{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.4,
"eval_steps": 500,
"global_step": 2000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.001,
"grad_norm": 721.6266479492188,
"learning_rate": 1.6000000000000001e-06,
"loss": 688.1156,
"step": 5
},
{
"epoch": 0.002,
"grad_norm": 544.0831298828125,
"learning_rate": 3.6e-06,
"loss": 692.814,
"step": 10
},
{
"epoch": 0.003,
"grad_norm": 435.138427734375,
"learning_rate": 5.600000000000001e-06,
"loss": 675.4897,
"step": 15
},
{
"epoch": 0.004,
"grad_norm": 231.80264282226562,
"learning_rate": 7.6e-06,
"loss": 678.7521,
"step": 20
},
{
"epoch": 0.005,
"grad_norm": 265.94085693359375,
"learning_rate": 9.600000000000001e-06,
"loss": 677.9869,
"step": 25
},
{
"epoch": 0.006,
"grad_norm": 286.4078063964844,
"learning_rate": 1.16e-05,
"loss": 641.2654,
"step": 30
},
{
"epoch": 0.007,
"grad_norm": 200.6824188232422,
"learning_rate": 1.3600000000000002e-05,
"loss": 623.5658,
"step": 35
},
{
"epoch": 0.008,
"grad_norm": 190.13320922851562,
"learning_rate": 1.56e-05,
"loss": 603.631,
"step": 40
},
{
"epoch": 0.009,
"grad_norm": 191.35208129882812,
"learning_rate": 1.76e-05,
"loss": 600.4304,
"step": 45
},
{
"epoch": 0.01,
"grad_norm": 234.3683319091797,
"learning_rate": 1.9600000000000002e-05,
"loss": 612.607,
"step": 50
},
{
"epoch": 0.011,
"grad_norm": 222.86151123046875,
"learning_rate": 2.16e-05,
"loss": 559.0464,
"step": 55
},
{
"epoch": 0.012,
"grad_norm": 184.71469116210938,
"learning_rate": 2.36e-05,
"loss": 552.2791,
"step": 60
},
{
"epoch": 0.013,
"grad_norm": 196.4359893798828,
"learning_rate": 2.5600000000000002e-05,
"loss": 541.9889,
"step": 65
},
{
"epoch": 0.014,
"grad_norm": 239.24853515625,
"learning_rate": 2.7600000000000003e-05,
"loss": 511.0809,
"step": 70
},
{
"epoch": 0.015,
"grad_norm": 179.1760711669922,
"learning_rate": 2.96e-05,
"loss": 485.0814,
"step": 75
},
{
"epoch": 0.016,
"grad_norm": 192.81739807128906,
"learning_rate": 3.16e-05,
"loss": 459.9401,
"step": 80
},
{
"epoch": 0.017,
"grad_norm": 156.54107666015625,
"learning_rate": 3.3600000000000004e-05,
"loss": 470.2632,
"step": 85
},
{
"epoch": 0.018,
"grad_norm": 147.86322021484375,
"learning_rate": 3.56e-05,
"loss": 446.1228,
"step": 90
},
{
"epoch": 0.019,
"grad_norm": 123.13829040527344,
"learning_rate": 3.76e-05,
"loss": 440.1239,
"step": 95
},
{
"epoch": 0.02,
"grad_norm": 149.69171142578125,
"learning_rate": 3.960000000000001e-05,
"loss": 413.2798,
"step": 100
},
{
"epoch": 0.021,
"grad_norm": 160.90667724609375,
"learning_rate": 4.16e-05,
"loss": 405.9687,
"step": 105
},
{
"epoch": 0.022,
"grad_norm": 135.00265502929688,
"learning_rate": 4.36e-05,
"loss": 391.3724,
"step": 110
},
{
"epoch": 0.023,
"grad_norm": 152.46453857421875,
"learning_rate": 4.5600000000000004e-05,
"loss": 377.1108,
"step": 115
},
{
"epoch": 0.024,
"grad_norm": 104.59321594238281,
"learning_rate": 4.76e-05,
"loss": 377.6848,
"step": 120
},
{
"epoch": 0.025,
"grad_norm": 89.6296615600586,
"learning_rate": 4.96e-05,
"loss": 362.3638,
"step": 125
},
{
"epoch": 0.026,
"grad_norm": 112.06822967529297,
"learning_rate": 5.16e-05,
"loss": 361.9335,
"step": 130
},
{
"epoch": 0.027,
"grad_norm": 156.09202575683594,
"learning_rate": 5.360000000000001e-05,
"loss": 357.1528,
"step": 135
},
{
"epoch": 0.028,
"grad_norm": 206.53880310058594,
"learning_rate": 5.560000000000001e-05,
"loss": 354.049,
"step": 140
},
{
"epoch": 0.029,
"grad_norm": 108.23499298095703,
"learning_rate": 5.76e-05,
"loss": 343.5889,
"step": 145
},
{
"epoch": 0.03,
"grad_norm": 75.28748321533203,
"learning_rate": 5.96e-05,
"loss": 347.4616,
"step": 150
},
{
"epoch": 0.031,
"grad_norm": 83.68946075439453,
"learning_rate": 6.16e-05,
"loss": 329.7481,
"step": 155
},
{
"epoch": 0.032,
"grad_norm": 83.15459442138672,
"learning_rate": 6.36e-05,
"loss": 337.4002,
"step": 160
},
{
"epoch": 0.033,
"grad_norm": 76.86617279052734,
"learning_rate": 6.560000000000001e-05,
"loss": 341.4927,
"step": 165
},
{
"epoch": 0.034,
"grad_norm": 98.58145141601562,
"learning_rate": 6.76e-05,
"loss": 277.4808,
"step": 170
},
{
"epoch": 0.035,
"grad_norm": 131.67160034179688,
"learning_rate": 6.96e-05,
"loss": 270.1535,
"step": 175
},
{
"epoch": 0.036,
"grad_norm": 115.2589340209961,
"learning_rate": 7.16e-05,
"loss": 313.2915,
"step": 180
},
{
"epoch": 0.037,
"grad_norm": 95.61432647705078,
"learning_rate": 7.36e-05,
"loss": 318.9492,
"step": 185
},
{
"epoch": 0.038,
"grad_norm": 94.05854797363281,
"learning_rate": 7.560000000000001e-05,
"loss": 331.3637,
"step": 190
},
{
"epoch": 0.039,
"grad_norm": 107.30905151367188,
"learning_rate": 7.76e-05,
"loss": 319.6421,
"step": 195
},
{
"epoch": 0.04,
"grad_norm": 79.12100219726562,
"learning_rate": 7.960000000000001e-05,
"loss": 294.7,
"step": 200
},
{
"epoch": 0.041,
"grad_norm": 75.0265121459961,
"learning_rate": 8.16e-05,
"loss": 334.8542,
"step": 205
},
{
"epoch": 0.042,
"grad_norm": 115.47676086425781,
"learning_rate": 8.36e-05,
"loss": 330.0034,
"step": 210
},
{
"epoch": 0.043,
"grad_norm": 68.13713073730469,
"learning_rate": 8.560000000000001e-05,
"loss": 315.0901,
"step": 215
},
{
"epoch": 0.044,
"grad_norm": 78.96424102783203,
"learning_rate": 8.76e-05,
"loss": 320.4563,
"step": 220
},
{
"epoch": 0.045,
"grad_norm": 90.30127716064453,
"learning_rate": 8.960000000000001e-05,
"loss": 320.057,
"step": 225
},
{
"epoch": 0.046,
"grad_norm": 84.05204772949219,
"learning_rate": 9.16e-05,
"loss": 330.0475,
"step": 230
},
{
"epoch": 0.047,
"grad_norm": 206.4952392578125,
"learning_rate": 9.360000000000001e-05,
"loss": 330.0047,
"step": 235
},
{
"epoch": 0.048,
"grad_norm": 91.48888397216797,
"learning_rate": 9.56e-05,
"loss": 318.4327,
"step": 240
},
{
"epoch": 0.049,
"grad_norm": 64.62387084960938,
"learning_rate": 9.76e-05,
"loss": 323.021,
"step": 245
},
{
"epoch": 0.05,
"grad_norm": 78.25593566894531,
"learning_rate": 9.960000000000001e-05,
"loss": 282.2581,
"step": 250
},
{
"epoch": 0.051,
"grad_norm": 104.33906555175781,
"learning_rate": 0.0001016,
"loss": 308.8392,
"step": 255
},
{
"epoch": 0.052,
"grad_norm": 100.70447540283203,
"learning_rate": 0.00010360000000000001,
"loss": 314.7235,
"step": 260
},
{
"epoch": 0.053,
"grad_norm": 80.67839050292969,
"learning_rate": 0.0001056,
"loss": 321.3608,
"step": 265
},
{
"epoch": 0.054,
"grad_norm": 87.63465881347656,
"learning_rate": 0.00010760000000000001,
"loss": 261.4398,
"step": 270
