{
"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": 5266.7001953125,
"learning_rate": 1.6000000000000001e-06,
"loss": 3782.8074,
"step": 5
},
{
"epoch": 0.002,
"grad_norm": 4745.4599609375,
"learning_rate": 3.6e-06,
"loss": 3699.0461,
"step": 10
},
{
"epoch": 0.003,
"grad_norm": 4176.05859375,
"learning_rate": 5.600000000000001e-06,
"loss": 3555.8453,
"step": 15
},
{
"epoch": 0.004,
"grad_norm": 3472.902587890625,
"learning_rate": 7.6e-06,
"loss": 3356.0918,
"step": 20
},
{
"epoch": 0.005,
"grad_norm": 2188.70166015625,
"learning_rate": 9.600000000000001e-06,
"loss": 3196.0379,
"step": 25
},
{
"epoch": 0.006,
"grad_norm": 1210.4024658203125,
"learning_rate": 1.16e-05,
"loss": 3019.327,
"step": 30
},
{
"epoch": 0.007,
"grad_norm": 1698.2469482421875,
"learning_rate": 1.3600000000000002e-05,
"loss": 2985.2305,
"step": 35
},
{
"epoch": 0.008,
"grad_norm": 781.6577758789062,
"learning_rate": 1.56e-05,
"loss": 2913.9523,
"step": 40
},
{
"epoch": 0.009,
"grad_norm": 915.7643432617188,
"learning_rate": 1.76e-05,
"loss": 2852.7895,
"step": 45
},
{
"epoch": 0.01,
"grad_norm": 642.8707885742188,
"learning_rate": 1.9600000000000002e-05,
"loss": 2772.2295,
"step": 50
},
{
"epoch": 0.011,
"grad_norm": 682.644287109375,
"learning_rate": 2.16e-05,
"loss": 2712.7576,
"step": 55
},
{
"epoch": 0.012,
"grad_norm": 601.84033203125,
"learning_rate": 2.36e-05,
"loss": 2632.6984,
"step": 60
},
{
"epoch": 0.013,
"grad_norm": 554.9131469726562,
"learning_rate": 2.5600000000000002e-05,
"loss": 2558.6363,
"step": 65
},
{
"epoch": 0.014,
"grad_norm": 587.393310546875,
"learning_rate": 2.7600000000000003e-05,
"loss": 2524.5031,
"step": 70
},
{
"epoch": 0.015,
"grad_norm": 549.9609375,
"learning_rate": 2.96e-05,
"loss": 2547.3141,
"step": 75
},
{
"epoch": 0.016,
"grad_norm": 595.7313232421875,
"learning_rate": 3.16e-05,
"loss": 2461.9041,
"step": 80
},
{
"epoch": 0.017,
"grad_norm": 731.033203125,
"learning_rate": 3.3600000000000004e-05,
"loss": 2410.2855,
"step": 85
},
{
"epoch": 0.018,
"grad_norm": 837.6647338867188,
"learning_rate": 3.56e-05,
"loss": 2452.1389,
"step": 90
},
{
"epoch": 0.019,
"grad_norm": 449.8694152832031,
"learning_rate": 3.76e-05,
"loss": 2434.4617,
"step": 95
},
{
"epoch": 0.02,
"grad_norm": 574.4240112304688,
"learning_rate": 3.960000000000001e-05,
"loss": 2413.1385,
"step": 100
},
{
"epoch": 0.021,
"grad_norm": 611.1188354492188,
"learning_rate": 4.16e-05,
"loss": 2428.4012,
"step": 105
},
{
"epoch": 0.022,
"grad_norm": 437.6591491699219,
"learning_rate": 4.36e-05,
"loss": 2427.1658,
"step": 110
},
{
"epoch": 0.023,
"grad_norm": 862.2918090820312,
"learning_rate": 4.5600000000000004e-05,
"loss": 2356.5787,
"step": 115
},
{
"epoch": 0.024,
"grad_norm": 435.08001708984375,
"learning_rate": 4.76e-05,
"loss": 2388.3979,
"step": 120
},
{
"epoch": 0.025,
"grad_norm": 457.7765197753906,
"learning_rate": 4.96e-05,
"loss": 2371.5564,
"step": 125
},
{
"epoch": 0.026,
"grad_norm": 574.1673583984375,
"learning_rate": 5.16e-05,
"loss": 2349.8391,
"step": 130
},
{
"epoch": 0.027,
"grad_norm": 507.05523681640625,
"learning_rate": 5.360000000000001e-05,
"loss": 2368.1389,
"step": 135
},
{
"epoch": 0.028,
"grad_norm": 835.8705444335938,
"learning_rate": 5.560000000000001e-05,
"loss": 2353.4416,
"step": 140
},
{
"epoch": 0.029,
"grad_norm": 497.61126708984375,
"learning_rate": 5.76e-05,
"loss": 2360.1156,
"step": 145
},
{
"epoch": 0.03,
"grad_norm": 952.9124755859375,
"learning_rate": 5.96e-05,
"loss": 2312.2059,
"step": 150
},
{
"epoch": 0.031,
"grad_norm": 850.2002563476562,
"learning_rate": 6.16e-05,
"loss": 2366.6486,
"step": 155
},
{
"epoch": 0.032,
"grad_norm": 1506.6605224609375,
"learning_rate": 6.36e-05,
"loss": 2311.8699,
"step": 160
},
{
"epoch": 0.033,
"grad_norm": 756.28125,
"learning_rate": 6.560000000000001e-05,
"loss": 2272.985,
"step": 165
},
{
"epoch": 0.034,
"grad_norm": 815.7053833007812,
"learning_rate": 6.76e-05,
"loss": 2406.5846,
"step": 170
},
{
"epoch": 0.035,
"grad_norm": 655.5988159179688,
"learning_rate": 6.96e-05,
"loss": 2359.5096,
"step": 175
},
{
"epoch": 0.036,
"grad_norm": 704.1683959960938,
"learning_rate": 7.16e-05,
"loss": 2298.8313,
"step": 180
},
{
"epoch": 0.037,
"grad_norm": 736.1341552734375,
"learning_rate": 7.36e-05,
"loss": 2272.4133,
"step": 185
},
{
"epoch": 0.038,
"grad_norm": 1187.62109375,
"learning_rate": 7.560000000000001e-05,
"loss": 2257.5275,
"step": 190
},
{
"epoch": 0.039,
"grad_norm": 542.8311157226562,
"learning_rate": 7.76e-05,
"loss": 2232.7543,
"step": 195
},
{
"epoch": 0.04,
"grad_norm": 957.5067749023438,
"learning_rate": 7.960000000000001e-05,
"loss": 2157.5338,
"step": 200
},
{
"epoch": 0.041,
"grad_norm": 1342.906982421875,
"learning_rate": 8.16e-05,
"loss": 2253.5855,
"step": 205
},
{
"epoch": 0.042,
"grad_norm": 610.5823974609375,
"learning_rate": 8.36e-05,
"loss": 2219.376,
"step": 210
},
{
"epoch": 0.043,
"grad_norm": 492.2629699707031,
"learning_rate": 8.560000000000001e-05,
"loss": 2214.3725,
"step": 215
},
{
"epoch": 0.044,
"grad_norm": 544.4318237304688,
"learning_rate": 8.76e-05,
"loss": 2249.9154,
"step": 220
},
{
"epoch": 0.045,
"grad_norm": 424.9266357421875,
"learning_rate": 8.960000000000001e-05,
"loss": 2178.3441,
"step": 225
},
{
"epoch": 0.046,
"grad_norm": 1075.974365234375,
"learning_rate": 9.16e-05,
"loss": 2183.6512,
"step": 230
},
{
"epoch": 0.047,
"grad_norm": 695.756591796875,
"learning_rate": 9.360000000000001e-05,
"loss": 2176.1957,
"step": 235
},
{
"epoch": 0.048,
"grad_norm": 681.6115112304688,
"learning_rate": 9.56e-05,
"loss": 2175.4352,
"step": 240
},
{
"epoch": 0.049,
"grad_norm": 414.23883056640625,
"learning_rate": 9.76e-05,
"loss": 2150.267,
"step": 245
},
{
"epoch": 0.05,
"grad_norm": 428.9521789550781,
"learning_rate": 9.960000000000001e-05,
"loss": 2180.2301,
"step": 250
},
{
"epoch": 0.051,
"grad_norm": 521.28466796875,
"learning_rate": 0.0001016,
"loss": 2132.1178,
"step": 255
},
{
"epoch": 0.052,
"grad_norm": 1059.0888671875,
"learning_rate": 0.00010360000000000001,
"loss": 2162.9885,
"step": 260
},
{
"epoch": 0.053,
"grad_norm": 444.8804931640625,
"learning_rate": 0.0001056,
"loss": 2120.9191,
"step": 265
},
{
"epoch": 0.054,
"grad_norm": 543.1753540039062,
"learning_rate": 0.00010760000000000001,
"loss": 2080.3918,
"step": 270
},
{
"epoch": 0.055,
"grad_norm": 918.5087890625,
"learning_rate": 0.00010960000000000001,
"loss": 2175.3832,
"step": 275
},
{
"epoch": 0.056,
"grad_norm": 537.5587768554688,
"learning_rate": 0.00011160000000000002,
"loss": 2137.8615,
"step": 280
},
{
"epoch": 0.057,
"grad_norm": 575.5532836914062,
"learning_rate": 0.0001136,
"loss": 2150.9424,
"step": 285
},
{
"epoch": 0.058,
"grad_norm": 503.91253662109375,
"learning_rate": 0.00011559999999999999,
"loss": 2082.6168,
"step": 290
},
{
"epoch": 0.059,
"grad_norm": 454.11468505859375,
"learning_rate": 0.0001176,
"loss": 2128.1039,
"step": 295
},
{
"epoch": 0.06,
"grad_norm": 720.2813110351562,
"learning_rate": 0.00011960000000000001,
"loss": 2135.1645,
"step": 300
},
{
"epoch": 0.061,
"grad_norm": 1057.0235595703125,
"learning_rate": 0.0001216,
"loss": 2101.7613,
"step": 305
},
{
"epoch": 0.062,
"grad_norm": 1169.8017578125,
"learning_rate": 0.0001236,
"loss": 2180.2941,
"step": 310
},
{
"epoch": 0.063,
"grad_norm": 897.830322265625,
"learning_rate": 0.00012560000000000002,
"loss": 2041.9826,
"step": 315
},
{
"epoch": 0.064,
"grad_norm": 1063.396240234375,
"learning_rate": 0.0001276,
"loss": 2035.5609,
"step": 320
},
{
"epoch": 0.065,
"grad_norm": 883.4168090820312,
"learning_rate": 0.0001296,
"loss": 2074.7363,
"step": 325
},
{
"epoch": 0.066,
"grad_norm": 764.0631713867188,
"learning_rate": 0.0001316,
"loss": 2086.6396,
"step": 330
},
{
"epoch": 0.067,
"grad_norm": 427.7580871582031,
"learning_rate": 0.00013360000000000002,
"loss": 2085.716,
"step": 335
},
{
"epoch": 0.068,
"grad_norm": 809.0924072265625,
"learning_rate": 0.00013560000000000002,
"loss": 2100.1373,
"step": 340
},
{
"epoch": 0.069,
"grad_norm": 630.7706298828125,
"learning_rate": 0.00013759999999999998,
"loss": 2044.4809,
"step": 345
},
{
"epoch": 0.07,
"grad_norm": 580.7897338867188,
"learning_rate": 0.0001396,
"loss": 2041.8256,
"step": 350
},
{
"epoch": 0.071,
"grad_norm": 519.4344482421875,
"learning_rate": 0.0001416,
"loss": 2027.6299,
"step": 355
},
{
"epoch": 0.072,
"grad_norm": 1008.7359619140625,
"learning_rate": 0.0001436,
"loss": 2001.7809,
"step": 360
},
{
"epoch": 0.073,
"grad_norm": 887.033447265625,
"learning_rate": 0.00014560000000000002,
"loss": 2003.2418,
"step": 365
},
{
"epoch": 0.074,
"grad_norm": 458.1086730957031,
"learning_rate": 0.0001476,
"loss": 2018.6246,
"step": 370
},
{
"epoch": 0.075,
"grad_norm": 558.6400146484375,
"learning_rate": 0.0001496,
"loss": 2010.2418,
"step": 375
},
{
"epoch": 0.076,
"grad_norm": 541.665283203125,
"learning_rate": 0.0001516,
"loss": 2003.2859,
"step": 380
},
{
"epoch": 0.077,
"grad_norm": 643.4810791015625,
"learning_rate": 0.00015360000000000002,
"loss": 1958.5557,
"step": 385
},
{
"epoch": 0.078,
"grad_norm": 607.7810668945312,
"learning_rate": 0.00015560000000000001,
"loss": 1960.0062,
"step": 390
},
{
"epoch": 0.079,
"grad_norm": 332.4576416015625,
"learning_rate": 0.0001576,
"loss": 1952.1887,
"step": 395
},
{
"epoch": 0.08,
"grad_norm": 739.3090209960938,
"learning_rate": 0.0001596,
"loss": 2015.8143,
"step": 400
},
{
"epoch": 0.081,
"grad_norm": 1086.49755859375,
"learning_rate": 0.00016160000000000002,
"loss": 1942.5027,
"step": 405
},
{
"epoch": 0.082,
"grad_norm": 807.6548461914062,
"learning_rate": 0.0001636,
"loss": 2029.6205,
"step": 410
},
{
"epoch": 0.083,
"grad_norm": 1160.2926025390625,
"learning_rate": 0.0001656,
"loss": 2011.9086,
"step": 415
},
{
"epoch": 0.084,
"grad_norm": 737.6138305664062,
"learning_rate": 0.0001676,
"loss": 2048.1787,
"step": 420
},
{
"epoch": 0.085,
"grad_norm": 610.2138061523438,
"learning_rate": 0.0001696,
"loss": 1998.4979,
"step": 425
},
{
"epoch": 0.086,
"grad_norm": 766.2254028320312,
"learning_rate": 0.0001716,
"loss": 1967.1303,
"step": 430
},
{
"epoch": 0.087,
"grad_norm": 726.3220825195312,
"learning_rate": 0.00017360000000000002,
"loss": 2003.876,
"step": 435
},
{
"epoch": 0.088,
"grad_norm": 770.865966796875,
"learning_rate": 0.0001756,
"loss": 2044.4623,
"step": 440
},
{
"epoch": 0.089,
"grad_norm": 545.40869140625,
"learning_rate": 0.0001776,
"loss": 2019.7451,
"step": 445
},
{
"epoch": 0.09,
"grad_norm": 588.9122924804688,
"learning_rate": 0.0001796,
"loss": 1934.8879,
"step": 450
},
{
"epoch": 0.091,
"grad_norm": 555.0855102539062,
"learning_rate": 0.00018160000000000002,
"loss": 1973.8857,
"step": 455
},
{
"epoch": 0.092,
"grad_norm": 739.3436889648438,
"learning_rate": 0.00018360000000000002,
"loss": 1968.1404,
"step": 460
},
{
"epoch": 0.093,
"grad_norm": 400.6427307128906,
"learning_rate": 0.0001856,
"loss": 1855.9383,
"step": 465
},
{
"epoch": 0.094,
"grad_norm": 369.4656982421875,
"learning_rate": 0.0001876,
"loss": 1878.5266,
"step": 470
},
{
"epoch": 0.095,
"grad_norm": 684.5033569335938,
"learning_rate": 0.0001896,
"loss": 1925.8629,
"step": 475
},
{
"epoch": 0.096,
"grad_norm": 601.646240234375,
"learning_rate": 0.0001916,
"loss": 1963.3482,
"step": 480
},
{
"epoch": 0.097,
"grad_norm": 449.1803283691406,
"learning_rate": 0.00019360000000000002,
"loss": 1874.283,
"step": 485
},
{
"epoch": 0.098,
"grad_norm": 376.5309143066406,
"learning_rate": 0.0001956,
"loss": 1911.0373,
"step": 490
},
{
"epoch": 0.099,
"grad_norm": 365.7178649902344,
"learning_rate": 0.0001976,
"loss": 1923.2469,
"step": 495
},
{
"epoch": 0.1,
"grad_norm": 349.053466796875,
"learning_rate": 0.0001996,
"loss": 1878.2211,
"step": 500
},
{
"epoch": 0.101,
"grad_norm": 809.0552978515625,
"learning_rate": 0.00019999961008995606,
"loss": 1917.9117,
"step": 505
},
{
"epoch": 0.102,
"grad_norm": 737.5787353515625,
"learning_rate": 0.0001999980260856137,
"loss": 1904.6941,
"step": 510
},
{
"epoch": 0.103,
"grad_norm": 493.6395568847656,
"learning_rate": 0.000199995223636881,
"loss": 1969.8635,
"step": 515
},
{
"epoch": 0.104,
"grad_norm": 672.5117797851562,
"learning_rate": 0.00019999120277790477,
"loss": 1987.7023,
"step": 520
},
{
"epoch": 0.105,
"grad_norm": 516.834716796875,
"learning_rate": 0.00019998596355767805,
"loss": 1929.0186,
"step": 525
},
{
"epoch": 0.106,
"grad_norm": 947.6466064453125,
"learning_rate": 0.000199979506040039,
"loss": 1963.7848,
"step": 530
},
{
"epoch": 0.107,
"grad_norm": 561.9028930664062,
"learning_rate": 0.00019997183030367048,
"loss": 1870.6865,
"step": 535
},
{
"epoch": 0.108,
"grad_norm": 794.3494873046875,
"learning_rate": 0.00019996293644209887,
"loss": 1933.8018,
"step": 540
},
{
"epoch": 0.109,
"grad_norm": 1117.1009521484375,
"learning_rate": 0.0001999528245636931,
"loss": 1905.3668,
"step": 545
},
{
"epoch": 0.11,
"grad_norm": 1181.3507080078125,
"learning_rate": 0.00019994149479166324,
"loss": 1906.2426,
"step": 550
},
{
"epoch": 0.111,
"grad_norm": 558.6856689453125,
"learning_rate": 0.00019992894726405893,
"loss": 1801.2777,
"step": 555
},
{
"epoch": 0.112,
"grad_norm": 475.2767639160156,
"learning_rate": 0.00019991518213376787,
"loss": 1892.2361,
"step": 560
},
{
"epoch": 0.113,
"grad_norm": 1280.0999755859375,
"learning_rate": 0.00019990019956851382,
"loss": 1962.0072,
"step": 565
},
{
"epoch": 0.114,
"grad_norm": 368.488525390625,
"learning_rate": 0.0001998839997508546,
"loss": 1889.4635,
"step": 570
},
{
"epoch": 0.115,
"grad_norm": 550.21826171875,
"learning_rate": 0.00019986658287817987,
"loss": 1877.3463,
"step": 575
},
{
"epoch": 0.116,
"grad_norm": 919.0028686523438,
"learning_rate": 0.00019984794916270876,
"loss": 1920.0283,
"step": 580
},
{
"epoch": 0.117,
"grad_norm": 613.1447143554688,
"learning_rate": 0.00019982809883148722,
"loss": 1918.0187,
"step": 585
},
{
"epoch": 0.118,
"grad_norm": 552.943115234375,
"learning_rate": 0.00019980703212638522,
"loss": 1889.6771,
"step": 590
},
{
"epoch": 0.119,
"grad_norm": 657.1201171875,
"learning_rate": 0.00019978474930409395,
"loss": 1928.1369,
"step": 595
},
{
"epoch": 0.12,
"grad_norm": 626.6583862304688,
"learning_rate": 0.00019976125063612252,
"loss": 1895.3066,
"step": 600
},
{
"epoch": 0.121,
"grad_norm": 890.3414916992188,
"learning_rate": 0.00019973653640879485,
"loss": 1884.4684,
"step": 605
},
{
"epoch": 0.122,
"grad_norm": 630.04638671875,
"learning_rate": 0.00019971060692324598,
"loss": 1889.1303,
"step": 610
},
{
"epoch": 0.123,
"grad_norm": 747.7299194335938,
"learning_rate": 0.00019968346249541846,
"loss": 1881.5625,
"step": 615
},
{
"epoch": 0.124,
"grad_norm": 743.1279296875,
"learning_rate": 0.00019965510345605866,
"loss": 1845.1594,
"step": 620
},
{
"epoch": 0.125,
"grad_norm": 1044.1627197265625,
"learning_rate": 0.0001996255301507125,
"loss": 1861.6158,
"step": 625
},
{
"epoch": 0.126,
"grad_norm": 440.7723083496094,
"learning_rate": 0.00019959474293972129,
"loss": 1892.6498,
"step": 630
},
{
"epoch": 0.127,
"grad_norm": 766.7957763671875,
"learning_rate": 0.00019956274219821757,
"loss": 1840.7287,
"step": 635
},
{
"epoch": 0.128,
"grad_norm": 364.86834716796875,
"learning_rate": 0.00019952952831612026,
"loss": 1898.2387,
"step": 640
},
{
"epoch": 0.129,
"grad_norm": 540.8771362304688,
"learning_rate": 0.00019949510169813003,
"loss": 1784.8539,
"step": 645
},
{
"epoch": 0.13,
"grad_norm": 524.658203125,
"learning_rate": 0.00019945946276372434,
"loss": 1850.4855,
"step": 650
},
{
"epoch": 0.131,
"grad_norm": 846.89599609375,
"learning_rate": 0.00019942261194715236,
"loss": 1852.6762,
"step": 655
},
{
"epoch": 0.132,
"grad_norm": 408.8316345214844,
"learning_rate": 0.00019938454969742968,
"loss": 1850.1617,
"step": 660
},
{
"epoch": 0.133,
"grad_norm": 407.37841796875,
"learning_rate": 0.00019934527647833276,
"loss": 1804.8211,
"step": 665
},
{
"epoch": 0.134,
"grad_norm": 400.1478576660156,
