{
"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": 5977.189453125,
"learning_rate": 1.6000000000000001e-06,
"loss": 4176.6922,
"step": 5
},
{
"epoch": 0.002,
"grad_norm": 5548.77294921875,
"learning_rate": 3.6e-06,
"loss": 4080.4453,
"step": 10
},
{
"epoch": 0.003,
"grad_norm": 5243.63818359375,
"learning_rate": 5.600000000000001e-06,
"loss": 3902.6047,
"step": 15
},
{
"epoch": 0.004,
"grad_norm": 4877.013671875,
"learning_rate": 7.6e-06,
"loss": 3666.2555,
"step": 20
},
{
"epoch": 0.005,
"grad_norm": 3969.211669921875,
"learning_rate": 9.600000000000001e-06,
"loss": 3427.1504,
"step": 25
},
{
"epoch": 0.006,
"grad_norm": 2239.075439453125,
"learning_rate": 1.16e-05,
"loss": 3055.777,
"step": 30
},
{
"epoch": 0.007,
"grad_norm": 1304.8623046875,
"learning_rate": 1.3600000000000002e-05,
"loss": 2876.9252,
"step": 35
},
{
"epoch": 0.008,
"grad_norm": 1697.9920654296875,
"learning_rate": 1.56e-05,
"loss": 2802.0432,
"step": 40
},
{
"epoch": 0.009,
"grad_norm": 911.6920776367188,
"learning_rate": 1.76e-05,
"loss": 2733.0045,
"step": 45
},
{
"epoch": 0.01,
"grad_norm": 867.3721313476562,
"learning_rate": 1.9600000000000002e-05,
"loss": 2599.157,
"step": 50
},
{
"epoch": 0.011,
"grad_norm": 699.8728637695312,
"learning_rate": 2.16e-05,
"loss": 2543.0188,
"step": 55
},
{
"epoch": 0.012,
"grad_norm": 812.1158447265625,
"learning_rate": 2.36e-05,
"loss": 2406.9127,
"step": 60
},
{
"epoch": 0.013,
"grad_norm": 696.8179931640625,
"learning_rate": 2.5600000000000002e-05,
"loss": 2299.7312,
"step": 65
},
{
"epoch": 0.014,
"grad_norm": 576.9798583984375,
"learning_rate": 2.7600000000000003e-05,
"loss": 2229.3176,
"step": 70
},
{
"epoch": 0.015,
"grad_norm": 627.7363891601562,
"learning_rate": 2.96e-05,
"loss": 2246.9426,
"step": 75
},
{
"epoch": 0.016,
"grad_norm": 505.7649230957031,
"learning_rate": 3.16e-05,
"loss": 2162.309,
"step": 80
},
{
"epoch": 0.017,
"grad_norm": 825.4861450195312,
"learning_rate": 3.3600000000000004e-05,
"loss": 2120.8205,
"step": 85
},
{
"epoch": 0.018,
"grad_norm": 904.3131713867188,
"learning_rate": 3.56e-05,
"loss": 2148.0926,
"step": 90
},
{
"epoch": 0.019,
"grad_norm": 451.5786437988281,
"learning_rate": 3.76e-05,
"loss": 2143.8396,
"step": 95
},
{
"epoch": 0.02,
"grad_norm": 652.9741821289062,
"learning_rate": 3.960000000000001e-05,
"loss": 2127.8096,
"step": 100
},
{
"epoch": 0.021,
"grad_norm": 837.4066162109375,
"learning_rate": 4.16e-05,
"loss": 2134.6881,
"step": 105
},
{
"epoch": 0.022,
"grad_norm": 582.4090576171875,
"learning_rate": 4.36e-05,
"loss": 2129.6404,
"step": 110
},
{
"epoch": 0.023,
"grad_norm": 1164.7110595703125,
"learning_rate": 4.5600000000000004e-05,
"loss": 2037.5197,
"step": 115
},
{
"epoch": 0.024,
"grad_norm": 501.4394836425781,
"learning_rate": 4.76e-05,
"loss": 2068.0564,
"step": 120
},
{
"epoch": 0.025,
"grad_norm": 544.5418090820312,
"learning_rate": 4.96e-05,
"loss": 2019.5807,
"step": 125
},
{
"epoch": 0.026,
"grad_norm": 580.2637939453125,
"learning_rate": 5.16e-05,
"loss": 2023.7322,
"step": 130
},
{
"epoch": 0.027,
"grad_norm": 569.7576293945312,
"learning_rate": 5.360000000000001e-05,
"loss": 2033.1109,
"step": 135
},
{
"epoch": 0.028,
"grad_norm": 831.3717041015625,
"learning_rate": 5.560000000000001e-05,
"loss": 2017.1475,
"step": 140
},
{
"epoch": 0.029,
"grad_norm": 563.41552734375,
"learning_rate": 5.76e-05,
"loss": 2026.6697,
"step": 145
},
{
"epoch": 0.03,
"grad_norm": 792.9361572265625,
"learning_rate": 5.96e-05,
"loss": 1961.2367,
"step": 150
},
{
"epoch": 0.031,
"grad_norm": 970.17431640625,
"learning_rate": 6.16e-05,
"loss": 2001.9727,
"step": 155
},
{
"epoch": 0.032,
"grad_norm": 1679.805908203125,
"learning_rate": 6.36e-05,
"loss": 1963.9105,
"step": 160
},
{
"epoch": 0.033,
"grad_norm": 644.0517578125,
"learning_rate": 6.560000000000001e-05,
"loss": 1912.0654,
"step": 165
},
{
"epoch": 0.034,
"grad_norm": 892.1741943359375,
"learning_rate": 6.76e-05,
"loss": 1837.0918,
"step": 170
},
{
"epoch": 0.035,
"grad_norm": 608.6478881835938,
"learning_rate": 6.96e-05,
"loss": 1706.4264,
"step": 175
},
{
"epoch": 0.036,
"grad_norm": 908.9398803710938,
"learning_rate": 7.16e-05,
"loss": 1869.0277,
"step": 180
},
{
"epoch": 0.037,
"grad_norm": 464.33331298828125,
"learning_rate": 7.36e-05,
"loss": 1812.2396,
"step": 185
},
{
"epoch": 0.038,
"grad_norm": 679.6697998046875,
"learning_rate": 7.560000000000001e-05,
"loss": 1867.2664,
"step": 190
},
{
"epoch": 0.039,
"grad_norm": 654.8929443359375,
"learning_rate": 7.76e-05,
"loss": 1828.2328,
"step": 195
},
{
"epoch": 0.04,
"grad_norm": 437.39752197265625,
"learning_rate": 7.960000000000001e-05,
"loss": 1666.0244,
"step": 200
},
{
"epoch": 0.041,
"grad_norm": 1037.017333984375,
"learning_rate": 8.16e-05,
"loss": 1842.732,
"step": 205
},
{
"epoch": 0.042,
"grad_norm": 549.6128540039062,
"learning_rate": 8.36e-05,
"loss": 1822.9572,
"step": 210
},
{
"epoch": 0.043,
"grad_norm": 657.9453125,
"learning_rate": 8.560000000000001e-05,
"loss": 1741.1838,
"step": 215
},
{
"epoch": 0.044,
"grad_norm": 428.5650329589844,
"learning_rate": 8.76e-05,
"loss": 1832.9475,
"step": 220
},
{
"epoch": 0.045,
"grad_norm": 548.7670288085938,
"learning_rate": 8.960000000000001e-05,
"loss": 1742.6555,
"step": 225
},
{
"epoch": 0.046,
"grad_norm": 712.0475463867188,
"learning_rate": 9.16e-05,
"loss": 1785.7578,
"step": 230
},
{
"epoch": 0.047,
"grad_norm": 916.4633178710938,
"learning_rate": 9.360000000000001e-05,
"loss": 1784.7539,
"step": 235
},
{
"epoch": 0.048,
"grad_norm": 610.3597412109375,
"learning_rate": 9.56e-05,
"loss": 1761.5906,
"step": 240
},
{
"epoch": 0.049,
"grad_norm": 501.7183532714844,
"learning_rate": 9.76e-05,
"loss": 1740.3812,
"step": 245
},
{
"epoch": 0.05,
"grad_norm": 308.77508544921875,
"learning_rate": 9.960000000000001e-05,
"loss": 1618.4629,
"step": 250
},
{
"epoch": 0.051,
"grad_norm": 584.0804443359375,
"learning_rate": 0.0001016,
"loss": 1677.3918,
"step": 255
},
{
"epoch": 0.052,
"grad_norm": 683.8309326171875,
"learning_rate": 0.00010360000000000001,
"loss": 1735.9088,
"step": 260
},
{
"epoch": 0.053,
"grad_norm": 608.8570556640625,
"learning_rate": 0.0001056,
"loss": 1721.3484,
"step": 265
},
{
"epoch": 0.054,
"grad_norm": 527.3626708984375,
"learning_rate": 0.00010760000000000001,
"loss": 1442.5366,
"step": 270
},
{
"epoch": 0.055,
"grad_norm": 463.33184814453125,
"learning_rate": 0.00010960000000000001,
"loss": 1797.8947,
"step": 275
},
{
"epoch": 0.056,
"grad_norm": 638.3303833007812,
"learning_rate": 0.00011160000000000002,
"loss": 1765.6303,
"step": 280
},
{
"epoch": 0.057,
"grad_norm": 540.8755493164062,
"learning_rate": 0.0001136,
"loss": 1756.9773,
"step": 285
},
{
"epoch": 0.058,
"grad_norm": 493.4992980957031,
"learning_rate": 0.00011559999999999999,
"loss": 1693.3232,
"step": 290
},
{
"epoch": 0.059,
"grad_norm": 637.87060546875,
"learning_rate": 0.0001176,
"loss": 1556.8593,
"step": 295
},
{
"epoch": 0.06,
"grad_norm": 508.1549072265625,
"learning_rate": 0.00011960000000000001,
"loss": 1598.8726,
"step": 300
},
{
"epoch": 0.061,
"grad_norm": 372.2669982910156,
"learning_rate": 0.0001216,
"loss": 1495.0916,
"step": 305
},
{
"epoch": 0.062,
"grad_norm": 593.2761840820312,
"learning_rate": 0.0001236,
"loss": 1755.276,
"step": 310
},
{
"epoch": 0.063,
"grad_norm": 788.5468139648438,
"learning_rate": 0.00012560000000000002,
"loss": 1447.1573,
"step": 315
},
{
"epoch": 0.064,
"grad_norm": 682.88916015625,
"learning_rate": 0.0001276,
"loss": 1354.0012,
"step": 320
},
{
"epoch": 0.065,
"grad_norm": 541.571044921875,
"learning_rate": 0.0001296,
"loss": 1522.7304,
"step": 325
},
{
"epoch": 0.066,
"grad_norm": 467.54364013671875,
"learning_rate": 0.0001316,
"loss": 1632.11,
"step": 330
},
{
"epoch": 0.067,
"grad_norm": 672.8633422851562,
"learning_rate": 0.00013360000000000002,
"loss": 1535.3983,
"step": 335
},
{
"epoch": 0.068,
"grad_norm": 373.9183044433594,
"learning_rate": 0.00013560000000000002,
"loss": 1657.9744,
"step": 340
},
{
"epoch": 0.069,
"grad_norm": 507.07672119140625,
"learning_rate": 0.00013759999999999998,
"loss": 1600.3876,
"step": 345
},
{
"epoch": 0.07,
"grad_norm": 523.6527709960938,
"learning_rate": 0.0001396,
"loss": 1543.3885,
"step": 350
},
{
"epoch": 0.071,
"grad_norm": 719.1765747070312,
"learning_rate": 0.0001416,
"loss": 1568.5024,
"step": 355
},
{
"epoch": 0.072,
"grad_norm": 378.8148193359375,
"learning_rate": 0.0001436,
"loss": 1495.3664,
"step": 360
},
{
"epoch": 0.073,
"grad_norm": 473.602783203125,
"learning_rate": 0.00014560000000000002,
"loss": 1416.7647,
"step": 365
},
{
"epoch": 0.074,
"grad_norm": 445.2165832519531,
"learning_rate": 0.0001476,
"loss": 1592.8248,
"step": 370
},
{
"epoch": 0.075,
"grad_norm": 508.59893798828125,
"learning_rate": 0.0001496,
"loss": 1521.7891,
"step": 375
},
{
"epoch": 0.076,
"grad_norm": 586.3047485351562,
"learning_rate": 0.0001516,
"loss": 1537.0664,
"step": 380
},
{
"epoch": 0.077,
"grad_norm": 464.0722351074219,
"learning_rate": 0.00015360000000000002,
"loss": 1344.8999,
"step": 385
},
{
"epoch": 0.078,
"grad_norm": 528.0317993164062,
"learning_rate": 0.00015560000000000001,
"loss": 1483.9109,
"step": 390
},
{
"epoch": 0.079,
"grad_norm": 476.54827880859375,
"learning_rate": 0.0001576,
"loss": 1480.9084,
"step": 395
},
{
"epoch": 0.08,
"grad_norm": 374.9960021972656,
"learning_rate": 0.0001596,
"loss": 1524.2561,
"step": 400
},
{
"epoch": 0.081,
"grad_norm": 284.5118408203125,
"learning_rate": 0.00016160000000000002,
"loss": 1269.595,
"step": 405
},
{
"epoch": 0.082,
"grad_norm": 563.6873168945312,
"learning_rate": 0.0001636,
"loss": 1495.8883,
"step": 410
},
{
"epoch": 0.083,
"grad_norm": 615.1558837890625,
"learning_rate": 0.0001656,
"loss": 1479.0792,
"step": 415
},
{
"epoch": 0.084,
"grad_norm": 588.6783447265625,
"learning_rate": 0.0001676,
"loss": 1453.7693,
"step": 420
},
{
"epoch": 0.085,
"grad_norm": 861.3825073242188,
"learning_rate": 0.0001696,
"loss": 1535.6776,
"step": 425
},
{
"epoch": 0.086,
"grad_norm": 485.8833312988281,
"learning_rate": 0.0001716,
"loss": 1401.2939,
"step": 430
},
{
"epoch": 0.087,
"grad_norm": 513.6403198242188,
"learning_rate": 0.00017360000000000002,
"loss": 1549.6225,
"step": 435
},
{
"epoch": 0.088,
"grad_norm": 434.6390075683594,
"learning_rate": 0.0001756,
"loss": 1579.3078,
"step": 440
},
{
"epoch": 0.089,
"grad_norm": 489.8847351074219,
"learning_rate": 0.0001776,
"loss": 1554.3975,
"step": 445
},
{
"epoch": 0.09,
"grad_norm": 774.1304931640625,
"learning_rate": 0.0001796,
"loss": 1459.8686,
"step": 450
},
{
"epoch": 0.091,
"grad_norm": 772.0237426757812,
"learning_rate": 0.00018160000000000002,
"loss": 1500.9382,
"step": 455
},
{
"epoch": 0.092,
"grad_norm": 789.3552856445312,
"learning_rate": 0.00018360000000000002,
"loss": 1535.6313,
"step": 460
},
{
"epoch": 0.093,
"grad_norm": 395.14227294921875,
"learning_rate": 0.0001856,
"loss": 1461.9279,
"step": 465
},
{
"epoch": 0.094,
"grad_norm": 494.6033935546875,
"learning_rate": 0.0001876,
"loss": 1421.2053,
"step": 470
},
{
"epoch": 0.095,
"grad_norm": 346.7718200683594,
"learning_rate": 0.0001896,
"loss": 1385.2923,
"step": 475
},
{
"epoch": 0.096,
"grad_norm": 973.2535400390625,
"learning_rate": 0.0001916,
"loss": 1474.1078,
"step": 480
},
{
"epoch": 0.097,
"grad_norm": 401.73004150390625,
"learning_rate": 0.00019360000000000002,
"loss": 1444.4386,
"step": 485
},
{
"epoch": 0.098,
"grad_norm": 367.757080078125,
"learning_rate": 0.0001956,
"loss": 1434.3037,
"step": 490
},
{
"epoch": 0.099,
"grad_norm": 342.89837646484375,
"learning_rate": 0.0001976,
"loss": 1450.9106,
"step": 495
},
{
"epoch": 0.1,
"grad_norm": 392.15716552734375,
"learning_rate": 0.0001996,
"loss": 1417.8502,
"step": 500
},
{
"epoch": 0.101,
"grad_norm": 948.5860595703125,
"learning_rate": 0.00019999961008995606,
"loss": 1483.1235,
"step": 505
},
{
"epoch": 0.102,
"grad_norm": 604.86181640625,
"learning_rate": 0.0001999980260856137,
"loss": 1430.4704,
"step": 510
},
{
"epoch": 0.103,
"grad_norm": 418.140380859375,
"learning_rate": 0.000199995223636881,
"loss": 1465.4646,
"step": 515
},
{
"epoch": 0.104,
"grad_norm": 596.5216674804688,
"learning_rate": 0.00019999120277790477,
"loss": 1550.6107,
"step": 520
},
{
"epoch": 0.105,
"grad_norm": 371.9090881347656,
"learning_rate": 0.00019998596355767805,
"loss": 1439.7612,
"step": 525
},
{
"epoch": 0.106,
"grad_norm": 500.018798828125,
"learning_rate": 0.000199979506040039,
"loss": 1516.8793,
"step": 530
},
{
"epoch": 0.107,
"grad_norm": 442.6863708496094,
"learning_rate": 0.00019997183030367048,
"loss": 1395.2951,
"step": 535
},
{
"epoch": 0.108,
"grad_norm": 389.804443359375,
"learning_rate": 0.00019996293644209887,
"loss": 1487.942,
"step": 540
},
{
"epoch": 0.109,
"grad_norm": 400.6053161621094,
"learning_rate": 0.0001999528245636931,
"loss": 1424.5754,
"step": 545
},
{
"epoch": 0.11,
"grad_norm": 253.59527587890625,
"learning_rate": 0.00019994149479166324,
"loss": 1294.4195,
"step": 550
},
{
"epoch": 0.111,
"grad_norm": 478.5777893066406,
"learning_rate": 0.00019992894726405893,
"loss": 1082.9523,
"step": 555
},
{
"epoch": 0.112,
"grad_norm": 608.3764038085938,
"learning_rate": 0.00019991518213376787,
"loss": 1432.2569,
"step": 560
},
{
"epoch": 0.113,
"grad_norm": 480.333740234375,
"learning_rate": 0.00019990019956851382,
"loss": 1417.7156,
"step": 565
},
{
"epoch": 0.114,
"grad_norm": 344.7553405761719,
"learning_rate": 0.0001998839997508546,
"loss": 1392.4636,
"step": 570
},
{
"epoch": 0.115,
"grad_norm": 584.9265747070312,
"learning_rate": 0.00019986658287817987,
"loss": 1352.0381,
"step": 575
},
{
"epoch": 0.116,
"grad_norm": 493.3850402832031,
"learning_rate": 0.00019984794916270876,
"loss": 1336.4258,
"step": 580
},
{
"epoch": 0.117,
"grad_norm": 328.3043212890625,
"learning_rate": 0.00019982809883148722,
"loss": 1366.3457,
"step": 585
},
{
"epoch": 0.118,
"grad_norm": 427.796630859375,
"learning_rate": 0.00019980703212638522,
"loss": 1239.9491,
"step": 590
},
{
"epoch": 0.119,
"grad_norm": 568.7474975585938,
"learning_rate": 0.00019978474930409395,
"loss": 1398.8503,
"step": 595
},
{
"epoch": 0.12,
"grad_norm": 655.2291870117188,
"learning_rate": 0.00019976125063612252,
"loss": 1390.6631,
"step": 600
},
{
"epoch": 0.121,
"grad_norm": 605.0892333984375,
"learning_rate": 0.00019973653640879485,
"loss": 1380.1759,
"step": 605
},
{
"epoch": 0.122,
"grad_norm": 653.2969970703125,
"learning_rate": 0.00019971060692324598,
"loss": 1364.7701,
"step": 610
},
{
"epoch": 0.123,
"grad_norm": 927.7265625,
"learning_rate": 0.00019968346249541846,
"loss": 1384.9365,
"step": 615
},
{
"epoch": 0.124,
"grad_norm": 243.21017456054688,
"learning_rate": 0.00019965510345605866,
"loss": 1295.512,
"step": 620
},
{
"epoch": 0.125,
"grad_norm": 426.5096435546875,
"learning_rate": 0.0001996255301507125,
"loss": 1333.3721,
"step": 625
},
{
"epoch": 0.126,
"grad_norm": 504.5038146972656,
"learning_rate": 0.00019959474293972129,
"loss": 1391.6972,
"step": 630
},
{
"epoch": 0.127,
"grad_norm": 317.4625244140625,
"learning_rate": 0.00019956274219821757,
"loss": 1256.8517,
"step": 635
},
{
"epoch": 0.128,
"grad_norm": 462.31353759765625,
"learning_rate": 0.00019952952831612026,
"loss": 1443.1719,
"step": 640
},
{
"epoch": 0.129,
"grad_norm": 374.0202941894531,
"learning_rate": 0.00019949510169813003,
"loss": 1341.1267,
"step": 645
},
{
"epoch": 0.13,
"grad_norm": 302.0836181640625,
"learning_rate": 0.00019945946276372434,
"loss": 1295.1974,
"step": 650
},
{
"epoch": 0.131,
"grad_norm": 538.4676513671875,
"learning_rate": 0.00019942261194715236,
"loss": 1271.0162,
"step": 655
},
{
"epoch": 0.132,
"grad_norm": 619.91650390625,
"learning_rate": 0.00019938454969742968,
"loss": 1381.4616,
"step": 660
},
{
"epoch": 0.133,
"grad_norm": 404.2091064453125,
"learning_rate": 0.00019934527647833276,
"loss": 1330.2831,
