{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 5000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.001,
"grad_norm": 5279.1005859375,
"learning_rate": 1.6000000000000001e-06,
"loss": 3210.6535,
"step": 5
},
{
"epoch": 0.002,
"grad_norm": 4751.84619140625,
"learning_rate": 3.6e-06,
"loss": 3126.2795,
"step": 10
},
{
"epoch": 0.003,
"grad_norm": 4194.10107421875,
"learning_rate": 5.600000000000001e-06,
"loss": 2981.9664,
"step": 15
},
{
"epoch": 0.004,
"grad_norm": 3518.244384765625,
"learning_rate": 7.6e-06,
"loss": 2782.1281,
"step": 20
},
{
"epoch": 0.005,
"grad_norm": 2281.134521484375,
"learning_rate": 9.600000000000001e-06,
"loss": 2620.7445,
"step": 25
},
{
"epoch": 0.006,
"grad_norm": 1110.303955078125,
"learning_rate": 1.16e-05,
"loss": 2435.4023,
"step": 30
},
{
"epoch": 0.007,
"grad_norm": 1619.8824462890625,
"learning_rate": 1.3600000000000002e-05,
"loss": 2396.1436,
"step": 35
},
{
"epoch": 0.008,
"grad_norm": 824.91162109375,
"learning_rate": 1.56e-05,
"loss": 2325.2439,
"step": 40
},
{
"epoch": 0.009,
"grad_norm": 889.560791015625,
"learning_rate": 1.76e-05,
"loss": 2262.3674,
"step": 45
},
{
"epoch": 0.01,
"grad_norm": 657.9000244140625,
"learning_rate": 1.9600000000000002e-05,
"loss": 2183.2623,
"step": 50
},
{
"epoch": 0.011,
"grad_norm": 652.0450439453125,
"learning_rate": 2.16e-05,
"loss": 2123.1746,
"step": 55
},
{
"epoch": 0.012,
"grad_norm": 605.9557495117188,
"learning_rate": 2.36e-05,
"loss": 2036.5979,
"step": 60
},
{
"epoch": 0.013,
"grad_norm": 557.3351440429688,
"learning_rate": 2.5600000000000002e-05,
"loss": 1961.0652,
"step": 65
},
{
"epoch": 0.014,
"grad_norm": 570.44873046875,
"learning_rate": 2.7600000000000003e-05,
"loss": 1923.0066,
"step": 70
},
{
"epoch": 0.015,
"grad_norm": 529.5690307617188,
"learning_rate": 2.96e-05,
"loss": 1940.8385,
"step": 75
},
{
"epoch": 0.016,
"grad_norm": 542.8247680664062,
"learning_rate": 3.16e-05,
"loss": 1868.4064,
"step": 80
},
{
"epoch": 0.017,
"grad_norm": 706.8983764648438,
"learning_rate": 3.3600000000000004e-05,
"loss": 1819.3414,
"step": 85
},
{
"epoch": 0.018,
"grad_norm": 800.0804443359375,
"learning_rate": 3.56e-05,
"loss": 1856.9164,
"step": 90
},
{
"epoch": 0.019,
"grad_norm": 402.6047668457031,
"learning_rate": 3.76e-05,
"loss": 1838.3961,
"step": 95
},
{
"epoch": 0.02,
"grad_norm": 535.2955932617188,
"learning_rate": 3.960000000000001e-05,
"loss": 1827.7572,
"step": 100
},
{
"epoch": 0.021,
"grad_norm": 576.1724243164062,
"learning_rate": 4.16e-05,
"loss": 1838.207,
"step": 105
},
{
"epoch": 0.022,
"grad_norm": 433.5221252441406,
"learning_rate": 4.36e-05,
"loss": 1837.9793,
"step": 110
},
{
"epoch": 0.023,
"grad_norm": 857.6431274414062,
"learning_rate": 4.5600000000000004e-05,
"loss": 1774.8434,
"step": 115
},
{
"epoch": 0.024,
"grad_norm": 415.0038757324219,
"learning_rate": 4.76e-05,
"loss": 1800.1463,
"step": 120
},
{
"epoch": 0.025,
"grad_norm": 432.4924621582031,
"learning_rate": 4.96e-05,
"loss": 1781.6961,
"step": 125
},
{
"epoch": 0.026,
"grad_norm": 512.7321166992188,
"learning_rate": 5.16e-05,
"loss": 1762.8789,
"step": 130
},
{
"epoch": 0.027,
"grad_norm": 477.39263916015625,
"learning_rate": 5.360000000000001e-05,
"loss": 1779.642,
"step": 135
},
{
"epoch": 0.028,
"grad_norm": 726.4237060546875,
"learning_rate": 5.560000000000001e-05,
"loss": 1764.2844,
"step": 140
},
{
"epoch": 0.029,
"grad_norm": 391.7130126953125,
"learning_rate": 5.76e-05,
"loss": 1771.5162,
"step": 145
},
{
"epoch": 0.03,
"grad_norm": 808.0087890625,
"learning_rate": 5.96e-05,
"loss": 1721.3072,
"step": 150
},
{
"epoch": 0.031,
"grad_norm": 547.3645629882812,
"learning_rate": 6.16e-05,
"loss": 1769.6092,
"step": 155
},
{
"epoch": 0.032,
"grad_norm": 909.0582275390625,
"learning_rate": 6.36e-05,
"loss": 1720.5717,
"step": 160
},
{
"epoch": 0.033,
"grad_norm": 815.1519775390625,
"learning_rate": 6.560000000000001e-05,
"loss": 1701.3572,
"step": 165
},
{
"epoch": 0.034,
"grad_norm": 923.1791381835938,
"learning_rate": 6.76e-05,
"loss": 1770.9336,
"step": 170
},
{
"epoch": 0.035,
"grad_norm": 424.7173767089844,
"learning_rate": 6.96e-05,
"loss": 1711.7115,
"step": 175
},
{
"epoch": 0.036,
"grad_norm": 652.283203125,
"learning_rate": 7.16e-05,
"loss": 1700.1742,
"step": 180
},
{
"epoch": 0.037,
"grad_norm": 569.8483276367188,
"learning_rate": 7.36e-05,
"loss": 1666.6309,
"step": 185
},
{
"epoch": 0.038,
"grad_norm": 826.189208984375,
"learning_rate": 7.560000000000001e-05,
"loss": 1666.5139,
"step": 190
},
{
"epoch": 0.039,
"grad_norm": 474.16363525390625,
"learning_rate": 7.76e-05,
"loss": 1650.0004,
"step": 195
},
{
"epoch": 0.04,
"grad_norm": 716.5734252929688,
"learning_rate": 7.960000000000001e-05,
"loss": 1572.1999,
"step": 200
},
{
"epoch": 0.041,
"grad_norm": 1321.4967041015625,
"learning_rate": 8.16e-05,
"loss": 1667.61,
"step": 205
},
{
"epoch": 0.042,
"grad_norm": 479.0678405761719,
"learning_rate": 8.36e-05,
"loss": 1641.3117,
"step": 210
},
{
"epoch": 0.043,
"grad_norm": 715.5798950195312,
"learning_rate": 8.560000000000001e-05,
"loss": 1624.0439,
"step": 215
},
{
"epoch": 0.044,
"grad_norm": 583.0526733398438,
"learning_rate": 8.76e-05,
"loss": 1658.2168,
"step": 220
},
{
"epoch": 0.045,
"grad_norm": 366.9625244140625,
"learning_rate": 8.960000000000001e-05,
"loss": 1604.8625,
"step": 225
},
{
"epoch": 0.046,
"grad_norm": 1079.0693359375,
"learning_rate": 9.16e-05,
"loss": 1610.7824,
"step": 230
},
{
"epoch": 0.047,
"grad_norm": 737.6953735351562,
"learning_rate": 9.360000000000001e-05,
"loss": 1605.8225,
"step": 235
},
{
"epoch": 0.048,
"grad_norm": 451.6602783203125,
"learning_rate": 9.56e-05,
"loss": 1604.6052,
"step": 240
},
{
"epoch": 0.049,
"grad_norm": 763.68505859375,
"learning_rate": 9.76e-05,
"loss": 1583.8987,
"step": 245
},
{
"epoch": 0.05,
"grad_norm": 713.450439453125,
"learning_rate": 9.960000000000001e-05,
"loss": 1598.5522,
"step": 250
},
{
"epoch": 0.051,
"grad_norm": 467.6012268066406,
"learning_rate": 0.0001016,
"loss": 1565.6337,
"step": 255
},
{
"epoch": 0.052,
"grad_norm": 486.3853759765625,
"learning_rate": 0.00010360000000000001,
"loss": 1577.1315,
"step": 260
},
{
"epoch": 0.053,
"grad_norm": 662.0369873046875,
"learning_rate": 0.0001056,
"loss": 1550.7387,
"step": 265
},
{
"epoch": 0.054,
"grad_norm": 753.3311767578125,
"learning_rate": 0.00010760000000000001,
"loss": 1513.7543,
"step": 270
},
{
"epoch": 0.055,
"grad_norm": 831.4561767578125,
"learning_rate": 0.00010960000000000001,
"loss": 1621.0024,
"step": 275
},
{
"epoch": 0.056,
"grad_norm": 1020.1363525390625,
"learning_rate": 0.00011160000000000002,
"loss": 1584.073,
"step": 280
},
{
"epoch": 0.057,
"grad_norm": 472.983154296875,
"learning_rate": 0.0001136,
"loss": 1580.8228,
"step": 285
},
{
"epoch": 0.058,
"grad_norm": 454.7581481933594,
"learning_rate": 0.00011559999999999999,
"loss": 1529.904,
"step": 290
},
{
"epoch": 0.059,
"grad_norm": 456.33734130859375,
"learning_rate": 0.0001176,
"loss": 1519.7635,
"step": 295
},
{
"epoch": 0.06,
"grad_norm": 422.54931640625,
"learning_rate": 0.00011960000000000001,
"loss": 1533.8492,
"step": 300
},
{
"epoch": 0.061,
"grad_norm": 778.0752563476562,
"learning_rate": 0.0001216,
"loss": 1495.4712,
"step": 305
},
{
"epoch": 0.062,
"grad_norm": 577.61865234375,
"learning_rate": 0.0001236,
"loss": 1585.0244,
"step": 310
},
{
"epoch": 0.063,
"grad_norm": 569.7201538085938,
"learning_rate": 0.00012560000000000002,
"loss": 1463.8175,
"step": 315
},
{
"epoch": 0.064,
"grad_norm": 631.9131469726562,
"learning_rate": 0.0001276,
"loss": 1442.0031,
"step": 320
},
{
"epoch": 0.065,
"grad_norm": 614.9479370117188,
"learning_rate": 0.0001296,
"loss": 1492.2247,
"step": 325
},
{
"epoch": 0.066,
"grad_norm": 439.1335144042969,
"learning_rate": 0.0001316,
"loss": 1510.2441,
"step": 330
},
{
"epoch": 0.067,
"grad_norm": 458.37249755859375,
"learning_rate": 0.00013360000000000002,
"loss": 1498.3837,
"step": 335
},
{
"epoch": 0.068,
"grad_norm": 427.5429382324219,
"learning_rate": 0.00013560000000000002,
"loss": 1523.6253,
"step": 340
},
{
"epoch": 0.069,
"grad_norm": 369.1468505859375,
"learning_rate": 0.00013759999999999998,
"loss": 1472.8765,
"step": 345
},
{
"epoch": 0.07,
"grad_norm": 805.6857299804688,
"learning_rate": 0.0001396,
"loss": 1473.3191,
"step": 350
},
{
"epoch": 0.071,
"grad_norm": 566.1781005859375,
"learning_rate": 0.0001416,
"loss": 1465.6092,
"step": 355
},
{
"epoch": 0.072,
"grad_norm": 1000.330322265625,
"learning_rate": 0.0001436,
"loss": 1447.2715,
"step": 360
},
{
"epoch": 0.073,
"grad_norm": 561.0407104492188,
"learning_rate": 0.00014560000000000002,
"loss": 1441.1647,
"step": 365
},
{
"epoch": 0.074,
"grad_norm": 642.50537109375,
"learning_rate": 0.0001476,
"loss": 1471.09,
"step": 370
},
{
"epoch": 0.075,
"grad_norm": 706.0594482421875,
"learning_rate": 0.0001496,
"loss": 1465.2126,
"step": 375
},
{
"epoch": 0.076,
"grad_norm": 611.6338500976562,
"learning_rate": 0.0001516,
"loss": 1452.6277,
"step": 380
},
{
"epoch": 0.077,
"grad_norm": 643.2686157226562,
"learning_rate": 0.00015360000000000002,
"loss": 1387.1741,
"step": 385
},
{
"epoch": 0.078,
"grad_norm": 414.7914123535156,
"learning_rate": 0.00015560000000000001,
"loss": 1397.9867,
"step": 390
},
{
"epoch": 0.079,
"grad_norm": 547.7757568359375,
"learning_rate": 0.0001576,
"loss": 1405.0514,
"step": 395
},
{
"epoch": 0.08,
"grad_norm": 440.1595458984375,
"learning_rate": 0.0001596,
"loss": 1458.3197,
"step": 400
},
{
"epoch": 0.081,
"grad_norm": 789.4036254882812,
"learning_rate": 0.00016160000000000002,
"loss": 1385.2363,
"step": 405
},
{
"epoch": 0.082,
"grad_norm": 477.3360290527344,
"learning_rate": 0.0001636,
"loss": 1463.8484,
"step": 410
},
{
"epoch": 0.083,
"grad_norm": 435.5836486816406,
"learning_rate": 0.0001656,
"loss": 1424.6798,
"step": 415
},
{
"epoch": 0.084,
"grad_norm": 605.2042846679688,
"learning_rate": 0.0001676,
"loss": 1445.6187,
"step": 420
},
{
"epoch": 0.085,
"grad_norm": 593.394287109375,
"learning_rate": 0.0001696,
"loss": 1429.8978,
"step": 425
},
{
"epoch": 0.086,
"grad_norm": 473.7935485839844,
"learning_rate": 0.0001716,
"loss": 1402.8562,
"step": 430
},
{
"epoch": 0.087,
"grad_norm": 417.0579528808594,
"learning_rate": 0.00017360000000000002,
"loss": 1432.4508,
"step": 435
},
{
"epoch": 0.088,
"grad_norm": 559.179443359375,
"learning_rate": 0.0001756,
"loss": 1474.8091,
"step": 440
},
{
"epoch": 0.089,
"grad_norm": 393.73291015625,
"learning_rate": 0.0001776,
"loss": 1447.1372,
"step": 445
},
{
"epoch": 0.09,
"grad_norm": 380.47845458984375,
"learning_rate": 0.0001796,
"loss": 1378.4016,
"step": 450
},
{
"epoch": 0.091,
"grad_norm": 461.0595397949219,
"learning_rate": 0.00018160000000000002,
"loss": 1412.4626,
"step": 455
},
{
"epoch": 0.092,
"grad_norm": 881.6057739257812,
"learning_rate": 0.00018360000000000002,
"loss": 1414.6184,
"step": 460
},
{
"epoch": 0.093,
"grad_norm": 333.7018737792969,
"learning_rate": 0.0001856,
"loss": 1326.6567,
"step": 465
},
{
"epoch": 0.094,
"grad_norm": 337.50262451171875,
"learning_rate": 0.0001876,
"loss": 1333.9395,
"step": 470
},
{
"epoch": 0.095,
"grad_norm": 447.1881408691406,
"learning_rate": 0.0001896,
"loss": 1375.5714,
"step": 475
},
{
"epoch": 0.096,
"grad_norm": 399.9327087402344,
"learning_rate": 0.0001916,
"loss": 1414.6846,
"step": 480
},
{
"epoch": 0.097,
"grad_norm": 349.3825988769531,
"learning_rate": 0.00019360000000000002,
"loss": 1335.5482,
"step": 485
},
{
"epoch": 0.098,
"grad_norm": 301.9490966796875,
"learning_rate": 0.0001956,
"loss": 1368.7355,
"step": 490
},
{
"epoch": 0.099,
"grad_norm": 343.9149169921875,
"learning_rate": 0.0001976,
"loss": 1376.4213,
"step": 495
},
{
"epoch": 0.1,
"grad_norm": 324.8498229980469,
"learning_rate": 0.0001996,
"loss": 1339.0545,
"step": 500
},
{
"epoch": 0.101,
"grad_norm": 517.1563720703125,
"learning_rate": 0.00019999961008995606,
"loss": 1375.8162,
"step": 505
},
{
"epoch": 0.102,
"grad_norm": 524.5974731445312,
"learning_rate": 0.0001999980260856137,
"loss": 1353.98,
"step": 510
},
{
"epoch": 0.103,
"grad_norm": 463.5816650390625,
"learning_rate": 0.000199995223636881,
"loss": 1405.0982,
"step": 515
},
{
"epoch": 0.104,
"grad_norm": 369.2015380859375,
"learning_rate": 0.00019999120277790477,
"loss": 1430.9626,
"step": 520
},
{
"epoch": 0.105,
"grad_norm": 1079.3238525390625,
"learning_rate": 0.00019998596355767805,
"loss": 1373.4903,
"step": 525
},
{
"epoch": 0.106,
"grad_norm": 459.20843505859375,
"learning_rate": 0.000199979506040039,
"loss": 1416.4962,
"step": 530
},
{
"epoch": 0.107,
"grad_norm": 446.02471923828125,
"learning_rate": 0.00019997183030367048,
"loss": 1322.7586,
"step": 535
},
{
"epoch": 0.108,
"grad_norm": 343.701171875,
"learning_rate": 0.00019996293644209887,
"loss": 1380.243,
"step": 540
},
{
"epoch": 0.109,
"grad_norm": 315.7219543457031,
"learning_rate": 0.0001999528245636931,
"loss": 1326.5701,
"step": 545
},
{
"epoch": 0.11,
"grad_norm": 580.9896240234375,
"learning_rate": 0.00019994149479166324,
"loss": 1309.9417,
"step": 550
},
{
"epoch": 0.111,
"grad_norm": 625.849609375,
"learning_rate": 0.00019992894726405893,
"loss": 1263.2275,
"step": 555
},
{
"epoch": 0.112,
"grad_norm": 474.86370849609375,
"learning_rate": 0.00019991518213376787,
"loss": 1356.6371,
"step": 560
},
{
"epoch": 0.113,
"grad_norm": 873.8657836914062,
"learning_rate": 0.00019990019956851382,
"loss": 1396.7087,
"step": 565
},
{
"epoch": 0.114,
"grad_norm": 382.961181640625,
"learning_rate": 0.0001998839997508546,
"loss": 1341.2105,
"step": 570
},
{
"epoch": 0.115,
"grad_norm": 413.8773193359375,
"learning_rate": 0.00019986658287817987,
"loss": 1322.209,
"step": 575
},
{
"epoch": 0.116,
"grad_norm": 624.048583984375,
"learning_rate": 0.00019984794916270876,
"loss": 1365.1193,
"step": 580
},
{
"epoch": 0.117,
"grad_norm": 370.50494384765625,
"learning_rate": 0.00019982809883148722,
"loss": 1340.4451,
"step": 585
},
{
"epoch": 0.118,
"grad_norm": 463.27001953125,
"learning_rate": 0.00019980703212638522,
"loss": 1304.5833,
"step": 590
},
{
"epoch": 0.119,
"grad_norm": 544.818115234375,
"learning_rate": 0.00019978474930409395,
"loss": 1347.7661,
"step": 595
},
{
"epoch": 0.12,
"grad_norm": 590.6436767578125,
"learning_rate": 0.00019976125063612252,
"loss": 1344.3582,
"step": 600
},
{
"epoch": 0.121,
"grad_norm": 571.65966796875,
"learning_rate": 0.00019973653640879485,
"loss": 1319.1026,
"step": 605
},
{
"epoch": 0.122,
"grad_norm": 315.9857482910156,
"learning_rate": 0.00019971060692324598,
"loss": 1317.5977,
"step": 610
},
{
"epoch": 0.123,
"grad_norm": 773.9674682617188,
"learning_rate": 0.00019968346249541846,
"loss": 1330.3486,
"step": 615
},
{
"epoch": 0.124,
"grad_norm": 475.9002990722656,
"learning_rate": 0.00019965510345605866,
"loss": 1293.1561,
"step": 620
},
{
"epoch": 0.125,
"grad_norm": 744.0804443359375,
"learning_rate": 0.0001996255301507125,
"loss": 1315.8885,
"step": 625
},
{
"epoch": 0.126,
"grad_norm": 389.9852294921875,
"learning_rate": 0.00019959474293972129,
"loss": 1332.0041,
"step": 630
},
{
"epoch": 0.127,
"grad_norm": 501.2006530761719,
"learning_rate": 0.00019956274219821757,
"loss": 1285.9961,
"step": 635
},
{
"epoch": 0.128,
"grad_norm": 359.9734191894531,
"learning_rate": 0.00019952952831612026,
"loss": 1357.8221,
"step": 640
},
{
"epoch": 0.129,
"grad_norm": 380.00140380859375,
"learning_rate": 0.00019949510169813003,
"loss": 1263.589,
"step": 645
},
{
"epoch": 0.13,
"grad_norm": 318.3768310546875,
"learning_rate": 0.00019945946276372434,
"loss": 1304.5432,
"step": 650
},
{
"epoch": 0.131,
"grad_norm": 608.3934326171875,
"learning_rate": 0.00019942261194715236,
"loss": 1303.573,
"step": 655
},
{
"epoch": 0.132,
"grad_norm": 891.711181640625,
"learning_rate": 0.00019938454969742968,
"loss": 1322.6826,
"step": 660
},
{
"epoch": 0.133,
"grad_norm": 480.198974609375,
"learning_rate": 0.00019934527647833276,