"learning_rate": 0.00019930479276839344,
"loss": 1781.7338,
"step": 670
},
{
"epoch": 0.135,
"grad_norm": 319.2127380371094,
"learning_rate": 0.0001992630990608929,
"loss": 1818.1621,
"step": 675
},
{
"epoch": 0.136,
"grad_norm": 530.6392822265625,
"learning_rate": 0.00019922019586385585,
"loss": 1796.25,
"step": 680
},
{
"epoch": 0.137,
"grad_norm": 877.326416015625,
"learning_rate": 0.00019917608370004417,
"loss": 1788.9123,
"step": 685
},
{
"epoch": 0.138,
"grad_norm": 525.0850830078125,
"learning_rate": 0.00019913076310695068,
"loss": 1806.9994,
"step": 690
},
{
"epoch": 0.139,
"grad_norm": 418.4032897949219,
"learning_rate": 0.00019908423463679248,
"loss": 1933.5846,
"step": 695
},
{
"epoch": 0.14,
"grad_norm": 392.0401916503906,
"learning_rate": 0.0001990364988565043,
"loss": 1790.9354,
"step": 700
},
{
"epoch": 0.141,
"grad_norm": 362.43817138671875,
"learning_rate": 0.00019898755634773158,
"loss": 1837.2445,
"step": 705
},
{
"epoch": 0.142,
"grad_norm": 546.3214721679688,
"learning_rate": 0.00019893740770682335,
"loss": 1816.8154,
"step": 710
},
{
"epoch": 0.143,
"grad_norm": 405.3300476074219,
"learning_rate": 0.0001988860535448249,
"loss": 1775.2393,
"step": 715
},
{
"epoch": 0.144,
"grad_norm": 508.8732604980469,
"learning_rate": 0.00019883349448747062,
"loss": 1824.049,
"step": 720
},
{
"epoch": 0.145,
"grad_norm": 519.3333740234375,
"learning_rate": 0.0001987797311751759,
"loss": 1784.351,
"step": 725
},
{
"epoch": 0.146,
"grad_norm": 496.0126953125,
"learning_rate": 0.00019872476426302982,
"loss": 1780.9803,
"step": 730
},
{
"epoch": 0.147,
"grad_norm": 392.27520751953125,
"learning_rate": 0.0001986685944207868,
"loss": 1781.626,
"step": 735
},
{
"epoch": 0.148,
"grad_norm": 548.461669921875,
"learning_rate": 0.0001986112223328587,
"loss": 1840.0234,
"step": 740
},
{
"epoch": 0.149,
"grad_norm": 376.74102783203125,
"learning_rate": 0.00019855264869830629,
"loss": 1762.6619,
"step": 745
},
{
"epoch": 0.15,
"grad_norm": 489.22052001953125,
"learning_rate": 0.00019849287423083078,
"loss": 1736.7232,
"step": 750
},
{
"epoch": 0.151,
"grad_norm": 676.6553344726562,
"learning_rate": 0.00019843189965876526,
"loss": 1786.0621,
"step": 755
},
{
"epoch": 0.152,
"grad_norm": 483.2108154296875,
"learning_rate": 0.00019836972572506557,
"loss": 1793.143,
"step": 760
},
{
"epoch": 0.153,
"grad_norm": 423.7899169921875,
"learning_rate": 0.00019830635318730154,
"loss": 1794.9334,
"step": 765
},
{
"epoch": 0.154,
"grad_norm": 323.81427001953125,
"learning_rate": 0.00019824178281764753,
"loss": 1718.9426,
"step": 770
},
{
"epoch": 0.155,
"grad_norm": 315.7181396484375,
"learning_rate": 0.00019817601540287306,
"loss": 1720.8762,
"step": 775
},
{
"epoch": 0.156,
"grad_norm": 445.88128662109375,
"learning_rate": 0.0001981090517443334,
"loss": 1783.6916,
"step": 780
},
{
"epoch": 0.157,
"grad_norm": 487.5122375488281,
"learning_rate": 0.0001980408926579596,
"loss": 1760.9703,
"step": 785
},
{
"epoch": 0.158,
"grad_norm": 424.6282653808594,
"learning_rate": 0.00019797153897424852,
"loss": 1805.3225,
"step": 790
},
{
"epoch": 0.159,
"grad_norm": 369.0574951171875,
"learning_rate": 0.000197900991538253,
"loss": 1777.6529,
"step": 795
},
{
"epoch": 0.16,
"grad_norm": 324.7747497558594,
"learning_rate": 0.00019782925120957124,
"loss": 1744.407,
"step": 800
},
{
"epoch": 0.161,
"grad_norm": 341.69903564453125,
"learning_rate": 0.00019775631886233654,
"loss": 1743.4342,
"step": 805
},
{
"epoch": 0.162,
"grad_norm": 562.1665649414062,
"learning_rate": 0.0001976821953852065,
"loss": 1749.1527,
"step": 810
},
{
"epoch": 0.163,
"grad_norm": 513.3624877929688,
"learning_rate": 0.00019760688168135232,
"loss": 1726.8922,
"step": 815
},
{
"epoch": 0.164,
"grad_norm": 532.7508544921875,
"learning_rate": 0.00019753037866844771,
"loss": 1766.6885,
"step": 820
},
{
"epoch": 0.165,
"grad_norm": 321.7651062011719,
"learning_rate": 0.00019745268727865774,
"loss": 1680.7545,
"step": 825
},
{
"epoch": 0.166,
"grad_norm": 475.8089904785156,
"learning_rate": 0.00019737380845862745,
"loss": 1782.0496,
"step": 830
},
{
"epoch": 0.167,
"grad_norm": 350.00030517578125,
"learning_rate": 0.0001972937431694704,
"loss": 1746.5789,
"step": 835
},
{
"epoch": 0.168,
"grad_norm": 407.5339050292969,
"learning_rate": 0.00019721249238675688,
"loss": 1729.3664,
"step": 840
},
{
"epoch": 0.169,
"grad_norm": 332.9736633300781,
"learning_rate": 0.000197130057100502,
"loss": 1741.0984,
"step": 845
},
{
"epoch": 0.17,
"grad_norm": 392.3819885253906,
"learning_rate": 0.00019704643831515374,
"loss": 1730.3512,
"step": 850
},
{
"epoch": 0.171,
"grad_norm": 369.69879150390625,
"learning_rate": 0.0001969616370495806,
"loss": 1776.7697,
"step": 855
},
{
"epoch": 0.172,
"grad_norm": 583.9386596679688,
"learning_rate": 0.00019687565433705926,
"loss": 1763.0309,
"step": 860
},
{
"epoch": 0.173,
"grad_norm": 297.38372802734375,
"learning_rate": 0.00019678849122526187,
"loss": 1688.7338,
"step": 865
},
{
"epoch": 0.174,
"grad_norm": 347.4983215332031,
"learning_rate": 0.00019670014877624353,
"loss": 1646.4459,
"step": 870
},
{
"epoch": 0.175,
"grad_norm": 267.96282958984375,
"learning_rate": 0.00019661062806642903,
"loss": 1641.9887,
"step": 875
},
{
"epoch": 0.176,
"grad_norm": 417.379150390625,
"learning_rate": 0.0001965199301866,
"loss": 1645.3246,
"step": 880
},
{
"epoch": 0.177,
"grad_norm": 406.1556701660156,
"learning_rate": 0.00019642805624188147,
"loss": 1657.9016,
"step": 885
},
{
"epoch": 0.178,
"grad_norm": 378.1866760253906,
"learning_rate": 0.0001963350073517285,
"loss": 1643.1467,
"step": 890
},
{
"epoch": 0.179,
"grad_norm": 417.39178466796875,
"learning_rate": 0.0001962407846499124,
"loss": 1616.9371,
"step": 895
},
{
"epoch": 0.18,
"grad_norm": 371.41436767578125,
"learning_rate": 0.0001961453892845071,
"loss": 1631.8616,
"step": 900
},
{
"epoch": 0.181,
"grad_norm": 700.8125,
"learning_rate": 0.00019604882241787498,
"loss": 1640.9674,
"step": 905
},
{
"epoch": 0.182,
"grad_norm": 339.4018859863281,
"learning_rate": 0.0001959510852266529,
"loss": 1680.6271,
"step": 910
},
{
"epoch": 0.183,
"grad_norm": 443.57025146484375,
"learning_rate": 0.0001958521789017376,
"loss": 1732.6074,
"step": 915
},
{
"epoch": 0.184,
"grad_norm": 366.4203186035156,
"learning_rate": 0.00019575210464827149,
"loss": 1743.9914,
"step": 920
},
{
"epoch": 0.185,
"grad_norm": 354.7658386230469,
"learning_rate": 0.0001956508636856278,
"loss": 1736.7658,
"step": 925
},
{
"epoch": 0.186,
"grad_norm": 371.41802978515625,
"learning_rate": 0.00019554845724739566,
"loss": 1660.8822,
"step": 930
},
{
"epoch": 0.187,
"grad_norm": 362.6243591308594,
"learning_rate": 0.00019544488658136523,
"loss": 1688.126,
"step": 935
},
{
"epoch": 0.188,
"grad_norm": 434.04583740234375,
"learning_rate": 0.00019534015294951233,
"loss": 1706.9334,
"step": 940
},
{
"epoch": 0.189,
"grad_norm": 730.594482421875,
"learning_rate": 0.00019523425762798329,
"loss": 1721.6439,
"step": 945
},
{
"epoch": 0.19,
"grad_norm": 389.14923095703125,
"learning_rate": 0.00019512720190707913,
"loss": 1666.877,
"step": 950
},
{
"epoch": 0.191,
"grad_norm": 510.31927490234375,
"learning_rate": 0.00019501898709124008,
"loss": 1671.1195,
"step": 955
},
{
"epoch": 0.192,
"grad_norm": 387.77435302734375,
"learning_rate": 0.00019490961449902946,
"loss": 1668.2145,
"step": 960
},
{
"epoch": 0.193,
"grad_norm": 411.1667175292969,
"learning_rate": 0.00019479908546311781,
"loss": 1681.9725,
"step": 965
},
{
"epoch": 0.194,
"grad_norm": 388.1283264160156,
"learning_rate": 0.0001946874013302666,
"loss": 1682.7111,
"step": 970
},
{
"epoch": 0.195,
"grad_norm": 715.8286743164062,
"learning_rate": 0.0001945745634613117,
"loss": 1726.801,
"step": 975
},
{
"epoch": 0.196,
"grad_norm": 371.25189208984375,
"learning_rate": 0.0001944605732311469,
"loss": 1668.8609,
"step": 980
},
{
"epoch": 0.197,
"grad_norm": 680.4701538085938,
"learning_rate": 0.00019434543202870725,
"loss": 1655.4727,
"step": 985
},
{
"epoch": 0.198,
"grad_norm": 569.31396484375,
"learning_rate": 0.0001942291412569519,
"loss": 1703.6672,
"step": 990
},
{
"epoch": 0.199,
"grad_norm": 478.22418212890625,
"learning_rate": 0.00019411170233284727,
"loss": 1672.3246,
"step": 995
},
{
"epoch": 0.2,
"grad_norm": 402.09710693359375,
"learning_rate": 0.00019399311668734956,
"loss": 1633.0029,
"step": 1000
},
{
"epoch": 0.201,
"grad_norm": 284.7216491699219,
"learning_rate": 0.00019387338576538744,
"loss": 1647.0232,
"step": 1005
},
{
"epoch": 0.202,
"grad_norm": 448.49798583984375,
"learning_rate": 0.0001937525110258444,
"loss": 1645.7176,
"step": 1010
},
{
"epoch": 0.203,
"grad_norm": 312.8065490722656,
"learning_rate": 0.00019363049394154094,
"loss": 1659.8564,
"step": 1015
},
{
"epoch": 0.204,
"grad_norm": 444.33258056640625,
"learning_rate": 0.00019350733599921683,
"loss": 1681.0209,
"step": 1020
},
{
"epoch": 0.205,
"grad_norm": 378.16033935546875,
"learning_rate": 0.00019338303869951269,
"loss": 1686.2465,
"step": 1025
},
{
"epoch": 0.206,
"grad_norm": 518.3790893554688,
"learning_rate": 0.00019325760355695188,
"loss": 1686.9229,
"step": 1030
},
{
"epoch": 0.207,
"grad_norm": 373.93426513671875,
"learning_rate": 0.00019313103209992204,
"loss": 1634.1305,
"step": 1035
},
{
"epoch": 0.208,
"grad_norm": 364.1773376464844,
"learning_rate": 0.0001930033258706564,
"loss": 1576.5645,
"step": 1040
},
{
"epoch": 0.209,
"grad_norm": 516.43603515625,
"learning_rate": 0.00019287448642521513,
"loss": 1707.992,
"step": 1045
},
{
"epoch": 0.21,
"grad_norm": 469.79400634765625,
"learning_rate": 0.00019274451533346615,
"loss": 1628.6922,
"step": 1050
},
{
"epoch": 0.211,
"grad_norm": 505.22125244140625,
"learning_rate": 0.00019261341417906621,
"loss": 1699.4549,
"step": 1055
},
{
"epoch": 0.212,
"grad_norm": 613.7994384765625,
"learning_rate": 0.0001924811845594415,
"loss": 1709.7367,
"step": 1060
},
{
"epoch": 0.213,
"grad_norm": 493.4976806640625,
"learning_rate": 0.00019234782808576824,
"loss": 1691.5451,
"step": 1065
},
{
"epoch": 0.214,
"grad_norm": 559.7821655273438,
"learning_rate": 0.00019221334638295294,
"loss": 1623.3421,
"step": 1070
},
{
"epoch": 0.215,
"grad_norm": 375.07818603515625,
"learning_rate": 0.00019207774108961272,
"loss": 1637.4212,
"step": 1075
},
{
"epoch": 0.216,
"grad_norm": 372.57269287109375,
"learning_rate": 0.0001919410138580553,
"loss": 1606.9484,
"step": 1080
},
{
"epoch": 0.217,
"grad_norm": 594.0621337890625,
"learning_rate": 0.0001918031663542588,
"loss": 1618.1923,
"step": 1085
},
{
"epoch": 0.218,
"grad_norm": 697.567138671875,
"learning_rate": 0.00019166420025785164,
"loss": 1631.5878,
"step": 1090
},
{
"epoch": 0.219,
"grad_norm": 383.8708801269531,
"learning_rate": 0.00019152411726209176,
"loss": 1698.517,
"step": 1095
},
{
"epoch": 0.22,
"grad_norm": 455.00775146484375,
"learning_rate": 0.0001913829190738463,
"loss": 1598.8373,
"step": 1100
},
{
"epoch": 0.221,
"grad_norm": 372.6204833984375,
"learning_rate": 0.00019124060741357063,
"loss": 1612.0878,
"step": 1105
},
{
"epoch": 0.222,
"grad_norm": 392.7117614746094,
"learning_rate": 0.0001910971840152874,
"loss": 1644.5711,
"step": 1110
},
{
"epoch": 0.223,
"grad_norm": 635.0313110351562,
"learning_rate": 0.00019095265062656544,
"loss": 1638.2535,
"step": 1115
},
{
"epoch": 0.224,
"grad_norm": 326.864013671875,
"learning_rate": 0.00019080700900849851,
"loss": 1610.9591,
"step": 1120
},
{
"epoch": 0.225,
"grad_norm": 450.5438232421875,
"learning_rate": 0.00019066026093568378,
"loss": 1610.8865,
"step": 1125
},
{
"epoch": 0.226,
"grad_norm": 311.9197082519531,
"learning_rate": 0.00019051240819620014,
"loss": 1631.8048,
"step": 1130
},
{
"epoch": 0.227,
"grad_norm": 307.99053955078125,
"learning_rate": 0.00019036345259158667,
"loss": 1619.252,
"step": 1135
},
{
"epoch": 0.228,
"grad_norm": 292.232666015625,
"learning_rate": 0.00019021339593682028,
"loss": 1615.9986,
"step": 1140
},
{
"epoch": 0.229,
"grad_norm": 283.7676696777344,
"learning_rate": 0.00019006224006029406,
"loss": 1551.8743,
"step": 1145
},
{
"epoch": 0.23,
"grad_norm": 321.44482421875,
"learning_rate": 0.00018990998680379456,
"loss": 1626.2422,
"step": 1150
},
{
"epoch": 0.231,
"grad_norm": 501.8728942871094,
"learning_rate": 0.00018975663802247976,
"loss": 1652.3547,
"step": 1155
},
{
"epoch": 0.232,
"grad_norm": 378.7218933105469,
"learning_rate": 0.0001896021955848561,
"loss": 1583.6457,
"step": 1160
},
{
"epoch": 0.233,
"grad_norm": 395.4049987792969,
"learning_rate": 0.000189446661372756,
"loss": 1643.2613,
"step": 1165
},
{
"epoch": 0.234,
"grad_norm": 342.15582275390625,
"learning_rate": 0.0001892900372813147,
"loss": 1594.4984,
"step": 1170
},
{
"epoch": 0.235,
"grad_norm": 396.94635009765625,
"learning_rate": 0.00018913232521894732,
"loss": 1596.1575,
"step": 1175
},
{
"epoch": 0.236,
"grad_norm": 463.575439453125,
"learning_rate": 0.00018897352710732564,
"loss": 1636.157,
"step": 1180
},
{
"epoch": 0.237,
"grad_norm": 447.37823486328125,
"learning_rate": 0.00018881364488135448,
"loss": 1588.8288,
"step": 1185
},
{
"epoch": 0.238,
"grad_norm": 468.59527587890625,
"learning_rate": 0.00018865268048914828,
"loss": 1621.0631,
"step": 1190
},
{
"epoch": 0.239,
"grad_norm": 436.2962951660156,
"learning_rate": 0.00018849063589200743,
"loss": 1591.581,
"step": 1195
},
{
"epoch": 0.24,
"grad_norm": 402.772705078125,
"learning_rate": 0.00018832751306439418,
"loss": 1599.9671,
"step": 1200
},
{
"epoch": 0.241,
"grad_norm": 466.1116638183594,
"learning_rate": 0.0001881633139939087,
"loss": 1617.8568,
"step": 1205
},
{
"epoch": 0.242,
"grad_norm": 541.4430541992188,
"learning_rate": 0.00018799804068126485,
"loss": 1586.9942,
"step": 1210
},
{
"epoch": 0.243,
"grad_norm": 342.62554931640625,
"learning_rate": 0.00018783169514026578,
"loss": 1585.6615,
"step": 1215
},
{
"epoch": 0.244,
"grad_norm": 348.2602233886719,
"learning_rate": 0.00018766427939777945,
"loss": 1565.8908,
"step": 1220
},
{
"epoch": 0.245,
"grad_norm": 593.7246704101562,
"learning_rate": 0.0001874957954937138,
"loss": 1592.5703,
"step": 1225
},
{
"epoch": 0.246,
"grad_norm": 508.72967529296875,
"learning_rate": 0.00018732624548099204,
"loss": 1620.3759,
"step": 1230
},
{
"epoch": 0.247,
"grad_norm": 526.719482421875,
"learning_rate": 0.00018715563142552758,
"loss": 1606.3888,
"step": 1235
},
{
"epoch": 0.248,
"grad_norm": 285.0360107421875,
"learning_rate": 0.0001869839554061988,
"loss": 1566.5856,
"step": 1240
},
{
"epoch": 0.249,
"grad_norm": 307.4193420410156,
"learning_rate": 0.00018681121951482393,
"loss": 1599.8107,
"step": 1245
},
{
"epoch": 0.25,
"grad_norm": 262.099853515625,
"learning_rate": 0.00018663742585613518,
"loss": 1598.2749,
"step": 1250
},
{
"epoch": 0.251,
"grad_norm": 260.7579345703125,
"learning_rate": 0.0001864625765477535,
"loss": 1578.2519,
"step": 1255
},
{
"epoch": 0.252,
"grad_norm": 290.5831298828125,
"learning_rate": 0.0001862866737201625,
"loss": 1550.1314,
"step": 1260
},
{
"epoch": 0.253,
"grad_norm": 421.46697998046875,
"learning_rate": 0.00018610971951668265,
"loss": 1579.9067,
"step": 1265
},
{
"epoch": 0.254,
"grad_norm": 257.4235534667969,
"learning_rate": 0.00018593171609344503,
"loss": 1587.5214,
"step": 1270
},
{
"epoch": 0.255,
"grad_norm": 336.5163879394531,
"learning_rate": 0.00018575266561936523,
"loss": 1546.8168,
"step": 1275
},
{
"epoch": 0.256,
"grad_norm": 372.4332580566406,
"learning_rate": 0.00018557257027611675,
"loss": 1542.0183,
"step": 1280
},
{
"epoch": 0.257,
"grad_norm": 456.28759765625,
"learning_rate": 0.0001853914322581045,
"loss": 1562.2891,
"step": 1285
},
{
"epoch": 0.258,
"grad_norm": 301.17413330078125,
"learning_rate": 0.0001852092537724381,
"loss": 1586.7509,
"step": 1290
},
{
"epoch": 0.259,
"grad_norm": 360.4347229003906,
"learning_rate": 0.00018502603703890488,
"loss": 1565.846,
"step": 1295
},
{
"epoch": 0.26,
"grad_norm": 354.089599609375,
"learning_rate": 0.0001848417842899429,