"step": 665
},
{
"epoch": 0.134,
"grad_norm": 398.3340759277344,
"learning_rate": 0.00019930479276839344,
"loss": 1299.5295,
"step": 670
},
{
"epoch": 0.135,
"grad_norm": 298.2498474121094,
"learning_rate": 0.0001992630990608929,
"loss": 1268.4473,
"step": 675
},
{
"epoch": 0.136,
"grad_norm": 306.759521484375,
"learning_rate": 0.00019922019586385585,
"loss": 1290.4852,
"step": 680
},
{
"epoch": 0.137,
"grad_norm": 321.7572937011719,
"learning_rate": 0.00019917608370004417,
"loss": 1176.8048,
"step": 685
},
{
"epoch": 0.138,
"grad_norm": 797.144775390625,
"learning_rate": 0.00019913076310695068,
"loss": 1193.3778,
"step": 690
},
{
"epoch": 0.139,
"grad_norm": 531.331787109375,
"learning_rate": 0.00019908423463679248,
"loss": 1411.3835,
"step": 695
},
{
"epoch": 0.14,
"grad_norm": 337.1986389160156,
"learning_rate": 0.0001990364988565043,
"loss": 1359.498,
"step": 700
},
{
"epoch": 0.141,
"grad_norm": 458.74090576171875,
"learning_rate": 0.00019898755634773158,
"loss": 1338.2063,
"step": 705
},
{
"epoch": 0.142,
"grad_norm": 534.9490356445312,
"learning_rate": 0.00019893740770682335,
"loss": 1323.2829,
"step": 710
},
{
"epoch": 0.143,
"grad_norm": 376.5198669433594,
"learning_rate": 0.0001988860535448249,
"loss": 1223.8159,
"step": 715
},
{
"epoch": 0.144,
"grad_norm": 554.9400024414062,
"learning_rate": 0.00019883349448747062,
"loss": 1340.7104,
"step": 720
},
{
"epoch": 0.145,
"grad_norm": 579.7927856445312,
"learning_rate": 0.0001987797311751759,
"loss": 1315.0251,
"step": 725
},
{
"epoch": 0.146,
"grad_norm": 458.1208190917969,
"learning_rate": 0.00019872476426302982,
"loss": 1293.3813,
"step": 730
},
{
"epoch": 0.147,
"grad_norm": 496.2734680175781,
"learning_rate": 0.0001986685944207868,
"loss": 1282.5014,
"step": 735
},
{
"epoch": 0.148,
"grad_norm": 570.13720703125,
"learning_rate": 0.0001986112223328587,
"loss": 1341.6562,
"step": 740
},
{
"epoch": 0.149,
"grad_norm": 338.264892578125,
"learning_rate": 0.00019855264869830629,
"loss": 1249.2329,
"step": 745
},
{
"epoch": 0.15,
"grad_norm": 517.7503662109375,
"learning_rate": 0.00019849287423083078,
"loss": 1251.4394,
"step": 750
},
{
"epoch": 0.151,
"grad_norm": 766.0257568359375,
"learning_rate": 0.00019843189965876526,
"loss": 1269.8669,
"step": 755
},
{
"epoch": 0.152,
"grad_norm": 566.4552612304688,
"learning_rate": 0.00019836972572506557,
"loss": 1298.9459,
"step": 760
},
{
"epoch": 0.153,
"grad_norm": 1069.763671875,
"learning_rate": 0.00019830635318730154,
"loss": 1257.4656,
"step": 765
},
{
"epoch": 0.154,
"grad_norm": 361.89764404296875,
"learning_rate": 0.00019824178281764753,
"loss": 1245.4639,
"step": 770
},
{
"epoch": 0.155,
"grad_norm": 309.0524597167969,
"learning_rate": 0.00019817601540287306,
"loss": 1198.7374,
"step": 775
},
{
"epoch": 0.156,
"grad_norm": 496.6186218261719,
"learning_rate": 0.0001981090517443334,
"loss": 1280.4866,
"step": 780
},
{
"epoch": 0.157,
"grad_norm": 364.4707946777344,
"learning_rate": 0.0001980408926579596,
"loss": 1213.601,
"step": 785
},
{
"epoch": 0.158,
"grad_norm": 652.3853759765625,
"learning_rate": 0.00019797153897424852,
"loss": 1332.6869,
"step": 790
},
{
"epoch": 0.159,
"grad_norm": 442.5556335449219,
"learning_rate": 0.000197900991538253,
"loss": 1252.1054,
"step": 795
},
{
"epoch": 0.16,
"grad_norm": 348.1319885253906,
"learning_rate": 0.00019782925120957124,
"loss": 1275.1951,
"step": 800
},
{
"epoch": 0.161,
"grad_norm": 338.5092468261719,
"learning_rate": 0.00019775631886233654,
"loss": 1232.0539,
"step": 805
},
{
"epoch": 0.162,
"grad_norm": 305.4432067871094,
"learning_rate": 0.0001976821953852065,
"loss": 1219.3042,
"step": 810
},
{
"epoch": 0.163,
"grad_norm": 457.9334716796875,
"learning_rate": 0.00019760688168135232,
"loss": 1223.909,
"step": 815
},
{
"epoch": 0.164,
"grad_norm": 598.2462158203125,
"learning_rate": 0.00019753037866844771,
"loss": 1218.067,
"step": 820
},
{
"epoch": 0.165,
"grad_norm": 371.88250732421875,
"learning_rate": 0.00019745268727865774,
"loss": 1192.5576,
"step": 825
},
{
"epoch": 0.166,
"grad_norm": 369.8703308105469,
"learning_rate": 0.00019737380845862745,
"loss": 1291.0953,
"step": 830
},
{
"epoch": 0.167,
"grad_norm": 361.28680419921875,
"learning_rate": 0.0001972937431694704,
"loss": 1226.9626,
"step": 835
},
{
"epoch": 0.168,
"grad_norm": 380.8177490234375,
"learning_rate": 0.00019721249238675688,
"loss": 1247.2252,
"step": 840
},
{
"epoch": 0.169,
"grad_norm": 385.90753173828125,
"learning_rate": 0.000197130057100502,
"loss": 1274.2963,
"step": 845
},
{
"epoch": 0.17,
"grad_norm": 300.01739501953125,
"learning_rate": 0.00019704643831515374,
"loss": 1250.6713,
"step": 850
},
{
"epoch": 0.171,
"grad_norm": 537.793212890625,
"learning_rate": 0.0001969616370495806,
"loss": 1263.4822,
"step": 855
},
{
"epoch": 0.172,
"grad_norm": 500.259765625,
"learning_rate": 0.00019687565433705926,
"loss": 1271.4924,
"step": 860
},
{
"epoch": 0.173,
"grad_norm": 310.17169189453125,
"learning_rate": 0.00019678849122526187,
"loss": 1162.188,
"step": 865
},
{
"epoch": 0.174,
"grad_norm": 262.8263244628906,
"learning_rate": 0.00019670014877624353,
"loss": 1122.4253,
"step": 870
},
{
"epoch": 0.175,
"grad_norm": 279.7691345214844,
"learning_rate": 0.00019661062806642903,
"loss": 1135.0541,
"step": 875
},
{
"epoch": 0.176,
"grad_norm": 423.6324768066406,
"learning_rate": 0.0001965199301866,
"loss": 1138.4077,
"step": 880
},
{
"epoch": 0.177,
"grad_norm": 370.619140625,
"learning_rate": 0.00019642805624188147,
"loss": 1130.1703,
"step": 885
},
{
"epoch": 0.178,
"grad_norm": 300.5290222167969,
"learning_rate": 0.0001963350073517285,
"loss": 1059.1783,
"step": 890
},
{
"epoch": 0.179,
"grad_norm": 432.7168884277344,
"learning_rate": 0.0001962407846499124,
"loss": 1083.3274,
"step": 895
},
{
"epoch": 0.18,
"grad_norm": 278.2895202636719,
"learning_rate": 0.0001961453892845071,
"loss": 1080.2434,
"step": 900
},
{
"epoch": 0.181,
"grad_norm": 362.66827392578125,
"learning_rate": 0.00019604882241787498,
"loss": 1111.9314,
"step": 905
},
{
"epoch": 0.182,
"grad_norm": 296.6867370605469,
"learning_rate": 0.0001959510852266529,
"loss": 1191.2515,
"step": 910
},
{
"epoch": 0.183,
"grad_norm": 328.760986328125,
"learning_rate": 0.0001958521789017376,
"loss": 1195.5976,
"step": 915
},
{
"epoch": 0.184,
"grad_norm": 355.9902648925781,
"learning_rate": 0.00019575210464827149,
"loss": 1261.8097,
"step": 920
},
{
"epoch": 0.185,
"grad_norm": 344.2992858886719,
"learning_rate": 0.0001956508636856278,
"loss": 1220.4645,
"step": 925
},
{
"epoch": 0.186,
"grad_norm": 377.9537353515625,
"learning_rate": 0.00019554845724739566,
"loss": 1134.2014,
"step": 930
},
{
"epoch": 0.187,
"grad_norm": 421.77484130859375,
"learning_rate": 0.00019544488658136523,
"loss": 1201.9515,
"step": 935
},
{
"epoch": 0.188,
"grad_norm": 346.87384033203125,
"learning_rate": 0.00019534015294951233,
"loss": 1212.9588,
"step": 940
},
{
"epoch": 0.189,
"grad_norm": 838.1333618164062,
"learning_rate": 0.00019523425762798329,
"loss": 1216.7469,
"step": 945
},
{
"epoch": 0.19,
"grad_norm": 416.6495361328125,
"learning_rate": 0.00019512720190707913,
"loss": 1146.3621,
"step": 950
},
{
"epoch": 0.191,
"grad_norm": 504.94891357421875,
"learning_rate": 0.00019501898709124008,
"loss": 1188.6436,
"step": 955
},
{
"epoch": 0.192,
"grad_norm": 364.1293640136719,
"learning_rate": 0.00019490961449902946,
"loss": 1172.5491,
"step": 960
},
{
"epoch": 0.193,
"grad_norm": 339.6297912597656,
"learning_rate": 0.00019479908546311781,
"loss": 1173.9819,
"step": 965
},
{
"epoch": 0.194,
"grad_norm": 400.9771423339844,
"learning_rate": 0.0001946874013302666,
"loss": 1174.6432,
"step": 970
},
{
"epoch": 0.195,
"grad_norm": 307.469482421875,
"learning_rate": 0.0001945745634613117,
"loss": 1202.5424,
"step": 975
},
{
"epoch": 0.196,
"grad_norm": 337.4597473144531,
"learning_rate": 0.0001944605732311469,
"loss": 1178.9882,
"step": 980
},
{
"epoch": 0.197,
"grad_norm": 504.6136474609375,
"learning_rate": 0.00019434543202870725,
"loss": 1149.5877,
"step": 985
},
{
"epoch": 0.198,
"grad_norm": 415.49090576171875,
"learning_rate": 0.0001942291412569519,
"loss": 1197.1549,
"step": 990
},
{
"epoch": 0.199,
"grad_norm": 466.6844787597656,
"learning_rate": 0.00019411170233284727,
"loss": 1205.2188,
"step": 995
},
{
"epoch": 0.2,
"grad_norm": 329.6707763671875,
"learning_rate": 0.00019399311668734956,
"loss": 1163.116,
"step": 1000
},
{
"epoch": 0.201,
"grad_norm": 433.10113525390625,
"learning_rate": 0.00019387338576538744,
"loss": 1181.8348,
"step": 1005
},
{
"epoch": 0.202,
"grad_norm": 355.80584716796875,
"learning_rate": 0.0001937525110258444,
"loss": 1169.028,
"step": 1010
},
{
"epoch": 0.203,
"grad_norm": 325.0740661621094,
"learning_rate": 0.00019363049394154094,
"loss": 1164.2173,
"step": 1015
},
{
"epoch": 0.204,
"grad_norm": 576.3699951171875,
"learning_rate": 0.00019350733599921683,
"loss": 1138.555,
"step": 1020
},
{
"epoch": 0.205,
"grad_norm": 319.3100280761719,
"learning_rate": 0.00019338303869951269,
"loss": 1161.8999,
"step": 1025
},
{
"epoch": 0.206,
"grad_norm": 352.3548889160156,
"learning_rate": 0.00019325760355695188,
"loss": 1167.3168,
"step": 1030
},
{
"epoch": 0.207,
"grad_norm": 357.7380676269531,
"learning_rate": 0.00019313103209992204,
"loss": 1124.1335,
"step": 1035
},
{
"epoch": 0.208,
"grad_norm": 317.7587585449219,
"learning_rate": 0.0001930033258706564,
"loss": 1103.9995,
"step": 1040
},
{
"epoch": 0.209,
"grad_norm": 480.9820556640625,
"learning_rate": 0.00019287448642521513,
"loss": 1202.1472,
"step": 1045
},
{
"epoch": 0.21,
"grad_norm": 373.9464111328125,
"learning_rate": 0.00019274451533346615,
"loss": 1146.4483,
"step": 1050
},
{
"epoch": 0.211,
"grad_norm": 331.75225830078125,
"learning_rate": 0.00019261341417906621,
"loss": 1177.7407,
"step": 1055
},
{
"epoch": 0.212,
"grad_norm": 335.7484436035156,
"learning_rate": 0.0001924811845594415,
"loss": 1114.1858,
"step": 1060
},
{
"epoch": 0.213,
"grad_norm": 393.0115966796875,
"learning_rate": 0.00019234782808576824,
"loss": 1164.0694,
"step": 1065
},
{
"epoch": 0.214,
"grad_norm": 577.9696044921875,
"learning_rate": 0.00019221334638295294,
"loss": 1093.3336,
"step": 1070
},
{
"epoch": 0.215,
"grad_norm": 528.8370361328125,
"learning_rate": 0.00019207774108961272,
"loss": 1161.8003,
"step": 1075
},
{
"epoch": 0.216,
"grad_norm": 378.6943054199219,
"learning_rate": 0.0001919410138580553,
"loss": 1103.0676,
"step": 1080
},
{
"epoch": 0.217,
"grad_norm": 848.318603515625,
"learning_rate": 0.0001918031663542588,
"loss": 1130.7642,
"step": 1085
},
{
"epoch": 0.218,
"grad_norm": 599.683349609375,
"learning_rate": 0.00019166420025785164,
"loss": 1137.3205,
"step": 1090
},
{
"epoch": 0.219,
"grad_norm": 330.8734436035156,
"learning_rate": 0.00019152411726209176,
"loss": 1215.3684,
"step": 1095
},
{
"epoch": 0.22,
"grad_norm": 307.56060791015625,
"learning_rate": 0.0001913829190738463,
"loss": 1062.1879,
"step": 1100
},
{
"epoch": 0.221,
"grad_norm": 364.14202880859375,
"learning_rate": 0.00019124060741357063,
"loss": 1155.5506,
"step": 1105
},
{
"epoch": 0.222,
"grad_norm": 471.0177917480469,
"learning_rate": 0.0001910971840152874,
"loss": 1133.2343,
"step": 1110
},
{
"epoch": 0.223,
"grad_norm": 448.39898681640625,
"learning_rate": 0.00019095265062656544,
"loss": 1125.9364,
"step": 1115
},
{
"epoch": 0.224,
"grad_norm": 408.38031005859375,
"learning_rate": 0.00019080700900849851,
"loss": 1091.1028,
"step": 1120
},
{
"epoch": 0.225,
"grad_norm": 399.3428649902344,
"learning_rate": 0.00019066026093568378,
"loss": 1115.1402,
"step": 1125
},
{
"epoch": 0.226,
"grad_norm": 460.17047119140625,
"learning_rate": 0.00019051240819620014,
"loss": 1128.7808,
"step": 1130
},
{
"epoch": 0.227,
"grad_norm": 348.2709655761719,
"learning_rate": 0.00019036345259158667,
"loss": 1138.4077,
"step": 1135
},
{
"epoch": 0.228,
"grad_norm": 512.5126953125,
"learning_rate": 0.00019021339593682028,
"loss": 1116.8225,
"step": 1140
},
{
"epoch": 0.229,
"grad_norm": 405.6308288574219,
"learning_rate": 0.00019006224006029406,
"loss": 1042.0444,
"step": 1145
},
{
"epoch": 0.23,
"grad_norm": 441.58978271484375,
"learning_rate": 0.00018990998680379456,
"loss": 1133.4608,
"step": 1150
},
{
"epoch": 0.231,
"grad_norm": 472.1557922363281,
"learning_rate": 0.00018975663802247976,
"loss": 1204.5274,
"step": 1155
},
{
"epoch": 0.232,
"grad_norm": 313.5436706542969,
"learning_rate": 0.0001896021955848561,
"loss": 1087.1398,
"step": 1160
},
{
"epoch": 0.233,
"grad_norm": 317.5483093261719,
"learning_rate": 0.000189446661372756,
"loss": 1114.3125,
"step": 1165
},
{
"epoch": 0.234,
"grad_norm": 374.3742370605469,
"learning_rate": 0.0001892900372813147,
"loss": 1099.0323,
"step": 1170
},
{
"epoch": 0.235,
"grad_norm": 419.49835205078125,
"learning_rate": 0.00018913232521894732,
"loss": 1093.8168,
"step": 1175
},
{
"epoch": 0.236,
"grad_norm": 702.2492065429688,
"learning_rate": 0.00018897352710732564,
"loss": 1123.4514,
"step": 1180
},
{
"epoch": 0.237,
"grad_norm": 553.2774658203125,
"learning_rate": 0.00018881364488135448,
"loss": 1131.6624,
"step": 1185
},
{
"epoch": 0.238,
"grad_norm": 483.2618103027344,
"learning_rate": 0.00018865268048914828,
"loss": 1058.241,
"step": 1190
},
{
"epoch": 0.239,
"grad_norm": 279.8911437988281,
"learning_rate": 0.00018849063589200743,
"loss": 1102.6486,
"step": 1195
},
{
"epoch": 0.24,
"grad_norm": 358.29571533203125,
"learning_rate": 0.00018832751306439418,
"loss": 1088.9724,
"step": 1200
},
{
"epoch": 0.241,
"grad_norm": 259.5635986328125,
"learning_rate": 0.0001881633139939087,
"loss": 1126.1268,
"step": 1205
},
{
"epoch": 0.242,
"grad_norm": 338.0083923339844,
"learning_rate": 0.00018799804068126485,
"loss": 1087.2512,
"step": 1210
},
{
"epoch": 0.243,
"grad_norm": 258.65460205078125,
"learning_rate": 0.00018783169514026578,
"loss": 1090.7016,
"step": 1215
},
{
"epoch": 0.244,
"grad_norm": 432.32427978515625,
"learning_rate": 0.00018766427939777945,
"loss": 1083.7304,
"step": 1220
},
{
"epoch": 0.245,
"grad_norm": 317.2571716308594,
"learning_rate": 0.0001874957954937138,
"loss": 1115.094,
"step": 1225
},
{
"epoch": 0.246,
"grad_norm": 458.0859375,
"learning_rate": 0.00018732624548099204,
"loss": 1086.6189,
"step": 1230
},
{
"epoch": 0.247,
"grad_norm": 618.451416015625,
"learning_rate": 0.00018715563142552758,
"loss": 1087.1704,
"step": 1235
},
{
"epoch": 0.248,
"grad_norm": 374.7634582519531,
"learning_rate": 0.0001869839554061988,
"loss": 1065.4443,
"step": 1240
},
{
"epoch": 0.249,
"grad_norm": 243.8141326904297,
"learning_rate": 0.00018681121951482393,
"loss": 1101.0541,
"step": 1245
},
{
"epoch": 0.25,
"grad_norm": 289.8293762207031,
"learning_rate": 0.00018663742585613518,
"loss": 1112.5844,
"step": 1250
},
{
"epoch": 0.251,
"grad_norm": 338.71112060546875,
"learning_rate": 0.0001864625765477535,
"loss": 1083.8898,
"step": 1255
},
{
"epoch": 0.252,
"grad_norm": 236.80482482910156,
"learning_rate": 0.0001862866737201625,
"loss": 1055.3561,
"step": 1260
},
{
"epoch": 0.253,
"grad_norm": 275.5596008300781,
"learning_rate": 0.00018610971951668265,
"loss": 1088.9395,
"step": 1265
},
{
"epoch": 0.254,
"grad_norm": 271.7322082519531,
"learning_rate": 0.00018593171609344503,
"loss": 1045.7624,
"step": 1270
},
{
"epoch": 0.255,
"grad_norm": 346.6656799316406,
"learning_rate": 0.00018575266561936523,
"loss": 1060.5358,
"step": 1275
},
{
"epoch": 0.256,
"grad_norm": 508.787109375,
"learning_rate": 0.00018557257027611675,
"loss": 1029.6087,
"step": 1280
},
{
"epoch": 0.257,
"grad_norm": 439.879150390625,
"learning_rate": 0.0001853914322581045,
"loss": 1080.2843,
"step": 1285
},
{
"epoch": 0.258,
"grad_norm": 424.4865417480469,
"learning_rate": 0.0001852092537724381,
"loss": 1045.0983,
"step": 1290
},
{
"epoch": 0.259,
"grad_norm": 292.44873046875,
"learning_rate": 0.00018502603703890488,