},
{
"epoch": 0.055,
"grad_norm": 92.7296371459961,
"learning_rate": 0.00010960000000000001,
"loss": 324.0834,
"step": 275
},
{
"epoch": 0.056,
"grad_norm": 87.1913070678711,
"learning_rate": 0.00011160000000000002,
"loss": 329.3604,
"step": 280
},
{
"epoch": 0.057,
"grad_norm": 79.63569641113281,
"learning_rate": 0.0001136,
"loss": 334.0321,
"step": 285
},
{
"epoch": 0.058,
"grad_norm": 126.32538604736328,
"learning_rate": 0.00011559999999999999,
"loss": 329.6052,
"step": 290
},
{
"epoch": 0.059,
"grad_norm": 94.25569152832031,
"learning_rate": 0.0001176,
"loss": 287.6086,
"step": 295
},
{
"epoch": 0.06,
"grad_norm": 72.69226837158203,
"learning_rate": 0.00011960000000000001,
"loss": 300.411,
"step": 300
},
{
"epoch": 0.061,
"grad_norm": 58.96094512939453,
"learning_rate": 0.0001216,
"loss": 278.935,
"step": 305
},
{
"epoch": 0.062,
"grad_norm": 99.136474609375,
"learning_rate": 0.0001236,
"loss": 328.2397,
"step": 310
},
{
"epoch": 0.063,
"grad_norm": 132.49497985839844,
"learning_rate": 0.00012560000000000002,
"loss": 281.8964,
"step": 315
},
{
"epoch": 0.064,
"grad_norm": 104.87638854980469,
"learning_rate": 0.0001276,
"loss": 260.9644,
"step": 320
},
{
"epoch": 0.065,
"grad_norm": 159.1914825439453,
"learning_rate": 0.0001296,
"loss": 287.5366,
"step": 325
},
{
"epoch": 0.066,
"grad_norm": 110.79325866699219,
"learning_rate": 0.0001316,
"loss": 321.1016,
"step": 330
},
{
"epoch": 0.067,
"grad_norm": 88.9395751953125,
"learning_rate": 0.00013360000000000002,
"loss": 287.1829,
"step": 335
},
{
"epoch": 0.068,
"grad_norm": 84.5783920288086,
"learning_rate": 0.00013560000000000002,
"loss": 321.4262,
"step": 340
},
{
"epoch": 0.069,
"grad_norm": 70.5678939819336,
"learning_rate": 0.00013759999999999998,
"loss": 321.5253,
"step": 345
},
{
"epoch": 0.07,
"grad_norm": 108.30426025390625,
"learning_rate": 0.0001396,
"loss": 308.183,
"step": 350
},
{
"epoch": 0.071,
"grad_norm": 102.5810775756836,
"learning_rate": 0.0001416,
"loss": 318.504,
"step": 355
},
{
"epoch": 0.072,
"grad_norm": 75.2052993774414,
"learning_rate": 0.0001436,
"loss": 301.0554,
"step": 360
},
{
"epoch": 0.073,
"grad_norm": 120.83828735351562,
"learning_rate": 0.00014560000000000002,
"loss": 279.8772,
"step": 365
},
{
"epoch": 0.074,
"grad_norm": 63.114463806152344,
"learning_rate": 0.0001476,
"loss": 323.9014,
"step": 370
},
{
"epoch": 0.075,
"grad_norm": 96.447265625,
"learning_rate": 0.0001496,
"loss": 309.335,
"step": 375
},
{
"epoch": 0.076,
"grad_norm": 105.62726593017578,
"learning_rate": 0.0001516,
"loss": 314.6242,
"step": 380
},
{
"epoch": 0.077,
"grad_norm": 74.49201202392578,
"learning_rate": 0.00015360000000000002,
"loss": 282.4204,
"step": 385
},
{
"epoch": 0.078,
"grad_norm": 63.78548812866211,
"learning_rate": 0.00015560000000000001,
"loss": 308.0999,
"step": 390
},
{
"epoch": 0.079,
"grad_norm": 75.9488525390625,
"learning_rate": 0.0001576,
"loss": 314.7893,
"step": 395
},
{
"epoch": 0.08,
"grad_norm": 63.09105682373047,
"learning_rate": 0.0001596,
"loss": 311.3621,
"step": 400
},
{
"epoch": 0.081,
"grad_norm": 50.02682876586914,
"learning_rate": 0.00016160000000000002,
"loss": 261.298,
"step": 405
},
{
"epoch": 0.082,
"grad_norm": 77.55859375,
"learning_rate": 0.0001636,
"loss": 286.2955,
"step": 410
},
{
"epoch": 0.083,
"grad_norm": 68.19657897949219,
"learning_rate": 0.0001656,
"loss": 301.9222,
"step": 415
},
{
"epoch": 0.084,
"grad_norm": 97.95561981201172,
"learning_rate": 0.0001676,
"loss": 283.372,
"step": 420
},
{
"epoch": 0.085,
"grad_norm": 79.69905090332031,
"learning_rate": 0.0001696,
"loss": 315.9672,
"step": 425
},
{
"epoch": 0.086,
"grad_norm": 104.90116119384766,
"learning_rate": 0.0001716,
"loss": 283.4394,
"step": 430
},
{
"epoch": 0.087,
"grad_norm": 66.73443603515625,
"learning_rate": 0.00017360000000000002,
"loss": 319.9743,
"step": 435
},
{
"epoch": 0.088,
"grad_norm": 87.68392181396484,
"learning_rate": 0.0001756,
"loss": 313.2186,
"step": 440
},
{
"epoch": 0.089,
"grad_norm": 120.080322265625,
"learning_rate": 0.0001776,
"loss": 310.0703,
"step": 445
},
{
"epoch": 0.09,
"grad_norm": 205.61668395996094,
"learning_rate": 0.0001796,
"loss": 306.0805,
"step": 450
},
{
"epoch": 0.091,
"grad_norm": 128.75393676757812,
"learning_rate": 0.00018160000000000002,
"loss": 308.8566,
"step": 455
},
{
"epoch": 0.092,
"grad_norm": 86.65980529785156,
"learning_rate": 0.00018360000000000002,
"loss": 315.4491,
"step": 460
},
{
"epoch": 0.093,
"grad_norm": 149.56349182128906,
"learning_rate": 0.0001856,
"loss": 323.8131,
"step": 465
},
{
"epoch": 0.094,
"grad_norm": 76.364013671875,
"learning_rate": 0.0001876,
"loss": 310.2711,
"step": 470
},
{
"epoch": 0.095,
"grad_norm": 91.30841827392578,
"learning_rate": 0.0001896,
"loss": 284.6678,
"step": 475
},
{
"epoch": 0.096,
"grad_norm": 125.94243621826172,
"learning_rate": 0.0001916,
"loss": 291.3752,
"step": 480
},
{
"epoch": 0.097,
"grad_norm": 94.07376098632812,
"learning_rate": 0.00019360000000000002,
"loss": 316.8861,
"step": 485
},
{
"epoch": 0.098,
"grad_norm": 86.89104461669922,
"learning_rate": 0.0001956,
"loss": 300.4785,
"step": 490
},
{
"epoch": 0.099,
"grad_norm": 61.397056579589844,
"learning_rate": 0.0001976,
"loss": 310.8486,
"step": 495
},
{
"epoch": 0.1,
"grad_norm": 93.50562286376953,
"learning_rate": 0.0001996,
"loss": 309.3899,
"step": 500
},
{
"epoch": 0.101,
"grad_norm": 124.1824951171875,
"learning_rate": 0.00019999961008995606,
"loss": 321.2337,
"step": 505
},
{
"epoch": 0.102,
"grad_norm": 85.46344757080078,
"learning_rate": 0.0001999980260856137,
"loss": 306.5626,
"step": 510
},
{
"epoch": 0.103,
"grad_norm": 63.943416595458984,
"learning_rate": 0.000199995223636881,
"loss": 291.7199,
"step": 515
},
{
"epoch": 0.104,
"grad_norm": 121.62495422363281,
"learning_rate": 0.00019999120277790477,
"loss": 319.896,
"step": 520
},
{
"epoch": 0.105,
"grad_norm": 132.1036834716797,
"learning_rate": 0.00019998596355767805,
"loss": 306.7945,
"step": 525
},
{
"epoch": 0.106,
"grad_norm": 74.25767517089844,
"learning_rate": 0.000199979506040039,
"loss": 309.2333,
"step": 530
},
{
"epoch": 0.107,
"grad_norm": 94.15550994873047,
"learning_rate": 0.00019997183030367048,
"loss": 301.1334,
"step": 535
},
{
"epoch": 0.108,
"grad_norm": 102.22862243652344,
"learning_rate": 0.00019996293644209887,
"loss": 306.8577,
"step": 540
},
{
"epoch": 0.109,
"grad_norm": 55.33135986328125,