"loss": 1283.3825,
"step": 665
},
{
"epoch": 0.134,
"grad_norm": 329.8459167480469,
"learning_rate": 0.00019930479276839344,
"loss": 1253.7623,
"step": 670
},
{
"epoch": 0.135,
"grad_norm": 247.00376892089844,
"learning_rate": 0.0001992630990608929,
"loss": 1266.8369,
"step": 675
},
{
"epoch": 0.136,
"grad_norm": 279.5446472167969,
"learning_rate": 0.00019922019586385585,
"loss": 1251.9748,
"step": 680
},
{
"epoch": 0.137,
"grad_norm": 317.87103271484375,
"learning_rate": 0.00019917608370004417,
"loss": 1227.311,
"step": 685
},
{
"epoch": 0.138,
"grad_norm": 1022.8506469726562,
"learning_rate": 0.00019913076310695068,
"loss": 1256.6351,
"step": 690
},
{
"epoch": 0.139,
"grad_norm": 469.2109069824219,
"learning_rate": 0.00019908423463679248,
"loss": 1369.1463,
"step": 695
},
{
"epoch": 0.14,
"grad_norm": 296.3825378417969,
"learning_rate": 0.0001990364988565043,
"loss": 1267.2126,
"step": 700
},
{
"epoch": 0.141,
"grad_norm": 349.3525695800781,
"learning_rate": 0.00019898755634773158,
"loss": 1289.4075,
"step": 705
},
{
"epoch": 0.142,
"grad_norm": 426.81402587890625,
"learning_rate": 0.00019893740770682335,
"loss": 1273.4889,
"step": 710
},
{
"epoch": 0.143,
"grad_norm": 389.8935852050781,
"learning_rate": 0.0001988860535448249,
"loss": 1226.6154,
"step": 715
},
{
"epoch": 0.144,
"grad_norm": 387.21484375,
"learning_rate": 0.00019883349448747062,
"loss": 1274.4033,
"step": 720
},
{
"epoch": 0.145,
"grad_norm": 442.667236328125,
"learning_rate": 0.0001987797311751759,
"loss": 1254.2538,
"step": 725
},
{
"epoch": 0.146,
"grad_norm": 317.6593322753906,
"learning_rate": 0.00019872476426302982,
"loss": 1240.0318,
"step": 730
},
{
"epoch": 0.147,
"grad_norm": 398.1370544433594,
"learning_rate": 0.0001986685944207868,
"loss": 1238.7697,
"step": 735
},
{
"epoch": 0.148,
"grad_norm": 304.2446594238281,
"learning_rate": 0.0001986112223328587,
"loss": 1285.4811,
"step": 740
},
{
"epoch": 0.149,
"grad_norm": 267.77862548828125,
"learning_rate": 0.00019855264869830629,
"loss": 1221.9878,
"step": 745
},
{
"epoch": 0.15,
"grad_norm": 448.2115783691406,
"learning_rate": 0.00019849287423083078,
"loss": 1208.55,
"step": 750
},
{
"epoch": 0.151,
"grad_norm": 563.0258178710938,
"learning_rate": 0.00019843189965876526,
"loss": 1238.9744,
"step": 755
},
{
"epoch": 0.152,
"grad_norm": 425.2115478515625,
"learning_rate": 0.00019836972572506557,
"loss": 1249.8229,
"step": 760
},
{
"epoch": 0.153,
"grad_norm": 483.08074951171875,
"learning_rate": 0.00019830635318730154,
"loss": 1246.732,
"step": 765
},
{
"epoch": 0.154,
"grad_norm": 292.0141296386719,
"learning_rate": 0.00019824178281764753,
"loss": 1187.9144,
"step": 770
},
{
"epoch": 0.155,
"grad_norm": 238.01025390625,
"learning_rate": 0.00019817601540287306,
"loss": 1191.5611,
"step": 775
},
{
"epoch": 0.156,
"grad_norm": 668.0966186523438,
"learning_rate": 0.0001981090517443334,
"loss": 1245.8677,
"step": 780
},
{
"epoch": 0.157,
"grad_norm": 434.55908203125,
"learning_rate": 0.0001980408926579596,
"loss": 1218.2303,
"step": 785
},
{
"epoch": 0.158,
"grad_norm": 443.0311279296875,
"learning_rate": 0.00019797153897424852,
"loss": 1270.7037,
"step": 790
},
{
"epoch": 0.159,
"grad_norm": 404.80426025390625,
"learning_rate": 0.000197900991538253,
"loss": 1245.5184,
"step": 795
},
{
"epoch": 0.16,
"grad_norm": 267.117431640625,
"learning_rate": 0.00019782925120957124,
"loss": 1222.8238,
"step": 800
},
{
"epoch": 0.161,
"grad_norm": 256.2340087890625,
"learning_rate": 0.00019775631886233654,
"loss": 1209.5636,
"step": 805
},
{
"epoch": 0.162,
"grad_norm": 311.1485595703125,
"learning_rate": 0.0001976821953852065,
"loss": 1211.1638,
"step": 810
},
{
"epoch": 0.163,
"grad_norm": 414.6141052246094,
"learning_rate": 0.00019760688168135232,
"loss": 1196.4056,
"step": 815
},
{
"epoch": 0.164,
"grad_norm": 352.2662048339844,
"learning_rate": 0.00019753037866844771,
"loss": 1217.5161,
"step": 820
},
{
"epoch": 0.165,
"grad_norm": 296.0804138183594,
"learning_rate": 0.00019745268727865774,
"loss": 1177.1819,
"step": 825
},
{
"epoch": 0.166,
"grad_norm": 528.9044189453125,
"learning_rate": 0.00019737380845862745,
"loss": 1248.7508,
"step": 830
},
{
"epoch": 0.167,
"grad_norm": 434.4969177246094,
"learning_rate": 0.0001972937431694704,
"loss": 1221.8674,
"step": 835
},
{
"epoch": 0.168,
"grad_norm": 345.0392761230469,
"learning_rate": 0.00019721249238675688,
"loss": 1205.7365,
"step": 840
},
{
"epoch": 0.169,
"grad_norm": 335.431884765625,
"learning_rate": 0.000197130057100502,
"loss": 1218.818,
"step": 845
},
{
"epoch": 0.17,
"grad_norm": 281.2326354980469,
"learning_rate": 0.00019704643831515374,
"loss": 1206.6269,
"step": 850
},
{
"epoch": 0.171,
"grad_norm": 373.72149658203125,
"learning_rate": 0.0001969616370495806,
"loss": 1236.0043,
"step": 855
},
{
"epoch": 0.172,
"grad_norm": 350.7597351074219,
"learning_rate": 0.00019687565433705926,
"loss": 1226.9392,
"step": 860
},
{
"epoch": 0.173,
"grad_norm": 316.2974548339844,
"learning_rate": 0.00019678849122526187,
"loss": 1167.641,
"step": 865
},
{
"epoch": 0.174,
"grad_norm": 266.1842041015625,
"learning_rate": 0.00019670014877624353,
"loss": 1137.0365,
"step": 870
},
{
"epoch": 0.175,
"grad_norm": 410.3638916015625,
"learning_rate": 0.00019661062806642903,
"loss": 1132.2924,
"step": 875
},
{
"epoch": 0.176,
"grad_norm": 337.53228759765625,
"learning_rate": 0.0001965199301866,
"loss": 1137.4544,
"step": 880
},
{
"epoch": 0.177,
"grad_norm": 261.6104431152344,
"learning_rate": 0.00019642805624188147,
"loss": 1140.9485,
"step": 885
},
{
"epoch": 0.178,
"grad_norm": 237.55018615722656,
"learning_rate": 0.0001963350073517285,
"loss": 1114.7934,
"step": 890
},
{
"epoch": 0.179,
"grad_norm": 293.7763671875,
"learning_rate": 0.0001962407846499124,
"loss": 1099.5645,
"step": 895
},
{
"epoch": 0.18,
"grad_norm": 406.61175537109375,
"learning_rate": 0.0001961453892845071,
"loss": 1108.5495,
"step": 900
},
{
"epoch": 0.181,
"grad_norm": 292.4315490722656,
"learning_rate": 0.00019604882241787498,
"loss": 1119.4605,
"step": 905
},
{
"epoch": 0.182,
"grad_norm": 283.885986328125,
"learning_rate": 0.0001959510852266529,
"loss": 1160.0693,
"step": 910
},
{
"epoch": 0.183,
"grad_norm": 356.6379089355469,
"learning_rate": 0.0001958521789017376,
"loss": 1193.7137,
"step": 915
},
{
"epoch": 0.184,
"grad_norm": 369.1276550292969,
"learning_rate": 0.00019575210464827149,
"loss": 1214.0327,
"step": 920
},
{
"epoch": 0.185,
"grad_norm": 295.2629699707031,
"learning_rate": 0.0001956508636856278,
"loss": 1202.7064,
"step": 925
},
{
"epoch": 0.186,
"grad_norm": 348.49444580078125,
"learning_rate": 0.00019554845724739566,
"loss": 1158.0232,
"step": 930
},
{
"epoch": 0.187,
"grad_norm": 315.1863708496094,
"learning_rate": 0.00019544488658136523,
"loss": 1172.8901,
"step": 935
},
{
"epoch": 0.188,
"grad_norm": 337.43560791015625,
"learning_rate": 0.00019534015294951233,
"loss": 1181.8953,
"step": 940
},
{
"epoch": 0.189,
"grad_norm": 681.9550170898438,
"learning_rate": 0.00019523425762798329,
"loss": 1190.3125,
"step": 945
},
{
"epoch": 0.19,
"grad_norm": 337.8601989746094,
"learning_rate": 0.00019512720190707913,
"loss": 1155.7871,
"step": 950
},
{
"epoch": 0.191,
"grad_norm": 376.707275390625,
"learning_rate": 0.00019501898709124008,
"loss": 1156.3426,
"step": 955
},
{
"epoch": 0.192,
"grad_norm": 374.6969909667969,
"learning_rate": 0.00019490961449902946,
"loss": 1153.0828,
"step": 960
},
{
"epoch": 0.193,
"grad_norm": 386.9150390625,
"learning_rate": 0.00019479908546311781,
"loss": 1163.4093,
"step": 965
},
{
"epoch": 0.194,
"grad_norm": 302.92474365234375,
"learning_rate": 0.0001946874013302666,
"loss": 1156.5795,
"step": 970
},
{
"epoch": 0.195,
"grad_norm": 516.5219116210938,
"learning_rate": 0.0001945745634613117,
"loss": 1193.0271,
"step": 975
},
{
"epoch": 0.196,
"grad_norm": 392.726318359375,
"learning_rate": 0.0001944605732311469,
"loss": 1157.3814,
"step": 980
},
{
"epoch": 0.197,
"grad_norm": 370.2920227050781,
"learning_rate": 0.00019434543202870725,
"loss": 1141.6649,
"step": 985
},
{
"epoch": 0.198,
"grad_norm": 332.8992004394531,
"learning_rate": 0.0001942291412569519,
"loss": 1174.0922,
"step": 990
},
{
"epoch": 0.199,
"grad_norm": 445.66864013671875,
"learning_rate": 0.00019411170233284727,
"loss": 1155.4588,
"step": 995
},
{
"epoch": 0.2,
"grad_norm": 394.4620056152344,
"learning_rate": 0.00019399311668734956,
"loss": 1126.4762,
"step": 1000
},
{
"epoch": 0.201,
"grad_norm": 308.9654235839844,
"learning_rate": 0.00019387338576538744,
"loss": 1136.0583,
"step": 1005
},
{
"epoch": 0.202,
"grad_norm": 290.95111083984375,
"learning_rate": 0.0001937525110258444,
"loss": 1136.5879,
"step": 1010
},
{
"epoch": 0.203,
"grad_norm": 354.3265380859375,
"learning_rate": 0.00019363049394154094,
"loss": 1145.3823,
"step": 1015
},
{
"epoch": 0.204,
"grad_norm": 388.37091064453125,
"learning_rate": 0.00019350733599921683,
"loss": 1155.2858,
"step": 1020
},
{
"epoch": 0.205,
"grad_norm": 418.05419921875,
"learning_rate": 0.00019338303869951269,
"loss": 1164.1896,
"step": 1025
},
{
"epoch": 0.206,
"grad_norm": 395.9677734375,
"learning_rate": 0.00019325760355695188,
"loss": 1156.1377,
"step": 1030
},
{
"epoch": 0.207,
"grad_norm": 295.811767578125,
"learning_rate": 0.00019313103209992204,
"loss": 1119.7596,
"step": 1035
},
{
"epoch": 0.208,
"grad_norm": 255.29721069335938,
"learning_rate": 0.0001930033258706564,
"loss": 1078.1983,
"step": 1040
},
{
"epoch": 0.209,
"grad_norm": 390.21954345703125,
"learning_rate": 0.00019287448642521513,
"loss": 1178.4872,
"step": 1045
},
{
"epoch": 0.21,
"grad_norm": 347.9909973144531,
"learning_rate": 0.00019274451533346615,
"loss": 1115.2313,
"step": 1050
},
{
"epoch": 0.211,
"grad_norm": 270.4188232421875,
"learning_rate": 0.00019261341417906621,
"loss": 1160.1594,
"step": 1055
},
{
"epoch": 0.212,
"grad_norm": 311.42449951171875,
"learning_rate": 0.0001924811845594415,
"loss": 1154.8939,
"step": 1060
},
{
"epoch": 0.213,
"grad_norm": 238.2523956298828,
"learning_rate": 0.00019234782808576824,
"loss": 1152.2226,
"step": 1065
},
{
"epoch": 0.214,
"grad_norm": 252.1710662841797,
"learning_rate": 0.00019221334638295294,
"loss": 1106.5138,
"step": 1070
},
{
"epoch": 0.215,
"grad_norm": 322.7612609863281,
"learning_rate": 0.00019207774108961272,
"loss": 1122.1278,
"step": 1075
},
{
"epoch": 0.216,
"grad_norm": 275.38006591796875,
"learning_rate": 0.0001919410138580553,
"loss": 1092.5637,
"step": 1080
},
{
"epoch": 0.217,
"grad_norm": 318.4013366699219,
"learning_rate": 0.0001918031663542588,
"loss": 1102.9309,
"step": 1085
},
{
"epoch": 0.218,
"grad_norm": 361.15240478515625,
"learning_rate": 0.00019166420025785164,
"loss": 1099.2401,
"step": 1090
},
{
"epoch": 0.219,
"grad_norm": 241.16232299804688,
"learning_rate": 0.00019152411726209176,
"loss": 1170.1941,
"step": 1095
},
{
"epoch": 0.22,
"grad_norm": 293.14208984375,
"learning_rate": 0.0001913829190738463,
"loss": 1091.8026,
"step": 1100
},
{
"epoch": 0.221,
"grad_norm": 240.7340850830078,
"learning_rate": 0.00019124060741357063,
"loss": 1097.5338,
"step": 1105
},
{
"epoch": 0.222,
"grad_norm": 514.5634765625,
"learning_rate": 0.0001910971840152874,
"loss": 1123.3128,
"step": 1110
},
{
"epoch": 0.223,
"grad_norm": 382.4951477050781,
"learning_rate": 0.00019095265062656544,
"loss": 1125.1537,
"step": 1115
},
{
"epoch": 0.224,
"grad_norm": 316.4914855957031,
"learning_rate": 0.00019080700900849851,
"loss": 1099.5656,
"step": 1120
},
{
"epoch": 0.225,
"grad_norm": 347.562744140625,
"learning_rate": 0.00019066026093568378,
"loss": 1103.5249,
"step": 1125
},
{
"epoch": 0.226,
"grad_norm": 264.34869384765625,
"learning_rate": 0.00019051240819620014,
"loss": 1118.3627,
"step": 1130
},
{
"epoch": 0.227,
"grad_norm": 275.8172607421875,
"learning_rate": 0.00019036345259158667,
"loss": 1110.0829,
"step": 1135
},
{
"epoch": 0.228,
"grad_norm": 375.1338806152344,
"learning_rate": 0.00019021339593682028,
"loss": 1106.9834,
"step": 1140
},
{
"epoch": 0.229,
"grad_norm": 301.5670166015625,
"learning_rate": 0.00019006224006029406,
"loss": 1062.9903,
"step": 1145
},
{
"epoch": 0.23,
"grad_norm": 304.4010009765625,
"learning_rate": 0.00018990998680379456,
"loss": 1117.6716,
"step": 1150
},
{
"epoch": 0.231,
"grad_norm": 395.1850891113281,
"learning_rate": 0.00018975663802247976,
"loss": 1135.8948,
"step": 1155
},
{
"epoch": 0.232,
"grad_norm": 308.4639892578125,
"learning_rate": 0.0001896021955848561,
"loss": 1083.076,
"step": 1160
},
{
"epoch": 0.233,
"grad_norm": 348.316650390625,
"learning_rate": 0.000189446661372756,
"loss": 1122.0164,
"step": 1165
},
{
"epoch": 0.234,
"grad_norm": 362.7312316894531,
"learning_rate": 0.0001892900372813147,
"loss": 1085.0613,
"step": 1170
},
{
"epoch": 0.235,
"grad_norm": 345.4062194824219,
"learning_rate": 0.00018913232521894732,
"loss": 1085.9612,
"step": 1175
},
{
"epoch": 0.236,
"grad_norm": 305.6242980957031,
"learning_rate": 0.00018897352710732564,
"loss": 1112.0549,
"step": 1180
},
{
"epoch": 0.237,
"grad_norm": 371.4139404296875,
"learning_rate": 0.00018881364488135448,
"loss": 1086.8083,
"step": 1185
},
{
"epoch": 0.238,
"grad_norm": 289.5921936035156,
"learning_rate": 0.00018865268048914828,
"loss": 1097.945,
"step": 1190
},
{
"epoch": 0.239,
"grad_norm": 346.43414306640625,
"learning_rate": 0.00018849063589200743,
"loss": 1081.0989,
"step": 1195
},
{
"epoch": 0.24,
"grad_norm": 360.85723876953125,
"learning_rate": 0.00018832751306439418,
"loss": 1089.6159,
"step": 1200
},
{
"epoch": 0.241,
"grad_norm": 279.0270690917969,
"learning_rate": 0.0001881633139939087,
"loss": 1108.7314,
"step": 1205
},
{
"epoch": 0.242,
"grad_norm": 348.4635009765625,
"learning_rate": 0.00018799804068126485,
"loss": 1071.7959,
"step": 1210
},
{
"epoch": 0.243,
"grad_norm": 277.997802734375,
"learning_rate": 0.00018783169514026578,
"loss": 1079.1819,
"step": 1215
},
{
"epoch": 0.244,
"grad_norm": 266.844970703125,
"learning_rate": 0.00018766427939777945,
"loss": 1065.2688,
"step": 1220
},
{
"epoch": 0.245,
"grad_norm": 508.8526306152344,
"learning_rate": 0.0001874957954937138,
"loss": 1088.8113,
"step": 1225
},
{
"epoch": 0.246,
"grad_norm": 420.46612548828125,
"learning_rate": 0.00018732624548099204,
"loss": 1096.4578,
"step": 1230
},
{
"epoch": 0.247,
"grad_norm": 434.08978271484375,
"learning_rate": 0.00018715563142552758,
"loss": 1092.0316,
"step": 1235
},
{
"epoch": 0.248,
"grad_norm": 235.50537109375,
"learning_rate": 0.0001869839554061988,
"loss": 1066.4626,
"step": 1240
},
{
"epoch": 0.249,
"grad_norm": 283.41693115234375,
"learning_rate": 0.00018681121951482393,
"loss": 1090.9525,
"step": 1245
},
{
"epoch": 0.25,
"grad_norm": 264.1053161621094,
"learning_rate": 0.00018663742585613518,
"loss": 1093.0311,
"step": 1250
},
{
"epoch": 0.251,
"grad_norm": 214.70904541015625,
"learning_rate": 0.0001864625765477535,
"loss": 1072.7176,
"step": 1255
},
{
"epoch": 0.252,
"grad_norm": 217.8924102783203,
"learning_rate": 0.0001862866737201625,
"loss": 1048.6648,
"step": 1260
},
{
"epoch": 0.253,
"grad_norm": 263.89080810546875,
"learning_rate": 0.00018610971951668265,
"loss": 1067.4382,
"step": 1265
},
{
"epoch": 0.254,
"grad_norm": 223.5115203857422,
"learning_rate": 0.00018593171609344503,
"loss": 1070.1833,
"step": 1270
},
{
"epoch": 0.255,
"grad_norm": 269.32562255859375,
"learning_rate": 0.00018575266561936523,
"loss": 1049.3262,
"step": 1275
},
{
"epoch": 0.256,
"grad_norm": 244.06114196777344,
"learning_rate": 0.00018557257027611675,
"loss": 1039.5672,
"step": 1280
},
{
"epoch": 0.257,
"grad_norm": 306.768798828125,
"learning_rate": 0.0001853914322581045,
"loss": 1059.2945,
"step": 1285
},
{
"epoch": 0.258,
"grad_norm": 229.2854461669922,
"learning_rate": 0.0001852092537724381,
"loss": 1076.5884,
"step": 1290
},
{
"epoch": 0.259,
"grad_norm": 281.59857177734375,
"learning_rate": 0.00018502603703890488,