"loss": 1055.0089,
"step": 1295
},
{
"epoch": 0.26,
"grad_norm": 307.0181884765625,
"learning_rate": 0.0001848417842899429,
"loss": 1112.0499,
"step": 1300
},
{
"epoch": 0.261,
"grad_norm": 273.61572265625,
"learning_rate": 0.0001846564977706138,
"loss": 1045.7533,
"step": 1305
},
{
"epoch": 0.262,
"grad_norm": 315.93389892578125,
"learning_rate": 0.00018447017973857532,
"loss": 1033.0324,
"step": 1310
},
{
"epoch": 0.263,
"grad_norm": 257.05841064453125,
"learning_rate": 0.0001842828324640539,
"loss": 1087.4455,
"step": 1315
},
{
"epoch": 0.264,
"grad_norm": 383.84228515625,
"learning_rate": 0.00018409445822981693,
"loss": 1059.7084,
"step": 1320
},
{
"epoch": 0.265,
"grad_norm": 359.3036193847656,
"learning_rate": 0.000183905059331145,
"loss": 1044.1739,
"step": 1325
},
{
"epoch": 0.266,
"grad_norm": 439.7004699707031,
"learning_rate": 0.000183714638075804,
"loss": 1055.6542,
"step": 1330
},
{
"epoch": 0.267,
"grad_norm": 459.02203369140625,
"learning_rate": 0.00018352319678401676,
"loss": 1076.628,
"step": 1335
},
{
"epoch": 0.268,
"grad_norm": 551.3557739257812,
"learning_rate": 0.000183330737788435,
"loss": 1083.4554,
"step": 1340
},
{
"epoch": 0.269,
"grad_norm": 254.03378295898438,
"learning_rate": 0.00018313726343411086,
"loss": 1086.5318,
"step": 1345
},
{
"epoch": 0.27,
"grad_norm": 239.25160217285156,
"learning_rate": 0.00018294277607846832,
"loss": 1025.4147,
"step": 1350
},
{
"epoch": 0.271,
"grad_norm": 318.9286193847656,
"learning_rate": 0.00018274727809127438,
"loss": 1050.3056,
"step": 1355
},
{
"epoch": 0.272,
"grad_norm": 445.1725158691406,
"learning_rate": 0.00018255077185461038,
"loss": 1012.3081,
"step": 1360
},
{
"epoch": 0.273,
"grad_norm": 250.2674102783203,
"learning_rate": 0.00018235325976284275,
"loss": 985.2935,
"step": 1365
},
{
"epoch": 0.274,
"grad_norm": 225.50357055664062,
"learning_rate": 0.00018215474422259402,
"loss": 945.1627,
"step": 1370
},
{
"epoch": 0.275,
"grad_norm": 459.1195983886719,
"learning_rate": 0.0001819552276527134,
"loss": 970.1604,
"step": 1375
},
{
"epoch": 0.276,
"grad_norm": 264.3739929199219,
"learning_rate": 0.0001817547124842473,
"loss": 1023.5753,
"step": 1380
},
{
"epoch": 0.277,
"grad_norm": 623.1638793945312,
"learning_rate": 0.00018155320116040982,
"loss": 1076.653,
"step": 1385
},
{
"epoch": 0.278,
"grad_norm": 246.1554412841797,
"learning_rate": 0.0001813506961365528,
"loss": 1060.2274,
"step": 1390
},
{
"epoch": 0.279,
"grad_norm": 242.12405395507812,
"learning_rate": 0.00018114719988013612,
"loss": 992.7894,
"step": 1395
},
{
"epoch": 0.28,
"grad_norm": 367.9578857421875,
"learning_rate": 0.00018094271487069735,
"loss": 1047.9647,
"step": 1400
},
{
"epoch": 0.281,
"grad_norm": 273.5019226074219,
"learning_rate": 0.00018073724359982186,
"loss": 1054.0553,
"step": 1405
},
{
"epoch": 0.282,
"grad_norm": 582.6957397460938,
"learning_rate": 0.0001805307885711122,
"loss": 1052.5864,
"step": 1410
},
{
"epoch": 0.283,
"grad_norm": 389.9174499511719,
"learning_rate": 0.0001803233523001578,
"loss": 971.8896,
"step": 1415
},
{
"epoch": 0.284,
"grad_norm": 392.4607849121094,
"learning_rate": 0.00018011493731450413,
"loss": 1013.7092,
"step": 1420
},
{
"epoch": 0.285,
"grad_norm": 376.24566650390625,
"learning_rate": 0.00017990554615362198,
"loss": 1076.1255,
"step": 1425
},
{
"epoch": 0.286,
"grad_norm": 270.658203125,
"learning_rate": 0.00017969518136887663,
"loss": 1042.8508,
"step": 1430
},
{
"epoch": 0.287,
"grad_norm": 251.15328979492188,
"learning_rate": 0.00017948384552349657,
"loss": 992.9181,
"step": 1435
},
{
"epoch": 0.288,
"grad_norm": 244.953369140625,
"learning_rate": 0.00017927154119254236,
"loss": 966.4935,
"step": 1440
},
{
"epoch": 0.289,
"grad_norm": 397.993896484375,
"learning_rate": 0.0001790582709628753,
"loss": 985.6442,
"step": 1445
},
{
"epoch": 0.29,
"grad_norm": 329.3663330078125,
"learning_rate": 0.00017884403743312582,
"loss": 1016.4588,
"step": 1450
},
{
"epoch": 0.291,
"grad_norm": 225.03994750976562,
"learning_rate": 0.00017862884321366188,
"loss": 984.9711,
"step": 1455
},
{
"epoch": 0.292,
"grad_norm": 325.5677795410156,
"learning_rate": 0.00017841269092655715,
"loss": 941.8141,
"step": 1460
},
{
"epoch": 0.293,
"grad_norm": 245.41311645507812,
"learning_rate": 0.000178195583205559,
"loss": 924.3403,
"step": 1465
},
{
"epoch": 0.294,
"grad_norm": 216.52772521972656,
"learning_rate": 0.00017797752269605653,
"loss": 924.4,
"step": 1470
},
{
"epoch": 0.295,
"grad_norm": 283.37371826171875,
"learning_rate": 0.0001777585120550482,
"loss": 981.6837,
"step": 1475
},
{
"epoch": 0.296,
"grad_norm": 287.1247253417969,
"learning_rate": 0.0001775385539511096,
"loss": 886.0231,
"step": 1480
},
{
"epoch": 0.297,
"grad_norm": 230.0948486328125,
"learning_rate": 0.00017731765106436073,
"loss": 936.1738,
"step": 1485
},
{
"epoch": 0.298,
"grad_norm": 298.68988037109375,
"learning_rate": 0.00017709580608643363,
"loss": 898.0942,
"step": 1490
},
{
"epoch": 0.299,
"grad_norm": 262.3580627441406,
"learning_rate": 0.00017687302172043933,
"loss": 923.3071,
"step": 1495
},
{
"epoch": 0.3,
"grad_norm": 254.61419677734375,
"learning_rate": 0.00017664930068093498,
"loss": 975.1044,
"step": 1500
},
{
"epoch": 0.301,
"grad_norm": 217.88912963867188,
"learning_rate": 0.0001764246456938909,
"loss": 998.1273,
"step": 1505
},
{
"epoch": 0.302,
"grad_norm": 252.59300231933594,
"learning_rate": 0.0001761990594966572,
"loss": 1033.2334,
"step": 1510
},
{
"epoch": 0.303,
"grad_norm": 230.06382751464844,
"learning_rate": 0.00017597254483793048,
"loss": 991.3079,
"step": 1515
},
{
"epoch": 0.304,
"grad_norm": 226.2967529296875,
"learning_rate": 0.00017574510447772039,
"loss": 982.3206,
"step": 1520
},
{
"epoch": 0.305,
"grad_norm": 310.20782470703125,
"learning_rate": 0.00017551674118731591,
"loss": 987.9093,
"step": 1525
},
{
"epoch": 0.306,
"grad_norm": 243.02679443359375,
"learning_rate": 0.00017528745774925172,
"loss": 999.148,
"step": 1530
},
{
"epoch": 0.307,
"grad_norm": 293.7989501953125,
"learning_rate": 0.00017505725695727412,
"loss": 963.7619,
"step": 1535
},
{
"epoch": 0.308,
"grad_norm": 373.4567565917969,
"learning_rate": 0.00017482614161630714,
"loss": 1027.8258,
"step": 1540
},
{
"epoch": 0.309,
"grad_norm": 219.02389526367188,
"learning_rate": 0.00017459411454241822,
"loss": 1062.3516,
"step": 1545
},
{
"epoch": 0.31,
"grad_norm": 301.466064453125,
"learning_rate": 0.0001743611785627841,
"loss": 998.3525,
"step": 1550
},
{
"epoch": 0.311,
"grad_norm": 484.38128662109375,
"learning_rate": 0.0001741273365156561,
"loss": 1010.5978,
"step": 1555
},
{
"epoch": 0.312,
"grad_norm": 199.44569396972656,
"learning_rate": 0.0001738925912503259,
"loss": 1006.017,
"step": 1560
},
{
"epoch": 0.313,
"grad_norm": 480.85736083984375,
"learning_rate": 0.00017365694562709034,
"loss": 937.8793,
"step": 1565
},
{
"epoch": 0.314,
"grad_norm": 318.4089660644531,
"learning_rate": 0.00017342040251721702,
"loss": 985.6497,
"step": 1570
},
{
"epoch": 0.315,
"grad_norm": 264.94598388671875,
"learning_rate": 0.0001731829648029091,
"loss": 1019.5021,
"step": 1575
},
{
"epoch": 0.316,
"grad_norm": 332.982421875,
"learning_rate": 0.00017294463537727024,
"loss": 983.5896,
"step": 1580
},
{
"epoch": 0.317,
"grad_norm": 300.7051086425781,
"learning_rate": 0.0001727054171442692,
"loss": 992.75,
"step": 1585
},
{
"epoch": 0.318,
"grad_norm": 198.2728729248047,
"learning_rate": 0.0001724653130187047,
"loss": 885.5138,
"step": 1590
},
{
"epoch": 0.319,
"grad_norm": 271.32684326171875,
"learning_rate": 0.0001722243259261697,
"loss": 964.0069,
"step": 1595
},
{
"epoch": 0.32,
"grad_norm": 256.55059814453125,
"learning_rate": 0.0001719824588030159,
"loss": 998.2665,
"step": 1600
},
{
"epoch": 0.321,
"grad_norm": 276.50286865234375,
"learning_rate": 0.00017173971459631787,
"loss": 952.5264,
"step": 1605
},
{
"epoch": 0.322,
"grad_norm": 353.3699645996094,
"learning_rate": 0.00017149609626383717,
"loss": 1031.197,
"step": 1610
},
{
"epoch": 0.323,
"grad_norm": 252.30897521972656,
"learning_rate": 0.00017125160677398626,
"loss": 991.4197,
"step": 1615
},
{
"epoch": 0.324,
"grad_norm": 272.0298156738281,
"learning_rate": 0.0001710062491057925,
"loss": 1002.9248,
"step": 1620
},
{
"epoch": 0.325,
"grad_norm": 238.3763885498047,
"learning_rate": 0.00017076002624886154,
"loss": 988.1311,
"step": 1625
},
{
"epoch": 0.326,
"grad_norm": 271.9325256347656,
"learning_rate": 0.00017051294120334125,
"loss": 956.2119,
"step": 1630
},
{
"epoch": 0.327,
"grad_norm": 206.01406860351562,
"learning_rate": 0.00017026499697988493,
"loss": 980.8301,
"step": 1635
},
{
"epoch": 0.328,
"grad_norm": 193.01438903808594,
"learning_rate": 0.00017001619659961467,
"loss": 943.5215,
"step": 1640
},
{
"epoch": 0.329,
"grad_norm": 194.94969177246094,
"learning_rate": 0.00016976654309408464,
"loss": 926.252,
"step": 1645
},
{
"epoch": 0.33,
"grad_norm": 334.0231018066406,
"learning_rate": 0.000169516039505244,
"loss": 1012.6068,
"step": 1650
},
{
"epoch": 0.331,
"grad_norm": 215.96275329589844,
"learning_rate": 0.0001692646888853999,
"loss": 988.8072,
"step": 1655
},
{
"epoch": 0.332,
"grad_norm": 213.20452880859375,
"learning_rate": 0.00016901249429718032,
"loss": 938.1824,
"step": 1660
},
{
"epoch": 0.333,
"grad_norm": 209.37989807128906,
"learning_rate": 0.00016875945881349676,
"loss": 949.0011,
"step": 1665
},
{
"epoch": 0.334,
"grad_norm": 187.8885498046875,
"learning_rate": 0.0001685055855175067,
"loss": 884.6617,
"step": 1670
},
{
"epoch": 0.335,
"grad_norm": 173.2116241455078,
"learning_rate": 0.0001682508775025762,
"loss": 1018.1157,
"step": 1675
},
{
"epoch": 0.336,
"grad_norm": 170.96185302734375,
"learning_rate": 0.00016799533787224192,
"loss": 958.5279,
"step": 1680
},
{
"epoch": 0.337,
"grad_norm": 194.2239227294922,
"learning_rate": 0.00016773896974017373,
"loss": 947.8539,
"step": 1685
},
{
"epoch": 0.338,
"grad_norm": 212.09201049804688,
"learning_rate": 0.00016748177623013638,
"loss": 931.0213,
"step": 1690
},
{
"epoch": 0.339,
"grad_norm": 225.2246856689453,
"learning_rate": 0.00016722376047595164,
"loss": 929.8265,
"step": 1695
},
{
"epoch": 0.34,
"grad_norm": 389.6763000488281,
"learning_rate": 0.00016696492562145996,
"loss": 932.7968,
"step": 1700
},
{
"epoch": 0.341,
"grad_norm": 239.18089294433594,
"learning_rate": 0.00016670527482048246,
"loss": 1008.8852,
"step": 1705
},
{
"epoch": 0.342,
"grad_norm": 310.074951171875,
"learning_rate": 0.00016644481123678217,
"loss": 905.8467,
"step": 1710
},
{
"epoch": 0.343,
"grad_norm": 211.65293884277344,
"learning_rate": 0.00016618353804402568,
"loss": 916.044,
"step": 1715
},
{
"epoch": 0.344,
"grad_norm": 190.54750061035156,
"learning_rate": 0.00016592145842574433,
"loss": 931.5848,
"step": 1720
},
{
"epoch": 0.345,
"grad_norm": 191.92825317382812,
"learning_rate": 0.00016565857557529566,
"loss": 969.8763,
"step": 1725
},
{
"epoch": 0.346,
"grad_norm": 191.98434448242188,
"learning_rate": 0.00016539489269582416,
"loss": 930.2919,
"step": 1730
},
{
"epoch": 0.347,
"grad_norm": 217.86575317382812,
"learning_rate": 0.00016513041300022255,
"loss": 928.9471,
"step": 1735
},
{
"epoch": 0.348,
"grad_norm": 186.0286865234375,
"learning_rate": 0.00016486513971109243,
"loss": 953.5211,
"step": 1740
},
{
"epoch": 0.349,
"grad_norm": 212.38792419433594,
"learning_rate": 0.0001645990760607051,
"loss": 897.9069,
"step": 1745
},
{
"epoch": 0.35,
"grad_norm": 213.73477172851562,
"learning_rate": 0.0001643322252909622,
"loss": 943.156,
"step": 1750
},
{
"epoch": 0.351,
"grad_norm": 264.6876525878906,
"learning_rate": 0.00016406459065335615,
"loss": 877.3924,
"step": 1755
},
{
"epoch": 0.352,
"grad_norm": 189.0636749267578,
"learning_rate": 0.00016379617540893056,
"loss": 871.5594,
"step": 1760
},
{
"epoch": 0.353,
"grad_norm": 242.30352783203125,
"learning_rate": 0.00016352698282824044,
"loss": 886.9946,
"step": 1765
},
{
"epoch": 0.354,
"grad_norm": 212.8794708251953,
"learning_rate": 0.00016325701619131246,
"loss": 935.4468,
"step": 1770
},
{
"epoch": 0.355,
"grad_norm": 159.4650115966797,
"learning_rate": 0.00016298627878760487,
"loss": 886.414,
"step": 1775
},
{
"epoch": 0.356,
"grad_norm": 200.6586151123047,
"learning_rate": 0.00016271477391596753,
"loss": 935.9916,
"step": 1780
},
{
"epoch": 0.357,
"grad_norm": 211.8888397216797,
"learning_rate": 0.00016244250488460158,
"loss": 966.4819,
"step": 1785
},
{
"epoch": 0.358,
"grad_norm": 176.99398803710938,
"learning_rate": 0.0001621694750110193,
"loss": 925.1163,
"step": 1790
},
{
"epoch": 0.359,
"grad_norm": 234.009521484375,
"learning_rate": 0.00016189568762200348,
"loss": 876.8671,
"step": 1795
},
{
"epoch": 0.36,
"grad_norm": 481.6249084472656,
"learning_rate": 0.00016162114605356703,
"loss": 904.2539,
"step": 1800
},
{
"epoch": 0.361,
"grad_norm": 267.3240966796875,
"learning_rate": 0.00016134585365091243,
"loss": 955.0919,
"step": 1805
},
{
"epoch": 0.362,
"grad_norm": 263.05712890625,
"learning_rate": 0.00016106981376839066,
"loss": 877.24,
"step": 1810
},
{
"epoch": 0.363,
"grad_norm": 301.3690490722656,
"learning_rate": 0.00016079302976946055,
"loss": 917.0097,
"step": 1815
},
{
"epoch": 0.364,
"grad_norm": 425.7259826660156,
"learning_rate": 0.0001605155050266478,
"loss": 876.4016,
"step": 1820
},
{
"epoch": 0.365,
"grad_norm": 241.50657653808594,
"learning_rate": 0.00016023724292150385,
"loss": 920.9963,
"step": 1825
},
{
"epoch": 0.366,
"grad_norm": 209.74761962890625,
"learning_rate": 0.00015995824684456465,
"loss": 902.2588,
"step": 1830
},
{
"epoch": 0.367,
"grad_norm": 162.1882781982422,
"learning_rate": 0.00015967852019530926,
"loss": 919.8326,
"step": 1835
},
{
"epoch": 0.368,
"grad_norm": 164.59991455078125,
"learning_rate": 0.0001593980663821187,
"loss": 893.5674,
"step": 1840
},
{
"epoch": 0.369,
"grad_norm": 262.630126953125,
"learning_rate": 0.0001591168888222342,
"loss": 909.9957,
"step": 1845
},
{
"epoch": 0.37,
"grad_norm": 173.30337524414062,
"learning_rate": 0.00015883499094171554,
"loss": 945.9417,
"step": 1850
},
{
"epoch": 0.371,
"grad_norm": 239.98890686035156,
"learning_rate": 0.0001585523761753994,
"loss": 932.0274,
"step": 1855
},
{
"epoch": 0.372,
"grad_norm": 199.22767639160156,
"learning_rate": 0.00015826904796685762,
"loss": 912.9127,
"step": 1860
},
{
"epoch": 0.373,
"grad_norm": 308.07464599609375,
"learning_rate": 0.00015798500976835493,
"loss": 918.1514,
"step": 1865
},
{
"epoch": 0.374,
"grad_norm": 281.8555603027344,
"learning_rate": 0.00015770026504080718,
"loss": 908.9704,
"step": 1870
},
{
"epoch": 0.375,
"grad_norm": 244.6559295654297,
"learning_rate": 0.000157414817253739,
"loss": 904.5717,
"step": 1875
},
{
"epoch": 0.376,
"grad_norm": 241.09442138671875,
"learning_rate": 0.00015712866988524155,
"loss": 900.7095,
"step": 1880
},
{
"epoch": 0.377,
"grad_norm": 169.1940460205078,
"learning_rate": 0.0001568418264219303,
"loss": 884.3492,
"step": 1885
},
{
"epoch": 0.378,
"grad_norm": 223.1148223876953,
"learning_rate": 0.0001565542903589023,
"loss": 810.9526,
"step": 1890
},
{
"epoch": 0.379,
"grad_norm": 194.6370391845703,
"learning_rate": 0.0001562660651996937,
"loss": 911.8098,
"step": 1895
},
{
"epoch": 0.38,
"grad_norm": 224.44166564941406,
"learning_rate": 0.00015597715445623712,
"loss": 890.4894,
"step": 1900
},
{
"epoch": 0.381,
"grad_norm": 197.1553192138672,
"learning_rate": 0.00015568756164881882,
"loss": 879.0866,
"step": 1905
},
{
"epoch": 0.382,
"grad_norm": 215.31675720214844,
"learning_rate": 0.00015539729030603574,
"loss": 864.9854,
"step": 1910
},
{
"epoch": 0.383,
"grad_norm": 261.93701171875,
"learning_rate": 0.0001551063439647526,
"loss": 882.0579,
"step": 1915
},
{
"epoch": 0.384,
"grad_norm": 183.36761474609375,
"learning_rate": 0.00015481472617005876,
"loss": 875.2665,
"step": 1920
},
{
"epoch": 0.385,