"learning_rate": 0.0001999528245636931,
"loss": 308.3073,
"step": 545
},
{
"epoch": 0.11,
"grad_norm": 85.55260467529297,
"learning_rate": 0.00019994149479166324,
"loss": 279.048,
"step": 550
},
{
"epoch": 0.111,
"grad_norm": 75.02954864501953,
"learning_rate": 0.00019992894726405893,
"loss": 242.1927,
"step": 555
},
{
"epoch": 0.112,
"grad_norm": 112.45849609375,
"learning_rate": 0.00019991518213376787,
"loss": 309.9958,
"step": 560
},
{
"epoch": 0.113,
"grad_norm": 72.08016967773438,
"learning_rate": 0.00019990019956851382,
"loss": 294.3192,
"step": 565
},
{
"epoch": 0.114,
"grad_norm": 78.4118423461914,
"learning_rate": 0.0001998839997508546,
"loss": 302.9115,
"step": 570
},
{
"epoch": 0.115,
"grad_norm": 69.09600830078125,
"learning_rate": 0.00019986658287817987,
"loss": 293.0752,
"step": 575
},
{
"epoch": 0.116,
"grad_norm": 90.061279296875,
"learning_rate": 0.00019984794916270876,
"loss": 273.8636,
"step": 580
},
{
"epoch": 0.117,
"grad_norm": 65.658203125,
"learning_rate": 0.00019982809883148722,
"loss": 290.0099,
"step": 585
},
{
"epoch": 0.118,
"grad_norm": 88.89976501464844,
"learning_rate": 0.00019980703212638522,
"loss": 268.4154,
"step": 590
},
{
"epoch": 0.119,
"grad_norm": 91.8514175415039,
"learning_rate": 0.00019978474930409395,
"loss": 295.2028,
"step": 595
},
{
"epoch": 0.12,
"grad_norm": 76.07625579833984,
"learning_rate": 0.00019976125063612252,
"loss": 290.6098,
"step": 600
},
{
"epoch": 0.121,
"grad_norm": 107.67623901367188,
"learning_rate": 0.00019973653640879485,
"loss": 296.3092,
"step": 605
},
{
"epoch": 0.122,
"grad_norm": 58.070045471191406,
"learning_rate": 0.00019971060692324598,
"loss": 288.3709,
"step": 610
},
{
"epoch": 0.123,
"grad_norm": 71.92018127441406,
"learning_rate": 0.00019968346249541846,
"loss": 290.0689,
"step": 615
},
{
"epoch": 0.124,
"grad_norm": 62.50072479248047,
"learning_rate": 0.00019965510345605866,
"loss": 282.9642,
"step": 620
},
{
"epoch": 0.125,
"grad_norm": 60.57828140258789,
"learning_rate": 0.0001996255301507125,
"loss": 297.7481,
"step": 625
},
{
"epoch": 0.126,
"grad_norm": 86.51339721679688,
"learning_rate": 0.00019959474293972129,
"loss": 299.4869,
"step": 630
},
{
"epoch": 0.127,
"grad_norm": 59.24555969238281,
"learning_rate": 0.00019956274219821757,
"loss": 278.622,
"step": 635
},
{
"epoch": 0.128,
"grad_norm": 66.11981201171875,
"learning_rate": 0.00019952952831612026,
"loss": 300.1323,
"step": 640
},
{
"epoch": 0.129,
"grad_norm": 66.8055648803711,
"learning_rate": 0.00019949510169813003,
"loss": 311.9121,
"step": 645
},
{
"epoch": 0.13,
"grad_norm": 50.631351470947266,
"learning_rate": 0.00019945946276372434,
"loss": 285.0186,
"step": 650
},
{
"epoch": 0.131,
"grad_norm": 96.61212158203125,
"learning_rate": 0.00019942261194715236,
"loss": 275.0642,
"step": 655
},
{
"epoch": 0.132,
"grad_norm": 49.41533660888672,
"learning_rate": 0.00019938454969742968,
"loss": 303.2291,
"step": 660
},
{
"epoch": 0.133,
"grad_norm": 88.05651092529297,
"learning_rate": 0.00019934527647833276,
"loss": 296.7646,
"step": 665
},
{
"epoch": 0.134,
"grad_norm": 68.4341812133789,
"learning_rate": 0.00019930479276839344,
"loss": 304.5721,
"step": 670
},
{
"epoch": 0.135,
"grad_norm": 62.958675384521484,
"learning_rate": 0.0001992630990608929,
"loss": 290.3239,
"step": 675
},
{
"epoch": 0.136,
"grad_norm": 117.90381622314453,
"learning_rate": 0.00019922019586385585,
"loss": 294.1542,
"step": 680
},
{
"epoch": 0.137,
"grad_norm": 78.882568359375,
"learning_rate": 0.00019917608370004417,
"loss": 264.7906,
"step": 685
},
{
"epoch": 0.138,
"grad_norm": 97.00440216064453,
"learning_rate": 0.00019913076310695068,
"loss": 261.5189,
"step": 690
},
{
"epoch": 0.139,
"grad_norm": 65.89900970458984,
"learning_rate": 0.00019908423463679248,
"loss": 291.6568,
"step": 695
},
{
"epoch": 0.14,
"grad_norm": 91.19474792480469,
"learning_rate": 0.0001990364988565043,
"loss": 314.4514,
"step": 700
},
{
"epoch": 0.141,
"grad_norm": 147.81488037109375,
"learning_rate": 0.00019898755634773158,
"loss": 297.4646,
"step": 705
},
{
"epoch": 0.142,
"grad_norm": 104.08643341064453,
"learning_rate": 0.00019893740770682335,
"loss": 298.0903,
"step": 710
},
{
"epoch": 0.143,
"grad_norm": 64.85063171386719,
"learning_rate": 0.0001988860535448249,
"loss": 274.8402,
"step": 715
},
{
"epoch": 0.144,
"grad_norm": 72.57569122314453,
"learning_rate": 0.00019883349448747062,
"loss": 296.2702,
"step": 720
},
{
"epoch": 0.145,
"grad_norm": 89.6478042602539,
"learning_rate": 0.0001987797311751759,
"loss": 297.48,
"step": 725
},
{
"epoch": 0.146,
"grad_norm": 81.26984405517578,
"learning_rate": 0.00019872476426302982,
"loss": 303.9232,
"step": 730
},
{
"epoch": 0.147,
"grad_norm": 113.67802429199219,
"learning_rate": 0.0001986685944207868,
"loss": 296.1964,
"step": 735
},
{
"epoch": 0.148,
"grad_norm": 66.95068359375,
"learning_rate": 0.0001986112223328587,
"loss": 299.4615,
"step": 740
},
{
"epoch": 0.149,
"grad_norm": 66.18724060058594,
"learning_rate": 0.00019855264869830629,
"loss": 293.955,
"step": 745
},
{
"epoch": 0.15,
"grad_norm": 66.7259292602539,
"learning_rate": 0.00019849287423083078,
"loss": 291.8635,
"step": 750
},
{
"epoch": 0.151,
"grad_norm": 83.87020111083984,
"learning_rate": 0.00019843189965876526,
"loss": 288.6063,
"step": 755
},
{
"epoch": 0.152,
"grad_norm": 92.86822509765625,
"learning_rate": 0.00019836972572506557,
"loss": 302.4482,
"step": 760
},
{
"epoch": 0.153,
"grad_norm": 94.06305694580078,
"learning_rate": 0.00019830635318730154,
"loss": 284.0443,
"step": 765
},
{
"epoch": 0.154,
"grad_norm": 73.96411895751953,
"learning_rate": 0.00019824178281764753,
"loss": 306.1422,
"step": 770
},
{
"epoch": 0.155,
"grad_norm": 62.4682502746582,
"learning_rate": 0.00019817601540287306,
"loss": 282.7384,
"step": 775
},
{
"epoch": 0.156,
"grad_norm": 98.09383392333984,
"learning_rate": 0.0001981090517443334,
"loss": 292.1351,
"step": 780
},
{
"epoch": 0.157,
"grad_norm": 52.13507080078125,
"learning_rate": 0.0001980408926579596,
"loss": 279.8974,
"step": 785
},
{
"epoch": 0.158,
"grad_norm": 79.9127197265625,
"learning_rate": 0.00019797153897424852,
"loss": 296.6204,
"step": 790
},
{
"epoch": 0.159,
"grad_norm": 85.21955108642578,
"learning_rate": 0.000197900991538253,
"loss": 283.3622,
"step": 795
},
{
"epoch": 0.16,
"grad_norm": 67.03531646728516,
"learning_rate": 0.00019782925120957124,
