,
"learning_rate": 1.3600000000000002e-05,
"loss": 315.1154,
"step": 35
},
{
"epoch": 0.008,
"grad_norm": 89.763427734375,
"learning_rate": 1.56e-05,
"loss": 307.5251,
"step": 40
},
{
"epoch": 0.009,
"grad_norm": 79.69110870361328,
"learning_rate": 1.76e-05,
"loss": 310.1657,
"step": 45
},
{
"epoch": 0.01,
"grad_norm": 83.45806121826172,
"learning_rate": 1.9600000000000002e-05,
"loss": 322.3456,
"step": 50
},
{
"epoch": 0.011,
"grad_norm": 83.1032943725586,
"learning_rate": 2.16e-05,
"loss": 307.5482,
"step": 55
},
{
"epoch": 0.012,
"grad_norm": 100.54994201660156,
"learning_rate": 2.36e-05,
"loss": 308.4983,
"step": 60
},
{
"epoch": 0.013,
"grad_norm": 74.47264099121094,
"learning_rate": 2.5600000000000002e-05,
"loss": 313.1681,