"grad_norm": 163.30677795410156,
"learning_rate": 0.00015452244047522502,
"loss": 855.2938,
"step": 1925
},
{
"epoch": 0.386,
"grad_norm": 214.3231658935547,
"learning_rate": 0.0001542294904416603,
"loss": 883.9722,
"step": 1930
},
{
"epoch": 0.387,
"grad_norm": 190.446533203125,
"learning_rate": 0.00015393587963886835,
"loss": 857.4982,
"step": 1935
},
{
"epoch": 0.388,
"grad_norm": 226.16278076171875,
"learning_rate": 0.0001536416116444041,
"loss": 904.5661,
"step": 1940
},
{
"epoch": 0.389,
"grad_norm": 282.7427673339844,
"learning_rate": 0.0001533466900438303,
"loss": 928.903,
"step": 1945
},
{
"epoch": 0.39,
"grad_norm": 203.53872680664062,
"learning_rate": 0.0001530511184306734,
"loss": 942.1082,
"step": 1950
},
{
"epoch": 0.391,
"grad_norm": 216.16693115234375,
"learning_rate": 0.00015275490040638038,
"loss": 906.7809,
"step": 1955
},
{
"epoch": 0.392,
"grad_norm": 165.1854248046875,
"learning_rate": 0.00015245803958027434,
"loss": 865.307,
"step": 1960
},
{
"epoch": 0.393,
"grad_norm": 202.11607360839844,
"learning_rate": 0.0001521605395695108,
"loss": 882.6717,
"step": 1965
},
{
"epoch": 0.394,
"grad_norm": 299.2461242675781,
"learning_rate": 0.00015186240399903342,
"loss": 901.993,
"step": 1970
},
{
"epoch": 0.395,
"grad_norm": 161.959716796875,
"learning_rate": 0.00015156363650153012,
"loss": 928.0579,
"step": 1975
},
{
"epoch": 0.396,
"grad_norm": 152.3892059326172,
"learning_rate": 0.0001512642407173885,
"loss": 924.4011,
"step": 1980
},
{
"epoch": 0.397,
"grad_norm": 207.178955078125,
"learning_rate": 0.00015096422029465178,
"loss": 891.941,
"step": 1985
},
{
"epoch": 0.398,
"grad_norm": 155.3944091796875,
"learning_rate": 0.0001506635788889741,
"loss": 816.7288,
"step": 1990
},
{
"epoch": 0.399,
"grad_norm": 241.54981994628906,
"learning_rate": 0.0001503623201635761,
"loss": 891.3294,
"step": 1995
},
{
"epoch": 0.4,
"grad_norm": 215.03546142578125,
"learning_rate": 0.0001500604477892003,
"loss": 873.6715,
"step": 2000
},
{
"epoch": 0.401,
"grad_norm": 160.4420166015625,
"learning_rate": 0.00014975796544406625,
"loss": 837.3065,
"step": 2005
},
{
"epoch": 0.402,
"grad_norm": 179.46249389648438,
"learning_rate": 0.00014945487681382598,
"loss": 861.33,
"step": 2010
},
{
"epoch": 0.403,
"grad_norm": 170.68350219726562,
"learning_rate": 0.0001491511855915187,
"loss": 854.8689,
"step": 2015
},
{
"epoch": 0.404,
"grad_norm": 187.6792449951172,
"learning_rate": 0.0001488468954775262,
"loss": 897.0034,
"step": 2020
},
{
"epoch": 0.405,
"grad_norm": 276.7402648925781,
"learning_rate": 0.0001485420101795274,
"loss": 867.1588,
"step": 2025
},
{
"epoch": 0.406,
"grad_norm": 249.02096557617188,
"learning_rate": 0.00014823653341245353,
"loss": 917.8216,
"step": 2030
},
{
"epoch": 0.407,
"grad_norm": 256.35418701171875,
"learning_rate": 0.0001479304688984425,
"loss": 910.963,
"step": 2035
},
{
"epoch": 0.408,
"grad_norm": 203.86692810058594,
"learning_rate": 0.0001476238203667939,
"loss": 912.6508,
"step": 2040
},
{
"epoch": 0.409,
"grad_norm": 198.213134765625,
"learning_rate": 0.00014731659155392332,
"loss": 859.705,
"step": 2045
},
{
"epoch": 0.41,
"grad_norm": 189.66043090820312,
"learning_rate": 0.00014700878620331684,
"loss": 860.2014,
"step": 2050
},
{
"epoch": 0.411,
"grad_norm": 178.77279663085938,
"learning_rate": 0.00014670040806548555,
"loss": 846.1357,
"step": 2055
},
{
"epoch": 0.412,
"grad_norm": 184.94345092773438,
"learning_rate": 0.0001463914608979197,
"loss": 876.095,
"step": 2060
},
{
"epoch": 0.413,
"grad_norm": 220.1967315673828,
"learning_rate": 0.0001460819484650431,
"loss": 882.9072,
"step": 2065
},
{
"epoch": 0.414,
"grad_norm": 182.5173797607422,
"learning_rate": 0.000145771874538167,
"loss": 845.1943,
"step": 2070
},
{
"epoch": 0.415,
"grad_norm": 230.20089721679688,
"learning_rate": 0.0001454612428954444,
"loss": 899.0667,
"step": 2075
},
{
"epoch": 0.416,
"grad_norm": 160.44415283203125,
"learning_rate": 0.00014515005732182383,
"loss": 858.749,
"step": 2080
},
{
"epoch": 0.417,
"grad_norm": 154.7128143310547,
"learning_rate": 0.00014483832160900326,
"loss": 852.5743,
"step": 2085
},
{
"epoch": 0.418,
"grad_norm": 196.9201202392578,
"learning_rate": 0.00014452603955538397,
"loss": 898.7283,
"step": 2090
},
{
"epoch": 0.419,
"grad_norm": 185.637939453125,
"learning_rate": 0.00014421321496602428,
"loss": 876.3255,
"step": 2095
},
{
"epoch": 0.42,
"grad_norm": 189.37393188476562,
"learning_rate": 0.00014389985165259308,
"loss": 897.3831,
"step": 2100
},
{
"epoch": 0.421,
"grad_norm": 212.31695556640625,
"learning_rate": 0.00014358595343332342,
"loss": 871.6611,
"step": 2105
},
{
"epoch": 0.422,
"grad_norm": 245.71499633789062,
"learning_rate": 0.00014327152413296608,
"loss": 855.5849,
"step": 2110
},
{
"epoch": 0.423,
"grad_norm": 149.73187255859375,
"learning_rate": 0.00014295656758274284,
"loss": 900.5024,
"step": 2115
},
{
"epoch": 0.424,
"grad_norm": 186.3016357421875,
"learning_rate": 0.0001426410876202999,
"loss": 850.3905,
"step": 2120
},
{
"epoch": 0.425,
"grad_norm": 152.69985961914062,
"learning_rate": 0.00014232508808966098,
"loss": 861.7628,
"step": 2125
},
{
"epoch": 0.426,
"grad_norm": 167.29525756835938,
"learning_rate": 0.00014200857284118066,
"loss": 845.4555,
"step": 2130
},
{
"epoch": 0.427,
"grad_norm": 354.45928955078125,
"learning_rate": 0.00014169154573149737,
"loss": 816.6266,
"step": 2135
},
{
"epoch": 0.428,
"grad_norm": 240.51016235351562,
"learning_rate": 0.00014137401062348638,
"loss": 884.0559,
"step": 2140
},
{
"epoch": 0.429,
"grad_norm": 231.72955322265625,
"learning_rate": 0.0001410559713862128,
"loss": 843.3504,
"step": 2145
},
{
"epoch": 0.43,
"grad_norm": 198.82933044433594,
"learning_rate": 0.00014073743189488435,
"loss": 875.6216,
"step": 2150
},
{
"epoch": 0.431,
"grad_norm": 225.33212280273438,
"learning_rate": 0.00014041839603080422,
"loss": 871.6975,
"step": 2155
},
{
"epoch": 0.432,
"grad_norm": 186.19754028320312,
"learning_rate": 0.00014009886768132375,
"loss": 804.6383,
"step": 2160
},
{
"epoch": 0.433,
"grad_norm": 153.83383178710938,
"learning_rate": 0.000139778850739795,
"loss": 869.9248,
"step": 2165
},
{
"epoch": 0.434,
"grad_norm": 165.3201141357422,
"learning_rate": 0.0001394583491055234,
"loss": 876.4612,
"step": 2170
},
{
"epoch": 0.435,
"grad_norm": 207.56594848632812,
"learning_rate": 0.00013913736668372026,
"loss": 878.3475,
"step": 2175
},
{
"epoch": 0.436,
"grad_norm": 163.65525817871094,
"learning_rate": 0.00013881590738545508,
"loss": 882.8765,
"step": 2180
},
{
"epoch": 0.437,
"grad_norm": 170.30677795410156,
"learning_rate": 0.00013849397512760795,
"loss": 869.7988,
"step": 2185
},
{
"epoch": 0.438,
"grad_norm": 236.1302490234375,
"learning_rate": 0.00013817157383282184,
"loss": 773.8237,
"step": 2190
},
{
"epoch": 0.439,
"grad_norm": 149.98876953125,
"learning_rate": 0.00013784870742945482,
"loss": 844.1923,
"step": 2195
},
{
"epoch": 0.44,
"grad_norm": 191.5624237060547,
"learning_rate": 0.0001375253798515321,
"loss": 829.0846,
"step": 2200
},
{
"epoch": 0.441,
"grad_norm": 134.98147583007812,
"learning_rate": 0.00013720159503869815,
"loss": 832.3159,
"step": 2205
},
{
"epoch": 0.442,
"grad_norm": 152.71177673339844,
"learning_rate": 0.00013687735693616876,
"loss": 858.6977,
"step": 2210
},
{
"epoch": 0.443,
"grad_norm": 184.22427368164062,
"learning_rate": 0.0001365526694946829,
"loss": 826.8185,
"step": 2215
},
{
"epoch": 0.444,
"grad_norm": 191.1162872314453,
"learning_rate": 0.00013622753667045457,
"loss": 862.5157,
"step": 2220
},
{
"epoch": 0.445,
"grad_norm": 214.53329467773438,
"learning_rate": 0.00013590196242512463,
"loss": 825.6411,
"step": 2225
},
{
"epoch": 0.446,
"grad_norm": 133.87489318847656,
"learning_rate": 0.0001355759507257125,
"loss": 831.7165,
"step": 2230
},
{
"epoch": 0.447,
"grad_norm": 169.10635375976562,
"learning_rate": 0.00013524950554456784,
"loss": 825.8194,
"step": 2235
},
{
"epoch": 0.448,
"grad_norm": 182.6426239013672,
"learning_rate": 0.00013492263085932224,
"loss": 843.8969,
"step": 2240
},
{
"epoch": 0.449,
"grad_norm": 145.77874755859375,
"learning_rate": 0.0001345953306528405,
"loss": 839.0958,
"step": 2245
},
{
"epoch": 0.45,
"grad_norm": 170.81744384765625,
"learning_rate": 0.00013426760891317236,
"loss": 833.7206,
"step": 2250
},
{
"epoch": 0.451,
"grad_norm": 198.10079956054688,
"learning_rate": 0.00013393946963350382,
"loss": 845.4177,
"step": 2255
},
{
"epoch": 0.452,
"grad_norm": 210.34024047851562,
"learning_rate": 0.00013361091681210845,
"loss": 853.7811,
"step": 2260
},
{
"epoch": 0.453,
"grad_norm": 157.50473022460938,
"learning_rate": 0.00013328195445229868,
"loss": 810.2634,
"step": 2265
},
{
"epoch": 0.454,
"grad_norm": 202.32183837890625,
"learning_rate": 0.00013295258656237702,
"loss": 827.9448,
"step": 2270
},
{
"epoch": 0.455,
"grad_norm": 144.81845092773438,
"learning_rate": 0.00013262281715558736,
"loss": 880.4411,
"step": 2275
},
{
"epoch": 0.456,
"grad_norm": 175.393310546875,
"learning_rate": 0.00013229265025006576,
"loss": 875.6698,
"step": 2280
},
{
"epoch": 0.457,
"grad_norm": 189.14453125,
"learning_rate": 0.0001319620898687918,
"loss": 872.7545,
"step": 2285
},
{
"epoch": 0.458,
"grad_norm": 165.8527374267578,
"learning_rate": 0.0001316311400395394,
"loss": 832.5983,
"step": 2290
},
{
"epoch": 0.459,
"grad_norm": 191.5207977294922,
"learning_rate": 0.00013129980479482782,
"loss": 862.4879,
"step": 2295
},
{
"epoch": 0.46,
"grad_norm": 148.66961669921875,
"learning_rate": 0.00013096808817187242,
"loss": 844.0641,
"step": 2300
},
{
"epoch": 0.461,
"grad_norm": 133.65966796875,
"learning_rate": 0.00013063599421253558,
"loss": 836.5675,
"step": 2305
},
{
"epoch": 0.462,
"grad_norm": 189.5343780517578,
"learning_rate": 0.00013030352696327742,
"loss": 836.8811,
"step": 2310
},
{
"epoch": 0.463,
"grad_norm": 169.067138671875,
"learning_rate": 0.0001299706904751064,
"loss": 842.2365,
"step": 2315
},
{
"epoch": 0.464,
"grad_norm": 194.0730743408203,
"learning_rate": 0.00012963748880353011,
"loss": 856.8031,
"step": 2320
},
{
"epoch": 0.465,
"grad_norm": 152.25364685058594,
"learning_rate": 0.00012930392600850573,
"loss": 832.5722,
"step": 2325
},
{
"epoch": 0.466,
"grad_norm": 221.9500732421875,
"learning_rate": 0.00012897000615439075,
"loss": 838.951,
"step": 2330
},
{
"epoch": 0.467,
"grad_norm": 160.90829467773438,
"learning_rate": 0.00012863573330989313,
"loss": 821.7913,
"step": 2335
},
{
"epoch": 0.468,
"grad_norm": 487.2472839355469,
"learning_rate": 0.00012830111154802203,
"loss": 959.618,
"step": 2340
},
{
"epoch": 0.469,
"grad_norm": 182.27003479003906,
"learning_rate": 0.000127966144946038,
"loss": 860.8049,
"step": 2345
},
{
"epoch": 0.47,
"grad_norm": 142.95794677734375,
"learning_rate": 0.00012763083758540337,
"loss": 862.508,
"step": 2350
},
{
"epoch": 0.471,
"grad_norm": 158.31808471679688,
"learning_rate": 0.00012729519355173254,
"loss": 876.9683,
"step": 2355
},
{
"epoch": 0.472,
"grad_norm": 161.0455780029297,
"learning_rate": 0.00012695921693474212,
"loss": 828.6441,
"step": 2360
},
{
"epoch": 0.473,
"grad_norm": 164.43112182617188,
"learning_rate": 0.00012662291182820114,
"loss": 816.7979,
"step": 2365
},
{
"epoch": 0.474,
"grad_norm": 434.65869140625,
"learning_rate": 0.0001262862823298812,
"loss": 888.6695,
"step": 2370
},
{
"epoch": 0.475,
"grad_norm": 180.43838500976562,
"learning_rate": 0.00012594933254150655,
"loss": 843.5484,
"step": 2375
},
{
"epoch": 0.476,
"grad_norm": 207.7638702392578,
"learning_rate": 0.00012561206656870396,
"loss": 843.8125,
"step": 2380
},
{
"epoch": 0.477,
"grad_norm": 184.69137573242188,
"learning_rate": 0.00012527448852095295,
"loss": 833.9275,
"step": 2385
},
{
"epoch": 0.478,
"grad_norm": 222.78887939453125,
"learning_rate": 0.0001249366025115354,
"loss": 835.312,
"step": 2390
},
{
"epoch": 0.479,
"grad_norm": 178.5324249267578,
"learning_rate": 0.0001245984126574858,
"loss": 812.073,
"step": 2395
},
{
"epoch": 0.48,
"grad_norm": 152.6232147216797,
"learning_rate": 0.00012425992307954075,
"loss": 815.533,
"step": 2400
},
{
"epoch": 0.481,
"grad_norm": 148.00204467773438,
"learning_rate": 0.00012392113790208895,
"loss": 795.3915,
"step": 2405
},
{
"epoch": 0.482,
"grad_norm": 146.94435119628906,
"learning_rate": 0.00012358206125312083,
"loss": 804.4675,
"step": 2410
},
{
"epoch": 0.483,
"grad_norm": 274.63092041015625,
"learning_rate": 0.0001232426972641784,
"loss": 866.7372,
"step": 2415
},
{
"epoch": 0.484,
"grad_norm": 176.61778259277344,
"learning_rate": 0.00012290305007030478,
"loss": 864.5067,
"step": 2420
},
{
"epoch": 0.485,
"grad_norm": 329.15313720703125,
"learning_rate": 0.00012256312380999376,
"loss": 815.2946,
"step": 2425
},
{
"epoch": 0.486,
"grad_norm": 324.6814270019531,
"learning_rate": 0.00012222292262513965,
"loss": 789.3961,
"step": 2430
},
{
"epoch": 0.487,
"grad_norm": 173.1524200439453,
"learning_rate": 0.00012188245066098647,
"loss": 819.9521,
"step": 2435
},
{
"epoch": 0.488,
"grad_norm": 188.3359832763672,
"learning_rate": 0.00012154171206607764,
"loss": 794.5644,
"step": 2440
},
{
"epoch": 0.489,
"grad_norm": 161.2691192626953,
"learning_rate": 0.00012120071099220549,
"loss": 831.5152,
"step": 2445
},
{
"epoch": 0.49,
"grad_norm": 228.6628875732422,
"learning_rate": 0.00012085945159436038,
"loss": 823.1729,
"step": 2450
},
{
"epoch": 0.491,
"grad_norm": 180.9890594482422,
"learning_rate": 0.00012051793803068046,
"loss": 812.7895,
"step": 2455
},
{
"epoch": 0.492,
"grad_norm": 187.55079650878906,
"learning_rate": 0.0001201761744624007,
"loss": 799.705,
"step": 2460
},
{
"epoch": 0.493,
"grad_norm": 181.92738342285156,
"learning_rate": 0.00011983416505380234,
"loss": 851.9943,
"step": 2465
},
{
"epoch": 0.494,
"grad_norm": 199.51272583007812,
"learning_rate": 0.00011949191397216206,
"loss": 852.3304,
"step": 2470
},
{
"epoch": 0.495,
"grad_norm": 234.70330810546875,
"learning_rate": 0.00011914942538770131,
"loss": 836.6265,
"step": 2475
},
{
"epoch": 0.496,
"grad_norm": 138.83944702148438,
"learning_rate": 0.00011880670347353539,
"loss": 822.9405,
"step": 2480
},
{
"epoch": 0.497,
"grad_norm": 178.9021453857422,
"learning_rate": 0.0001184637524056227,
"loss": 851.2311,
"step": 2485
},
{
"epoch": 0.498,
"grad_norm": 193.6486053466797,
"learning_rate": 0.00011812057636271374,
"loss": 791.2046,
"step": 2490
},
{
"epoch": 0.499,
"grad_norm": 196.60572814941406,
"learning_rate": 0.00011777717952630031,
"loss": 862.4189,
"step": 2495
},
{
"epoch": 0.5,
"grad_norm": 291.8324890136719,
"learning_rate": 0.00011743356608056449,
"loss": 822.1684,
"step": 2500
},
{
"epoch": 0.501,
"grad_norm": 265.4393310546875,
"learning_rate": 0.00011708974021232769,
"loss": 867.2006,
"step": 2505
},
{
"epoch": 0.502,
"grad_norm": 154.43882751464844,
"learning_rate": 0.00011674570611099955,
"loss": 805.2405,
"step": 2510
},
{
"epoch": 0.503,
"grad_norm": 277.2109375,
"learning_rate": 0.00011640146796852711,
"loss": 801.9671,
"step": 2515
},
{
"epoch": 0.504,
"grad_norm": 167.88511657714844,
"learning_rate": 0.00011605702997934345,
"loss": 815.2396,
"step": 2520
},
{
"epoch": 0.505,
"grad_norm": 205.5147705078125,
"learning_rate": 0.00011571239634031679,
"loss": 822.219,
"step": 2525
},
{
"epoch": 0.506,
"grad_norm": 162.12977600097656,
"learning_rate": 0.00011536757125069923,
"loss": 849.6047,
"step": 2530
},
{
"epoch": 0.507,
"grad_norm": 175.38499450683594,
"learning_rate": 0.00011502255891207572,
"loss": 834.8542,
"step": 2535
},
{
"epoch": 0.508,
"grad_norm": 157.32347106933594,
"learning_rate": 0.00011467736352831266,
"loss": 813.3625,
"step": 2540
},
{
"epoch": 0.509,
"grad_norm": 159.6200408935547,
"learning_rate": 0.00011433198930550695,
"loss": 825.0824,
"step": 2545
},
{
"epoch": 0.51,
"grad_norm": 150.39125061035156,
"learning_rate": 0.00011398644045193444,
"loss": 835.2948,