"loss": 296.4992,
"step": 800
},
{
"epoch": 0.161,
"grad_norm": 49.998443603515625,
"learning_rate": 0.00019775631886233654,
"loss": 287.845,
"step": 805
},
{
"epoch": 0.162,
"grad_norm": 60.7090950012207,
"learning_rate": 0.0001976821953852065,
"loss": 284.9949,
"step": 810
},
{
"epoch": 0.163,
"grad_norm": 91.3003158569336,
"learning_rate": 0.00019760688168135232,
"loss": 284.6543,
"step": 815
},
{
"epoch": 0.164,
"grad_norm": 65.61592102050781,
"learning_rate": 0.00019753037866844771,
"loss": 269.3663,
"step": 820
},
{
"epoch": 0.165,
"grad_norm": 84.06629180908203,
"learning_rate": 0.00019745268727865774,
"loss": 276.6913,
"step": 825
},
{
"epoch": 0.166,
"grad_norm": 69.59475708007812,
"learning_rate": 0.00019737380845862745,
"loss": 293.6215,
"step": 830
},
{
"epoch": 0.167,
"grad_norm": 59.689762115478516,
"learning_rate": 0.0001972937431694704,
"loss": 274.3984,
"step": 835
},
{
"epoch": 0.168,
"grad_norm": 61.54899597167969,
"learning_rate": 0.00019721249238675688,
"loss": 282.3356,
"step": 840
},
{
"epoch": 0.169,
"grad_norm": 70.57260131835938,
"learning_rate": 0.000197130057100502,
"loss": 293.4205,
"step": 845
},
{
"epoch": 0.17,
"grad_norm": 73.15179443359375,
"learning_rate": 0.00019704643831515374,
"loss": 293.3117,
"step": 850
},
{
"epoch": 0.171,
"grad_norm": 110.24932861328125,
"learning_rate": 0.0001969616370495806,
"loss": 287.4728,
"step": 855
},
{
"epoch": 0.172,
"grad_norm": 73.43761444091797,
"learning_rate": 0.00019687565433705926,
"loss": 294.6618,
"step": 860
},
{
"epoch": 0.173,
"grad_norm": 42.46028518676758,
"learning_rate": 0.00019678849122526187,
"loss": 269.4611,
"step": 865
},
{
"epoch": 0.174,
"grad_norm": 58.331390380859375,
"learning_rate": 0.00019670014877624353,
"loss": 268.3172,
"step": 870
},
{
"epoch": 0.175,
"grad_norm": 71.15776824951172,
"learning_rate": 0.00019661062806642903,
"loss": 276.0507,
"step": 875
},
{
"epoch": 0.176,
"grad_norm": 95.34080505371094,
"learning_rate": 0.0001965199301866,
"loss": 266.9972,
"step": 880
},
{
"epoch": 0.177,
"grad_norm": 47.86874008178711,
"learning_rate": 0.00019642805624188147,
"loss": 271.5521,
"step": 885
},
{
"epoch": 0.178,
"grad_norm": 76.51673126220703,
"learning_rate": 0.0001963350073517285,
"loss": 258.1407,
"step": 890
},
{
"epoch": 0.179,
"grad_norm": 68.5263442993164,
"learning_rate": 0.0001962407846499124,
"loss": 271.9136,
"step": 895
},
{
"epoch": 0.18,
"grad_norm": 51.415252685546875,
"learning_rate": 0.0001961453892845071,
"loss": 265.3341,
"step": 900
},
{
"epoch": 0.181,
"grad_norm": 69.9641342163086,
"learning_rate": 0.00019604882241787498,
"loss": 268.0674,
"step": 905
},
{
"epoch": 0.182,
"grad_norm": 55.494667053222656,
"learning_rate": 0.0001959510852266529,
"loss": 286.973,
"step": 910
},
{
"epoch": 0.183,
"grad_norm": 69.05979919433594,
"learning_rate": 0.0001958521789017376,
"loss": 283.8615,
"step": 915
},
{
"epoch": 0.184,
"grad_norm": 56.791221618652344,
"learning_rate": 0.00019575210464827149,
"loss": 297.5191,
"step": 920
},
{
"epoch": 0.185,
"grad_norm": 54.62588119506836,
"learning_rate": 0.0001956508636856278,
"loss": 284.7207,
"step": 925
},
{
"epoch": 0.186,
"grad_norm": 100.90968322753906,
"learning_rate": 0.00019554845724739566,
"loss": 278.4306,
"step": 930
},
{
"epoch": 0.187,
"grad_norm": 97.32073211669922,
"learning_rate": 0.00019544488658136523,
"loss": 291.9125,
"step": 935
},
{
"epoch": 0.188,
"grad_norm": 59.047760009765625,
"learning_rate": 0.00019534015294951233,
"loss": 290.831,
"step": 940
},
{
"epoch": 0.189,
"grad_norm": 67.04729461669922,
"learning_rate": 0.00019523425762798329,
"loss": 292.7931,
"step": 945
},
{
"epoch": 0.19,
"grad_norm": 66.2221450805664,
"learning_rate": 0.00019512720190707913,
"loss": 270.6295,
"step": 950
},
{
"epoch": 0.191,
"grad_norm": 81.3147964477539,
"learning_rate": 0.00019501898709124008,
"loss": 287.4311,
"step": 955
},
{
"epoch": 0.192,
"grad_norm": 59.24137496948242,
"learning_rate": 0.00019490961449902946,
"loss": 290.4354,
"step": 960
},
{
"epoch": 0.193,
"grad_norm": 59.3768424987793,
"learning_rate": 0.00019479908546311781,
"loss": 292.8068,
"step": 965
},
{
"epoch": 0.194,
"grad_norm": 58.498252868652344,
"learning_rate": 0.0001946874013302666,
"loss": 286.5132,
"step": 970
},
{
"epoch": 0.195,
"grad_norm": 70.20816802978516,
"learning_rate": 0.0001945745634613117,
"loss": 289.8918,
"step": 975
},
{
"epoch": 0.196,
"grad_norm": 68.6861801147461,
"learning_rate": 0.0001944605732311469,
"loss": 292.0127,
"step": 980
},
{
"epoch": 0.197,
"grad_norm": 112.44960021972656,
"learning_rate": 0.00019434543202870725,
"loss": 282.9435,
"step": 985
},
{
"epoch": 0.198,
"grad_norm": 87.5137710571289,
"learning_rate": 0.0001942291412569519,
"loss": 291.7861,
"step": 990
},
{
"epoch": 0.199,
"grad_norm": 79.94171142578125,
"learning_rate": 0.00019411170233284727,
"loss": 297.5708,
"step": 995
},
{
"epoch": 0.2,
"grad_norm": 53.373779296875,
"learning_rate": 0.00019399311668734956,
"loss": 294.6695,
"step": 1000
},
{
"epoch": 0.201,
"grad_norm": 50.53867721557617,
"learning_rate": 0.00019387338576538744,
"loss": 297.0786,
"step": 1005
},
{
"epoch": 0.202,
"grad_norm": 65.7881851196289,
"learning_rate": 0.0001937525110258444,
"loss": 285.9436,
"step": 1010
},
{
"epoch": 0.203,
"grad_norm": 72.31036376953125,
"learning_rate": 0.00019363049394154094,
"loss": 293.7754,
"step": 1015
},
{
"epoch": 0.204,
"grad_norm": 74.89788818359375,
"learning_rate": 0.00019350733599921683,
"loss": 278.0034,
"step": 1020
},
{
"epoch": 0.205,
"grad_norm": 51.37041473388672,
"learning_rate": 0.00019338303869951269,
"loss": 282.1696,
"step": 1025
},
{
"epoch": 0.206,
"grad_norm": 84.7848892211914,
"learning_rate": 0.00019325760355695188,
"loss": 294.6034,
"step": 1030
},
{
"epoch": 0.207,
"grad_norm": 47.8759765625,
"learning_rate": 0.00019313103209992204,
"loss": 280.1621,
"step": 1035
},
{
"epoch": 0.208,
"grad_norm": 87.6491928100586,
"learning_rate": 0.0001930033258706564,
"loss": 285.7532,
"step": 1040
},
{
"epoch": 0.209,
"grad_norm": 80.30960845947266,
"learning_rate": 0.00019287448642521513,
"loss": 292.9598,
"step": 1045
},
{
"epoch": 0.21,
"grad_norm": 84.16554260253906,
"learning_rate": 0.00019274451533346615,
"loss": 288.1893,
"step": 1050
},
{
"epoch": 0.211,
"grad_norm": 57.2189826965332,
"learning_rate": 0.00019261341417906621,
"loss": 289.7508,
"step": 1055
},
{
"epoch": 0.212,
