{
"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": 1.2604342699050903,
"learning_rate": 1.6000000000000001e-06,
"loss": 10.9732,
"step": 5
},
{
"epoch": 0.002,
"grad_norm": 1.1417402029037476,
"learning_rate": 3.6e-06,
"loss": 10.9292,
"step": 10
},
{
"epoch": 0.003,
"grad_norm": 1.0900236368179321,
"learning_rate": 5.600000000000001e-06,
"loss": 10.9342,
"step": 15
},
{
"epoch": 0.004,
"grad_norm": 1.0668010711669922,
"learning_rate": 7.6e-06,
"loss": 10.8892,
"step": 20
},
{
"epoch": 0.005,
"grad_norm": 0.85555499792099,
"learning_rate": 9.600000000000001e-06,
"loss": 10.6586,
"step": 25
},
{
"epoch": 0.006,
"grad_norm": 0.9816857576370239,
"learning_rate": 1.16e-05,
"loss": 10.6141,
"step": 30
},
{
"epoch": 0.007,
"grad_norm": 1.0871800184249878,
"learning_rate": 1.3600000000000002e-05,
"loss": 10.6435,
"step": 35
},
{
"epoch": 0.008,
"grad_norm": 0.9939376711845398,
"learning_rate": 1.56e-05,
"loss": 10.2936,
"step": 40
},
{
"epoch": 0.009,
"grad_norm": 1.0439313650131226,
"learning_rate": 1.76e-05,
"loss": 9.9938,
"step": 45
},
{
"epoch": 0.01,
"grad_norm": 1.1758387088775635,
"learning_rate": 1.9600000000000002e-05,
"loss": 10.0906,
"step": 50
},
{
"epoch": 0.011,
"grad_norm": 1.1925978660583496,
"learning_rate": 2.16e-05,
"loss": 9.6833,
"step": 55
},
{
"epoch": 0.012,
"grad_norm": 0.9983498454093933,
"learning_rate": 2.36e-05,
"loss": 9.7356,
"step": 60
},
{
"epoch": 0.013,
"grad_norm": 1.0689743757247925,
"learning_rate": 2.5600000000000002e-05,
"loss": 9.5145,
"step": 65
},
{
"epoch": 0.014,
"grad_norm": 0.8712257742881775,
"learning_rate": 2.7600000000000003e-05,
"loss": 9.4596,
"step": 70
},
{
"epoch": 0.015,
"grad_norm": 0.7808308601379395,
"learning_rate": 2.96e-05,
"loss": 9.4905,
"step": 75
},
{
"epoch": 0.016,
"grad_norm": 0.7554465532302856,
"learning_rate": 3.16e-05,
"loss": 9.1161,
"step": 80
},
{
"epoch": 0.017,
"grad_norm": 0.9761037230491638,
"learning_rate": 3.3600000000000004e-05,
"loss": 8.9161,
"step": 85
},
{
"epoch": 0.018,
"grad_norm": 0.8736913800239563,
"learning_rate": 3.56e-05,
"loss": 8.9094,
"step": 90
},
{
"epoch": 0.019,
"grad_norm": 0.6800994873046875,
"learning_rate": 3.76e-05,
"loss": 8.9293,
"step": 95
},
{
"epoch": 0.02,
"grad_norm": 1.0810476541519165,
"learning_rate": 3.960000000000001e-05,
"loss": 8.8197,
"step": 100
},
{
"epoch": 0.021,
"grad_norm": 0.8229161500930786,
"learning_rate": 4.16e-05,
"loss": 8.6136,
"step": 105
},
{
"epoch": 0.022,
"grad_norm": 0.7339630126953125,
"learning_rate": 4.36e-05,
"loss": 8.8362,
"step": 110
},
{
"epoch": 0.023,
"grad_norm": 0.9734928607940674,
"learning_rate": 4.5600000000000004e-05,
"loss": 8.5627,
"step": 115
},
{
"epoch": 0.024,
"grad_norm": 0.7515960335731506,
"learning_rate": 4.76e-05,
"loss": 8.5492,
"step": 120
},
{
"epoch": 0.025,
"grad_norm": 0.7057774066925049,
"learning_rate": 4.96e-05,
"loss": 8.5448,
"step": 125
},
{
"epoch": 0.026,
"grad_norm": 0.6431692242622375,
"learning_rate": 5.16e-05,
"loss": 8.5691,
"step": 130
},
{
"epoch": 0.027,
"grad_norm": 0.9278597831726074,
"learning_rate": 5.360000000000001e-05,
"loss": 8.354,
"step": 135
},
{
"epoch": 0.028,
"grad_norm": 0.9409669637680054,
"learning_rate": 5.560000000000001e-05,
"loss": 8.4009,
"step": 140
},
{
"epoch": 0.029,
"grad_norm": 0.6378563642501831,
"learning_rate": 5.76e-05,
"loss": 8.2387,
"step": 145
},
{
"epoch": 0.03,
"grad_norm": 0.7090245485305786,
"learning_rate": 5.96e-05,
"loss": 8.1847,
"step": 150
},
{
"epoch": 0.031,
"grad_norm": 0.8132306933403015,
"learning_rate": 6.16e-05,
"loss": 8.2947,
"step": 155
},
{
"epoch": 0.032,
"grad_norm": 0.7476041316986084,
"learning_rate": 6.36e-05,
"loss": 8.1633,
"step": 160
},
{
"epoch": 0.033,
"grad_norm": 0.7301468849182129,
"learning_rate": 6.560000000000001e-05,
"loss": 8.1476,
"step": 165
},
{
"epoch": 0.034,
"grad_norm": 0.9826472997665405,
"learning_rate": 6.76e-05,
"loss": 8.4932,
"step": 170
},
{
"epoch": 0.035,
"grad_norm": 1.4184170961380005,
"learning_rate": 6.96e-05,
"loss": 8.3817,
"step": 175
},
{
"epoch": 0.036,
"grad_norm": 1.0743205547332764,
"learning_rate": 7.16e-05,
"loss": 8.159,
"step": 180
},
{
"epoch": 0.037,
"grad_norm": 0.7333476543426514,
"learning_rate": 7.36e-05,
"loss": 8.0566,
"step": 185
},
{
"epoch": 0.038,
"grad_norm": 0.8829195499420166,
"learning_rate": 7.560000000000001e-05,
"loss": 7.9668,
"step": 190
},
{
"epoch": 0.039,
"grad_norm": 0.6747652292251587,
"learning_rate": 7.76e-05,
"loss": 7.9084,
"step": 195
},
{
"epoch": 0.04,
"grad_norm": 0.9228882193565369,
"learning_rate": 7.960000000000001e-05,
"loss": 7.765,
"step": 200
},
{
"epoch": 0.041,
"grad_norm": 0.9495064616203308,
"learning_rate": 8.16e-05,
"loss": 7.86,
"step": 205
},
{
"epoch": 0.042,
"grad_norm": 0.9488210082054138,
"learning_rate": 8.36e-05,
"loss": 7.8187,
"step": 210
},
{
"epoch": 0.043,
"grad_norm": 1.186676263809204,
"learning_rate": 8.560000000000001e-05,
"loss": 7.8206,
"step": 215
},
{
"epoch": 0.044,
"grad_norm": 1.2464865446090698,
"learning_rate": 8.76e-05,
"loss": 7.9844,
"step": 220
},
{
"epoch": 0.045,
"grad_norm": 0.6412062644958496,
"learning_rate": 8.960000000000001e-05,
"loss": 7.8572,
"step": 225
},
{
"epoch": 0.046,
"grad_norm": 0.7745037078857422,
"learning_rate": 9.16e-05,
"loss": 7.7099,
"step": 230
},
{
"epoch": 0.047,
"grad_norm": 0.7298027873039246,
"learning_rate": 9.360000000000001e-05,
"loss": 7.6338,
"step": 235
},
{
"epoch": 0.048,
"grad_norm": 0.7224679589271545,
"learning_rate": 9.56e-05,
"loss": 7.7049,
"step": 240
},
{
"epoch": 0.049,
"grad_norm": 0.5778278708457947,
"learning_rate": 9.76e-05,
"loss": 7.6171,
"step": 245
},
{
"epoch": 0.05,
"grad_norm": 0.7234050035476685,
"learning_rate": 9.960000000000001e-05,
"loss": 7.8185,
"step": 250
},
{
"epoch": 0.051,
"grad_norm": 0.6330353617668152,
"learning_rate": 0.0001016,
"loss": 7.6258,
"step": 255
},
{
"epoch": 0.052,
"grad_norm": 0.5528980493545532,
"learning_rate": 0.00010360000000000001,
"loss": 7.6289,
"step": 260
},
{
"epoch": 0.053,
"grad_norm": 1.08527410030365,
"learning_rate": 0.0001056,
"loss": 7.6233,
"step": 265
},
{
"epoch": 0.054,
"grad_norm": 0.8998336791992188,
"learning_rate": 0.00010760000000000001,
"loss": 7.6974,
"step": 270
},
{
"epoch": 0.055,
"grad_norm": 0.7755799889564514,
"learning_rate": 0.00010960000000000001,
"loss": 7.6252,
"step": 275
},
{
"epoch": 0.056,
"grad_norm": 0.5202886462211609,
"learning_rate": 0.00011160000000000002,
"loss": 7.5713,
"step": 280
},
{
"epoch": 0.057,
"grad_norm": 0.6631245017051697,
"learning_rate": 0.0001136,
"loss": 7.5136,
"step": 285
},
{
"epoch": 0.058,
"grad_norm": 0.6417354345321655,
"learning_rate": 0.00011559999999999999,
"loss": 7.4928,
"step": 290
},
{
"epoch": 0.059,
"grad_norm": 0.7988592982292175,
"learning_rate": 0.0001176,
"loss": 7.602,
"step": 295
},
{
"epoch": 0.06,
"grad_norm": 0.5386444330215454,
"learning_rate": 0.00011960000000000001,
"loss": 7.5281,
"step": 300
},
{
"epoch": 0.061,
"grad_norm": 0.5688593983650208,
"learning_rate": 0.0001216,
"loss": 7.6125,
"step": 305
},
{
"epoch": 0.062,
"grad_norm": 0.6441075205802917,
"learning_rate": 0.0001236,
"loss": 7.4255,
"step": 310
},
{
"epoch": 0.063,
"grad_norm": 0.780218780040741,
"learning_rate": 0.00012560000000000002,
"loss": 7.4621,
"step": 315
},
{
"epoch": 0.064,
"grad_norm": 0.6642858386039734,
"learning_rate": 0.0001276,
"loss": 7.4566,
"step": 320
},
{
"epoch": 0.065,
"grad_norm": 0.5822940468788147,
"learning_rate": 0.0001296,
"loss": 7.4942,
"step": 325
},
{
"epoch": 0.066,
"grad_norm": 0.9171116352081299,
"learning_rate": 0.0001316,
"loss": 7.3084,
"step": 330
},
{
"epoch": 0.067,
"grad_norm": 0.7546496391296387,
"learning_rate": 0.00013360000000000002,
"loss": 7.5661,
"step": 335
},
{
"epoch": 0.068,
"grad_norm": 0.6694166660308838,
"learning_rate": 0.00013560000000000002,
"loss": 7.4008,
"step": 340
},
{
"epoch": 0.069,
"grad_norm": 0.7674323320388794,
"learning_rate": 0.00013759999999999998,
"loss": 7.3421,
"step": 345
},
{
"epoch": 0.07,
"grad_norm": 0.754805326461792,
"learning_rate": 0.0001396,
"loss": 7.4399,
"step": 350
},
{
"epoch": 0.071,
"grad_norm": 0.8022285103797913,
"learning_rate": 0.0001416,
"loss": 7.3559,
"step": 355
},
{
"epoch": 0.072,
"grad_norm": 0.7880796790122986,
"learning_rate": 0.0001436,
"loss": 7.4394,
"step": 360
},
{
"epoch": 0.073,
"grad_norm": 0.5846539735794067,
"learning_rate": 0.00014560000000000002,
"loss": 7.3898,
"step": 365
},
{
"epoch": 0.074,
"grad_norm": 0.668461263179779,
"learning_rate": 0.0001476,
"loss": 7.3558,
"step": 370
},
{
"epoch": 0.075,
"grad_norm": 0.5052613615989685,
"learning_rate": 0.0001496,
"loss": 7.312,
"step": 375
},
{
"epoch": 0.076,
"grad_norm": 0.5788829922676086,
"learning_rate": 0.0001516,
"loss": 7.3202,
"step": 380
},
{
"epoch": 0.077,
"grad_norm": 0.5080456733703613,
"learning_rate": 0.00015360000000000002,
"loss": 7.2045,
"step": 385
},
{
"epoch": 0.078,
"grad_norm": 0.552971363067627,
"learning_rate": 0.00015560000000000001,
"loss": 7.2849,
"step": 390
},
{
"epoch": 0.079,
"grad_norm": 0.4407593905925751,
"learning_rate": 0.0001576,
"loss": 7.2542,
"step": 395
},
{
"epoch": 0.08,
"grad_norm": 0.6450212597846985,
"learning_rate": 0.0001596,
"loss": 7.3136,
"step": 400
},
{
"epoch": 0.081,
"grad_norm": 0.5040855407714844,
"learning_rate": 0.00016160000000000002,
"loss": 7.1858,
"step": 405
},
{
"epoch": 0.082,
"grad_norm": 0.5349072217941284,
"learning_rate": 0.0001636,
"loss": 7.3762,
"step": 410
},
{
"epoch": 0.083,
"grad_norm": 0.7044780850410461,
"learning_rate": 0.0001656,
"loss": 7.3471,
"step": 415
},
{
"epoch": 0.084,
"grad_norm": 1.0048245191574097,
"learning_rate": 0.0001676,
"loss": 7.2368,
"step": 420
},
{
"epoch": 0.085,
"grad_norm": 0.5878656506538391,
"learning_rate": 0.0001696,
"loss": 7.1726,
"step": 425
},
{
"epoch": 0.086,
"grad_norm": 0.6114814281463623,
"learning_rate": 0.0001716,
"loss": 7.2407,
"step": 430
},
{
"epoch": 0.087,
"grad_norm": 0.6904076337814331,
"learning_rate": 0.00017360000000000002,
"loss": 7.1245,
"step": 435
},
{
"epoch": 0.088,
"grad_norm": 0.5978814959526062,
"learning_rate": 0.0001756,
"loss": 7.2473,
"step": 440
},
{
"epoch": 0.089,
"grad_norm": 0.6442691087722778,
"learning_rate": 0.0001776,
"loss": 7.2608,
"step": 445
},
{
"epoch": 0.09,
"grad_norm": 0.5155648589134216,
"learning_rate": 0.0001796,
"loss": 7.1874,
"step": 450
},
{
"epoch": 0.091,
"grad_norm": 0.6984358429908752,
"learning_rate": 0.00018160000000000002,
"loss": 7.1262,
"step": 455
},
{
"epoch": 0.092,
"grad_norm": 0.5820157527923584,
"learning_rate": 0.00018360000000000002,
"loss": 7.1114,
"step": 460
},
{
"epoch": 0.093,
"grad_norm": 0.4343531131744385,
"learning_rate": 0.0001856,
"loss": 6.9295,
"step": 465
},
{
"epoch": 0.094,
"grad_norm": 0.5058460235595703,
"learning_rate": 0.0001876,
"loss": 7.0463,
"step": 470
},
{
"epoch": 0.095,
"grad_norm": 0.772259533405304,
"learning_rate": 0.0001896,
"loss": 7.0728,
"step": 475
},
{
"epoch": 0.096,
"grad_norm": 0.540140688419342,
"learning_rate": 0.0001916,
"loss": 7.2069,
"step": 480
},
{
"epoch": 0.097,
"grad_norm": 0.6079742908477783,
"learning_rate": 0.00019360000000000002,
"loss": 6.9598,
"step": 485
},
{
"epoch": 0.098,
"grad_norm": 0.5649901628494263,
"learning_rate": 0.0001956,
"loss": 7.2093,
"step": 490
},
{
"epoch": 0.099,
"grad_norm": 0.39070388674736023,
"learning_rate": 0.0001976,
"loss": 7.11,
"step": 495
},
{
"epoch": 0.1,
"grad_norm": 0.6088619232177734,
"learning_rate": 0.0001996,
"loss": 7.0,
"step": 500
},
{
"epoch": 0.101,
"grad_norm": 0.5481492877006531,
"learning_rate": 0.00019999961008995606,
"loss": 6.9314,
"step": 505
},
{
"epoch": 0.102,
"grad_norm": 0.7485499978065491,
"learning_rate": 0.0001999980260856137,
"loss": 7.0109,
"step": 510
},
{
"epoch": 0.103,
"grad_norm": 0.5922184586524963,
"learning_rate": 0.000199995223636881,
"loss": 7.0429,
"step": 515
},
{
"epoch": 0.104,
"grad_norm": 0.6894124150276184,
"learning_rate": 0.00019999120277790477,
"loss": 6.836,
"step": 520
},
{
"epoch": 0.105,
"grad_norm": 0.5878778100013733,
"learning_rate": 0.00019998596355767805,
"loss": 7.054,
"step": 525
},
{
"epoch": 0.106,
"grad_norm": 0.6900726556777954,
"learning_rate": 0.000199979506040039,
"loss": 7.0141,
"step": 530
},
{
"epoch": 0.107,
"grad_norm": 0.5072543621063232,
"learning_rate": 0.00019997183030367048,
"loss": 6.9427,
"step": 535
},
{
"epoch": 0.108,
"grad_norm": 0.6441262364387512,
"learning_rate": 0.00019996293644209887,
"loss": 7.0172,
"step": 540
},
{
"epoch": 0.109,
"grad_norm": 0.4545087516307831,
"learning_rate": 0.0001999528245636931,
"loss": 6.991,
"step": 545
},
{
"epoch": 0.11,
"grad_norm": 0.6167481541633606,
"learning_rate": 0.00019994149479166324,
"loss": 7.0618,
"step": 550
},
{
"epoch": 0.111,
"grad_norm": 0.6698728799819946,
"learning_rate": 0.00019992894726405893,
"loss": 6.8868,
"step": 555
},
{
"epoch": 0.112,
"grad_norm": 0.6254208087921143,
"learning_rate": 0.00019991518213376787,
"loss": 7.0001,
"step": 560
},
{
"epoch": 0.113,
"grad_norm": 0.7478207945823669,
"learning_rate": 0.00019990019956851382,
"loss": 7.0042,
"step": 565
},
{
"epoch": 0.114,
"grad_norm": 0.49813634157180786,
"learning_rate": 0.0001998839997508546,
"loss": 6.9408,
"step": 570
},
{
"epoch": 0.115,
"grad_norm": 0.8321104645729065,
"learning_rate": 0.00019986658287817987,
"loss": 6.9307,
"step": 575
},
{
"epoch": 0.116,
"grad_norm": 0.5029225945472717,
"learning_rate": 0.00019984794916270876,
"loss": 6.954,
"step": 580
},
{
"epoch": 0.117,
"grad_norm": 0.6227285265922546,
"learning_rate": 0.00019982809883148722,
"loss": 6.9611,
"step": 585
},
{
"epoch": 0.118,
"grad_norm": 0.6020491123199463,
"learning_rate": 0.00019980703212638522,
"loss": 6.9747,
"step": 590
},
{
"epoch": 0.119,
"grad_norm": 0.5989589095115662,