"step": 2550
},
{
"epoch": 0.511,
"grad_norm": 167.98046875,
"learning_rate": 0.00011364072117799885,
"loss": 809.6759,
"step": 2555
},
{
"epoch": 0.512,
"grad_norm": 210.5797119140625,
"learning_rate": 0.00011329483569618045,
"loss": 817.4881,
"step": 2560
},
{
"epoch": 0.513,
"grad_norm": 132.72593688964844,
"learning_rate": 0.00011294878822098469,
"loss": 842.5558,
"step": 2565
},
{
"epoch": 0.514,
"grad_norm": 178.2217254638672,
"learning_rate": 0.00011260258296889086,
"loss": 778.5318,
"step": 2570
},
{
"epoch": 0.515,
"grad_norm": 481.5330810546875,
"learning_rate": 0.00011225622415830068,
"loss": 644.6433,
"step": 2575
},
{
"epoch": 0.516,
"grad_norm": 169.58985900878906,
"learning_rate": 0.00011190971600948699,
"loss": 769.8687,
"step": 2580
},
{
"epoch": 0.517,
"grad_norm": 140.553955078125,
"learning_rate": 0.00011156306274454218,
"loss": 784.2127,
"step": 2585
},
{
"epoch": 0.518,
"grad_norm": 133.93504333496094,
"learning_rate": 0.0001112162685873269,
"loss": 792.4177,
"step": 2590
},
{
"epoch": 0.519,
"grad_norm": 143.3046417236328,
"learning_rate": 0.00011086933776341852,
"loss": 814.5849,
"step": 2595
},
{
"epoch": 0.52,
"grad_norm": 158.92787170410156,
"learning_rate": 0.00011052227450005967,
"loss": 768.5281,
"step": 2600
},
{
"epoch": 0.521,
"grad_norm": 153.1136016845703,
"learning_rate": 0.00011017508302610664,
"loss": 791.6676,
"step": 2605
},
{
"epoch": 0.522,
"grad_norm": 133.82943725585938,
"learning_rate": 0.00010982776757197799,
"loss": 875.2488,
"step": 2610
},
{
"epoch": 0.523,
"grad_norm": 270.63812255859375,
"learning_rate": 0.00010948033236960294,
"loss": 816.948,
"step": 2615
},
{
"epoch": 0.524,
"grad_norm": 135.55084228515625,
"learning_rate": 0.00010913278165236978,
"loss": 823.8183,
"step": 2620
},
{
"epoch": 0.525,
"grad_norm": 184.64266967773438,
"learning_rate": 0.00010878511965507434,
"loss": 834.5635,
"step": 2625
},
{
"epoch": 0.526,
"grad_norm": 199.2083282470703,
"learning_rate": 0.00010843735061386828,
"loss": 769.5794,
"step": 2630
},
{
"epoch": 0.527,
"grad_norm": 288.3158264160156,
"learning_rate": 0.00010808947876620767,
"loss": 794.0706,
"step": 2635
},
{
"epoch": 0.528,
"grad_norm": 155.88998413085938,
"learning_rate": 0.00010774150835080119,
"loss": 749.0082,
"step": 2640
},
{
"epoch": 0.529,
"grad_norm": 164.1727294921875,
"learning_rate": 0.00010739344360755852,
"loss": 837.0731,
"step": 2645
},
{
"epoch": 0.53,
"grad_norm": 150.399658203125,
"learning_rate": 0.0001070452887775387,
"loss": 809.6169,
"step": 2650
},
{
"epoch": 0.531,
"grad_norm": 175.54684448242188,
"learning_rate": 0.00010669704810289851,
"loss": 817.6178,
"step": 2655
},
{
"epoch": 0.532,
"grad_norm": 267.57818603515625,
"learning_rate": 0.00010634872582684061,
"loss": 831.9534,
"step": 2660
},
{
"epoch": 0.533,
"grad_norm": 217.36386108398438,
"learning_rate": 0.00010600032619356209,
"loss": 825.4096,
"step": 2665
},
{
"epoch": 0.534,
"grad_norm": 195.0107421875,
"learning_rate": 0.00010565185344820247,
"loss": 822.8702,
"step": 2670
},
{
"epoch": 0.535,
"grad_norm": 172.881591796875,
"learning_rate": 0.00010530331183679218,
"loss": 802.696,
"step": 2675
},
{
"epoch": 0.536,
"grad_norm": 139.90159606933594,
"learning_rate": 0.00010495470560620083,
"loss": 815.2499,
"step": 2680
},
{
"epoch": 0.537,
"grad_norm": 140.33912658691406,
"learning_rate": 0.00010460603900408523,
"loss": 809.8368,
"step": 2685
},
{
"epoch": 0.538,
"grad_norm": 143.82052612304688,
"learning_rate": 0.00010425731627883797,
"loss": 807.0465,
"step": 2690
},
{
"epoch": 0.539,
"grad_norm": 107.30050659179688,
"learning_rate": 0.00010390854167953537,
"loss": 815.4495,
"step": 2695
},
{
"epoch": 0.54,
"grad_norm": 136.02220153808594,
"learning_rate": 0.00010355971945588585,
"loss": 827.2295,
"step": 2700
},
{
"epoch": 0.541,
"grad_norm": 116.0698013305664,
"learning_rate": 0.00010321085385817817,
"loss": 771.4588,
"step": 2705
},
{
"epoch": 0.542,
"grad_norm": 149.52056884765625,
"learning_rate": 0.00010286194913722948,
"loss": 868.0029,
"step": 2710
},
{
"epoch": 0.543,
"grad_norm": 143.8325653076172,
"learning_rate": 0.00010251300954433376,
"loss": 757.1806,
"step": 2715
},
{
"epoch": 0.544,
"grad_norm": 151.38221740722656,
"learning_rate": 0.00010216403933120979,
"loss": 809.9926,
"step": 2720
},
{
"epoch": 0.545,
"grad_norm": 152.74847412109375,
"learning_rate": 0.00010181504274994948,
"loss": 819.6856,
"step": 2725
},
{
"epoch": 0.546,
"grad_norm": 132.6685333251953,
"learning_rate": 0.00010146602405296607,
"loss": 808.8384,
"step": 2730
},
{
"epoch": 0.547,
"grad_norm": 142.92433166503906,
"learning_rate": 0.00010111698749294223,
"loss": 809.297,
"step": 2735
},
{
"epoch": 0.548,
"grad_norm": 135.9753875732422,
"learning_rate": 0.00010076793732277829,
"loss": 798.764,
"step": 2740
},
{
"epoch": 0.549,
"grad_norm": 149.92601013183594,
"learning_rate": 0.0001004188777955404,
"loss": 780.8618,
"step": 2745
},
{
"epoch": 0.55,
"grad_norm": 120.03385162353516,
"learning_rate": 0.00010006981316440875,
"loss": 795.1664,
"step": 2750
},
{
"epoch": 0.551,
"grad_norm": 155.63893127441406,
"learning_rate": 9.972074768262576e-05,
"loss": 807.7022,
"step": 2755
},
{
"epoch": 0.552,
"grad_norm": 114.12002563476562,
"learning_rate": 9.937168560344412e-05,
"loss": 784.8116,
"step": 2760
},
{
"epoch": 0.553,
"grad_norm": 168.14593505859375,
"learning_rate": 9.902263118007513e-05,
"loss": 799.9511,
"step": 2765
},
{
"epoch": 0.554,
"grad_norm": 129.99725341796875,
"learning_rate": 9.867358866563673e-05,
"loss": 767.1122,
"step": 2770
},
{
"epoch": 0.555,
"grad_norm": 145.47637939453125,
"learning_rate": 9.832456231310189e-05,
"loss": 832.7085,
"step": 2775
},
{
"epoch": 0.556,
"grad_norm": 151.25416564941406,
"learning_rate": 9.797555637524649e-05,
"loss": 833.8287,
"step": 2780
},
{
"epoch": 0.557,
"grad_norm": 186.23486328125,
"learning_rate": 9.762657510459783e-05,
"loss": 812.7203,
"step": 2785
},
{
"epoch": 0.558,
"grad_norm": 169.421875,
"learning_rate": 9.727762275338246e-05,
"loss": 802.2107,
"step": 2790
},
{
"epoch": 0.559,
"grad_norm": 338.2839660644531,
"learning_rate": 9.692870357347473e-05,
"loss": 775.4507,
"step": 2795
},
{
"epoch": 0.56,
"grad_norm": 156.75137329101562,
"learning_rate": 9.657982181634475e-05,
"loss": 807.304,
"step": 2800
},
{
"epoch": 0.561,
"grad_norm": 130.74855041503906,
"learning_rate": 9.623098173300654e-05,
"loss": 816.2872,
"step": 2805
},
{
"epoch": 0.562,
"grad_norm": 140.08087158203125,
"learning_rate": 9.588218757396655e-05,
"loss": 796.5068,
"step": 2810
},
{
"epoch": 0.563,
"grad_norm": 144.9915771484375,
"learning_rate": 9.55334435891714e-05,
"loss": 824.2264,
"step": 2815
},
{
"epoch": 0.564,
"grad_norm": 133.88232421875,
"learning_rate": 9.518475402795661e-05,
"loss": 745.2025,
"step": 2820
},
{
"epoch": 0.565,
"grad_norm": 145.7711639404297,
"learning_rate": 9.483612313899435e-05,
"loss": 750.5229,
"step": 2825
},
{
"epoch": 0.566,
"grad_norm": 149.07687377929688,
"learning_rate": 9.448755517024206e-05,
"loss": 768.7809,
"step": 2830
},
{
"epoch": 0.567,
"grad_norm": 164.96543884277344,
"learning_rate": 9.413905436889035e-05,
"loss": 821.3931,
"step": 2835
},
{
"epoch": 0.568,
"grad_norm": 133.78567504882812,
"learning_rate": 9.37906249813116e-05,
"loss": 770.3438,
"step": 2840
},
{
"epoch": 0.569,
"grad_norm": 177.8256378173828,
"learning_rate": 9.344227125300788e-05,
"loss": 793.7009,
"step": 2845
},
{
"epoch": 0.57,
"grad_norm": 126.65879821777344,
"learning_rate": 9.309399742855942e-05,
"loss": 819.0963,
"step": 2850
},
{
"epoch": 0.571,
"grad_norm": 151.43150329589844,
"learning_rate": 9.274580775157294e-05,
"loss": 801.7747,
"step": 2855
},
{
"epoch": 0.572,
"grad_norm": 141.89642333984375,
"learning_rate": 9.239770646462968e-05,
"loss": 794.124,
"step": 2860
},
{
"epoch": 0.573,
"grad_norm": 203.23561096191406,
"learning_rate": 9.204969780923403e-05,
"loss": 762.5094,
"step": 2865
},
{
"epoch": 0.574,
"grad_norm": 167.36102294921875,
"learning_rate": 9.17017860257616e-05,
"loss": 782.9039,
"step": 2870
},
{
"epoch": 0.575,
"grad_norm": 163.43972778320312,
"learning_rate": 9.135397535340773e-05,
"loss": 814.3578,
"step": 2875
},
{
"epoch": 0.576,
"grad_norm": 153.7261199951172,
"learning_rate": 9.100627003013562e-05,
"loss": 779.1543,
"step": 2880
},
{
"epoch": 0.577,
"grad_norm": 202.79595947265625,
"learning_rate": 9.065867429262496e-05,
"loss": 812.134,
"step": 2885
},
{
"epoch": 0.578,
"grad_norm": 127.43997192382812,
"learning_rate": 9.03111923762201e-05,
"loss": 751.3185,
"step": 2890
},
{
"epoch": 0.579,
"grad_norm": 144.194580078125,
"learning_rate": 8.99638285148785e-05,
"loss": 823.5222,
"step": 2895
},
{
"epoch": 0.58,
"grad_norm": 169.5374755859375,
"learning_rate": 8.961658694111929e-05,
"loss": 818.534,
"step": 2900
},
{
"epoch": 0.581,
"grad_norm": 155.55274963378906,
"learning_rate": 8.926947188597134e-05,
"loss": 805.9754,
"step": 2905
},
{
"epoch": 0.582,
"grad_norm": 119.93128967285156,
"learning_rate": 8.892248757892214e-05,
"loss": 786.0286,
"step": 2910
},
{
"epoch": 0.583,
"grad_norm": 167.47544860839844,
"learning_rate": 8.857563824786596e-05,
"loss": 764.7861,
"step": 2915
},
{
"epoch": 0.584,
"grad_norm": 132.19467163085938,
"learning_rate": 8.822892811905237e-05,
"loss": 765.1289,
"step": 2920
},
{
"epoch": 0.585,
"grad_norm": 131.78787231445312,
"learning_rate": 8.788236141703498e-05,
"loss": 779.2658,
"step": 2925
},
{
"epoch": 0.586,
"grad_norm": 237.951416015625,
"learning_rate": 8.753594236461957e-05,
"loss": 767.5281,
"step": 2930
},
{
"epoch": 0.587,
"grad_norm": 120.70050048828125,
"learning_rate": 8.718967518281307e-05,
"loss": 810.8456,
"step": 2935
},
{
"epoch": 0.588,
"grad_norm": 145.0762939453125,
"learning_rate": 8.684356409077176e-05,
"loss": 758.1484,
"step": 2940
},
{
"epoch": 0.589,
"grad_norm": 128.1086883544922,
"learning_rate": 8.64976133057501e-05,
"loss": 780.6106,
"step": 2945
},
{
"epoch": 0.59,
"grad_norm": 122.51020050048828,
"learning_rate": 8.615182704304918e-05,
"loss": 794.9964,
"step": 2950
},
{
"epoch": 0.591,
"grad_norm": 144.20684814453125,
"learning_rate": 8.580620951596557e-05,
"loss": 805.2985,
"step": 2955
},
{
"epoch": 0.592,
"grad_norm": 155.75184631347656,
"learning_rate": 8.546076493573972e-05,
"loss": 819.1504,
"step": 2960
},
{
"epoch": 0.593,
"grad_norm": 148.36634826660156,
"learning_rate": 8.511549751150479e-05,
"loss": 778.1723,
"step": 2965
},
{
"epoch": 0.594,
"grad_norm": 362.0986633300781,
"learning_rate": 8.477041145023546e-05,
"loss": 739.6347,
"step": 2970
},
{
"epoch": 0.595,
"grad_norm": 169.08551025390625,
"learning_rate": 8.442551095669639e-05,
"loss": 763.5583,
"step": 2975
},
{
"epoch": 0.596,
"grad_norm": 134.86868286132812,
"learning_rate": 8.408080023339133e-05,
"loss": 792.7255,
"step": 2980
},
{
"epoch": 0.597,
"grad_norm": 213.27809143066406,
"learning_rate": 8.373628348051165e-05,
"loss": 764.7088,
"step": 2985
},
{
"epoch": 0.598,
"grad_norm": 145.9313507080078,
"learning_rate": 8.339196489588523e-05,
"loss": 789.4269,
"step": 2990
},
{
"epoch": 0.599,
"grad_norm": 165.81288146972656,
"learning_rate": 8.30478486749254e-05,
"loss": 792.468,
"step": 2995
},
{
"epoch": 0.6,
"grad_norm": 182.40457153320312,
"learning_rate": 8.270393901057964e-05,
"loss": 829.8767,
"step": 3000
},
{
"epoch": 0.601,
"grad_norm": 123.09002685546875,
"learning_rate": 8.236024009327879e-05,
"loss": 837.5494,
"step": 3005
},
{
"epoch": 0.602,
"grad_norm": 145.4431610107422,
"learning_rate": 8.201675611088558e-05,
"loss": 807.6495,
"step": 3010
},
{
"epoch": 0.603,
"grad_norm": 135.4163360595703,
"learning_rate": 8.167349124864405e-05,
"loss": 804.4878,
"step": 3015
},
{
"epoch": 0.604,
"grad_norm": 152.54949951171875,
"learning_rate": 8.133044968912811e-05,
"loss": 761.2072,
"step": 3020
},
{
"epoch": 0.605,
"grad_norm": 151.20590209960938,
"learning_rate": 8.0987635612191e-05,
"loss": 808.5088,
"step": 3025
},
{
"epoch": 0.606,
"grad_norm": 132.63885498046875,
"learning_rate": 8.064505319491398e-05,
"loss": 771.028,
"step": 3030
},
{
"epoch": 0.607,
"grad_norm": 163.3816680908203,
"learning_rate": 8.030270661155574e-05,
"loss": 753.3155,
"step": 3035
},
{
"epoch": 0.608,
"grad_norm": 142.8243408203125,
"learning_rate": 7.996060003350139e-05,
"loss": 823.1657,
"step": 3040
},
{
"epoch": 0.609,
"grad_norm": 133.87303161621094,
"learning_rate": 7.961873762921153e-05,
"loss": 763.2889,
"step": 3045
},
{
"epoch": 0.61,
"grad_norm": 125.75581359863281,
"learning_rate": 7.927712356417176e-05,
"loss": 784.2502,
"step": 3050
},
{
"epoch": 0.611,
"grad_norm": 122.01504516601562,
"learning_rate": 7.893576200084159e-05,
"loss": 784.4317,
"step": 3055
},
{
"epoch": 0.612,
"grad_norm": 128.63099670410156,
"learning_rate": 7.8594657098604e-05,
"loss": 765.4088,
"step": 3060
},
{
"epoch": 0.613,
"grad_norm": 128.91946411132812,
"learning_rate": 7.825381301371452e-05,
"loss": 756.3482,
"step": 3065
},
{
"epoch": 0.614,
"grad_norm": 153.96783447265625,
"learning_rate": 7.791323389925084e-05,
"loss": 811.6901,
"step": 3070
},
{
"epoch": 0.615,
"grad_norm": 114.74537658691406,
"learning_rate": 7.75729239050619e-05,
"loss": 789.4233,
"step": 3075
},
{
"epoch": 0.616,
"grad_norm": 167.40408325195312,
"learning_rate": 7.723288717771761e-05,
"loss": 785.3338,
"step": 3080
},
{
"epoch": 0.617,
"grad_norm": 135.498046875,
"learning_rate": 7.689312786045823e-05,
"loss": 837.2147,
"step": 3085
},
{
"epoch": 0.618,
"grad_norm": 117.9854507446289,
"learning_rate": 7.655365009314374e-05,
"loss": 783.9552,
"step": 3090
},
{
"epoch": 0.619,
"grad_norm": 123.13225555419922,
"learning_rate": 7.621445801220371e-05,
"loss": 797.7458,
"step": 3095
},
{
"epoch": 0.62,
"grad_norm": 148.2063751220703,
"learning_rate": 7.587555575058649e-05,
"loss": 755.1008,
"step": 3100
},
{
"epoch": 0.621,
"grad_norm": 147.5942840576172,
"learning_rate": 7.553694743770928e-05,
"loss": 782.9431,
"step": 3105
},
{
"epoch": 0.622,
"grad_norm": 155.6824188232422,
"learning_rate": 7.519863719940748e-05,
"loss": 767.9115,
"step": 3110
},
{
"epoch": 0.623,
"grad_norm": 123.38619995117188,
"learning_rate": 7.486062915788452e-05,
"loss": 772.6462,
"step": 3115
},
{
"epoch": 0.624,
"grad_norm": 143.84808349609375,
"learning_rate": 7.45229274316618e-05,
"loss": 762.2471,
"step": 3120
},
{
"epoch": 0.625,
"grad_norm": 199.48330688476562,
"learning_rate": 7.418553613552825e-05,
"loss": 791.3727,
"step": 3125
},
{
"epoch": 0.626,
"grad_norm": 211.0545654296875,
"learning_rate": 7.384845938049031e-05,
"loss": 719.78,
"step": 3130
},
{
"epoch": 0.627,
"grad_norm": 319.76409912109375,
"learning_rate": 7.351170127372191e-05,
"loss": 563.9574,
"step": 3135
},
{
"epoch": 0.628,
"grad_norm": 201.25372314453125,
"learning_rate": 7.317526591851433e-05,
"loss": 488.1105,
"step": 3140
},
{
"epoch": 0.629,
"grad_norm": 178.85572814941406,
"learning_rate": 7.283915741422612e-05,
"loss": 470.45,
"step": 3145
},
{
"epoch": 0.63,
"grad_norm": 193.7493133544922,
"learning_rate": 7.250337985623342e-05,
"loss": 473.5503,
"step": 3150
},
{
"epoch": 0.631,
"grad_norm": 114.29776000976562,
"learning_rate": 7.216793733587976e-05,
"loss": 623.0975,
"step": 3155
},
{
"epoch": 0.632,
"grad_norm": 123.51734161376953,
"learning_rate": 7.183283394042634e-05,
"loss": 717.1698,
"step": 3160
},
{
"epoch": 0.633,
"grad_norm": 132.81411743164062,
"learning_rate": 7.149807375300239e-05,
"loss": 801.2156,
"step": 3165
},
{
"epoch": 0.634,
"grad_norm": 120.20478820800781,
"learning_rate": 7.11636608525551e-05,
"loss": 779.116,
"step": 3170
},
{
"epoch": 0.635,
"grad_norm": 128.9480743408203,
"learning_rate": 7.082959931380011e-05,
"loss": 783.6341,
"step": 3175
},
{
"epoch": 0.636,
"grad_norm": 120.74846649169922,
"learning_rate": 7.049589320717186e-05,
"loss": 757.5237,
"step": 3180
},
{