"loss": 1061.3541,
"step": 1295
},
{
"epoch": 0.26,
"grad_norm": 239.98216247558594,
"learning_rate": 0.0001848417842899429,
"loss": 1097.9248,
"step": 1300
},
{
"epoch": 0.261,
"grad_norm": 265.7215270996094,
"learning_rate": 0.0001846564977706138,
"loss": 1059.6121,
"step": 1305
},
{
"epoch": 0.262,
"grad_norm": 299.55902099609375,
"learning_rate": 0.00018447017973857532,
"loss": 1073.1376,
"step": 1310
},
{
"epoch": 0.263,
"grad_norm": 285.3116149902344,
"learning_rate": 0.0001842828324640539,
"loss": 1055.4644,
"step": 1315
},
{
"epoch": 0.264,
"grad_norm": 317.26446533203125,
"learning_rate": 0.00018409445822981693,
"loss": 1052.6249,
"step": 1320
},
{
"epoch": 0.265,
"grad_norm": 343.3573303222656,
"learning_rate": 0.000183905059331145,
"loss": 1053.0,
"step": 1325
},
{
"epoch": 0.266,
"grad_norm": 404.0450134277344,
"learning_rate": 0.000183714638075804,
"loss": 1043.6904,
"step": 1330
},
{
"epoch": 0.267,
"grad_norm": 543.4042358398438,
"learning_rate": 0.00018352319678401676,
"loss": 1065.9138,
"step": 1335
},
{
"epoch": 0.268,
"grad_norm": 285.4433898925781,
"learning_rate": 0.000183330737788435,
"loss": 1078.2165,
"step": 1340
},
{
"epoch": 0.269,
"grad_norm": 213.30618286132812,
"learning_rate": 0.00018313726343411086,
"loss": 1066.829,
"step": 1345
},
{
"epoch": 0.27,
"grad_norm": 235.436279296875,
"learning_rate": 0.00018294277607846832,
"loss": 1047.4146,
"step": 1350
},
{
"epoch": 0.271,
"grad_norm": 283.26531982421875,
"learning_rate": 0.00018274727809127438,
"loss": 1066.3693,
"step": 1355
},
{
"epoch": 0.272,
"grad_norm": 326.6208190917969,
"learning_rate": 0.00018255077185461038,
"loss": 1023.6049,
"step": 1360
},
{
"epoch": 0.273,
"grad_norm": 244.29141235351562,
"learning_rate": 0.00018235325976284275,
"loss": 1029.4432,
"step": 1365
},
{
"epoch": 0.274,
"grad_norm": 203.6373748779297,
"learning_rate": 0.00018215474422259402,
"loss": 986.6041,
"step": 1370
},
{
"epoch": 0.275,
"grad_norm": 305.4809875488281,
"learning_rate": 0.0001819552276527134,
"loss": 1009.8521,
"step": 1375
},
{
"epoch": 0.276,
"grad_norm": 256.42742919921875,
"learning_rate": 0.0001817547124842473,
"loss": 1053.44,
"step": 1380
},
{
"epoch": 0.277,
"grad_norm": 666.8038330078125,
"learning_rate": 0.00018155320116040982,
"loss": 1077.8596,
"step": 1385
},
{
"epoch": 0.278,
"grad_norm": 237.40663146972656,
"learning_rate": 0.0001813506961365528,
"loss": 1078.5756,
"step": 1390
},
{
"epoch": 0.279,
"grad_norm": 259.9591979980469,
"learning_rate": 0.00018114719988013612,
"loss": 1008.5125,
"step": 1395
},
{
"epoch": 0.28,
"grad_norm": 321.2199401855469,
"learning_rate": 0.00018094271487069735,
"loss": 1043.4688,
"step": 1400
},
{
"epoch": 0.281,
"grad_norm": 254.0988006591797,
"learning_rate": 0.00018073724359982186,
"loss": 1050.6137,
"step": 1405
},
{
"epoch": 0.282,
"grad_norm": 471.7392578125,
"learning_rate": 0.0001805307885711122,
"loss": 1052.5917,
"step": 1410
},
{
"epoch": 0.283,
"grad_norm": 299.6447448730469,
"learning_rate": 0.0001803233523001578,
"loss": 998.101,
"step": 1415
},
{
"epoch": 0.284,
"grad_norm": 323.5834655761719,
"learning_rate": 0.00018011493731450413,
"loss": 1049.8648,
"step": 1420
},
{
"epoch": 0.285,
"grad_norm": 284.193115234375,
"learning_rate": 0.00017990554615362198,
"loss": 1053.8817,
"step": 1425
},
{
"epoch": 0.286,
"grad_norm": 227.78009033203125,
"learning_rate": 0.00017969518136887663,
"loss": 1037.6826,
"step": 1430
},
{
"epoch": 0.287,
"grad_norm": 248.8629608154297,
"learning_rate": 0.00017948384552349657,
"loss": 1013.6808,
"step": 1435
},
{
"epoch": 0.288,
"grad_norm": 241.92422485351562,
"learning_rate": 0.00017927154119254236,
"loss": 1004.8881,
"step": 1440
},
{
"epoch": 0.289,
"grad_norm": 320.44561767578125,
"learning_rate": 0.0001790582709628753,
"loss": 1001.6612,
"step": 1445
},
{
"epoch": 0.29,
"grad_norm": 219.94284057617188,
"learning_rate": 0.00017884403743312582,
"loss": 1039.6969,
"step": 1450
},
{
"epoch": 0.291,
"grad_norm": 266.00347900390625,
"learning_rate": 0.00017862884321366188,
"loss": 1016.238,
"step": 1455
},
{
"epoch": 0.292,
"grad_norm": 326.7903747558594,
"learning_rate": 0.00017841269092655715,
"loss": 1011.0079,
"step": 1460
},
{
"epoch": 0.293,
"grad_norm": 217.0819854736328,
"learning_rate": 0.000178195583205559,
"loss": 985.2447,
"step": 1465
},
{
"epoch": 0.294,
"grad_norm": 271.7309265136719,
"learning_rate": 0.00017797752269605653,
"loss": 962.1066,
"step": 1470
},
{
"epoch": 0.295,
"grad_norm": 274.3617248535156,
"learning_rate": 0.0001777585120550482,
"loss": 993.0564,
"step": 1475
},
{
"epoch": 0.296,
"grad_norm": 320.3966369628906,
"learning_rate": 0.0001775385539511096,
"loss": 958.5461,
"step": 1480
},
{
"epoch": 0.297,
"grad_norm": 275.8265686035156,
"learning_rate": 0.00017731765106436073,
"loss": 966.4637,
"step": 1485
},
{
"epoch": 0.298,
"grad_norm": 266.7901916503906,
"learning_rate": 0.00017709580608643363,
"loss": 933.5135,
"step": 1490
},
{
"epoch": 0.299,
"grad_norm": 226.40182495117188,
"learning_rate": 0.00017687302172043933,
"loss": 956.7207,
"step": 1495
},
{
"epoch": 0.3,
"grad_norm": 218.72525024414062,
"learning_rate": 0.00017664930068093498,
"loss": 1000.8804,
"step": 1500
},
{
"epoch": 0.301,
"grad_norm": 234.19960021972656,
"learning_rate": 0.0001764246456938909,
"loss": 1011.2401,
"step": 1505
},
{
"epoch": 0.302,
"grad_norm": 269.55621337890625,
"learning_rate": 0.0001761990594966572,
"loss": 1030.2077,
"step": 1510
},
{
"epoch": 0.303,
"grad_norm": 236.81202697753906,
"learning_rate": 0.00017597254483793048,
"loss": 983.3459,
"step": 1515
},
{
"epoch": 0.304,
"grad_norm": 242.6949920654297,
"learning_rate": 0.00017574510447772039,
"loss": 995.5935,
"step": 1520
},
{
"epoch": 0.305,
"grad_norm": 287.9051818847656,
"learning_rate": 0.00017551674118731591,
"loss": 1014.47,
"step": 1525
},
{
"epoch": 0.306,
"grad_norm": 275.30560302734375,
"learning_rate": 0.00017528745774925172,
"loss": 1036.5403,
"step": 1530
},
{
"epoch": 0.307,
"grad_norm": 256.5018615722656,
"learning_rate": 0.00017505725695727412,
"loss": 1006.0028,
"step": 1535
},
{
"epoch": 0.308,
"grad_norm": 269.4521179199219,
"learning_rate": 0.00017482614161630714,
"loss": 988.4326,
"step": 1540
},
{
"epoch": 0.309,
"grad_norm": 347.630615234375,
"learning_rate": 0.00017459411454241822,
"loss": 1057.1867,
"step": 1545
},
{
"epoch": 0.31,
"grad_norm": 236.9237518310547,
"learning_rate": 0.0001743611785627841,
"loss": 1022.6224,
"step": 1550
},
{
"epoch": 0.311,
"grad_norm": 298.8004455566406,
"learning_rate": 0.0001741273365156561,
"loss": 1004.5094,
"step": 1555
},
{
"epoch": 0.312,
"grad_norm": 200.8118896484375,
"learning_rate": 0.0001738925912503259,
"loss": 1004.3117,
"step": 1560
},
{
"epoch": 0.313,
"grad_norm": 655.1298217773438,
"learning_rate": 0.00017365694562709034,
"loss": 988.4531,
"step": 1565
},
{
"epoch": 0.314,
"grad_norm": 297.77099609375,
"learning_rate": 0.00017342040251721702,
"loss": 1025.0047,
"step": 1570
},
{
"epoch": 0.315,
"grad_norm": 287.94464111328125,
"learning_rate": 0.0001731829648029091,
"loss": 1020.3543,
"step": 1575
},
{
"epoch": 0.316,
"grad_norm": 410.5948181152344,
"learning_rate": 0.00017294463537727024,
"loss": 994.9609,
"step": 1580
},
{
"epoch": 0.317,
"grad_norm": 254.32174682617188,
"learning_rate": 0.0001727054171442692,
"loss": 1012.8915,
"step": 1585
},
{
"epoch": 0.318,
"grad_norm": 285.630859375,
"learning_rate": 0.0001724653130187047,
"loss": 946.0062,
"step": 1590
},
{
"epoch": 0.319,
"grad_norm": 291.9698181152344,
"learning_rate": 0.0001722243259261697,
"loss": 1006.198,
"step": 1595
},
{
"epoch": 0.32,
"grad_norm": 224.92977905273438,
"learning_rate": 0.0001719824588030159,
"loss": 1009.1939,
"step": 1600
},
{
"epoch": 0.321,
"grad_norm": 334.95672607421875,
"learning_rate": 0.00017173971459631787,
"loss": 992.3065,
"step": 1605
},
{
"epoch": 0.322,
"grad_norm": 389.25567626953125,
"learning_rate": 0.00017149609626383717,
"loss": 1030.9268,
"step": 1610
},
{
"epoch": 0.323,
"grad_norm": 289.8702392578125,
"learning_rate": 0.00017125160677398626,
"loss": 1012.4631,
"step": 1615
},
{
"epoch": 0.324,
"grad_norm": 290.34539794921875,
"learning_rate": 0.0001710062491057925,
"loss": 1047.0967,
"step": 1620
},
{
"epoch": 0.325,
"grad_norm": 206.34848022460938,
"learning_rate": 0.00017076002624886154,
"loss": 1052.0495,
"step": 1625
},
{
"epoch": 0.326,
"grad_norm": 396.9317932128906,
"learning_rate": 0.00017051294120334125,
"loss": 1056.2835,
"step": 1630
},
{
"epoch": 0.327,
"grad_norm": 203.18028259277344,
"learning_rate": 0.00017026499697988493,
"loss": 1014.0154,
"step": 1635
},
{
"epoch": 0.328,
"grad_norm": 179.22271728515625,
"learning_rate": 0.00017001619659961467,
"loss": 1017.1076,
"step": 1640
},
{
"epoch": 0.329,
"grad_norm": 193.84983825683594,
"learning_rate": 0.00016976654309408464,
"loss": 1037.1671,
"step": 1645
},
{
"epoch": 0.33,
"grad_norm": 320.1146240234375,
"learning_rate": 0.000169516039505244,
"loss": 1044.7144,
"step": 1650
},
{
"epoch": 0.331,
"grad_norm": 207.214599609375,
"learning_rate": 0.0001692646888853999,
"loss": 1028.7762,
"step": 1655
},
{
"epoch": 0.332,
"grad_norm": 218.6260223388672,
"learning_rate": 0.00016901249429718032,
"loss": 1009.5104,
"step": 1660
},
{
"epoch": 0.333,
"grad_norm": 200.37716674804688,
"learning_rate": 0.00016875945881349676,
"loss": 1021.783,
"step": 1665
},
{
"epoch": 0.334,
"grad_norm": 220.53073120117188,
"learning_rate": 0.0001685055855175067,
"loss": 992.0745,
"step": 1670
},
{
"epoch": 0.335,
"grad_norm": 176.90362548828125,
"learning_rate": 0.0001682508775025762,
"loss": 1057.6017,
"step": 1675
},
{
"epoch": 0.336,
"grad_norm": 189.5352325439453,
"learning_rate": 0.00016799533787224192,
"loss": 996.6545,
"step": 1680
},
{
"epoch": 0.337,
"grad_norm": 212.36593627929688,
"learning_rate": 0.00016773896974017373,
"loss": 987.5402,
"step": 1685
},
{
"epoch": 0.338,
"grad_norm": 217.8600616455078,
"learning_rate": 0.00016748177623013638,
"loss": 1028.2988,
"step": 1690
},
{
"epoch": 0.339,
"grad_norm": 199.49465942382812,
"learning_rate": 0.00016722376047595164,
"loss": 977.5404,
"step": 1695
},
{
"epoch": 0.34,
"grad_norm": 196.61676025390625,
"learning_rate": 0.00016696492562145996,
"loss": 986.4854,
"step": 1700
},
{
"epoch": 0.341,
"grad_norm": 185.09750366210938,
"learning_rate": 0.00016670527482048246,
"loss": 1058.1143,
"step": 1705
},
{
"epoch": 0.342,
"grad_norm": 205.19175720214844,
"learning_rate": 0.00016644481123678217,
"loss": 970.7956,
"step": 1710
},
{
"epoch": 0.343,
"grad_norm": 255.39553833007812,
"learning_rate": 0.00016618353804402568,
"loss": 1021.6194,
"step": 1715
},
{
"epoch": 0.344,
"grad_norm": 188.8345184326172,
"learning_rate": 0.00016592145842574433,
"loss": 1008.6794,
"step": 1720
},
{
"epoch": 0.345,
"grad_norm": 226.53973388671875,
"learning_rate": 0.00016565857557529566,
"loss": 1010.8551,
"step": 1725
},
{
"epoch": 0.346,
"grad_norm": 211.10513305664062,
"learning_rate": 0.00016539489269582416,
"loss": 980.6236,
"step": 1730
},
{
"epoch": 0.347,
"grad_norm": 208.87754821777344,
"learning_rate": 0.00016513041300022255,
"loss": 966.3775,
"step": 1735
},
{
"epoch": 0.348,
"grad_norm": 196.63742065429688,
"learning_rate": 0.00016486513971109243,
"loss": 953.6501,
"step": 1740
},
{
"epoch": 0.349,
"grad_norm": 227.57904052734375,
"learning_rate": 0.0001645990760607051,
"loss": 978.5168,
"step": 1745
},
{
"epoch": 0.35,
"grad_norm": 232.06228637695312,
"learning_rate": 0.0001643322252909622,
"loss": 1028.8913,
"step": 1750
},
{
"epoch": 0.351,
"grad_norm": 200.58627319335938,
"learning_rate": 0.00016406459065335615,
"loss": 997.7672,
"step": 1755
},
{
"epoch": 0.352,
"grad_norm": 252.1472625732422,
"learning_rate": 0.00016379617540893056,
"loss": 980.9877,
"step": 1760
},
{
"epoch": 0.353,
"grad_norm": 218.61880493164062,
"learning_rate": 0.00016352698282824044,
"loss": 973.382,
"step": 1765
},
{
"epoch": 0.354,
"grad_norm": 199.73057556152344,
"learning_rate": 0.00016325701619131246,
"loss": 1000.0478,
"step": 1770
},
{
"epoch": 0.355,
"grad_norm": 191.9346923828125,
"learning_rate": 0.00016298627878760487,
"loss": 953.2058,
"step": 1775
},
{
"epoch": 0.356,
"grad_norm": 207.17630004882812,
"learning_rate": 0.00016271477391596753,
"loss": 966.8748,
"step": 1780
},
{
"epoch": 0.357,
"grad_norm": 262.46710205078125,
"learning_rate": 0.00016244250488460158,
"loss": 1036.3131,
"step": 1785
},
{
"epoch": 0.358,
"grad_norm": 228.26031494140625,
"learning_rate": 0.0001621694750110193,
"loss": 974.3422,
"step": 1790
},
{
"epoch": 0.359,
"grad_norm": 275.9803161621094,
"learning_rate": 0.00016189568762200348,
"loss": 1007.4902,
"step": 1795
},
{
"epoch": 0.36,
"grad_norm": 474.3383483886719,
"learning_rate": 0.00016162114605356703,
"loss": 1000.2535,
"step": 1800
},
{
"epoch": 0.361,
"grad_norm": 227.62649536132812,
"learning_rate": 0.00016134585365091243,
"loss": 1026.9078,
"step": 1805
},
{
"epoch": 0.362,
"grad_norm": 239.06814575195312,
"learning_rate": 0.00016106981376839066,
"loss": 958.0942,
"step": 1810
},
{
"epoch": 0.363,
"grad_norm": 311.8114929199219,
"learning_rate": 0.00016079302976946055,
"loss": 974.6862,
"step": 1815
},
{
"epoch": 0.364,
"grad_norm": 559.9185791015625,
"learning_rate": 0.0001605155050266478,
"loss": 968.6005,
"step": 1820
},
{
"epoch": 0.365,
"grad_norm": 426.073974609375,
"learning_rate": 0.00016023724292150385,
"loss": 999.1157,
"step": 1825
},
{
"epoch": 0.366,
"grad_norm": 180.09617614746094,
"learning_rate": 0.00015995824684456465,
"loss": 961.5708,
"step": 1830
},
{
"epoch": 0.367,
"grad_norm": 192.3475799560547,
"learning_rate": 0.00015967852019530926,
"loss": 952.075,
"step": 1835
},
{
"epoch": 0.368,
"grad_norm": 180.1802978515625,
"learning_rate": 0.0001593980663821187,
"loss": 961.4676,
"step": 1840
},
{
"epoch": 0.369,
"grad_norm": 252.459716796875,
"learning_rate": 0.0001591168888222342,
"loss": 953.0187,
"step": 1845
},
{
"epoch": 0.37,
"grad_norm": 211.34185791015625,
"learning_rate": 0.00015883499094171554,
"loss": 967.8315,
"step": 1850
},
{
"epoch": 0.371,
"grad_norm": 214.6551055908203,
"learning_rate": 0.0001585523761753994,
"loss": 1051.1145,
"step": 1855
},
{
"epoch": 0.372,
"grad_norm": 179.5479278564453,
"learning_rate": 0.00015826904796685762,
"loss": 960.9272,
"step": 1860
},
{
"epoch": 0.373,
"grad_norm": 311.80694580078125,
"learning_rate": 0.00015798500976835493,
"loss": 978.2753,
"step": 1865
},
{
"epoch": 0.374,
"grad_norm": 277.00189208984375,
"learning_rate": 0.00015770026504080718,
"loss": 953.3916,
"step": 1870
},
{
"epoch": 0.375,
"grad_norm": 200.1035919189453,
"learning_rate": 0.000157414817253739,
"loss": 983.0482,
"step": 1875
},
{
"epoch": 0.376,
"grad_norm": 306.6880798339844,
"learning_rate": 0.00015712866988524155,
"loss": 940.6244,
"step": 1880
},
{
"epoch": 0.377,
"grad_norm": 184.86061096191406,
"learning_rate": 0.0001568418264219303,
"loss": 943.8717,
"step": 1885
},
{
"epoch": 0.378,
"grad_norm": 222.7330322265625,
"learning_rate": 0.0001565542903589023,
"loss": 921.1686,
"step": 1890
},
{
"epoch": 0.379,
"grad_norm": 352.63555908203125,
"learning_rate": 0.0001562660651996937,
"loss": 956.3995,
"step": 1895
},
{
"epoch": 0.38,
"grad_norm": 211.2472381591797,
"learning_rate": 0.00015597715445623712,
"loss": 950.3778,
"step": 1900
},
{
"epoch": 0.381,
"grad_norm": 196.08921813964844,
"learning_rate": 0.00015568756164881882,
"loss": 968.4602,
"step": 1905
},
{
"epoch": 0.382,
"grad_norm": 363.86083984375,
"learning_rate": 0.00015539729030603574,
"loss": 952.5543,
"step": 1910
},
{
"epoch": 0.383,
"grad_norm": 244.16067504882812,
"learning_rate": 0.0001551063439647526,
"loss": 954.9736,
"step": 1915
},
{
"epoch": 0.384,
"grad_norm": 179.36209106445312,
"learning_rate": 0.00015481472617005876,
"loss": 940.8331,
"step": 1920
},
{
"epoch": 0.385,