"loss": 1603.4535,
"step": 1300
},
{
"epoch": 0.261,
"grad_norm": 351.3242492675781,
"learning_rate": 0.0001846564977706138,
"loss": 1561.1306,
"step": 1305
},
{
"epoch": 0.262,
"grad_norm": 388.5971984863281,
"learning_rate": 0.00018447017973857532,
"loss": 1591.9506,
"step": 1310
},
{
"epoch": 0.263,
"grad_norm": 386.6748962402344,
"learning_rate": 0.0001842828324640539,
"loss": 1557.1815,
"step": 1315
},
{
"epoch": 0.264,
"grad_norm": 753.9038696289062,
"learning_rate": 0.00018409445822981693,
"loss": 1565.7465,
"step": 1320
},
{
"epoch": 0.265,
"grad_norm": 512.3551025390625,
"learning_rate": 0.000183905059331145,
"loss": 1560.9855,
"step": 1325
},
{
"epoch": 0.266,
"grad_norm": 429.489013671875,
"learning_rate": 0.000183714638075804,
"loss": 1536.7678,
"step": 1330
},
{
"epoch": 0.267,
"grad_norm": 505.0700988769531,
"learning_rate": 0.00018352319678401676,
"loss": 1556.9496,
"step": 1335
},
{
"epoch": 0.268,
"grad_norm": 323.2864685058594,
"learning_rate": 0.000183330737788435,
"loss": 1590.1255,
"step": 1340
},
{
"epoch": 0.269,
"grad_norm": 446.08038330078125,
"learning_rate": 0.00018313726343411086,
"loss": 1582.6836,
"step": 1345
},
{
"epoch": 0.27,
"grad_norm": 347.1296691894531,
"learning_rate": 0.00018294277607846832,
"loss": 1555.663,
"step": 1350
},
{
"epoch": 0.271,
"grad_norm": 298.9117126464844,
"learning_rate": 0.00018274727809127438,
"loss": 1567.8468,
"step": 1355
},
{
"epoch": 0.272,
"grad_norm": 355.4424133300781,
"learning_rate": 0.00018255077185461038,
"loss": 1511.3764,
"step": 1360
},
{
"epoch": 0.273,
"grad_norm": 397.7882080078125,
"learning_rate": 0.00018235325976284275,
"loss": 1527.3235,
"step": 1365
},
{
"epoch": 0.274,
"grad_norm": 347.29296875,
"learning_rate": 0.00018215474422259402,
"loss": 1467.4915,
"step": 1370
},
{
"epoch": 0.275,
"grad_norm": 323.222412109375,
"learning_rate": 0.0001819552276527134,
"loss": 1493.0916,
"step": 1375
},
{
"epoch": 0.276,
"grad_norm": 300.4835205078125,
"learning_rate": 0.0001817547124842473,
"loss": 1558.935,
"step": 1380
},
{
"epoch": 0.277,
"grad_norm": 527.3101196289062,
"learning_rate": 0.00018155320116040982,
"loss": 1593.7415,
"step": 1385
},
{
"epoch": 0.278,
"grad_norm": 279.7092590332031,
"learning_rate": 0.0001813506961365528,
"loss": 1587.2331,
"step": 1390
},
{
"epoch": 0.279,
"grad_norm": 377.8092041015625,
"learning_rate": 0.00018114719988013612,
"loss": 1493.7384,
"step": 1395
},
{
"epoch": 0.28,
"grad_norm": 335.34527587890625,
"learning_rate": 0.00018094271487069735,
"loss": 1534.8452,
"step": 1400
},
{
"epoch": 0.281,
"grad_norm": 439.6481628417969,
"learning_rate": 0.00018073724359982186,
"loss": 1557.8491,
"step": 1405
},
{
"epoch": 0.282,
"grad_norm": 501.93780517578125,
"learning_rate": 0.0001805307885711122,
"loss": 1561.8083,
"step": 1410
},
{
"epoch": 0.283,
"grad_norm": 374.47247314453125,
"learning_rate": 0.0001803233523001578,
"loss": 1480.9174,
"step": 1415
},
{
"epoch": 0.284,
"grad_norm": 309.0087890625,
"learning_rate": 0.00018011493731450413,
"loss": 1557.0936,
"step": 1420
},
{
"epoch": 0.285,
"grad_norm": 348.65203857421875,
"learning_rate": 0.00017990554615362198,
"loss": 1551.467,
"step": 1425
},
{
"epoch": 0.286,
"grad_norm": 315.370361328125,
"learning_rate": 0.00017969518136887663,
"loss": 1532.3428,
"step": 1430
},
{
"epoch": 0.287,
"grad_norm": 334.51080322265625,
"learning_rate": 0.00017948384552349657,
"loss": 1504.3698,
"step": 1435
},
{
"epoch": 0.288,
"grad_norm": 261.4054870605469,
"learning_rate": 0.00017927154119254236,
"loss": 1486.2069,
"step": 1440
},
{
"epoch": 0.289,
"grad_norm": 384.9761962890625,
"learning_rate": 0.0001790582709628753,
"loss": 1482.8846,
"step": 1445
},
{
"epoch": 0.29,
"grad_norm": 336.9621887207031,
"learning_rate": 0.00017884403743312582,
"loss": 1545.4182,
"step": 1450
},
{
"epoch": 0.291,
"grad_norm": 316.27764892578125,
"learning_rate": 0.00017862884321366188,
"loss": 1511.9294,
"step": 1455
},
{
"epoch": 0.292,
"grad_norm": 431.42108154296875,
"learning_rate": 0.00017841269092655715,
"loss": 1511.4192,
"step": 1460
},
{
"epoch": 0.293,
"grad_norm": 301.8031311035156,
"learning_rate": 0.000178195583205559,
"loss": 1472.3467,
"step": 1465
},
{
"epoch": 0.294,
"grad_norm": 272.3699645996094,
"learning_rate": 0.00017797752269605653,
"loss": 1432.9184,
"step": 1470
},
{
"epoch": 0.295,
"grad_norm": 310.1900634765625,
"learning_rate": 0.0001777585120550482,
"loss": 1478.1456,
"step": 1475
},
{
"epoch": 0.296,
"grad_norm": 289.23529052734375,
"learning_rate": 0.0001775385539511096,
"loss": 1434.7309,
"step": 1480
},
{
"epoch": 0.297,
"grad_norm": 322.4385986328125,
"learning_rate": 0.00017731765106436073,
"loss": 1433.886,
"step": 1485
},
{
"epoch": 0.298,
"grad_norm": 346.07879638671875,
"learning_rate": 0.00017709580608643363,
"loss": 1394.033,
"step": 1490
},
{
"epoch": 0.299,
"grad_norm": 295.3197021484375,
"learning_rate": 0.00017687302172043933,
"loss": 1427.0694,
"step": 1495
},
{
"epoch": 0.3,
"grad_norm": 318.86309814453125,
"learning_rate": 0.00017664930068093498,
"loss": 1487.126,
"step": 1500
},
{
"epoch": 0.301,
"grad_norm": 314.1716613769531,
"learning_rate": 0.0001764246456938909,
"loss": 1509.1698,
"step": 1505
},
{
"epoch": 0.302,
"grad_norm": 334.33587646484375,
"learning_rate": 0.0001761990594966572,
"loss": 1527.8225,
"step": 1510
},
{
"epoch": 0.303,
"grad_norm": 287.6945495605469,
"learning_rate": 0.00017597254483793048,
"loss": 1453.7525,
"step": 1515
},
{
"epoch": 0.304,
"grad_norm": 305.794677734375,
"learning_rate": 0.00017574510447772039,
"loss": 1477.4018,
"step": 1520
},
{
"epoch": 0.305,
"grad_norm": 362.19866943359375,
"learning_rate": 0.00017551674118731591,
"loss": 1501.1844,
"step": 1525
},
{
"epoch": 0.306,
"grad_norm": 359.1415100097656,
"learning_rate": 0.00017528745774925172,
"loss": 1543.3537,
"step": 1530
},
{
"epoch": 0.307,
"grad_norm": 319.7608642578125,
"learning_rate": 0.00017505725695727412,
"loss": 1496.5308,
"step": 1535
},
{
"epoch": 0.308,
"grad_norm": 330.65252685546875,
"learning_rate": 0.00017482614161630714,
"loss": 1460.9619,
"step": 1540
},
{
"epoch": 0.309,
"grad_norm": 299.6116638183594,
"learning_rate": 0.00017459411454241822,
"loss": 1561.6634,
"step": 1545
},
{
"epoch": 0.31,
"grad_norm": 289.3191833496094,
"learning_rate": 0.0001743611785627841,
"loss": 1519.8671,
"step": 1550
},
{
"epoch": 0.311,
"grad_norm": 368.9864196777344,
"learning_rate": 0.0001741273365156561,
"loss": 1491.5584,
"step": 1555
},
{
"epoch": 0.312,
"grad_norm": 321.2856140136719,
"learning_rate": 0.0001738925912503259,
"loss": 1489.0335,
"step": 1560
},
{
"epoch": 0.313,
"grad_norm": 1057.5482177734375,
"learning_rate": 0.00017365694562709034,
"loss": 1478.6297,
"step": 1565
},
{
"epoch": 0.314,
"grad_norm": 386.780029296875,
"learning_rate": 0.00017342040251721702,
"loss": 1534.6357,
"step": 1570
},
{
"epoch": 0.315,
"grad_norm": 337.16900634765625,
"learning_rate": 0.0001731829648029091,
"loss": 1517.4396,
"step": 1575
},
{
"epoch": 0.316,
"grad_norm": 406.7330322265625,
"learning_rate": 0.00017294463537727024,
"loss": 1470.857,
"step": 1580
},
{
"epoch": 0.317,
"grad_norm": 358.8523254394531,
"learning_rate": 0.0001727054171442692,
"loss": 1495.3683,
"step": 1585
},
{
"epoch": 0.318,
"grad_norm": 341.9473876953125,
"learning_rate": 0.0001724653130187047,
"loss": 1418.8222,
"step": 1590
},
{
"epoch": 0.319,
"grad_norm": 301.25958251953125,
"learning_rate": 0.0001722243259261697,
"loss": 1493.1056,
"step": 1595
},
{
"epoch": 0.32,
"grad_norm": 290.7584228515625,
"learning_rate": 0.0001719824588030159,
"loss": 1493.7634,
"step": 1600
},
{
"epoch": 0.321,
"grad_norm": 356.7821350097656,
"learning_rate": 0.00017173971459631787,
"loss": 1473.3163,
"step": 1605
},
{
"epoch": 0.322,
"grad_norm": 354.9071960449219,
"learning_rate": 0.00017149609626383717,
"loss": 1511.7058,
"step": 1610
},
{
"epoch": 0.323,
"grad_norm": 357.91632080078125,
"learning_rate": 0.00017125160677398626,
"loss": 1505.169,
"step": 1615
},
{
"epoch": 0.324,
"grad_norm": 388.84912109375,
"learning_rate": 0.0001710062491057925,
"loss": 1558.1594,
"step": 1620
},
{
"epoch": 0.325,
"grad_norm": 312.2912292480469,
"learning_rate": 0.00017076002624886154,
"loss": 1581.8037,
"step": 1625
},
{
"epoch": 0.326,
"grad_norm": 398.4658508300781,
"learning_rate": 0.00017051294120334125,
"loss": 1590.962,
"step": 1630
},
{
"epoch": 0.327,
"grad_norm": 268.677001953125,
"learning_rate": 0.00017026499697988493,
"loss": 1508.0789,
"step": 1635
},
{
"epoch": 0.328,
"grad_norm": 258.3197937011719,
"learning_rate": 0.00017001619659961467,
"loss": 1520.1296,
"step": 1640
},
{
"epoch": 0.329,
"grad_norm": 296.1904602050781,
"learning_rate": 0.00016976654309408464,
"loss": 1557.9673,
"step": 1645
},
{
"epoch": 0.33,
"grad_norm": 357.5792236328125,
"learning_rate": 0.000169516039505244,
"loss": 1546.0013,
"step": 1650
},
{
"epoch": 0.331,
"grad_norm": 280.5234375,
"learning_rate": 0.0001692646888853999,
"loss": 1532.0529,
"step": 1655
},
{
"epoch": 0.332,
"grad_norm": 308.712158203125,
"learning_rate": 0.00016901249429718032,
"loss": 1514.6807,
"step": 1660
},
{
"epoch": 0.333,
"grad_norm": 281.579833984375,
"learning_rate": 0.00016875945881349676,
"loss": 1529.6741,
"step": 1665
},
{
"epoch": 0.334,
"grad_norm": 291.5606994628906,
"learning_rate": 0.0001685055855175067,
"loss": 1494.1529,
"step": 1670
},
{
"epoch": 0.335,
"grad_norm": 238.4098663330078,
"learning_rate": 0.0001682508775025762,
"loss": 1578.589,
"step": 1675
},
{
"epoch": 0.336,
"grad_norm": 259.8029479980469,
"learning_rate": 0.00016799533787224192,
"loss": 1489.9505,
"step": 1680
},
{
"epoch": 0.337,
"grad_norm": 288.19384765625,
"learning_rate": 0.00016773896974017373,
"loss": 1475.2109,
"step": 1685
},
{
"epoch": 0.338,
"grad_norm": 820.6987915039062,
"learning_rate": 0.00016748177623013638,
"loss": 1559.9329,
"step": 1690
},
{
"epoch": 0.339,
"grad_norm": 266.0748596191406,
"learning_rate": 0.00016722376047595164,
"loss": 1465.6208,
"step": 1695
},
{
"epoch": 0.34,
"grad_norm": 258.5553283691406,
"learning_rate": 0.00016696492562145996,
"loss": 1481.4977,
"step": 1700
},
{
"epoch": 0.341,
"grad_norm": 304.99481201171875,
"learning_rate": 0.00016670527482048246,
"loss": 1575.8835,
"step": 1705
},
{
"epoch": 0.342,
"grad_norm": 285.0276184082031,
"learning_rate": 0.00016644481123678217,
"loss": 1460.693,
"step": 1710
},
{
"epoch": 0.343,
"grad_norm": 379.4126281738281,
"learning_rate": 0.00016618353804402568,
"loss": 1535.477,
"step": 1715
},
{
"epoch": 0.344,
"grad_norm": 232.01364135742188,
"learning_rate": 0.00016592145842574433,
"loss": 1513.8178,
"step": 1720
},
{
"epoch": 0.345,
"grad_norm": 268.1295471191406,
"learning_rate": 0.00016565857557529566,
"loss": 1513.1709,
"step": 1725
},
{
"epoch": 0.346,
"grad_norm": 272.30029296875,
"learning_rate": 0.00016539489269582416,
"loss": 1472.8502,
"step": 1730
},
{
"epoch": 0.347,
"grad_norm": 314.4810485839844,
"learning_rate": 0.00016513041300022255,
"loss": 1453.6019,
"step": 1735
},
{
"epoch": 0.348,
"grad_norm": 299.1487731933594,
"learning_rate": 0.00016486513971109243,
"loss": 1428.7026,
"step": 1740
},
{
"epoch": 0.349,
"grad_norm": 307.4020080566406,
"learning_rate": 0.0001645990760607051,
"loss": 1472.6029,
"step": 1745
},
{
"epoch": 0.35,
"grad_norm": 353.69049072265625,
"learning_rate": 0.0001643322252909622,
"loss": 1537.4584,
"step": 1750
},
{
"epoch": 0.351,
"grad_norm": 252.397216796875,
"learning_rate": 0.00016406459065335615,
"loss": 1494.4208,
"step": 1755
},
{
"epoch": 0.352,
"grad_norm": 357.94183349609375,
"learning_rate": 0.00016379617540893056,
"loss": 1481.1629,
"step": 1760
},
{
"epoch": 0.353,
"grad_norm": 367.845703125,
"learning_rate": 0.00016352698282824044,
"loss": 1464.2977,
"step": 1765
},
{
"epoch": 0.354,
"grad_norm": 266.83245849609375,
"learning_rate": 0.00016325701619131246,
"loss": 1500.2894,
"step": 1770
},
{
"epoch": 0.355,
"grad_norm": 258.43853759765625,
"learning_rate": 0.00016298627878760487,
"loss": 1436.3902,
"step": 1775
},
{
"epoch": 0.356,
"grad_norm": 303.6440734863281,
"learning_rate": 0.00016271477391596753,
"loss": 1451.7178,
"step": 1780
},
{
"epoch": 0.357,
"grad_norm": 323.26202392578125,
"learning_rate": 0.00016244250488460158,
"loss": 1554.7997,
"step": 1785
},
{
"epoch": 0.358,
"grad_norm": 312.61932373046875,
"learning_rate": 0.0001621694750110193,
"loss": 1462.4665,
"step": 1790
},
{
"epoch": 0.359,
"grad_norm": 391.6678466796875,
"learning_rate": 0.00016189568762200348,
"loss": 1523.6189,
"step": 1795
},
{
"epoch": 0.36,
"grad_norm": 639.271728515625,
"learning_rate": 0.00016162114605356703,
"loss": 1511.0107,
"step": 1800
},
{
"epoch": 0.361,
"grad_norm": 248.77041625976562,
"learning_rate": 0.00016134585365091243,
"loss": 1534.0523,
"step": 1805
},
{
"epoch": 0.362,
"grad_norm": 259.441162109375,
"learning_rate": 0.00016106981376839066,
"loss": 1439.3098,
"step": 1810
},
{
"epoch": 0.363,
"grad_norm": 397.7359619140625,
"learning_rate": 0.00016079302976946055,
"loss": 1462.7748,
"step": 1815
},
{
"epoch": 0.364,
"grad_norm": 707.6983642578125,
"learning_rate": 0.0001605155050266478,
"loss": 1464.4302,
"step": 1820
},
{
"epoch": 0.365,
"grad_norm": 631.993408203125,
"learning_rate": 0.00016023724292150385,
"loss": 1500.332,
"step": 1825
},
{
"epoch": 0.366,
"grad_norm": 245.61119079589844,
"learning_rate": 0.00015995824684456465,
"loss": 1445.0183,
"step": 1830
},
{
"epoch": 0.367,
"grad_norm": 251.85386657714844,
"learning_rate": 0.00015967852019530926,
"loss": 1433.5646,
"step": 1835
},
{
"epoch": 0.368,
"grad_norm": 290.6611022949219,
"learning_rate": 0.0001593980663821187,
"loss": 1448.081,
"step": 1840
},
{
"epoch": 0.369,
"grad_norm": 347.8661804199219,
"learning_rate": 0.0001591168888222342,
"loss": 1431.2149,
"step": 1845
},
{
"epoch": 0.37,
"grad_norm": 288.5362854003906,
"learning_rate": 0.00015883499094171554,
"loss": 1457.938,
"step": 1850
},
{
"epoch": 0.371,
"grad_norm": 313.3053894042969,
"learning_rate": 0.0001585523761753994,
"loss": 1590.2515,
"step": 1855
},
{
"epoch": 0.372,
"grad_norm": 229.26861572265625,
"learning_rate": 0.00015826904796685762,
"loss": 1447.6748,
"step": 1860
},
{
"epoch": 0.373,
"grad_norm": 422.7262268066406,
"learning_rate": 0.00015798500976835493,
"loss": 1481.6865,
"step": 1865
},
{
"epoch": 0.374,
"grad_norm": 406.8356018066406,
"learning_rate": 0.00015770026504080718,
"loss": 1436.4104,
"step": 1870
},
{
"epoch": 0.375,
"grad_norm": 323.3093566894531,
"learning_rate": 0.000157414817253739,
"loss": 1480.7864,
"step": 1875
},
{
"epoch": 0.376,
"grad_norm": 411.99993896484375,
"learning_rate": 0.00015712866988524155,
"loss": 1421.9411,
"step": 1880
},
{
"epoch": 0.377,
"grad_norm": 265.91119384765625,
"learning_rate": 0.0001568418264219303,
"loss": 1422.2998,
"step": 1885
},
{
"epoch": 0.378,
"grad_norm": 317.93109130859375,
"learning_rate": 0.0001565542903589023,
"loss": 1392.15,
"step": 1890
},
{
"epoch": 0.379,
"grad_norm": 535.3139038085938,
"learning_rate": 0.0001562660651996937,
"loss": 1436.6208,
"step": 1895
},
{
"epoch": 0.38,
"grad_norm": 336.3572998046875,
"learning_rate": 0.00015597715445623712,
"loss": 1434.3992,
"step": 1900
},
{
"epoch": 0.381,
"grad_norm": 240.66677856445312,
"learning_rate": 0.00015568756164881882,
"loss": 1469.998,
"step": 1905
},
{
"epoch": 0.382,
"grad_norm": 398.14678955078125,
"learning_rate": 0.00015539729030603574,
"loss": 1436.2607,
"step": 1910
},
{
"epoch": 0.383,
"grad_norm": 308.904296875,
"learning_rate": 0.0001551063439647526,
"loss": 1432.353,
"step": 1915
},
{
"epoch": 0.384,
"grad_norm": 268.0305480957031,
"learning_rate": 0.00015481472617005876,
"loss": 1416.4469,
"step": 1920
},
{
"epoch": 0.385,
"grad_norm": 290.0729064941406,
"learning_rate": 0.00015452244047522502,
"loss": 1432.3045,
"step": 1925
},
{
"epoch": 0.386,
"grad_norm": 408.9584045410156,