"epoch": 0.637,
"grad_norm": 163.25668334960938,
"learning_rate": 7.016254659877398e-05,
"loss": 766.6184,
"step": 3185
},
{
"epoch": 0.638,
"grad_norm": 152.9709014892578,
"learning_rate": 6.982956355032968e-05,
"loss": 742.6142,
"step": 3190
},
{
"epoch": 0.639,
"grad_norm": 131.53237915039062,
"learning_rate": 6.949694811913225e-05,
"loss": 756.6069,
"step": 3195
},
{
"epoch": 0.64,
"grad_norm": 137.20274353027344,
"learning_rate": 6.916470435799587e-05,
"loss": 729.0635,
"step": 3200
},
{
"epoch": 0.641,
"grad_norm": 172.50946044921875,
"learning_rate": 6.883283631520582e-05,
"loss": 726.232,
"step": 3205
},
{
"epoch": 0.642,
"grad_norm": 125.7096939086914,
"learning_rate": 6.850134803446954e-05,
"loss": 733.4033,
"step": 3210
},
{
"epoch": 0.643,
"grad_norm": 154.6427459716797,
"learning_rate": 6.817024355486706e-05,
"loss": 721.2454,
"step": 3215
},
{
"epoch": 0.644,
"grad_norm": 241.71302795410156,
"learning_rate": 6.783952691080203e-05,
"loss": 750.08,
"step": 3220
},
{
"epoch": 0.645,
"grad_norm": 139.3504180908203,
"learning_rate": 6.750920213195238e-05,
"loss": 755.3592,
"step": 3225
},
{
"epoch": 0.646,
"grad_norm": 177.2030029296875,
"learning_rate": 6.717927324322124e-05,
"loss": 719.8516,
"step": 3230
},
{
"epoch": 0.647,
"grad_norm": 127.54790496826172,
"learning_rate": 6.684974426468808e-05,
"loss": 813.4113,
"step": 3235
},
{
"epoch": 0.648,
"grad_norm": 138.21978759765625,
"learning_rate": 6.652061921155943e-05,
"loss": 791.7522,
"step": 3240
},
{
"epoch": 0.649,
"grad_norm": 147.03927612304688,
"learning_rate": 6.61919020941203e-05,
"loss": 777.2082,
"step": 3245
},
{
"epoch": 0.65,
"grad_norm": 172.43484497070312,
"learning_rate": 6.58635969176849e-05,
"loss": 800.4409,
"step": 3250
},
{
"epoch": 0.651,
"grad_norm": 108.15738677978516,
"learning_rate": 6.55357076825483e-05,
"loss": 748.914,
"step": 3255
},
{
"epoch": 0.652,
"grad_norm": 159.50357055664062,
"learning_rate": 6.520823838393731e-05,
"loss": 753.5385,
"step": 3260
},
{
"epoch": 0.653,
"grad_norm": 114.12923431396484,
"learning_rate": 6.488119301196201e-05,
"loss": 778.383,
"step": 3265
},
{
"epoch": 0.654,
"grad_norm": 148.7251739501953,
"learning_rate": 6.455457555156705e-05,
"loss": 740.0044,
"step": 3270
},
{
"epoch": 0.655,
"grad_norm": 183.39170837402344,
"learning_rate": 6.422838998248307e-05,
"loss": 720.3347,
"step": 3275
},
{
"epoch": 0.656,
"grad_norm": 130.4141082763672,
"learning_rate": 6.390264027917836e-05,
"loss": 748.4357,
"step": 3280
},
{
"epoch": 0.657,
"grad_norm": 499.4146728515625,
"learning_rate": 6.357733041081018e-05,
"loss": 745.7531,
"step": 3285
},
{
"epoch": 0.658,
"grad_norm": 151.0502166748047,
"learning_rate": 6.325246434117668e-05,
"loss": 711.5639,
"step": 3290
},
{
"epoch": 0.659,
"grad_norm": 119.97664642333984,
"learning_rate": 6.292804602866834e-05,
"loss": 806.5756,
"step": 3295
},
{
"epoch": 0.66,
"grad_norm": 115.34526062011719,
"learning_rate": 6.260407942621998e-05,
"loss": 781.869,
"step": 3300
},
{
"epoch": 0.661,
"grad_norm": 183.5809326171875,
"learning_rate": 6.228056848126236e-05,
"loss": 779.2279,
"step": 3305
},
{
"epoch": 0.662,
"grad_norm": 134.220703125,
"learning_rate": 6.195751713567427e-05,
"loss": 746.7994,
"step": 3310
},
{
"epoch": 0.663,
"grad_norm": 145.3468017578125,
"learning_rate": 6.163492932573438e-05,
"loss": 739.755,
"step": 3315
},
{
"epoch": 0.664,
"grad_norm": 161.59474182128906,
"learning_rate": 6.131280898207339e-05,
"loss": 778.9429,
"step": 3320
},
{
"epoch": 0.665,
"grad_norm": 166.95713806152344,
"learning_rate": 6.099116002962604e-05,
"loss": 800.3176,
"step": 3325
},
{
"epoch": 0.666,
"grad_norm": 110.76078033447266,
"learning_rate": 6.066998638758326e-05,
"loss": 750.2778,
"step": 3330
},
{
"epoch": 0.667,
"grad_norm": 127.31350708007812,
"learning_rate": 6.034929196934459e-05,
"loss": 783.055,
"step": 3335
},
{
"epoch": 0.668,
"grad_norm": 115.09233856201172,
"learning_rate": 6.002908068247024e-05,
"loss": 774.6731,
"step": 3340
},
{
"epoch": 0.669,
"grad_norm": 114.95280456542969,
"learning_rate": 5.9709356428633746e-05,
"loss": 802.8275,
"step": 3345
},
{
"epoch": 0.67,
"grad_norm": 125.50543975830078,
"learning_rate": 5.9390123103574215e-05,
"loss": 772.4195,
"step": 3350
},
{
"epoch": 0.671,
"grad_norm": 125.0716323852539,
"learning_rate": 5.907138459704895e-05,
"loss": 776.7305,
"step": 3355
},
{
"epoch": 0.672,
"grad_norm": 109.57327270507812,
"learning_rate": 5.8753144792786096e-05,
"loss": 783.1432,
"step": 3360
},
{
"epoch": 0.673,
"grad_norm": 151.8736572265625,
"learning_rate": 5.8435407568437216e-05,
"loss": 741.6959,
"step": 3365
},
{
"epoch": 0.674,
"grad_norm": 191.57054138183594,
"learning_rate": 5.8118176795530176e-05,
"loss": 775.3784,
"step": 3370
},
{
"epoch": 0.675,
"grad_norm": 187.3772735595703,
"learning_rate": 5.780145633942173e-05,
"loss": 753.1751,
"step": 3375
},
{
"epoch": 0.676,
"grad_norm": 124.19963073730469,
"learning_rate": 5.748525005925074e-05,
"loss": 789.8846,
"step": 3380
},
{
"epoch": 0.677,
"grad_norm": 115.7330551147461,
"learning_rate": 5.716956180789098e-05,
"loss": 752.9587,
"step": 3385
},
{
"epoch": 0.678,
"grad_norm": 114.07674407958984,
"learning_rate": 5.6854395431904094e-05,
"loss": 728.0029,
"step": 3390
},
{
"epoch": 0.679,
"grad_norm": 119.20211791992188,
"learning_rate": 5.653975477149298e-05,
"loss": 752.3581,
"step": 3395
},
{
"epoch": 0.68,
"grad_norm": 136.1088409423828,
"learning_rate": 5.622564366045472e-05,
"loss": 743.1903,
"step": 3400
},
{
"epoch": 0.681,
"grad_norm": 123.04347229003906,
"learning_rate": 5.591206592613416e-05,
"loss": 763.8268,
"step": 3405
},
{
"epoch": 0.682,
"grad_norm": 138.43167114257812,
"learning_rate": 5.5599025389376935e-05,
"loss": 787.1986,
"step": 3410
},
{
"epoch": 0.683,
"grad_norm": 130.23532104492188,
"learning_rate": 5.5286525864483285e-05,
"loss": 768.9363,
"step": 3415
},
{
"epoch": 0.684,
"grad_norm": 139.71078491210938,
"learning_rate": 5.497457115916127e-05,
"loss": 756.3555,
"step": 3420
},
{
"epoch": 0.685,
"grad_norm": 121.11155700683594,
"learning_rate": 5.466316507448048e-05,
"loss": 760.1915,
"step": 3425
},
{
"epoch": 0.686,
"grad_norm": 131.9729461669922,
"learning_rate": 5.435231140482587e-05,
"loss": 750.09,
"step": 3430
},
{
"epoch": 0.687,
"grad_norm": 132.2626953125,
"learning_rate": 5.404201393785122e-05,
"loss": 732.5554,
"step": 3435
},
{
"epoch": 0.688,
"grad_norm": 144.8626251220703,
"learning_rate": 5.373227645443332e-05,
"loss": 743.0169,
"step": 3440
},
{
"epoch": 0.689,
"grad_norm": 111.8534164428711,
"learning_rate": 5.3423102728625574e-05,
"loss": 741.1021,
"step": 3445
},
{
"epoch": 0.69,
"grad_norm": 116.85664367675781,
"learning_rate": 5.311449652761235e-05,
"loss": 802.9158,
"step": 3450
},
{
"epoch": 0.691,
"grad_norm": 153.246826171875,
"learning_rate": 5.2806461611662735e-05,
"loss": 788.3172,
"step": 3455
},
{
"epoch": 0.692,
"grad_norm": 171.2090606689453,
"learning_rate": 5.2499001734085044e-05,
"loss": 780.0562,
"step": 3460
},
{
"epoch": 0.693,
"grad_norm": 115.50946044921875,
"learning_rate": 5.2192120641180786e-05,
"loss": 710.9954,
"step": 3465
},
{
"epoch": 0.694,
"grad_norm": 127.65371704101562,
"learning_rate": 5.188582207219931e-05,
"loss": 744.0518,
"step": 3470
},
{
"epoch": 0.695,
"grad_norm": 126.49425506591797,
"learning_rate": 5.158010975929193e-05,
"loss": 766.379,
"step": 3475
},
{
"epoch": 0.696,
"grad_norm": 137.4571075439453,
"learning_rate": 5.127498742746675e-05,
"loss": 802.5211,
"step": 3480
},
{
"epoch": 0.697,
"grad_norm": 241.0354766845703,
"learning_rate": 5.097045879454313e-05,
"loss": 752.2326,
"step": 3485
},
{
"epoch": 0.698,
"grad_norm": 110.30218505859375,
"learning_rate": 5.066652757110628e-05,
"loss": 772.0919,
"step": 3490
},
{
"epoch": 0.699,
"grad_norm": 130.7154998779297,
"learning_rate": 5.036319746046232e-05,
"loss": 780.2617,
"step": 3495
},
{
"epoch": 0.7,
"grad_norm": 124.79840087890625,
"learning_rate": 5.006047215859289e-05,
"loss": 765.1436,
"step": 3500
},
{
"epoch": 0.701,
"grad_norm": 206.5087127685547,
"learning_rate": 4.97583553541102e-05,
"loss": 773.1494,
"step": 3505
},
{
"epoch": 0.702,
"grad_norm": 132.0094757080078,
"learning_rate": 4.945685072821227e-05,
"loss": 698.1,
"step": 3510
},
{
"epoch": 0.703,
"grad_norm": 138.01504516601562,
"learning_rate": 4.915596195463773e-05,
"loss": 715.8787,
"step": 3515
},
{
"epoch": 0.704,
"grad_norm": 239.7610321044922,
"learning_rate": 4.885569269962142e-05,
"loss": 742.0323,
"step": 3520
},
{
"epoch": 0.705,
"grad_norm": 147.96165466308594,
"learning_rate": 4.8556046621849346e-05,
"loss": 750.3816,
"step": 3525
},
{
"epoch": 0.706,
"grad_norm": 118.51763153076172,
"learning_rate": 4.825702737241452e-05,
"loss": 730.9293,
"step": 3530
},
{
"epoch": 0.707,
"grad_norm": 121.93814086914062,
"learning_rate": 4.7958638594772064e-05,
"loss": 740.376,
"step": 3535
},
{
"epoch": 0.708,
"grad_norm": 251.99169921875,
"learning_rate": 4.766088392469506e-05,
"loss": 565.7253,
"step": 3540
},
{
"epoch": 0.709,
"grad_norm": 101.92109680175781,
"learning_rate": 4.736376699023023e-05,
"loss": 595.0812,
"step": 3545
},
{
"epoch": 0.71,
"grad_norm": 132.72080993652344,
"learning_rate": 4.706729141165361e-05,
"loss": 794.1597,
"step": 3550
},
{
"epoch": 0.711,
"grad_norm": 133.33570861816406,
"learning_rate": 4.6771460801426635e-05,
"loss": 754.0317,
"step": 3555
},
{
"epoch": 0.712,
"grad_norm": 131.1138916015625,
"learning_rate": 4.647627876415186e-05,
"loss": 788.6007,
"step": 3560
},
{
"epoch": 0.713,
"grad_norm": 156.98782348632812,
"learning_rate": 4.6181748896529273e-05,
"loss": 745.7137,
"step": 3565
},
{
"epoch": 0.714,
"grad_norm": 139.6029815673828,
"learning_rate": 4.588787478731242e-05,
"loss": 771.5374,
"step": 3570
},
{
"epoch": 0.715,
"grad_norm": 115.74078369140625,
"learning_rate": 4.559466001726451e-05,
"loss": 699.469,
"step": 3575
},
{
"epoch": 0.716,
"grad_norm": 125.93366241455078,
"learning_rate": 4.530210815911504e-05,
"loss": 728.8559,
"step": 3580
},
{
"epoch": 0.717,
"grad_norm": 115.40399169921875,
"learning_rate": 4.501022277751602e-05,
"loss": 726.9937,
"step": 3585
},
{
"epoch": 0.718,
"grad_norm": 127.34805297851562,
"learning_rate": 4.471900742899876e-05,
"loss": 731.9443,
"step": 3590
},
{
"epoch": 0.719,
"grad_norm": 118.46029663085938,
"learning_rate": 4.4428465661930343e-05,
"loss": 725.6402,
"step": 3595
},
{
"epoch": 0.72,
"grad_norm": 138.3831787109375,
"learning_rate": 4.413860101647055e-05,
"loss": 778.4342,
"step": 3600
},
{
"epoch": 0.721,
"grad_norm": 117.67982482910156,
"learning_rate": 4.3849417024528564e-05,
"loss": 867.4777,
"step": 3605
},
{
"epoch": 0.722,
"grad_norm": 155.1906280517578,
"learning_rate": 4.356091720972011e-05,
"loss": 777.5222,
"step": 3610
},
{
"epoch": 0.723,
"grad_norm": 124.51838684082031,
"learning_rate": 4.327310508732437e-05,
"loss": 743.9003,
"step": 3615
},
{
"epoch": 0.724,
"grad_norm": 147.5206756591797,
"learning_rate": 4.29859841642412e-05,
"loss": 794.709,
"step": 3620
},
{
"epoch": 0.725,
"grad_norm": 117.43269348144531,
"learning_rate": 4.26995579389485e-05,
"loss": 731.7601,
"step": 3625
},
{
"epoch": 0.726,
"grad_norm": 158.4900360107422,
"learning_rate": 4.2413829901459344e-05,
"loss": 819.125,
"step": 3630
},
{
"epoch": 0.727,
"grad_norm": 127.22176361083984,
"learning_rate": 4.212880353327979e-05,
"loss": 761.3026,
"step": 3635
},
{
"epoch": 0.728,
"grad_norm": 146.33895874023438,
"learning_rate": 4.184448230736613e-05,
"loss": 769.5451,
"step": 3640
},
{
"epoch": 0.729,
"grad_norm": 116.52557373046875,
"learning_rate": 4.15608696880828e-05,
"loss": 751.8731,
"step": 3645
},
{
"epoch": 0.73,
"grad_norm": 124.79627990722656,
"learning_rate": 4.1277969131160045e-05,
"loss": 736.895,
"step": 3650
},
{
"epoch": 0.731,
"grad_norm": 109.68138122558594,
"learning_rate": 4.099578408365191e-05,
"loss": 738.7706,
"step": 3655
},
{
"epoch": 0.732,
"grad_norm": 118.26542663574219,
"learning_rate": 4.071431798389408e-05,
"loss": 742.2397,
"step": 3660
},
{
"epoch": 0.733,
"grad_norm": 104.11935424804688,
"learning_rate": 4.0433574261462206e-05,
"loss": 730.1089,
"step": 3665
},
{
"epoch": 0.734,
"grad_norm": 106.6944580078125,
"learning_rate": 4.015355633712996e-05,
"loss": 760.6916,
"step": 3670
},
{
"epoch": 0.735,
"grad_norm": 134.86776733398438,
"learning_rate": 3.987426762282733e-05,
"loss": 725.5132,
"step": 3675
},
{
"epoch": 0.736,
"grad_norm": 112.6491928100586,
"learning_rate": 3.9595711521599224e-05,
"loss": 781.6226,
"step": 3680
},
{
"epoch": 0.737,
"grad_norm": 127.73168182373047,
"learning_rate": 3.931789142756377e-05,
"loss": 763.4833,
"step": 3685
},
{
"epoch": 0.738,
"grad_norm": 98.76712799072266,
"learning_rate": 3.904081072587119e-05,
"loss": 779.2334,
"step": 3690
},
{
"epoch": 0.739,
"grad_norm": 115.99645233154297,
"learning_rate": 3.876447279266238e-05,
"loss": 755.5624,
"step": 3695
},
{
"epoch": 0.74,
"grad_norm": 119.31414031982422,
"learning_rate": 3.8488880995027786e-05,
"loss": 706.1799,
"step": 3700
},
{
"epoch": 0.741,
"grad_norm": 116.8663101196289,
"learning_rate": 3.821403869096658e-05,
"loss": 752.1791,
"step": 3705
},
{
"epoch": 0.742,
"grad_norm": 166.67538452148438,
"learning_rate": 3.793994922934544e-05,
"loss": 745.1276,
"step": 3710
},
{
"epoch": 0.743,
"grad_norm": 111.32856750488281,
"learning_rate": 3.766661594985801e-05,
"loss": 797.8338,
"step": 3715
},
{
"epoch": 0.744,
"grad_norm": 155.2139434814453,
"learning_rate": 3.739404218298398e-05,
"loss": 766.8993,
"step": 3720
},
{
"epoch": 0.745,
"grad_norm": 112.45269012451172,
"learning_rate": 3.712223124994875e-05,
"loss": 788.1872,
"step": 3725
},
{
"epoch": 0.746,
"grad_norm": 122.84798431396484,
"learning_rate": 3.685118646268272e-05,
"loss": 748.4491,
"step": 3730
},
{
"epoch": 0.747,
"grad_norm": 198.7731475830078,
"learning_rate": 3.6580911123781056e-05,
"loss": 773.2386,
"step": 3735
},
{
"epoch": 0.748,
"grad_norm": 160.95582580566406,
"learning_rate": 3.631140852646355e-05,
"loss": 798.8534,
"step": 3740
},
{
"epoch": 0.749,
"grad_norm": 163.7533721923828,
"learning_rate": 3.604268195453421e-05,
"loss": 811.804,
"step": 3745
},
{
"epoch": 0.75,
"grad_norm": 144.27359008789062,
"learning_rate": 3.577473468234156e-05,
"loss": 775.0225,
"step": 3750
},
{
"epoch": 0.751,
"grad_norm": 145.66903686523438,
"learning_rate": 3.5507569974738574e-05,
"loss": 797.9318,
"step": 3755
},
{
"epoch": 0.752,
"grad_norm": 120.09302520751953,
"learning_rate": 3.524119108704286e-05,
"loss": 768.0831,
"step": 3760
},
{
"epoch": 0.753,
"grad_norm": 109.70848083496094,
"learning_rate": 3.497560126499709e-05,
"loss": 747.4637,
"step": 3765
},
{
"epoch": 0.754,
"grad_norm": 120.63890075683594,
"learning_rate": 3.4710803744729515e-05,
"loss": 778.2264,
"step": 3770
},
{
"epoch": 0.755,
"grad_norm": 149.050537109375,
"learning_rate": 3.444680175271428e-05,
"loss": 782.9156,
"step": 3775
},
{
"epoch": 0.756,
"grad_norm": 118.29425811767578,
"learning_rate": 3.418359850573234e-05,
"loss": 777.2292,
"step": 3780
},
{
"epoch": 0.757,
"grad_norm": 112.38211059570312,
"learning_rate": 3.3921197210832235e-05,
"loss": 749.7371,
"step": 3785
},
{
"epoch": 0.758,
"grad_norm": 122.3675537109375,
"learning_rate": 3.3659601065290893e-05,
"loss": 798.1592,
"step": 3790
},
{
"epoch": 0.759,
"grad_norm": 115.7859115600586,
"learning_rate": 3.339881325657484e-05,
"loss": 785.4167,
"step": 3795
},
{
"epoch": 0.76,
"grad_norm": 116.8576889038086,
"learning_rate": 3.313883696230119e-05,
"loss": 741.9291,
"step": 3800
},
{
"epoch": 0.761,
"grad_norm": 140.4699249267578,
"learning_rate": 3.287967535019908e-05,
"loss": 719.3675,
"step": 3805
},
{
"epoch": 0.762,
"grad_norm": 114.81166076660156,
"learning_rate": 3.2621331578070934e-05,
"loss": 799.3105,
"step": 3810
},
{
"epoch": 0.763,