"grad_norm": 181.5355682373047,
"learning_rate": 0.00015452244047522502,
"loss": 947.7073,
"step": 1925
},
{
"epoch": 0.386,
"grad_norm": 267.5448303222656,
"learning_rate": 0.0001542294904416603,
"loss": 957.0993,
"step": 1930
},
{
"epoch": 0.387,
"grad_norm": 200.86630249023438,
"learning_rate": 0.00015393587963886835,
"loss": 947.9074,
"step": 1935
},
{
"epoch": 0.388,
"grad_norm": 192.0878143310547,
"learning_rate": 0.0001536416116444041,
"loss": 947.1439,
"step": 1940
},
{
"epoch": 0.389,
"grad_norm": 285.38311767578125,
"learning_rate": 0.0001533466900438303,
"loss": 952.9485,
"step": 1945
},
{
"epoch": 0.39,
"grad_norm": 213.99044799804688,
"learning_rate": 0.0001530511184306734,
"loss": 969.5572,
"step": 1950
},
{
"epoch": 0.391,
"grad_norm": 283.1478576660156,
"learning_rate": 0.00015275490040638038,
"loss": 953.785,
"step": 1955
},
{
"epoch": 0.392,
"grad_norm": 234.0,
"learning_rate": 0.00015245803958027434,
"loss": 934.231,
"step": 1960
},
{
"epoch": 0.393,
"grad_norm": 221.9193572998047,
"learning_rate": 0.0001521605395695108,
"loss": 940.2802,
"step": 1965
},
{
"epoch": 0.394,
"grad_norm": 328.9258117675781,
"learning_rate": 0.00015186240399903342,
"loss": 1003.1011,
"step": 1970
},
{
"epoch": 0.395,
"grad_norm": 176.4397430419922,
"learning_rate": 0.00015156363650153012,
"loss": 987.4318,
"step": 1975
},
{
"epoch": 0.396,
"grad_norm": 162.47352600097656,
"learning_rate": 0.0001512642407173885,
"loss": 956.5973,
"step": 1980
},
{
"epoch": 0.397,
"grad_norm": 213.25868225097656,
"learning_rate": 0.00015096422029465178,
"loss": 944.4022,
"step": 1985
},
{
"epoch": 0.398,
"grad_norm": 207.72850036621094,
"learning_rate": 0.0001506635788889741,
"loss": 970.8667,
"step": 1990
},
{
"epoch": 0.399,
"grad_norm": 207.43284606933594,
"learning_rate": 0.0001503623201635761,
"loss": 928.8271,
"step": 1995
},
{
"epoch": 0.4,
"grad_norm": 192.6944580078125,
"learning_rate": 0.0001500604477892003,
"loss": 936.0121,
"step": 2000
},
{
"epoch": 0.401,
"grad_norm": 213.77349853515625,
"learning_rate": 0.00014975796544406625,
"loss": 939.8703,
"step": 2005
},
{
"epoch": 0.402,
"grad_norm": 246.71189880371094,
"learning_rate": 0.00014945487681382598,
"loss": 940.1261,
"step": 2010
},
{
"epoch": 0.403,
"grad_norm": 244.46693420410156,
"learning_rate": 0.0001491511855915187,
"loss": 932.8948,
"step": 2015
},
{
"epoch": 0.404,
"grad_norm": 200.62562561035156,
"learning_rate": 0.0001488468954775262,
"loss": 954.7191,
"step": 2020
},
{
"epoch": 0.405,
"grad_norm": 249.8688507080078,
"learning_rate": 0.0001485420101795274,
"loss": 931.6166,
"step": 2025
},
{
"epoch": 0.406,
"grad_norm": 202.1702117919922,
"learning_rate": 0.00014823653341245353,
"loss": 949.4802,
"step": 2030
},
{
"epoch": 0.407,
"grad_norm": 244.0718231201172,
"learning_rate": 0.0001479304688984425,
"loss": 945.3966,
"step": 2035
},
{
"epoch": 0.408,
"grad_norm": 204.07923889160156,
"learning_rate": 0.0001476238203667939,
"loss": 946.7539,
"step": 2040
},
{
"epoch": 0.409,
"grad_norm": 187.79458618164062,
"learning_rate": 0.00014731659155392332,
"loss": 923.5418,
"step": 2045
},
{
"epoch": 0.41,
"grad_norm": 209.61497497558594,
"learning_rate": 0.00014700878620331684,
"loss": 937.6193,
"step": 2050
},
{
"epoch": 0.411,
"grad_norm": 188.27285766601562,
"learning_rate": 0.00014670040806548555,
"loss": 929.8365,
"step": 2055
},
{
"epoch": 0.412,
"grad_norm": 184.00228881835938,
"learning_rate": 0.0001463914608979197,
"loss": 904.3766,
"step": 2060
},
{
"epoch": 0.413,
"grad_norm": 192.0320587158203,
"learning_rate": 0.0001460819484650431,
"loss": 930.9064,
"step": 2065
},
{
"epoch": 0.414,
"grad_norm": 190.41326904296875,
"learning_rate": 0.000145771874538167,
"loss": 947.0927,
"step": 2070
},
{
"epoch": 0.415,
"grad_norm": 209.45518493652344,
"learning_rate": 0.0001454612428954444,
"loss": 945.5041,
"step": 2075
},
{
"epoch": 0.416,
"grad_norm": 186.41477966308594,
"learning_rate": 0.00014515005732182383,
"loss": 945.4051,
"step": 2080
},
{
"epoch": 0.417,
"grad_norm": 174.24708557128906,
"learning_rate": 0.00014483832160900326,
"loss": 939.2478,
"step": 2085
},
{
"epoch": 0.418,
"grad_norm": 176.3769989013672,
"learning_rate": 0.00014452603955538397,
"loss": 928.1729,
"step": 2090
},
{
"epoch": 0.419,
"grad_norm": 173.285400390625,
"learning_rate": 0.00014421321496602428,
"loss": 906.3039,
"step": 2095
},
{
"epoch": 0.42,
"grad_norm": 218.50750732421875,
"learning_rate": 0.00014389985165259308,
"loss": 943.871,
"step": 2100
},
{
"epoch": 0.421,
"grad_norm": 183.60511779785156,
"learning_rate": 0.00014358595343332342,
"loss": 933.4746,
"step": 2105
},
{
"epoch": 0.422,
"grad_norm": 240.73046875,
"learning_rate": 0.00014327152413296608,
"loss": 920.2143,
"step": 2110
},
{
"epoch": 0.423,
"grad_norm": 170.73402404785156,
"learning_rate": 0.00014295656758274284,
"loss": 923.9563,
"step": 2115
},
{
"epoch": 0.424,
"grad_norm": 208.78106689453125,
"learning_rate": 0.0001426410876202999,
"loss": 934.3674,
"step": 2120
},
{
"epoch": 0.425,
"grad_norm": 190.66261291503906,
"learning_rate": 0.00014232508808966098,
"loss": 933.4468,
"step": 2125
},
{
"epoch": 0.426,
"grad_norm": 185.3400421142578,
"learning_rate": 0.00014200857284118066,
"loss": 962.6744,
"step": 2130
},
{
"epoch": 0.427,
"grad_norm": 330.33685302734375,
"learning_rate": 0.00014169154573149737,
"loss": 921.2138,
"step": 2135
},
{
"epoch": 0.428,
"grad_norm": 226.8712158203125,
"learning_rate": 0.00014137401062348638,
"loss": 926.6334,
"step": 2140
},
{
"epoch": 0.429,
"grad_norm": 226.29331970214844,
"learning_rate": 0.0001410559713862128,
"loss": 913.1242,
"step": 2145
},
{
"epoch": 0.43,
"grad_norm": 204.52630615234375,
"learning_rate": 0.00014073743189488435,
"loss": 937.5739,
"step": 2150
},
{
"epoch": 0.431,
"grad_norm": 183.06947326660156,
"learning_rate": 0.00014041839603080422,
"loss": 917.315,
"step": 2155
},
{
"epoch": 0.432,
"grad_norm": 285.8097839355469,
"learning_rate": 0.00014009886768132375,
"loss": 929.0412,
"step": 2160
},
{
"epoch": 0.433,
"grad_norm": 212.503173828125,
"learning_rate": 0.000139778850739795,
"loss": 921.338,
"step": 2165
},
{
"epoch": 0.434,
"grad_norm": 186.3415985107422,
"learning_rate": 0.0001394583491055234,
"loss": 909.0187,
"step": 2170
},
{
"epoch": 0.435,
"grad_norm": 220.2411346435547,
"learning_rate": 0.00013913736668372026,
"loss": 931.6104,
"step": 2175
},
{
"epoch": 0.436,
"grad_norm": 166.42340087890625,
"learning_rate": 0.00013881590738545508,
"loss": 899.8335,
"step": 2180
},
{
"epoch": 0.437,
"grad_norm": 208.23660278320312,
"learning_rate": 0.00013849397512760795,
"loss": 920.6911,
"step": 2185
},
{
"epoch": 0.438,
"grad_norm": 324.3873596191406,
"learning_rate": 0.00013817157383282184,
"loss": 883.1972,
"step": 2190
},
{
"epoch": 0.439,
"grad_norm": 185.64044189453125,
"learning_rate": 0.00013784870742945482,
"loss": 924.5156,
"step": 2195
},
{
"epoch": 0.44,
"grad_norm": 202.95806884765625,
"learning_rate": 0.0001375253798515321,
"loss": 888.6787,
"step": 2200
},
{
"epoch": 0.441,
"grad_norm": 170.1503448486328,
"learning_rate": 0.00013720159503869815,
"loss": 902.3832,
"step": 2205
},
{
"epoch": 0.442,
"grad_norm": 173.28440856933594,
"learning_rate": 0.00013687735693616876,
"loss": 911.5302,
"step": 2210
},
{
"epoch": 0.443,
"grad_norm": 208.61097717285156,
"learning_rate": 0.0001365526694946829,
"loss": 949.5707,
"step": 2215
},
{
"epoch": 0.444,
"grad_norm": 337.42041015625,
"learning_rate": 0.00013622753667045457,
"loss": 918.905,
"step": 2220
},
{
"epoch": 0.445,
"grad_norm": 260.4453125,
"learning_rate": 0.00013590196242512463,
"loss": 903.3555,
"step": 2225
},
{
"epoch": 0.446,
"grad_norm": 220.509033203125,
"learning_rate": 0.0001355759507257125,
"loss": 902.1919,
"step": 2230
},
{
"epoch": 0.447,
"grad_norm": 230.7152099609375,
"learning_rate": 0.00013524950554456784,
"loss": 905.4905,
"step": 2235
},
{
"epoch": 0.448,
"grad_norm": 210.8260040283203,
"learning_rate": 0.00013492263085932224,
"loss": 905.2182,
"step": 2240
},
{
"epoch": 0.449,
"grad_norm": 180.2090606689453,
"learning_rate": 0.0001345953306528405,
"loss": 912.7699,
"step": 2245
},
{
"epoch": 0.45,
"grad_norm": 318.7266540527344,
"learning_rate": 0.00013426760891317236,
"loss": 938.8822,
"step": 2250
},
{
"epoch": 0.451,
"grad_norm": 200.44085693359375,
"learning_rate": 0.00013393946963350382,
"loss": 914.2893,
"step": 2255
},
{
"epoch": 0.452,
"grad_norm": 178.8852996826172,
"learning_rate": 0.00013361091681210845,
"loss": 901.4141,
"step": 2260
},
{
"epoch": 0.453,
"grad_norm": 182.22802734375,
"learning_rate": 0.00013328195445229868,
"loss": 903.95,
"step": 2265
},
{
"epoch": 0.454,
"grad_norm": 182.5507049560547,
"learning_rate": 0.00013295258656237702,
"loss": 910.6504,
"step": 2270
},
{
"epoch": 0.455,
"grad_norm": 176.39581298828125,
"learning_rate": 0.00013262281715558736,
"loss": 922.5725,
"step": 2275
},
{
"epoch": 0.456,
"grad_norm": 191.7860870361328,
"learning_rate": 0.00013229265025006576,
"loss": 947.7403,
"step": 2280
},
{
"epoch": 0.457,
"grad_norm": 211.9285888671875,
"learning_rate": 0.0001319620898687918,
"loss": 907.4664,
"step": 2285
},
{
"epoch": 0.458,
"grad_norm": 183.74891662597656,
"learning_rate": 0.0001316311400395394,
"loss": 886.4211,
"step": 2290
},
{
"epoch": 0.459,
"grad_norm": 216.7848663330078,
"learning_rate": 0.00013129980479482782,
"loss": 916.1842,
"step": 2295
},
{
"epoch": 0.46,
"grad_norm": 186.71469116210938,
"learning_rate": 0.00013096808817187242,
"loss": 888.6675,
"step": 2300
},
{
"epoch": 0.461,
"grad_norm": 171.18002319335938,
"learning_rate": 0.00013063599421253558,
"loss": 913.2043,
"step": 2305
},
{
"epoch": 0.462,
"grad_norm": 226.50338745117188,
"learning_rate": 0.00013030352696327742,
"loss": 907.4754,
"step": 2310
},
{
"epoch": 0.463,
"grad_norm": 183.06195068359375,
"learning_rate": 0.0001299706904751064,
"loss": 913.6343,
"step": 2315
},
{
"epoch": 0.464,
"grad_norm": 188.16903686523438,
"learning_rate": 0.00012963748880353011,
"loss": 912.5733,
"step": 2320
},
{
"epoch": 0.465,
"grad_norm": 189.9056854248047,
"learning_rate": 0.00012930392600850573,
"loss": 923.2314,
"step": 2325
},
{
"epoch": 0.466,
"grad_norm": 219.354736328125,
"learning_rate": 0.00012897000615439075,
"loss": 896.5633,
"step": 2330
},
{
"epoch": 0.467,
"grad_norm": 167.04757690429688,
"learning_rate": 0.00012863573330989313,
"loss": 902.8287,
"step": 2335
},
{
"epoch": 0.468,
"grad_norm": 400.5047302246094,
"learning_rate": 0.00012830111154802203,
"loss": 1069.1405,
"step": 2340
},
{
"epoch": 0.469,
"grad_norm": 257.8697204589844,
"learning_rate": 0.000127966144946038,
"loss": 908.1852,
"step": 2345
},
{
"epoch": 0.47,
"grad_norm": 234.10845947265625,
"learning_rate": 0.00012763083758540337,
"loss": 910.9126,
"step": 2350
},
{
"epoch": 0.471,
"grad_norm": 247.15235900878906,
"learning_rate": 0.00012729519355173254,
"loss": 912.2539,
"step": 2355
},
{
"epoch": 0.472,
"grad_norm": 246.75550842285156,
"learning_rate": 0.00012695921693474212,
"loss": 927.304,
"step": 2360
},
{
"epoch": 0.473,
"grad_norm": 183.9586181640625,
"learning_rate": 0.00012662291182820114,
"loss": 893.5921,
"step": 2365
},
{
"epoch": 0.474,
"grad_norm": 419.762939453125,
"learning_rate": 0.0001262862823298812,
"loss": 969.074,
"step": 2370
},
{
"epoch": 0.475,
"grad_norm": 197.27835083007812,
"learning_rate": 0.00012594933254150655,
"loss": 954.4241,
"step": 2375
},
{
"epoch": 0.476,
"grad_norm": 206.9922637939453,
"learning_rate": 0.00012561206656870396,
"loss": 903.298,
"step": 2380
},
{
"epoch": 0.477,
"grad_norm": 185.92971801757812,
"learning_rate": 0.00012527448852095295,
"loss": 919.3008,
"step": 2385
},
{
"epoch": 0.478,
"grad_norm": 235.80641174316406,
"learning_rate": 0.0001249366025115354,
"loss": 916.868,
"step": 2390
},
{
"epoch": 0.479,
"grad_norm": 210.42575073242188,
"learning_rate": 0.0001245984126574858,
"loss": 902.8715,
"step": 2395
},
{
"epoch": 0.48,
"grad_norm": 253.51988220214844,
"learning_rate": 0.00012425992307954075,
"loss": 893.3043,
"step": 2400
},
{
"epoch": 0.481,
"grad_norm": 188.373779296875,
"learning_rate": 0.00012392113790208895,
"loss": 1005.0773,
"step": 2405
},
{
"epoch": 0.482,
"grad_norm": 175.98626708984375,
"learning_rate": 0.00012358206125312083,
"loss": 871.008,
"step": 2410
},
{
"epoch": 0.483,
"grad_norm": 310.9893798828125,
"learning_rate": 0.0001232426972641784,
"loss": 905.9484,
"step": 2415
},
{
"epoch": 0.484,
"grad_norm": 185.6499786376953,
"learning_rate": 0.00012290305007030478,
"loss": 900.5751,
"step": 2420
},
{
"epoch": 0.485,
"grad_norm": 250.2499542236328,
"learning_rate": 0.00012256312380999376,
"loss": 902.6573,
"step": 2425
},
{
"epoch": 0.486,
"grad_norm": 234.06948852539062,
"learning_rate": 0.00012222292262513965,
"loss": 887.3303,
"step": 2430
},
{
"epoch": 0.487,
"grad_norm": 173.5924072265625,
"learning_rate": 0.00012188245066098647,
"loss": 875.0962,
"step": 2435
},
{
"epoch": 0.488,
"grad_norm": 224.32798767089844,
"learning_rate": 0.00012154171206607764,
"loss": 884.6464,
"step": 2440
},
{
"epoch": 0.489,
"grad_norm": 171.93360900878906,
"learning_rate": 0.00012120071099220549,
"loss": 885.1161,
"step": 2445
},
{
"epoch": 0.49,
"grad_norm": 181.95492553710938,
"learning_rate": 0.00012085945159436038,
"loss": 892.5318,
"step": 2450
},
{
"epoch": 0.491,
"grad_norm": 221.41375732421875,
"learning_rate": 0.00012051793803068046,
"loss": 876.8442,
"step": 2455
},
{
"epoch": 0.492,
"grad_norm": 170.9804229736328,
"learning_rate": 0.0001201761744624007,
"loss": 948.0444,
"step": 2460
},
{
"epoch": 0.493,
"grad_norm": 164.31732177734375,
"learning_rate": 0.00011983416505380234,
"loss": 917.3749,
"step": 2465
},
{
"epoch": 0.494,
"grad_norm": 187.4403839111328,
"learning_rate": 0.00011949191397216206,
"loss": 900.3194,
"step": 2470
},
{
"epoch": 0.495,
"grad_norm": 170.93589782714844,
"learning_rate": 0.00011914942538770131,
"loss": 881.0633,
"step": 2475
},
{
"epoch": 0.496,
"grad_norm": 191.4259033203125,
"learning_rate": 0.00011880670347353539,
"loss": 881.8791,
"step": 2480
},
{
"epoch": 0.497,
"grad_norm": 193.06837463378906,
"learning_rate": 0.0001184637524056227,
"loss": 972.3412,
"step": 2485
},
{
"epoch": 0.498,
"grad_norm": 221.10488891601562,
"learning_rate": 0.00011812057636271374,
"loss": 888.1727,
"step": 2490
},
{
"epoch": 0.499,
"grad_norm": 238.4519805908203,
"learning_rate": 0.00011777717952630031,
"loss": 889.4736,
"step": 2495
},
{
"epoch": 0.5,
"grad_norm": 223.88760375976562,
"learning_rate": 0.00011743356608056449,
"loss": 896.5576,
"step": 2500
},
{
"epoch": 0.501,
"grad_norm": 240.4513397216797,
"learning_rate": 0.00011708974021232769,
"loss": 899.7922,
"step": 2505
},
{
"epoch": 0.502,
"grad_norm": 194.39569091796875,
"learning_rate": 0.00011674570611099955,
"loss": 899.6859,
"step": 2510
},
{
"epoch": 0.503,
"grad_norm": 226.50128173828125,
"learning_rate": 0.00011640146796852711,
"loss": 890.7002,
"step": 2515
},
{
"epoch": 0.504,
"grad_norm": 184.0170440673828,
"learning_rate": 0.00011605702997934345,
"loss": 910.8449,
"step": 2520
},
{
"epoch": 0.505,
"grad_norm": 181.56736755371094,
"learning_rate": 0.00011571239634031679,
"loss": 898.2225,
"step": 2525
},
{
"epoch": 0.506,
"grad_norm": 206.15257263183594,
"learning_rate": 0.00011536757125069923,
"loss": 875.3796,
"step": 2530
},
{
"epoch": 0.507,
"grad_norm": 199.19313049316406,
"learning_rate": 0.00011502255891207572,
"loss": 893.1937,
"step": 2535
},
{
"epoch": 0.508,
"grad_norm": 160.26722717285156,
"learning_rate": 0.00011467736352831266,
"loss": 885.7165,
"step": 2540
},
{
"epoch": 0.509,
"grad_norm": 236.8365478515625,
"learning_rate": 0.00011433198930550695,
"loss": 876.056,
"step": 2545
},
{
"epoch": 0.51,
"grad_norm": 166.82191467285156,
"learning_rate": 0.00011398644045193444,
"loss": 875.452,
"step": 2550
},
{
"epoch": 0.511,