"learning_rate": 0.0001542294904416603,
"loss": 1447.2331,
"step": 1930
},
{
"epoch": 0.387,
"grad_norm": 314.1492614746094,
"learning_rate": 0.00015393587963886835,
"loss": 1434.1525,
"step": 1935
},
{
"epoch": 0.388,
"grad_norm": 261.0567321777344,
"learning_rate": 0.0001536416116444041,
"loss": 1427.5081,
"step": 1940
},
{
"epoch": 0.389,
"grad_norm": 324.7414855957031,
"learning_rate": 0.0001533466900438303,
"loss": 1434.3611,
"step": 1945
},
{
"epoch": 0.39,
"grad_norm": 246.6747589111328,
"learning_rate": 0.0001530511184306734,
"loss": 1454.9498,
"step": 1950
},
{
"epoch": 0.391,
"grad_norm": 401.06304931640625,
"learning_rate": 0.00015275490040638038,
"loss": 1439.9566,
"step": 1955
},
{
"epoch": 0.392,
"grad_norm": 349.8895568847656,
"learning_rate": 0.00015245803958027434,
"loss": 1405.956,
"step": 1960
},
{
"epoch": 0.393,
"grad_norm": 313.7919921875,
"learning_rate": 0.0001521605395695108,
"loss": 1420.6883,
"step": 1965
},
{
"epoch": 0.394,
"grad_norm": 438.8692932128906,
"learning_rate": 0.00015186240399903342,
"loss": 1524.2902,
"step": 1970
},
{
"epoch": 0.395,
"grad_norm": 253.5648193359375,
"learning_rate": 0.00015156363650153012,
"loss": 1488.5444,
"step": 1975
},
{
"epoch": 0.396,
"grad_norm": 239.78768920898438,
"learning_rate": 0.0001512642407173885,
"loss": 1439.3692,
"step": 1980
},
{
"epoch": 0.397,
"grad_norm": 283.5133361816406,
"learning_rate": 0.00015096422029465178,
"loss": 1427.4454,
"step": 1985
},
{
"epoch": 0.398,
"grad_norm": 340.5876770019531,
"learning_rate": 0.0001506635788889741,
"loss": 1475.4712,
"step": 1990
},
{
"epoch": 0.399,
"grad_norm": 285.7615966796875,
"learning_rate": 0.0001503623201635761,
"loss": 1405.0807,
"step": 1995
},
{
"epoch": 0.4,
"grad_norm": 318.30450439453125,
"learning_rate": 0.0001500604477892003,
"loss": 1424.8064,
"step": 2000
},
{
"epoch": 0.401,
"grad_norm": 315.82293701171875,
"learning_rate": 0.00014975796544406625,
"loss": 1428.5253,
"step": 2005
},
{
"epoch": 0.402,
"grad_norm": 272.7846984863281,
"learning_rate": 0.00014945487681382598,
"loss": 1418.0566,
"step": 2010
},
{
"epoch": 0.403,
"grad_norm": 244.93446350097656,
"learning_rate": 0.0001491511855915187,
"loss": 1412.541,
"step": 2015
},
{
"epoch": 0.404,
"grad_norm": 303.28692626953125,
"learning_rate": 0.0001488468954775262,
"loss": 1443.0754,
"step": 2020
},
{
"epoch": 0.405,
"grad_norm": 348.1090087890625,
"learning_rate": 0.0001485420101795274,
"loss": 1415.3831,
"step": 2025
},
{
"epoch": 0.406,
"grad_norm": 268.109375,
"learning_rate": 0.00014823653341245353,
"loss": 1433.1892,
"step": 2030
},
{
"epoch": 0.407,
"grad_norm": 297.5362243652344,
"learning_rate": 0.0001479304688984425,
"loss": 1427.0258,
"step": 2035
},
{
"epoch": 0.408,
"grad_norm": 277.9589538574219,
"learning_rate": 0.0001476238203667939,
"loss": 1431.6777,
"step": 2040
},
{
"epoch": 0.409,
"grad_norm": 257.7864074707031,
"learning_rate": 0.00014731659155392332,
"loss": 1402.0762,
"step": 2045
},
{
"epoch": 0.41,
"grad_norm": 295.5390625,
"learning_rate": 0.00014700878620331684,
"loss": 1421.3163,
"step": 2050
},
{
"epoch": 0.411,
"grad_norm": 249.41329956054688,
"learning_rate": 0.00014670040806548555,
"loss": 1409.8797,
"step": 2055
},
{
"epoch": 0.412,
"grad_norm": 265.3221740722656,
"learning_rate": 0.0001463914608979197,
"loss": 1366.6104,
"step": 2060
},
{
"epoch": 0.413,
"grad_norm": 283.0120544433594,
"learning_rate": 0.0001460819484650431,
"loss": 1405.7507,
"step": 2065
},
{
"epoch": 0.414,
"grad_norm": 292.8707275390625,
"learning_rate": 0.000145771874538167,
"loss": 1443.2951,
"step": 2070
},
{
"epoch": 0.415,
"grad_norm": 307.2060241699219,
"learning_rate": 0.0001454612428954444,
"loss": 1434.6252,
"step": 2075
},
{
"epoch": 0.416,
"grad_norm": 283.6821594238281,
"learning_rate": 0.00014515005732182383,
"loss": 1429.7807,
"step": 2080
},
{
"epoch": 0.417,
"grad_norm": 246.47007751464844,
"learning_rate": 0.00014483832160900326,
"loss": 1427.9858,
"step": 2085
},
{
"epoch": 0.418,
"grad_norm": 257.2790222167969,
"learning_rate": 0.00014452603955538397,
"loss": 1404.0112,
"step": 2090
},
{
"epoch": 0.419,
"grad_norm": 234.81748962402344,
"learning_rate": 0.00014421321496602428,
"loss": 1368.2209,
"step": 2095
},
{
"epoch": 0.42,
"grad_norm": 359.444091796875,
"learning_rate": 0.00014389985165259308,
"loss": 1426.0274,
"step": 2100
},
{
"epoch": 0.421,
"grad_norm": 274.1839904785156,
"learning_rate": 0.00014358595343332342,
"loss": 1412.1633,
"step": 2105
},
{
"epoch": 0.422,
"grad_norm": 340.42816162109375,
"learning_rate": 0.00014327152413296608,
"loss": 1395.9547,
"step": 2110
},
{
"epoch": 0.423,
"grad_norm": 245.00772094726562,
"learning_rate": 0.00014295656758274284,
"loss": 1395.4584,
"step": 2115
},
{
"epoch": 0.424,
"grad_norm": 250.99899291992188,
"learning_rate": 0.0001426410876202999,
"loss": 1418.859,
"step": 2120
},
{
"epoch": 0.425,
"grad_norm": 269.6187744140625,
"learning_rate": 0.00014232508808966098,
"loss": 1416.975,
"step": 2125
},
{
"epoch": 0.426,
"grad_norm": 321.69964599609375,
"learning_rate": 0.00014200857284118066,
"loss": 1468.6527,
"step": 2130
},
{
"epoch": 0.427,
"grad_norm": 424.7634582519531,
"learning_rate": 0.00014169154573149737,
"loss": 1401.973,
"step": 2135
},
{
"epoch": 0.428,
"grad_norm": 237.03012084960938,
"learning_rate": 0.00014137401062348638,
"loss": 1406.0178,
"step": 2140
},
{
"epoch": 0.429,
"grad_norm": 309.3263244628906,
"learning_rate": 0.0001410559713862128,
"loss": 1387.1151,
"step": 2145
},
{
"epoch": 0.43,
"grad_norm": 262.7537536621094,
"learning_rate": 0.00014073743189488435,
"loss": 1419.1463,
"step": 2150
},
{
"epoch": 0.431,
"grad_norm": 243.84014892578125,
"learning_rate": 0.00014041839603080422,
"loss": 1391.175,
"step": 2155
},
{
"epoch": 0.432,
"grad_norm": 367.34814453125,
"learning_rate": 0.00014009886768132375,
"loss": 1411.4178,
"step": 2160
},
{
"epoch": 0.433,
"grad_norm": 262.67791748046875,
"learning_rate": 0.000139778850739795,
"loss": 1397.9669,
"step": 2165
},
{
"epoch": 0.434,
"grad_norm": 240.74307250976562,
"learning_rate": 0.0001394583491055234,
"loss": 1375.1194,
"step": 2170
},
{
"epoch": 0.435,
"grad_norm": 269.6568603515625,
"learning_rate": 0.00013913736668372026,
"loss": 1410.7743,
"step": 2175
},
{
"epoch": 0.436,
"grad_norm": 231.243896484375,
"learning_rate": 0.00013881590738545508,
"loss": 1359.1831,
"step": 2180
},
{
"epoch": 0.437,
"grad_norm": 306.330078125,
"learning_rate": 0.00013849397512760795,
"loss": 1398.267,
"step": 2185
},
{
"epoch": 0.438,
"grad_norm": 423.2845458984375,
"learning_rate": 0.00013817157383282184,
"loss": 1336.2269,
"step": 2190
},
{
"epoch": 0.439,
"grad_norm": 259.2425537109375,
"learning_rate": 0.00013784870742945482,
"loss": 1404.7994,
"step": 2195
},
{
"epoch": 0.44,
"grad_norm": 274.7835693359375,
"learning_rate": 0.0001375253798515321,
"loss": 1344.7232,
"step": 2200
},
{
"epoch": 0.441,
"grad_norm": 252.34133911132812,
"learning_rate": 0.00013720159503869815,
"loss": 1374.9285,
"step": 2205
},
{
"epoch": 0.442,
"grad_norm": 247.49398803710938,
"learning_rate": 0.00013687735693616876,
"loss": 1384.578,
"step": 2210
},
{
"epoch": 0.443,
"grad_norm": 291.9062194824219,
"learning_rate": 0.0001365526694946829,
"loss": 1452.1499,
"step": 2215
},
{
"epoch": 0.444,
"grad_norm": 309.0041198730469,
"learning_rate": 0.00013622753667045457,
"loss": 1391.6157,
"step": 2220
},
{
"epoch": 0.445,
"grad_norm": 309.00482177734375,
"learning_rate": 0.00013590196242512463,
"loss": 1367.9757,
"step": 2225
},
{
"epoch": 0.446,
"grad_norm": 289.17724609375,
"learning_rate": 0.0001355759507257125,
"loss": 1372.8035,
"step": 2230
},
{
"epoch": 0.447,
"grad_norm": 302.4632263183594,
"learning_rate": 0.00013524950554456784,
"loss": 1379.2575,
"step": 2235
},
{
"epoch": 0.448,
"grad_norm": 294.2777099609375,
"learning_rate": 0.00013492263085932224,
"loss": 1371.4715,
"step": 2240
},
{
"epoch": 0.449,
"grad_norm": 272.22589111328125,
"learning_rate": 0.0001345953306528405,
"loss": 1389.8592,
"step": 2245
},
{
"epoch": 0.45,
"grad_norm": 611.509765625,
"learning_rate": 0.00013426760891317236,
"loss": 1439.2106,
"step": 2250
},
{
"epoch": 0.451,
"grad_norm": 322.945556640625,
"learning_rate": 0.00013393946963350382,
"loss": 1387.5879,
"step": 2255
},
{
"epoch": 0.452,
"grad_norm": 278.8100280761719,
"learning_rate": 0.00013361091681210845,
"loss": 1371.5867,
"step": 2260
},
{
"epoch": 0.453,
"grad_norm": 265.065673828125,
"learning_rate": 0.00013328195445229868,
"loss": 1369.7708,
"step": 2265
},
{
"epoch": 0.454,
"grad_norm": 263.76409912109375,
"learning_rate": 0.00013295258656237702,
"loss": 1385.7157,
"step": 2270
},
{
"epoch": 0.455,
"grad_norm": 233.55699157714844,
"learning_rate": 0.00013262281715558736,
"loss": 1400.3553,
"step": 2275
},
{
"epoch": 0.456,
"grad_norm": 230.30047607421875,
"learning_rate": 0.00013229265025006576,
"loss": 1438.5815,
"step": 2280
},
{
"epoch": 0.457,
"grad_norm": 328.4666442871094,
"learning_rate": 0.0001319620898687918,
"loss": 1377.5845,
"step": 2285
},
{
"epoch": 0.458,
"grad_norm": 248.78076171875,
"learning_rate": 0.0001316311400395394,
"loss": 1347.0407,
"step": 2290
},
{
"epoch": 0.459,
"grad_norm": 302.1549987792969,
"learning_rate": 0.00013129980479482782,
"loss": 1394.7351,
"step": 2295
},
{
"epoch": 0.46,
"grad_norm": 301.294921875,
"learning_rate": 0.00013096808817187242,
"loss": 1350.3959,
"step": 2300
},
{
"epoch": 0.461,
"grad_norm": 271.3141784667969,
"learning_rate": 0.00013063599421253558,
"loss": 1387.9567,
"step": 2305
},
{
"epoch": 0.462,
"grad_norm": 309.3506164550781,
"learning_rate": 0.00013030352696327742,
"loss": 1374.4325,
"step": 2310
},
{
"epoch": 0.463,
"grad_norm": 261.0451965332031,
"learning_rate": 0.0001299706904751064,
"loss": 1387.2097,
"step": 2315
},
{
"epoch": 0.464,
"grad_norm": 254.21702575683594,
"learning_rate": 0.00012963748880353011,
"loss": 1387.6664,
"step": 2320
},
{
"epoch": 0.465,
"grad_norm": 299.75799560546875,
"learning_rate": 0.00012930392600850573,
"loss": 1410.417,
"step": 2325
},
{
"epoch": 0.466,
"grad_norm": 283.8753967285156,
"learning_rate": 0.00012897000615439075,
"loss": 1364.755,
"step": 2330
},
{
"epoch": 0.467,
"grad_norm": 242.93115234375,
"learning_rate": 0.00012863573330989313,
"loss": 1377.8827,
"step": 2335
},
{
"epoch": 0.468,
"grad_norm": 484.2723083496094,
"learning_rate": 0.00012830111154802203,
"loss": 1630.8855,
"step": 2340
},
{
"epoch": 0.469,
"grad_norm": 329.9387512207031,
"learning_rate": 0.000127966144946038,
"loss": 1380.5309,
"step": 2345
},
{
"epoch": 0.47,
"grad_norm": 277.8216247558594,
"learning_rate": 0.00012763083758540337,
"loss": 1387.0185,
"step": 2350
},
{
"epoch": 0.471,
"grad_norm": 308.7984924316406,
"learning_rate": 0.00012729519355173254,
"loss": 1388.2554,
"step": 2355
},
{
"epoch": 0.472,
"grad_norm": 294.68365478515625,
"learning_rate": 0.00012695921693474212,
"loss": 1416.0645,
"step": 2360
},
{
"epoch": 0.473,
"grad_norm": 287.7560729980469,
"learning_rate": 0.00012662291182820114,
"loss": 1358.1361,
"step": 2365
},
{
"epoch": 0.474,
"grad_norm": 553.662109375,
"learning_rate": 0.0001262862823298812,
"loss": 1466.3041,
"step": 2370
},
{
"epoch": 0.475,
"grad_norm": 321.2275390625,
"learning_rate": 0.00012594933254150655,
"loss": 1460.7632,
"step": 2375
},
{
"epoch": 0.476,
"grad_norm": 338.652099609375,
"learning_rate": 0.00012561206656870396,
"loss": 1379.4611,
"step": 2380
},
{
"epoch": 0.477,
"grad_norm": 283.2237548828125,
"learning_rate": 0.00012527448852095295,
"loss": 1405.0285,
"step": 2385
},
{
"epoch": 0.478,
"grad_norm": 349.830078125,
"learning_rate": 0.0001249366025115354,
"loss": 1395.5649,
"step": 2390
},
{
"epoch": 0.479,
"grad_norm": 293.798583984375,
"learning_rate": 0.0001245984126574858,
"loss": 1378.1871,
"step": 2395
},
{
"epoch": 0.48,
"grad_norm": 388.56280517578125,
"learning_rate": 0.00012425992307954075,
"loss": 1361.9743,
"step": 2400
},
{
"epoch": 0.481,
"grad_norm": 264.3885192871094,
"learning_rate": 0.00012392113790208895,
"loss": 1542.8669,
"step": 2405
},
{
"epoch": 0.482,
"grad_norm": 260.3326721191406,
"learning_rate": 0.00012358206125312083,
"loss": 1323.2955,
"step": 2410
},
{
"epoch": 0.483,
"grad_norm": 421.1486511230469,
"learning_rate": 0.0001232426972641784,
"loss": 1381.6287,
"step": 2415
},
{
"epoch": 0.484,
"grad_norm": 285.879638671875,
"learning_rate": 0.00012290305007030478,
"loss": 1374.0941,
"step": 2420
},
{
"epoch": 0.485,
"grad_norm": 389.511474609375,
"learning_rate": 0.00012256312380999376,
"loss": 1384.7048,
"step": 2425
},
{
"epoch": 0.486,
"grad_norm": 260.9061279296875,
"learning_rate": 0.00012222292262513965,
"loss": 1356.9418,
"step": 2430
},
{
"epoch": 0.487,
"grad_norm": 295.1590881347656,
"learning_rate": 0.00012188245066098647,
"loss": 1331.9424,
"step": 2435
},
{
"epoch": 0.488,
"grad_norm": 326.0806884765625,
"learning_rate": 0.00012154171206607764,
"loss": 1352.8967,
"step": 2440
},
{
"epoch": 0.489,
"grad_norm": 245.17294311523438,
"learning_rate": 0.00012120071099220549,
"loss": 1349.254,
"step": 2445
},
{
"epoch": 0.49,
"grad_norm": 273.85931396484375,
"learning_rate": 0.00012085945159436038,
"loss": 1364.5745,
"step": 2450
},
{
"epoch": 0.491,
"grad_norm": 273.1905822753906,
"learning_rate": 0.00012051793803068046,
"loss": 1341.8094,
"step": 2455
},
{
"epoch": 0.492,
"grad_norm": 231.4274444580078,
"learning_rate": 0.0001201761744624007,
"loss": 1459.3311,
"step": 2460
},
{
"epoch": 0.493,
"grad_norm": 305.7416076660156,
"learning_rate": 0.00011983416505380234,
"loss": 1406.7941,
"step": 2465
},
{
"epoch": 0.494,
"grad_norm": 273.35113525390625,
"learning_rate": 0.00011949191397216206,
"loss": 1370.8031,
"step": 2470
},
{
"epoch": 0.495,
"grad_norm": 244.70884704589844,
"learning_rate": 0.00011914942538770131,
"loss": 1342.7066,
"step": 2475
},
{
"epoch": 0.496,
"grad_norm": 254.96353149414062,
"learning_rate": 0.00011880670347353539,
"loss": 1345.2316,
"step": 2480
},
{
"epoch": 0.497,
"grad_norm": 264.1344909667969,
"learning_rate": 0.0001184637524056227,
"loss": 1489.4447,
"step": 2485
},
{
"epoch": 0.498,
"grad_norm": 277.9652099609375,
"learning_rate": 0.00011812057636271374,
"loss": 1359.3355,
"step": 2490
},
{
"epoch": 0.499,
"grad_norm": 309.2872314453125,
"learning_rate": 0.00011777717952630031,
"loss": 1352.334,
"step": 2495
},
{
"epoch": 0.5,
"grad_norm": 260.66253662109375,
"learning_rate": 0.00011743356608056449,
"loss": 1368.4162,
"step": 2500
},
{
"epoch": 0.501,
"grad_norm": 360.15045166015625,
"learning_rate": 0.00011708974021232769,
"loss": 1371.7344,
"step": 2505
},
{
"epoch": 0.502,
"grad_norm": 321.1947937011719,
"learning_rate": 0.00011674570611099955,
"loss": 1375.4278,
"step": 2510
},
{
"epoch": 0.503,
"grad_norm": 366.26287841796875,
"learning_rate": 0.00011640146796852711,
"loss": 1369.9809,
"step": 2515
},
{
"epoch": 0.504,
"grad_norm": 328.142333984375,
"learning_rate": 0.00011605702997934345,
"loss": 1411.5463,
"step": 2520
},
{
"epoch": 0.505,
"grad_norm": 301.1791687011719,
"learning_rate": 0.00011571239634031679,
"loss": 1386.2127,
"step": 2525
},
{
"epoch": 0.506,
"grad_norm": 289.2198791503906,
"learning_rate": 0.00011536757125069923,
"loss": 1335.1715,
"step": 2530
},
{
"epoch": 0.507,
"grad_norm": 321.41168212890625,
"learning_rate": 0.00011502255891207572,
"loss": 1372.8841,
"step": 2535
},
{
"epoch": 0.508,
"grad_norm": 233.05947875976562,
"learning_rate": 0.00011467736352831266,
"loss": 1362.002,
"step": 2540
},
{
"epoch": 0.509,
"grad_norm": 313.7733459472656,
"learning_rate": 0.00011433198930550695,
"loss": 1345.5781,
"step": 2545
},
{
"epoch": 0.51,
"grad_norm": 257.8642272949219,
"learning_rate": 0.00011398644045193444,
"loss": 1348.0139,
"step": 2550
},
{
"epoch": 0.511,
"grad_norm": 268.5954895019531,
"learning_rate": 0.00011364072117799885,
"loss": 1356.0134,
"step": 2555