"grad_norm": 88.89424896240234,
"learning_rate": 0.0001924811845594415,
"loss": 273.876,
"step": 1060
},
{
"epoch": 0.213,
"grad_norm": 62.698768615722656,
"learning_rate": 0.00019234782808576824,
"loss": 289.2718,
"step": 1065
},
{
"epoch": 0.214,
"grad_norm": 59.00851821899414,
"learning_rate": 0.00019221334638295294,
"loss": 277.7494,
"step": 1070
},
{
"epoch": 0.215,
"grad_norm": 73.75175476074219,
"learning_rate": 0.00019207774108961272,
"loss": 281.7055,
"step": 1075
},
{
"epoch": 0.216,
"grad_norm": 105.1325454711914,
"learning_rate": 0.0001919410138580553,
"loss": 285.3777,
"step": 1080
},
{
"epoch": 0.217,
"grad_norm": 47.78352737426758,
"learning_rate": 0.0001918031663542588,
"loss": 279.1757,
"step": 1085
},
{
"epoch": 0.218,
"grad_norm": 47.43684005737305,
"learning_rate": 0.00019166420025785164,
"loss": 288.4603,
"step": 1090
},
{
"epoch": 0.219,
"grad_norm": 56.90763854980469,
"learning_rate": 0.00019152411726209176,
"loss": 287.2032,
"step": 1095
},
{
"epoch": 0.22,
"grad_norm": 55.48545837402344,
"learning_rate": 0.0001913829190738463,
"loss": 262.6919,
"step": 1100
},
{
"epoch": 0.221,
"grad_norm": 60.73474884033203,
"learning_rate": 0.00019124060741357063,
"loss": 290.0553,
"step": 1105
},
{
"epoch": 0.222,
"grad_norm": 62.76375961303711,
"learning_rate": 0.0001910971840152874,
"loss": 286.0122,
"step": 1110
},
{
"epoch": 0.223,
"grad_norm": 76.55494689941406,
"learning_rate": 0.00019095265062656544,
"loss": 278.1667,
"step": 1115
},
{
"epoch": 0.224,
"grad_norm": 46.926509857177734,
"learning_rate": 0.00019080700900849851,
"loss": 274.3072,
"step": 1120
},
{
"epoch": 0.225,
"grad_norm": 67.72985076904297,
"learning_rate": 0.00019066026093568378,
"loss": 285.3217,
"step": 1125
},
{
"epoch": 0.226,
"grad_norm": 54.657615661621094,
"learning_rate": 0.00019051240819620014,
"loss": 285.1919,
"step": 1130
},
{
"epoch": 0.227,
"grad_norm": 45.5067024230957,
"learning_rate": 0.00019036345259158667,
"loss": 284.6996,
"step": 1135
},
{
"epoch": 0.228,
"grad_norm": 67.70008087158203,
"learning_rate": 0.00019021339593682028,
"loss": 285.2029,
"step": 1140
},
{
"epoch": 0.229,
"grad_norm": 71.9408187866211,
"learning_rate": 0.00019006224006029406,
"loss": 272.0893,
"step": 1145
},
{
"epoch": 0.23,
"grad_norm": 47.899776458740234,
"learning_rate": 0.00018990998680379456,
"loss": 284.0704,
"step": 1150
},
{
"epoch": 0.231,
"grad_norm": 71.90850067138672,
"learning_rate": 0.00018975663802247976,
"loss": 299.1536,
"step": 1155
},
{
"epoch": 0.232,
"grad_norm": 71.13914489746094,
"learning_rate": 0.0001896021955848561,
"loss": 281.1104,
"step": 1160
},
{
"epoch": 0.233,
"grad_norm": 79.44478607177734,
"learning_rate": 0.000189446661372756,
"loss": 285.0072,
"step": 1165
},
{
"epoch": 0.234,
"grad_norm": 48.450565338134766,
"learning_rate": 0.0001892900372813147,
"loss": 290.2966,
"step": 1170
},
{
"epoch": 0.235,
"grad_norm": 46.08928298950195,
"learning_rate": 0.00018913232521894732,
"loss": 283.9791,
"step": 1175
},
{
"epoch": 0.236,
"grad_norm": 87.15494537353516,
"learning_rate": 0.00018897352710732564,
"loss": 284.3176,
"step": 1180
},
{
"epoch": 0.237,
"grad_norm": 72.91138458251953,
"learning_rate": 0.00018881364488135448,
"loss": 293.523,
"step": 1185
},
{
"epoch": 0.238,
"grad_norm": 91.03216552734375,
"learning_rate": 0.00018865268048914828,
"loss": 278.3575,
"step": 1190
},
{
"epoch": 0.239,
"grad_norm": 49.394996643066406,
"learning_rate": 0.00018849063589200743,
"loss": 284.6896,
"step": 1195
},
{
"epoch": 0.24,
"grad_norm": 65.91350555419922,
"learning_rate": 0.00018832751306439418,
"loss": 276.9552,
"step": 1200
},
{
"epoch": 0.241,
"grad_norm": 70.55412292480469,
"learning_rate": 0.0001881633139939087,
"loss": 285.7885,
"step": 1205
},
{
"epoch": 0.242,
"grad_norm": 53.15175247192383,
"learning_rate": 0.00018799804068126485,
"loss": 278.9684,
"step": 1210
},
{
"epoch": 0.243,
"grad_norm": 40.634952545166016,
"learning_rate": 0.00018783169514026578,
"loss": 280.7583,
"step": 1215
},
{
"epoch": 0.244,
"grad_norm": 44.89534378051758,
"learning_rate": 0.00018766427939777945,
"loss": 283.1476,
"step": 1220
},
{
"epoch": 0.245,
"grad_norm": 88.98763275146484,
"learning_rate": 0.0001874957954937138,
"loss": 286.8778,
"step": 1225
},
{
"epoch": 0.246,
"grad_norm": 93.19581604003906,
"learning_rate": 0.00018732624548099204,
"loss": 284.3598,
"step": 1230
},
{
"epoch": 0.247,
"grad_norm": 87.3250732421875,
"learning_rate": 0.00018715563142552758,
"loss": 281.9109,
"step": 1235
},
{
"epoch": 0.248,
"grad_norm": 50.004520416259766,
"learning_rate": 0.0001869839554061988,
"loss": 281.0474,
"step": 1240
},
{
"epoch": 0.249,
"grad_norm": 46.03998947143555,
"learning_rate": 0.00018681121951482393,
"loss": 285.7507,
"step": 1245
},
{
"epoch": 0.25,
"grad_norm": 65.46299743652344,
"learning_rate": 0.00018663742585613518,
"loss": 283.4638,
"step": 1250
},
{
"epoch": 0.251,
"grad_norm": 35.428707122802734,
"learning_rate": 0.0001864625765477535,
"loss": 284.2321,
"step": 1255
},
{
"epoch": 0.252,
"grad_norm": 34.89768981933594,
"learning_rate": 0.0001862866737201625,
"loss": 281.0757,
"step": 1260
},
{
"epoch": 0.253,
"grad_norm": 50.68819046020508,
"learning_rate": 0.00018610971951668265,
"loss": 293.8362,
"step": 1265
},
{
"epoch": 0.254,
"grad_norm": 40.92366027832031,
"learning_rate": 0.00018593171609344503,
"loss": 275.2758,
"step": 1270
},
{
"epoch": 0.255,
"grad_norm": 53.57720947265625,
"learning_rate": 0.00018575266561936523,
"loss": 285.29,
"step": 1275
},
{
"epoch": 0.256,
"grad_norm": 70.32237243652344,
"learning_rate": 0.00018557257027611675,
"loss": 283.8794,
"step": 1280
},
{
"epoch": 0.257,
"grad_norm": 57.056663513183594,
"learning_rate": 0.0001853914322581045,
"loss": 282.1696,
"step": 1285
},
{
"epoch": 0.258,
"grad_norm": 45.29707336425781,
"learning_rate": 0.0001852092537724381,
"loss": 266.2094,
"step": 1290
},
{
"epoch": 0.259,
"grad_norm": 53.193565368652344,
"learning_rate": 0.00018502603703890488,
"loss": 274.3787,
"step": 1295
},
{
"epoch": 0.26,
"grad_norm": 50.95241165161133,
"learning_rate": 0.0001848417842899429,
"loss": 283.8544,
"step": 1300
},
{
"epoch": 0.261,
"grad_norm": 45.28376770019531,
"learning_rate": 0.0001846564977706138,
"loss": 275.1506,
"step": 1305
},
{
"epoch": 0.262,
"grad_norm": 48.52288055419922,
"learning_rate": 0.00018447017973857532,
"loss": 270.7076,
"step": 1310