"grad_norm": 157.22360229492188,
"learning_rate": 0.00011364072117799885,
"loss": 881.2471,
"step": 2555
},
{
"epoch": 0.512,
"grad_norm": 211.3368682861328,
"learning_rate": 0.00011329483569618045,
"loss": 852.7133,
"step": 2560
},
{
"epoch": 0.513,
"grad_norm": 247.2423095703125,
"learning_rate": 0.00011294878822098469,
"loss": 883.9519,
"step": 2565
},
{
"epoch": 0.514,
"grad_norm": 453.9803771972656,
"learning_rate": 0.00011260258296889086,
"loss": 858.2674,
"step": 2570
},
{
"epoch": 0.515,
"grad_norm": 828.89013671875,
"learning_rate": 0.00011225622415830068,
"loss": 934.7731,
"step": 2575
},
{
"epoch": 0.516,
"grad_norm": 175.52134704589844,
"learning_rate": 0.00011190971600948699,
"loss": 860.2802,
"step": 2580
},
{
"epoch": 0.517,
"grad_norm": 177.6731414794922,
"learning_rate": 0.00011156306274454218,
"loss": 878.3054,
"step": 2585
},
{
"epoch": 0.518,
"grad_norm": 174.72874450683594,
"learning_rate": 0.0001112162685873269,
"loss": 878.843,
"step": 2590
},
{
"epoch": 0.519,
"grad_norm": 193.2017822265625,
"learning_rate": 0.00011086933776341852,
"loss": 860.8799,
"step": 2595
},
{
"epoch": 0.52,
"grad_norm": 188.33438110351562,
"learning_rate": 0.00011052227450005967,
"loss": 851.5081,
"step": 2600
},
{
"epoch": 0.521,
"grad_norm": 170.20108032226562,
"learning_rate": 0.00011017508302610664,
"loss": 863.9661,
"step": 2605
},
{
"epoch": 0.522,
"grad_norm": 179.63592529296875,
"learning_rate": 0.00010982776757197799,
"loss": 923.5085,
"step": 2610
},
{
"epoch": 0.523,
"grad_norm": 273.0093078613281,
"learning_rate": 0.00010948033236960294,
"loss": 878.4118,
"step": 2615
},
{
"epoch": 0.524,
"grad_norm": 232.55331420898438,
"learning_rate": 0.00010913278165236978,
"loss": 862.3436,
"step": 2620
},
{
"epoch": 0.525,
"grad_norm": 219.42568969726562,
"learning_rate": 0.00010878511965507434,
"loss": 904.0182,
"step": 2625
},
{
"epoch": 0.526,
"grad_norm": 238.19923400878906,
"learning_rate": 0.00010843735061386828,
"loss": 876.6498,
"step": 2630
},
{
"epoch": 0.527,
"grad_norm": 244.96551513671875,
"learning_rate": 0.00010808947876620767,
"loss": 881.0285,
"step": 2635
},
{
"epoch": 0.528,
"grad_norm": 195.77760314941406,
"learning_rate": 0.00010774150835080119,
"loss": 899.9534,
"step": 2640
},
{
"epoch": 0.529,
"grad_norm": 209.44198608398438,
"learning_rate": 0.00010739344360755852,
"loss": 879.5733,
"step": 2645
},
{
"epoch": 0.53,
"grad_norm": 172.40255737304688,
"learning_rate": 0.0001070452887775387,
"loss": 882.1128,
"step": 2650
},
{
"epoch": 0.531,
"grad_norm": 187.79551696777344,
"learning_rate": 0.00010669704810289851,
"loss": 924.9053,
"step": 2655
},
{
"epoch": 0.532,
"grad_norm": 397.74920654296875,
"learning_rate": 0.00010634872582684061,
"loss": 883.5871,
"step": 2660
},
{
"epoch": 0.533,
"grad_norm": 220.04095458984375,
"learning_rate": 0.00010600032619356209,
"loss": 907.9898,
"step": 2665
},
{
"epoch": 0.534,
"grad_norm": 174.2458953857422,
"learning_rate": 0.00010565185344820247,
"loss": 868.8557,
"step": 2670
},
{
"epoch": 0.535,
"grad_norm": 170.26751708984375,
"learning_rate": 0.00010530331183679218,
"loss": 863.9757,
"step": 2675
},
{
"epoch": 0.536,
"grad_norm": 196.84242248535156,
"learning_rate": 0.00010495470560620083,
"loss": 883.5931,
"step": 2680
},
{
"epoch": 0.537,
"grad_norm": 162.90882873535156,
"learning_rate": 0.00010460603900408523,
"loss": 867.5802,
"step": 2685
},
{
"epoch": 0.538,
"grad_norm": 181.29417419433594,
"learning_rate": 0.00010425731627883797,
"loss": 884.4985,
"step": 2690
},
{
"epoch": 0.539,
"grad_norm": 165.95692443847656,
"learning_rate": 0.00010390854167953537,
"loss": 887.5756,
"step": 2695
},
{
"epoch": 0.54,
"grad_norm": 260.92730712890625,
"learning_rate": 0.00010355971945588585,
"loss": 890.2235,
"step": 2700
},
{
"epoch": 0.541,
"grad_norm": 184.26519775390625,
"learning_rate": 0.00010321085385817817,
"loss": 870.6565,
"step": 2705
},
{
"epoch": 0.542,
"grad_norm": 210.80551147460938,
"learning_rate": 0.00010286194913722948,
"loss": 862.5367,
"step": 2710
},
{
"epoch": 0.543,
"grad_norm": 182.25160217285156,
"learning_rate": 0.00010251300954433376,
"loss": 859.8624,
"step": 2715
},
{
"epoch": 0.544,
"grad_norm": 174.89602661132812,
"learning_rate": 0.00010216403933120979,
"loss": 874.0044,
"step": 2720
},
{
"epoch": 0.545,
"grad_norm": 178.487548828125,
"learning_rate": 0.00010181504274994948,
"loss": 872.0665,
"step": 2725
},
{
"epoch": 0.546,
"grad_norm": 173.76824951171875,
"learning_rate": 0.00010146602405296607,
"loss": 882.5121,
"step": 2730
},
{
"epoch": 0.547,
"grad_norm": 177.2438507080078,
"learning_rate": 0.00010111698749294223,
"loss": 880.1572,
"step": 2735
},
{
"epoch": 0.548,
"grad_norm": 172.43914794921875,
"learning_rate": 0.00010076793732277829,
"loss": 853.2588,
"step": 2740
},
{
"epoch": 0.549,
"grad_norm": 157.2755889892578,
"learning_rate": 0.0001004188777955404,
"loss": 828.7634,
"step": 2745
},
{
"epoch": 0.55,
"grad_norm": 147.0779571533203,
"learning_rate": 0.00010006981316440875,
"loss": 838.6358,
"step": 2750
},
{
"epoch": 0.551,
"grad_norm": 165.32284545898438,
"learning_rate": 9.972074768262576e-05,
"loss": 843.7614,
"step": 2755
},
{
"epoch": 0.552,
"grad_norm": 147.40509033203125,
"learning_rate": 9.937168560344412e-05,
"loss": 842.9076,
"step": 2760
},
{
"epoch": 0.553,
"grad_norm": 219.02676391601562,
"learning_rate": 9.902263118007513e-05,
"loss": 874.4397,
"step": 2765
},
{
"epoch": 0.554,
"grad_norm": 172.1724395751953,
"learning_rate": 9.867358866563673e-05,
"loss": 860.238,
"step": 2770
},
{
"epoch": 0.555,
"grad_norm": 178.1503448486328,
"learning_rate": 9.832456231310189e-05,
"loss": 890.6468,
"step": 2775
},
{
"epoch": 0.556,
"grad_norm": 183.7974853515625,
"learning_rate": 9.797555637524649e-05,
"loss": 879.393,
"step": 2780
},
{
"epoch": 0.557,
"grad_norm": 181.21990966796875,
"learning_rate": 9.762657510459783e-05,
"loss": 907.4206,
"step": 2785
},
{
"epoch": 0.558,
"grad_norm": 185.48129272460938,
"learning_rate": 9.727762275338246e-05,
"loss": 846.8659,
"step": 2790
},
{
"epoch": 0.559,
"grad_norm": 513.8157958984375,
"learning_rate": 9.692870357347473e-05,
"loss": 833.2876,
"step": 2795
},
{
"epoch": 0.56,
"grad_norm": 207.86695861816406,
"learning_rate": 9.657982181634475e-05,
"loss": 900.4038,
"step": 2800
},
{
"epoch": 0.561,
"grad_norm": 151.79029846191406,
"learning_rate": 9.623098173300654e-05,
"loss": 866.3104,
"step": 2805
},
{
"epoch": 0.562,
"grad_norm": 191.39971923828125,
"learning_rate": 9.588218757396655e-05,
"loss": 864.6956,
"step": 2810
},
{
"epoch": 0.563,
"grad_norm": 177.32855224609375,
"learning_rate": 9.55334435891714e-05,
"loss": 856.6219,
"step": 2815
},
{
"epoch": 0.564,
"grad_norm": 213.04193115234375,
"learning_rate": 9.518475402795661e-05,
"loss": 896.7647,
"step": 2820
},
{
"epoch": 0.565,
"grad_norm": 208.61721801757812,
"learning_rate": 9.483612313899435e-05,
"loss": 880.6354,
"step": 2825
},
{
"epoch": 0.566,
"grad_norm": 186.201416015625,
"learning_rate": 9.448755517024206e-05,
"loss": 873.7563,
"step": 2830
},
{
"epoch": 0.567,
"grad_norm": 174.54150390625,
"learning_rate": 9.413905436889035e-05,
"loss": 880.4528,
"step": 2835
},
{
"epoch": 0.568,
"grad_norm": 169.50253295898438,
"learning_rate": 9.37906249813116e-05,
"loss": 858.2946,
"step": 2840
},
{
"epoch": 0.569,
"grad_norm": 205.4982452392578,
"learning_rate": 9.344227125300788e-05,
"loss": 880.0034,
"step": 2845
},
{
"epoch": 0.57,
"grad_norm": 167.8470916748047,
"learning_rate": 9.309399742855942e-05,
"loss": 868.6187,
"step": 2850
},
{
"epoch": 0.571,
"grad_norm": 185.9294891357422,
"learning_rate": 9.274580775157294e-05,
"loss": 840.8251,
"step": 2855
},
{
"epoch": 0.572,
"grad_norm": 197.36343383789062,
"learning_rate": 9.239770646462968e-05,
"loss": 843.6756,
"step": 2860
},
{
"epoch": 0.573,
"grad_norm": 214.83657836914062,
"learning_rate": 9.204969780923403e-05,
"loss": 855.042,
"step": 2865
},
{
"epoch": 0.574,
"grad_norm": 179.92628479003906,
"learning_rate": 9.17017860257616e-05,
"loss": 853.3512,
"step": 2870
},
{
"epoch": 0.575,
"grad_norm": 193.4222869873047,
"learning_rate": 9.135397535340773e-05,
"loss": 872.4227,
"step": 2875
},
{
"epoch": 0.576,
"grad_norm": 249.0337371826172,
"learning_rate": 9.100627003013562e-05,
"loss": 851.9912,
"step": 2880
},
{
"epoch": 0.577,
"grad_norm": 268.4931640625,
"learning_rate": 9.065867429262496e-05,
"loss": 870.783,
"step": 2885
},
{
"epoch": 0.578,
"grad_norm": 160.5849151611328,
"learning_rate": 9.03111923762201e-05,
"loss": 861.0972,
"step": 2890
},
{
"epoch": 0.579,
"grad_norm": 180.5119171142578,
"learning_rate": 8.99638285148785e-05,
"loss": 872.4458,
"step": 2895
},
{
"epoch": 0.58,
"grad_norm": 185.67103576660156,
"learning_rate": 8.961658694111929e-05,
"loss": 881.5423,
"step": 2900
},
{
"epoch": 0.581,
"grad_norm": 210.33914184570312,
"learning_rate": 8.926947188597134e-05,
"loss": 849.8383,
"step": 2905
},
{
"epoch": 0.582,
"grad_norm": 151.79464721679688,
"learning_rate": 8.892248757892214e-05,
"loss": 848.748,
"step": 2910
},
{
"epoch": 0.583,
"grad_norm": 172.87567138671875,
"learning_rate": 8.857563824786596e-05,
"loss": 863.4705,
"step": 2915
},
{
"epoch": 0.584,
"grad_norm": 195.47532653808594,
"learning_rate": 8.822892811905237e-05,
"loss": 844.3872,
"step": 2920
},
{
"epoch": 0.585,
"grad_norm": 193.5167236328125,
"learning_rate": 8.788236141703498e-05,
"loss": 868.0327,
"step": 2925
},
{
"epoch": 0.586,
"grad_norm": 563.900146484375,
"learning_rate": 8.753594236461957e-05,
"loss": 867.5116,
"step": 2930
},
{
"epoch": 0.587,
"grad_norm": 166.45535278320312,
"learning_rate": 8.718967518281307e-05,
"loss": 856.36,
"step": 2935
},
{
"epoch": 0.588,
"grad_norm": 264.9775390625,
"learning_rate": 8.684356409077176e-05,
"loss": 862.0073,
"step": 2940
},
{
"epoch": 0.589,
"grad_norm": 279.6457824707031,
"learning_rate": 8.64976133057501e-05,
"loss": 858.8056,
"step": 2945
},
{
"epoch": 0.59,
"grad_norm": 210.4329833984375,
"learning_rate": 8.615182704304918e-05,
"loss": 851.6025,
"step": 2950
},
{
"epoch": 0.591,
"grad_norm": 227.38717651367188,
"learning_rate": 8.580620951596557e-05,
"loss": 858.4251,
"step": 2955
},
{
"epoch": 0.592,
"grad_norm": 188.0125274658203,
"learning_rate": 8.546076493573972e-05,
"loss": 877.9513,
"step": 2960
},
{
"epoch": 0.593,
"grad_norm": 182.4275665283203,
"learning_rate": 8.511549751150479e-05,
"loss": 850.0612,
"step": 2965
},
{
"epoch": 0.594,
"grad_norm": 789.3680419921875,
"learning_rate": 8.477041145023546e-05,
"loss": 886.3138,
"step": 2970
},
{
"epoch": 0.595,
"grad_norm": 202.1874542236328,
"learning_rate": 8.442551095669639e-05,
"loss": 899.7643,
"step": 2975
},
{
"epoch": 0.596,
"grad_norm": 165.9135284423828,
"learning_rate": 8.408080023339133e-05,
"loss": 834.4099,
"step": 2980
},
{
"epoch": 0.597,
"grad_norm": 251.65908813476562,
"learning_rate": 8.373628348051165e-05,
"loss": 872.1891,
"step": 2985
},
{
"epoch": 0.598,
"grad_norm": 167.5531768798828,
"learning_rate": 8.339196489588523e-05,
"loss": 840.2023,
"step": 2990
},
{
"epoch": 0.599,
"grad_norm": 248.2529296875,
"learning_rate": 8.30478486749254e-05,
"loss": 858.6496,
"step": 2995
},
{
"epoch": 0.6,
"grad_norm": 314.3301086425781,
"learning_rate": 8.270393901057964e-05,
"loss": 888.115,
"step": 3000
},
{
"epoch": 0.601,
"grad_norm": 204.793701171875,
"learning_rate": 8.236024009327879e-05,
"loss": 926.6144,
"step": 3005
},
{
"epoch": 0.602,
"grad_norm": 210.56192016601562,
"learning_rate": 8.201675611088558e-05,
"loss": 860.38,
"step": 3010
},
{
"epoch": 0.603,
"grad_norm": 164.27398681640625,
"learning_rate": 8.167349124864405e-05,
"loss": 842.1946,
"step": 3015
},
{
"epoch": 0.604,
"grad_norm": 197.9868927001953,
"learning_rate": 8.133044968912811e-05,
"loss": 841.3525,
"step": 3020
},
{
"epoch": 0.605,
"grad_norm": 231.40501403808594,
"learning_rate": 8.0987635612191e-05,
"loss": 838.5433,
"step": 3025
},
{
"epoch": 0.606,
"grad_norm": 170.30770874023438,
"learning_rate": 8.064505319491398e-05,
"loss": 844.4794,
"step": 3030
},
{
"epoch": 0.607,
"grad_norm": 557.181884765625,
"learning_rate": 8.030270661155574e-05,
"loss": 873.9128,
"step": 3035
},
{
"epoch": 0.608,
"grad_norm": 170.9451141357422,
"learning_rate": 7.996060003350139e-05,
"loss": 853.5265,
"step": 3040
},
{
"epoch": 0.609,
"grad_norm": 194.94729614257812,
"learning_rate": 7.961873762921153e-05,
"loss": 852.497,
"step": 3045
},
{
"epoch": 0.61,
"grad_norm": 167.3991241455078,
"learning_rate": 7.927712356417176e-05,
"loss": 854.4564,
"step": 3050
},
{
"epoch": 0.611,
"grad_norm": 163.7258758544922,
"learning_rate": 7.893576200084159e-05,
"loss": 860.9714,
"step": 3055
},
{
"epoch": 0.612,
"grad_norm": 183.81007385253906,
"learning_rate": 7.8594657098604e-05,
"loss": 852.1116,
"step": 3060
},
{
"epoch": 0.613,
"grad_norm": 177.9263916015625,
"learning_rate": 7.825381301371452e-05,
"loss": 850.9779,
"step": 3065
},
{
"epoch": 0.614,
"grad_norm": 198.31021118164062,
"learning_rate": 7.791323389925084e-05,
"loss": 861.2728,
"step": 3070
},
{
"epoch": 0.615,
"grad_norm": 287.78192138671875,
"learning_rate": 7.75729239050619e-05,
"loss": 851.6341,
"step": 3075
},
{
"epoch": 0.616,
"grad_norm": 183.6859130859375,
"learning_rate": 7.723288717771761e-05,
"loss": 850.2264,
"step": 3080
},
{
"epoch": 0.617,
"grad_norm": 171.34625244140625,
"learning_rate": 7.689312786045823e-05,
"loss": 887.5685,
"step": 3085
},
{
"epoch": 0.618,
"grad_norm": 159.31690979003906,
"learning_rate": 7.655365009314374e-05,
"loss": 849.9249,
"step": 3090
},
{
"epoch": 0.619,
"grad_norm": 198.5939178466797,
"learning_rate": 7.621445801220371e-05,
"loss": 850.1029,
"step": 3095
},
{
"epoch": 0.62,
"grad_norm": 205.10964965820312,
"learning_rate": 7.587555575058649e-05,
"loss": 833.2944,
"step": 3100
},
{
"epoch": 0.621,
"grad_norm": 176.21609497070312,
"learning_rate": 7.553694743770928e-05,
"loss": 848.5025,
"step": 3105
},
{
"epoch": 0.622,
"grad_norm": 191.91737365722656,
"learning_rate": 7.519863719940748e-05,
"loss": 828.6109,
"step": 3110
},
{
"epoch": 0.623,
"grad_norm": 160.35391235351562,
"learning_rate": 7.486062915788452e-05,
"loss": 844.1729,
"step": 3115
},
{
"epoch": 0.624,
"grad_norm": 144.19825744628906,
"learning_rate": 7.45229274316618e-05,
"loss": 823.8797,
"step": 3120
},
{
"epoch": 0.625,
"grad_norm": 181.0189971923828,
"learning_rate": 7.418553613552825e-05,
"loss": 862.9917,
"step": 3125
},
{
"epoch": 0.626,
"grad_norm": 630.267822265625,
"learning_rate": 7.384845938049031e-05,
"loss": 891.0334,
"step": 3130
},
{
"epoch": 0.627,
"grad_norm": 650.041015625,
"learning_rate": 7.351170127372191e-05,
"loss": 972.2668,
"step": 3135
},
{
"epoch": 0.628,
"grad_norm": 578.6989135742188,
"learning_rate": 7.317526591851433e-05,
"loss": 894.063,
"step": 3140
},
{
"epoch": 0.629,
"grad_norm": 394.5833740234375,
"learning_rate": 7.283915741422612e-05,
"loss": 826.7015,
"step": 3145
},
{
"epoch": 0.63,
"grad_norm": 744.22705078125,
"learning_rate": 7.250337985623342e-05,
"loss": 842.7498,
"step": 3150
},
{
"epoch": 0.631,
"grad_norm": 280.5011901855469,
"learning_rate": 7.216793733587976e-05,
"loss": 837.3308,
"step": 3155
},
{
"epoch": 0.632,
"grad_norm": 189.82467651367188,
"learning_rate": 7.183283394042634e-05,
"loss": 882.3633,
"step": 3160
},
{
"epoch": 0.633,
"grad_norm": 193.23202514648438,
"learning_rate": 7.149807375300239e-05,
"loss": 860.21,
"step": 3165
},
{
"epoch": 0.634,
"grad_norm": 176.29458618164062,
"learning_rate": 7.11636608525551e-05,
"loss": 850.7104,
"step": 3170
},
{
"epoch": 0.635,
"grad_norm": 276.6162414550781,
"learning_rate": 7.082959931380011e-05,
"loss": 852.1934,
"step": 3175
},
{
"epoch": 0.636,
"grad_norm": 205.14427185058594,
"learning_rate": 7.049589320717186e-05,
"loss": 853.1243,
"step": 3180
},
{
"epoch": 0.637,
"grad_norm": 252.27911376953125,
"learning_rate": 7.016254659877398e-05,