"learning_rate": 0.00019978474930409395,
"loss": 6.9523,
"step": 595
},
{
"epoch": 0.12,
"grad_norm": 0.4419194757938385,
"learning_rate": 0.00019976125063612252,
"loss": 6.8444,
"step": 600
},
{
"epoch": 0.121,
"grad_norm": 0.4280748963356018,
"learning_rate": 0.00019973653640879485,
"loss": 6.8869,
"step": 605
},
{
"epoch": 0.122,
"grad_norm": 0.6325187683105469,
"learning_rate": 0.00019971060692324598,
"loss": 6.8637,
"step": 610
},
{
"epoch": 0.123,
"grad_norm": 0.5768767595291138,
"learning_rate": 0.00019968346249541846,
"loss": 6.8622,
"step": 615
},
{
"epoch": 0.124,
"grad_norm": 0.46739277243614197,
"learning_rate": 0.00019965510345605866,
"loss": 6.8758,
"step": 620
},
{
"epoch": 0.125,
"grad_norm": 0.4968409240245819,
"learning_rate": 0.0001996255301507125,
"loss": 6.8271,
"step": 625
},
{
"epoch": 0.126,
"grad_norm": 0.5342600345611572,
"learning_rate": 0.00019959474293972129,
"loss": 6.927,
"step": 630
},
{
"epoch": 0.127,
"grad_norm": 0.5409016013145447,
"learning_rate": 0.00019956274219821757,
"loss": 6.9234,
"step": 635
},
{
"epoch": 0.128,
"grad_norm": 0.4150596261024475,
"learning_rate": 0.00019952952831612026,
"loss": 6.936,
"step": 640
},
{
"epoch": 0.129,
"grad_norm": 0.5268542766571045,
"learning_rate": 0.00019949510169813003,
"loss": 6.6226,
"step": 645
},
{
"epoch": 0.13,
"grad_norm": 0.5258546471595764,
"learning_rate": 0.00019945946276372434,
"loss": 6.8606,
"step": 650
},
{
"epoch": 0.131,
"grad_norm": 0.5089524388313293,
"learning_rate": 0.00019942261194715236,
"loss": 6.8858,
"step": 655
},
{
"epoch": 0.132,
"grad_norm": 0.6068436503410339,
"learning_rate": 0.00019938454969742968,
"loss": 6.9261,
"step": 660
},
{
"epoch": 0.133,
"grad_norm": 0.661700963973999,
"learning_rate": 0.00019934527647833276,
"loss": 6.895,
"step": 665
},
{
"epoch": 0.134,
"grad_norm": 0.46374189853668213,
"learning_rate": 0.00019930479276839344,
"loss": 6.6465,
"step": 670
},
{
"epoch": 0.135,
"grad_norm": 0.3547118306159973,
"learning_rate": 0.0001992630990608929,
"loss": 6.8859,
"step": 675
},
{
"epoch": 0.136,
"grad_norm": 0.5092146992683411,
"learning_rate": 0.00019922019586385585,
"loss": 6.6581,
"step": 680
},
{
"epoch": 0.137,
"grad_norm": 0.3911869525909424,
"learning_rate": 0.00019917608370004417,
"loss": 6.8095,
"step": 685
},
{
"epoch": 0.138,
"grad_norm": 0.6035128831863403,
"learning_rate": 0.00019913076310695068,
"loss": 6.8519,
"step": 690
},
{
"epoch": 0.139,
"grad_norm": 0.4681578576564789,
"learning_rate": 0.00019908423463679248,
"loss": 6.924,
"step": 695
},
{
"epoch": 0.14,
"grad_norm": 0.6169058084487915,
"learning_rate": 0.0001990364988565043,
"loss": 6.5598,
"step": 700
},
{
"epoch": 0.141,
"grad_norm": 0.4181090295314789,
"learning_rate": 0.00019898755634773158,
"loss": 6.7711,
"step": 705
},
{
"epoch": 0.142,
"grad_norm": 0.7568718194961548,
"learning_rate": 0.00019893740770682335,
"loss": 6.7187,
"step": 710
},
{
"epoch": 0.143,
"grad_norm": 0.6706321835517883,
"learning_rate": 0.0001988860535448249,
"loss": 6.7352,
"step": 715
},
{
"epoch": 0.144,
"grad_norm": 0.6102882623672485,
"learning_rate": 0.00019883349448747062,
"loss": 6.8037,
"step": 720
},
{
"epoch": 0.145,
"grad_norm": 0.6073884963989258,
"learning_rate": 0.0001987797311751759,
"loss": 6.8059,
"step": 725
},
{
"epoch": 0.146,
"grad_norm": 0.6573454737663269,
"learning_rate": 0.00019872476426302982,
"loss": 6.6057,
"step": 730
},
{
"epoch": 0.147,
"grad_norm": 0.4902370870113373,
"learning_rate": 0.0001986685944207868,
"loss": 6.7349,
"step": 735
},
{
"epoch": 0.148,
"grad_norm": 0.469754695892334,
"learning_rate": 0.0001986112223328587,
"loss": 6.783,
"step": 740
},
{
"epoch": 0.149,
"grad_norm": 0.5391649603843689,
"learning_rate": 0.00019855264869830629,
"loss": 6.6472,
"step": 745
},
{
"epoch": 0.15,
"grad_norm": 0.501196563243866,
"learning_rate": 0.00019849287423083078,
"loss": 6.6748,
"step": 750
},
{
"epoch": 0.151,
"grad_norm": 0.8189754486083984,
"learning_rate": 0.00019843189965876526,
"loss": 6.8497,
"step": 755
},
{
"epoch": 0.152,
"grad_norm": 0.6332266926765442,
"learning_rate": 0.00019836972572506557,
"loss": 6.7451,
"step": 760
},
{
"epoch": 0.153,
"grad_norm": 0.8133648037910461,
"learning_rate": 0.00019830635318730154,
"loss": 6.8109,
"step": 765
},
{
"epoch": 0.154,
"grad_norm": 0.5993229746818542,
"learning_rate": 0.00019824178281764753,
"loss": 6.5225,
"step": 770
},
{
"epoch": 0.155,
"grad_norm": 0.38865023851394653,
"learning_rate": 0.00019817601540287306,
"loss": 6.653,
"step": 775
},
{
"epoch": 0.156,
"grad_norm": 0.6270468235015869,
"learning_rate": 0.0001981090517443334,
"loss": 6.5849,
"step": 780
},
{
"epoch": 0.157,
"grad_norm": 0.5338872075080872,
"learning_rate": 0.0001980408926579596,
"loss": 6.6997,
"step": 785
},
{
"epoch": 0.158,
"grad_norm": 0.7134827375411987,
"learning_rate": 0.00019797153897424852,
"loss": 6.6264,
"step": 790
},
{
"epoch": 0.159,
"grad_norm": 0.4080445170402527,
"learning_rate": 0.000197900991538253,
"loss": 6.6574,
"step": 795
},
{
"epoch": 0.16,
"grad_norm": 0.42877915501594543,
"learning_rate": 0.00019782925120957124,
"loss": 6.6608,
"step": 800
},
{
"epoch": 0.161,
"grad_norm": 0.43775516748428345,
"learning_rate": 0.00019775631886233654,
"loss": 6.679,
"step": 805
},
{
"epoch": 0.162,
"grad_norm": 0.5000062584877014,
"learning_rate": 0.0001976821953852065,
"loss": 6.6203,
"step": 810
},
{
"epoch": 0.163,
"grad_norm": 0.548990786075592,
"learning_rate": 0.00019760688168135232,
"loss": 6.6727,
"step": 815
},
{
"epoch": 0.164,
"grad_norm": 0.6624634265899658,
"learning_rate": 0.00019753037866844771,
"loss": 6.781,
"step": 820
},
{
"epoch": 0.165,
"grad_norm": 0.4716901183128357,
"learning_rate": 0.00019745268727865774,
"loss": 6.6656,
"step": 825
},
{
"epoch": 0.166,
"grad_norm": 0.4770507216453552,
"learning_rate": 0.00019737380845862745,
"loss": 6.6563,
"step": 830
},
{
"epoch": 0.167,
"grad_norm": 0.5978116989135742,
"learning_rate": 0.0001972937431694704,
"loss": 6.7225,
"step": 835
},
{
"epoch": 0.168,
"grad_norm": 0.470944344997406,
"learning_rate": 0.00019721249238675688,
"loss": 6.7136,
"step": 840
},
{
"epoch": 0.169,
"grad_norm": 0.48099949955940247,
"learning_rate": 0.000197130057100502,
"loss": 6.7351,
"step": 845
},
{
"epoch": 0.17,
"grad_norm": 0.5023111701011658,
"learning_rate": 0.00019704643831515374,
"loss": 6.693,
"step": 850
},
{
"epoch": 0.171,
"grad_norm": 0.4576558470726013,
"learning_rate": 0.0001969616370495806,
"loss": 6.7353,
"step": 855
},
{
"epoch": 0.172,
"grad_norm": 0.530335009098053,
"learning_rate": 0.00019687565433705926,
"loss": 6.5784,
"step": 860
},
{
"epoch": 0.173,
"grad_norm": 0.5121427774429321,
"learning_rate": 0.00019678849122526187,
"loss": 6.6563,
"step": 865
},
{
"epoch": 0.174,
"grad_norm": 0.3545079827308655,
"learning_rate": 0.00019670014877624353,
"loss": 6.544,
"step": 870
},
{
"epoch": 0.175,
"grad_norm": 0.36093252897262573,
"learning_rate": 0.00019661062806642903,
"loss": 6.5394,
"step": 875
},
{
"epoch": 0.176,
"grad_norm": 0.3128730356693268,
"learning_rate": 0.0001965199301866,
"loss": 6.5584,
"step": 880
},
{
"epoch": 0.177,
"grad_norm": 0.43507492542266846,
"learning_rate": 0.00019642805624188147,
"loss": 6.5066,
"step": 885
},
{
"epoch": 0.178,
"grad_norm": 0.48262467980384827,
"learning_rate": 0.0001963350073517285,
"loss": 6.4535,
"step": 890
},
{
"epoch": 0.179,
"grad_norm": 0.6799952983856201,
"learning_rate": 0.0001962407846499124,
"loss": 6.3919,
"step": 895
},
{
"epoch": 0.18,
"grad_norm": 0.37337756156921387,
"learning_rate": 0.0001961453892845071,
"loss": 6.4093,
"step": 900
},
{
"epoch": 0.181,
"grad_norm": 0.47801485657691956,
"learning_rate": 0.00019604882241787498,
"loss": 6.6047,
"step": 905
},
{
"epoch": 0.182,
"grad_norm": 0.6047532558441162,
"learning_rate": 0.0001959510852266529,
"loss": 6.5754,
"step": 910
},
{
"epoch": 0.183,
"grad_norm": 0.6003972887992859,
"learning_rate": 0.0001958521789017376,
"loss": 6.599,
"step": 915
},
{
"epoch": 0.184,
"grad_norm": 0.5080412030220032,
"learning_rate": 0.00019575210464827149,
"loss": 6.5061,
"step": 920
},
{
"epoch": 0.185,
"grad_norm": 0.44362491369247437,
"learning_rate": 0.0001956508636856278,
"loss": 6.5872,
"step": 925
},
{
"epoch": 0.186,
"grad_norm": 0.6508392691612244,
"learning_rate": 0.00019554845724739566,
"loss": 6.4992,
"step": 930
},
{
"epoch": 0.187,
"grad_norm": 0.5883591175079346,
"learning_rate": 0.00019544488658136523,
"loss": 6.4971,
"step": 935
},
{
"epoch": 0.188,
"grad_norm": 0.47867658734321594,
"learning_rate": 0.00019534015294951233,
"loss": 6.3813,
"step": 940
},
{
"epoch": 0.189,
"grad_norm": 0.5380808115005493,
"learning_rate": 0.00019523425762798329,
"loss": 6.5163,
"step": 945
},
{
"epoch": 0.19,
"grad_norm": 0.551408588886261,
"learning_rate": 0.00019512720190707913,
"loss": 6.4207,
"step": 950
},
{
"epoch": 0.191,
"grad_norm": 0.4695829451084137,
"learning_rate": 0.00019501898709124008,
"loss": 6.4578,
"step": 955
},
{
"epoch": 0.192,
"grad_norm": 0.5122077465057373,
"learning_rate": 0.00019490961449902946,
"loss": 6.3922,
"step": 960
},
{
"epoch": 0.193,
"grad_norm": 0.5563646554946899,
"learning_rate": 0.00019479908546311781,
"loss": 6.3827,
"step": 965
},
{
"epoch": 0.194,
"grad_norm": 0.364351361989975,
"learning_rate": 0.0001946874013302666,
"loss": 6.4519,
"step": 970
},
{
"epoch": 0.195,
"grad_norm": 0.5940439105033875,
"learning_rate": 0.0001945745634613117,
"loss": 6.6195,
"step": 975
},
{
"epoch": 0.196,
"grad_norm": 0.6122324466705322,
"learning_rate": 0.0001944605732311469,
"loss": 6.4159,
"step": 980
},
{
"epoch": 0.197,
"grad_norm": 0.6779868602752686,
"learning_rate": 0.00019434543202870725,
"loss": 6.4041,
"step": 985
},
{
"epoch": 0.198,
"grad_norm": 0.5750985145568848,
"learning_rate": 0.0001942291412569519,
"loss": 6.4273,
"step": 990
},
{
"epoch": 0.199,
"grad_norm": 0.7129701972007751,
"learning_rate": 0.00019411170233284727,
"loss": 6.3745,
"step": 995
},
{
"epoch": 0.2,
"grad_norm": 0.6493417024612427,
"learning_rate": 0.00019399311668734956,
"loss": 6.3816,
"step": 1000
},
{
"epoch": 0.201,
"grad_norm": 0.3835955858230591,
"learning_rate": 0.00019387338576538744,
"loss": 6.408,
"step": 1005
},
{
"epoch": 0.202,
"grad_norm": 0.7438299059867859,
"learning_rate": 0.0001937525110258444,
"loss": 6.4081,
"step": 1010
},
{
"epoch": 0.203,
"grad_norm": 0.36970216035842896,
"learning_rate": 0.00019363049394154094,
"loss": 6.2792,
"step": 1015
},
{
"epoch": 0.204,
"grad_norm": 0.38203170895576477,
"learning_rate": 0.00019350733599921683,
"loss": 6.4732,
"step": 1020
},
{
"epoch": 0.205,
"grad_norm": 0.5633097290992737,
"learning_rate": 0.00019338303869951269,
"loss": 6.3919,
"step": 1025
},
{
"epoch": 0.206,
"grad_norm": 0.4961247742176056,
"learning_rate": 0.00019325760355695188,
"loss": 6.3564,
"step": 1030
},
{
"epoch": 0.207,
"grad_norm": 0.3417356014251709,
"learning_rate": 0.00019313103209992204,
"loss": 6.3538,
"step": 1035
},
{
"epoch": 0.208,
"grad_norm": 0.4510824978351593,
"learning_rate": 0.0001930033258706564,
"loss": 6.2649,
"step": 1040
},
{
"epoch": 0.209,
"grad_norm": 0.5434358716011047,
"learning_rate": 0.00019287448642521513,
"loss": 6.461,
"step": 1045
},
{
"epoch": 0.21,
"grad_norm": 0.44008851051330566,
"learning_rate": 0.00019274451533346615,
"loss": 6.2933,
"step": 1050
},
{
"epoch": 0.211,
"grad_norm": 0.4456416070461273,
"learning_rate": 0.00019261341417906621,
"loss": 6.4106,
"step": 1055
},
{
"epoch": 0.212,
"grad_norm": 0.3489581048488617,
"learning_rate": 0.0001924811845594415,
"loss": 6.4071,
"step": 1060
},
{
"epoch": 0.213,
"grad_norm": 0.38813433051109314,
"learning_rate": 0.00019234782808576824,
"loss": 6.4609,
"step": 1065
},
{
"epoch": 0.214,
"grad_norm": 0.8258797526359558,
"learning_rate": 0.00019221334638295294,
"loss": 6.3388,
"step": 1070
},
{
"epoch": 0.215,
"grad_norm": 0.7194433212280273,
"learning_rate": 0.00019207774108961272,
"loss": 6.4124,
"step": 1075
},
{
"epoch": 0.216,
"grad_norm": 0.4413435161113739,
"learning_rate": 0.0001919410138580553,
"loss": 6.3415,
"step": 1080
},
{
"epoch": 0.217,
"grad_norm": 0.5122642517089844,
"learning_rate": 0.0001918031663542588,
"loss": 6.3945,
"step": 1085
},
{
"epoch": 0.218,
"grad_norm": 0.5478972792625427,
"learning_rate": 0.00019166420025785164,
"loss": 6.213,
"step": 1090
},
{
"epoch": 0.219,
"grad_norm": 0.3870508670806885,
"learning_rate": 0.00019152411726209176,
"loss": 6.4148,
"step": 1095
},
{
"epoch": 0.22,
"grad_norm": 0.4939492642879486,
"learning_rate": 0.0001913829190738463,
"loss": 6.3511,
"step": 1100
},
{
"epoch": 0.221,
"grad_norm": 0.4421197772026062,
"learning_rate": 0.00019124060741357063,
"loss": 6.2141,
"step": 1105
},
{
"epoch": 0.222,
"grad_norm": 0.4341946542263031,
"learning_rate": 0.0001910971840152874,
"loss": 6.364,
"step": 1110
},
{
"epoch": 0.223,
"grad_norm": 0.5682588219642639,
"learning_rate": 0.00019095265062656544,
"loss": 6.362,
"step": 1115
},
{
"epoch": 0.224,
"grad_norm": 0.5375432968139648,
"learning_rate": 0.00019080700900849851,
"loss": 6.3539,
"step": 1120
},
{
"epoch": 0.225,
"grad_norm": 0.45399194955825806,
"learning_rate": 0.00019066026093568378,
"loss": 6.1695,
"step": 1125
},
{
"epoch": 0.226,
"grad_norm": 0.3457292318344116,
"learning_rate": 0.00019051240819620014,
"loss": 6.3994,
"step": 1130
},
{
"epoch": 0.227,
"grad_norm": 0.40977784991264343,
"learning_rate": 0.00019036345259158667,
"loss": 6.3785,
"step": 1135
},
{
"epoch": 0.228,
"grad_norm": 0.4201465845108032,
"learning_rate": 0.00019021339593682028,
"loss": 6.2701,
"step": 1140
},
{
"epoch": 0.229,
"grad_norm": 0.46519070863723755,
"learning_rate": 0.00019006224006029406,
"loss": 6.2397,
"step": 1145
},
{
"epoch": 0.23,
"grad_norm": 0.44138190150260925,
"learning_rate": 0.00018990998680379456,