},
{
"epoch": 0.263,
"grad_norm": 42.88216018676758,
"learning_rate": 0.0001842828324640539,
"loss": 287.7696,
"step": 1315
},
{
"epoch": 0.264,
"grad_norm": 46.99845504760742,
"learning_rate": 0.00018409445822981693,
"loss": 282.9669,
"step": 1320
},
{
"epoch": 0.265,
"grad_norm": 70.14559936523438,
"learning_rate": 0.000183905059331145,
"loss": 280.1171,
"step": 1325
},
{
"epoch": 0.266,
"grad_norm": 61.58141326904297,
"learning_rate": 0.000183714638075804,
"loss": 277.4109,
"step": 1330
},
{
"epoch": 0.267,
"grad_norm": 59.32926940917969,
"learning_rate": 0.00018352319678401676,
"loss": 277.6602,
"step": 1335
},
{
"epoch": 0.268,
"grad_norm": 55.59295654296875,
"learning_rate": 0.000183330737788435,
"loss": 282.889,
"step": 1340
},
{
"epoch": 0.269,
"grad_norm": 46.76960754394531,
"learning_rate": 0.00018313726343411086,
"loss": 274.8359,
"step": 1345
},
{
"epoch": 0.27,
"grad_norm": 54.482173919677734,
"learning_rate": 0.00018294277607846832,
"loss": 273.2726,
"step": 1350
},
{
"epoch": 0.271,
"grad_norm": 53.481849670410156,
"learning_rate": 0.00018274727809127438,
"loss": 272.7189,
"step": 1355
},
{
"epoch": 0.272,
"grad_norm": 70.35366821289062,
"learning_rate": 0.00018255077185461038,
"loss": 272.5354,
"step": 1360
},
{
"epoch": 0.273,
"grad_norm": 67.23841094970703,
"learning_rate": 0.00018235325976284275,
"loss": 270.036,
"step": 1365
},
{
"epoch": 0.274,
"grad_norm": 53.24208450317383,
"learning_rate": 0.00018215474422259402,
"loss": 265.8981,
"step": 1370
},
{
"epoch": 0.275,
"grad_norm": 58.5646858215332,
"learning_rate": 0.0001819552276527134,
"loss": 267.2826,
"step": 1375
},
{
"epoch": 0.276,
"grad_norm": 56.198246002197266,
"learning_rate": 0.0001817547124842473,
"loss": 276.0754,
"step": 1380
},
{
"epoch": 0.277,
"grad_norm": 83.87222290039062,
"learning_rate": 0.00018155320116040982,
"loss": 283.7645,
"step": 1385
},
{
"epoch": 0.278,
"grad_norm": 46.861106872558594,
"learning_rate": 0.0001813506961365528,
"loss": 273.932,
"step": 1390
},
{
"epoch": 0.279,
"grad_norm": 54.57172393798828,
"learning_rate": 0.00018114719988013612,
"loss": 280.4784,
"step": 1395
},
{
"epoch": 0.28,
"grad_norm": 42.61497497558594,
"learning_rate": 0.00018094271487069735,
"loss": 285.2917,
"step": 1400
},
{
"epoch": 0.281,
"grad_norm": 52.070709228515625,
"learning_rate": 0.00018073724359982186,
"loss": 288.0597,
"step": 1405
},
{
"epoch": 0.282,
"grad_norm": 50.17939758300781,
"learning_rate": 0.0001805307885711122,
"loss": 282.1938,
"step": 1410
},
{
"epoch": 0.283,
"grad_norm": 54.37077331542969,
"learning_rate": 0.0001803233523001578,
"loss": 265.5668,
"step": 1415
},
{
"epoch": 0.284,
"grad_norm": 72.30459594726562,
"learning_rate": 0.00018011493731450413,
"loss": 275.8549,
"step": 1420
},
{
"epoch": 0.285,
"grad_norm": 122.11575317382812,
"learning_rate": 0.00017990554615362198,
"loss": 296.4225,
"step": 1425
},
{
"epoch": 0.286,
"grad_norm": 62.20444107055664,
"learning_rate": 0.00017969518136887663,
"loss": 280.5539,
"step": 1430
},
{
"epoch": 0.287,
"grad_norm": 80.03302764892578,
"learning_rate": 0.00017948384552349657,
"loss": 274.914,
"step": 1435
},
{
"epoch": 0.288,
"grad_norm": 42.05292510986328,
"learning_rate": 0.00017927154119254236,
"loss": 257.9184,
"step": 1440
},
{
"epoch": 0.289,
"grad_norm": 46.070884704589844,
"learning_rate": 0.0001790582709628753,
"loss": 264.3405,
"step": 1445
},
{
"epoch": 0.29,
"grad_norm": 59.20568084716797,
"learning_rate": 0.00017884403743312582,
"loss": 274.6118,
"step": 1450
},
{
"epoch": 0.291,
"grad_norm": 92.71176147460938,
"learning_rate": 0.00017862884321366188,
"loss": 267.0795,
"step": 1455
},
{
"epoch": 0.292,
"grad_norm": 80.04141235351562,
"learning_rate": 0.00017841269092655715,
"loss": 261.5915,
"step": 1460
},
{
"epoch": 0.293,
"grad_norm": 49.57596969604492,
"learning_rate": 0.000178195583205559,
"loss": 255.5927,
"step": 1465
},
{
"epoch": 0.294,
"grad_norm": 44.54609298706055,
"learning_rate": 0.00017797752269605653,
"loss": 256.7559,
"step": 1470
},
{
"epoch": 0.295,
"grad_norm": 83.10302734375,
"learning_rate": 0.0001777585120550482,
"loss": 274.4178,
"step": 1475
},
{
"epoch": 0.296,
"grad_norm": 55.65082931518555,
"learning_rate": 0.0001775385539511096,
"loss": 248.2579,
"step": 1480
},
{
"epoch": 0.297,
"grad_norm": 62.14948654174805,
"learning_rate": 0.00017731765106436073,
"loss": 256.783,
"step": 1485
},
{
"epoch": 0.298,
"grad_norm": 48.27973175048828,
"learning_rate": 0.00017709580608643363,
"loss": 259.1802,
"step": 1490
},
{
"epoch": 0.299,
"grad_norm": 59.15861511230469,
"learning_rate": 0.00017687302172043933,
"loss": 263.0967,
"step": 1495
},
{
"epoch": 0.3,
"grad_norm": 67.1439208984375,
"learning_rate": 0.00017664930068093498,
"loss": 268.8813,
"step": 1500
},
{
"epoch": 0.301,
"grad_norm": 49.04071044921875,
"learning_rate": 0.0001764246456938909,
"loss": 281.8383,
"step": 1505
},
{
"epoch": 0.302,
"grad_norm": 72.35908508300781,
"learning_rate": 0.0001761990594966572,
"loss": 287.5075,
"step": 1510
},
{
"epoch": 0.303,
"grad_norm": 49.84059143066406,
"learning_rate": 0.00017597254483793048,
"loss": 275.7599,
"step": 1515
},
{
"epoch": 0.304,
"grad_norm": 41.90044021606445,
"learning_rate": 0.00017574510447772039,
"loss": 280.2814,
"step": 1520
},
{
"epoch": 0.305,
"grad_norm": 61.44948959350586,
"learning_rate": 0.00017551674118731591,
"loss": 277.0804,
"step": 1525
},
{
"epoch": 0.306,
"grad_norm": 48.61772155761719,
"learning_rate": 0.00017528745774925172,
"loss": 269.1419,
"step": 1530
},
{
"epoch": 0.307,
"grad_norm": 37.91169357299805,
"learning_rate": 0.00017505725695727412,
"loss": 273.8426,
"step": 1535
},
{
"epoch": 0.308,
"grad_norm": 55.58927536010742,
"learning_rate": 0.00017482614161630714,
"loss": 285.5702,
"step": 1540
},
{
"epoch": 0.309,
"grad_norm": 43.23332214355469,
"learning_rate": 0.00017459411454241822,
"loss": 287.7304,
"step": 1545
},
{
"epoch": 0.31,
"grad_norm": 59.054664611816406,
"learning_rate": 0.0001743611785627841,
"loss": 266.6447,
"step": 1550
},
{
"epoch": 0.311,
"grad_norm": 51.07796096801758,
"learning_rate": 0.0001741273365156561,
"loss": 277.6055,
"step": 1555
},
{
"epoch": 0.312,
"grad_norm": 65.10200500488281,
"learning_rate": 0.0001738925912503259,
"loss": 279.7805,
"step": 1560
},
{
"epoch": 0.313,
"grad_norm": 78.84537506103516,
"learning_rate": 0.00017365694562709034,
"loss": 267.9302,