},
{
"epoch": 0.512,
"grad_norm": 276.7738952636719,
"learning_rate": 0.00011329483569618045,
"loss": 1305.1,
"step": 2560
},
{
"epoch": 0.513,
"grad_norm": 294.1953125,
"learning_rate": 0.00011294878822098469,
"loss": 1351.8869,
"step": 2565
},
{
"epoch": 0.514,
"grad_norm": 636.6434936523438,
"learning_rate": 0.00011260258296889086,
"loss": 1318.7723,
"step": 2570
},
{
"epoch": 0.515,
"grad_norm": 1318.931396484375,
"learning_rate": 0.00011225622415830068,
"loss": 1435.0399,
"step": 2575
},
{
"epoch": 0.516,
"grad_norm": 235.9900665283203,
"learning_rate": 0.00011190971600948699,
"loss": 1323.2521,
"step": 2580
},
{
"epoch": 0.517,
"grad_norm": 251.1705780029297,
"learning_rate": 0.00011156306274454218,
"loss": 1342.8834,
"step": 2585
},
{
"epoch": 0.518,
"grad_norm": 277.85858154296875,
"learning_rate": 0.0001112162685873269,
"loss": 1347.3779,
"step": 2590
},
{
"epoch": 0.519,
"grad_norm": 260.86358642578125,
"learning_rate": 0.00011086933776341852,
"loss": 1314.1563,
"step": 2595
},
{
"epoch": 0.52,
"grad_norm": 248.18017578125,
"learning_rate": 0.00011052227450005967,
"loss": 1302.3666,
"step": 2600
},
{
"epoch": 0.521,
"grad_norm": 241.2575225830078,
"learning_rate": 0.00011017508302610664,
"loss": 1320.4064,
"step": 2605
},
{
"epoch": 0.522,
"grad_norm": 247.57205200195312,
"learning_rate": 0.00010982776757197799,
"loss": 1412.0438,
"step": 2610
},
{
"epoch": 0.523,
"grad_norm": 408.563720703125,
"learning_rate": 0.00010948033236960294,
"loss": 1341.5176,
"step": 2615
},
{
"epoch": 0.524,
"grad_norm": 345.8548583984375,
"learning_rate": 0.00010913278165236978,
"loss": 1316.2202,
"step": 2620
},
{
"epoch": 0.525,
"grad_norm": 341.7524719238281,
"learning_rate": 0.00010878511965507434,
"loss": 1381.1137,
"step": 2625
},
{
"epoch": 0.526,
"grad_norm": 308.1810302734375,
"learning_rate": 0.00010843735061386828,
"loss": 1347.2566,
"step": 2630
},
{
"epoch": 0.527,
"grad_norm": 267.44549560546875,
"learning_rate": 0.00010808947876620767,
"loss": 1345.8852,
"step": 2635
},
{
"epoch": 0.528,
"grad_norm": 282.438720703125,
"learning_rate": 0.00010774150835080119,
"loss": 1391.3448,
"step": 2640
},
{
"epoch": 0.529,
"grad_norm": 294.7178955078125,
"learning_rate": 0.00010739344360755852,
"loss": 1350.3508,
"step": 2645
},
{
"epoch": 0.53,
"grad_norm": 242.7730712890625,
"learning_rate": 0.0001070452887775387,
"loss": 1348.7876,
"step": 2650
},
{
"epoch": 0.531,
"grad_norm": 310.2391357421875,
"learning_rate": 0.00010669704810289851,
"loss": 1415.1726,
"step": 2655
},
{
"epoch": 0.532,
"grad_norm": 794.92529296875,
"learning_rate": 0.00010634872582684061,
"loss": 1349.9646,
"step": 2660
},
{
"epoch": 0.533,
"grad_norm": 274.75848388671875,
"learning_rate": 0.00010600032619356209,
"loss": 1386.0256,
"step": 2665
},
{
"epoch": 0.534,
"grad_norm": 231.7100372314453,
"learning_rate": 0.00010565185344820247,
"loss": 1326.0863,
"step": 2670
},
{
"epoch": 0.535,
"grad_norm": 246.2277374267578,
"learning_rate": 0.00010530331183679218,
"loss": 1321.1257,
"step": 2675
},
{
"epoch": 0.536,
"grad_norm": 291.01385498046875,
"learning_rate": 0.00010495470560620083,
"loss": 1352.0442,
"step": 2680
},
{
"epoch": 0.537,
"grad_norm": 256.653564453125,
"learning_rate": 0.00010460603900408523,
"loss": 1323.9802,
"step": 2685
},
{
"epoch": 0.538,
"grad_norm": 272.612548828125,
"learning_rate": 0.00010425731627883797,
"loss": 1361.8487,
"step": 2690
},
{
"epoch": 0.539,
"grad_norm": 224.1992950439453,
"learning_rate": 0.00010390854167953537,
"loss": 1358.5256,
"step": 2695
},
{
"epoch": 0.54,
"grad_norm": 403.5385437011719,
"learning_rate": 0.00010355971945588585,
"loss": 1361.6113,
"step": 2700
},
{
"epoch": 0.541,
"grad_norm": 264.61029052734375,
"learning_rate": 0.00010321085385817817,
"loss": 1334.0704,
"step": 2705
},
{
"epoch": 0.542,
"grad_norm": 287.67291259765625,
"learning_rate": 0.00010286194913722948,
"loss": 1311.8278,
"step": 2710
},
{
"epoch": 0.543,
"grad_norm": 235.52584838867188,
"learning_rate": 0.00010251300954433376,
"loss": 1322.6191,
"step": 2715
},
{
"epoch": 0.544,
"grad_norm": 238.90267944335938,
"learning_rate": 0.00010216403933120979,
"loss": 1335.7116,
"step": 2720
},
{
"epoch": 0.545,
"grad_norm": 290.0345153808594,
"learning_rate": 0.00010181504274994948,
"loss": 1338.3769,
"step": 2725
},
{
"epoch": 0.546,
"grad_norm": 264.44818115234375,
"learning_rate": 0.00010146602405296607,
"loss": 1353.3686,
"step": 2730
},
{
"epoch": 0.547,
"grad_norm": 280.40667724609375,
"learning_rate": 0.00010111698749294223,
"loss": 1345.9088,
"step": 2735
},
{
"epoch": 0.548,
"grad_norm": 260.65740966796875,
"learning_rate": 0.00010076793732277829,
"loss": 1311.9045,
"step": 2740
},
{
"epoch": 0.549,
"grad_norm": 250.76678466796875,
"learning_rate": 0.0001004188777955404,
"loss": 1278.0279,
"step": 2745
},
{
"epoch": 0.55,
"grad_norm": 212.83750915527344,
"learning_rate": 0.00010006981316440875,
"loss": 1293.0671,
"step": 2750
},
{
"epoch": 0.551,
"grad_norm": 226.5438232421875,
"learning_rate": 9.972074768262576e-05,
"loss": 1295.8313,
"step": 2755
},
{
"epoch": 0.552,
"grad_norm": 224.22412109375,
"learning_rate": 9.937168560344412e-05,
"loss": 1294.6375,
"step": 2760
},
{
"epoch": 0.553,
"grad_norm": 325.15081787109375,
"learning_rate": 9.902263118007513e-05,
"loss": 1340.774,
"step": 2765
},
{
"epoch": 0.554,
"grad_norm": 242.34141540527344,
"learning_rate": 9.867358866563673e-05,
"loss": 1322.9476,
"step": 2770
},
{
"epoch": 0.555,
"grad_norm": 267.2673645019531,
"learning_rate": 9.832456231310189e-05,
"loss": 1361.4934,
"step": 2775
},
{
"epoch": 0.556,
"grad_norm": 247.887939453125,
"learning_rate": 9.797555637524649e-05,
"loss": 1346.7934,
"step": 2780
},
{
"epoch": 0.557,
"grad_norm": 261.70501708984375,
"learning_rate": 9.762657510459783e-05,
"loss": 1391.8466,
"step": 2785
},
{
"epoch": 0.558,
"grad_norm": 255.74456787109375,
"learning_rate": 9.727762275338246e-05,
"loss": 1294.8977,
"step": 2790
},
{
"epoch": 0.559,
"grad_norm": 834.498291015625,
"learning_rate": 9.692870357347473e-05,
"loss": 1274.6477,
"step": 2795
},
{
"epoch": 0.56,
"grad_norm": 281.3625793457031,
"learning_rate": 9.657982181634475e-05,
"loss": 1384.5984,
"step": 2800
},
{
"epoch": 0.561,
"grad_norm": 218.0636444091797,
"learning_rate": 9.623098173300654e-05,
"loss": 1327.4049,
"step": 2805
},
{
"epoch": 0.562,
"grad_norm": 251.52679443359375,
"learning_rate": 9.588218757396655e-05,
"loss": 1325.4081,
"step": 2810
},
{
"epoch": 0.563,
"grad_norm": 255.21902465820312,
"learning_rate": 9.55334435891714e-05,
"loss": 1309.528,
"step": 2815
},
{
"epoch": 0.564,
"grad_norm": 359.7253723144531,
"learning_rate": 9.518475402795661e-05,
"loss": 1389.2806,
"step": 2820
},
{
"epoch": 0.565,
"grad_norm": 278.9259033203125,
"learning_rate": 9.483612313899435e-05,
"loss": 1342.4894,
"step": 2825
},
{
"epoch": 0.566,
"grad_norm": 283.5463562011719,
"learning_rate": 9.448755517024206e-05,
"loss": 1340.6566,
"step": 2830
},
{
"epoch": 0.567,
"grad_norm": 237.6826629638672,
"learning_rate": 9.413905436889035e-05,
"loss": 1345.2654,
"step": 2835
},
{
"epoch": 0.568,
"grad_norm": 226.28175354003906,
"learning_rate": 9.37906249813116e-05,
"loss": 1315.0161,
"step": 2840
},
{
"epoch": 0.569,
"grad_norm": 309.6024169921875,
"learning_rate": 9.344227125300788e-05,
"loss": 1345.7384,
"step": 2845
},
{
"epoch": 0.57,
"grad_norm": 242.26414489746094,
"learning_rate": 9.309399742855942e-05,
"loss": 1329.2398,
"step": 2850
},
{
"epoch": 0.571,
"grad_norm": 272.2978210449219,
"learning_rate": 9.274580775157294e-05,
"loss": 1287.7483,
"step": 2855
},
{
"epoch": 0.572,
"grad_norm": 282.52642822265625,
"learning_rate": 9.239770646462968e-05,
"loss": 1290.7809,
"step": 2860
},
{
"epoch": 0.573,
"grad_norm": 333.8104553222656,
"learning_rate": 9.204969780923403e-05,
"loss": 1309.6762,
"step": 2865
},
{
"epoch": 0.574,
"grad_norm": 230.75772094726562,
"learning_rate": 9.17017860257616e-05,
"loss": 1305.9682,
"step": 2870
},
{
"epoch": 0.575,
"grad_norm": 265.77911376953125,
"learning_rate": 9.135397535340773e-05,
"loss": 1335.8804,
"step": 2875
},
{
"epoch": 0.576,
"grad_norm": 372.9284973144531,
"learning_rate": 9.100627003013562e-05,
"loss": 1311.8564,
"step": 2880
},
{
"epoch": 0.577,
"grad_norm": 336.9934997558594,
"learning_rate": 9.065867429262496e-05,
"loss": 1330.9292,
"step": 2885
},
{
"epoch": 0.578,
"grad_norm": 242.35894775390625,
"learning_rate": 9.03111923762201e-05,
"loss": 1325.7193,
"step": 2890
},
{
"epoch": 0.579,
"grad_norm": 268.2100830078125,
"learning_rate": 8.99638285148785e-05,
"loss": 1336.7386,
"step": 2895
},
{
"epoch": 0.58,
"grad_norm": 253.7952117919922,
"learning_rate": 8.961658694111929e-05,
"loss": 1347.156,
"step": 2900
},
{
"epoch": 0.581,
"grad_norm": 307.61810302734375,
"learning_rate": 8.926947188597134e-05,
"loss": 1300.8784,
"step": 2905
},
{
"epoch": 0.582,
"grad_norm": 236.55508422851562,
"learning_rate": 8.892248757892214e-05,
"loss": 1302.8757,
"step": 2910
},
{
"epoch": 0.583,
"grad_norm": 274.8486328125,
"learning_rate": 8.857563824786596e-05,
"loss": 1326.8547,
"step": 2915
},
{
"epoch": 0.584,
"grad_norm": 252.6243896484375,
"learning_rate": 8.822892811905237e-05,
"loss": 1295.911,
"step": 2920
},
{
"epoch": 0.585,
"grad_norm": 299.3502197265625,
"learning_rate": 8.788236141703498e-05,
"loss": 1336.3136,
"step": 2925
},
{
"epoch": 0.586,
"grad_norm": 907.1848754882812,
"learning_rate": 8.753594236461957e-05,
"loss": 1335.3393,
"step": 2930
},
{
"epoch": 0.587,
"grad_norm": 250.04161071777344,
"learning_rate": 8.718967518281307e-05,
"loss": 1310.1785,
"step": 2935
},
{
"epoch": 0.588,
"grad_norm": 255.69981384277344,
"learning_rate": 8.684356409077176e-05,
"loss": 1325.6193,
"step": 2940
},
{
"epoch": 0.589,
"grad_norm": 297.2423400878906,
"learning_rate": 8.64976133057501e-05,
"loss": 1315.807,
"step": 2945
},
{
"epoch": 0.59,
"grad_norm": 253.99241638183594,
"learning_rate": 8.615182704304918e-05,
"loss": 1303.0527,
"step": 2950
},
{
"epoch": 0.591,
"grad_norm": 306.4051513671875,
"learning_rate": 8.580620951596557e-05,
"loss": 1315.8326,
"step": 2955
},
{
"epoch": 0.592,
"grad_norm": 260.3808898925781,
"learning_rate": 8.546076493573972e-05,
"loss": 1343.7293,
"step": 2960
},
{
"epoch": 0.593,
"grad_norm": 249.91424560546875,
"learning_rate": 8.511549751150479e-05,
"loss": 1303.4373,
"step": 2965
},
{
"epoch": 0.594,
"grad_norm": 1215.6756591796875,
"learning_rate": 8.477041145023546e-05,
"loss": 1377.5453,
"step": 2970
},
{
"epoch": 0.595,
"grad_norm": 283.0006408691406,
"learning_rate": 8.442551095669639e-05,
"loss": 1392.2133,
"step": 2975
},
{
"epoch": 0.596,
"grad_norm": 236.7594757080078,
"learning_rate": 8.408080023339133e-05,
"loss": 1276.8621,
"step": 2980
},
{
"epoch": 0.597,
"grad_norm": 387.7016296386719,
"learning_rate": 8.373628348051165e-05,
"loss": 1345.7743,
"step": 2985
},
{
"epoch": 0.598,
"grad_norm": 249.59451293945312,
"learning_rate": 8.339196489588523e-05,
"loss": 1288.6088,
"step": 2990
},
{
"epoch": 0.599,
"grad_norm": 325.0008544921875,
"learning_rate": 8.30478486749254e-05,
"loss": 1317.4807,
"step": 2995
},
{
"epoch": 0.6,
"grad_norm": 429.10009765625,
"learning_rate": 8.270393901057964e-05,
"loss": 1359.9636,
"step": 3000
},
{
"epoch": 0.601,
"grad_norm": 302.112548828125,
"learning_rate": 8.236024009327879e-05,
"loss": 1421.3981,
"step": 3005
},
{
"epoch": 0.602,
"grad_norm": 288.81756591796875,
"learning_rate": 8.201675611088558e-05,
"loss": 1314.2562,
"step": 3010
},
{
"epoch": 0.603,
"grad_norm": 229.85308837890625,
"learning_rate": 8.167349124864405e-05,
"loss": 1288.9699,
"step": 3015
},
{
"epoch": 0.604,
"grad_norm": 281.24798583984375,
"learning_rate": 8.133044968912811e-05,
"loss": 1292.687,
"step": 3020
},
{
"epoch": 0.605,
"grad_norm": 312.5220642089844,
"learning_rate": 8.0987635612191e-05,
"loss": 1283.7124,
"step": 3025
},
{
"epoch": 0.606,
"grad_norm": 239.10496520996094,
"learning_rate": 8.064505319491398e-05,
"loss": 1293.9194,
"step": 3030
},
{
"epoch": 0.607,
"grad_norm": 738.5653076171875,
"learning_rate": 8.030270661155574e-05,
"loss": 1343.8078,
"step": 3035
},
{
"epoch": 0.608,
"grad_norm": 247.14537048339844,
"learning_rate": 7.996060003350139e-05,
"loss": 1304.8693,
"step": 3040
},
{
"epoch": 0.609,
"grad_norm": 260.45098876953125,
"learning_rate": 7.961873762921153e-05,
"loss": 1311.7038,
"step": 3045
},
{
"epoch": 0.61,
"grad_norm": 240.45220947265625,
"learning_rate": 7.927712356417176e-05,
"loss": 1312.8882,
"step": 3050
},
{
"epoch": 0.611,
"grad_norm": 240.4870147705078,
"learning_rate": 7.893576200084159e-05,
"loss": 1321.7453,
"step": 3055
},
{
"epoch": 0.612,
"grad_norm": 271.0423583984375,
"learning_rate": 7.8594657098604e-05,
"loss": 1309.2872,
"step": 3060
},
{
"epoch": 0.613,
"grad_norm": 264.652099609375,
"learning_rate": 7.825381301371452e-05,
"loss": 1311.772,
"step": 3065
},
{
"epoch": 0.614,
"grad_norm": 268.085205078125,
"learning_rate": 7.791323389925084e-05,
"loss": 1322.1474,
"step": 3070
},
{
"epoch": 0.615,
"grad_norm": 397.0932312011719,
"learning_rate": 7.75729239050619e-05,
"loss": 1305.0425,
"step": 3075
},
{
"epoch": 0.616,
"grad_norm": 275.91888427734375,
"learning_rate": 7.723288717771761e-05,
"loss": 1303.9185,
"step": 3080
},
{
"epoch": 0.617,
"grad_norm": 248.13320922851562,
"learning_rate": 7.689312786045823e-05,
"loss": 1357.317,
"step": 3085
},
{
"epoch": 0.618,
"grad_norm": 243.19830322265625,
"learning_rate": 7.655365009314374e-05,
"loss": 1303.7456,
"step": 3090
},
{
"epoch": 0.619,
"grad_norm": 265.4331359863281,
"learning_rate": 7.621445801220371e-05,
"loss": 1303.0954,
"step": 3095
},
{
"epoch": 0.62,
"grad_norm": 295.4071044921875,
"learning_rate": 7.587555575058649e-05,
"loss": 1281.2282,
"step": 3100
},
{
"epoch": 0.621,
"grad_norm": 274.4746398925781,
"learning_rate": 7.553694743770928e-05,
"loss": 1301.2179,
"step": 3105
},
{
"epoch": 0.622,
"grad_norm": 289.707275390625,
"learning_rate": 7.519863719940748e-05,
"loss": 1271.9883,
"step": 3110
},
{
"epoch": 0.623,
"grad_norm": 260.5859680175781,
"learning_rate": 7.486062915788452e-05,
"loss": 1296.6228,
"step": 3115
},
{
"epoch": 0.624,
"grad_norm": 217.7989501953125,
"learning_rate": 7.45229274316618e-05,
"loss": 1264.1604,
"step": 3120
},
{
"epoch": 0.625,
"grad_norm": 275.3687438964844,
"learning_rate": 7.418553613552825e-05,
"loss": 1325.1691,
"step": 3125
},
{
"epoch": 0.626,
"grad_norm": 1288.2607421875,
"learning_rate": 7.384845938049031e-05,
"loss": 1368.3996,
"step": 3130
},
{
"epoch": 0.627,
"grad_norm": 984.128173828125,
"learning_rate": 7.351170127372191e-05,
"loss": 1519.1678,
"step": 3135
},
{
"epoch": 0.628,
"grad_norm": 1053.3822021484375,
"learning_rate": 7.317526591851433e-05,
"loss": 1391.2614,
"step": 3140
},
{
"epoch": 0.629,
"grad_norm": 647.2850341796875,
"learning_rate": 7.283915741422612e-05,
"loss": 1279.5723,
"step": 3145
},
{
"epoch": 0.63,
"grad_norm": 815.1610107421875,
"learning_rate": 7.250337985623342e-05,
"loss": 1294.7196,
"step": 3150
},
{
"epoch": 0.631,
"grad_norm": 402.7500915527344,
"learning_rate": 7.216793733587976e-05,
"loss": 1291.0354,
"step": 3155
},
{
"epoch": 0.632,
"grad_norm": 282.2257995605469,
"learning_rate": 7.183283394042634e-05,
"loss": 1361.8387,
"step": 3160
},
{
"epoch": 0.633,
"grad_norm": 262.54901123046875,
"learning_rate": 7.149807375300239e-05,
"loss": 1317.7299,
"step": 3165
},
{
"epoch": 0.634,
"grad_norm": 292.96429443359375,
"learning_rate": 7.11636608525551e-05,
"loss": 1307.3158,
"step": 3170
},
{
"epoch": 0.635,
"grad_norm": 345.77813720703125,
"learning_rate": 7.082959931380011e-05,
"loss": 1306.5719,
"step": 3175
},
{
"epoch": 0.636,
"grad_norm": 281.2658386230469,
"learning_rate": 7.049589320717186e-05,
"loss": 1307.6872,
"step": 3180
},
{
"epoch": 0.637,
"grad_norm": 362.6583557128906,
"learning_rate": 7.016254659877398e-05,
"loss": 1312.8996,