"loss": 6.4213,
"step": 1150
},
{
"epoch": 0.231,
"grad_norm": 0.6856333613395691,
"learning_rate": 0.00018975663802247976,
"loss": 6.3462,
"step": 1155
},
{
"epoch": 0.232,
"grad_norm": 0.4140591621398926,
"learning_rate": 0.0001896021955848561,
"loss": 6.2644,
"step": 1160
},
{
"epoch": 0.233,
"grad_norm": 0.4577389657497406,
"learning_rate": 0.000189446661372756,
"loss": 6.4065,
"step": 1165
},
{
"epoch": 0.234,
"grad_norm": 0.4256591498851776,
"learning_rate": 0.0001892900372813147,
"loss": 6.241,
"step": 1170
},
{
"epoch": 0.235,
"grad_norm": 0.4557815492153168,
"learning_rate": 0.00018913232521894732,
"loss": 6.2398,
"step": 1175
},
{
"epoch": 0.236,
"grad_norm": 0.533744215965271,
"learning_rate": 0.00018897352710732564,
"loss": 6.305,
"step": 1180
},
{
"epoch": 0.237,
"grad_norm": 0.4700031578540802,
"learning_rate": 0.00018881364488135448,
"loss": 6.1193,
"step": 1185
},
{
"epoch": 0.238,
"grad_norm": 0.4799516201019287,
"learning_rate": 0.00018865268048914828,
"loss": 6.2693,
"step": 1190
},
{
"epoch": 0.239,
"grad_norm": 0.517643928527832,
"learning_rate": 0.00018849063589200743,
"loss": 6.2634,
"step": 1195
},
{
"epoch": 0.24,
"grad_norm": 0.36942240595817566,
"learning_rate": 0.00018832751306439418,
"loss": 6.2712,
"step": 1200
},
{
"epoch": 0.241,
"grad_norm": 0.3681972026824951,
"learning_rate": 0.0001881633139939087,
"loss": 6.2223,
"step": 1205
},
{
"epoch": 0.242,
"grad_norm": 0.41460973024368286,
"learning_rate": 0.00018799804068126485,
"loss": 6.1747,
"step": 1210
},
{
"epoch": 0.243,
"grad_norm": 0.43505749106407166,
"learning_rate": 0.00018783169514026578,
"loss": 6.1742,
"step": 1215
},
{
"epoch": 0.244,
"grad_norm": 0.5257707238197327,
"learning_rate": 0.00018766427939777945,
"loss": 6.1276,
"step": 1220
},
{
"epoch": 0.245,
"grad_norm": 0.5611069798469543,
"learning_rate": 0.0001874957954937138,
"loss": 6.2122,
"step": 1225
},
{
"epoch": 0.246,
"grad_norm": 0.6506351828575134,
"learning_rate": 0.00018732624548099204,
"loss": 6.27,
"step": 1230
},
{
"epoch": 0.247,
"grad_norm": 0.7269455790519714,
"learning_rate": 0.00018715563142552758,
"loss": 6.1688,
"step": 1235
},
{
"epoch": 0.248,
"grad_norm": 0.3960244357585907,
"learning_rate": 0.0001869839554061988,
"loss": 6.1849,
"step": 1240
},
{
"epoch": 0.249,
"grad_norm": 0.387102872133255,
"learning_rate": 0.00018681121951482393,
"loss": 6.135,
"step": 1245
},
{
"epoch": 0.25,
"grad_norm": 0.3663654923439026,
"learning_rate": 0.00018663742585613518,
"loss": 6.3214,
"step": 1250
},
{
"epoch": 0.251,
"grad_norm": 0.40777140855789185,
"learning_rate": 0.0001864625765477535,
"loss": 6.2307,
"step": 1255
},
{
"epoch": 0.252,
"grad_norm": 0.4322759211063385,
"learning_rate": 0.0001862866737201625,
"loss": 6.1738,
"step": 1260
},
{
"epoch": 0.253,
"grad_norm": 0.4331606924533844,
"learning_rate": 0.00018610971951668265,
"loss": 6.0921,
"step": 1265
},
{
"epoch": 0.254,
"grad_norm": 0.4313614070415497,
"learning_rate": 0.00018593171609344503,
"loss": 6.2658,
"step": 1270
},
{
"epoch": 0.255,
"grad_norm": 0.5980773568153381,
"learning_rate": 0.00018575266561936523,
"loss": 6.1688,
"step": 1275
},
{
"epoch": 0.256,
"grad_norm": 0.42396366596221924,
"learning_rate": 0.00018557257027611675,
"loss": 6.0981,
"step": 1280
},
{
"epoch": 0.257,
"grad_norm": 0.45760318636894226,
"learning_rate": 0.0001853914322581045,
"loss": 6.0753,
"step": 1285
},
{
"epoch": 0.258,
"grad_norm": 0.3706681728363037,
"learning_rate": 0.0001852092537724381,
"loss": 6.2031,
"step": 1290
},
{
"epoch": 0.259,
"grad_norm": 0.4272838234901428,
"learning_rate": 0.00018502603703890488,
"loss": 6.2135,
"step": 1295
},
{
"epoch": 0.26,
"grad_norm": 0.33726340532302856,
"learning_rate": 0.0001848417842899429,
"loss": 6.1878,
"step": 1300
},
{
"epoch": 0.261,
"grad_norm": 0.36913183331489563,
"learning_rate": 0.0001846564977706138,
"loss": 6.1218,
"step": 1305
},
{
"epoch": 0.262,
"grad_norm": 0.48305293917655945,
"learning_rate": 0.00018447017973857532,
"loss": 6.2088,
"step": 1310
},
{
"epoch": 0.263,
"grad_norm": 0.4010171890258789,
"learning_rate": 0.0001842828324640539,
"loss": 6.0917,
"step": 1315
},
{
"epoch": 0.264,
"grad_norm": 0.49192050099372864,
"learning_rate": 0.00018409445822981693,
"loss": 6.0712,
"step": 1320
},
{
"epoch": 0.265,
"grad_norm": 0.3645775318145752,
"learning_rate": 0.000183905059331145,
"loss": 6.0423,
"step": 1325
},
{
"epoch": 0.266,
"grad_norm": 0.49323707818984985,
"learning_rate": 0.000183714638075804,
"loss": 6.0686,
"step": 1330
},
{
"epoch": 0.267,
"grad_norm": 0.5149185657501221,
"learning_rate": 0.00018352319678401676,
"loss": 6.1107,
"step": 1335
},
{
"epoch": 0.268,
"grad_norm": 0.3971852660179138,
"learning_rate": 0.000183330737788435,
"loss": 6.1647,
"step": 1340
},
{
"epoch": 0.269,
"grad_norm": 0.35680779814720154,
"learning_rate": 0.00018313726343411086,
"loss": 6.1133,
"step": 1345
},
{
"epoch": 0.27,
"grad_norm": 0.3231695890426636,
"learning_rate": 0.00018294277607846832,
"loss": 6.1486,
"step": 1350
},
{
"epoch": 0.271,
"grad_norm": 0.40682390332221985,
"learning_rate": 0.00018274727809127438,
"loss": 6.1807,
"step": 1355
},
{
"epoch": 0.272,
"grad_norm": 0.4406977891921997,
"learning_rate": 0.00018255077185461038,
"loss": 6.1073,
"step": 1360
},
{
"epoch": 0.273,
"grad_norm": 0.4062846004962921,
"learning_rate": 0.00018235325976284275,
"loss": 6.0636,
"step": 1365
},
{
"epoch": 0.274,
"grad_norm": 0.37812697887420654,
"learning_rate": 0.00018215474422259402,
"loss": 6.0176,
"step": 1370
},
{
"epoch": 0.275,
"grad_norm": 0.39671772718429565,
"learning_rate": 0.0001819552276527134,
"loss": 6.136,
"step": 1375
},
{
"epoch": 0.276,
"grad_norm": 0.4100985825061798,
"learning_rate": 0.0001817547124842473,
"loss": 6.1366,
"step": 1380
},
{
"epoch": 0.277,
"grad_norm": 0.47902652621269226,
"learning_rate": 0.00018155320116040982,
"loss": 6.1621,
"step": 1385
},
{
"epoch": 0.278,
"grad_norm": 0.40917810797691345,
"learning_rate": 0.0001813506961365528,
"loss": 6.2207,
"step": 1390
},
{
"epoch": 0.279,
"grad_norm": 0.39686450362205505,
"learning_rate": 0.00018114719988013612,
"loss": 5.9831,
"step": 1395
},
{
"epoch": 0.28,
"grad_norm": 0.43156924843788147,
"learning_rate": 0.00018094271487069735,
"loss": 6.0139,
"step": 1400
},
{
"epoch": 0.281,
"grad_norm": 0.4098886251449585,
"learning_rate": 0.00018073724359982186,
"loss": 6.0446,
"step": 1405
},
{
"epoch": 0.282,
"grad_norm": 0.6339080929756165,
"learning_rate": 0.0001805307885711122,
"loss": 6.1193,
"step": 1410
},
{
"epoch": 0.283,
"grad_norm": 0.42279052734375,
"learning_rate": 0.0001803233523001578,
"loss": 6.099,
"step": 1415
},
{
"epoch": 0.284,
"grad_norm": 0.3999897241592407,
"learning_rate": 0.00018011493731450413,
"loss": 6.0587,
"step": 1420
},
{
"epoch": 0.285,
"grad_norm": 0.4981236457824707,
"learning_rate": 0.00017990554615362198,
"loss": 5.9889,
"step": 1425
},
{
"epoch": 0.286,
"grad_norm": 0.41206473112106323,
"learning_rate": 0.00017969518136887663,
"loss": 6.0198,
"step": 1430
},
{
"epoch": 0.287,
"grad_norm": 0.4251125454902649,
"learning_rate": 0.00017948384552349657,
"loss": 6.0798,
"step": 1435
},
{
"epoch": 0.288,
"grad_norm": 0.4591384828090668,
"learning_rate": 0.00017927154119254236,
"loss": 6.145,
"step": 1440
},
{
"epoch": 0.289,
"grad_norm": 0.4861222803592682,
"learning_rate": 0.0001790582709628753,
"loss": 6.0633,
"step": 1445
},
{
"epoch": 0.29,
"grad_norm": 0.36734747886657715,
"learning_rate": 0.00017884403743312582,
"loss": 6.0409,
"step": 1450
},
{
"epoch": 0.291,
"grad_norm": 0.3610234260559082,
"learning_rate": 0.00017862884321366188,
"loss": 6.0942,
"step": 1455
},
{
"epoch": 0.292,
"grad_norm": 0.379261314868927,
"learning_rate": 0.00017841269092655715,
"loss": 6.0181,
"step": 1460
},
{
"epoch": 0.293,
"grad_norm": 0.35124316811561584,
"learning_rate": 0.000178195583205559,
"loss": 6.0369,
"step": 1465
},
{
"epoch": 0.294,
"grad_norm": 0.3410089910030365,
"learning_rate": 0.00017797752269605653,
"loss": 5.942,
"step": 1470
},
{
"epoch": 0.295,
"grad_norm": 0.4798443913459778,
"learning_rate": 0.0001777585120550482,
"loss": 5.9586,
"step": 1475
},
{
"epoch": 0.296,
"grad_norm": 0.33171337842941284,
"learning_rate": 0.0001775385539511096,
"loss": 5.9432,
"step": 1480
},
{
"epoch": 0.297,
"grad_norm": 0.3579927980899811,
"learning_rate": 0.00017731765106436073,
"loss": 5.9876,
"step": 1485
},
{
"epoch": 0.298,
"grad_norm": 0.41850897669792175,
"learning_rate": 0.00017709580608643363,
"loss": 5.8325,
"step": 1490
},
{
"epoch": 0.299,
"grad_norm": 0.37741610407829285,
"learning_rate": 0.00017687302172043933,
"loss": 5.919,
"step": 1495
},
{
"epoch": 0.3,
"grad_norm": 0.41643622517585754,
"learning_rate": 0.00017664930068093498,
"loss": 6.036,
"step": 1500
},
{
"epoch": 0.301,
"grad_norm": 0.3685619831085205,
"learning_rate": 0.0001764246456938909,
"loss": 6.0009,
"step": 1505
},
{
"epoch": 0.302,
"grad_norm": 0.3619703948497772,
"learning_rate": 0.0001761990594966572,
"loss": 5.9713,
"step": 1510
},
{
"epoch": 0.303,
"grad_norm": 0.3995906710624695,
"learning_rate": 0.00017597254483793048,
"loss": 6.0567,
"step": 1515
},
{
"epoch": 0.304,
"grad_norm": 0.38931819796562195,
"learning_rate": 0.00017574510447772039,
"loss": 5.9885,
"step": 1520
},
{
"epoch": 0.305,
"grad_norm": 0.451968252658844,
"learning_rate": 0.00017551674118731591,
"loss": 5.9656,
"step": 1525
},
{
"epoch": 0.306,
"grad_norm": 0.5130440592765808,
"learning_rate": 0.00017528745774925172,
"loss": 6.0424,
"step": 1530
},
{
"epoch": 0.307,
"grad_norm": 0.39372026920318604,
"learning_rate": 0.00017505725695727412,
"loss": 5.9762,
"step": 1535
},
{
"epoch": 0.308,
"grad_norm": 0.46877938508987427,
"learning_rate": 0.00017482614161630714,
"loss": 5.8472,
"step": 1540
},
{
"epoch": 0.309,
"grad_norm": 0.3462335169315338,
"learning_rate": 0.00017459411454241822,
"loss": 6.0315,
"step": 1545
},
{
"epoch": 0.31,
"grad_norm": 0.35697898268699646,
"learning_rate": 0.0001743611785627841,
"loss": 6.0914,
"step": 1550
},
{
"epoch": 0.311,
"grad_norm": 0.34111288189888,
"learning_rate": 0.0001741273365156561,
"loss": 5.9358,
"step": 1555
},
{
"epoch": 0.312,
"grad_norm": 0.41930457949638367,
"learning_rate": 0.0001738925912503259,
"loss": 5.9524,
"step": 1560
},
{
"epoch": 0.313,
"grad_norm": 0.49193844199180603,
"learning_rate": 0.00017365694562709034,
"loss": 5.8958,
"step": 1565
},
{
"epoch": 0.314,
"grad_norm": 0.4947580397129059,
"learning_rate": 0.00017342040251721702,
"loss": 5.9175,
"step": 1570
},
{
"epoch": 0.315,
"grad_norm": 0.4703611135482788,
"learning_rate": 0.0001731829648029091,
"loss": 5.9377,
"step": 1575
},
{
"epoch": 0.316,
"grad_norm": 0.3478267788887024,
"learning_rate": 0.00017294463537727024,
"loss": 5.8391,
"step": 1580
},
{
"epoch": 0.317,
"grad_norm": 0.3845519721508026,
"learning_rate": 0.0001727054171442692,
"loss": 5.9738,
"step": 1585
},
{
"epoch": 0.318,
"grad_norm": 0.3889566957950592,
"learning_rate": 0.0001724653130187047,
"loss": 5.8768,
"step": 1590
},
{
"epoch": 0.319,
"grad_norm": 0.5290016531944275,
"learning_rate": 0.0001722243259261697,
"loss": 5.925,
"step": 1595
},
{
"epoch": 0.32,
"grad_norm": 0.3517289459705353,
"learning_rate": 0.0001719824588030159,
"loss": 6.0385,
"step": 1600
},
{
"epoch": 0.321,
"grad_norm": 0.49223145842552185,
"learning_rate": 0.00017173971459631787,
"loss": 5.9177,
"step": 1605
},
{
"epoch": 0.322,
"grad_norm": 0.4061746597290039,
"learning_rate": 0.00017149609626383717,
"loss": 5.962,
"step": 1610
},
{
"epoch": 0.323,
"grad_norm": 0.47528573870658875,
"learning_rate": 0.00017125160677398626,
"loss": 5.9018,
"step": 1615
},
{
"epoch": 0.324,
"grad_norm": 0.42449259757995605,
"learning_rate": 0.0001710062491057925,
"loss": 5.9316,
"step": 1620
},
{
"epoch": 0.325,
"grad_norm": 0.3160227835178375,
"learning_rate": 0.00017076002624886154,
"loss": 6.0239,
"step": 1625
},
{
"epoch": 0.326,
"grad_norm": 0.4954349994659424,
"learning_rate": 0.00017051294120334125,
"loss": 5.9971,
"step": 1630
},
{
"epoch": 0.327,
"grad_norm": 0.3726606070995331,
"learning_rate": 0.00017026499697988493,
"loss": 5.9362,
"step": 1635
},
{
"epoch": 0.328,
"grad_norm": 0.38831502199172974,
"learning_rate": 0.00017001619659961467,
"loss": 6.0072,
"step": 1640
},
{
"epoch": 0.329,
"grad_norm": 0.3331487774848938,
"learning_rate": 0.00016976654309408464,
"loss": 6.0685,
"step": 1645
},
{
"epoch": 0.33,
"grad_norm": 0.5266425013542175,
"learning_rate": 0.000169516039505244,
"loss": 5.9523,
"step": 1650
},
{
"epoch": 0.331,
"grad_norm": 0.4450986683368683,
"learning_rate": 0.0001692646888853999,
"loss": 5.9295,
"step": 1655
},
{
"epoch": 0.332,
"grad_norm": 0.3169552981853485,
"learning_rate": 0.00016901249429718032,
"loss": 5.9039,
"step": 1660
},
{
"epoch": 0.333,
"grad_norm": 0.2805604040622711,
"learning_rate": 0.00016875945881349676,
"loss": 5.9543,
"step": 1665
},
{
"epoch": 0.334,
"grad_norm": 0.3343287706375122,
"learning_rate": 0.0001685055855175067,
"loss": 5.8581,
"step": 1670
},
{
"epoch": 0.335,
"grad_norm": 0.29907503724098206,
"learning_rate": 0.0001682508775025762,
"loss": 6.0683,
"step": 1675
},
{
"epoch": 0.336,
"grad_norm": 0.2978798449039459,
"learning_rate": 0.00016799533787224192,
"loss": 5.854,
"step": 1680
},
{
"epoch": 0.337,
"grad_norm": 0.3322925865650177,
"learning_rate": 0.00016773896974017373,
"loss": 5.8392,
"step": 1685
},
{
"epoch": 0.338,
"grad_norm": 0.4063414931297302,
"learning_rate": 0.00016748177623013638,
"loss": 6.0117,
"step": 1690
},
{
"epoch": 0.339,
"grad_norm": 0.36568233370780945,
"learning_rate": 0.00016722376047595164,
"loss": 5.8,
"step": 1695
},
{
"epoch": 0.34,
"grad_norm": 0.3385249972343445,
"learning_rate": 0.00016696492562145996,
"loss": 5.854,
"step": 1700
},
{
"epoch": 0.341,