"loss": 855.2658,
"step": 3185
},
{
"epoch": 0.638,
"grad_norm": 253.9312744140625,
"learning_rate": 6.982956355032968e-05,
"loss": 828.9792,
"step": 3190
},
{
"epoch": 0.639,
"grad_norm": 174.5731201171875,
"learning_rate": 6.949694811913225e-05,
"loss": 846.2183,
"step": 3195
},
{
"epoch": 0.64,
"grad_norm": 179.3285369873047,
"learning_rate": 6.916470435799587e-05,
"loss": 826.1234,
"step": 3200
},
{
"epoch": 0.641,
"grad_norm": 191.0880889892578,
"learning_rate": 6.883283631520582e-05,
"loss": 869.5899,
"step": 3205
},
{
"epoch": 0.642,
"grad_norm": 169.4415283203125,
"learning_rate": 6.850134803446954e-05,
"loss": 875.2319,
"step": 3210
},
{
"epoch": 0.643,
"grad_norm": 220.75099182128906,
"learning_rate": 6.817024355486706e-05,
"loss": 847.2343,
"step": 3215
},
{
"epoch": 0.644,
"grad_norm": 376.08880615234375,
"learning_rate": 6.783952691080203e-05,
"loss": 851.8294,
"step": 3220
},
{
"epoch": 0.645,
"grad_norm": 172.34500122070312,
"learning_rate": 6.750920213195238e-05,
"loss": 858.6748,
"step": 3225
},
{
"epoch": 0.646,
"grad_norm": 386.2594299316406,
"learning_rate": 6.717927324322124e-05,
"loss": 842.1083,
"step": 3230
},
{
"epoch": 0.647,
"grad_norm": 173.05787658691406,
"learning_rate": 6.684974426468808e-05,
"loss": 845.2005,
"step": 3235
},
{
"epoch": 0.648,
"grad_norm": 175.74008178710938,
"learning_rate": 6.652061921155943e-05,
"loss": 839.0009,
"step": 3240
},
{
"epoch": 0.649,
"grad_norm": 244.4064178466797,
"learning_rate": 6.61919020941203e-05,
"loss": 860.1235,
"step": 3245
},
{
"epoch": 0.65,
"grad_norm": 205.42152404785156,
"learning_rate": 6.58635969176849e-05,
"loss": 883.1491,
"step": 3250
},
{
"epoch": 0.651,
"grad_norm": 192.5198211669922,
"learning_rate": 6.55357076825483e-05,
"loss": 830.3912,
"step": 3255
},
{
"epoch": 0.652,
"grad_norm": 187.1549530029297,
"learning_rate": 6.520823838393731e-05,
"loss": 844.1321,
"step": 3260
},
{
"epoch": 0.653,
"grad_norm": 163.7439422607422,
"learning_rate": 6.488119301196201e-05,
"loss": 850.0932,
"step": 3265
},
{
"epoch": 0.654,
"grad_norm": 296.8761901855469,
"learning_rate": 6.455457555156705e-05,
"loss": 863.6457,
"step": 3270
},
{
"epoch": 0.655,
"grad_norm": 200.95254516601562,
"learning_rate": 6.422838998248307e-05,
"loss": 817.3543,
"step": 3275
},
{
"epoch": 0.656,
"grad_norm": 170.5740509033203,
"learning_rate": 6.390264027917836e-05,
"loss": 830.6383,
"step": 3280
},
{
"epoch": 0.657,
"grad_norm": 745.0942993164062,
"learning_rate": 6.357733041081018e-05,
"loss": 896.5307,
"step": 3285
},
{
"epoch": 0.658,
"grad_norm": 228.6047821044922,
"learning_rate": 6.325246434117668e-05,
"loss": 815.7207,
"step": 3290
},
{
"epoch": 0.659,
"grad_norm": 203.5364532470703,
"learning_rate": 6.292804602866834e-05,
"loss": 865.6739,
"step": 3295
},
{
"epoch": 0.66,
"grad_norm": 162.81414794921875,
"learning_rate": 6.260407942621998e-05,
"loss": 836.2892,
"step": 3300
},
{
"epoch": 0.661,
"grad_norm": 232.7904510498047,
"learning_rate": 6.228056848126236e-05,
"loss": 845.3945,
"step": 3305
},
{
"epoch": 0.662,
"grad_norm": 193.78883361816406,
"learning_rate": 6.195751713567427e-05,
"loss": 846.0749,
"step": 3310
},
{
"epoch": 0.663,
"grad_norm": 185.9735107421875,
"learning_rate": 6.163492932573438e-05,
"loss": 847.3547,
"step": 3315
},
{
"epoch": 0.664,
"grad_norm": 185.92410278320312,
"learning_rate": 6.131280898207339e-05,
"loss": 835.3866,
"step": 3320
},
{
"epoch": 0.665,
"grad_norm": 169.37564086914062,
"learning_rate": 6.099116002962604e-05,
"loss": 834.7155,
"step": 3325
},
{
"epoch": 0.666,
"grad_norm": 181.5061798095703,
"learning_rate": 6.066998638758326e-05,
"loss": 822.1385,
"step": 3330
},
{
"epoch": 0.667,
"grad_norm": 145.32733154296875,
"learning_rate": 6.034929196934459e-05,
"loss": 899.9922,
"step": 3335
},
{
"epoch": 0.668,
"grad_norm": 155.46023559570312,
"learning_rate": 6.002908068247024e-05,
"loss": 839.7246,
"step": 3340
},
{
"epoch": 0.669,
"grad_norm": 163.65704345703125,
"learning_rate": 5.9709356428633746e-05,
"loss": 824.4993,
"step": 3345
},
{
"epoch": 0.67,
"grad_norm": 156.68556213378906,
"learning_rate": 5.9390123103574215e-05,
"loss": 819.0005,
"step": 3350
},
{
"epoch": 0.671,
"grad_norm": 228.06988525390625,
"learning_rate": 5.907138459704895e-05,
"loss": 862.8385,
"step": 3355
},
{
"epoch": 0.672,
"grad_norm": 145.85723876953125,
"learning_rate": 5.8753144792786096e-05,
"loss": 821.917,
"step": 3360
},
{
"epoch": 0.673,
"grad_norm": 184.79037475585938,
"learning_rate": 5.8435407568437216e-05,
"loss": 834.9686,
"step": 3365
},
{
"epoch": 0.674,
"grad_norm": 377.11590576171875,
"learning_rate": 5.8118176795530176e-05,
"loss": 843.2138,
"step": 3370
},
{
"epoch": 0.675,
"grad_norm": 212.89569091796875,
"learning_rate": 5.780145633942173e-05,
"loss": 825.5447,
"step": 3375
},
{
"epoch": 0.676,
"grad_norm": 193.37506103515625,
"learning_rate": 5.748525005925074e-05,
"loss": 836.8977,
"step": 3380
},
{
"epoch": 0.677,
"grad_norm": 172.0506134033203,
"learning_rate": 5.716956180789098e-05,
"loss": 851.2486,
"step": 3385
},
{
"epoch": 0.678,
"grad_norm": 163.49945068359375,
"learning_rate": 5.6854395431904094e-05,
"loss": 831.5011,
"step": 3390
},
{
"epoch": 0.679,
"grad_norm": 155.61534118652344,
"learning_rate": 5.653975477149298e-05,
"loss": 810.1409,
"step": 3395
},
{
"epoch": 0.68,
"grad_norm": 171.41111755371094,
"learning_rate": 5.622564366045472e-05,
"loss": 806.0254,
"step": 3400
},
{
"epoch": 0.681,
"grad_norm": 167.66603088378906,
"learning_rate": 5.591206592613416e-05,
"loss": 847.7459,
"step": 3405
},
{
"epoch": 0.682,
"grad_norm": 170.98443603515625,
"learning_rate": 5.5599025389376935e-05,
"loss": 827.1237,
"step": 3410
},
{
"epoch": 0.683,
"grad_norm": 163.09613037109375,
"learning_rate": 5.5286525864483285e-05,
"loss": 837.8238,
"step": 3415
},
{
"epoch": 0.684,
"grad_norm": 195.7082061767578,
"learning_rate": 5.497457115916127e-05,
"loss": 822.1993,
"step": 3420
},
{
"epoch": 0.685,
"grad_norm": 150.1494598388672,
"learning_rate": 5.466316507448048e-05,
"loss": 822.4528,
"step": 3425
},
{
"epoch": 0.686,
"grad_norm": 165.59104919433594,
"learning_rate": 5.435231140482587e-05,
"loss": 828.4628,
"step": 3430
},
{
"epoch": 0.687,
"grad_norm": 158.3415985107422,
"learning_rate": 5.404201393785122e-05,
"loss": 841.0097,
"step": 3435
},
{
"epoch": 0.688,
"grad_norm": 239.25967407226562,
"learning_rate": 5.373227645443332e-05,
"loss": 827.506,
"step": 3440
},
{
"epoch": 0.689,
"grad_norm": 150.80775451660156,
"learning_rate": 5.3423102728625574e-05,
"loss": 820.2757,
"step": 3445
},
{
"epoch": 0.69,
"grad_norm": 161.40476989746094,
"learning_rate": 5.311449652761235e-05,
"loss": 854.3861,
"step": 3450
},
{
"epoch": 0.691,
"grad_norm": 187.94578552246094,
"learning_rate": 5.2806461611662735e-05,
"loss": 843.8693,
"step": 3455
},
{
"epoch": 0.692,
"grad_norm": 191.099853515625,
"learning_rate": 5.2499001734085044e-05,
"loss": 904.5116,
"step": 3460
},
{
"epoch": 0.693,
"grad_norm": 249.60235595703125,
"learning_rate": 5.2192120641180786e-05,
"loss": 831.1794,
"step": 3465
},
{
"epoch": 0.694,
"grad_norm": 205.0454864501953,
"learning_rate": 5.188582207219931e-05,
"loss": 849.2126,
"step": 3470
},
{
"epoch": 0.695,
"grad_norm": 187.80517578125,
"learning_rate": 5.158010975929193e-05,
"loss": 838.8146,
"step": 3475
},
{
"epoch": 0.696,
"grad_norm": 175.30050659179688,
"learning_rate": 5.127498742746675e-05,
"loss": 835.0662,
"step": 3480
},
{
"epoch": 0.697,
"grad_norm": 646.1378173828125,
"learning_rate": 5.097045879454313e-05,
"loss": 866.6721,
"step": 3485
},
{
"epoch": 0.698,
"grad_norm": 173.72032165527344,
"learning_rate": 5.066652757110628e-05,
"loss": 829.3619,
"step": 3490
},
{
"epoch": 0.699,
"grad_norm": 187.02671813964844,
"learning_rate": 5.036319746046232e-05,
"loss": 846.8831,
"step": 3495
},
{
"epoch": 0.7,
"grad_norm": 180.11883544921875,
"learning_rate": 5.006047215859289e-05,
"loss": 802.9071,
"step": 3500
},
{
"epoch": 0.701,
"grad_norm": 261.693115234375,
"learning_rate": 4.97583553541102e-05,
"loss": 840.5458,
"step": 3505
},
{
"epoch": 0.702,
"grad_norm": 179.55819702148438,
"learning_rate": 4.945685072821227e-05,
"loss": 841.7169,
"step": 3510
},
{
"epoch": 0.703,
"grad_norm": 187.09844970703125,
"learning_rate": 4.915596195463773e-05,
"loss": 813.579,
"step": 3515
},
{
"epoch": 0.704,
"grad_norm": 315.7233581542969,
"learning_rate": 4.885569269962142e-05,
"loss": 842.7813,
"step": 3520
},
{
"epoch": 0.705,
"grad_norm": 285.4256896972656,
"learning_rate": 4.8556046621849346e-05,
"loss": 852.6779,
"step": 3525
},
{
"epoch": 0.706,
"grad_norm": 153.60548400878906,
"learning_rate": 4.825702737241452e-05,
"loss": 965.3455,
"step": 3530
},
{
"epoch": 0.707,
"grad_norm": 282.6001892089844,
"learning_rate": 4.7958638594772064e-05,
"loss": 827.8323,
"step": 3535
},
{
"epoch": 0.708,
"grad_norm": 552.1526489257812,
"learning_rate": 4.766088392469506e-05,
"loss": 897.2234,
"step": 3540
},
{
"epoch": 0.709,
"grad_norm": 277.0527648925781,
"learning_rate": 4.736376699023023e-05,
"loss": 867.8769,
"step": 3545
},
{
"epoch": 0.71,
"grad_norm": 183.481201171875,
"learning_rate": 4.706729141165361e-05,
"loss": 814.3304,
"step": 3550
},
{
"epoch": 0.711,
"grad_norm": 167.50672912597656,
"learning_rate": 4.6771460801426635e-05,
"loss": 818.502,
"step": 3555
},
{
"epoch": 0.712,
"grad_norm": 188.61032104492188,
"learning_rate": 4.647627876415186e-05,
"loss": 826.1941,
"step": 3560
},
{
"epoch": 0.713,
"grad_norm": 287.95758056640625,
"learning_rate": 4.6181748896529273e-05,
"loss": 839.3263,
"step": 3565
},
{
"epoch": 0.714,
"grad_norm": 144.6120147705078,
"learning_rate": 4.588787478731242e-05,
"loss": 846.2146,
"step": 3570
},
{
"epoch": 0.715,
"grad_norm": 190.93946838378906,
"learning_rate": 4.559466001726451e-05,
"loss": 825.4708,
"step": 3575
},
{
"epoch": 0.716,
"grad_norm": 165.2403106689453,
"learning_rate": 4.530210815911504e-05,
"loss": 813.6226,
"step": 3580
},
{
"epoch": 0.717,
"grad_norm": 139.42828369140625,
"learning_rate": 4.501022277751602e-05,
"loss": 822.2021,
"step": 3585
},
{
"epoch": 0.718,
"grad_norm": 156.0709991455078,
"learning_rate": 4.471900742899876e-05,
"loss": 831.8678,
"step": 3590
},
{
"epoch": 0.719,
"grad_norm": 173.2205047607422,
"learning_rate": 4.4428465661930343e-05,
"loss": 809.273,
"step": 3595
},
{
"epoch": 0.72,
"grad_norm": 167.11412048339844,
"learning_rate": 4.413860101647055e-05,
"loss": 845.0512,
"step": 3600
},
{
"epoch": 0.721,
"grad_norm": 165.02774047851562,
"learning_rate": 4.3849417024528564e-05,
"loss": 880.6978,
"step": 3605
},
{
"epoch": 0.722,
"grad_norm": 173.11236572265625,
"learning_rate": 4.356091720972011e-05,
"loss": 827.9276,
"step": 3610
},
{
"epoch": 0.723,
"grad_norm": 241.18252563476562,
"learning_rate": 4.327310508732437e-05,
"loss": 831.6043,
"step": 3615
},
{
"epoch": 0.724,
"grad_norm": 189.077392578125,
"learning_rate": 4.29859841642412e-05,
"loss": 841.8475,
"step": 3620
},
{
"epoch": 0.725,
"grad_norm": 183.71636962890625,
"learning_rate": 4.26995579389485e-05,
"loss": 844.9749,
"step": 3625
},
{
"epoch": 0.726,
"grad_norm": 197.54388427734375,
"learning_rate": 4.2413829901459344e-05,
"loss": 897.3824,
"step": 3630
},
{
"epoch": 0.727,
"grad_norm": 185.13418579101562,
"learning_rate": 4.212880353327979e-05,
"loss": 802.725,
"step": 3635
},
{
"epoch": 0.728,
"grad_norm": 211.5841522216797,
"learning_rate": 4.184448230736613e-05,
"loss": 834.2378,
"step": 3640
},
{
"epoch": 0.729,
"grad_norm": 163.61923217773438,
"learning_rate": 4.15608696880828e-05,
"loss": 836.1257,
"step": 3645
},
{
"epoch": 0.73,
"grad_norm": 167.6706085205078,
"learning_rate": 4.1277969131160045e-05,
"loss": 832.4568,
"step": 3650
},
{
"epoch": 0.731,
"grad_norm": 206.24961853027344,
"learning_rate": 4.099578408365191e-05,
"loss": 811.0208,
"step": 3655
},
{
"epoch": 0.732,
"grad_norm": 162.81881713867188,
"learning_rate": 4.071431798389408e-05,
"loss": 813.4133,
"step": 3660
},
{
"epoch": 0.733,
"grad_norm": 185.35714721679688,
"learning_rate": 4.0433574261462206e-05,
"loss": 803.7883,
"step": 3665
},
{
"epoch": 0.734,
"grad_norm": 145.22793579101562,
"learning_rate": 4.015355633712996e-05,
"loss": 817.8212,
"step": 3670
},
{
"epoch": 0.735,
"grad_norm": 181.67274475097656,
"learning_rate": 3.987426762282733e-05,
"loss": 821.5995,
"step": 3675
},
{
"epoch": 0.736,
"grad_norm": 149.40306091308594,
"learning_rate": 3.9595711521599224e-05,
"loss": 818.9462,
"step": 3680
},
{
"epoch": 0.737,
"grad_norm": 157.6987762451172,
"learning_rate": 3.931789142756377e-05,
"loss": 827.0548,
"step": 3685
},
{
"epoch": 0.738,
"grad_norm": 152.69866943359375,
"learning_rate": 3.904081072587119e-05,
"loss": 824.3227,
"step": 3690
},
{
"epoch": 0.739,
"grad_norm": 156.4852752685547,
"learning_rate": 3.876447279266238e-05,
"loss": 833.6684,
"step": 3695
},
{
"epoch": 0.74,
"grad_norm": 180.8666229248047,
"learning_rate": 3.8488880995027786e-05,
"loss": 832.709,
"step": 3700
},
{
"epoch": 0.741,
"grad_norm": 187.2139892578125,
"learning_rate": 3.821403869096658e-05,
"loss": 813.0282,
"step": 3705
},
{
"epoch": 0.742,
"grad_norm": 218.80923461914062,
"learning_rate": 3.793994922934544e-05,
"loss": 809.1613,
"step": 3710
},
{
"epoch": 0.743,
"grad_norm": 171.41195678710938,
"learning_rate": 3.766661594985801e-05,
"loss": 808.8602,
"step": 3715
},
{
"epoch": 0.744,
"grad_norm": 263.1960144042969,
"learning_rate": 3.739404218298398e-05,
"loss": 852.9854,
"step": 3720
},
{
"epoch": 0.745,
"grad_norm": 154.79232788085938,
"learning_rate": 3.712223124994875e-05,
"loss": 836.9613,
"step": 3725
},
{
"epoch": 0.746,
"grad_norm": 170.7035675048828,
"learning_rate": 3.685118646268272e-05,
"loss": 847.7803,
"step": 3730
},
{
"epoch": 0.747,
"grad_norm": 372.16973876953125,
"learning_rate": 3.6580911123781056e-05,
"loss": 872.5756,
"step": 3735
},
{
"epoch": 0.748,
"grad_norm": 188.24618530273438,
"learning_rate": 3.631140852646355e-05,
"loss": 835.7386,
"step": 3740
},
{
"epoch": 0.749,
"grad_norm": 177.70042419433594,
"learning_rate": 3.604268195453421e-05,
"loss": 832.6261,
"step": 3745
},
{
"epoch": 0.75,
"grad_norm": 159.23385620117188,
"learning_rate": 3.577473468234156e-05,
"loss": 835.6718,
"step": 3750
},
{
"epoch": 0.751,
"grad_norm": 190.92835998535156,
"learning_rate": 3.5507569974738574e-05,
"loss": 832.225,
"step": 3755
},
{
"epoch": 0.752,
"grad_norm": 181.1046142578125,
"learning_rate": 3.524119108704286e-05,
"loss": 823.9772,
"step": 3760
},
{
"epoch": 0.753,
"grad_norm": 150.6414794921875,
"learning_rate": 3.497560126499709e-05,
"loss": 821.5393,
"step": 3765
},
{
"epoch": 0.754,
"grad_norm": 186.4093017578125,
"learning_rate": 3.4710803744729515e-05,
"loss": 840.1177,
"step": 3770
},
{
"epoch": 0.755,
"grad_norm": 184.1460418701172,
"learning_rate": 3.444680175271428e-05,
"loss": 855.5023,
"step": 3775
},
{
"epoch": 0.756,
"grad_norm": 161.29299926757812,
"learning_rate": 3.418359850573234e-05,
"loss": 847.5938,
"step": 3780
},
{
"epoch": 0.757,
"grad_norm": 188.8201141357422,
"learning_rate": 3.3921197210832235e-05,
"loss": 835.7382,
"step": 3785
},
{
"epoch": 0.758,
"grad_norm": 165.71035766601562,
"learning_rate": 3.3659601065290893e-05,
"loss": 823.5226,
"step": 3790
},
{
"epoch": 0.759,
"grad_norm": 159.93692016601562,
"learning_rate": 3.339881325657484e-05,
"loss": 823.8916,
"step": 3795
},
{
"epoch": 0.76,
"grad_norm": 160.29820251464844,
"learning_rate": 3.313883696230119e-05,
"loss": 807.8741,
"step": 3800
},
{
"epoch": 0.761,
"grad_norm": 174.91749572753906,
"learning_rate": 3.287967535019908e-05,
"loss": 842.6376,
"step": 3805
},
{
"epoch": 0.762,
"grad_norm": 160.27154541015625,
"learning_rate": 3.2621331578070934e-05,
"loss": 815.4893,
"step": 3810
},
{
"epoch": 0.763,
"grad_norm": 199.35694885253906,
"learning_rate": 3.236380879375408e-05,
"loss": 810.4059,
"step": 3815