"grad_norm": 148.6519317626953,
"learning_rate": 3.236380879375408e-05,
"loss": 770.3386,
"step": 3815
},
{
"epoch": 0.764,
"grad_norm": 121.94597625732422,
"learning_rate": 3.210711013508242e-05,
"loss": 776.2046,
"step": 3820
},
{
"epoch": 0.765,
"grad_norm": 113.5713882446289,
"learning_rate": 3.1851238729848034e-05,
"loss": 756.8803,
"step": 3825
},
{
"epoch": 0.766,
"grad_norm": 202.44180297851562,
"learning_rate": 3.159619769576333e-05,
"loss": 697.6727,
"step": 3830
},
{
"epoch": 0.767,
"grad_norm": 119.29793548583984,
"learning_rate": 3.134199014042274e-05,
"loss": 725.7883,
"step": 3835
},
{
"epoch": 0.768,
"grad_norm": 128.6842041015625,
"learning_rate": 3.108861916126518e-05,
"loss": 732.3524,
"step": 3840
},
{
"epoch": 0.769,
"grad_norm": 134.20880126953125,
"learning_rate": 3.0836087845536e-05,
"loss": 755.2562,
"step": 3845
},
{
"epoch": 0.77,
"grad_norm": 124.41024780273438,
"learning_rate": 3.058439927024962e-05,
"loss": 708.0303,
"step": 3850
},
{
"epoch": 0.771,
"grad_norm": 124.63196563720703,
"learning_rate": 3.0333556502151926e-05,
"loss": 764.0821,
"step": 3855
},
{
"epoch": 0.772,
"grad_norm": 136.0846405029297,
"learning_rate": 3.0083562597682847e-05,
"loss": 794.6262,
"step": 3860
},
{
"epoch": 0.773,
"grad_norm": 123.802978515625,
"learning_rate": 2.9834420602939263e-05,
"loss": 759.9534,
"step": 3865
},
{
"epoch": 0.774,
"grad_norm": 107.51209259033203,
"learning_rate": 2.9586133553637683e-05,
"loss": 753.6651,
"step": 3870
},
{
"epoch": 0.775,
"grad_norm": 110.35235595703125,
"learning_rate": 2.933870447507753e-05,
"loss": 748.2208,
"step": 3875
},
{
"epoch": 0.776,
"grad_norm": 123.97808074951172,
"learning_rate": 2.9092136382103973e-05,
"loss": 759.3203,
"step": 3880
},
{
"epoch": 0.777,
"grad_norm": 105.23466491699219,
"learning_rate": 2.8846432279071467e-05,
"loss": 725.8572,
"step": 3885
},
{
"epoch": 0.778,
"grad_norm": 155.94854736328125,
"learning_rate": 2.860159515980695e-05,
"loss": 777.8391,
"step": 3890
},
{
"epoch": 0.779,
"grad_norm": 124.55339050292969,
"learning_rate": 2.835762800757341e-05,
"loss": 736.8788,
"step": 3895
},
{
"epoch": 0.78,
"grad_norm": 123.58473205566406,
"learning_rate": 2.8114533795033683e-05,
"loss": 747.5851,
"step": 3900
},
{
"epoch": 0.781,
"grad_norm": 130.49105834960938,
"learning_rate": 2.7872315484213952e-05,
"loss": 717.7368,
"step": 3905
},
{
"epoch": 0.782,
"grad_norm": 106.47259521484375,
"learning_rate": 2.7630976026467968e-05,
"loss": 724.4656,
"step": 3910
},
{
"epoch": 0.783,
"grad_norm": 149.3709259033203,
"learning_rate": 2.7390518362440808e-05,
"loss": 768.671,
"step": 3915
},
{
"epoch": 0.784,
"grad_norm": 134.93649291992188,
"learning_rate": 2.715094542203327e-05,
"loss": 678.3123,
"step": 3920
},
{
"epoch": 0.785,
"grad_norm": 123.28882598876953,
"learning_rate": 2.6912260124366006e-05,
"loss": 773.308,
"step": 3925
},
{
"epoch": 0.786,
"grad_norm": 110.87435913085938,
"learning_rate": 2.6674465377744017e-05,
"loss": 748.4667,
"step": 3930
},
{
"epoch": 0.787,
"grad_norm": 105.61002349853516,
"learning_rate": 2.6437564079621267e-05,
"loss": 780.9644,
"step": 3935
},
{
"epoch": 0.788,
"grad_norm": 111.76212310791016,
"learning_rate": 2.6201559116565345e-05,
"loss": 699.371,
"step": 3940
},
{
"epoch": 0.789,
"grad_norm": 108.44900512695312,
"learning_rate": 2.5966453364222186e-05,
"loss": 759.2867,
"step": 3945
},
{
"epoch": 0.79,
"grad_norm": 126.96375274658203,
"learning_rate": 2.573224968728123e-05,
"loss": 771.0279,
"step": 3950
},
{
"epoch": 0.791,
"grad_norm": 121.80357360839844,
"learning_rate": 2.549895093944039e-05,
"loss": 701.9709,
"step": 3955
},
{
"epoch": 0.792,
"grad_norm": 95.78489685058594,
"learning_rate": 2.5266559963371216e-05,
"loss": 762.7878,
"step": 3960
},
{
"epoch": 0.793,
"grad_norm": 107.50474548339844,
"learning_rate": 2.5035079590684497e-05,
"loss": 762.8253,
"step": 3965
},
{
"epoch": 0.794,
"grad_norm": 119.09774780273438,
"learning_rate": 2.480451264189546e-05,
"loss": 756.1296,
"step": 3970
},
{
"epoch": 0.795,
"grad_norm": 109.22418212890625,
"learning_rate": 2.4574861926389615e-05,
"loss": 777.2449,
"step": 3975
},
{
"epoch": 0.796,
"grad_norm": 151.73672485351562,
"learning_rate": 2.43461302423885e-05,
"loss": 776.2843,
"step": 3980
},
{
"epoch": 0.797,
"grad_norm": 133.659423828125,
"learning_rate": 2.411832037691545e-05,
"loss": 718.8113,
"step": 3985
},
{
"epoch": 0.798,
"grad_norm": 109.64379119873047,
"learning_rate": 2.389143510576184e-05,
"loss": 726.7709,
"step": 3990
},
{
"epoch": 0.799,
"grad_norm": 143.59727478027344,
"learning_rate": 2.3665477193453034e-05,
"loss": 738.54,
"step": 3995
},
{
"epoch": 0.8,
"grad_norm": 104.3723373413086,
"learning_rate": 2.3440449393214948e-05,
"loss": 743.9062,
"step": 4000
},
{
"epoch": 0.801,
"grad_norm": 130.1102752685547,
"learning_rate": 2.321635444694028e-05,
"loss": 722.1185,
"step": 4005
},
{
"epoch": 0.802,
"grad_norm": 159.1897430419922,
"learning_rate": 2.2993195085155205e-05,
"loss": 770.8436,
"step": 4010
},
{
"epoch": 0.803,
"grad_norm": 99.38143157958984,
"learning_rate": 2.277097402698619e-05,
"loss": 747.8705,
"step": 4015
},
{
"epoch": 0.804,
"grad_norm": 165.09844970703125,
"learning_rate": 2.254969398012663e-05,
"loss": 750.7329,
"step": 4020
},
{
"epoch": 0.805,
"grad_norm": 116.33419036865234,
"learning_rate": 2.2329357640804117e-05,
"loss": 765.071,
"step": 4025
},
{
"epoch": 0.806,
"grad_norm": 124.26374053955078,
"learning_rate": 2.210996769374737e-05,
"loss": 756.1622,
"step": 4030
},
{
"epoch": 0.807,
"grad_norm": 102.22627258300781,
"learning_rate": 2.1891526812153672e-05,
"loss": 736.3818,
"step": 4035
},
{
"epoch": 0.808,
"grad_norm": 117.34593963623047,
"learning_rate": 2.1674037657656266e-05,
"loss": 758.4687,
"step": 4040
},
{
"epoch": 0.809,
"grad_norm": 129.66217041015625,
"learning_rate": 2.1457502880291812e-05,
"loss": 744.6741,
"step": 4045
},
{
"epoch": 0.81,
"grad_norm": 110.15367126464844,
"learning_rate": 2.1241925118468287e-05,
"loss": 744.5062,
"step": 4050
},
{
"epoch": 0.811,
"grad_norm": 120.07591247558594,
"learning_rate": 2.1027306998932627e-05,
"loss": 788.2117,
"step": 4055
},
{
"epoch": 0.812,
"grad_norm": 103.54853057861328,
"learning_rate": 2.0813651136738954e-05,
"loss": 780.7417,
"step": 4060
},
{
"epoch": 0.813,
"grad_norm": 117.86383056640625,
"learning_rate": 2.0600960135216462e-05,
"loss": 723.3116,
"step": 4065
},
{
"epoch": 0.814,
"grad_norm": 114.02228546142578,
"learning_rate": 2.0389236585937945e-05,
"loss": 695.2932,
"step": 4070
},
{
"epoch": 0.815,
"grad_norm": 112.42250061035156,
"learning_rate": 2.017848306868797e-05,
"loss": 779.6751,
"step": 4075
},
{
"epoch": 0.816,
"grad_norm": 131.00047302246094,
"learning_rate": 1.9968702151431696e-05,
"loss": 764.7673,
"step": 4080
},
{
"epoch": 0.817,
"grad_norm": 125.86773681640625,
"learning_rate": 1.9759896390283362e-05,
"loss": 763.137,
"step": 4085
},
{
"epoch": 0.818,
"grad_norm": 133.52008056640625,
"learning_rate": 1.955206832947526e-05,
"loss": 744.5103,
"step": 4090
},
{
"epoch": 0.819,
"grad_norm": 109.47015380859375,
"learning_rate": 1.9345220501326777e-05,
"loss": 764.0292,
"step": 4095
},
{
"epoch": 0.82,
"grad_norm": 103.33470916748047,
"learning_rate": 1.9139355426213347e-05,
"loss": 742.5783,
"step": 4100
},
{
"epoch": 0.821,
"grad_norm": 111.80830383300781,
"learning_rate": 1.8934475612536017e-05,
"loss": 753.7018,
"step": 4105
},
{
"epoch": 0.822,
"grad_norm": 110.24060821533203,
"learning_rate": 1.8730583556690605e-05,
"loss": 692.8928,
"step": 4110
},
{
"epoch": 0.823,
"grad_norm": 105.61619567871094,
"learning_rate": 1.852768174303752e-05,
"loss": 750.0059,
"step": 4115
},
{
"epoch": 0.824,
"grad_norm": 179.3662567138672,
"learning_rate": 1.8325772643871265e-05,
"loss": 730.0432,
"step": 4120
},
{
"epoch": 0.825,
"grad_norm": 127.46566772460938,
"learning_rate": 1.812485871939056e-05,
"loss": 792.3266,
"step": 4125
},
{
"epoch": 0.826,
"grad_norm": 116.48438262939453,
"learning_rate": 1.792494241766811e-05,
"loss": 768.7869,
"step": 4130
},
{
"epoch": 0.827,
"grad_norm": 138.55764770507812,
"learning_rate": 1.7726026174621003e-05,
"loss": 755.5712,
"step": 4135
},
{
"epoch": 0.828,
"grad_norm": 113.16971588134766,
"learning_rate": 1.752811241398089e-05,
"loss": 715.291,
"step": 4140
},
{
"epoch": 0.829,
"grad_norm": 104.35687255859375,
"learning_rate": 1.7331203547264453e-05,
"loss": 744.6895,
"step": 4145
},
{
"epoch": 0.83,
"grad_norm": 108.22552490234375,
"learning_rate": 1.7135301973744124e-05,
"loss": 720.8159,
"step": 4150
},
{
"epoch": 0.831,
"grad_norm": 187.9698028564453,
"learning_rate": 1.6940410080418723e-05,
"loss": 764.4953,
"step": 4155
},
{
"epoch": 0.832,
"grad_norm": 101.60509490966797,
"learning_rate": 1.6746530241984504e-05,
"loss": 712.7717,
"step": 4160
},
{
"epoch": 0.833,
"grad_norm": 98.50192260742188,
"learning_rate": 1.6553664820806102e-05,
"loss": 728.3149,
"step": 4165
},
{
"epoch": 0.834,
"grad_norm": 125.23453521728516,
"learning_rate": 1.6361816166887768e-05,
"loss": 785.3762,
"step": 4170
},
{
"epoch": 0.835,
"grad_norm": 119.21240234375,
"learning_rate": 1.6170986617844863e-05,
"loss": 709.8583,
"step": 4175
},
{
"epoch": 0.836,
"grad_norm": 94.34806060791016,
"learning_rate": 1.598117849887518e-05,
"loss": 781.8713,
"step": 4180
},
{
"epoch": 0.837,
"grad_norm": 159.22396850585938,
"learning_rate": 1.579239412273078e-05,
"loss": 781.5875,
"step": 4185
},
{
"epoch": 0.838,
"grad_norm": 137.92727661132812,
"learning_rate": 1.560463578968967e-05,
"loss": 774.0704,
"step": 4190
},
{
"epoch": 0.839,
"grad_norm": 93.41771697998047,
"learning_rate": 1.541790578752794e-05,
"loss": 760.1525,
"step": 4195
},
{
"epoch": 0.84,
"grad_norm": 136.81143188476562,
"learning_rate": 1.5232206391491699e-05,
"loss": 756.3504,
"step": 4200
},
{
"epoch": 0.841,
"grad_norm": 105.10299682617188,
"learning_rate": 1.5047539864269478e-05,
"loss": 727.5134,
"step": 4205
},
{
"epoch": 0.842,
"grad_norm": 116.32719421386719,
"learning_rate": 1.486390845596466e-05,
"loss": 735.8066,
"step": 4210
},
{
"epoch": 0.843,
"grad_norm": 107.66499328613281,
"learning_rate": 1.468131440406798e-05,
"loss": 731.8051,
"step": 4215
},
{
"epoch": 0.844,
"grad_norm": 133.8819580078125,
"learning_rate": 1.4499759933430346e-05,
"loss": 765.5967,
"step": 4220
},
{
"epoch": 0.845,
"grad_norm": 102.5728759765625,
"learning_rate": 1.4319247256235714e-05,
"loss": 726.3236,
"step": 4225
},
{
"epoch": 0.846,
"grad_norm": 126.71195220947266,
"learning_rate": 1.4139778571974049e-05,
"loss": 730.6939,
"step": 4230
},
{
"epoch": 0.847,
"grad_norm": 106.07266235351562,
"learning_rate": 1.3961356067414666e-05,
"loss": 716.6035,
"step": 4235
},
{
"epoch": 0.848,
"grad_norm": 145.76808166503906,
"learning_rate": 1.3783981916579446e-05,
"loss": 747.8283,
"step": 4240
},
{
"epoch": 0.849,
"grad_norm": 120.42158508300781,
"learning_rate": 1.3607658280716473e-05,
"loss": 745.3865,
"step": 4245
},
{
"epoch": 0.85,
"grad_norm": 100.27706909179688,
"learning_rate": 1.3432387308273575e-05,
"loss": 754.6483,
"step": 4250
},
{
"epoch": 0.851,
"grad_norm": 110.44722747802734,
"learning_rate": 1.3258171134872265e-05,
"loss": 746.1795,
"step": 4255
},
{
"epoch": 0.852,
"grad_norm": 95.80634307861328,
"learning_rate": 1.3085011883281606e-05,
"loss": 729.2498,
"step": 4260
},
{
"epoch": 0.853,
"grad_norm": 99.60895538330078,
"learning_rate": 1.2912911663392469e-05,
"loss": 754.9077,
"step": 4265
},
{
"epoch": 0.854,
"grad_norm": 114.73807525634766,
"learning_rate": 1.2741872572191682e-05,
"loss": 650.0629,
"step": 4270
},
{
"epoch": 0.855,
"grad_norm": 107.70165252685547,
"learning_rate": 1.257189669373664e-05,
"loss": 752.4048,
"step": 4275
},
{
"epoch": 0.856,
"grad_norm": 107.06097412109375,
"learning_rate": 1.2402986099129765e-05,
"loss": 775.8019,
"step": 4280
},
{
"epoch": 0.857,
"grad_norm": 104.68925476074219,
"learning_rate": 1.2235142846493308e-05,
"loss": 730.576,
"step": 4285
},
{
"epoch": 0.858,
"grad_norm": 95.80131530761719,
"learning_rate": 1.206836898094439e-05,
"loss": 764.7757,
"step": 4290
},
{
"epoch": 0.859,
"grad_norm": 119.42138671875,
"learning_rate": 1.1902666534569883e-05,
"loss": 778.1505,
"step": 4295
},
{
"epoch": 0.86,
"grad_norm": 104.68960571289062,
"learning_rate": 1.1738037526401857e-05,
"loss": 743.42,
"step": 4300
},
{
"epoch": 0.861,
"grad_norm": 112.42256927490234,
"learning_rate": 1.1574483962392767e-05,
"loss": 773.981,
"step": 4305
},
{
"epoch": 0.862,
"grad_norm": 133.5937042236328,
"learning_rate": 1.1412007835391236e-05,
"loss": 733.7224,
"step": 4310
},
{
"epoch": 0.863,
"grad_norm": 130.4263458251953,
"learning_rate": 1.1250611125117527e-05,
"loss": 773.2284,
"step": 4315
},
{
"epoch": 0.864,
"grad_norm": 123.56578063964844,
"learning_rate": 1.1090295798139672e-05,
"loss": 797.0182,
"step": 4320
},
{
"epoch": 0.865,
"grad_norm": 108.34945678710938,
"learning_rate": 1.093106380784934e-05,
"loss": 706.1183,
"step": 4325
},
{
"epoch": 0.866,
"grad_norm": 196.333984375,
"learning_rate": 1.0772917094438051e-05,
"loss": 772.0679,
"step": 4330
},
{
"epoch": 0.867,
"grad_norm": 136.76158142089844,
"learning_rate": 1.0615857584873623e-05,
"loss": 748.4519,
"step": 4335
},
{
"epoch": 0.868,
"grad_norm": 104.26521301269531,
"learning_rate": 1.0459887192876594e-05,
"loss": 726.3264,
"step": 4340
},
{
"epoch": 0.869,
"grad_norm": 100.40541076660156,
"learning_rate": 1.0305007818897006e-05,
"loss": 700.3576,
"step": 4345
},
{
"epoch": 0.87,
"grad_norm": 109.7436752319336,
"learning_rate": 1.0151221350091134e-05,
"loss": 734.363,
"step": 4350
},
{
"epoch": 0.871,
"grad_norm": 107.25484466552734,
"learning_rate": 9.998529660298539e-06,
"loss": 744.9003,
"step": 4355
},
{
"epoch": 0.872,
"grad_norm": 100.47745513916016,
"learning_rate": 9.84693461001932e-06,
"loss": 774.2802,
"step": 4360
},
{
"epoch": 0.873,
"grad_norm": 163.5693817138672,
"learning_rate": 9.696438046391288e-06,
"loss": 735.4435,
"step": 4365
},
{
"epoch": 0.874,
"grad_norm": 114.36474609375,
"learning_rate": 9.5470418031676e-06,
"loss": 749.1832,
"step": 4370
},
{
"epoch": 0.875,
"grad_norm": 125.52037048339844,
"learning_rate": 9.398747700694322e-06,
"loss": 717.7115,
"step": 4375
},
{
"epoch": 0.876,
"grad_norm": 128.82594299316406,
"learning_rate": 9.251557545888312e-06,
"loss": 705.2951,
"step": 4380
},
{
"epoch": 0.877,
"grad_norm": 122.6993408203125,
"learning_rate": 9.105473132215125e-06,
"loss": 723.27,
"step": 4385
},
{
"epoch": 0.878,
"grad_norm": 112.09241485595703,
"learning_rate": 8.960496239667282e-06,
"loss": 770.7658,
"step": 4390
},
{
"epoch": 0.879,
"grad_norm": 160.94784545898438,
"learning_rate": 8.816628634742441e-06,
"loss": 745.847,
"step": 4395
},
{
"epoch": 0.88,
"grad_norm": 121.04492950439453,
"learning_rate": 8.67387207042194e-06,
"loss": 730.6075,
"step": 4400
},
{
"epoch": 0.881,
"grad_norm": 108.06427001953125,
"learning_rate": 8.532228286149501e-06,
"loss": 772.9648,
"step": 4405
},
{
"epoch": 0.882,
"grad_norm": 99.53275299072266,
"learning_rate": 8.39169900780995e-06,
"loss": 761.7057,
"step": 4410
},
{
"epoch": 0.883,
"grad_norm": 98.8696060180664,
"learning_rate": 8.252285947708139e-06,
"loss": 739.0488,
"step": 4415
},
{
"epoch": 0.884,
"grad_norm": 155.01358032226562,
"learning_rate": 8.113990804548244e-06,
"loss": 761.6779,
"step": 4420
},
{
"epoch": 0.885,
"grad_norm": 123.83946990966797,
"learning_rate": 7.976815263412963e-06,
"loss": 744.7947,
"step": 4425
},
{
"epoch": 0.886,
"grad_norm": 135.30189514160156,
"learning_rate": 7.840760995742946e-06,
"loss": 785.6837,
"step": 4430
},
{
"epoch": 0.887,
"grad_norm": 120.61870574951172,
"learning_rate": 7.7058296593165e-06,
"loss": 770.114,
"step": 4435
},
{
"epoch": 0.888,
"grad_norm": 125.45433044433594,
"learning_rate": 7.572022898229403e-06,
"loss": 771.3337,