"grad_norm": 0.3121187388896942,
"learning_rate": 0.00016670527482048246,
"loss": 6.0099,
"step": 1705
},
{
"epoch": 0.342,
"grad_norm": 0.30285727977752686,
"learning_rate": 0.00016644481123678217,
"loss": 5.8401,
"step": 1710
},
{
"epoch": 0.343,
"grad_norm": 0.3610534965991974,
"learning_rate": 0.00016618353804402568,
"loss": 5.9126,
"step": 1715
},
{
"epoch": 0.344,
"grad_norm": 0.3499062955379486,
"learning_rate": 0.00016592145842574433,
"loss": 5.8717,
"step": 1720
},
{
"epoch": 0.345,
"grad_norm": 0.3706279993057251,
"learning_rate": 0.00016565857557529566,
"loss": 5.8349,
"step": 1725
},
{
"epoch": 0.346,
"grad_norm": 0.3694944977760315,
"learning_rate": 0.00016539489269582416,
"loss": 5.7109,
"step": 1730
},
{
"epoch": 0.347,
"grad_norm": 0.30279800295829773,
"learning_rate": 0.00016513041300022255,
"loss": 5.8013,
"step": 1735
},
{
"epoch": 0.348,
"grad_norm": 0.44268837571144104,
"learning_rate": 0.00016486513971109243,
"loss": 5.6836,
"step": 1740
},
{
"epoch": 0.349,
"grad_norm": 0.3473615050315857,
"learning_rate": 0.0001645990760607051,
"loss": 5.7748,
"step": 1745
},
{
"epoch": 0.35,
"grad_norm": 0.34418827295303345,
"learning_rate": 0.0001643322252909622,
"loss": 5.8331,
"step": 1750
},
{
"epoch": 0.351,
"grad_norm": 0.27867886424064636,
"learning_rate": 0.00016406459065335615,
"loss": 5.8361,
"step": 1755
},
{
"epoch": 0.352,
"grad_norm": 0.33102256059646606,
"learning_rate": 0.00016379617540893056,
"loss": 5.782,
"step": 1760
},
{
"epoch": 0.353,
"grad_norm": 0.2792224884033203,
"learning_rate": 0.00016352698282824044,
"loss": 5.7017,
"step": 1765
},
{
"epoch": 0.354,
"grad_norm": 0.2662978768348694,
"learning_rate": 0.00016325701619131246,
"loss": 5.7476,
"step": 1770
},
{
"epoch": 0.355,
"grad_norm": 0.281979501247406,
"learning_rate": 0.00016298627878760487,
"loss": 5.7435,
"step": 1775
},
{
"epoch": 0.356,
"grad_norm": 0.2954462468624115,
"learning_rate": 0.00016271477391596753,
"loss": 5.734,
"step": 1780
},
{
"epoch": 0.357,
"grad_norm": 0.29816684126853943,
"learning_rate": 0.00016244250488460158,
"loss": 5.8916,
"step": 1785
},
{
"epoch": 0.358,
"grad_norm": 0.3801019489765167,
"learning_rate": 0.0001621694750110193,
"loss": 5.801,
"step": 1790
},
{
"epoch": 0.359,
"grad_norm": 0.42032888531684875,
"learning_rate": 0.00016189568762200348,
"loss": 5.789,
"step": 1795
},
{
"epoch": 0.36,
"grad_norm": 0.764586329460144,
"learning_rate": 0.00016162114605356703,
"loss": 5.834,
"step": 1800
},
{
"epoch": 0.361,
"grad_norm": 0.416716605424881,
"learning_rate": 0.00016134585365091243,
"loss": 6.0296,
"step": 1805
},
{
"epoch": 0.362,
"grad_norm": 0.4305168092250824,
"learning_rate": 0.00016106981376839066,
"loss": 5.7726,
"step": 1810
},
{
"epoch": 0.363,
"grad_norm": 0.3263167440891266,
"learning_rate": 0.00016079302976946055,
"loss": 5.7375,
"step": 1815
},
{
"epoch": 0.364,
"grad_norm": 0.39238011837005615,
"learning_rate": 0.0001605155050266478,
"loss": 5.7494,
"step": 1820
},
{
"epoch": 0.365,
"grad_norm": 0.43032458424568176,
"learning_rate": 0.00016023724292150385,
"loss": 5.8209,
"step": 1825
},
{
"epoch": 0.366,
"grad_norm": 0.29273220896720886,
"learning_rate": 0.00015995824684456465,
"loss": 5.7449,
"step": 1830
},
{
"epoch": 0.367,
"grad_norm": 0.3445495367050171,
"learning_rate": 0.00015967852019530926,
"loss": 5.6958,
"step": 1835
},
{
"epoch": 0.368,
"grad_norm": 0.30198732018470764,
"learning_rate": 0.0001593980663821187,
"loss": 5.7432,
"step": 1840
},
{
"epoch": 0.369,
"grad_norm": 0.46524691581726074,
"learning_rate": 0.0001591168888222342,
"loss": 5.7076,
"step": 1845
},
{
"epoch": 0.37,
"grad_norm": 0.27144256234169006,
"learning_rate": 0.00015883499094171554,
"loss": 5.7035,
"step": 1850
},
{
"epoch": 0.371,
"grad_norm": 0.41292163729667664,
"learning_rate": 0.0001585523761753994,
"loss": 5.9395,
"step": 1855
},
{
"epoch": 0.372,
"grad_norm": 0.3124617040157318,
"learning_rate": 0.00015826904796685762,
"loss": 5.724,
"step": 1860
},
{
"epoch": 0.373,
"grad_norm": 0.5617573857307434,
"learning_rate": 0.00015798500976835493,
"loss": 5.6804,
"step": 1865
},
{
"epoch": 0.374,
"grad_norm": 0.39303892850875854,
"learning_rate": 0.00015770026504080718,
"loss": 5.6761,
"step": 1870
},
{
"epoch": 0.375,
"grad_norm": 0.35757169127464294,
"learning_rate": 0.000157414817253739,
"loss": 5.8032,
"step": 1875
},
{
"epoch": 0.376,
"grad_norm": 0.36906924843788147,
"learning_rate": 0.00015712866988524155,
"loss": 5.6276,
"step": 1880
},
{
"epoch": 0.377,
"grad_norm": 0.31051650643348694,
"learning_rate": 0.0001568418264219303,
"loss": 5.7165,
"step": 1885
},
{
"epoch": 0.378,
"grad_norm": 0.4598417580127716,
"learning_rate": 0.0001565542903589023,
"loss": 5.6927,
"step": 1890
},
{
"epoch": 0.379,
"grad_norm": 0.3252059817314148,
"learning_rate": 0.0001562660651996937,
"loss": 5.6879,
"step": 1895
},
{
"epoch": 0.38,
"grad_norm": 0.3023173213005066,
"learning_rate": 0.00015597715445623712,
"loss": 5.6614,
"step": 1900
},
{
"epoch": 0.381,
"grad_norm": 0.3083731532096863,
"learning_rate": 0.00015568756164881882,
"loss": 5.6561,
"step": 1905
},
{
"epoch": 0.382,
"grad_norm": 0.375782310962677,
"learning_rate": 0.00015539729030603574,
"loss": 5.6885,
"step": 1910
},
{
"epoch": 0.383,
"grad_norm": 0.43237435817718506,
"learning_rate": 0.0001551063439647526,
"loss": 5.6874,
"step": 1915
},
{
"epoch": 0.384,
"grad_norm": 0.27824482321739197,
"learning_rate": 0.00015481472617005876,
"loss": 5.6668,
"step": 1920
},
{
"epoch": 0.385,
"grad_norm": 0.3259798586368561,
"learning_rate": 0.00015452244047522502,
"loss": 5.6314,
"step": 1925
},
{
"epoch": 0.386,
"grad_norm": 0.2962264120578766,
"learning_rate": 0.0001542294904416603,
"loss": 5.6399,
"step": 1930
},
{
"epoch": 0.387,
"grad_norm": 0.286247193813324,
"learning_rate": 0.00015393587963886835,
"loss": 5.6226,
"step": 1935
},
{
"epoch": 0.388,
"grad_norm": 0.29193416237831116,
"learning_rate": 0.0001536416116444041,
"loss": 5.6982,
"step": 1940
},
{
"epoch": 0.389,
"grad_norm": 0.36029288172721863,
"learning_rate": 0.0001533466900438303,
"loss": 5.6379,
"step": 1945
},
{
"epoch": 0.39,
"grad_norm": 0.29870983958244324,
"learning_rate": 0.0001530511184306734,
"loss": 5.7272,
"step": 1950
},
{
"epoch": 0.391,
"grad_norm": 0.30721089243888855,
"learning_rate": 0.00015275490040638038,
"loss": 5.6866,
"step": 1955
},
{
"epoch": 0.392,
"grad_norm": 0.41106119751930237,
"learning_rate": 0.00015245803958027434,
"loss": 5.7401,
"step": 1960
},
{
"epoch": 0.393,
"grad_norm": 0.3437632620334625,
"learning_rate": 0.0001521605395695108,
"loss": 5.6598,
"step": 1965
},
{
"epoch": 0.394,
"grad_norm": 0.5682230591773987,
"learning_rate": 0.00015186240399903342,
"loss": 5.7351,
"step": 1970
},
{
"epoch": 0.395,
"grad_norm": 0.3357604742050171,
"learning_rate": 0.00015156363650153012,
"loss": 5.7496,
"step": 1975
},
{
"epoch": 0.396,
"grad_norm": 0.2964901924133301,
"learning_rate": 0.0001512642407173885,
"loss": 5.7094,
"step": 1980
},
{
"epoch": 0.397,
"grad_norm": 0.3898102045059204,
"learning_rate": 0.00015096422029465178,
"loss": 5.6822,
"step": 1985
},
{
"epoch": 0.398,
"grad_norm": 0.39044174551963806,
"learning_rate": 0.0001506635788889741,
"loss": 5.6629,
"step": 1990
},
{
"epoch": 0.399,
"grad_norm": 0.42848286032676697,
"learning_rate": 0.0001503623201635761,
"loss": 5.6248,
"step": 1995
},
{
"epoch": 0.4,
"grad_norm": 0.3119700849056244,
"learning_rate": 0.0001500604477892003,
"loss": 5.5978,
"step": 2000
},
{
"epoch": 0.401,
"grad_norm": 0.359042227268219,
"learning_rate": 0.00014975796544406625,
"loss": 5.6446,
"step": 2005
},
{
"epoch": 0.402,
"grad_norm": 0.3751426935195923,
"learning_rate": 0.00014945487681382598,
"loss": 5.6572,
"step": 2010
},
{
"epoch": 0.403,
"grad_norm": 0.3175458610057831,
"learning_rate": 0.0001491511855915187,
"loss": 5.6355,
"step": 2015
},
{
"epoch": 0.404,
"grad_norm": 0.29330259561538696,
"learning_rate": 0.0001488468954775262,
"loss": 5.6697,
"step": 2020
},
{
"epoch": 0.405,
"grad_norm": 0.33121609687805176,
"learning_rate": 0.0001485420101795274,
"loss": 5.6004,
"step": 2025
},
{
"epoch": 0.406,
"grad_norm": 0.3290939927101135,
"learning_rate": 0.00014823653341245353,
"loss": 5.6227,
"step": 2030
},
{
"epoch": 0.407,
"grad_norm": 0.41140642762184143,
"learning_rate": 0.0001479304688984425,
"loss": 5.547,
"step": 2035
},
{
"epoch": 0.408,
"grad_norm": 0.3178607225418091,
"learning_rate": 0.0001476238203667939,
"loss": 5.6034,
"step": 2040
},
{
"epoch": 0.409,
"grad_norm": 0.31642797589302063,
"learning_rate": 0.00014731659155392332,
"loss": 5.5181,
"step": 2045
},
{
"epoch": 0.41,
"grad_norm": 0.42407357692718506,
"learning_rate": 0.00014700878620331684,
"loss": 5.6152,
"step": 2050
},
{
"epoch": 0.411,
"grad_norm": 0.28860345482826233,
"learning_rate": 0.00014670040806548555,
"loss": 5.6218,
"step": 2055
},
{
"epoch": 0.412,
"grad_norm": 0.3322913944721222,
"learning_rate": 0.0001463914608979197,
"loss": 5.5297,
"step": 2060
},
{
"epoch": 0.413,
"grad_norm": 0.3378022015094757,
"learning_rate": 0.0001460819484650431,
"loss": 5.641,
"step": 2065
},
{
"epoch": 0.414,
"grad_norm": 0.3152814507484436,
"learning_rate": 0.000145771874538167,
"loss": 5.6073,
"step": 2070
},
{
"epoch": 0.415,
"grad_norm": 0.318118155002594,
"learning_rate": 0.0001454612428954444,
"loss": 5.5902,
"step": 2075
},
{
"epoch": 0.416,
"grad_norm": 0.27085062861442566,
"learning_rate": 0.00014515005732182383,
"loss": 5.692,
"step": 2080
},
{
"epoch": 0.417,
"grad_norm": 0.26865479350090027,
"learning_rate": 0.00014483832160900326,
"loss": 5.6276,
"step": 2085
},
{
"epoch": 0.418,
"grad_norm": 0.2979885935783386,
"learning_rate": 0.00014452603955538397,
"loss": 5.6299,
"step": 2090
},
{
"epoch": 0.419,
"grad_norm": 0.3181059956550598,
"learning_rate": 0.00014421321496602428,
"loss": 5.5522,
"step": 2095
},
{
"epoch": 0.42,
"grad_norm": 0.27677199244499207,
"learning_rate": 0.00014389985165259308,
"loss": 5.6269,
"step": 2100
},
{
"epoch": 0.421,
"grad_norm": 0.35586413741111755,
"learning_rate": 0.00014358595343332342,
"loss": 5.5948,
"step": 2105
},
{
"epoch": 0.422,
"grad_norm": 0.2938143014907837,
"learning_rate": 0.00014327152413296608,
"loss": 5.516,
"step": 2110
},
{
"epoch": 0.423,
"grad_norm": 0.3539797067642212,
"learning_rate": 0.00014295656758274284,
"loss": 5.6014,
"step": 2115
},
{
"epoch": 0.424,
"grad_norm": 0.29920482635498047,
"learning_rate": 0.0001426410876202999,
"loss": 5.6152,
"step": 2120
},
{
"epoch": 0.425,
"grad_norm": 0.291869193315506,
"learning_rate": 0.00014232508808966098,
"loss": 5.6475,
"step": 2125
},
{
"epoch": 0.426,
"grad_norm": 0.3039844036102295,
"learning_rate": 0.00014200857284118066,
"loss": 5.6472,
"step": 2130
},
{
"epoch": 0.427,
"grad_norm": 0.3983248472213745,
"learning_rate": 0.00014169154573149737,
"loss": 5.6457,
"step": 2135
},
{
"epoch": 0.428,
"grad_norm": 0.3491370677947998,
"learning_rate": 0.00014137401062348638,
"loss": 5.5989,
"step": 2140
},
{
"epoch": 0.429,
"grad_norm": 0.38335534930229187,
"learning_rate": 0.0001410559713862128,
"loss": 5.5682,
"step": 2145
},
{
"epoch": 0.43,
"grad_norm": 0.4026370346546173,
"learning_rate": 0.00014073743189488435,
"loss": 5.6137,
"step": 2150
},
{
"epoch": 0.431,
"grad_norm": 0.3056047260761261,
"learning_rate": 0.00014041839603080422,
"loss": 5.5482,
"step": 2155
},
{
"epoch": 0.432,
"grad_norm": 0.2888528108596802,
"learning_rate": 0.00014009886768132375,
"loss": 5.5778,
"step": 2160
},
{
"epoch": 0.433,
"grad_norm": 0.3022766709327698,
"learning_rate": 0.000139778850739795,
"loss": 5.5476,
"step": 2165
},
{
"epoch": 0.434,
"grad_norm": 0.247889906167984,
"learning_rate": 0.0001394583491055234,
"loss": 5.5662,
"step": 2170
},
{
"epoch": 0.435,
"grad_norm": 0.3966282606124878,
"learning_rate": 0.00013913736668372026,
"loss": 5.5657,
"step": 2175
},
{
"epoch": 0.436,
"grad_norm": 0.34489527344703674,
"learning_rate": 0.00013881590738545508,
"loss": 5.5588,
"step": 2180
},
{
"epoch": 0.437,
"grad_norm": 0.3281410336494446,
"learning_rate": 0.00013849397512760795,
"loss": 5.5667,
"step": 2185
},
{
"epoch": 0.438,
"grad_norm": 0.4603831171989441,
"learning_rate": 0.00013817157383282184,
"loss": 5.5977,
"step": 2190
},
{
"epoch": 0.439,
"grad_norm": 0.323536217212677,
"learning_rate": 0.00013784870742945482,
"loss": 5.544,
"step": 2195
},
{
"epoch": 0.44,
"grad_norm": 0.28041359782218933,
"learning_rate": 0.0001375253798515321,
"loss": 5.5155,
"step": 2200
},
{
"epoch": 0.441,
"grad_norm": 0.29295065999031067,
"learning_rate": 0.00013720159503869815,
"loss": 5.5679,
"step": 2205
},
{
"epoch": 0.442,
"grad_norm": 0.23894783854484558,
"learning_rate": 0.00013687735693616876,
"loss": 5.5811,
"step": 2210
},
{
"epoch": 0.443,
"grad_norm": 0.3773079514503479,
"learning_rate": 0.0001365526694946829,
"loss": 5.5451,
"step": 2215
},
{
"epoch": 0.444,
"grad_norm": 0.29099738597869873,
"learning_rate": 0.00013622753667045457,
"loss": 5.5894,
"step": 2220
},
{
"epoch": 0.445,
"grad_norm": 0.33015793561935425,
"learning_rate": 0.00013590196242512463,
"loss": 5.4994,
"step": 2225
},
{
"epoch": 0.446,
"grad_norm": 0.3676055669784546,
"learning_rate": 0.0001355759507257125,
"loss": 5.5635,
"step": 2230
},
{
"epoch": 0.447,
"grad_norm": 0.3159097731113434,
"learning_rate": 0.00013524950554456784,
"loss": 5.5022,
"step": 2235
},
{
"epoch": 0.448,
"grad_norm": 0.34263792634010315,
"learning_rate": 0.00013492263085932224,
"loss": 5.5289,
"step": 2240
},
{
"epoch": 0.449,
"grad_norm": 0.3048504590988159,
"learning_rate": 0.0001345953306528405,
"loss": 5.4589,
"step": 2245
},
{
"epoch": 0.45,
"grad_norm": 0.39898982644081116,
"learning_rate": 0.00013426760891317236,
"loss": 5.617,
"step": 2250
},
{
"epoch": 0.451,
"grad_norm": 0.321245938539505,