},
{
"epoch": 0.764,
"grad_norm": 169.80209350585938,
"learning_rate": 3.210711013508242e-05,
"loss": 841.3033,
"step": 3820
},
{
"epoch": 0.765,
"grad_norm": 151.818115234375,
"learning_rate": 3.1851238729848034e-05,
"loss": 849.0903,
"step": 3825
},
{
"epoch": 0.766,
"grad_norm": 706.8538208007812,
"learning_rate": 3.159619769576333e-05,
"loss": 853.5063,
"step": 3830
},
{
"epoch": 0.767,
"grad_norm": 163.5894775390625,
"learning_rate": 3.134199014042274e-05,
"loss": 825.7124,
"step": 3835
},
{
"epoch": 0.768,
"grad_norm": 187.44241333007812,
"learning_rate": 3.108861916126518e-05,
"loss": 826.6904,
"step": 3840
},
{
"epoch": 0.769,
"grad_norm": 155.9772186279297,
"learning_rate": 3.0836087845536e-05,
"loss": 802.2458,
"step": 3845
},
{
"epoch": 0.77,
"grad_norm": 151.75833129882812,
"learning_rate": 3.058439927024962e-05,
"loss": 808.8752,
"step": 3850
},
{
"epoch": 0.771,
"grad_norm": 179.33641052246094,
"learning_rate": 3.0333556502151926e-05,
"loss": 837.8887,
"step": 3855
},
{
"epoch": 0.772,
"grad_norm": 186.0498504638672,
"learning_rate": 3.0083562597682847e-05,
"loss": 821.6766,
"step": 3860
},
{
"epoch": 0.773,
"grad_norm": 190.3414764404297,
"learning_rate": 2.9834420602939263e-05,
"loss": 818.5714,
"step": 3865
},
{
"epoch": 0.774,
"grad_norm": 160.43333435058594,
"learning_rate": 2.9586133553637683e-05,
"loss": 839.2374,
"step": 3870
},
{
"epoch": 0.775,
"grad_norm": 173.05870056152344,
"learning_rate": 2.933870447507753e-05,
"loss": 811.9852,
"step": 3875
},
{
"epoch": 0.776,
"grad_norm": 160.53541564941406,
"learning_rate": 2.9092136382103973e-05,
"loss": 823.8334,
"step": 3880
},
{
"epoch": 0.777,
"grad_norm": 144.64414978027344,
"learning_rate": 2.8846432279071467e-05,
"loss": 809.7136,
"step": 3885
},
{
"epoch": 0.778,
"grad_norm": 208.7626190185547,
"learning_rate": 2.860159515980695e-05,
"loss": 847.9287,
"step": 3890
},
{
"epoch": 0.779,
"grad_norm": 197.5725860595703,
"learning_rate": 2.835762800757341e-05,
"loss": 837.8223,
"step": 3895
},
{
"epoch": 0.78,
"grad_norm": 224.62864685058594,
"learning_rate": 2.8114533795033683e-05,
"loss": 806.8575,
"step": 3900
},
{
"epoch": 0.781,
"grad_norm": 266.3263854980469,
"learning_rate": 2.7872315484213952e-05,
"loss": 788.8047,
"step": 3905
},
{
"epoch": 0.782,
"grad_norm": 161.09571838378906,
"learning_rate": 2.7630976026467968e-05,
"loss": 810.4803,
"step": 3910
},
{
"epoch": 0.783,
"grad_norm": 393.39520263671875,
"learning_rate": 2.7390518362440808e-05,
"loss": 839.1063,
"step": 3915
},
{
"epoch": 0.784,
"grad_norm": 184.70999145507812,
"learning_rate": 2.715094542203327e-05,
"loss": 841.5317,
"step": 3920
},
{
"epoch": 0.785,
"grad_norm": 175.04495239257812,
"learning_rate": 2.6912260124366006e-05,
"loss": 844.2166,
"step": 3925
},
{
"epoch": 0.786,
"grad_norm": 173.22146606445312,
"learning_rate": 2.6674465377744017e-05,
"loss": 825.1905,
"step": 3930
},
{
"epoch": 0.787,
"grad_norm": 163.3852081298828,
"learning_rate": 2.6437564079621267e-05,
"loss": 829.5522,
"step": 3935
},
{
"epoch": 0.788,
"grad_norm": 174.34063720703125,
"learning_rate": 2.6201559116565345e-05,
"loss": 841.8118,
"step": 3940
},
{
"epoch": 0.789,
"grad_norm": 170.45120239257812,
"learning_rate": 2.5966453364222186e-05,
"loss": 822.4509,
"step": 3945
},
{
"epoch": 0.79,
"grad_norm": 193.31787109375,
"learning_rate": 2.573224968728123e-05,
"loss": 825.9681,
"step": 3950
},
{
"epoch": 0.791,
"grad_norm": 162.05215454101562,
"learning_rate": 2.549895093944039e-05,
"loss": 842.7674,
"step": 3955
},
{
"epoch": 0.792,
"grad_norm": 158.86866760253906,
"learning_rate": 2.5266559963371216e-05,
"loss": 802.8705,
"step": 3960
},
{
"epoch": 0.793,
"grad_norm": 157.63226318359375,
"learning_rate": 2.5035079590684497e-05,
"loss": 813.0919,
"step": 3965
},
{
"epoch": 0.794,
"grad_norm": 189.8999786376953,
"learning_rate": 2.480451264189546e-05,
"loss": 825.2505,
"step": 3970
},
{
"epoch": 0.795,
"grad_norm": 162.4189453125,
"learning_rate": 2.4574861926389615e-05,
"loss": 821.5019,
"step": 3975
},
{
"epoch": 0.796,
"grad_norm": 182.46099853515625,
"learning_rate": 2.43461302423885e-05,
"loss": 852.5521,
"step": 3980
},
{
"epoch": 0.797,
"grad_norm": 194.37109375,
"learning_rate": 2.411832037691545e-05,
"loss": 864.261,
"step": 3985
},
{
"epoch": 0.798,
"grad_norm": 164.24978637695312,
"learning_rate": 2.389143510576184e-05,
"loss": 818.7509,
"step": 3990
},
{
"epoch": 0.799,
"grad_norm": 192.30813598632812,
"learning_rate": 2.3665477193453034e-05,
"loss": 827.6118,
"step": 3995
},
{
"epoch": 0.8,
"grad_norm": 151.38917541503906,
"learning_rate": 2.3440449393214948e-05,
"loss": 792.9098,
"step": 4000
},
{
"epoch": 0.801,
"grad_norm": 268.562744140625,
"learning_rate": 2.321635444694028e-05,
"loss": 809.3757,
"step": 4005
},
{
"epoch": 0.802,
"grad_norm": 213.591064453125,
"learning_rate": 2.2993195085155205e-05,
"loss": 832.9626,
"step": 4010
},
{
"epoch": 0.803,
"grad_norm": 185.75546264648438,
"learning_rate": 2.277097402698619e-05,
"loss": 813.362,
"step": 4015
},
{
"epoch": 0.804,
"grad_norm": 220.29612731933594,
"learning_rate": 2.254969398012663e-05,
"loss": 834.2664,
"step": 4020
},
{
"epoch": 0.805,
"grad_norm": 176.3155059814453,
"learning_rate": 2.2329357640804117e-05,
"loss": 833.2977,
"step": 4025
},
{
"epoch": 0.806,
"grad_norm": 156.5010223388672,
"learning_rate": 2.210996769374737e-05,
"loss": 846.0734,
"step": 4030
},
{
"epoch": 0.807,
"grad_norm": 152.3187713623047,
"learning_rate": 2.1891526812153672e-05,
"loss": 809.9341,
"step": 4035
},
{
"epoch": 0.808,
"grad_norm": 166.04559326171875,
"learning_rate": 2.1674037657656266e-05,
"loss": 829.5463,
"step": 4040
},
{
"epoch": 0.809,
"grad_norm": 165.9083709716797,
"learning_rate": 2.1457502880291812e-05,
"loss": 814.9198,
"step": 4045
},
{
"epoch": 0.81,
"grad_norm": 160.3354034423828,
"learning_rate": 2.1241925118468287e-05,
"loss": 820.7165,
"step": 4050
},
{
"epoch": 0.811,
"grad_norm": 167.6192626953125,
"learning_rate": 2.1027306998932627e-05,
"loss": 829.3275,
"step": 4055
},
{
"epoch": 0.812,
"grad_norm": 142.8562469482422,
"learning_rate": 2.0813651136738954e-05,
"loss": 807.2986,
"step": 4060
},
{
"epoch": 0.813,
"grad_norm": 165.8729248046875,
"learning_rate": 2.0600960135216462e-05,
"loss": 829.0283,
"step": 4065
},
{
"epoch": 0.814,
"grad_norm": 166.341552734375,
"learning_rate": 2.0389236585937945e-05,
"loss": 818.6373,
"step": 4070
},
{
"epoch": 0.815,
"grad_norm": 147.79537963867188,
"learning_rate": 2.017848306868797e-05,
"loss": 810.4259,
"step": 4075
},
{
"epoch": 0.816,
"grad_norm": 168.47686767578125,
"learning_rate": 1.9968702151431696e-05,
"loss": 824.7432,
"step": 4080
},
{
"epoch": 0.817,
"grad_norm": 164.18496704101562,
"learning_rate": 1.9759896390283362e-05,
"loss": 814.6573,
"step": 4085
},
{
"epoch": 0.818,
"grad_norm": 202.83558654785156,
"learning_rate": 1.955206832947526e-05,
"loss": 829.0407,
"step": 4090
},
{
"epoch": 0.819,
"grad_norm": 165.85816955566406,
"learning_rate": 1.9345220501326777e-05,
"loss": 842.8767,
"step": 4095
},
{
"epoch": 0.82,
"grad_norm": 175.4813232421875,
"learning_rate": 1.9139355426213347e-05,
"loss": 785.6057,
"step": 4100
},
{
"epoch": 0.821,
"grad_norm": 153.1288299560547,
"learning_rate": 1.8934475612536017e-05,
"loss": 810.2104,
"step": 4105
},
{
"epoch": 0.822,
"grad_norm": 152.03030395507812,
"learning_rate": 1.8730583556690605e-05,
"loss": 803.0228,
"step": 4110
},
{
"epoch": 0.823,
"grad_norm": 157.3311004638672,
"learning_rate": 1.852768174303752e-05,
"loss": 831.3484,
"step": 4115
},
{
"epoch": 0.824,
"grad_norm": 264.9814758300781,
"learning_rate": 1.8325772643871265e-05,
"loss": 825.5386,
"step": 4120
},
{
"epoch": 0.825,
"grad_norm": 165.8664093017578,
"learning_rate": 1.812485871939056e-05,
"loss": 844.349,
"step": 4125
},
{
"epoch": 0.826,
"grad_norm": 165.5538787841797,
"learning_rate": 1.792494241766811e-05,
"loss": 831.5804,
"step": 4130
},
{
"epoch": 0.827,
"grad_norm": 190.30157470703125,
"learning_rate": 1.7726026174621003e-05,
"loss": 814.9881,
"step": 4135
},
{
"epoch": 0.828,
"grad_norm": 180.5849151611328,
"learning_rate": 1.752811241398089e-05,
"loss": 821.3646,
"step": 4140
},
{
"epoch": 0.829,
"grad_norm": 155.110107421875,
"learning_rate": 1.7331203547264453e-05,
"loss": 842.2369,
"step": 4145
},
{
"epoch": 0.83,
"grad_norm": 164.41519165039062,
"learning_rate": 1.7135301973744124e-05,
"loss": 815.9298,
"step": 4150
},
{
"epoch": 0.831,
"grad_norm": 232.93336486816406,
"learning_rate": 1.6940410080418723e-05,
"loss": 831.4393,
"step": 4155
},
{
"epoch": 0.832,
"grad_norm": 160.31639099121094,
"learning_rate": 1.6746530241984504e-05,
"loss": 789.7336,
"step": 4160
},
{
"epoch": 0.833,
"grad_norm": 134.45037841796875,
"learning_rate": 1.6553664820806102e-05,
"loss": 807.274,
"step": 4165
},
{
"epoch": 0.834,
"grad_norm": 162.50738525390625,
"learning_rate": 1.6361816166887768e-05,
"loss": 826.2143,
"step": 4170
},
{
"epoch": 0.835,
"grad_norm": 218.41229248046875,
"learning_rate": 1.6170986617844863e-05,
"loss": 816.0254,
"step": 4175
},
{
"epoch": 0.836,
"grad_norm": 132.81663513183594,
"learning_rate": 1.598117849887518e-05,
"loss": 818.0706,
"step": 4180
},
{
"epoch": 0.837,
"grad_norm": 219.66366577148438,
"learning_rate": 1.579239412273078e-05,
"loss": 833.8011,
"step": 4185
},
{
"epoch": 0.838,
"grad_norm": 159.22406005859375,
"learning_rate": 1.560463578968967e-05,
"loss": 830.5652,
"step": 4190
},
{
"epoch": 0.839,
"grad_norm": 148.52362060546875,
"learning_rate": 1.541790578752794e-05,
"loss": 802.296,
"step": 4195
},
{
"epoch": 0.84,
"grad_norm": 185.96881103515625,
"learning_rate": 1.5232206391491699e-05,
"loss": 836.1291,
"step": 4200
},
{
"epoch": 0.841,
"grad_norm": 148.203369140625,
"learning_rate": 1.5047539864269478e-05,
"loss": 829.3544,
"step": 4205
},
{
"epoch": 0.842,
"grad_norm": 267.35455322265625,
"learning_rate": 1.486390845596466e-05,
"loss": 845.7994,
"step": 4210
},
{
"epoch": 0.843,
"grad_norm": 149.257568359375,
"learning_rate": 1.468131440406798e-05,
"loss": 826.6091,
"step": 4215
},
{
"epoch": 0.844,
"grad_norm": 181.48008728027344,
"learning_rate": 1.4499759933430346e-05,
"loss": 826.3685,
"step": 4220
},
{
"epoch": 0.845,
"grad_norm": 166.0313720703125,
"learning_rate": 1.4319247256235714e-05,
"loss": 803.8119,
"step": 4225
},
{
"epoch": 0.846,
"grad_norm": 200.03123474121094,
"learning_rate": 1.4139778571974049e-05,
"loss": 819.7854,
"step": 4230
},
{
"epoch": 0.847,
"grad_norm": 205.01365661621094,
"learning_rate": 1.3961356067414666e-05,
"loss": 802.1063,
"step": 4235
},
{
"epoch": 0.848,
"grad_norm": 189.55880737304688,
"learning_rate": 1.3783981916579446e-05,
"loss": 798.5604,
"step": 4240
},
{
"epoch": 0.849,
"grad_norm": 155.40597534179688,
"learning_rate": 1.3607658280716473e-05,
"loss": 845.5261,
"step": 4245
},
{
"epoch": 0.85,
"grad_norm": 147.583251953125,
"learning_rate": 1.3432387308273575e-05,
"loss": 814.0461,
"step": 4250
},
{
"epoch": 0.851,
"grad_norm": 162.8997802734375,
"learning_rate": 1.3258171134872265e-05,
"loss": 832.7277,
"step": 4255
},
{
"epoch": 0.852,
"grad_norm": 141.01824951171875,
"learning_rate": 1.3085011883281606e-05,
"loss": 779.9535,
"step": 4260
},
{
"epoch": 0.853,
"grad_norm": 142.87045288085938,
"learning_rate": 1.2912911663392469e-05,
"loss": 804.4996,
"step": 4265
},
{
"epoch": 0.854,
"grad_norm": 148.2899932861328,
"learning_rate": 1.2741872572191682e-05,
"loss": 865.1075,
"step": 4270
},
{
"epoch": 0.855,
"grad_norm": 149.4261016845703,
"learning_rate": 1.257189669373664e-05,
"loss": 819.4632,
"step": 4275
},
{
"epoch": 0.856,
"grad_norm": 147.55001831054688,
"learning_rate": 1.2402986099129765e-05,
"loss": 815.777,
"step": 4280
},
{
"epoch": 0.857,
"grad_norm": 151.38690185546875,
"learning_rate": 1.2235142846493308e-05,
"loss": 810.5693,
"step": 4285
},
{
"epoch": 0.858,
"grad_norm": 132.70278930664062,
"learning_rate": 1.206836898094439e-05,
"loss": 812.064,
"step": 4290
},
{
"epoch": 0.859,
"grad_norm": 175.10488891601562,
"learning_rate": 1.1902666534569883e-05,
"loss": 823.8109,
"step": 4295
},
{
"epoch": 0.86,
"grad_norm": 154.4387969970703,
"learning_rate": 1.1738037526401857e-05,
"loss": 840.7293,
"step": 4300
},
{
"epoch": 0.861,
"grad_norm": 163.52073669433594,
"learning_rate": 1.1574483962392767e-05,
"loss": 815.4345,
"step": 4305
},
{
"epoch": 0.862,
"grad_norm": 186.3319549560547,
"learning_rate": 1.1412007835391236e-05,
"loss": 828.5958,
"step": 4310
},
{
"epoch": 0.863,
"grad_norm": 172.6900177001953,
"learning_rate": 1.1250611125117527e-05,
"loss": 839.8334,
"step": 4315
},
{
"epoch": 0.864,
"grad_norm": 159.2743377685547,
"learning_rate": 1.1090295798139672e-05,
"loss": 861.3876,
"step": 4320
},
{
"epoch": 0.865,
"grad_norm": 149.8535919189453,
"learning_rate": 1.093106380784934e-05,
"loss": 808.7278,
"step": 4325
},
{
"epoch": 0.866,
"grad_norm": 219.28245544433594,
"learning_rate": 1.0772917094438051e-05,
"loss": 825.0284,
"step": 4330
},
{
"epoch": 0.867,
"grad_norm": 194.07716369628906,
"learning_rate": 1.0615857584873623e-05,
"loss": 823.1203,
"step": 4335
},
{
"epoch": 0.868,
"grad_norm": 152.9429168701172,
"learning_rate": 1.0459887192876594e-05,
"loss": 817.3022,
"step": 4340
},
{
"epoch": 0.869,
"grad_norm": 147.1473388671875,
"learning_rate": 1.0305007818897006e-05,
"loss": 825.8506,
"step": 4345
},
{
"epoch": 0.87,
"grad_norm": 164.50848388671875,
"learning_rate": 1.0151221350091134e-05,
"loss": 804.2999,
"step": 4350
},
{
"epoch": 0.871,
"grad_norm": 174.57861328125,
"learning_rate": 9.998529660298539e-06,
"loss": 795.8227,
"step": 4355
},
{
"epoch": 0.872,
"grad_norm": 160.61026000976562,
"learning_rate": 9.84693461001932e-06,
"loss": 822.601,
"step": 4360
},
{
"epoch": 0.873,
"grad_norm": 186.08636474609375,
"learning_rate": 9.696438046391288e-06,
"loss": 837.4211,
"step": 4365
},
{
"epoch": 0.874,
"grad_norm": 164.05355834960938,
"learning_rate": 9.5470418031676e-06,
"loss": 815.7881,
"step": 4370
},
{
"epoch": 0.875,
"grad_norm": 460.3487548828125,
"learning_rate": 9.398747700694322e-06,
"loss": 831.4762,
"step": 4375
},
{
"epoch": 0.876,
"grad_norm": 184.38632202148438,
"learning_rate": 9.251557545888312e-06,
"loss": 822.7251,
"step": 4380
},
{
"epoch": 0.877,
"grad_norm": 179.9202423095703,
"learning_rate": 9.105473132215125e-06,
"loss": 807.6312,
"step": 4385
},
{
"epoch": 0.878,
"grad_norm": 157.07420349121094,
"learning_rate": 8.960496239667282e-06,
"loss": 818.3611,
"step": 4390
},
{
"epoch": 0.879,
"grad_norm": 212.20059204101562,
"learning_rate": 8.816628634742441e-06,
"loss": 810.7883,
"step": 4395
},
{
"epoch": 0.88,
"grad_norm": 180.29074096679688,
"learning_rate": 8.67387207042194e-06,
"loss": 836.6943,
"step": 4400
},
{
"epoch": 0.881,
"grad_norm": 156.96832275390625,
"learning_rate": 8.532228286149501e-06,
"loss": 824.9143,
"step": 4405
},
{
"epoch": 0.882,
"grad_norm": 143.6281280517578,
"learning_rate": 8.39169900780995e-06,
"loss": 828.8754,
"step": 4410
},
{
"epoch": 0.883,
"grad_norm": 139.39044189453125,
"learning_rate": 8.252285947708139e-06,
"loss": 820.2086,
"step": 4415
},
{
"epoch": 0.884,
"grad_norm": 255.1716766357422,
"learning_rate": 8.113990804548244e-06,
"loss": 847.6983,
"step": 4420
},
{
"epoch": 0.885,
"grad_norm": 172.9536590576172,
"learning_rate": 7.976815263412963e-06,
"loss": 812.0037,
"step": 4425
},
{
"epoch": 0.886,
"grad_norm": 208.5325164794922,
"learning_rate": 7.840760995742946e-06,
"loss": 820.4124,
"step": 4430
},
{
"epoch": 0.887,
"grad_norm": 183.39390563964844,
"learning_rate": 7.7058296593165e-06,
"loss": 812.4181,
"step": 4435
},
{
"epoch": 0.888,
"grad_norm": 170.19125366210938,
"learning_rate": 7.572022898229403e-06,
"loss": 835.6829,
"step": 4440
},
{
"epoch": 0.889,
"grad_norm": 132.9561309814453,
"learning_rate": 7.439342342874789e-06,
"loss": 831.0935,
"step": 4445
},
{
"epoch": 0.89,