"step": 4440
},
{
"epoch": 0.889,
"grad_norm": 96.52245330810547,
"learning_rate": 7.439342342874789e-06,
"loss": 777.5343,
"step": 4445
},
{
"epoch": 0.89,
"grad_norm": 104.95310974121094,
"learning_rate": 7.3077896099233765e-06,
"loss": 731.9451,
"step": 4450
},
{
"epoch": 0.891,
"grad_norm": 125.06282806396484,
"learning_rate": 7.177366302303667e-06,
"loss": 767.6096,
"step": 4455
},
{
"epoch": 0.892,
"grad_norm": 158.36920166015625,
"learning_rate": 7.048074009182548e-06,
"loss": 729.1504,
"step": 4460
},
{
"epoch": 0.893,
"grad_norm": 118.87617492675781,
"learning_rate": 6.919914305945774e-06,
"loss": 752.0161,
"step": 4465
},
{
"epoch": 0.894,
"grad_norm": 108.28852844238281,
"learning_rate": 6.7928887541789055e-06,
"loss": 783.4393,
"step": 4470
},
{
"epoch": 0.895,
"grad_norm": 116.9722671508789,
"learning_rate": 6.666998901648203e-06,
"loss": 809.5685,
"step": 4475
},
{
"epoch": 0.896,
"grad_norm": 109.63611602783203,
"learning_rate": 6.542246282281772e-06,
"loss": 750.9903,
"step": 4480
},
{
"epoch": 0.897,
"grad_norm": 103.23604583740234,
"learning_rate": 6.418632416150927e-06,
"loss": 748.7111,
"step": 4485
},
{
"epoch": 0.898,
"grad_norm": 99.45317077636719,
"learning_rate": 6.296158809451602e-06,
"loss": 757.3596,
"step": 4490
},
{
"epoch": 0.899,
"grad_norm": 132.72683715820312,
"learning_rate": 6.174826954486068e-06,
"loss": 716.1179,
"step": 4495
},
{
"epoch": 0.9,
"grad_norm": 102.58924865722656,
"learning_rate": 6.054638329644657e-06,
"loss": 728.9538,
"step": 4500
},
{
"epoch": 0.901,
"grad_norm": 146.4499053955078,
"learning_rate": 5.935594399387856e-06,
"loss": 764.7059,
"step": 4505
},
{
"epoch": 0.902,
"grad_norm": 135.03732299804688,
"learning_rate": 5.8176966142283965e-06,
"loss": 721.9727,
"step": 4510
},
{
"epoch": 0.903,
"grad_norm": 112.37531280517578,
"learning_rate": 5.700946410713548e-06,
"loss": 748.3583,
"step": 4515
},
{
"epoch": 0.904,
"grad_norm": 104.35015106201172,
"learning_rate": 5.585345211407733e-06,
"loss": 608.586,
"step": 4520
},
{
"epoch": 0.905,
"grad_norm": 154.65383911132812,
"learning_rate": 5.470894424875062e-06,
"loss": 768.8149,
"step": 4525
},
{
"epoch": 0.906,
"grad_norm": 104.11727142333984,
"learning_rate": 5.357595445662267e-06,
"loss": 801.9335,
"step": 4530
},
{
"epoch": 0.907,
"grad_norm": 95.1136245727539,
"learning_rate": 5.245449654281631e-06,
"loss": 745.119,
"step": 4535
},
{
"epoch": 0.908,
"grad_norm": 107.61206817626953,
"learning_rate": 5.134458417194254e-06,
"loss": 741.723,
"step": 4540
},
{
"epoch": 0.909,
"grad_norm": 119.71781158447266,
"learning_rate": 5.024623086793323e-06,
"loss": 788.0633,
"step": 4545
},
{
"epoch": 0.91,
"grad_norm": 115.66255187988281,
"learning_rate": 4.915945001387667e-06,
"loss": 751.7903,
"step": 4550
},
{
"epoch": 0.911,
"grad_norm": 111.3946533203125,
"learning_rate": 4.808425485185486e-06,
"loss": 761.7375,
"step": 4555
},
{
"epoch": 0.912,
"grad_norm": 157.9624786376953,
"learning_rate": 4.702065848278126e-06,
"loss": 751.2642,
"step": 4560
},
{
"epoch": 0.913,
"grad_norm": 110.56884765625,
"learning_rate": 4.596867386624215e-06,
"loss": 736.481,
"step": 4565
},
{
"epoch": 0.914,
"grad_norm": 125.71932220458984,
"learning_rate": 4.492831382033791e-06,
"loss": 732.392,
"step": 4570
},
{
"epoch": 0.915,
"grad_norm": 100.00736236572266,
"learning_rate": 4.389959102152774e-06,
"loss": 791.489,
"step": 4575
},
{
"epoch": 0.916,
"grad_norm": 105.15299224853516,
"learning_rate": 4.288251800447385e-06,
"loss": 711.2834,
"step": 4580
},
{
"epoch": 0.917,
"grad_norm": 134.78321838378906,
"learning_rate": 4.187710716189042e-06,
"loss": 765.7188,
"step": 4585
},
{
"epoch": 0.918,
"grad_norm": 94.43842315673828,
"learning_rate": 4.088337074439097e-06,
"loss": 740.3535,
"step": 4590
},
{
"epoch": 0.919,
"grad_norm": 110.41334533691406,
"learning_rate": 3.990132086034026e-06,
"loss": 758.2499,
"step": 4595
},
{
"epoch": 0.92,
"grad_norm": 132.27561950683594,
"learning_rate": 3.893096947570618e-06,
"loss": 760.9839,
"step": 4600
},
{
"epoch": 0.921,
"grad_norm": 133.86276245117188,
"learning_rate": 3.797232841391407e-06,
"loss": 752.3381,
"step": 4605
},
{
"epoch": 0.922,
"grad_norm": 96.37591552734375,
"learning_rate": 3.7025409355702976e-06,
"loss": 733.5309,
"step": 4610
},
{
"epoch": 0.923,
"grad_norm": 146.95863342285156,
"learning_rate": 3.6090223838982417e-06,
"loss": 732.8718,
"step": 4615
},
{
"epoch": 0.924,
"grad_norm": 102.6016616821289,
"learning_rate": 3.516678325869316e-06,
"loss": 770.3316,
"step": 4620
},
{
"epoch": 0.925,
"grad_norm": 151.89987182617188,
"learning_rate": 3.425509886666711e-06,
"loss": 751.9114,
"step": 4625
},
{
"epoch": 0.926,
"grad_norm": 107.16527557373047,
"learning_rate": 3.3355181771490772e-06,
"loss": 771.952,
"step": 4630
},
{
"epoch": 0.927,
"grad_norm": 102.35575866699219,
"learning_rate": 3.246704293837011e-06,
"loss": 728.56,
"step": 4635
},
{
"epoch": 0.928,
"grad_norm": 106.2490005493164,
"learning_rate": 3.1590693188996323e-06,
"loss": 658.9286,
"step": 4640
},
{
"epoch": 0.929,
"grad_norm": 108.29335021972656,
"learning_rate": 3.072614320141487e-06,
"loss": 739.0025,
"step": 4645
},
{
"epoch": 0.93,
"grad_norm": 108.69361877441406,
"learning_rate": 2.9873403509894203e-06,
"loss": 727.1281,
"step": 4650
},
{
"epoch": 0.931,
"grad_norm": 114.34329223632812,
"learning_rate": 2.9032484504798452e-06,
"loss": 718.425,
"step": 4655
},
{
"epoch": 0.932,
"grad_norm": 94.90485382080078,
"learning_rate": 2.8203396432460506e-06,
"loss": 736.1497,
"step": 4660
},
{
"epoch": 0.933,
"grad_norm": 100.45852661132812,
"learning_rate": 2.738614939505646e-06,
"loss": 732.7588,
"step": 4665
},
{
"epoch": 0.934,
"grad_norm": 132.92970275878906,
"learning_rate": 2.6580753350484046e-06,
"loss": 710.9928,
"step": 4670
},
{
"epoch": 0.935,
"grad_norm": 105.40165710449219,
"learning_rate": 2.5787218112239496e-06,
"loss": 751.2794,
"step": 4675
},
{
"epoch": 0.936,
"grad_norm": 148.64309692382812,
"learning_rate": 2.5005553349299547e-06,
"loss": 760.1068,
"step": 4680
},
{
"epoch": 0.937,
"grad_norm": 103.80183410644531,
"learning_rate": 2.4235768586002517e-06,
"loss": 763.0013,
"step": 4685
},
{
"epoch": 0.938,
"grad_norm": 113.28507232666016,
"learning_rate": 2.3477873201932734e-06,
"loss": 771.9984,
"step": 4690
},
{
"epoch": 0.939,
"grad_norm": 100.18511199951172,
"learning_rate": 2.273187643180652e-06,
"loss": 754.0826,
"step": 4695
},
{
"epoch": 0.94,
"grad_norm": 104.23270416259766,
"learning_rate": 2.1997787365358958e-06,
"loss": 757.5555,
"step": 4700
},
{
"epoch": 0.941,
"grad_norm": 101.6742172241211,
"learning_rate": 2.1275614947233624e-06,
"loss": 756.4926,
"step": 4705
},
{
"epoch": 0.942,
"grad_norm": 99.96138000488281,
"learning_rate": 2.0565367976873584e-06,
"loss": 777.0503,
"step": 4710
},
{
"epoch": 0.943,
"grad_norm": 106.09489440917969,
"learning_rate": 1.986705510841402e-06,
"loss": 737.227,
"step": 4715
},
{
"epoch": 0.944,
"grad_norm": 95.21876525878906,
"learning_rate": 1.918068485057689e-06,
"loss": 732.3941,
"step": 4720
},
{
"epoch": 0.945,
"grad_norm": 112.30679321289062,
"learning_rate": 1.8506265566567094e-06,
"loss": 733.5752,
"step": 4725
},
{
"epoch": 0.946,
"grad_norm": 161.1216278076172,
"learning_rate": 1.7843805473970798e-06,
"loss": 748.2802,
"step": 4730
},
{
"epoch": 0.947,
"grad_norm": 151.18914794921875,
"learning_rate": 1.719331264465529e-06,
"loss": 797.7781,
"step": 4735
},
{
"epoch": 0.948,
"grad_norm": 123.8327407836914,
"learning_rate": 1.6554795004670388e-06,
"loss": 760.2449,
"step": 4740
},
{
"epoch": 0.949,
"grad_norm": 152.73231506347656,
"learning_rate": 1.5928260334151845e-06,
"loss": 794.5867,
"step": 4745
},
{
"epoch": 0.95,
"grad_norm": 145.68008422851562,
"learning_rate": 1.5313716267226996e-06,
"loss": 753.2548,
"step": 4750
},
{
"epoch": 0.951,
"grad_norm": 109.66212463378906,
"learning_rate": 1.4711170291921484e-06,
"loss": 754.8116,
"step": 4755
},
{
"epoch": 0.952,
"grad_norm": 98.61844635009766,
"learning_rate": 1.412062975006767e-06,
"loss": 752.2364,
"step": 4760
},
{
"epoch": 0.953,
"grad_norm": 131.85299682617188,
"learning_rate": 1.3542101837215826e-06,
"loss": 780.2983,
"step": 4765
},
{
"epoch": 0.954,
"grad_norm": 226.88719177246094,
"learning_rate": 1.2975593602545965e-06,
"loss": 734.6846,
"step": 4770
},
{
"epoch": 0.955,
"grad_norm": 128.00872802734375,
"learning_rate": 1.2421111948782149e-06,
"loss": 761.6058,
"step": 4775
},
{
"epoch": 0.956,
"grad_norm": 98.53839111328125,
"learning_rate": 1.1878663632108322e-06,
"loss": 749.4281,
"step": 4780
},
{
"epoch": 0.957,
"grad_norm": 109.58452606201172,
"learning_rate": 1.134825526208605e-06,
"loss": 749.3813,
"step": 4785
},
{
"epoch": 0.958,
"grad_norm": 93.3302001953125,
"learning_rate": 1.0829893301573913e-06,
"loss": 736.0413,
"step": 4790
},
{
"epoch": 0.959,
"grad_norm": 109.39580535888672,
"learning_rate": 1.0323584066648795e-06,
"loss": 685.6495,
"step": 4795
},
{
"epoch": 0.96,
"grad_norm": 101.05670166015625,
"learning_rate": 9.829333726529056e-07,
"loss": 711.7023,
"step": 4800
},
{
"epoch": 0.961,
"grad_norm": 91.90048217773438,
"learning_rate": 9.347148303499142e-07,
"loss": 714.1281,
"step": 4805
},
{
"epoch": 0.962,
"grad_norm": 132.90899658203125,
"learning_rate": 8.877033672835988e-07,
"loss": 650.3487,
"step": 4810
},
{
"epoch": 0.963,
"grad_norm": 133.3742218017578,
"learning_rate": 8.418995562738285e-07,
"loss": 504.1983,
"step": 4815
},
{
"epoch": 0.964,
"grad_norm": 230.92562866210938,
"learning_rate": 7.973039554255768e-07,
"loss": 522.0018,
"step": 4820
},
{
"epoch": 0.965,
"grad_norm": 107.40252685546875,
"learning_rate": 7.539171081221596e-07,
"loss": 719.0375,
"step": 4825
},
{
"epoch": 0.966,
"grad_norm": 126.61492919921875,
"learning_rate": 7.117395430186414e-07,
"loss": 766.144,
"step": 4830
},
{
"epoch": 0.967,
"grad_norm": 124.14632415771484,
"learning_rate": 6.707717740353059e-07,
"loss": 704.1049,
"step": 4835
},
{
"epoch": 0.968,
"grad_norm": 95.9910659790039,
"learning_rate": 6.310143003515179e-07,
"loss": 743.6468,
"step": 4840
},
{
"epoch": 0.969,
"grad_norm": 104.16435241699219,
"learning_rate": 5.924676063995382e-07,
"loss": 736.4371,
"step": 4845
},
{
"epoch": 0.97,
"grad_norm": 119.34164428710938,
"learning_rate": 5.551321618586736e-07,
"loss": 758.1264,
"step": 4850
},
{
"epoch": 0.971,
"grad_norm": 102.001708984375,
"learning_rate": 5.190084216495361e-07,
"loss": 747.3734,
"step": 4855
},
{
"epoch": 0.972,
"grad_norm": 99.4837875366211,
"learning_rate": 4.840968259284817e-07,
"loss": 691.5573,
"step": 4860
},
{
"epoch": 0.973,
"grad_norm": 127.46372985839844,
"learning_rate": 4.503978000823028e-07,
"loss": 761.9104,
"step": 4865
},
{
"epoch": 0.974,
"grad_norm": 115.3523178100586,
"learning_rate": 4.179117547229883e-07,
"loss": 723.2627,
"step": 4870
},
{
"epoch": 0.975,
"grad_norm": 98.55084228515625,
"learning_rate": 3.866390856827495e-07,
"loss": 735.3536,
"step": 4875
},
{
"epoch": 0.976,
"grad_norm": 111.00328826904297,
"learning_rate": 3.565801740092023e-07,
"loss": 719.1537,
"step": 4880
},
{
"epoch": 0.977,
"grad_norm": 128.44131469726562,
"learning_rate": 3.277353859606813e-07,
"loss": 753.0574,
"step": 4885
},
{
"epoch": 0.978,
"grad_norm": 108.69052124023438,
"learning_rate": 3.001050730018218e-07,
"loss": 755.361,
"step": 4890
},
{
"epoch": 0.979,
"grad_norm": 105.29934692382812,
"learning_rate": 2.73689571799296e-07,
"loss": 738.1923,
"step": 4895
},
{
"epoch": 0.98,
"grad_norm": 106.6639633178711,
"learning_rate": 2.484892042176279e-07,
"loss": 745.6405,
"step": 4900
},
{
"epoch": 0.981,
"grad_norm": 98.6537094116211,
"learning_rate": 2.2450427731534053e-07,
"loss": 773.02,
"step": 4905
},
{
"epoch": 0.982,
"grad_norm": 135.0740203857422,
"learning_rate": 2.017350833412146e-07,
"loss": 795.1915,
"step": 4910
},
{
"epoch": 0.983,
"grad_norm": 122.50352478027344,
"learning_rate": 1.8018189973069143e-07,
"loss": 737.5824,
"step": 4915
},
{
"epoch": 0.984,
"grad_norm": 112.06875610351562,
"learning_rate": 1.598449891024978e-07,
"loss": 766.6222,
"step": 4920
},
{
"epoch": 0.985,
"grad_norm": 104.23927307128906,
"learning_rate": 1.4072459925548177e-07,
"loss": 752.4283,
"step": 4925
},
{
"epoch": 0.986,
"grad_norm": 100.96743774414062,
"learning_rate": 1.2282096316554858e-07,
"loss": 771.0345,
"step": 4930
},
{
"epoch": 0.987,
"grad_norm": 106.14868927001953,
"learning_rate": 1.0613429898287398e-07,
"loss": 775.1817,
"step": 4935
},
{
"epoch": 0.988,
"grad_norm": 158.51129150390625,
"learning_rate": 9.066481002918403e-08,
"loss": 815.6966,
"step": 4940
},
{
"epoch": 0.989,
"grad_norm": 98.22708892822266,
"learning_rate": 7.641268479531283e-08,
"loss": 743.8709,
"step": 4945
},
{
"epoch": 0.99,
"grad_norm": 104.54468536376953,
"learning_rate": 6.337809693891527e-08,
"loss": 731.0731,
"step": 4950
},
{
"epoch": 0.991,
"grad_norm": 105.42850494384766,
"learning_rate": 5.1561205282335547e-08,
"loss": 725.0262,
"step": 4955
},
{
"epoch": 0.992,
"grad_norm": 128.5075225830078,
"learning_rate": 4.096215381066415e-08,
"loss": 673.3387,
"step": 4960
},
{
"epoch": 0.993,
"grad_norm": 105.47679138183594,
"learning_rate": 3.1581071670006015e-08,
"loss": 748.1797,
"step": 4965
},
{
"epoch": 0.994,
"grad_norm": 95.47534942626953,
"learning_rate": 2.3418073165870636e-08,
"loss": 733.9268,
"step": 4970
},
{
"epoch": 0.995,
"grad_norm": 106.262451171875,
"learning_rate": 1.6473257761828732e-08,
"loss": 749.126,
"step": 4975
},
{
"epoch": 0.996,
"grad_norm": 121.89802551269531,
"learning_rate": 1.074671007825767e-08,
"loss": 701.0299,
"step": 4980
},
{
"epoch": 0.997,
"grad_norm": 131.22096252441406,
"learning_rate": 6.238499891353389e-09,
"loss": 738.4447,
"step": 4985
},
{
"epoch": 0.998,
"grad_norm": 139.19468688964844,
"learning_rate": 2.948682132208891e-09,
"loss": 660.0165,
"step": 4990
},
{
"epoch": 0.999,
"grad_norm": 133.82562255859375,
"learning_rate": 8.772968862369446e-10,
"loss": 651.3972,
"step": 4995
},
{
"epoch": 1.0,
"grad_norm": 136.07565307617188,
"learning_rate": 2.4369392592760164e-11,
"loss": 755.8577,
"step": 5000
},
{
"epoch": 1.0,
"step": 5000,
"total_flos": 7.022422523904e+16,
"train_loss": 981.1424667480469,
"train_runtime": 13577.5856,
"train_samples_per_second": 11.784,
"train_steps_per_second": 0.368
}
],
"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": 5977.189453125,
"learning_rate": 1.6000000000000001e-06,
"loss": 4176.6922,
"step": 5
},
{
"epoch": 0.002,
"grad_norm": 5548.77294921875,
"learning_rate": 3.6e-06,
"loss": 4080.4453,
"step": 10
},
{
"epoch": 0.003,
"grad_norm": 5243.63818359375,
"learning_rate": 5.600000000000001e-06,
"loss": 3902.6047,
"step": 15
},
{
"epoch": 0.004,
"grad_norm": 4877.013671875,
"learning_rate": 7.6e-06,
"loss": 3666.2555,
"step": 20
},
{
"epoch": 0.005,
"grad_norm": 3969.211669921875,
"learning_rate": 9.600000000000001e-06,
"loss": 3427.1504,
"step": 25
},
{
"epoch": 0.006,
"grad_norm": 2239.075439453125,
"learning_rate": 1.16e-05,
"loss": 3055.777,
"step": 30
},
{
"epoch": 0.007,
"grad_norm": 1304.8623046875,
"learning_rate": 1.3600000000000002e-05,
"loss": 2876.9252,
"step": 35
},
{
"epoch": 0.008,
"grad_norm": 1697.9920654296875,
"learning_rate": 1.56e-05,
"loss": 2802.0432,
"step": 40
},
{
"epoch": 0.009,
"grad_norm": 911.6920776367188,
"learning_rate": 1.76e-05,
"loss": 2733.0045,
"step": 45
},
{
"epoch": 0.01,
"grad_norm": 867.3721313476562,
"learning_rate": 1.9600000000000002e-05,
"loss": 2599.157,
"step": 50
},
{
"epoch": 0.011,
"grad_norm": 699.8728637695312,
"learning_rate": 2.16e-05,
"loss": 2543.0188,
"step": 55
},
{
"epoch": 0.012,
"grad_norm": 812.1158447265625,
"learning_rate": 2.36e-05,
"loss": 2406.9127,
"step": 60
},
{
"epoch": 0.013,
"grad_norm": 696.8179931640625,
"learning_rate": 2.5600000000000002e-05,
"loss": 2299.7312,