"learning_rate": 0.00013393946963350382,
"loss": 5.5168,
"step": 2255
},
{
"epoch": 0.452,
"grad_norm": 0.32747530937194824,
"learning_rate": 0.00013361091681210845,
"loss": 5.4908,
"step": 2260
},
{
"epoch": 0.453,
"grad_norm": 0.37126070261001587,
"learning_rate": 0.00013328195445229868,
"loss": 5.5558,
"step": 2265
},
{
"epoch": 0.454,
"grad_norm": 0.33093732595443726,
"learning_rate": 0.00013295258656237702,
"loss": 5.5587,
"step": 2270
},
{
"epoch": 0.455,
"grad_norm": 0.44282758235931396,
"learning_rate": 0.00013262281715558736,
"loss": 5.5145,
"step": 2275
},
{
"epoch": 0.456,
"grad_norm": 0.4337998628616333,
"learning_rate": 0.00013229265025006576,
"loss": 5.6944,
"step": 2280
},
{
"epoch": 0.457,
"grad_norm": 0.3878089487552643,
"learning_rate": 0.0001319620898687918,
"loss": 5.5054,
"step": 2285
},
{
"epoch": 0.458,
"grad_norm": 0.3406029939651489,
"learning_rate": 0.0001316311400395394,
"loss": 5.5016,
"step": 2290
},
{
"epoch": 0.459,
"grad_norm": 0.31370994448661804,
"learning_rate": 0.00013129980479482782,
"loss": 5.4938,
"step": 2295
},
{
"epoch": 0.46,
"grad_norm": 0.3675851821899414,
"learning_rate": 0.00013096808817187242,
"loss": 5.453,
"step": 2300
},
{
"epoch": 0.461,
"grad_norm": 0.25260183215141296,
"learning_rate": 0.00013063599421253558,
"loss": 5.5487,
"step": 2305
},
{
"epoch": 0.462,
"grad_norm": 0.3090387284755707,
"learning_rate": 0.00013030352696327742,
"loss": 5.492,
"step": 2310
},
{
"epoch": 0.463,
"grad_norm": 0.26351872086524963,
"learning_rate": 0.0001299706904751064,
"loss": 5.5681,
"step": 2315
},
{
"epoch": 0.464,
"grad_norm": 0.29761579632759094,
"learning_rate": 0.00012963748880353011,
"loss": 5.4649,
"step": 2320
},
{
"epoch": 0.465,
"grad_norm": 0.26398584246635437,
"learning_rate": 0.00012930392600850573,
"loss": 5.505,
"step": 2325
},
{
"epoch": 0.466,
"grad_norm": 0.3758007287979126,
"learning_rate": 0.00012897000615439075,
"loss": 5.4095,
"step": 2330
},
{
"epoch": 0.467,
"grad_norm": 0.2692521810531616,
"learning_rate": 0.00012863573330989313,
"loss": 5.4815,
"step": 2335
},
{
"epoch": 0.468,
"grad_norm": 0.8237748742103577,
"learning_rate": 0.00012830111154802203,
"loss": 5.9314,
"step": 2340
},
{
"epoch": 0.469,
"grad_norm": 0.33631670475006104,
"learning_rate": 0.000127966144946038,
"loss": 5.5196,
"step": 2345
},
{
"epoch": 0.47,
"grad_norm": 0.4719831645488739,
"learning_rate": 0.00012763083758540337,
"loss": 5.5508,
"step": 2350
},
{
"epoch": 0.471,
"grad_norm": 0.3192049562931061,
"learning_rate": 0.00012729519355173254,
"loss": 5.4382,
"step": 2355
},
{
"epoch": 0.472,
"grad_norm": 0.3001237213611603,
"learning_rate": 0.00012695921693474212,
"loss": 5.5249,
"step": 2360
},
{
"epoch": 0.473,
"grad_norm": 0.29654818773269653,
"learning_rate": 0.00012662291182820114,
"loss": 5.5102,
"step": 2365
},
{
"epoch": 0.474,
"grad_norm": 0.6102756261825562,
"learning_rate": 0.0001262862823298812,
"loss": 5.6503,
"step": 2370
},
{
"epoch": 0.475,
"grad_norm": 0.45264965295791626,
"learning_rate": 0.00012594933254150655,
"loss": 5.4913,
"step": 2375
},
{
"epoch": 0.476,
"grad_norm": 0.38555464148521423,
"learning_rate": 0.00012561206656870396,
"loss": 5.4967,
"step": 2380
},
{
"epoch": 0.477,
"grad_norm": 0.3452162444591522,
"learning_rate": 0.00012527448852095295,
"loss": 5.5801,
"step": 2385
},
{
"epoch": 0.478,
"grad_norm": 0.3990365266799927,
"learning_rate": 0.0001249366025115354,
"loss": 5.5648,
"step": 2390
},
{
"epoch": 0.479,
"grad_norm": 0.3488164246082306,
"learning_rate": 0.0001245984126574858,
"loss": 5.5171,
"step": 2395
},
{
"epoch": 0.48,
"grad_norm": 0.35271403193473816,
"learning_rate": 0.00012425992307954075,
"loss": 5.5451,
"step": 2400
},
{
"epoch": 0.481,
"grad_norm": 0.42017239332199097,
"learning_rate": 0.00012392113790208895,
"loss": 5.9545,
"step": 2405
},
{
"epoch": 0.482,
"grad_norm": 0.3527601957321167,
"learning_rate": 0.00012358206125312083,
"loss": 5.4707,
"step": 2410
},
{
"epoch": 0.483,
"grad_norm": 0.40405744314193726,
"learning_rate": 0.0001232426972641784,
"loss": 5.4708,
"step": 2415
},
{
"epoch": 0.484,
"grad_norm": 0.35929733514785767,
"learning_rate": 0.00012290305007030478,
"loss": 5.4704,
"step": 2420
},
{
"epoch": 0.485,
"grad_norm": 0.38914307951927185,
"learning_rate": 0.00012256312380999376,
"loss": 5.4808,
"step": 2425
},
{
"epoch": 0.486,
"grad_norm": 0.42944034934043884,
"learning_rate": 0.00012222292262513965,
"loss": 5.5292,
"step": 2430
},
{
"epoch": 0.487,
"grad_norm": 0.3027641475200653,
"learning_rate": 0.00012188245066098647,
"loss": 5.4427,
"step": 2435
},
{
"epoch": 0.488,
"grad_norm": 0.279289186000824,
"learning_rate": 0.00012154171206607764,
"loss": 5.4924,
"step": 2440
},
{
"epoch": 0.489,
"grad_norm": 0.3019217848777771,
"learning_rate": 0.00012120071099220549,
"loss": 5.5185,
"step": 2445
},
{
"epoch": 0.49,
"grad_norm": 0.3058886229991913,
"learning_rate": 0.00012085945159436038,
"loss": 5.4757,
"step": 2450
},
{
"epoch": 0.491,
"grad_norm": 0.26931965351104736,
"learning_rate": 0.00012051793803068046,
"loss": 5.4207,
"step": 2455
},
{
"epoch": 0.492,
"grad_norm": 0.37244701385498047,
"learning_rate": 0.0001201761744624007,
"loss": 5.6636,
"step": 2460
},
{
"epoch": 0.493,
"grad_norm": 0.27376365661621094,
"learning_rate": 0.00011983416505380234,
"loss": 5.5538,
"step": 2465
},
{
"epoch": 0.494,
"grad_norm": 0.3278793692588806,
"learning_rate": 0.00011949191397216206,
"loss": 5.4935,
"step": 2470
},
{
"epoch": 0.495,
"grad_norm": 0.2681702673435211,
"learning_rate": 0.00011914942538770131,
"loss": 5.4121,
"step": 2475
},
{
"epoch": 0.496,
"grad_norm": 0.3019610345363617,
"learning_rate": 0.00011880670347353539,
"loss": 5.457,
"step": 2480
},
{
"epoch": 0.497,
"grad_norm": 0.3759955167770386,
"learning_rate": 0.0001184637524056227,
"loss": 5.7233,
"step": 2485
},
{
"epoch": 0.498,
"grad_norm": 0.3341779410839081,
"learning_rate": 0.00011812057636271374,
"loss": 5.541,
"step": 2490
},
{
"epoch": 0.499,
"grad_norm": 0.33677196502685547,
"learning_rate": 0.00011777717952630031,
"loss": 5.3867,
"step": 2495
},
{
"epoch": 0.5,
"grad_norm": 0.3573932647705078,
"learning_rate": 0.00011743356608056449,
"loss": 5.4744,
"step": 2500
},
{
"epoch": 0.501,
"grad_norm": 0.3194741904735565,
"learning_rate": 0.00011708974021232769,
"loss": 5.4797,
"step": 2505
},
{
"epoch": 0.502,
"grad_norm": 0.27344363927841187,
"learning_rate": 0.00011674570611099955,
"loss": 5.4679,
"step": 2510
},
{
"epoch": 0.503,
"grad_norm": 0.30184876918792725,
"learning_rate": 0.00011640146796852711,
"loss": 5.4427,
"step": 2515
},
{
"epoch": 0.504,
"grad_norm": 0.30186185240745544,
"learning_rate": 0.00011605702997934345,
"loss": 5.48,
"step": 2520
},
{
"epoch": 0.505,
"grad_norm": 0.27094995975494385,
"learning_rate": 0.00011571239634031679,
"loss": 5.4568,
"step": 2525
},
{
"epoch": 0.506,
"grad_norm": 0.2836481034755707,
"learning_rate": 0.00011536757125069923,
"loss": 5.4044,
"step": 2530
},
{
"epoch": 0.507,
"grad_norm": 0.3479526937007904,
"learning_rate": 0.00011502255891207572,
"loss": 5.4372,
"step": 2535
},
{
"epoch": 0.508,
"grad_norm": 0.2542615830898285,
"learning_rate": 0.00011467736352831266,
"loss": 5.3994,
"step": 2540
},
{
"epoch": 0.509,
"grad_norm": 0.4875389039516449,
"learning_rate": 0.00011433198930550695,
"loss": 5.4744,
"step": 2545
},
{
"epoch": 0.51,
"grad_norm": 0.3258989453315735,
"learning_rate": 0.00011398644045193444,
"loss": 5.4959,
"step": 2550
},
{
"epoch": 0.511,
"grad_norm": 0.2606883645057678,
"learning_rate": 0.00011364072117799885,
"loss": 5.4891,
"step": 2555
},
{
"epoch": 0.512,
"grad_norm": 0.2600470185279846,
"learning_rate": 0.00011329483569618045,
"loss": 5.43,
"step": 2560
},
{
"epoch": 0.513,
"grad_norm": 0.2783809304237366,
"learning_rate": 0.00011294878822098469,
"loss": 5.4184,
"step": 2565
},
{
"epoch": 0.514,
"grad_norm": 0.3892756700515747,
"learning_rate": 0.00011260258296889086,
"loss": 5.4224,
"step": 2570
},
{
"epoch": 0.515,
"grad_norm": 0.8294858932495117,
"learning_rate": 0.00011225622415830068,
"loss": 5.3681,
"step": 2575
},
{
"epoch": 0.516,
"grad_norm": 0.2929677665233612,
"learning_rate": 0.00011190971600948699,
"loss": 5.4258,
"step": 2580
},
{
"epoch": 0.517,
"grad_norm": 0.3827914893627167,
"learning_rate": 0.00011156306274454218,
"loss": 5.396,
"step": 2585
},
{
"epoch": 0.518,
"grad_norm": 0.290621817111969,
"learning_rate": 0.0001112162685873269,
"loss": 5.3213,
"step": 2590
},
{
"epoch": 0.519,
"grad_norm": 0.31230252981185913,
"learning_rate": 0.00011086933776341852,
"loss": 5.3023,
"step": 2595
},
{
"epoch": 0.52,
"grad_norm": 0.26596009731292725,
"learning_rate": 0.00011052227450005967,
"loss": 5.3687,
"step": 2600
},
{
"epoch": 0.521,
"grad_norm": 0.2653489410877228,
"learning_rate": 0.00011017508302610664,
"loss": 5.3431,
"step": 2605
},
{
"epoch": 0.522,
"grad_norm": 0.32015326619148254,
"learning_rate": 0.00010982776757197799,
"loss": 5.4422,
"step": 2610
},
{
"epoch": 0.523,
"grad_norm": 0.334026575088501,
"learning_rate": 0.00010948033236960294,
"loss": 5.334,
"step": 2615
},
{
"epoch": 0.524,
"grad_norm": 0.28240248560905457,
"learning_rate": 0.00010913278165236978,
"loss": 5.3217,
"step": 2620
},
{
"epoch": 0.525,
"grad_norm": 0.2885652482509613,
"learning_rate": 0.00010878511965507434,
"loss": 5.405,
"step": 2625
},
{
"epoch": 0.526,
"grad_norm": 0.3738548755645752,
"learning_rate": 0.00010843735061386828,
"loss": 5.3878,
"step": 2630
},
{
"epoch": 0.527,
"grad_norm": 0.28945764899253845,
"learning_rate": 0.00010808947876620767,
"loss": 5.3712,
"step": 2635
},
{
"epoch": 0.528,
"grad_norm": 0.39489033818244934,
"learning_rate": 0.00010774150835080119,
"loss": 5.2561,
"step": 2640
},
{
"epoch": 0.529,
"grad_norm": 0.4362444579601288,
"learning_rate": 0.00010739344360755852,
"loss": 5.3931,
"step": 2645
},
{
"epoch": 0.53,
"grad_norm": 0.31048476696014404,
"learning_rate": 0.0001070452887775387,
"loss": 5.4041,
"step": 2650
},
{
"epoch": 0.531,
"grad_norm": 0.3073086440563202,
"learning_rate": 0.00010669704810289851,
"loss": 5.5369,
"step": 2655
},
{
"epoch": 0.532,
"grad_norm": 0.37829118967056274,
"learning_rate": 0.00010634872582684061,
"loss": 5.438,
"step": 2660
},
{
"epoch": 0.533,
"grad_norm": 0.3791942596435547,
"learning_rate": 0.00010600032619356209,
"loss": 5.4333,
"step": 2665
},
{
"epoch": 0.534,
"grad_norm": 0.3788481652736664,
"learning_rate": 0.00010565185344820247,
"loss": 5.3688,
"step": 2670
},
{
"epoch": 0.535,
"grad_norm": 0.31421589851379395,
"learning_rate": 0.00010530331183679218,
"loss": 5.3357,
"step": 2675
},
{
"epoch": 0.536,
"grad_norm": 0.3763849139213562,
"learning_rate": 0.00010495470560620083,
"loss": 5.3861,
"step": 2680
},
{
"epoch": 0.537,
"grad_norm": 0.30694714188575745,
"learning_rate": 0.00010460603900408523,
"loss": 5.3513,
"step": 2685
},
{
"epoch": 0.538,
"grad_norm": 0.28069713711738586,
"learning_rate": 0.00010425731627883797,
"loss": 5.3282,
"step": 2690
},
{
"epoch": 0.539,
"grad_norm": 0.2651154696941376,
"learning_rate": 0.00010390854167953537,
"loss": 5.415,
"step": 2695
},
{
"epoch": 0.54,
"grad_norm": 0.24997186660766602,
"learning_rate": 0.00010355971945588585,
"loss": 5.3686,
"step": 2700
},
{
"epoch": 0.541,
"grad_norm": 0.28760799765586853,
"learning_rate": 0.00010321085385817817,
"loss": 5.4028,
"step": 2705
},
{
"epoch": 0.542,
"grad_norm": 0.289225310087204,
"learning_rate": 0.00010286194913722948,
"loss": 5.2747,
"step": 2710
},
{
"epoch": 0.543,
"grad_norm": 0.25723472237586975,
"learning_rate": 0.00010251300954433376,
"loss": 5.3369,
"step": 2715
},
{
"epoch": 0.544,
"grad_norm": 0.32451340556144714,
"learning_rate": 0.00010216403933120979,
"loss": 5.3274,
"step": 2720
},
{
"epoch": 0.545,
"grad_norm": 0.3142393231391907,
"learning_rate": 0.00010181504274994948,
"loss": 5.2825,
"step": 2725
},
{
"epoch": 0.546,
"grad_norm": 0.312741756439209,
"learning_rate": 0.00010146602405296607,
"loss": 5.3867,
"step": 2730
},
{
"epoch": 0.547,
"grad_norm": 0.3702278137207031,
"learning_rate": 0.00010111698749294223,
"loss": 5.3268,
"step": 2735
},
{
"epoch": 0.548,
"grad_norm": 0.27364611625671387,
"learning_rate": 0.00010076793732277829,
"loss": 5.4009,
"step": 2740
},
{
"epoch": 0.549,
"grad_norm": 0.3004075288772583,
"learning_rate": 0.0001004188777955404,
"loss": 5.4159,
"step": 2745
},
{
"epoch": 0.55,
"grad_norm": 0.24836541712284088,
"learning_rate": 0.00010006981316440875,
"loss": 5.3794,
"step": 2750
},
{
"epoch": 0.551,
"grad_norm": 0.350300133228302,
"learning_rate": 9.972074768262576e-05,
"loss": 5.3473,
"step": 2755
},
{
"epoch": 0.552,
"grad_norm": 0.220030277967453,
"learning_rate": 9.937168560344412e-05,
"loss": 5.338,
"step": 2760
},
{
"epoch": 0.553,
"grad_norm": 0.3507874608039856,
"learning_rate": 9.902263118007513e-05,
"loss": 5.3403,
"step": 2765
},
{
"epoch": 0.554,
"grad_norm": 0.2632776200771332,
"learning_rate": 9.867358866563673e-05,
"loss": 5.2928,
"step": 2770
},
{
"epoch": 0.555,
"grad_norm": 0.33953189849853516,
"learning_rate": 9.832456231310189e-05,
"loss": 5.3133,
"step": 2775
},
{
"epoch": 0.556,
"grad_norm": 0.3873049318790436,
"learning_rate": 9.797555637524649e-05,
"loss": 5.3026,
"step": 2780
},
{
"epoch": 0.557,
"grad_norm": 0.3209889531135559,
"learning_rate": 9.762657510459783e-05,
"loss": 5.3441,
"step": 2785
},
{
"epoch": 0.558,
"grad_norm": 0.2819998860359192,
"learning_rate": 9.727762275338246e-05,
"loss": 5.2829,
"step": 2790
},
{
"epoch": 0.559,
"grad_norm": 0.7692443132400513,
"learning_rate": 9.692870357347473e-05,
"loss": 5.3,
"step": 2795
},
{
"epoch": 0.56,
"grad_norm": 0.3640769422054291,
"learning_rate": 9.657982181634475e-05,
"loss": 5.4305,
"step": 2800
},
{
"epoch": 0.561,
"grad_norm": 0.2912924289703369,
"learning_rate": 9.623098173300654e-05,
"loss": 5.3194,