"step": 3185
},
{
"epoch": 0.638,
"grad_norm": 443.9662780761719,
"learning_rate": 6.982956355032968e-05,
"loss": 1271.555,
"step": 3190
},
{
"epoch": 0.639,
"grad_norm": 240.9832763671875,
"learning_rate": 6.949694811913225e-05,
"loss": 1300.715,
"step": 3195
},
{
"epoch": 0.64,
"grad_norm": 253.03407287597656,
"learning_rate": 6.916470435799587e-05,
"loss": 1269.5942,
"step": 3200
},
{
"epoch": 0.641,
"grad_norm": 290.7709655761719,
"learning_rate": 6.883283631520582e-05,
"loss": 1344.419,
"step": 3205
},
{
"epoch": 0.642,
"grad_norm": 235.1630401611328,
"learning_rate": 6.850134803446954e-05,
"loss": 1350.1804,
"step": 3210
},
{
"epoch": 0.643,
"grad_norm": 271.03289794921875,
"learning_rate": 6.817024355486706e-05,
"loss": 1307.8426,
"step": 3215
},
{
"epoch": 0.644,
"grad_norm": 554.9446411132812,
"learning_rate": 6.783952691080203e-05,
"loss": 1308.3281,
"step": 3220
},
{
"epoch": 0.645,
"grad_norm": 257.90667724609375,
"learning_rate": 6.750920213195238e-05,
"loss": 1327.424,
"step": 3225
},
{
"epoch": 0.646,
"grad_norm": 504.7820739746094,
"learning_rate": 6.717927324322124e-05,
"loss": 1290.4453,
"step": 3230
},
{
"epoch": 0.647,
"grad_norm": 277.0068054199219,
"learning_rate": 6.684974426468808e-05,
"loss": 1295.5068,
"step": 3235
},
{
"epoch": 0.648,
"grad_norm": 259.60577392578125,
"learning_rate": 6.652061921155943e-05,
"loss": 1282.632,
"step": 3240
},
{
"epoch": 0.649,
"grad_norm": 392.2469177246094,
"learning_rate": 6.61919020941203e-05,
"loss": 1321.9872,
"step": 3245
},
{
"epoch": 0.65,
"grad_norm": 333.8143005371094,
"learning_rate": 6.58635969176849e-05,
"loss": 1360.6781,
"step": 3250
},
{
"epoch": 0.651,
"grad_norm": 263.462646484375,
"learning_rate": 6.55357076825483e-05,
"loss": 1274.5674,
"step": 3255
},
{
"epoch": 0.652,
"grad_norm": 256.18878173828125,
"learning_rate": 6.520823838393731e-05,
"loss": 1298.1985,
"step": 3260
},
{
"epoch": 0.653,
"grad_norm": 229.60397338867188,
"learning_rate": 6.488119301196201e-05,
"loss": 1306.7311,
"step": 3265
},
{
"epoch": 0.654,
"grad_norm": 437.06927490234375,
"learning_rate": 6.455457555156705e-05,
"loss": 1326.0975,
"step": 3270
},
{
"epoch": 0.655,
"grad_norm": 312.4342346191406,
"learning_rate": 6.422838998248307e-05,
"loss": 1258.3517,
"step": 3275
},
{
"epoch": 0.656,
"grad_norm": 267.7524719238281,
"learning_rate": 6.390264027917836e-05,
"loss": 1285.6211,
"step": 3280
},
{
"epoch": 0.657,
"grad_norm": 908.039794921875,
"learning_rate": 6.357733041081018e-05,
"loss": 1393.8192,
"step": 3285
},
{
"epoch": 0.658,
"grad_norm": 331.30462646484375,
"learning_rate": 6.325246434117668e-05,
"loss": 1255.3387,
"step": 3290
},
{
"epoch": 0.659,
"grad_norm": 456.7723083496094,
"learning_rate": 6.292804602866834e-05,
"loss": 1327.5662,
"step": 3295
},
{
"epoch": 0.66,
"grad_norm": 257.1352233886719,
"learning_rate": 6.260407942621998e-05,
"loss": 1284.9213,
"step": 3300
},
{
"epoch": 0.661,
"grad_norm": 328.7150573730469,
"learning_rate": 6.228056848126236e-05,
"loss": 1297.0059,
"step": 3305
},
{
"epoch": 0.662,
"grad_norm": 267.4071960449219,
"learning_rate": 6.195751713567427e-05,
"loss": 1299.791,
"step": 3310
},
{
"epoch": 0.663,
"grad_norm": 322.7093200683594,
"learning_rate": 6.163492932573438e-05,
"loss": 1306.3097,
"step": 3315
},
{
"epoch": 0.664,
"grad_norm": 263.0763244628906,
"learning_rate": 6.131280898207339e-05,
"loss": 1280.3305,
"step": 3320
},
{
"epoch": 0.665,
"grad_norm": 261.4583435058594,
"learning_rate": 6.099116002962604e-05,
"loss": 1277.8259,
"step": 3325
},
{
"epoch": 0.666,
"grad_norm": 266.81842041015625,
"learning_rate": 6.066998638758326e-05,
"loss": 1266.7106,
"step": 3330
},
{
"epoch": 0.667,
"grad_norm": 212.54733276367188,
"learning_rate": 6.034929196934459e-05,
"loss": 1383.4156,
"step": 3335
},
{
"epoch": 0.668,
"grad_norm": 236.7985076904297,
"learning_rate": 6.002908068247024e-05,
"loss": 1288.6369,
"step": 3340
},
{
"epoch": 0.669,
"grad_norm": 236.44354248046875,
"learning_rate": 5.9709356428633746e-05,
"loss": 1265.5572,
"step": 3345
},
{
"epoch": 0.67,
"grad_norm": 429.1231994628906,
"learning_rate": 5.9390123103574215e-05,
"loss": 1263.3389,
"step": 3350
},
{
"epoch": 0.671,
"grad_norm": 346.5932922363281,
"learning_rate": 5.907138459704895e-05,
"loss": 1328.3272,
"step": 3355
},
{
"epoch": 0.672,
"grad_norm": 237.2406005859375,
"learning_rate": 5.8753144792786096e-05,
"loss": 1265.5292,
"step": 3360
},
{
"epoch": 0.673,
"grad_norm": 274.960205078125,
"learning_rate": 5.8435407568437216e-05,
"loss": 1287.0539,
"step": 3365
},
{
"epoch": 0.674,
"grad_norm": 547.3673706054688,
"learning_rate": 5.8118176795530176e-05,
"loss": 1300.5678,
"step": 3370
},
{
"epoch": 0.675,
"grad_norm": 293.45074462890625,
"learning_rate": 5.780145633942173e-05,
"loss": 1271.2639,
"step": 3375
},
{
"epoch": 0.676,
"grad_norm": 256.02874755859375,
"learning_rate": 5.748525005925074e-05,
"loss": 1283.1988,
"step": 3380
},
{
"epoch": 0.677,
"grad_norm": 250.6363067626953,
"learning_rate": 5.716956180789098e-05,
"loss": 1313.0365,
"step": 3385
},
{
"epoch": 0.678,
"grad_norm": 234.90528869628906,
"learning_rate": 5.6854395431904094e-05,
"loss": 1281.815,
"step": 3390
},
{
"epoch": 0.679,
"grad_norm": 235.28265380859375,
"learning_rate": 5.653975477149298e-05,
"loss": 1252.7053,
"step": 3395
},
{
"epoch": 0.68,
"grad_norm": 248.4268341064453,
"learning_rate": 5.622564366045472e-05,
"loss": 1237.355,
"step": 3400
},
{
"epoch": 0.681,
"grad_norm": 248.0801544189453,
"learning_rate": 5.591206592613416e-05,
"loss": 1302.4162,
"step": 3405
},
{
"epoch": 0.682,
"grad_norm": 250.66860961914062,
"learning_rate": 5.5599025389376935e-05,
"loss": 1268.7936,
"step": 3410
},
{
"epoch": 0.683,
"grad_norm": 229.06912231445312,
"learning_rate": 5.5286525864483285e-05,
"loss": 1288.0536,
"step": 3415
},
{
"epoch": 0.684,
"grad_norm": 284.2197570800781,
"learning_rate": 5.497457115916127e-05,
"loss": 1265.7467,
"step": 3420
},
{
"epoch": 0.685,
"grad_norm": 215.25067138671875,
"learning_rate": 5.466316507448048e-05,
"loss": 1265.0119,
"step": 3425
},
{
"epoch": 0.686,
"grad_norm": 250.35739135742188,
"learning_rate": 5.435231140482587e-05,
"loss": 1273.9391,
"step": 3430
},
{
"epoch": 0.687,
"grad_norm": 235.7361602783203,
"learning_rate": 5.404201393785122e-05,
"loss": 1299.2939,
"step": 3435
},
{
"epoch": 0.688,
"grad_norm": 347.4424743652344,
"learning_rate": 5.373227645443332e-05,
"loss": 1278.3284,
"step": 3440
},
{
"epoch": 0.689,
"grad_norm": 231.99691772460938,
"learning_rate": 5.3423102728625574e-05,
"loss": 1262.1102,
"step": 3445
},
{
"epoch": 0.69,
"grad_norm": 247.3707275390625,
"learning_rate": 5.311449652761235e-05,
"loss": 1301.6031,
"step": 3450
},
{
"epoch": 0.691,
"grad_norm": 271.9532775878906,
"learning_rate": 5.2806461611662735e-05,
"loss": 1288.7795,
"step": 3455
},
{
"epoch": 0.692,
"grad_norm": 288.9332275390625,
"learning_rate": 5.2499001734085044e-05,
"loss": 1383.866,
"step": 3460
},
{
"epoch": 0.693,
"grad_norm": 406.1845397949219,
"learning_rate": 5.2192120641180786e-05,
"loss": 1281.0271,
"step": 3465
},
{
"epoch": 0.694,
"grad_norm": 291.4728088378906,
"learning_rate": 5.188582207219931e-05,
"loss": 1306.8142,
"step": 3470
},
{
"epoch": 0.695,
"grad_norm": 272.9517517089844,
"learning_rate": 5.158010975929193e-05,
"loss": 1291.8693,
"step": 3475
},
{
"epoch": 0.696,
"grad_norm": 257.42828369140625,
"learning_rate": 5.127498742746675e-05,
"loss": 1277.8821,
"step": 3480
},
{
"epoch": 0.697,
"grad_norm": 1106.9957275390625,
"learning_rate": 5.097045879454313e-05,
"loss": 1344.0602,
"step": 3485
},
{
"epoch": 0.698,
"grad_norm": 252.6271514892578,
"learning_rate": 5.066652757110628e-05,
"loss": 1278.0932,
"step": 3490
},
{
"epoch": 0.699,
"grad_norm": 271.9337158203125,
"learning_rate": 5.036319746046232e-05,
"loss": 1303.0128,
"step": 3495
},
{
"epoch": 0.7,
"grad_norm": 265.9996643066406,
"learning_rate": 5.006047215859289e-05,
"loss": 1233.7605,
"step": 3500
},
{
"epoch": 0.701,
"grad_norm": 369.9506530761719,
"learning_rate": 4.97583553541102e-05,
"loss": 1292.9807,
"step": 3505
},
{
"epoch": 0.702,
"grad_norm": 248.90902709960938,
"learning_rate": 4.945685072821227e-05,
"loss": 1298.5791,
"step": 3510
},
{
"epoch": 0.703,
"grad_norm": 280.69219970703125,
"learning_rate": 4.915596195463773e-05,
"loss": 1251.0454,
"step": 3515
},
{
"epoch": 0.704,
"grad_norm": 433.5792236328125,
"learning_rate": 4.885569269962142e-05,
"loss": 1295.0089,
"step": 3520
},
{
"epoch": 0.705,
"grad_norm": 440.1638488769531,
"learning_rate": 4.8556046621849346e-05,
"loss": 1312.7502,
"step": 3525
},
{
"epoch": 0.706,
"grad_norm": 224.58413696289062,
"learning_rate": 4.825702737241452e-05,
"loss": 1501.2768,
"step": 3530
},
{
"epoch": 0.707,
"grad_norm": 510.2673645019531,
"learning_rate": 4.7958638594772064e-05,
"loss": 1278.8876,
"step": 3535
},
{
"epoch": 0.708,
"grad_norm": 1025.1546630859375,
"learning_rate": 4.766088392469506e-05,
"loss": 1408.0525,
"step": 3540
},
{
"epoch": 0.709,
"grad_norm": 543.3572998046875,
"learning_rate": 4.736376699023023e-05,
"loss": 1340.9316,
"step": 3545
},
{
"epoch": 0.71,
"grad_norm": 261.21905517578125,
"learning_rate": 4.706729141165361e-05,
"loss": 1247.6393,
"step": 3550
},
{
"epoch": 0.711,
"grad_norm": 254.30355834960938,
"learning_rate": 4.6771460801426635e-05,
"loss": 1258.4004,
"step": 3555
},
{
"epoch": 0.712,
"grad_norm": 289.28533935546875,
"learning_rate": 4.647627876415186e-05,
"loss": 1268.4976,
"step": 3560
},
{
"epoch": 0.713,
"grad_norm": 427.8967590332031,
"learning_rate": 4.6181748896529273e-05,
"loss": 1300.0154,
"step": 3565
},
{
"epoch": 0.714,
"grad_norm": 232.45130920410156,
"learning_rate": 4.588787478731242e-05,
"loss": 1298.4209,
"step": 3570
},
{
"epoch": 0.715,
"grad_norm": 304.25042724609375,
"learning_rate": 4.559466001726451e-05,
"loss": 1272.5296,
"step": 3575
},
{
"epoch": 0.716,
"grad_norm": 265.6990661621094,
"learning_rate": 4.530210815911504e-05,
"loss": 1254.9911,
"step": 3580
},
{
"epoch": 0.717,
"grad_norm": 212.3408660888672,
"learning_rate": 4.501022277751602e-05,
"loss": 1267.6885,
"step": 3585
},
{
"epoch": 0.718,
"grad_norm": 232.7149200439453,
"learning_rate": 4.471900742899876e-05,
"loss": 1284.7026,
"step": 3590
},
{
"epoch": 0.719,
"grad_norm": 272.26806640625,
"learning_rate": 4.4428465661930343e-05,
"loss": 1246.2651,
"step": 3595
},
{
"epoch": 0.72,
"grad_norm": 255.49290466308594,
"learning_rate": 4.413860101647055e-05,
"loss": 1295.4066,
"step": 3600
},
{
"epoch": 0.721,
"grad_norm": 231.83895874023438,
"learning_rate": 4.3849417024528564e-05,
"loss": 1353.474,
"step": 3605
},
{
"epoch": 0.722,
"grad_norm": 251.35107421875,
"learning_rate": 4.356091720972011e-05,
"loss": 1270.7032,
"step": 3610
},
{
"epoch": 0.723,
"grad_norm": 442.9390563964844,
"learning_rate": 4.327310508732437e-05,
"loss": 1283.5675,
"step": 3615
},
{
"epoch": 0.724,
"grad_norm": 273.5343933105469,
"learning_rate": 4.29859841642412e-05,
"loss": 1290.2618,
"step": 3620
},
{
"epoch": 0.725,
"grad_norm": 247.04347229003906,
"learning_rate": 4.26995579389485e-05,
"loss": 1302.2106,
"step": 3625
},
{
"epoch": 0.726,
"grad_norm": 282.27276611328125,
"learning_rate": 4.2413829901459344e-05,
"loss": 1381.3751,
"step": 3630
},
{
"epoch": 0.727,
"grad_norm": 259.0196228027344,
"learning_rate": 4.212880353327979e-05,
"loss": 1233.9972,
"step": 3635
},
{
"epoch": 0.728,
"grad_norm": 310.1590881347656,
"learning_rate": 4.184448230736613e-05,
"loss": 1282.2009,
"step": 3640
},
{
"epoch": 0.729,
"grad_norm": 244.57882690429688,
"learning_rate": 4.15608696880828e-05,
"loss": 1288.2392,
"step": 3645
},
{
"epoch": 0.73,
"grad_norm": 266.11859130859375,
"learning_rate": 4.1277969131160045e-05,
"loss": 1283.517,
"step": 3650
},
{
"epoch": 0.731,
"grad_norm": 359.607421875,
"learning_rate": 4.099578408365191e-05,
"loss": 1247.8046,
"step": 3655
},
{
"epoch": 0.732,
"grad_norm": 242.9519500732422,
"learning_rate": 4.071431798389408e-05,
"loss": 1250.5926,
"step": 3660
},
{
"epoch": 0.733,
"grad_norm": 274.9290466308594,
"learning_rate": 4.0433574261462206e-05,
"loss": 1238.7865,
"step": 3665
},
{
"epoch": 0.734,
"grad_norm": 209.9217071533203,
"learning_rate": 4.015355633712996e-05,
"loss": 1254.7511,
"step": 3670
},
{
"epoch": 0.735,
"grad_norm": 262.1658630371094,
"learning_rate": 3.987426762282733e-05,
"loss": 1263.9171,
"step": 3675
},
{
"epoch": 0.736,
"grad_norm": 222.66236877441406,
"learning_rate": 3.9595711521599224e-05,
"loss": 1258.4786,
"step": 3680
},
{
"epoch": 0.737,
"grad_norm": 237.26905822753906,
"learning_rate": 3.931789142756377e-05,
"loss": 1277.3754,
"step": 3685
},
{
"epoch": 0.738,
"grad_norm": 229.42071533203125,
"learning_rate": 3.904081072587119e-05,
"loss": 1268.7519,
"step": 3690
},
{
"epoch": 0.739,
"grad_norm": 229.69680786132812,
"learning_rate": 3.876447279266238e-05,
"loss": 1283.6924,
"step": 3695
},
{
"epoch": 0.74,
"grad_norm": 251.71824645996094,
"learning_rate": 3.8488880995027786e-05,
"loss": 1288.0123,
"step": 3700
},
{
"epoch": 0.741,
"grad_norm": 287.8528747558594,
"learning_rate": 3.821403869096658e-05,
"loss": 1250.9646,
"step": 3705
},
{
"epoch": 0.742,
"grad_norm": 337.2502746582031,
"learning_rate": 3.793994922934544e-05,
"loss": 1243.0608,
"step": 3710
},
{
"epoch": 0.743,
"grad_norm": 265.68316650390625,
"learning_rate": 3.766661594985801e-05,
"loss": 1243.0595,
"step": 3715
},
{
"epoch": 0.744,
"grad_norm": 391.8319396972656,
"learning_rate": 3.739404218298398e-05,
"loss": 1314.2666,
"step": 3720
},
{
"epoch": 0.745,
"grad_norm": 230.19635009765625,
"learning_rate": 3.712223124994875e-05,
"loss": 1287.2367,
"step": 3725
},
{
"epoch": 0.746,
"grad_norm": 235.80422973632812,
"learning_rate": 3.685118646268272e-05,
"loss": 1309.399,
"step": 3730
},
{
"epoch": 0.747,
"grad_norm": 597.7236938476562,
"learning_rate": 3.6580911123781056e-05,
"loss": 1346.6137,
"step": 3735
},
{
"epoch": 0.748,
"grad_norm": 287.1773376464844,
"learning_rate": 3.631140852646355e-05,
"loss": 1281.7015,
"step": 3740
},
{
"epoch": 0.749,
"grad_norm": 250.05520629882812,
"learning_rate": 3.604268195453421e-05,
"loss": 1277.5244,
"step": 3745
},
{
"epoch": 0.75,
"grad_norm": 241.22874450683594,
"learning_rate": 3.577473468234156e-05,
"loss": 1284.8863,
"step": 3750
},
{
"epoch": 0.751,
"grad_norm": 264.1650085449219,
"learning_rate": 3.5507569974738574e-05,
"loss": 1276.9885,
"step": 3755
},
{
"epoch": 0.752,
"grad_norm": 287.9472961425781,
"learning_rate": 3.524119108704286e-05,
"loss": 1266.1238,
"step": 3760
},
{
"epoch": 0.753,
"grad_norm": 229.09190368652344,
"learning_rate": 3.497560126499709e-05,
"loss": 1265.4324,
"step": 3765
},
{
"epoch": 0.754,
"grad_norm": 316.47576904296875,
"learning_rate": 3.4710803744729515e-05,
"loss": 1292.4234,
"step": 3770
},
{
"epoch": 0.755,
"grad_norm": 274.4029541015625,
"learning_rate": 3.444680175271428e-05,
"loss": 1315.2333,
"step": 3775
},
{
"epoch": 0.756,
"grad_norm": 232.93960571289062,
"learning_rate": 3.418359850573234e-05,
"loss": 1304.5767,
"step": 3780
},
{
"epoch": 0.757,
"grad_norm": 274.5046691894531,
"learning_rate": 3.3921197210832235e-05,
"loss": 1286.3933,
"step": 3785
},
{
"epoch": 0.758,
"grad_norm": 246.56390380859375,
"learning_rate": 3.3659601065290893e-05,
"loss": 1264.8206,
"step": 3790
},
{
"epoch": 0.759,
"grad_norm": 225.13082885742188,
"learning_rate": 3.339881325657484e-05,
"loss": 1266.5393,
"step": 3795
},
{
"epoch": 0.76,
"grad_norm": 247.62850952148438,
"learning_rate": 3.313883696230119e-05,
"loss": 1241.6483,
"step": 3800
},
{
"epoch": 0.761,
"grad_norm": 259.89569091796875,
"learning_rate": 3.287967535019908e-05,
"loss": 1301.5986,
"step": 3805
},
{
"epoch": 0.762,
"grad_norm": 240.48779296875,
"learning_rate": 3.2621331578070934e-05,
"loss": 1253.5451,
"step": 3810
},
{
"epoch": 0.763,
"grad_norm": 279.7120056152344,