"step": 1565
},
{
"epoch": 0.314,
"grad_norm": 53.87149429321289,
"learning_rate": 0.00017342040251721702,
"loss": 277.3384,
"step": 1570
},
{
"epoch": 0.315,
"grad_norm": 72.6865463256836,
"learning_rate": 0.0001731829648029091,
"loss": 284.417,
"step": 1575
},
{
"epoch": 0.316,
"grad_norm": 60.568382263183594,
"learning_rate": 0.00017294463537727024,
"loss": 278.1744,
"step": 1580
},
{
"epoch": 0.317,
"grad_norm": 49.6313362121582,
"learning_rate": 0.0001727054171442692,
"loss": 272.0263,
"step": 1585
},
{
"epoch": 0.318,
"grad_norm": 44.25932693481445,
"learning_rate": 0.0001724653130187047,
"loss": 253.4824,
"step": 1590
},
{
"epoch": 0.319,
"grad_norm": 63.32981872558594,
"learning_rate": 0.0001722243259261697,
"loss": 265.8034,
"step": 1595
},
{
"epoch": 0.32,
"grad_norm": 80.81440734863281,
"learning_rate": 0.0001719824588030159,
"loss": 268.7385,
"step": 1600
},
{
"epoch": 0.321,
"grad_norm": 50.437217712402344,
"learning_rate": 0.00017173971459631787,
"loss": 271.163,
"step": 1605
},
{
"epoch": 0.322,
"grad_norm": 66.62611389160156,
"learning_rate": 0.00017149609626383717,
"loss": 283.2287,
"step": 1610
},
{
"epoch": 0.323,
"grad_norm": 42.248043060302734,
"learning_rate": 0.00017125160677398626,
"loss": 278.8558,
"step": 1615
},
{
"epoch": 0.324,
"grad_norm": 65.10708618164062,
"learning_rate": 0.0001710062491057925,
"loss": 271.8052,
"step": 1620
},
{
"epoch": 0.325,
"grad_norm": 60.78662109375,
"learning_rate": 0.00017076002624886154,
"loss": 267.4533,
"step": 1625
},
{
"epoch": 0.326,
"grad_norm": 71.01763916015625,
"learning_rate": 0.00017051294120334125,
"loss": 262.8858,
"step": 1630
},
{
"epoch": 0.327,
"grad_norm": 35.78629684448242,
"learning_rate": 0.00017026499697988493,
"loss": 270.7043,
"step": 1635
},
{
"epoch": 0.328,
"grad_norm": 49.859493255615234,
"learning_rate": 0.00017001619659961467,
"loss": 262.8616,
"step": 1640
},
{
"epoch": 0.329,
"grad_norm": 67.82917785644531,
"learning_rate": 0.00016976654309408464,
"loss": 249.6295,
"step": 1645
},
{
"epoch": 0.33,
"grad_norm": 57.860225677490234,
"learning_rate": 0.000169516039505244,
"loss": 265.909,
"step": 1650
},
{
"epoch": 0.331,
"grad_norm": 37.71580505371094,
"learning_rate": 0.0001692646888853999,
"loss": 272.4596,
"step": 1655
},
{
"epoch": 0.332,
"grad_norm": 35.990482330322266,
"learning_rate": 0.00016901249429718032,
"loss": 259.8827,
"step": 1660
},
{
"epoch": 0.333,
"grad_norm": 46.31774139404297,
"learning_rate": 0.00016875945881349676,
"loss": 260.6465,
"step": 1665
},
{
"epoch": 0.334,
"grad_norm": 37.01717758178711,
"learning_rate": 0.0001685055855175067,
"loss": 250.4776,
"step": 1670
},
{
"epoch": 0.335,
"grad_norm": 33.50545883178711,
"learning_rate": 0.0001682508775025762,
"loss": 279.6247,
"step": 1675
},
{
"epoch": 0.336,
"grad_norm": 49.965633392333984,
"learning_rate": 0.00016799533787224192,
"loss": 271.1682,
"step": 1680
},
{
"epoch": 0.337,
"grad_norm": 46.16508483886719,
"learning_rate": 0.00016773896974017373,
"loss": 267.4003,
"step": 1685
},
{
"epoch": 0.338,
"grad_norm": 56.339237213134766,
"learning_rate": 0.00016748177623013638,
"loss": 257.5167,
"step": 1690
},
{
"epoch": 0.339,
"grad_norm": 38.992488861083984,
"learning_rate": 0.00016722376047595164,
"loss": 263.6959,
"step": 1695
},
{
"epoch": 0.34,
"grad_norm": 40.52589797973633,
"learning_rate": 0.00016696492562145996,
"loss": 268.3028,
"step": 1700
},
{
"epoch": 0.341,
"grad_norm": 37.26987838745117,
"learning_rate": 0.00016670527482048246,
"loss": 264.4117,
"step": 1705
},
{
"epoch": 0.342,
"grad_norm": 43.69699478149414,
"learning_rate": 0.00016644481123678217,
"loss": 256.6173,
"step": 1710
},
{
"epoch": 0.343,
"grad_norm": 63.566070556640625,
"learning_rate": 0.00016618353804402568,
"loss": 247.262,
"step": 1715
},
{
"epoch": 0.344,
"grad_norm": 35.37077331542969,
"learning_rate": 0.00016592145842574433,
"loss": 262.0297,
"step": 1720
},
{
"epoch": 0.345,
"grad_norm": 58.24921798706055,
"learning_rate": 0.00016565857557529566,
"loss": 281.2879,
"step": 1725
},
{
"epoch": 0.346,
"grad_norm": 37.89385986328125,
"learning_rate": 0.00016539489269582416,
"loss": 271.9182,
"step": 1730
},
{
"epoch": 0.347,
"grad_norm": 36.575096130371094,
"learning_rate": 0.00016513041300022255,
"loss": 266.9994,
"step": 1735
},
{
"epoch": 0.348,
"grad_norm": 41.07619094848633,
"learning_rate": 0.00016486513971109243,
"loss": 275.6728,
"step": 1740
},
{
"epoch": 0.349,
"grad_norm": 65.42058563232422,
"learning_rate": 0.0001645990760607051,
"loss": 259.6047,
"step": 1745
},
{
"epoch": 0.35,
"grad_norm": 49.802494049072266,
"learning_rate": 0.0001643322252909622,
"loss": 270.0911,
"step": 1750
},
{
"epoch": 0.351,
"grad_norm": 46.43568801879883,
"learning_rate": 0.00016406459065335615,
"loss": 251.1292,
"step": 1755
},
{
"epoch": 0.352,
"grad_norm": 35.510047912597656,
"learning_rate": 0.00016379617540893056,
"loss": 254.5043,
"step": 1760
},
{
"epoch": 0.353,
"grad_norm": 41.64132308959961,
"learning_rate": 0.00016352698282824044,
"loss": 260.7519,
"step": 1765
},
{
"epoch": 0.354,
"grad_norm": 61.35075378417969,
"learning_rate": 0.00016325701619131246,
"loss": 265.2428,
"step": 1770
},
{
"epoch": 0.355,
"grad_norm": 35.688392639160156,
"learning_rate": 0.00016298627878760487,
"loss": 256.5798,
"step": 1775
},
{
"epoch": 0.356,
"grad_norm": 68.3086166381836,
"learning_rate": 0.00016271477391596753,
"loss": 273.1155,
"step": 1780
},
{
"epoch": 0.357,
"grad_norm": 44.82316970825195,
"learning_rate": 0.00016244250488460158,
"loss": 268.5443,
"step": 1785
},
{
"epoch": 0.358,
"grad_norm": 46.79513931274414,
"learning_rate": 0.0001621694750110193,
"loss": 266.774,
"step": 1790
},
{
"epoch": 0.359,
"grad_norm": 47.058231353759766,
"learning_rate": 0.00016189568762200348,
"loss": 256.6073,
"step": 1795
},
{
"epoch": 0.36,
"grad_norm": 109.32071685791016,
"learning_rate": 0.00016162114605356703,
"loss": 260.7372,
"step": 1800
},
{
"epoch": 0.361,
"grad_norm": 44.57652282714844,
"learning_rate": 0.00016134585365091243,
"loss": 257.0972,
"step": 1805
},
{
"epoch": 0.362,
"grad_norm": 38.321041107177734,
"learning_rate": 0.00016106981376839066,
"loss": 255.8471,
"step": 1810
},
{
"epoch": 0.363,
"grad_norm": 36.388641357421875,
"learning_rate": 0.00016079302976946055,
"loss": 260.7444,
"step": 1815
},
{
"epoch": 0.364,
"grad_norm": 94.66785430908203,
"learning_rate": 0.0001605155050266478,