"step": 2805
},
{
"epoch": 0.562,
"grad_norm": 0.3209432065486908,
"learning_rate": 9.588218757396655e-05,
"loss": 5.294,
"step": 2810
},
{
"epoch": 0.563,
"grad_norm": 0.2979467511177063,
"learning_rate": 9.55334435891714e-05,
"loss": 5.2736,
"step": 2815
},
{
"epoch": 0.564,
"grad_norm": 0.33661767840385437,
"learning_rate": 9.518475402795661e-05,
"loss": 5.3409,
"step": 2820
},
{
"epoch": 0.565,
"grad_norm": 0.2850003242492676,
"learning_rate": 9.483612313899435e-05,
"loss": 5.3871,
"step": 2825
},
{
"epoch": 0.566,
"grad_norm": 0.2953025996685028,
"learning_rate": 9.448755517024206e-05,
"loss": 5.3482,
"step": 2830
},
{
"epoch": 0.567,
"grad_norm": 0.2745295464992523,
"learning_rate": 9.413905436889035e-05,
"loss": 5.3423,
"step": 2835
},
{
"epoch": 0.568,
"grad_norm": 0.3061926066875458,
"learning_rate": 9.37906249813116e-05,
"loss": 5.3476,
"step": 2840
},
{
"epoch": 0.569,
"grad_norm": 0.3320010304450989,
"learning_rate": 9.344227125300788e-05,
"loss": 5.3862,
"step": 2845
},
{
"epoch": 0.57,
"grad_norm": 0.2780536115169525,
"learning_rate": 9.309399742855942e-05,
"loss": 5.2954,
"step": 2850
},
{
"epoch": 0.571,
"grad_norm": 0.2803821265697479,
"learning_rate": 9.274580775157294e-05,
"loss": 5.201,
"step": 2855
},
{
"epoch": 0.572,
"grad_norm": 0.3918452560901642,
"learning_rate": 9.239770646462968e-05,
"loss": 5.2655,
"step": 2860
},
{
"epoch": 0.573,
"grad_norm": 0.2901855707168579,
"learning_rate": 9.204969780923403e-05,
"loss": 5.3085,
"step": 2865
},
{
"epoch": 0.574,
"grad_norm": 0.26251551508903503,
"learning_rate": 9.17017860257616e-05,
"loss": 5.3378,
"step": 2870
},
{
"epoch": 0.575,
"grad_norm": 0.2798098921775818,
"learning_rate": 9.135397535340773e-05,
"loss": 5.3546,
"step": 2875
},
{
"epoch": 0.576,
"grad_norm": 0.2912362515926361,
"learning_rate": 9.100627003013562e-05,
"loss": 5.2979,
"step": 2880
},
{
"epoch": 0.577,
"grad_norm": 0.282420814037323,
"learning_rate": 9.065867429262496e-05,
"loss": 5.314,
"step": 2885
},
{
"epoch": 0.578,
"grad_norm": 0.2818324863910675,
"learning_rate": 9.03111923762201e-05,
"loss": 5.2338,
"step": 2890
},
{
"epoch": 0.579,
"grad_norm": 0.2554740607738495,
"learning_rate": 8.99638285148785e-05,
"loss": 5.3275,
"step": 2895
},
{
"epoch": 0.58,
"grad_norm": 0.26442036032676697,
"learning_rate": 8.961658694111929e-05,
"loss": 5.3656,
"step": 2900
},
{
"epoch": 0.581,
"grad_norm": 0.32014816999435425,
"learning_rate": 8.926947188597134e-05,
"loss": 5.2176,
"step": 2905
},
{
"epoch": 0.582,
"grad_norm": 0.24048133194446564,
"learning_rate": 8.892248757892214e-05,
"loss": 5.2843,
"step": 2910
},
{
"epoch": 0.583,
"grad_norm": 0.26643553376197815,
"learning_rate": 8.857563824786596e-05,
"loss": 5.3086,
"step": 2915
},
{
"epoch": 0.584,
"grad_norm": 0.27889102697372437,
"learning_rate": 8.822892811905237e-05,
"loss": 5.266,
"step": 2920
},
{
"epoch": 0.585,
"grad_norm": 0.2976931035518646,
"learning_rate": 8.788236141703498e-05,
"loss": 5.3473,
"step": 2925
},
{
"epoch": 0.586,
"grad_norm": 0.46499502658843994,
"learning_rate": 8.753594236461957e-05,
"loss": 5.2626,
"step": 2930
},
{
"epoch": 0.587,
"grad_norm": 0.2723909616470337,
"learning_rate": 8.718967518281307e-05,
"loss": 5.2613,
"step": 2935
},
{
"epoch": 0.588,
"grad_norm": 0.2973109483718872,
"learning_rate": 8.684356409077176e-05,
"loss": 5.2828,
"step": 2940
},
{
"epoch": 0.589,
"grad_norm": 0.2992641031742096,
"learning_rate": 8.64976133057501e-05,
"loss": 5.2767,
"step": 2945
},
{
"epoch": 0.59,
"grad_norm": 0.2976066470146179,
"learning_rate": 8.615182704304918e-05,
"loss": 5.2978,
"step": 2950
},
{
"epoch": 0.591,
"grad_norm": 0.37647151947021484,
"learning_rate": 8.580620951596557e-05,
"loss": 5.2408,
"step": 2955
},
{
"epoch": 0.592,
"grad_norm": 0.2456439882516861,
"learning_rate": 8.546076493573972e-05,
"loss": 5.3098,
"step": 2960
},
{
"epoch": 0.593,
"grad_norm": 0.28480783104896545,
"learning_rate": 8.511549751150479e-05,
"loss": 5.2736,
"step": 2965
},
{
"epoch": 0.594,
"grad_norm": 0.7012133598327637,
"learning_rate": 8.477041145023546e-05,
"loss": 5.2568,
"step": 2970
},
{
"epoch": 0.595,
"grad_norm": 0.3797517716884613,
"learning_rate": 8.442551095669639e-05,
"loss": 5.2786,
"step": 2975
},
{
"epoch": 0.596,
"grad_norm": 0.2727696895599365,
"learning_rate": 8.408080023339133e-05,
"loss": 5.2483,
"step": 2980
},
{
"epoch": 0.597,
"grad_norm": 0.34131133556365967,
"learning_rate": 8.373628348051165e-05,
"loss": 5.3409,
"step": 2985
},
{
"epoch": 0.598,
"grad_norm": 0.2863699793815613,
"learning_rate": 8.339196489588523e-05,
"loss": 5.2918,
"step": 2990
},
{
"epoch": 0.599,
"grad_norm": 0.2978050410747528,
"learning_rate": 8.30478486749254e-05,
"loss": 5.258,
"step": 2995
},
{
"epoch": 0.6,
"grad_norm": 0.722728967666626,
"learning_rate": 8.270393901057964e-05,
"loss": 5.4831,
"step": 3000
},
{
"epoch": 0.601,
"grad_norm": 0.5127167105674744,
"learning_rate": 8.236024009327879e-05,
"loss": 5.5376,
"step": 3005
},
{
"epoch": 0.602,
"grad_norm": 0.40371599793434143,
"learning_rate": 8.201675611088558e-05,
"loss": 5.2984,
"step": 3010
},
{
"epoch": 0.603,
"grad_norm": 0.31022998690605164,
"learning_rate": 8.167349124864405e-05,
"loss": 5.2447,
"step": 3015
},
{
"epoch": 0.604,
"grad_norm": 0.24242441356182098,
"learning_rate": 8.133044968912811e-05,
"loss": 5.2163,
"step": 3020
},
{
"epoch": 0.605,
"grad_norm": 0.27865615487098694,
"learning_rate": 8.0987635612191e-05,
"loss": 5.2058,
"step": 3025
},
{
"epoch": 0.606,
"grad_norm": 0.24681493639945984,
"learning_rate": 8.064505319491398e-05,
"loss": 5.3071,
"step": 3030
},
{
"epoch": 0.607,
"grad_norm": 0.43465790152549744,
"learning_rate": 8.030270661155574e-05,
"loss": 5.3424,
"step": 3035
},
{
"epoch": 0.608,
"grad_norm": 0.2665650546550751,
"learning_rate": 7.996060003350139e-05,
"loss": 5.2428,
"step": 3040
},
{
"epoch": 0.609,
"grad_norm": 0.3211173415184021,
"learning_rate": 7.961873762921153e-05,
"loss": 5.2593,
"step": 3045
},
{
"epoch": 0.61,
"grad_norm": 0.24610266089439392,
"learning_rate": 7.927712356417176e-05,
"loss": 5.2461,
"step": 3050
},
{
"epoch": 0.611,
"grad_norm": 0.2529318034648895,
"learning_rate": 7.893576200084159e-05,
"loss": 5.2882,
"step": 3055
},
{
"epoch": 0.612,
"grad_norm": 0.28791025280952454,
"learning_rate": 7.8594657098604e-05,
"loss": 5.2649,
"step": 3060
},
{
"epoch": 0.613,
"grad_norm": 0.27318936586380005,
"learning_rate": 7.825381301371452e-05,
"loss": 5.2432,
"step": 3065
},
{
"epoch": 0.614,
"grad_norm": 0.29395630955696106,
"learning_rate": 7.791323389925084e-05,
"loss": 5.2634,
"step": 3070
},
{
"epoch": 0.615,
"grad_norm": 0.23689384758472443,
"learning_rate": 7.75729239050619e-05,
"loss": 5.1561,
"step": 3075
},
{
"epoch": 0.616,
"grad_norm": 0.2849836051464081,
"learning_rate": 7.723288717771761e-05,
"loss": 5.2908,
"step": 3080
},
{
"epoch": 0.617,
"grad_norm": 0.30474284291267395,
"learning_rate": 7.689312786045823e-05,
"loss": 5.3088,
"step": 3085
},
{
"epoch": 0.618,
"grad_norm": 0.2566715478897095,
"learning_rate": 7.655365009314374e-05,
"loss": 5.2626,
"step": 3090
},
{
"epoch": 0.619,
"grad_norm": 0.2644171118736267,
"learning_rate": 7.621445801220371e-05,
"loss": 5.2419,
"step": 3095
},
{
"epoch": 0.62,
"grad_norm": 0.24471698701381683,
"learning_rate": 7.587555575058649e-05,
"loss": 5.2304,
"step": 3100
},
{
"epoch": 0.621,
"grad_norm": 0.2859196364879608,
"learning_rate": 7.553694743770928e-05,
"loss": 5.2368,
"step": 3105
},
{
"epoch": 0.622,
"grad_norm": 0.2455093264579773,
"learning_rate": 7.519863719940748e-05,
"loss": 5.2015,
"step": 3110
},
{
"epoch": 0.623,
"grad_norm": 0.2638492286205292,
"learning_rate": 7.486062915788452e-05,
"loss": 5.2114,
"step": 3115
},
{
"epoch": 0.624,
"grad_norm": 0.2487843781709671,
"learning_rate": 7.45229274316618e-05,
"loss": 5.1837,
"step": 3120
},
{
"epoch": 0.625,
"grad_norm": 0.3540295958518982,
"learning_rate": 7.418553613552825e-05,
"loss": 5.3032,
"step": 3125
},
{
"epoch": 0.626,
"grad_norm": 0.5158248543739319,
"learning_rate": 7.384845938049031e-05,
"loss": 5.2142,
"step": 3130
},
{
"epoch": 0.627,
"grad_norm": 0.5496995449066162,
"learning_rate": 7.351170127372191e-05,
"loss": 5.3021,
"step": 3135
},
{
"epoch": 0.628,
"grad_norm": 0.5478867888450623,
"learning_rate": 7.317526591851433e-05,
"loss": 5.3128,
"step": 3140
},
{
"epoch": 0.629,
"grad_norm": 0.4349045157432556,
"learning_rate": 7.283915741422612e-05,
"loss": 5.2391,
"step": 3145
},
{
"epoch": 0.63,
"grad_norm": 0.45268532633781433,
"learning_rate": 7.250337985623342e-05,
"loss": 5.1468,
"step": 3150
},
{
"epoch": 0.631,
"grad_norm": 0.5932441353797913,
"learning_rate": 7.216793733587976e-05,
"loss": 5.2497,
"step": 3155
},
{
"epoch": 0.632,
"grad_norm": 0.40024855732917786,
"learning_rate": 7.183283394042634e-05,
"loss": 5.329,
"step": 3160
},
{
"epoch": 0.633,
"grad_norm": 0.36189743876457214,
"learning_rate": 7.149807375300239e-05,
"loss": 5.3013,
"step": 3165
},
{
"epoch": 0.634,
"grad_norm": 0.2974001467227936,
"learning_rate": 7.11636608525551e-05,
"loss": 5.2652,
"step": 3170
},
{
"epoch": 0.635,
"grad_norm": 0.32158851623535156,
"learning_rate": 7.082959931380011e-05,
"loss": 5.2461,
"step": 3175
},
{
"epoch": 0.636,
"grad_norm": 0.30008625984191895,
"learning_rate": 7.049589320717186e-05,
"loss": 5.2108,
"step": 3180
},
{
"epoch": 0.637,
"grad_norm": 0.30666792392730713,
"learning_rate": 7.016254659877398e-05,
"loss": 5.2785,
"step": 3185
},
{
"epoch": 0.638,
"grad_norm": 0.25224629044532776,
"learning_rate": 6.982956355032968e-05,
"loss": 5.1379,
"step": 3190
},
{
"epoch": 0.639,
"grad_norm": 0.33399754762649536,
"learning_rate": 6.949694811913225e-05,
"loss": 5.2274,
"step": 3195
},
{
"epoch": 0.64,
"grad_norm": 0.2418002486228943,
"learning_rate": 6.916470435799587e-05,
"loss": 5.2388,
"step": 3200
},
{
"epoch": 0.641,
"grad_norm": 0.3420831263065338,
"learning_rate": 6.883283631520582e-05,
"loss": 5.3162,
"step": 3205
},
{
"epoch": 0.642,
"grad_norm": 0.29210999608039856,
"learning_rate": 6.850134803446954e-05,
"loss": 5.2046,
"step": 3210
},
{
"epoch": 0.643,
"grad_norm": 0.25016501545906067,
"learning_rate": 6.817024355486706e-05,
"loss": 5.1858,
"step": 3215
},
{
"epoch": 0.644,
"grad_norm": 0.41076964139938354,
"learning_rate": 6.783952691080203e-05,
"loss": 5.2111,
"step": 3220
},
{
"epoch": 0.645,
"grad_norm": 0.3289218246936798,
"learning_rate": 6.750920213195238e-05,
"loss": 5.1305,
"step": 3225
},
{
"epoch": 0.646,
"grad_norm": 0.2879229187965393,
"learning_rate": 6.717927324322124e-05,
"loss": 5.1363,
"step": 3230
},
{
"epoch": 0.647,
"grad_norm": 0.33354708552360535,
"learning_rate": 6.684974426468808e-05,
"loss": 5.2601,
"step": 3235
},
{
"epoch": 0.648,
"grad_norm": 0.3253793716430664,
"learning_rate": 6.652061921155943e-05,
"loss": 5.2497,
"step": 3240
},
{
"epoch": 0.649,
"grad_norm": 0.3734394311904907,
"learning_rate": 6.61919020941203e-05,
"loss": 5.2514,
"step": 3245
},
{
"epoch": 0.65,
"grad_norm": 0.3051718473434448,
"learning_rate": 6.58635969176849e-05,
"loss": 5.215,
"step": 3250
},
{
"epoch": 0.651,
"grad_norm": 0.2642398476600647,
"learning_rate": 6.55357076825483e-05,
"loss": 5.207,
"step": 3255
},
{
"epoch": 0.652,
"grad_norm": 0.32345372438430786,
"learning_rate": 6.520823838393731e-05,
"loss": 5.1757,
"step": 3260
},
{
"epoch": 0.653,
"grad_norm": 0.24656705558300018,
"learning_rate": 6.488119301196201e-05,
"loss": 5.273,
"step": 3265
},
{
"epoch": 0.654,
"grad_norm": 0.363528311252594,
"learning_rate": 6.455457555156705e-05,
"loss": 5.1954,
"step": 3270
},
{
"epoch": 0.655,
"grad_norm": 0.2929413914680481,
"learning_rate": 6.422838998248307e-05,
"loss": 5.1656,
"step": 3275
},
{
"epoch": 0.656,
"grad_norm": 0.2669423222541809,
"learning_rate": 6.390264027917836e-05,
"loss": 5.114,
"step": 3280
},
{
"epoch": 0.657,
"grad_norm": 0.6234262585639954,
"learning_rate": 6.357733041081018e-05,
"loss": 5.0385,
"step": 3285
},
{
"epoch": 0.658,
"grad_norm": 0.39093971252441406,
"learning_rate": 6.325246434117668e-05,
"loss": 5.0109,
"step": 3290
},
{
"epoch": 0.659,
"grad_norm": 0.35687553882598877,
"learning_rate": 6.292804602866834e-05,
"loss": 5.1987,
"step": 3295
},
{
"epoch": 0.66,
"grad_norm": 0.2942413091659546,
"learning_rate": 6.260407942621998e-05,
"loss": 5.235,
"step": 3300
},
{
"epoch": 0.661,
"grad_norm": 0.38060927391052246,
"learning_rate": 6.228056848126236e-05,
"loss": 5.1898,
"step": 3305
},
{
"epoch": 0.662,
"grad_norm": 0.2921803891658783,
"learning_rate": 6.195751713567427e-05,
"loss": 5.2781,
"step": 3310
},
{
"epoch": 0.663,
"grad_norm": 0.3189259171485901,
"learning_rate": 6.163492932573438e-05,
"loss": 5.1196,
"step": 3315
},
{
"epoch": 0.664,
"grad_norm": 0.2514961361885071,
"learning_rate": 6.131280898207339e-05,
"loss": 5.1631,
"step": 3320
},
{
"epoch": 0.665,
"grad_norm": 0.24589456617832184,
"learning_rate": 6.099116002962604e-05,
"loss": 5.1739,
"step": 3325
},
{
"epoch": 0.666,
"grad_norm": 0.24858522415161133,
"learning_rate": 6.066998638758326e-05,
"loss": 5.1274,
"step": 3330
},
{
"epoch": 0.667,
"grad_norm": 0.25541970133781433,
"learning_rate": 6.034929196934459e-05,
"loss": 5.4017,
"step": 3335
},
{
"epoch": 0.668,
"grad_norm": 0.26863232254981995,
"learning_rate": 6.002908068247024e-05,
"loss": 5.1952,
"step": 3340
},
{
"epoch": 0.669,
"grad_norm": 0.25654324889183044,
"learning_rate": 5.9709356428633746e-05,
"loss": 5.1226,
"step": 3345
},
{
"epoch": 0.67,
"grad_norm": 0.2805996537208557,
"learning_rate": 5.9390123103574215e-05,
"loss": 5.1552,
"step": 3350
},
{
"epoch": 0.671,
"grad_norm": 0.2460358589887619,
"learning_rate": 5.907138459704895e-05,
"loss": 5.2625,
"step": 3355
},
{
"epoch": 0.672,
"grad_norm": 0.2586885690689087,
"learning_rate": 5.8753144792786096e-05,
"loss": 5.1173,
"step": 3360