"grad_norm": 164.27333068847656,
"learning_rate": 7.3077896099233765e-06,
"loss": 801.2688,
"step": 4450
},
{
"epoch": 0.891,
"grad_norm": 186.7030792236328,
"learning_rate": 7.177366302303667e-06,
"loss": 817.3094,
"step": 4455
},
{
"epoch": 0.892,
"grad_norm": 226.6078338623047,
"learning_rate": 7.048074009182548e-06,
"loss": 857.6896,
"step": 4460
},
{
"epoch": 0.893,
"grad_norm": 155.87315368652344,
"learning_rate": 6.919914305945774e-06,
"loss": 792.5851,
"step": 4465
},
{
"epoch": 0.894,
"grad_norm": 166.4764862060547,
"learning_rate": 6.7928887541789055e-06,
"loss": 844.3668,
"step": 4470
},
{
"epoch": 0.895,
"grad_norm": 150.7865447998047,
"learning_rate": 6.666998901648203e-06,
"loss": 858.1795,
"step": 4475
},
{
"epoch": 0.896,
"grad_norm": 185.10494995117188,
"learning_rate": 6.542246282281772e-06,
"loss": 833.9468,
"step": 4480
},
{
"epoch": 0.897,
"grad_norm": 144.32440185546875,
"learning_rate": 6.418632416150927e-06,
"loss": 802.7703,
"step": 4485
},
{
"epoch": 0.898,
"grad_norm": 134.36404418945312,
"learning_rate": 6.296158809451602e-06,
"loss": 830.8499,
"step": 4490
},
{
"epoch": 0.899,
"grad_norm": 211.725830078125,
"learning_rate": 6.174826954486068e-06,
"loss": 843.7534,
"step": 4495
},
{
"epoch": 0.9,
"grad_norm": 144.10057067871094,
"learning_rate": 6.054638329644657e-06,
"loss": 794.4008,
"step": 4500
},
{
"epoch": 0.901,
"grad_norm": 194.78773498535156,
"learning_rate": 5.935594399387856e-06,
"loss": 832.2634,
"step": 4505
},
{
"epoch": 0.902,
"grad_norm": 197.158447265625,
"learning_rate": 5.8176966142283965e-06,
"loss": 801.228,
"step": 4510
},
{
"epoch": 0.903,
"grad_norm": 166.54376220703125,
"learning_rate": 5.700946410713548e-06,
"loss": 799.4511,
"step": 4515
},
{
"epoch": 0.904,
"grad_norm": 141.40403747558594,
"learning_rate": 5.585345211407733e-06,
"loss": 818.8427,
"step": 4520
},
{
"epoch": 0.905,
"grad_norm": 281.9321594238281,
"learning_rate": 5.470894424875062e-06,
"loss": 846.4567,
"step": 4525
},
{
"epoch": 0.906,
"grad_norm": 151.18963623046875,
"learning_rate": 5.357595445662267e-06,
"loss": 840.316,
"step": 4530
},
{
"epoch": 0.907,
"grad_norm": 143.24981689453125,
"learning_rate": 5.245449654281631e-06,
"loss": 816.4864,
"step": 4535
},
{
"epoch": 0.908,
"grad_norm": 147.96136474609375,
"learning_rate": 5.134458417194254e-06,
"loss": 821.8139,
"step": 4540
},
{
"epoch": 0.909,
"grad_norm": 200.25262451171875,
"learning_rate": 5.024623086793323e-06,
"loss": 835.5049,
"step": 4545
},
{
"epoch": 0.91,
"grad_norm": 150.36900329589844,
"learning_rate": 4.915945001387667e-06,
"loss": 829.5826,
"step": 4550
},
{
"epoch": 0.911,
"grad_norm": 149.1263427734375,
"learning_rate": 4.808425485185486e-06,
"loss": 834.8281,
"step": 4555
},
{
"epoch": 0.912,
"grad_norm": 241.9333038330078,
"learning_rate": 4.702065848278126e-06,
"loss": 846.3979,
"step": 4560
},
{
"epoch": 0.913,
"grad_norm": 161.45513916015625,
"learning_rate": 4.596867386624215e-06,
"loss": 812.6189,
"step": 4565
},
{
"epoch": 0.914,
"grad_norm": 272.3618469238281,
"learning_rate": 4.492831382033791e-06,
"loss": 854.2891,
"step": 4570
},
{
"epoch": 0.915,
"grad_norm": 140.44573974609375,
"learning_rate": 4.389959102152774e-06,
"loss": 825.1257,
"step": 4575
},
{
"epoch": 0.916,
"grad_norm": 189.04844665527344,
"learning_rate": 4.288251800447385e-06,
"loss": 815.8679,
"step": 4580
},
{
"epoch": 0.917,
"grad_norm": 175.9573211669922,
"learning_rate": 4.187710716189042e-06,
"loss": 830.1973,
"step": 4585
},
{
"epoch": 0.918,
"grad_norm": 144.702880859375,
"learning_rate": 4.088337074439097e-06,
"loss": 817.3748,
"step": 4590
},
{
"epoch": 0.919,
"grad_norm": 179.07887268066406,
"learning_rate": 3.990132086034026e-06,
"loss": 792.1403,
"step": 4595
},
{
"epoch": 0.92,
"grad_norm": 259.09185791015625,
"learning_rate": 3.893096947570618e-06,
"loss": 825.2243,
"step": 4600
},
{
"epoch": 0.921,
"grad_norm": 178.89744567871094,
"learning_rate": 3.797232841391407e-06,
"loss": 810.3354,
"step": 4605
},
{
"epoch": 0.922,
"grad_norm": 138.10081481933594,
"learning_rate": 3.7025409355702976e-06,
"loss": 814.2742,
"step": 4610
},
{
"epoch": 0.923,
"grad_norm": 209.85922241210938,
"learning_rate": 3.6090223838982417e-06,
"loss": 833.0231,
"step": 4615
},
{
"epoch": 0.924,
"grad_norm": 142.18609619140625,
"learning_rate": 3.516678325869316e-06,
"loss": 820.892,
"step": 4620
},
{
"epoch": 0.925,
"grad_norm": 192.4384002685547,
"learning_rate": 3.425509886666711e-06,
"loss": 803.0066,
"step": 4625
},
{
"epoch": 0.926,
"grad_norm": 168.78675842285156,
"learning_rate": 3.3355181771490772e-06,
"loss": 804.5506,
"step": 4630
},
{
"epoch": 0.927,
"grad_norm": 170.886962890625,
"learning_rate": 3.246704293837011e-06,
"loss": 823.0868,
"step": 4635
},
{
"epoch": 0.928,
"grad_norm": 238.86241149902344,
"learning_rate": 3.1590693188996323e-06,
"loss": 798.7037,
"step": 4640
},
{
"epoch": 0.929,
"grad_norm": 167.5196075439453,
"learning_rate": 3.072614320141487e-06,
"loss": 794.8482,
"step": 4645
},
{
"epoch": 0.93,
"grad_norm": 167.90846252441406,
"learning_rate": 2.9873403509894203e-06,
"loss": 829.4581,
"step": 4650
},
{
"epoch": 0.931,
"grad_norm": 151.90879821777344,
"learning_rate": 2.9032484504798452e-06,
"loss": 827.0729,
"step": 4655
},
{
"epoch": 0.932,
"grad_norm": 136.2193145751953,
"learning_rate": 2.8203396432460506e-06,
"loss": 786.7301,
"step": 4660
},
{
"epoch": 0.933,
"grad_norm": 148.20098876953125,
"learning_rate": 2.738614939505646e-06,
"loss": 823.6492,
"step": 4665
},
{
"epoch": 0.934,
"grad_norm": 203.78973388671875,
"learning_rate": 2.6580753350484046e-06,
"loss": 808.0218,
"step": 4670
},
{
"epoch": 0.935,
"grad_norm": 155.33274841308594,
"learning_rate": 2.5787218112239496e-06,
"loss": 800.6808,
"step": 4675
},
{
"epoch": 0.936,
"grad_norm": 205.0608673095703,
"learning_rate": 2.5005553349299547e-06,
"loss": 831.8427,
"step": 4680
},
{
"epoch": 0.937,
"grad_norm": 147.56495666503906,
"learning_rate": 2.4235768586002517e-06,
"loss": 815.3526,
"step": 4685
},
{
"epoch": 0.938,
"grad_norm": 152.44374084472656,
"learning_rate": 2.3477873201932734e-06,
"loss": 817.2921,
"step": 4690
},
{
"epoch": 0.939,
"grad_norm": 154.4458465576172,
"learning_rate": 2.273187643180652e-06,
"loss": 800.2947,
"step": 4695
},
{
"epoch": 0.94,
"grad_norm": 159.09095764160156,
"learning_rate": 2.1997787365358958e-06,
"loss": 831.3467,
"step": 4700
},
{
"epoch": 0.941,
"grad_norm": 167.7750244140625,
"learning_rate": 2.1275614947233624e-06,
"loss": 806.6193,
"step": 4705
},
{
"epoch": 0.942,
"grad_norm": 141.71629333496094,
"learning_rate": 2.0565367976873584e-06,
"loss": 827.8622,
"step": 4710
},
{
"epoch": 0.943,
"grad_norm": 159.79388427734375,
"learning_rate": 1.986705510841402e-06,
"loss": 819.0367,
"step": 4715
},
{
"epoch": 0.944,
"grad_norm": 139.17254638671875,
"learning_rate": 1.918068485057689e-06,
"loss": 813.1224,
"step": 4720
},
{
"epoch": 0.945,
"grad_norm": 168.83607482910156,
"learning_rate": 1.8506265566567094e-06,
"loss": 824.8682,
"step": 4725
},
{
"epoch": 0.946,
"grad_norm": 246.98583984375,
"learning_rate": 1.7843805473970798e-06,
"loss": 855.1469,
"step": 4730
},
{
"epoch": 0.947,
"grad_norm": 175.99917602539062,
"learning_rate": 1.719331264465529e-06,
"loss": 834.5853,
"step": 4735
},
{
"epoch": 0.948,
"grad_norm": 183.69479370117188,
"learning_rate": 1.6554795004670388e-06,
"loss": 826.5273,
"step": 4740
},
{
"epoch": 0.949,
"grad_norm": 286.907958984375,
"learning_rate": 1.5928260334151845e-06,
"loss": 848.4817,
"step": 4745
},
{
"epoch": 0.95,
"grad_norm": 243.87196350097656,
"learning_rate": 1.5313716267226996e-06,
"loss": 852.8782,
"step": 4750
},
{
"epoch": 0.951,
"grad_norm": 153.57398986816406,
"learning_rate": 1.4711170291921484e-06,
"loss": 824.005,
"step": 4755
},
{
"epoch": 0.952,
"grad_norm": 149.03909301757812,
"learning_rate": 1.412062975006767e-06,
"loss": 811.1326,
"step": 4760
},
{
"epoch": 0.953,
"grad_norm": 179.749267578125,
"learning_rate": 1.3542101837215826e-06,
"loss": 845.0927,
"step": 4765
},
{
"epoch": 0.954,
"grad_norm": 286.92999267578125,
"learning_rate": 1.2975593602545965e-06,
"loss": 858.6895,
"step": 4770
},
{
"epoch": 0.955,
"grad_norm": 179.12916564941406,
"learning_rate": 1.2421111948782149e-06,
"loss": 827.3731,
"step": 4775
},
{
"epoch": 0.956,
"grad_norm": 163.22598266601562,
"learning_rate": 1.1878663632108322e-06,
"loss": 793.5028,
"step": 4780
},
{
"epoch": 0.957,
"grad_norm": 152.43026733398438,
"learning_rate": 1.134825526208605e-06,
"loss": 819.8253,
"step": 4785
},
{
"epoch": 0.958,
"grad_norm": 139.1593017578125,
"learning_rate": 1.0829893301573913e-06,
"loss": 804.5345,
"step": 4790
},
{
"epoch": 0.959,
"grad_norm": 155.72425842285156,
"learning_rate": 1.0323584066648795e-06,
"loss": 792.0783,
"step": 4795
},
{
"epoch": 0.96,
"grad_norm": 233.99363708496094,
"learning_rate": 9.829333726529056e-07,
"loss": 813.6428,
"step": 4800
},
{
"epoch": 0.961,
"grad_norm": 141.5477752685547,
"learning_rate": 9.347148303499142e-07,
"loss": 803.4646,
"step": 4805
},
{
"epoch": 0.962,
"grad_norm": 643.3412475585938,
"learning_rate": 8.877033672835988e-07,
"loss": 790.2094,
"step": 4810
},
{
"epoch": 0.963,
"grad_norm": 326.49627685546875,
"learning_rate": 8.418995562738285e-07,
"loss": 778.9743,
"step": 4815
},
{
"epoch": 0.964,
"grad_norm": 425.9938049316406,
"learning_rate": 7.973039554255768e-07,
"loss": 869.6862,
"step": 4820
},
{
"epoch": 0.965,
"grad_norm": 151.62254333496094,
"learning_rate": 7.539171081221596e-07,
"loss": 853.4119,
"step": 4825
},
{
"epoch": 0.966,
"grad_norm": 173.75526428222656,
"learning_rate": 7.117395430186414e-07,
"loss": 832.4118,
"step": 4830
},
{
"epoch": 0.967,
"grad_norm": 297.1338195800781,
"learning_rate": 6.707717740353059e-07,
"loss": 844.3934,
"step": 4835
},
{
"epoch": 0.968,
"grad_norm": 144.38206481933594,
"learning_rate": 6.310143003515179e-07,
"loss": 808.8445,
"step": 4840
},
{
"epoch": 0.969,
"grad_norm": 158.19541931152344,
"learning_rate": 5.924676063995382e-07,
"loss": 817.0394,
"step": 4845
},
{
"epoch": 0.97,
"grad_norm": 154.05984497070312,
"learning_rate": 5.551321618586736e-07,
"loss": 815.1714,
"step": 4850
},
{
"epoch": 0.971,
"grad_norm": 160.18014526367188,
"learning_rate": 5.190084216495361e-07,
"loss": 806.4308,
"step": 4855
},
{
"epoch": 0.972,
"grad_norm": 161.3776397705078,
"learning_rate": 4.840968259284817e-07,
"loss": 902.7519,
"step": 4860
},
{
"epoch": 0.973,
"grad_norm": 171.7818603515625,
"learning_rate": 4.503978000823028e-07,
"loss": 809.0996,
"step": 4865
},
{
"epoch": 0.974,
"grad_norm": 196.0985870361328,
"learning_rate": 4.179117547229883e-07,
"loss": 837.9623,
"step": 4870
},
{
"epoch": 0.975,
"grad_norm": 166.36448669433594,
"learning_rate": 3.866390856827495e-07,
"loss": 827.3932,
"step": 4875
},
{
"epoch": 0.976,
"grad_norm": 158.51332092285156,
"learning_rate": 3.565801740092023e-07,
"loss": 810.2068,
"step": 4880
},
{
"epoch": 0.977,
"grad_norm": 189.5699462890625,
"learning_rate": 3.277353859606813e-07,
"loss": 823.0144,
"step": 4885
},
{
"epoch": 0.978,
"grad_norm": 166.66798400878906,
"learning_rate": 3.001050730018218e-07,
"loss": 820.7362,
"step": 4890
},
{
"epoch": 0.979,
"grad_norm": 163.32327270507812,
"learning_rate": 2.73689571799296e-07,
"loss": 825.5743,
"step": 4895
},
{
"epoch": 0.98,
"grad_norm": 160.5224609375,
"learning_rate": 2.484892042176279e-07,
"loss": 831.9496,
"step": 4900
},
{
"epoch": 0.981,
"grad_norm": 180.9062957763672,
"learning_rate": 2.2450427731534053e-07,
"loss": 816.5383,
"step": 4905
},
{
"epoch": 0.982,
"grad_norm": 194.46311950683594,
"learning_rate": 2.017350833412146e-07,
"loss": 833.615,
"step": 4910
},
{
"epoch": 0.983,
"grad_norm": 170.17005920410156,
"learning_rate": 1.8018189973069143e-07,
"loss": 826.376,
"step": 4915
},
{
"epoch": 0.984,
"grad_norm": 165.7243194580078,
"learning_rate": 1.598449891024978e-07,
"loss": 817.7029,
"step": 4920
},
{
"epoch": 0.985,
"grad_norm": 145.6960906982422,
"learning_rate": 1.4072459925548177e-07,
"loss": 816.7054,
"step": 4925
},
{
"epoch": 0.986,
"grad_norm": 148.9720458984375,
"learning_rate": 1.2282096316554858e-07,
"loss": 831.6587,
"step": 4930
},
{
"epoch": 0.987,
"grad_norm": 157.1361083984375,
"learning_rate": 1.0613429898287398e-07,
"loss": 819.3745,
"step": 4935
},
{
"epoch": 0.988,
"grad_norm": 194.59036254882812,
"learning_rate": 9.066481002918403e-08,
"loss": 824.7155,
"step": 4940
},
{
"epoch": 0.989,
"grad_norm": 147.76844787597656,
"learning_rate": 7.641268479531283e-08,
"loss": 812.9468,
"step": 4945
},
{
"epoch": 0.99,
"grad_norm": 147.85858154296875,
"learning_rate": 6.337809693891527e-08,
"loss": 796.4284,
"step": 4950
},
{
"epoch": 0.991,
"grad_norm": 215.4252471923828,
"learning_rate": 5.1561205282335547e-08,
"loss": 805.8412,
"step": 4955
},
{
"epoch": 0.992,
"grad_norm": 175.8349151611328,
"learning_rate": 4.096215381066415e-08,
"loss": 803.6872,
"step": 4960
},
{
"epoch": 0.993,
"grad_norm": 153.05731201171875,
"learning_rate": 3.1581071670006015e-08,
"loss": 817.3902,
"step": 4965
},
{
"epoch": 0.994,
"grad_norm": 177.2631072998047,
"learning_rate": 2.3418073165870636e-08,
"loss": 819.4301,
"step": 4970
},
{
"epoch": 0.995,
"grad_norm": 148.4215850830078,
"learning_rate": 1.6473257761828732e-08,
"loss": 827.9391,
"step": 4975
},
{
"epoch": 0.996,
"grad_norm": 221.35057067871094,
"learning_rate": 1.074671007825767e-08,
"loss": 860.5812,
"step": 4980
},
{
"epoch": 0.997,
"grad_norm": 179.9678955078125,
"learning_rate": 6.238499891353389e-09,
"loss": 842.4149,
"step": 4985
},
{
"epoch": 0.998,
"grad_norm": 250.8158721923828,
"learning_rate": 2.948682132208891e-09,
"loss": 815.797,
"step": 4990
},
{
"epoch": 0.999,
"grad_norm": 221.18157958984375,
"learning_rate": 8.772968862369446e-10,
"loss": 803.2718,
"step": 4995
},
{
"epoch": 1.0,
"grad_norm": 180.0848388671875,
"learning_rate": 2.4369392592760164e-11,
"loss": 829.8369,
"step": 5000
},
{
"epoch": 1.0,
"step": 5000,
"total_flos": 7.022422523904e+16,
"train_loss": 332.44232041015624,
"train_runtime": 5190.6404,
"train_samples_per_second": 30.825,
"train_steps_per_second": 0.963
}
],
"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": true
},
"attributes": {}
}
},
"total_flos": 7.022422523904e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 5000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.001,
"grad_norm": 5279.1005859375,
"learning_rate": 1.6000000000000001e-06,
"loss": 3210.6535,
"step": 5
},
{
"epoch": 0.002,
"grad_norm": 4751.84619140625,
"learning_rate": 3.6e-06,
"loss": 3126.2795,
"step": 10
},
{
"epoch": 0.003,
"grad_norm": 4194.10107421875,
"learning_rate": 5.600000000000001e-06,
"loss": 2981.9664,
"step": 15
},
{
"epoch": 0.004,
"grad_norm": 3518.244384765625,
"learning_rate": 7.6e-06,
"loss": 2782.1281,
"step": 20
},
{
"epoch": 0.005,
"grad_norm": 2281.134521484375,
"learning_rate": 9.600000000000001e-06,
"loss": 2620.7445,
"step": 25
},
{
"epoch": 0.006,
"grad_norm": 1110.303955078125,
"learning_rate": 1.16e-05,
"loss": 2435.4023,
"step": 30
},
{
"epoch": 0.007,
"grad_norm": 1619.8824462890625,
"learning_rate": 1.3600000000000002e-05,
"loss": 2396.1436,
"step": 35
},
{
"epoch": 0.008,
"grad_norm": 824.91162109375,
"learning_rate": 1.56e-05,
"loss": 2325.2439,
"step": 40
},
{
"epoch": 0.009,
"grad_norm": 889.560791015625,
"learning_rate": 1.76e-05,
"loss": 2262.3674,
"step": 45
},
{
"epoch": 0.01,
"grad_norm": 657.9000244140625,
"learning_rate": 1.9600000000000002e-05,
"loss": 2183.2623,
"step": 50
},
{
"epoch": 0.011,
"grad_norm": 652.0450439453125,
"learning_rate": 2.16e-05,
"loss": 2123.1746,
"step": 55
},
{
"epoch": 0.012,
"grad_norm": 605.9557495117188,
"learning_rate": 2.36e-05,
"loss": 2036.5979,
"step": 60
},
{
"epoch": 0.013,
"grad_norm": 557.3351440429688,
"learning_rate": 2.5600000000000002e-05,
"loss": 1961.0652,