"learning_rate": 3.236380879375408e-05,
"loss": 1246.671,
"step": 3815
},
{
"epoch": 0.764,
"grad_norm": 241.607177734375,
"learning_rate": 3.210711013508242e-05,
"loss": 1297.333,
"step": 3820
},
{
"epoch": 0.765,
"grad_norm": 228.6789093017578,
"learning_rate": 3.1851238729848034e-05,
"loss": 1308.9502,
"step": 3825
},
{
"epoch": 0.766,
"grad_norm": 584.2429809570312,
"learning_rate": 3.159619769576333e-05,
"loss": 1313.6634,
"step": 3830
},
{
"epoch": 0.767,
"grad_norm": 232.77394104003906,
"learning_rate": 3.134199014042274e-05,
"loss": 1253.371,
"step": 3835
},
{
"epoch": 0.768,
"grad_norm": 258.13519287109375,
"learning_rate": 3.108861916126518e-05,
"loss": 1278.4747,
"step": 3840
},
{
"epoch": 0.769,
"grad_norm": 226.85568237304688,
"learning_rate": 3.0836087845536e-05,
"loss": 1234.501,
"step": 3845
},
{
"epoch": 0.77,
"grad_norm": 230.62644958496094,
"learning_rate": 3.058439927024962e-05,
"loss": 1248.4223,
"step": 3850
},
{
"epoch": 0.771,
"grad_norm": 268.6643371582031,
"learning_rate": 3.0333556502151926e-05,
"loss": 1289.9641,
"step": 3855
},
{
"epoch": 0.772,
"grad_norm": 294.9214172363281,
"learning_rate": 3.0083562597682847e-05,
"loss": 1264.0324,
"step": 3860
},
{
"epoch": 0.773,
"grad_norm": 262.3878173828125,
"learning_rate": 2.9834420602939263e-05,
"loss": 1260.5714,
"step": 3865
},
{
"epoch": 0.774,
"grad_norm": 233.42506408691406,
"learning_rate": 2.9586133553637683e-05,
"loss": 1288.3376,
"step": 3870
},
{
"epoch": 0.775,
"grad_norm": 255.8433837890625,
"learning_rate": 2.933870447507753e-05,
"loss": 1250.1626,
"step": 3875
},
{
"epoch": 0.776,
"grad_norm": 230.3672332763672,
"learning_rate": 2.9092136382103973e-05,
"loss": 1268.3102,
"step": 3880
},
{
"epoch": 0.777,
"grad_norm": 217.95208740234375,
"learning_rate": 2.8846432279071467e-05,
"loss": 1251.6467,
"step": 3885
},
{
"epoch": 0.778,
"grad_norm": 296.6186218261719,
"learning_rate": 2.860159515980695e-05,
"loss": 1302.2947,
"step": 3890
},
{
"epoch": 0.779,
"grad_norm": 294.1287841796875,
"learning_rate": 2.835762800757341e-05,
"loss": 1291.2716,
"step": 3895
},
{
"epoch": 0.78,
"grad_norm": 344.5246276855469,
"learning_rate": 2.8114533795033683e-05,
"loss": 1241.6314,
"step": 3900
},
{
"epoch": 0.781,
"grad_norm": 455.2098388671875,
"learning_rate": 2.7872315484213952e-05,
"loss": 1213.3473,
"step": 3905
},
{
"epoch": 0.782,
"grad_norm": 249.8082733154297,
"learning_rate": 2.7630976026467968e-05,
"loss": 1250.2201,
"step": 3910
},
{
"epoch": 0.783,
"grad_norm": 788.1091918945312,
"learning_rate": 2.7390518362440808e-05,
"loss": 1293.0925,
"step": 3915
},
{
"epoch": 0.784,
"grad_norm": 277.9227294921875,
"learning_rate": 2.715094542203327e-05,
"loss": 1293.4035,
"step": 3920
},
{
"epoch": 0.785,
"grad_norm": 259.3800048828125,
"learning_rate": 2.6912260124366006e-05,
"loss": 1303.2888,
"step": 3925
},
{
"epoch": 0.786,
"grad_norm": 257.3354187011719,
"learning_rate": 2.6674465377744017e-05,
"loss": 1273.2924,
"step": 3930
},
{
"epoch": 0.787,
"grad_norm": 224.82492065429688,
"learning_rate": 2.6437564079621267e-05,
"loss": 1275.2481,
"step": 3935
},
{
"epoch": 0.788,
"grad_norm": 285.6820373535156,
"learning_rate": 2.6201559116565345e-05,
"loss": 1316.8004,
"step": 3940
},
{
"epoch": 0.789,
"grad_norm": 245.67742919921875,
"learning_rate": 2.5966453364222186e-05,
"loss": 1267.3149,
"step": 3945
},
{
"epoch": 0.79,
"grad_norm": 262.1764221191406,
"learning_rate": 2.573224968728123e-05,
"loss": 1270.9531,
"step": 3950
},
{
"epoch": 0.791,
"grad_norm": 232.96571350097656,
"learning_rate": 2.549895093944039e-05,
"loss": 1304.4828,
"step": 3955
},
{
"epoch": 0.792,
"grad_norm": 255.89581298828125,
"learning_rate": 2.5266559963371216e-05,
"loss": 1230.8467,
"step": 3960
},
{
"epoch": 0.793,
"grad_norm": 239.95997619628906,
"learning_rate": 2.5035079590684497e-05,
"loss": 1250.584,
"step": 3965
},
{
"epoch": 0.794,
"grad_norm": 273.9261779785156,
"learning_rate": 2.480451264189546e-05,
"loss": 1265.645,
"step": 3970
},
{
"epoch": 0.795,
"grad_norm": 238.4413299560547,
"learning_rate": 2.4574861926389615e-05,
"loss": 1260.546,
"step": 3975
},
{
"epoch": 0.796,
"grad_norm": 285.26361083984375,
"learning_rate": 2.43461302423885e-05,
"loss": 1314.9657,
"step": 3980
},
{
"epoch": 0.797,
"grad_norm": 297.1378479003906,
"learning_rate": 2.411832037691545e-05,
"loss": 1341.1153,
"step": 3985
},
{
"epoch": 0.798,
"grad_norm": 246.28668212890625,
"learning_rate": 2.389143510576184e-05,
"loss": 1259.7807,
"step": 3990
},
{
"epoch": 0.799,
"grad_norm": 294.2397766113281,
"learning_rate": 2.3665477193453034e-05,
"loss": 1274.8513,
"step": 3995
},
{
"epoch": 0.8,
"grad_norm": 216.7938995361328,
"learning_rate": 2.3440449393214948e-05,
"loss": 1222.6264,
"step": 4000
},
{
"epoch": 0.801,
"grad_norm": 316.46563720703125,
"learning_rate": 2.321635444694028e-05,
"loss": 1245.8781,
"step": 4005
},
{
"epoch": 0.802,
"grad_norm": 318.5700378417969,
"learning_rate": 2.2993195085155205e-05,
"loss": 1277.8398,
"step": 4010
},
{
"epoch": 0.803,
"grad_norm": 361.9563903808594,
"learning_rate": 2.277097402698619e-05,
"loss": 1250.4374,
"step": 4015
},
{
"epoch": 0.804,
"grad_norm": 318.5209655761719,
"learning_rate": 2.254969398012663e-05,
"loss": 1285.3773,
"step": 4020
},
{
"epoch": 0.805,
"grad_norm": 250.24574279785156,
"learning_rate": 2.2329357640804117e-05,
"loss": 1282.8163,
"step": 4025
},
{
"epoch": 0.806,
"grad_norm": 231.8607635498047,
"learning_rate": 2.210996769374737e-05,
"loss": 1306.5397,
"step": 4030
},
{
"epoch": 0.807,
"grad_norm": 225.60009765625,
"learning_rate": 2.1891526812153672e-05,
"loss": 1245.0155,
"step": 4035
},
{
"epoch": 0.808,
"grad_norm": 255.72134399414062,
"learning_rate": 2.1674037657656266e-05,
"loss": 1276.583,
"step": 4040
},
{
"epoch": 0.809,
"grad_norm": 235.26173400878906,
"learning_rate": 2.1457502880291812e-05,
"loss": 1255.5608,
"step": 4045
},
{
"epoch": 0.81,
"grad_norm": 253.36618041992188,
"learning_rate": 2.1241925118468287e-05,
"loss": 1264.5601,
"step": 4050
},
{
"epoch": 0.811,
"grad_norm": 251.9161834716797,
"learning_rate": 2.1027306998932627e-05,
"loss": 1275.3649,
"step": 4055
},
{
"epoch": 0.812,
"grad_norm": 203.58822631835938,
"learning_rate": 2.0813651136738954e-05,
"loss": 1243.1853,
"step": 4060
},
{
"epoch": 0.813,
"grad_norm": 241.9400634765625,
"learning_rate": 2.0600960135216462e-05,
"loss": 1279.7758,
"step": 4065
},
{
"epoch": 0.814,
"grad_norm": 243.53924560546875,
"learning_rate": 2.0389236585937945e-05,
"loss": 1266.1336,
"step": 4070
},
{
"epoch": 0.815,
"grad_norm": 212.11488342285156,
"learning_rate": 2.017848306868797e-05,
"loss": 1246.9063,
"step": 4075
},
{
"epoch": 0.816,
"grad_norm": 258.4122314453125,
"learning_rate": 1.9968702151431696e-05,
"loss": 1269.5753,
"step": 4080
},
{
"epoch": 0.817,
"grad_norm": 247.7945098876953,
"learning_rate": 1.9759896390283362e-05,
"loss": 1252.075,
"step": 4085
},
{
"epoch": 0.818,
"grad_norm": 313.71435546875,
"learning_rate": 1.955206832947526e-05,
"loss": 1277.7242,
"step": 4090
},
{
"epoch": 0.819,
"grad_norm": 240.216064453125,
"learning_rate": 1.9345220501326777e-05,
"loss": 1301.8305,
"step": 4095
},
{
"epoch": 0.82,
"grad_norm": 261.0376892089844,
"learning_rate": 1.9139355426213347e-05,
"loss": 1209.6584,
"step": 4100
},
{
"epoch": 0.821,
"grad_norm": 233.87245178222656,
"learning_rate": 1.8934475612536017e-05,
"loss": 1248.8694,
"step": 4105
},
{
"epoch": 0.822,
"grad_norm": 224.53736877441406,
"learning_rate": 1.8730583556690605e-05,
"loss": 1237.8229,
"step": 4110
},
{
"epoch": 0.823,
"grad_norm": 229.07666015625,
"learning_rate": 1.852768174303752e-05,
"loss": 1282.7551,
"step": 4115
},
{
"epoch": 0.824,
"grad_norm": 368.8656311035156,
"learning_rate": 1.8325772643871265e-05,
"loss": 1272.311,
"step": 4120
},
{
"epoch": 0.825,
"grad_norm": 237.4892578125,
"learning_rate": 1.812485871939056e-05,
"loss": 1299.4718,
"step": 4125
},
{
"epoch": 0.826,
"grad_norm": 231.9585723876953,
"learning_rate": 1.792494241766811e-05,
"loss": 1279.8513,
"step": 4130
},
{
"epoch": 0.827,
"grad_norm": 283.12750244140625,
"learning_rate": 1.7726026174621003e-05,
"loss": 1254.4344,
"step": 4135
},
{
"epoch": 0.828,
"grad_norm": 285.6492614746094,
"learning_rate": 1.752811241398089e-05,
"loss": 1266.8676,
"step": 4140
},
{
"epoch": 0.829,
"grad_norm": 228.58395385742188,
"learning_rate": 1.7331203547264453e-05,
"loss": 1294.2273,
"step": 4145
},
{
"epoch": 0.83,
"grad_norm": 257.78033447265625,
"learning_rate": 1.7135301973744124e-05,
"loss": 1257.6217,
"step": 4150
},
{
"epoch": 0.831,
"grad_norm": 337.0272216796875,
"learning_rate": 1.6940410080418723e-05,
"loss": 1279.7018,
"step": 4155
},
{
"epoch": 0.832,
"grad_norm": 239.84548950195312,
"learning_rate": 1.6746530241984504e-05,
"loss": 1215.4563,
"step": 4160
},
{
"epoch": 0.833,
"grad_norm": 206.06887817382812,
"learning_rate": 1.6553664820806102e-05,
"loss": 1244.4292,
"step": 4165
},
{
"epoch": 0.834,
"grad_norm": 232.3435516357422,
"learning_rate": 1.6361816166887768e-05,
"loss": 1267.0978,
"step": 4170
},
{
"epoch": 0.835,
"grad_norm": 356.8957214355469,
"learning_rate": 1.6170986617844863e-05,
"loss": 1259.4301,
"step": 4175
},
{
"epoch": 0.836,
"grad_norm": 203.85726928710938,
"learning_rate": 1.598117849887518e-05,
"loss": 1256.5121,
"step": 4180
},
{
"epoch": 0.837,
"grad_norm": 326.1778259277344,
"learning_rate": 1.579239412273078e-05,
"loss": 1282.6159,
"step": 4185
},
{
"epoch": 0.838,
"grad_norm": 237.78929138183594,
"learning_rate": 1.560463578968967e-05,
"loss": 1275.8921,
"step": 4190
},
{
"epoch": 0.839,
"grad_norm": 232.11679077148438,
"learning_rate": 1.541790578752794e-05,
"loss": 1235.2606,
"step": 4195
},
{
"epoch": 0.84,
"grad_norm": 291.945068359375,
"learning_rate": 1.5232206391491699e-05,
"loss": 1290.4143,
"step": 4200
},
{
"epoch": 0.841,
"grad_norm": 225.68850708007812,
"learning_rate": 1.5047539864269478e-05,
"loss": 1282.0326,
"step": 4205
},
{
"epoch": 0.842,
"grad_norm": 333.8077087402344,
"learning_rate": 1.486390845596466e-05,
"loss": 1306.688,
"step": 4210
},
{
"epoch": 0.843,
"grad_norm": 225.36940002441406,
"learning_rate": 1.468131440406798e-05,
"loss": 1277.2607,
"step": 4215
},
{
"epoch": 0.844,
"grad_norm": 282.03302001953125,
"learning_rate": 1.4499759933430346e-05,
"loss": 1267.9396,
"step": 4220
},
{
"epoch": 0.845,
"grad_norm": 245.85311889648438,
"learning_rate": 1.4319247256235714e-05,
"loss": 1241.1733,
"step": 4225
},
{
"epoch": 0.846,
"grad_norm": 356.6911315917969,
"learning_rate": 1.4139778571974049e-05,
"loss": 1262.5599,
"step": 4230
},
{
"epoch": 0.847,
"grad_norm": 320.9154357910156,
"learning_rate": 1.3961356067414666e-05,
"loss": 1239.6616,
"step": 4235
},
{
"epoch": 0.848,
"grad_norm": 269.1080627441406,
"learning_rate": 1.3783981916579446e-05,
"loss": 1227.2613,
"step": 4240
},
{
"epoch": 0.849,
"grad_norm": 232.03726196289062,
"learning_rate": 1.3607658280716473e-05,
"loss": 1302.4891,
"step": 4245
},
{
"epoch": 0.85,
"grad_norm": 216.3743438720703,
"learning_rate": 1.3432387308273575e-05,
"loss": 1255.9799,
"step": 4250
},
{
"epoch": 0.851,
"grad_norm": 237.74461364746094,
"learning_rate": 1.3258171134872265e-05,
"loss": 1283.3469,
"step": 4255
},
{
"epoch": 0.852,
"grad_norm": 208.8504180908203,
"learning_rate": 1.3085011883281606e-05,
"loss": 1198.5111,
"step": 4260
},
{
"epoch": 0.853,
"grad_norm": 215.67691040039062,
"learning_rate": 1.2912911663392469e-05,
"loss": 1240.215,
"step": 4265
},
{
"epoch": 0.854,
"grad_norm": 236.99240112304688,
"learning_rate": 1.2741872572191682e-05,
"loss": 1347.5431,
"step": 4270
},
{
"epoch": 0.855,
"grad_norm": 226.73367309570312,
"learning_rate": 1.257189669373664e-05,
"loss": 1263.9368,
"step": 4275
},
{
"epoch": 0.856,
"grad_norm": 221.49786376953125,
"learning_rate": 1.2402986099129765e-05,
"loss": 1250.1319,
"step": 4280
},
{
"epoch": 0.857,
"grad_norm": 228.9852752685547,
"learning_rate": 1.2235142846493308e-05,
"loss": 1251.3385,
"step": 4285
},
{
"epoch": 0.858,
"grad_norm": 200.24404907226562,
"learning_rate": 1.206836898094439e-05,
"loss": 1252.4089,
"step": 4290
},
{
"epoch": 0.859,
"grad_norm": 261.0468444824219,
"learning_rate": 1.1902666534569883e-05,
"loss": 1267.6674,
"step": 4295
},
{
"epoch": 0.86,
"grad_norm": 235.56564331054688,
"learning_rate": 1.1738037526401857e-05,
"loss": 1298.8137,
"step": 4300
},
{
"epoch": 0.861,
"grad_norm": 232.68536376953125,
"learning_rate": 1.1574483962392767e-05,
"loss": 1254.4432,
"step": 4305
},
{
"epoch": 0.862,
"grad_norm": 305.9205322265625,
"learning_rate": 1.1412007835391236e-05,
"loss": 1281.5415,
"step": 4310
},
{
"epoch": 0.863,
"grad_norm": 267.0234069824219,
"learning_rate": 1.1250611125117527e-05,
"loss": 1292.2422,
"step": 4315
},
{
"epoch": 0.864,
"grad_norm": 226.78778076171875,
"learning_rate": 1.1090295798139672e-05,
"loss": 1322.5876,
"step": 4320
},
{
"epoch": 0.865,
"grad_norm": 233.42002868652344,
"learning_rate": 1.093106380784934e-05,
"loss": 1246.4797,
"step": 4325
},
{
"epoch": 0.866,
"grad_norm": 322.5086669921875,
"learning_rate": 1.0772917094438051e-05,
"loss": 1267.4037,
"step": 4330
},
{
"epoch": 0.867,
"grad_norm": 309.5242004394531,
"learning_rate": 1.0615857584873623e-05,
"loss": 1267.5219,
"step": 4335
},
{
"epoch": 0.868,
"grad_norm": 232.40745544433594,
"learning_rate": 1.0459887192876594e-05,
"loss": 1262.018,
"step": 4340
},
{
"epoch": 0.869,
"grad_norm": 218.6525115966797,
"learning_rate": 1.0305007818897006e-05,
"loss": 1274.2437,
"step": 4345
},
{
"epoch": 0.87,
"grad_norm": 238.4595947265625,
"learning_rate": 1.0151221350091134e-05,
"loss": 1239.8048,
"step": 4350
},
{
"epoch": 0.871,
"grad_norm": 259.2078857421875,
"learning_rate": 9.998529660298539e-06,
"loss": 1225.8527,
"step": 4355
},
{
"epoch": 0.872,
"grad_norm": 246.32936096191406,
"learning_rate": 9.84693461001932e-06,
"loss": 1266.3213,
"step": 4360
},
{
"epoch": 0.873,
"grad_norm": 258.5328063964844,
"learning_rate": 9.696438046391288e-06,
"loss": 1291.4793,
"step": 4365
},
{
"epoch": 0.874,
"grad_norm": 248.4127655029297,
"learning_rate": 9.5470418031676e-06,
"loss": 1255.7428,
"step": 4370
},
{
"epoch": 0.875,
"grad_norm": 878.7903442382812,
"learning_rate": 9.398747700694322e-06,
"loss": 1290.1146,
"step": 4375
},
{
"epoch": 0.876,
"grad_norm": 263.7088317871094,
"learning_rate": 9.251557545888312e-06,
"loss": 1262.7498,
"step": 4380
},
{
"epoch": 0.877,
"grad_norm": 274.1349182128906,
"learning_rate": 9.105473132215125e-06,
"loss": 1245.4878,
"step": 4385
},
{
"epoch": 0.878,
"grad_norm": 244.28407287597656,
"learning_rate": 8.960496239667282e-06,
"loss": 1262.1215,
"step": 4390
},
{
"epoch": 0.879,
"grad_norm": 311.4893493652344,
"learning_rate": 8.816628634742441e-06,
"loss": 1249.9404,
"step": 4395
},
{
"epoch": 0.88,
"grad_norm": 258.85821533203125,
"learning_rate": 8.67387207042194e-06,
"loss": 1291.9261,
"step": 4400
},
{
"epoch": 0.881,
"grad_norm": 231.1480255126953,
"learning_rate": 8.532228286149501e-06,
"loss": 1271.2632,
"step": 4405
},
{
"epoch": 0.882,
"grad_norm": 211.44822692871094,
"learning_rate": 8.39169900780995e-06,
"loss": 1280.1188,
"step": 4410
},
{
"epoch": 0.883,
"grad_norm": 213.5997314453125,
"learning_rate": 8.252285947708139e-06,
"loss": 1269.4296,
"step": 4415
},
{
"epoch": 0.884,
"grad_norm": 352.0444641113281,
"learning_rate": 8.113990804548244e-06,
"loss": 1319.9928,
"step": 4420
},
{
"epoch": 0.885,
"grad_norm": 254.0896759033203,
"learning_rate": 7.976815263412963e-06,
"loss": 1255.2222,
"step": 4425
},
{
"epoch": 0.886,
"grad_norm": 307.3138427734375,
"learning_rate": 7.840760995742946e-06,
"loss": 1263.2812,
"step": 4430
},
{
"epoch": 0.887,
"grad_norm": 285.4303894042969,
"learning_rate": 7.7058296593165e-06,
"loss": 1254.4887,
"step": 4435
},
{
"epoch": 0.888,
"grad_norm": 261.50030517578125,
"learning_rate": 7.572022898229403e-06,
"loss": 1286.1383,
"step": 4440