},
{
"epoch": 0.673,
"grad_norm": 0.29832497239112854,
"learning_rate": 5.8435407568437216e-05,
"loss": 5.1933,
"step": 3365
},
{
"epoch": 0.674,
"grad_norm": 0.3527740240097046,
"learning_rate": 5.8118176795530176e-05,
"loss": 5.1663,
"step": 3370
},
{
"epoch": 0.675,
"grad_norm": 0.2930378317832947,
"learning_rate": 5.780145633942173e-05,
"loss": 5.1726,
"step": 3375
},
{
"epoch": 0.676,
"grad_norm": 0.2947482466697693,
"learning_rate": 5.748525005925074e-05,
"loss": 5.2048,
"step": 3380
},
{
"epoch": 0.677,
"grad_norm": 0.30825063586235046,
"learning_rate": 5.716956180789098e-05,
"loss": 5.1437,
"step": 3385
},
{
"epoch": 0.678,
"grad_norm": 0.2567844092845917,
"learning_rate": 5.6854395431904094e-05,
"loss": 5.1551,
"step": 3390
},
{
"epoch": 0.679,
"grad_norm": 0.23571062088012695,
"learning_rate": 5.653975477149298e-05,
"loss": 5.1339,
"step": 3395
},
{
"epoch": 0.68,
"grad_norm": 0.27327629923820496,
"learning_rate": 5.622564366045472e-05,
"loss": 5.1608,
"step": 3400
},
{
"epoch": 0.681,
"grad_norm": 0.2491593360900879,
"learning_rate": 5.591206592613416e-05,
"loss": 5.2255,
"step": 3405
},
{
"epoch": 0.682,
"grad_norm": 0.31111979484558105,
"learning_rate": 5.5599025389376935e-05,
"loss": 5.1604,
"step": 3410
},
{
"epoch": 0.683,
"grad_norm": 0.28547173738479614,
"learning_rate": 5.5286525864483285e-05,
"loss": 5.2009,
"step": 3415
},
{
"epoch": 0.684,
"grad_norm": 0.25247544050216675,
"learning_rate": 5.497457115916127e-05,
"loss": 5.1368,
"step": 3420
},
{
"epoch": 0.685,
"grad_norm": 0.26237839460372925,
"learning_rate": 5.466316507448048e-05,
"loss": 5.2146,
"step": 3425
},
{
"epoch": 0.686,
"grad_norm": 0.28280800580978394,
"learning_rate": 5.435231140482587e-05,
"loss": 5.2023,
"step": 3430
},
{
"epoch": 0.687,
"grad_norm": 0.258825421333313,
"learning_rate": 5.404201393785122e-05,
"loss": 5.2545,
"step": 3435
},
{
"epoch": 0.688,
"grad_norm": 0.2758336365222931,
"learning_rate": 5.373227645443332e-05,
"loss": 5.1652,
"step": 3440
},
{
"epoch": 0.689,
"grad_norm": 0.27414658665657043,
"learning_rate": 5.3423102728625574e-05,
"loss": 5.2222,
"step": 3445
},
{
"epoch": 0.69,
"grad_norm": 0.265582799911499,
"learning_rate": 5.311449652761235e-05,
"loss": 5.25,
"step": 3450
},
{
"epoch": 0.691,
"grad_norm": 0.2817150354385376,
"learning_rate": 5.2806461611662735e-05,
"loss": 5.2174,
"step": 3455
},
{
"epoch": 0.692,
"grad_norm": 0.36035773158073425,
"learning_rate": 5.2499001734085044e-05,
"loss": 5.3905,
"step": 3460
},
{
"epoch": 0.693,
"grad_norm": 0.31820374727249146,
"learning_rate": 5.2192120641180786e-05,
"loss": 5.1871,
"step": 3465
},
{
"epoch": 0.694,
"grad_norm": 0.3060813546180725,
"learning_rate": 5.188582207219931e-05,
"loss": 5.2235,
"step": 3470
},
{
"epoch": 0.695,
"grad_norm": 0.2906821072101593,
"learning_rate": 5.158010975929193e-05,
"loss": 5.1854,
"step": 3475
},
{
"epoch": 0.696,
"grad_norm": 0.3510681986808777,
"learning_rate": 5.127498742746675e-05,
"loss": 5.1922,
"step": 3480
},
{
"epoch": 0.697,
"grad_norm": 0.49263423681259155,
"learning_rate": 5.097045879454313e-05,
"loss": 5.214,
"step": 3485
},
{
"epoch": 0.698,
"grad_norm": 0.2974720001220703,
"learning_rate": 5.066652757110628e-05,
"loss": 5.1818,
"step": 3490
},
{
"epoch": 0.699,
"grad_norm": 0.30888310074806213,
"learning_rate": 5.036319746046232e-05,
"loss": 5.1639,
"step": 3495
},
{
"epoch": 0.7,
"grad_norm": 0.321418434381485,
"learning_rate": 5.006047215859289e-05,
"loss": 5.09,
"step": 3500
},
{
"epoch": 0.701,
"grad_norm": 0.43778350949287415,
"learning_rate": 4.97583553541102e-05,
"loss": 5.17,
"step": 3505
},
{
"epoch": 0.702,
"grad_norm": 0.28933051228523254,
"learning_rate": 4.945685072821227e-05,
"loss": 5.32,
"step": 3510
},
{
"epoch": 0.703,
"grad_norm": 0.36108508706092834,
"learning_rate": 4.915596195463773e-05,
"loss": 5.1303,
"step": 3515
},
{
"epoch": 0.704,
"grad_norm": 0.4934180676937103,
"learning_rate": 4.885569269962142e-05,
"loss": 5.2916,
"step": 3520
},
{
"epoch": 0.705,
"grad_norm": 0.3828926384449005,
"learning_rate": 4.8556046621849346e-05,
"loss": 5.2302,
"step": 3525
},
{
"epoch": 0.706,
"grad_norm": 0.405647337436676,
"learning_rate": 4.825702737241452e-05,
"loss": 5.7641,
"step": 3530
},
{
"epoch": 0.707,
"grad_norm": 0.3142770826816559,
"learning_rate": 4.7958638594772064e-05,
"loss": 5.1437,
"step": 3535
},
{
"epoch": 0.708,
"grad_norm": 0.5846819877624512,
"learning_rate": 4.766088392469506e-05,
"loss": 5.0997,
"step": 3540
},
{
"epoch": 0.709,
"grad_norm": 0.3353482484817505,
"learning_rate": 4.736376699023023e-05,
"loss": 5.0558,
"step": 3545
},
{
"epoch": 0.71,
"grad_norm": 0.33807501196861267,
"learning_rate": 4.706729141165361e-05,
"loss": 5.1087,
"step": 3550
},
{
"epoch": 0.711,
"grad_norm": 0.32923805713653564,
"learning_rate": 4.6771460801426635e-05,
"loss": 5.1541,
"step": 3555
},
{
"epoch": 0.712,
"grad_norm": 0.2972225546836853,
"learning_rate": 4.647627876415186e-05,
"loss": 5.1059,
"step": 3560
},
{
"epoch": 0.713,
"grad_norm": 0.34732481837272644,
"learning_rate": 4.6181748896529273e-05,
"loss": 5.1268,
"step": 3565
},
{
"epoch": 0.714,
"grad_norm": 0.23517797887325287,
"learning_rate": 4.588787478731242e-05,
"loss": 5.2163,
"step": 3570
},
{
"epoch": 0.715,
"grad_norm": 0.23000796139240265,
"learning_rate": 4.559466001726451e-05,
"loss": 5.1531,
"step": 3575
},
{
"epoch": 0.716,
"grad_norm": 0.2599681615829468,
"learning_rate": 4.530210815911504e-05,
"loss": 5.1697,
"step": 3580
},
{
"epoch": 0.717,
"grad_norm": 0.27313607931137085,
"learning_rate": 4.501022277751602e-05,
"loss": 5.1645,
"step": 3585
},
{
"epoch": 0.718,
"grad_norm": 0.2490123063325882,
"learning_rate": 4.471900742899876e-05,
"loss": 5.1721,
"step": 3590
},
{
"epoch": 0.719,
"grad_norm": 0.23599159717559814,
"learning_rate": 4.4428465661930343e-05,
"loss": 5.1477,
"step": 3595
},
{
"epoch": 0.72,
"grad_norm": 0.3851112425327301,
"learning_rate": 4.413860101647055e-05,
"loss": 5.2074,
"step": 3600
},
{
"epoch": 0.721,
"grad_norm": 0.33540791273117065,
"learning_rate": 4.3849417024528564e-05,
"loss": 5.1429,
"step": 3605
},
{
"epoch": 0.722,
"grad_norm": 0.31464365124702454,
"learning_rate": 4.356091720972011e-05,
"loss": 5.1488,
"step": 3610
},
{
"epoch": 0.723,
"grad_norm": 0.2853056490421295,
"learning_rate": 4.327310508732437e-05,
"loss": 5.1478,
"step": 3615
},
{
"epoch": 0.724,
"grad_norm": 0.29359641671180725,
"learning_rate": 4.29859841642412e-05,
"loss": 5.145,
"step": 3620
},
{
"epoch": 0.725,
"grad_norm": 0.24871863424777985,
"learning_rate": 4.26995579389485e-05,
"loss": 5.1864,
"step": 3625
},
{
"epoch": 0.726,
"grad_norm": 0.3626295030117035,
"learning_rate": 4.2413829901459344e-05,
"loss": 5.19,
"step": 3630
},
{
"epoch": 0.727,
"grad_norm": 0.3969113230705261,
"learning_rate": 4.212880353327979e-05,
"loss": 5.1083,
"step": 3635
},
{
"epoch": 0.728,
"grad_norm": 0.28976768255233765,
"learning_rate": 4.184448230736613e-05,
"loss": 5.1568,
"step": 3640
},
{
"epoch": 0.729,
"grad_norm": 0.24984069168567657,
"learning_rate": 4.15608696880828e-05,
"loss": 5.1832,
"step": 3645
},
{
"epoch": 0.73,
"grad_norm": 0.2891409397125244,
"learning_rate": 4.1277969131160045e-05,
"loss": 5.1249,
"step": 3650
},
{
"epoch": 0.731,
"grad_norm": 0.3602142930030823,
"learning_rate": 4.099578408365191e-05,
"loss": 5.1179,
"step": 3655
},
{
"epoch": 0.732,
"grad_norm": 0.3074999153614044,
"learning_rate": 4.071431798389408e-05,
"loss": 5.1658,
"step": 3660
},
{
"epoch": 0.733,
"grad_norm": 0.2616201341152191,
"learning_rate": 4.0433574261462206e-05,
"loss": 5.0473,
"step": 3665
},
{
"epoch": 0.734,
"grad_norm": 0.2502526640892029,
"learning_rate": 4.015355633712996e-05,
"loss": 5.1071,
"step": 3670
},
{
"epoch": 0.735,
"grad_norm": 0.2705118954181671,
"learning_rate": 3.987426762282733e-05,
"loss": 5.2449,
"step": 3675
},
{
"epoch": 0.736,
"grad_norm": 0.24241133034229279,
"learning_rate": 3.9595711521599224e-05,
"loss": 5.0725,
"step": 3680
},
{
"epoch": 0.737,
"grad_norm": 0.251188188791275,
"learning_rate": 3.931789142756377e-05,
"loss": 5.1989,
"step": 3685
},
{
"epoch": 0.738,
"grad_norm": 0.25423479080200195,
"learning_rate": 3.904081072587119e-05,
"loss": 5.127,
"step": 3690
},
{
"epoch": 0.739,
"grad_norm": 0.22999754548072815,
"learning_rate": 3.876447279266238e-05,
"loss": 5.1928,
"step": 3695
},
{
"epoch": 0.74,
"grad_norm": 0.32315826416015625,
"learning_rate": 3.8488880995027786e-05,
"loss": 5.0881,
"step": 3700
},
{
"epoch": 0.741,
"grad_norm": 0.2563725411891937,
"learning_rate": 3.821403869096658e-05,
"loss": 5.1423,
"step": 3705
},
{
"epoch": 0.742,
"grad_norm": 0.4680487811565399,
"learning_rate": 3.793994922934544e-05,
"loss": 5.16,
"step": 3710
},
{
"epoch": 0.743,
"grad_norm": 0.3002435564994812,
"learning_rate": 3.766661594985801e-05,
"loss": 5.0286,
"step": 3715
},
{
"epoch": 0.744,
"grad_norm": 0.545009434223175,
"learning_rate": 3.739404218298398e-05,
"loss": 5.1994,
"step": 3720
},
{
"epoch": 0.745,
"grad_norm": 0.31745418906211853,
"learning_rate": 3.712223124994875e-05,
"loss": 5.1911,
"step": 3725
},
{
"epoch": 0.746,
"grad_norm": 0.30484360456466675,
"learning_rate": 3.685118646268272e-05,
"loss": 5.2375,
"step": 3730
},
{
"epoch": 0.747,
"grad_norm": 0.4349173903465271,
"learning_rate": 3.6580911123781056e-05,
"loss": 5.2416,
"step": 3735
},
{
"epoch": 0.748,
"grad_norm": 0.394788920879364,
"learning_rate": 3.631140852646355e-05,
"loss": 5.1523,
"step": 3740
},
{
"epoch": 0.749,
"grad_norm": 0.26544034481048584,
"learning_rate": 3.604268195453421e-05,
"loss": 5.0886,
"step": 3745
},
{
"epoch": 0.75,
"grad_norm": 0.26938632130622864,
"learning_rate": 3.577473468234156e-05,
"loss": 5.2101,
"step": 3750
},
{
"epoch": 0.751,
"grad_norm": 0.31986427307128906,
"learning_rate": 3.5507569974738574e-05,
"loss": 5.1127,
"step": 3755
},
{
"epoch": 0.752,
"grad_norm": 0.33934304118156433,
"learning_rate": 3.524119108704286e-05,
"loss": 5.1499,
"step": 3760
},
{
"epoch": 0.753,
"grad_norm": 0.22165915369987488,
"learning_rate": 3.497560126499709e-05,
"loss": 5.2039,
"step": 3765
},
{
"epoch": 0.754,
"grad_norm": 0.3137538433074951,
"learning_rate": 3.4710803744729515e-05,
"loss": 5.178,
"step": 3770
},
{
"epoch": 0.755,
"grad_norm": 0.327399343252182,
"learning_rate": 3.444680175271428e-05,
"loss": 5.175,
"step": 3775
},
{
"epoch": 0.756,
"grad_norm": 0.2913539409637451,
"learning_rate": 3.418359850573234e-05,
"loss": 5.1825,
"step": 3780
},
{
"epoch": 0.757,
"grad_norm": 0.2608703374862671,
"learning_rate": 3.3921197210832235e-05,
"loss": 5.1484,
"step": 3785
},
{
"epoch": 0.758,
"grad_norm": 0.22804005444049835,
"learning_rate": 3.3659601065290893e-05,
"loss": 5.1017,
"step": 3790
},
{
"epoch": 0.759,
"grad_norm": 0.2799939215183258,
"learning_rate": 3.339881325657484e-05,
"loss": 5.0905,
"step": 3795
},
{
"epoch": 0.76,
"grad_norm": 0.2560652196407318,
"learning_rate": 3.313883696230119e-05,
"loss": 5.1123,
"step": 3800
},
{
"epoch": 0.761,
"grad_norm": 0.2641059458255768,
"learning_rate": 3.287967535019908e-05,
"loss": 5.1905,
"step": 3805
},
{
"epoch": 0.762,
"grad_norm": 0.23254606127738953,
"learning_rate": 3.2621331578070934e-05,
"loss": 5.056,
"step": 3810
},
{
"epoch": 0.763,
"grad_norm": 0.33298707008361816,
"learning_rate": 3.236380879375408e-05,
"loss": 5.0303,
"step": 3815
},
{
"epoch": 0.764,
"grad_norm": 0.2716754078865051,
"learning_rate": 3.210711013508242e-05,
"loss": 5.1135,
"step": 3820
},
{
"epoch": 0.765,
"grad_norm": 0.2564438581466675,
"learning_rate": 3.1851238729848034e-05,
"loss": 5.1271,
"step": 3825
},
{
"epoch": 0.766,
"grad_norm": 0.262759268283844,
"learning_rate": 3.159619769576333e-05,
"loss": 5.1628,
"step": 3830
},
{
"epoch": 0.767,
"grad_norm": 0.24736341834068298,
"learning_rate": 3.134199014042274e-05,
"loss": 5.1296,
"step": 3835
},
{
"epoch": 0.768,
"grad_norm": 0.228183776140213,
"learning_rate": 3.108861916126518e-05,
"loss": 5.121,
"step": 3840
},
{
"epoch": 0.769,
"grad_norm": 0.24445924162864685,
"learning_rate": 3.0836087845536e-05,
"loss": 5.0986,
"step": 3845
},
{
"epoch": 0.77,
"grad_norm": 0.25795966386795044,
"learning_rate": 3.058439927024962e-05,
"loss": 5.1669,
"step": 3850
},
{
"epoch": 0.771,
"grad_norm": 0.24204669892787933,
"learning_rate": 3.0333556502151926e-05,
"loss": 5.144,
"step": 3855
},
{
"epoch": 0.772,
"grad_norm": 0.2623887360095978,
"learning_rate": 3.0083562597682847e-05,
"loss": 5.0788,
"step": 3860
},
{
"epoch": 0.773,
"grad_norm": 0.28754106163978577,
"learning_rate": 2.9834420602939263e-05,
"loss": 5.1624,
"step": 3865
},
{
"epoch": 0.774,
"grad_norm": 0.25644269585609436,
"learning_rate": 2.9586133553637683e-05,
"loss": 5.1187,
"step": 3870
},
{
"epoch": 0.775,
"grad_norm": 0.2573501765727997,
"learning_rate": 2.933870447507753e-05,
"loss": 5.1188,
"step": 3875
},
{
"epoch": 0.776,
"grad_norm": 0.33023008704185486,
"learning_rate": 2.9092136382103973e-05,
"loss": 5.0713,
"step": 3880
},
{
"epoch": 0.777,
"grad_norm": 0.22395578026771545,
"learning_rate": 2.8846432279071467e-05,
"loss": 5.1788,
"step": 3885
},
{
"epoch": 0.778,
"grad_norm": 0.3413115441799164,
"learning_rate": 2.860159515980695e-05,
"loss": 5.1688,
"step": 3890
},
{
"epoch": 0.779,
"grad_norm": 0.29099181294441223,
"learning_rate": 2.835762800757341e-05,
"loss": 5.1227,
"step": 3895
},
{
"epoch": 0.78,
"grad_norm": 0.3346491754055023,
"learning_rate": 2.8114533795033683e-05,
"loss": 5.0012,
"step": 3900
},
{
"epoch": 0.781,
"grad_norm": 0.5266372561454773,
"learning_rate": 2.7872315484213952e-05,
"loss": 5.0863,
"step": 3905
},
{
"epoch": 0.782,
"grad_norm": 0.2958402633666992,
"learning_rate": 2.7630976026467968e-05,
"loss": 5.0392,
"step": 3910
},
{
"epoch": 0.783,
"grad_norm": 0.389279305934906,
"learning_rate": 2.7390518362440808e-05,