"loss": 253.4496,
"step": 1820
},
{
"epoch": 0.365,
"grad_norm": 77.06111145019531,
"learning_rate": 0.00016023724292150385,
"loss": 256.3463,
"step": 1825
},
{
"epoch": 0.366,
"grad_norm": 40.19953918457031,
"learning_rate": 0.00015995824684456465,
"loss": 260.9844,
"step": 1830
},
{
"epoch": 0.367,
"grad_norm": 32.95935821533203,
"learning_rate": 0.00015967852019530926,
"loss": 269.7871,
"step": 1835
},
{
"epoch": 0.368,
"grad_norm": 36.255950927734375,
"learning_rate": 0.0001593980663821187,
"loss": 258.6917,
"step": 1840
},
{
"epoch": 0.369,
"grad_norm": 40.596534729003906,
"learning_rate": 0.0001591168888222342,
"loss": 264.166,
"step": 1845
},
{
"epoch": 0.37,
"grad_norm": 41.804840087890625,
"learning_rate": 0.00015883499094171554,
"loss": 278.4484,
"step": 1850
},
{
"epoch": 0.371,
"grad_norm": 39.5411491394043,
"learning_rate": 0.0001585523761753994,
"loss": 254.3773,
"step": 1855
},
{
"epoch": 0.372,
"grad_norm": 37.29084777832031,
"learning_rate": 0.00015826904796685762,
"loss": 268.0813,
"step": 1860
},
{
"epoch": 0.373,
"grad_norm": 61.140445709228516,
"learning_rate": 0.00015798500976835493,
"loss": 273.8309,
"step": 1865
},
{
"epoch": 0.374,
"grad_norm": 45.03831481933594,
"learning_rate": 0.00015770026504080718,
"loss": 265.622,
"step": 1870
},
{
"epoch": 0.375,
"grad_norm": 52.34563064575195,
"learning_rate": 0.000157414817253739,
"loss": 254.2759,
"step": 1875
},
{
"epoch": 0.376,
"grad_norm": 56.100215911865234,
"learning_rate": 0.00015712866988524155,
"loss": 267.7266,
"step": 1880
},
{
"epoch": 0.377,
"grad_norm": 52.495113372802734,
"learning_rate": 0.0001568418264219303,
"loss": 256.926,
"step": 1885
},
{
"epoch": 0.378,
"grad_norm": 53.72835922241211,
"learning_rate": 0.0001565542903589023,
"loss": 236.3117,
"step": 1890
},
{
"epoch": 0.379,
"grad_norm": 37.485774993896484,
"learning_rate": 0.0001562660651996937,
"loss": 267.7916,
"step": 1895
},
{
"epoch": 0.38,
"grad_norm": 44.8703727722168,
"learning_rate": 0.00015597715445623712,
"loss": 261.7762,
"step": 1900
},
{
"epoch": 0.381,
"grad_norm": 38.38932418823242,
"learning_rate": 0.00015568756164881882,
"loss": 257.1802,
"step": 1905
},
{
"epoch": 0.382,
"grad_norm": 58.02499008178711,
"learning_rate": 0.00015539729030603574,
"loss": 256.1124,
"step": 1910
},
{
"epoch": 0.383,
"grad_norm": 53.02233123779297,
"learning_rate": 0.0001551063439647526,
"loss": 255.6204,
"step": 1915
},
{
"epoch": 0.384,
"grad_norm": 47.31920623779297,
"learning_rate": 0.00015481472617005876,
"loss": 255.1329,
"step": 1920
},
{
"epoch": 0.385,
"grad_norm": 40.35784149169922,
"learning_rate": 0.00015452244047522502,
"loss": 251.7157,
"step": 1925
},
{
"epoch": 0.386,
"grad_norm": 53.671417236328125,
"learning_rate": 0.0001542294904416603,
"loss": 254.7249,
"step": 1930
},
{
"epoch": 0.387,
"grad_norm": 41.42934799194336,
"learning_rate": 0.00015393587963886835,
"loss": 249.6459,
"step": 1935
},
{
"epoch": 0.388,
"grad_norm": 42.91515350341797,
"learning_rate": 0.0001536416116444041,
"loss": 267.1157,
"step": 1940
},
{
"epoch": 0.389,
"grad_norm": 48.3343391418457,
"learning_rate": 0.0001533466900438303,
"loss": 276.324,
"step": 1945
},
{
"epoch": 0.39,
"grad_norm": 39.65613555908203,
"learning_rate": 0.0001530511184306734,
"loss": 272.9655,
"step": 1950
},
{
"epoch": 0.391,
"grad_norm": 48.36925506591797,
"learning_rate": 0.00015275490040638038,
"loss": 266.2594,
"step": 1955
},
{
"epoch": 0.392,
"grad_norm": 45.968544006347656,
"learning_rate": 0.00015245803958027434,
"loss": 255.14,
"step": 1960
},
{
"epoch": 0.393,
"grad_norm": 48.558467864990234,
"learning_rate": 0.0001521605395695108,
"loss": 260.9482,
"step": 1965
},
{
"epoch": 0.394,
"grad_norm": 58.97275161743164,
"learning_rate": 0.00015186240399903342,
"loss": 262.1167,
"step": 1970
},
{
"epoch": 0.395,
"grad_norm": 44.67347717285156,
"learning_rate": 0.00015156363650153012,
"loss": 265.6916,
"step": 1975
},
{
"epoch": 0.396,
"grad_norm": 33.31349563598633,
"learning_rate": 0.0001512642407173885,
"loss": 266.1023,
"step": 1980
},
{
"epoch": 0.397,
"grad_norm": 59.28323745727539,
"learning_rate": 0.00015096422029465178,
"loss": 263.0022,
"step": 1985
},
{
"epoch": 0.398,
"grad_norm": 38.22578430175781,
"learning_rate": 0.0001506635788889741,
"loss": 237.127,
"step": 1990
},
{
"epoch": 0.399,
"grad_norm": 48.65337371826172,
"learning_rate": 0.0001503623201635761,
"loss": 265.4248,
"step": 1995
},
{
"epoch": 0.4,
"grad_norm": 43.83149719238281,
"learning_rate": 0.0001500604477892003,
"loss": 265.4522,
"step": 2000
}
],
"logging_steps": 5,
"max_steps": 5000,
"num_input_tokens_seen": 0,
"num_train_epochs": 9223372036854775807,
"save_steps": 1000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 2.7509869510656e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.4,
"eval_steps": 500,
"global_step": 2000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.001,
"grad_norm": 721.6266479492188,
"learning_rate": 1.6000000000000001e-06,
"loss": 688.1156,
"step": 5
},
{
"epoch": 0.002,
"grad_norm": 544.0831298828125,
"learning_rate": 3.6e-06,
"loss": 692.814,
"step": 10
},
{
"epoch": 0.003,
"grad_norm": 435.138427734375,
"learning_rate": 5.600000000000001e-06,
"loss": 675.4897,
"step": 15
},
{
"epoch": 0.004,
"grad_norm": 231.80264282226562,
"learning_rate": 7.6e-06,
"loss": 678.7521,
"step": 20
},
{
"epoch": 0.005,
"grad_norm": 265.94085693359375,
"learning_rate": 9.600000000000001e-06,
"loss": 677.9869,
"step": 25
},
{
"epoch": 0.006,
"grad_norm": 286.4078063964844,
"learning_rate": 1.16e-05,
"loss": 641.2654,
"step": 30
},
{
"epoch": 0.007,
"grad_norm": 200.6824188232422,
"learning_rate": 1.3600000000000002e-05,
"loss": 623.5658,
"step": 35
},
{
"epoch": 0.008,
"grad_norm": 190.13320922851562,
"learning_rate": 1.56e-05,
"loss": 603.631,
"step": 40
},
{
"epoch": 0.009,
"grad_norm": 191.35208129882812,
"learning_rate": 1.76e-05,
"loss": 600.4304,
"step": 45
},
{
"epoch": 0.01,
"grad_norm": 234.3683319091797,
"learning_rate": 1.9600000000000002e-05,
"loss": 612.607,
"step": 50
},
{
"epoch": 0.011,
"grad_norm": 222.86151123046875,
"learning_rate": 2.16e-05,
"loss": 559.0464,
"step": 55
},
{
"epoch": 0.012,
"grad_norm": 184.71469116210938,
"learning_rate": 2.36e-05,
"loss": 552.2791,
"step": 60
},
{
"epoch": 0.013,
"grad_norm": 196.4359893798828,
"learning_rate": 2.5600000000000002e-05,
"loss": 541.9889,