},
{
"epoch": 0.889,
"grad_norm": 202.16885375976562,
"learning_rate": 7.439342342874789e-06,
"loss": 1278.7167,
"step": 4445
},
{
"epoch": 0.89,
"grad_norm": 257.2974548339844,
"learning_rate": 7.3077896099233765e-06,
"loss": 1234.5917,
"step": 4450
},
{
"epoch": 0.891,
"grad_norm": 318.0147705078125,
"learning_rate": 7.177366302303667e-06,
"loss": 1258.6867,
"step": 4455
},
{
"epoch": 0.892,
"grad_norm": 322.2470397949219,
"learning_rate": 7.048074009182548e-06,
"loss": 1322.0943,
"step": 4460
},
{
"epoch": 0.893,
"grad_norm": 228.141845703125,
"learning_rate": 6.919914305945774e-06,
"loss": 1219.8931,
"step": 4465
},
{
"epoch": 0.894,
"grad_norm": 230.3792266845703,
"learning_rate": 6.7928887541789055e-06,
"loss": 1299.9222,
"step": 4470
},
{
"epoch": 0.895,
"grad_norm": 228.13856506347656,
"learning_rate": 6.666998901648203e-06,
"loss": 1318.3175,
"step": 4475
},
{
"epoch": 0.896,
"grad_norm": 292.2648620605469,
"learning_rate": 6.542246282281772e-06,
"loss": 1285.2484,
"step": 4480
},
{
"epoch": 0.897,
"grad_norm": 214.20396423339844,
"learning_rate": 6.418632416150927e-06,
"loss": 1235.2114,
"step": 4485
},
{
"epoch": 0.898,
"grad_norm": 204.71218872070312,
"learning_rate": 6.296158809451602e-06,
"loss": 1280.9836,
"step": 4490
},
{
"epoch": 0.899,
"grad_norm": 364.37408447265625,
"learning_rate": 6.174826954486068e-06,
"loss": 1293.8603,
"step": 4495
},
{
"epoch": 0.9,
"grad_norm": 209.87579345703125,
"learning_rate": 6.054638329644657e-06,
"loss": 1225.0778,
"step": 4500
},
{
"epoch": 0.901,
"grad_norm": 277.7846374511719,
"learning_rate": 5.935594399387856e-06,
"loss": 1280.3837,
"step": 4505
},
{
"epoch": 0.902,
"grad_norm": 331.7242736816406,
"learning_rate": 5.8176966142283965e-06,
"loss": 1235.1035,
"step": 4510
},
{
"epoch": 0.903,
"grad_norm": 240.9756317138672,
"learning_rate": 5.700946410713548e-06,
"loss": 1231.7378,
"step": 4515
},
{
"epoch": 0.904,
"grad_norm": 214.67323303222656,
"learning_rate": 5.585345211407733e-06,
"loss": 1264.5803,
"step": 4520
},
{
"epoch": 0.905,
"grad_norm": 411.5826110839844,
"learning_rate": 5.470894424875062e-06,
"loss": 1305.6395,
"step": 4525
},
{
"epoch": 0.906,
"grad_norm": 245.5397186279297,
"learning_rate": 5.357595445662267e-06,
"loss": 1289.6215,
"step": 4530
},
{
"epoch": 0.907,
"grad_norm": 233.54295349121094,
"learning_rate": 5.245449654281631e-06,
"loss": 1258.7133,
"step": 4535
},
{
"epoch": 0.908,
"grad_norm": 220.2629852294922,
"learning_rate": 5.134458417194254e-06,
"loss": 1267.0936,
"step": 4540
},
{
"epoch": 0.909,
"grad_norm": 308.7809753417969,
"learning_rate": 5.024623086793323e-06,
"loss": 1287.339,
"step": 4545
},
{
"epoch": 0.91,
"grad_norm": 219.0414276123047,
"learning_rate": 4.915945001387667e-06,
"loss": 1276.7831,
"step": 4550
},
{
"epoch": 0.911,
"grad_norm": 223.63941955566406,
"learning_rate": 4.808425485185486e-06,
"loss": 1289.9722,
"step": 4555
},
{
"epoch": 0.912,
"grad_norm": 407.245849609375,
"learning_rate": 4.702065848278126e-06,
"loss": 1309.1957,
"step": 4560
},
{
"epoch": 0.913,
"grad_norm": 237.7763671875,
"learning_rate": 4.596867386624215e-06,
"loss": 1254.248,
"step": 4565
},
{
"epoch": 0.914,
"grad_norm": 415.60479736328125,
"learning_rate": 4.492831382033791e-06,
"loss": 1327.3475,
"step": 4570
},
{
"epoch": 0.915,
"grad_norm": 206.93702697753906,
"learning_rate": 4.389959102152774e-06,
"loss": 1270.9877,
"step": 4575
},
{
"epoch": 0.916,
"grad_norm": 295.16461181640625,
"learning_rate": 4.288251800447385e-06,
"loss": 1256.1207,
"step": 4580
},
{
"epoch": 0.917,
"grad_norm": 258.4662170410156,
"learning_rate": 4.187710716189042e-06,
"loss": 1279.1704,
"step": 4585
},
{
"epoch": 0.918,
"grad_norm": 216.54153442382812,
"learning_rate": 4.088337074439097e-06,
"loss": 1262.6107,
"step": 4590
},
{
"epoch": 0.919,
"grad_norm": 246.62554931640625,
"learning_rate": 3.990132086034026e-06,
"loss": 1216.6658,
"step": 4595
},
{
"epoch": 0.92,
"grad_norm": 369.988525390625,
"learning_rate": 3.893096947570618e-06,
"loss": 1267.589,
"step": 4600
},
{
"epoch": 0.921,
"grad_norm": 272.2461242675781,
"learning_rate": 3.797232841391407e-06,
"loss": 1246.4156,
"step": 4605
},
{
"epoch": 0.922,
"grad_norm": 209.1966552734375,
"learning_rate": 3.7025409355702976e-06,
"loss": 1253.9043,
"step": 4610
},
{
"epoch": 0.923,
"grad_norm": 310.2215270996094,
"learning_rate": 3.6090223838982417e-06,
"loss": 1284.1882,
"step": 4615
},
{
"epoch": 0.924,
"grad_norm": 218.298095703125,
"learning_rate": 3.516678325869316e-06,
"loss": 1265.9823,
"step": 4620
},
{
"epoch": 0.925,
"grad_norm": 270.3793029785156,
"learning_rate": 3.425509886666711e-06,
"loss": 1236.5802,
"step": 4625
},
{
"epoch": 0.926,
"grad_norm": 258.8869934082031,
"learning_rate": 3.3355181771490772e-06,
"loss": 1239.476,
"step": 4630
},
{
"epoch": 0.927,
"grad_norm": 261.8749694824219,
"learning_rate": 3.246704293837011e-06,
"loss": 1271.9206,
"step": 4635
},
{
"epoch": 0.928,
"grad_norm": 288.6155700683594,
"learning_rate": 3.1590693188996323e-06,
"loss": 1235.6616,
"step": 4640
},
{
"epoch": 0.929,
"grad_norm": 265.2295837402344,
"learning_rate": 3.072614320141487e-06,
"loss": 1225.8398,
"step": 4645
},
{
"epoch": 0.93,
"grad_norm": 261.2476806640625,
"learning_rate": 2.9873403509894203e-06,
"loss": 1281.0352,
"step": 4650
},
{
"epoch": 0.931,
"grad_norm": 226.79232788085938,
"learning_rate": 2.9032484504798452e-06,
"loss": 1283.1519,
"step": 4655
},
{
"epoch": 0.932,
"grad_norm": 207.0574951171875,
"learning_rate": 2.8203396432460506e-06,
"loss": 1214.1301,
"step": 4660
},
{
"epoch": 0.933,
"grad_norm": 214.75564575195312,
"learning_rate": 2.738614939505646e-06,
"loss": 1269.1134,
"step": 4665
},
{
"epoch": 0.934,
"grad_norm": 301.5157165527344,
"learning_rate": 2.6580753350484046e-06,
"loss": 1246.647,
"step": 4670
},
{
"epoch": 0.935,
"grad_norm": 239.28280639648438,
"learning_rate": 2.5787218112239496e-06,
"loss": 1232.1958,
"step": 4675
},
{
"epoch": 0.936,
"grad_norm": 300.007568359375,
"learning_rate": 2.5005553349299547e-06,
"loss": 1283.4491,
"step": 4680
},
{
"epoch": 0.937,
"grad_norm": 236.75270080566406,
"learning_rate": 2.4235768586002517e-06,
"loss": 1253.773,
"step": 4685
},
{
"epoch": 0.938,
"grad_norm": 221.49700927734375,
"learning_rate": 2.3477873201932734e-06,
"loss": 1259.7163,
"step": 4690
},
{
"epoch": 0.939,
"grad_norm": 225.40213012695312,
"learning_rate": 2.273187643180652e-06,
"loss": 1232.4826,
"step": 4695
},
{
"epoch": 0.94,
"grad_norm": 254.2238006591797,
"learning_rate": 2.1997787365358958e-06,
"loss": 1282.798,
"step": 4700
},
{
"epoch": 0.941,
"grad_norm": 259.62103271484375,
"learning_rate": 2.1275614947233624e-06,
"loss": 1243.1798,
"step": 4705
},
{
"epoch": 0.942,
"grad_norm": 210.20333862304688,
"learning_rate": 2.0565367976873584e-06,
"loss": 1273.8919,
"step": 4710
},
{
"epoch": 0.943,
"grad_norm": 249.57077026367188,
"learning_rate": 1.986705510841402e-06,
"loss": 1265.1047,
"step": 4715
},
{
"epoch": 0.944,
"grad_norm": 204.94834899902344,
"learning_rate": 1.918068485057689e-06,
"loss": 1255.6227,
"step": 4720
},
{
"epoch": 0.945,
"grad_norm": 257.9980773925781,
"learning_rate": 1.8506265566567094e-06,
"loss": 1275.9813,
"step": 4725
},
{
"epoch": 0.946,
"grad_norm": 370.14642333984375,
"learning_rate": 1.7843805473970798e-06,
"loss": 1321.8407,
"step": 4730
},
{
"epoch": 0.947,
"grad_norm": 252.0769500732422,
"learning_rate": 1.719331264465529e-06,
"loss": 1282.7529,
"step": 4735
},
{
"epoch": 0.948,
"grad_norm": 267.9647521972656,
"learning_rate": 1.6554795004670388e-06,
"loss": 1274.7761,
"step": 4740
},
{
"epoch": 0.949,
"grad_norm": 461.8729553222656,
"learning_rate": 1.5928260334151845e-06,
"loss": 1306.7576,
"step": 4745
},
{
"epoch": 0.95,
"grad_norm": 334.6704406738281,
"learning_rate": 1.5313716267226996e-06,
"loss": 1318.161,
"step": 4750
},
{
"epoch": 0.951,
"grad_norm": 225.33218383789062,
"learning_rate": 1.4711170291921484e-06,
"loss": 1270.5868,
"step": 4755
},
{
"epoch": 0.952,
"grad_norm": 223.90199279785156,
"learning_rate": 1.412062975006767e-06,
"loss": 1247.6047,
"step": 4760
},
{
"epoch": 0.953,
"grad_norm": 262.23760986328125,
"learning_rate": 1.3542101837215826e-06,
"loss": 1300.5552,
"step": 4765
},
{
"epoch": 0.954,
"grad_norm": 443.9941711425781,
"learning_rate": 1.2975593602545965e-06,
"loss": 1329.1407,
"step": 4770
},
{
"epoch": 0.955,
"grad_norm": 265.2261047363281,
"learning_rate": 1.2421111948782149e-06,
"loss": 1278.8901,
"step": 4775
},
{
"epoch": 0.956,
"grad_norm": 242.17044067382812,
"learning_rate": 1.1878663632108322e-06,
"loss": 1227.1126,
"step": 4780
},
{
"epoch": 0.957,
"grad_norm": 218.51039123535156,
"learning_rate": 1.134825526208605e-06,
"loss": 1267.375,
"step": 4785
},
{
"epoch": 0.958,
"grad_norm": 213.923828125,
"learning_rate": 1.0829893301573913e-06,
"loss": 1239.249,
"step": 4790
},
{
"epoch": 0.959,
"grad_norm": 225.5285186767578,
"learning_rate": 1.0323584066648795e-06,
"loss": 1225.3078,
"step": 4795
},
{
"epoch": 0.96,
"grad_norm": 358.7773132324219,
"learning_rate": 9.829333726529056e-07,
"loss": 1257.9765,
"step": 4800
},
{
"epoch": 0.961,
"grad_norm": 220.1189422607422,
"learning_rate": 9.347148303499142e-07,
"loss": 1237.8258,
"step": 4805
},
{
"epoch": 0.962,
"grad_norm": 1254.54296875,
"learning_rate": 8.877033672835988e-07,
"loss": 1225.979,
"step": 4810
},
{
"epoch": 0.963,
"grad_norm": 545.1520385742188,
"learning_rate": 8.418995562738285e-07,
"loss": 1219.9365,
"step": 4815
},
{
"epoch": 0.964,
"grad_norm": 834.0431518554688,
"learning_rate": 7.973039554255768e-07,
"loss": 1358.6379,
"step": 4820
},
{
"epoch": 0.965,
"grad_norm": 243.01600646972656,
"learning_rate": 7.539171081221596e-07,
"loss": 1317.7663,
"step": 4825
},
{
"epoch": 0.966,
"grad_norm": 255.29454040527344,
"learning_rate": 7.117395430186414e-07,
"loss": 1281.7281,
"step": 4830
},
{
"epoch": 0.967,
"grad_norm": 487.57781982421875,
"learning_rate": 6.707717740353059e-07,
"loss": 1308.0234,
"step": 4835
},
{
"epoch": 0.968,
"grad_norm": 236.874755859375,
"learning_rate": 6.310143003515179e-07,
"loss": 1246.869,
"step": 4840
},
{
"epoch": 0.969,
"grad_norm": 252.80709838867188,
"learning_rate": 5.924676063995382e-07,
"loss": 1261.783,
"step": 4845
},
{
"epoch": 0.97,
"grad_norm": 222.19398498535156,
"learning_rate": 5.551321618586736e-07,
"loss": 1254.4523,
"step": 4850
},
{
"epoch": 0.971,
"grad_norm": 242.57333374023438,
"learning_rate": 5.190084216495361e-07,
"loss": 1240.5143,
"step": 4855
},
{
"epoch": 0.972,
"grad_norm": 256.2544860839844,
"learning_rate": 4.840968259284817e-07,
"loss": 1402.7913,
"step": 4860
},
{
"epoch": 0.973,
"grad_norm": 269.0944519042969,
"learning_rate": 4.503978000823028e-07,
"loss": 1246.179,
"step": 4865
},
{
"epoch": 0.974,
"grad_norm": 306.2163391113281,
"learning_rate": 4.179117547229883e-07,
"loss": 1296.239,
"step": 4870
},
{
"epoch": 0.975,
"grad_norm": 247.04510498046875,
"learning_rate": 3.866390856827495e-07,
"loss": 1274.2123,
"step": 4875
},
{
"epoch": 0.976,
"grad_norm": 240.17337036132812,
"learning_rate": 3.565801740092023e-07,
"loss": 1253.9863,
"step": 4880
},
{
"epoch": 0.977,
"grad_norm": 285.96673583984375,
"learning_rate": 3.277353859606813e-07,
"loss": 1266.5,
"step": 4885
},
{
"epoch": 0.978,
"grad_norm": 255.36180114746094,
"learning_rate": 3.001050730018218e-07,
"loss": 1263.1057,
"step": 4890
},
{
"epoch": 0.979,
"grad_norm": 243.5221710205078,
"learning_rate": 2.73689571799296e-07,
"loss": 1267.1412,
"step": 4895
},
{
"epoch": 0.98,
"grad_norm": 235.5934600830078,
"learning_rate": 2.484892042176279e-07,
"loss": 1281.6612,
"step": 4900
},
{
"epoch": 0.981,
"grad_norm": 282.17218017578125,
"learning_rate": 2.2450427731534053e-07,
"loss": 1256.7972,
"step": 4905
},
{
"epoch": 0.982,
"grad_norm": 297.5190124511719,
"learning_rate": 2.017350833412146e-07,
"loss": 1281.9959,
"step": 4910
},
{
"epoch": 0.983,
"grad_norm": 253.92880249023438,
"learning_rate": 1.8018189973069143e-07,
"loss": 1270.2993,
"step": 4915
},
{
"epoch": 0.984,
"grad_norm": 250.03184509277344,
"learning_rate": 1.598449891024978e-07,
"loss": 1256.2616,
"step": 4920
},
{
"epoch": 0.985,
"grad_norm": 219.2830810546875,
"learning_rate": 1.4072459925548177e-07,
"loss": 1259.83,
"step": 4925
},
{
"epoch": 0.986,
"grad_norm": 234.6300811767578,
"learning_rate": 1.2282096316554858e-07,
"loss": 1282.4576,
"step": 4930
},
{
"epoch": 0.987,
"grad_norm": 240.56991577148438,
"learning_rate": 1.0613429898287398e-07,
"loss": 1263.2266,
"step": 4935
},
{
"epoch": 0.988,
"grad_norm": 283.3948059082031,
"learning_rate": 9.066481002918403e-08,
"loss": 1262.1501,
"step": 4940
},
{
"epoch": 0.989,
"grad_norm": 219.71871948242188,
"learning_rate": 7.641268479531283e-08,
"loss": 1254.484,
"step": 4945
},
{
"epoch": 0.99,
"grad_norm": 224.98611450195312,
"learning_rate": 6.337809693891527e-08,
"loss": 1225.1323,
"step": 4950
},
{
"epoch": 0.991,
"grad_norm": 254.57723999023438,
"learning_rate": 5.1561205282335547e-08,
"loss": 1245.898,
"step": 4955
},
{
"epoch": 0.992,
"grad_norm": 255.16879272460938,
"learning_rate": 4.096215381066415e-08,
"loss": 1247.1624,
"step": 4960
},
{
"epoch": 0.993,
"grad_norm": 236.37399291992188,
"learning_rate": 3.1581071670006015e-08,
"loss": 1261.8342,
"step": 4965
},
{
"epoch": 0.994,
"grad_norm": 301.8701477050781,
"learning_rate": 2.3418073165870636e-08,
"loss": 1263.4551,
"step": 4970
},
{
"epoch": 0.995,
"grad_norm": 220.14791870117188,
"learning_rate": 1.6473257761828732e-08,
"loss": 1276.9561,
"step": 4975
},
{
"epoch": 0.996,
"grad_norm": 357.2049255371094,
"learning_rate": 1.074671007825767e-08,
"loss": 1334.4171,
"step": 4980
},
{
"epoch": 0.997,
"grad_norm": 284.9293212890625,
"learning_rate": 6.238499891353389e-09,
"loss": 1298.0241,
"step": 4985
},
{
"epoch": 0.998,
"grad_norm": 443.5886535644531,
"learning_rate": 2.948682132208891e-09,
"loss": 1257.9468,
"step": 4990
},
{
"epoch": 0.999,
"grad_norm": 337.0032958984375,
"learning_rate": 8.772968862369446e-10,
"loss": 1241.2061,
"step": 4995
},
{
"epoch": 1.0,
"grad_norm": 270.656005859375,
"learning_rate": 2.4369392592760164e-11,
"loss": 1279.8621,
"step": 5000
},
{
"epoch": 1.0,
"step": 5000,
"total_flos": 7.022422523904e+16,
"train_loss": 1497.3410962890625,
"train_runtime": 13142.4691,
"train_samples_per_second": 12.174,
"train_steps_per_second": 0.38
}
],
"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": 5266.7001953125,
"learning_rate": 1.6000000000000001e-06,
"loss": 3782.8074,
"step": 5
},
{
"epoch": 0.002,
"grad_norm": 4745.4599609375,
"learning_rate": 3.6e-06,
"loss": 3699.0461,
"step": 10
},
{
"epoch": 0.003,
"grad_norm": 4176.05859375,
"learning_rate": 5.600000000000001e-06,
"loss": 3555.8453,
"step": 15
},
{
"epoch": 0.004,
"grad_norm": 3472.902587890625,
"learning_rate": 7.6e-06,
"loss": 3356.0918,
"step": 20
},
{
"epoch": 0.005,
"grad_norm": 2188.70166015625,
"learning_rate": 9.600000000000001e-06,
"loss": 3196.0379,
"step": 25
},
{
"epoch": 0.006,
"grad_norm": 1210.4024658203125,
"learning_rate": 1.16e-05,
"loss": 3019.327,
"step": 30
},
{
"epoch": 0.007,
"grad_norm": 1698.2469482421875,
"learning_rate": 1.3600000000000002e-05,
"loss": 2985.2305,
"step": 35
},
{
"epoch": 0.008,
"grad_norm": 781.6577758789062,
"learning_rate": 1.56e-05,
"loss": 2913.9523,
"step": 40
},
{
"epoch": 0.009,
"grad_norm": 915.7643432617188,
"learning_rate": 1.76e-05,
"loss": 2852.7895,
"step": 45
},
{
"epoch": 0.01,
"grad_norm": 642.8707885742188,
"learning_rate": 1.9600000000000002e-05,
"loss": 2772.2295,
"step": 50
},
{
"epoch": 0.011,
"grad_norm": 682.644287109375,
"learning_rate": 2.16e-05,
"loss": 2712.7576,
"step": 55
},
{
"epoch": 0.012,
"grad_norm": 601.84033203125,
"learning_rate": 2.36e-05,
"loss": 2632.6984,
"step": 60
},
{
"epoch": 0.013,
"grad_norm": 554.9131469726562,
"learning_rate": 2.5600000000000002e-05,
"loss": 2558.6363,