"loss": 5.0483,
"step": 3915
},
{
"epoch": 0.784,
"grad_norm": 0.34358248114585876,
"learning_rate": 2.715094542203327e-05,
"loss": 5.0089,
"step": 3920
},
{
"epoch": 0.785,
"grad_norm": 0.29305362701416016,
"learning_rate": 2.6912260124366006e-05,
"loss": 5.1741,
"step": 3925
},
{
"epoch": 0.786,
"grad_norm": 0.24087849259376526,
"learning_rate": 2.6674465377744017e-05,
"loss": 5.1137,
"step": 3930
},
{
"epoch": 0.787,
"grad_norm": 0.2460707277059555,
"learning_rate": 2.6437564079621267e-05,
"loss": 5.1405,
"step": 3935
},
{
"epoch": 0.788,
"grad_norm": 0.34061485528945923,
"learning_rate": 2.6201559116565345e-05,
"loss": 5.0787,
"step": 3940
},
{
"epoch": 0.789,
"grad_norm": 0.23867876827716827,
"learning_rate": 2.5966453364222186e-05,
"loss": 5.1016,
"step": 3945
},
{
"epoch": 0.79,
"grad_norm": 0.23024287819862366,
"learning_rate": 2.573224968728123e-05,
"loss": 5.0967,
"step": 3950
},
{
"epoch": 0.791,
"grad_norm": 0.2635563611984253,
"learning_rate": 2.549895093944039e-05,
"loss": 5.2122,
"step": 3955
},
{
"epoch": 0.792,
"grad_norm": 0.27382388710975647,
"learning_rate": 2.5266559963371216e-05,
"loss": 5.059,
"step": 3960
},
{
"epoch": 0.793,
"grad_norm": 0.23172074556350708,
"learning_rate": 2.5035079590684497e-05,
"loss": 5.1111,
"step": 3965
},
{
"epoch": 0.794,
"grad_norm": 0.24881790578365326,
"learning_rate": 2.480451264189546e-05,
"loss": 5.1023,
"step": 3970
},
{
"epoch": 0.795,
"grad_norm": 0.23356951773166656,
"learning_rate": 2.4574861926389615e-05,
"loss": 5.0756,
"step": 3975
},
{
"epoch": 0.796,
"grad_norm": 0.39573103189468384,
"learning_rate": 2.43461302423885e-05,
"loss": 5.1876,
"step": 3980
},
{
"epoch": 0.797,
"grad_norm": 0.36956608295440674,
"learning_rate": 2.411832037691545e-05,
"loss": 5.2628,
"step": 3985
},
{
"epoch": 0.798,
"grad_norm": 0.29458558559417725,
"learning_rate": 2.389143510576184e-05,
"loss": 5.0812,
"step": 3990
},
{
"epoch": 0.799,
"grad_norm": 0.2434677928686142,
"learning_rate": 2.3665477193453034e-05,
"loss": 5.1257,
"step": 3995
},
{
"epoch": 0.8,
"grad_norm": 0.217316672205925,
"learning_rate": 2.3440449393214948e-05,
"loss": 5.0084,
"step": 4000
},
{
"epoch": 0.801,
"grad_norm": 0.322103351354599,
"learning_rate": 2.321635444694028e-05,
"loss": 5.0164,
"step": 4005
},
{
"epoch": 0.802,
"grad_norm": 0.3849366009235382,
"learning_rate": 2.2993195085155205e-05,
"loss": 5.0705,
"step": 4010
},
{
"epoch": 0.803,
"grad_norm": 0.25024399161338806,
"learning_rate": 2.277097402698619e-05,
"loss": 5.0704,
"step": 4015
},
{
"epoch": 0.804,
"grad_norm": 0.3271205723285675,
"learning_rate": 2.254969398012663e-05,
"loss": 5.1637,
"step": 4020
},
{
"epoch": 0.805,
"grad_norm": 0.289032906293869,
"learning_rate": 2.2329357640804117e-05,
"loss": 5.1086,
"step": 4025
},
{
"epoch": 0.806,
"grad_norm": 0.2275077998638153,
"learning_rate": 2.210996769374737e-05,
"loss": 5.1471,
"step": 4030
},
{
"epoch": 0.807,
"grad_norm": 0.23290930688381195,
"learning_rate": 2.1891526812153672e-05,
"loss": 5.1158,
"step": 4035
},
{
"epoch": 0.808,
"grad_norm": 0.24038785696029663,
"learning_rate": 2.1674037657656266e-05,
"loss": 5.1052,
"step": 4040
},
{
"epoch": 0.809,
"grad_norm": 0.2918753921985626,
"learning_rate": 2.1457502880291812e-05,
"loss": 5.123,
"step": 4045
},
{
"epoch": 0.81,
"grad_norm": 0.2754362225532532,
"learning_rate": 2.1241925118468287e-05,
"loss": 5.2038,
"step": 4050
},
{
"epoch": 0.811,
"grad_norm": 0.2677970230579376,
"learning_rate": 2.1027306998932627e-05,
"loss": 5.1486,
"step": 4055
},
{
"epoch": 0.812,
"grad_norm": 0.22959089279174805,
"learning_rate": 2.0813651136738954e-05,
"loss": 5.0638,
"step": 4060
},
{
"epoch": 0.813,
"grad_norm": 0.2706676721572876,
"learning_rate": 2.0600960135216462e-05,
"loss": 5.1317,
"step": 4065
},
{
"epoch": 0.814,
"grad_norm": 0.23487025499343872,
"learning_rate": 2.0389236585937945e-05,
"loss": 5.0852,
"step": 4070
},
{
"epoch": 0.815,
"grad_norm": 0.3063757121562958,
"learning_rate": 2.017848306868797e-05,
"loss": 5.0415,
"step": 4075
},
{
"epoch": 0.816,
"grad_norm": 0.2563547194004059,
"learning_rate": 1.9968702151431696e-05,
"loss": 5.1094,
"step": 4080
},
{
"epoch": 0.817,
"grad_norm": 0.23000560700893402,
"learning_rate": 1.9759896390283362e-05,
"loss": 5.1024,
"step": 4085
},
{
"epoch": 0.818,
"grad_norm": 0.28403353691101074,
"learning_rate": 1.955206832947526e-05,
"loss": 5.0703,
"step": 4090
},
{
"epoch": 0.819,
"grad_norm": 0.2204357534646988,
"learning_rate": 1.9345220501326777e-05,
"loss": 5.1449,
"step": 4095
},
{
"epoch": 0.82,
"grad_norm": 0.2466605007648468,
"learning_rate": 1.9139355426213347e-05,
"loss": 5.103,
"step": 4100
},
{
"epoch": 0.821,
"grad_norm": 0.2660214900970459,
"learning_rate": 1.8934475612536017e-05,
"loss": 5.0441,
"step": 4105
},
{
"epoch": 0.822,
"grad_norm": 0.22450104355812073,
"learning_rate": 1.8730583556690605e-05,
"loss": 5.1433,
"step": 4110
},
{
"epoch": 0.823,
"grad_norm": 0.2551158368587494,
"learning_rate": 1.852768174303752e-05,
"loss": 5.0912,
"step": 4115
},
{
"epoch": 0.824,
"grad_norm": 0.38103002309799194,
"learning_rate": 1.8325772643871265e-05,
"loss": 5.073,
"step": 4120
},
{
"epoch": 0.825,
"grad_norm": 0.2854713201522827,
"learning_rate": 1.812485871939056e-05,
"loss": 5.0864,
"step": 4125
},
{
"epoch": 0.826,
"grad_norm": 0.2670081853866577,
"learning_rate": 1.792494241766811e-05,
"loss": 5.1375,
"step": 4130
},
{
"epoch": 0.827,
"grad_norm": 0.27579382061958313,
"learning_rate": 1.7726026174621003e-05,
"loss": 5.1162,
"step": 4135
},
{
"epoch": 0.828,
"grad_norm": 0.2304496467113495,
"learning_rate": 1.752811241398089e-05,
"loss": 5.1812,
"step": 4140
},
{
"epoch": 0.829,
"grad_norm": 0.21075308322906494,
"learning_rate": 1.7331203547264453e-05,
"loss": 5.1961,
"step": 4145
},
{
"epoch": 0.83,
"grad_norm": 0.23746763169765472,
"learning_rate": 1.7135301973744124e-05,
"loss": 5.1018,
"step": 4150
},
{
"epoch": 0.831,
"grad_norm": 0.33572885394096375,
"learning_rate": 1.6940410080418723e-05,
"loss": 5.1138,
"step": 4155
},
{
"epoch": 0.832,
"grad_norm": 0.27261218428611755,
"learning_rate": 1.6746530241984504e-05,
"loss": 5.0935,
"step": 4160
},
{
"epoch": 0.833,
"grad_norm": 0.20708340406417847,
"learning_rate": 1.6553664820806102e-05,
"loss": 5.0667,
"step": 4165
},
{
"epoch": 0.834,
"grad_norm": 0.2631475627422333,
"learning_rate": 1.6361816166887768e-05,
"loss": 5.1547,
"step": 4170
},
{
"epoch": 0.835,
"grad_norm": 0.3124708831310272,
"learning_rate": 1.6170986617844863e-05,
"loss": 5.1468,
"step": 4175
},
{
"epoch": 0.836,
"grad_norm": 0.2195052057504654,
"learning_rate": 1.598117849887518e-05,
"loss": 5.039,
"step": 4180
},
{
"epoch": 0.837,
"grad_norm": 0.4436738193035126,
"learning_rate": 1.579239412273078e-05,
"loss": 5.1339,
"step": 4185
},
{
"epoch": 0.838,
"grad_norm": 0.2705097794532776,
"learning_rate": 1.560463578968967e-05,
"loss": 5.0876,
"step": 4190
},
{
"epoch": 0.839,
"grad_norm": 0.23402278125286102,
"learning_rate": 1.541790578752794e-05,
"loss": 5.0036,
"step": 4195
},
{
"epoch": 0.84,
"grad_norm": 0.30986011028289795,
"learning_rate": 1.5232206391491699e-05,
"loss": 5.0722,
"step": 4200
},
{
"epoch": 0.841,
"grad_norm": 0.2453794926404953,
"learning_rate": 1.5047539864269478e-05,
"loss": 5.1298,
"step": 4205
},
{
"epoch": 0.842,
"grad_norm": 0.3003180921077728,
"learning_rate": 1.486390845596466e-05,
"loss": 5.1269,
"step": 4210
},
{
"epoch": 0.843,
"grad_norm": 0.2445596307516098,
"learning_rate": 1.468131440406798e-05,
"loss": 5.0509,
"step": 4215
},
{
"epoch": 0.844,
"grad_norm": 0.2482488602399826,
"learning_rate": 1.4499759933430346e-05,
"loss": 5.1162,
"step": 4220
},
{
"epoch": 0.845,
"grad_norm": 0.33505016565322876,
"learning_rate": 1.4319247256235714e-05,
"loss": 5.0152,
"step": 4225
},
{
"epoch": 0.846,
"grad_norm": 0.23183396458625793,
"learning_rate": 1.4139778571974049e-05,
"loss": 5.0536,
"step": 4230
},
{
"epoch": 0.847,
"grad_norm": 0.2753032445907593,
"learning_rate": 1.3961356067414666e-05,
"loss": 5.0371,
"step": 4235
},
{
"epoch": 0.848,
"grad_norm": 0.28026026487350464,
"learning_rate": 1.3783981916579446e-05,
"loss": 5.0849,
"step": 4240
},
{
"epoch": 0.849,
"grad_norm": 0.22306375205516815,
"learning_rate": 1.3607658280716473e-05,
"loss": 5.0886,
"step": 4245
},
{
"epoch": 0.85,
"grad_norm": 0.2506760358810425,
"learning_rate": 1.3432387308273575e-05,
"loss": 5.1157,
"step": 4250
},
{
"epoch": 0.851,
"grad_norm": 0.26801741123199463,
"learning_rate": 1.3258171134872265e-05,
"loss": 5.1511,
"step": 4255
},
{
"epoch": 0.852,
"grad_norm": 0.2264227718114853,
"learning_rate": 1.3085011883281606e-05,
"loss": 5.0669,
"step": 4260
},
{
"epoch": 0.853,
"grad_norm": 0.2607322931289673,
"learning_rate": 1.2912911663392469e-05,
"loss": 5.0391,
"step": 4265
},
{
"epoch": 0.854,
"grad_norm": 0.2878810465335846,
"learning_rate": 1.2741872572191682e-05,
"loss": 5.1589,
"step": 4270
},
{
"epoch": 0.855,
"grad_norm": 0.2933845520019531,
"learning_rate": 1.257189669373664e-05,
"loss": 5.0784,
"step": 4275
},
{
"epoch": 0.856,
"grad_norm": 0.2782781422138214,
"learning_rate": 1.2402986099129765e-05,
"loss": 5.0924,
"step": 4280
},
{
"epoch": 0.857,
"grad_norm": 0.2926121950149536,
"learning_rate": 1.2235142846493308e-05,
"loss": 5.1172,
"step": 4285
},
{
"epoch": 0.858,
"grad_norm": 0.22161071002483368,
"learning_rate": 1.206836898094439e-05,
"loss": 5.0583,
"step": 4290
},
{
"epoch": 0.859,
"grad_norm": 0.3642433285713196,
"learning_rate": 1.1902666534569883e-05,
"loss": 5.1373,
"step": 4295
},
{
"epoch": 0.86,
"grad_norm": 0.24289703369140625,
"learning_rate": 1.1738037526401857e-05,
"loss": 5.1953,
"step": 4300
},
{
"epoch": 0.861,
"grad_norm": 0.305922269821167,
"learning_rate": 1.1574483962392767e-05,
"loss": 5.0563,
"step": 4305
},
{
"epoch": 0.862,
"grad_norm": 0.3565390706062317,
"learning_rate": 1.1412007835391236e-05,
"loss": 5.1069,
"step": 4310
},
{
"epoch": 0.863,
"grad_norm": 0.2853083908557892,
"learning_rate": 1.1250611125117527e-05,
"loss": 5.1049,
"step": 4315
},
{
"epoch": 0.864,
"grad_norm": 0.24222713708877563,
"learning_rate": 1.1090295798139672e-05,
"loss": 5.1866,
"step": 4320
},
{
"epoch": 0.865,
"grad_norm": 0.2596699893474579,
"learning_rate": 1.093106380784934e-05,
"loss": 5.1269,
"step": 4325
},
{
"epoch": 0.866,
"grad_norm": 0.638543426990509,
"learning_rate": 1.0772917094438051e-05,
"loss": 5.1169,
"step": 4330
},
{
"epoch": 0.867,
"grad_norm": 0.28333714604377747,
"learning_rate": 1.0615857584873623e-05,
"loss": 5.1237,
"step": 4335
},
{
"epoch": 0.868,
"grad_norm": 0.2674027979373932,
"learning_rate": 1.0459887192876594e-05,
"loss": 5.1189,
"step": 4340
},
{
"epoch": 0.869,
"grad_norm": 0.22415874898433685,
"learning_rate": 1.0305007818897006e-05,
"loss": 5.1492,
"step": 4345
},
{
"epoch": 0.87,
"grad_norm": 0.2645719051361084,
"learning_rate": 1.0151221350091134e-05,
"loss": 5.0202,
"step": 4350
},
{
"epoch": 0.871,
"grad_norm": 0.3162263333797455,
"learning_rate": 9.998529660298539e-06,
"loss": 5.0307,
"step": 4355
},
{
"epoch": 0.872,
"grad_norm": 0.20605884492397308,
"learning_rate": 9.84693461001932e-06,
"loss": 5.101,
"step": 4360
},
{
"epoch": 0.873,
"grad_norm": 0.3320538103580475,
"learning_rate": 9.696438046391288e-06,
"loss": 5.1201,
"step": 4365
},
{
"epoch": 0.874,
"grad_norm": 0.24943017959594727,
"learning_rate": 9.5470418031676e-06,
"loss": 5.1212,
"step": 4370
},
{
"epoch": 0.875,
"grad_norm": 0.4204804599285126,
"learning_rate": 9.398747700694322e-06,
"loss": 5.1518,
"step": 4375
},
{
"epoch": 0.876,
"grad_norm": 0.254229873418808,
"learning_rate": 9.251557545888312e-06,
"loss": 5.0942,
"step": 4380
},
{
"epoch": 0.877,
"grad_norm": 0.2604995369911194,
"learning_rate": 9.105473132215125e-06,
"loss": 5.0364,
"step": 4385
},
{
"epoch": 0.878,
"grad_norm": 0.2345636636018753,
"learning_rate": 8.960496239667282e-06,
"loss": 5.0902,
"step": 4390
},
{
"epoch": 0.879,
"grad_norm": 0.26052191853523254,
"learning_rate": 8.816628634742441e-06,
"loss": 5.0689,
"step": 4395
},
{
"epoch": 0.88,
"grad_norm": 0.2771487832069397,
"learning_rate": 8.67387207042194e-06,
"loss": 5.1534,
"step": 4400
},
{
"epoch": 0.881,
"grad_norm": 0.27210870385169983,
"learning_rate": 8.532228286149501e-06,
"loss": 5.0478,
"step": 4405
},
{
"epoch": 0.882,
"grad_norm": 0.242442786693573,
"learning_rate": 8.39169900780995e-06,
"loss": 5.1411,
"step": 4410
},
{
"epoch": 0.883,
"grad_norm": 0.23587566614151,
"learning_rate": 8.252285947708139e-06,
"loss": 5.105,
"step": 4415
},
{
"epoch": 0.884,
"grad_norm": 0.4089321196079254,
"learning_rate": 8.113990804548244e-06,
"loss": 5.0357,
"step": 4420
},
{
"epoch": 0.885,
"grad_norm": 0.2824915945529938,
"learning_rate": 7.976815263412963e-06,
"loss": 5.0579,
"step": 4425
},
{
"epoch": 0.886,
"grad_norm": 0.46637028455734253,
"learning_rate": 7.840760995742946e-06,
"loss": 5.0366,
"step": 4430
},
{
"epoch": 0.887,
"grad_norm": 0.2925930619239807,
"learning_rate": 7.7058296593165e-06,
"loss": 5.0091,
"step": 4435
},
{
"epoch": 0.888,
"grad_norm": 0.32699304819107056,
"learning_rate": 7.572022898229403e-06,
"loss": 5.1491,
"step": 4440
},
{
"epoch": 0.889,
"grad_norm": 0.2378702014684677,
"learning_rate": 7.439342342874789e-06,
"loss": 5.1257,
"step": 4445
},
{
"epoch": 0.89,
"grad_norm": 0.23806598782539368,
"learning_rate": 7.3077896099233765e-06,
"loss": 5.0726,
"step": 4450
},
{
"epoch": 0.891,
"grad_norm": 0.2510644793510437,
"learning_rate": 7.177366302303667e-06,
"loss": 5.0795,
"step": 4455
},
{
"epoch": 0.892,
"grad_norm": 0.2585172653198242,
"learning_rate": 7.048074009182548e-06,
"loss": 5.1597,
"step": 4460
},
{
"epoch": 0.893,
"grad_norm": 0.25811630487442017,
"learning_rate": 6.919914305945774e-06,
"loss": 5.0452,
"step": 4465
},
{
"epoch": 0.894,
"grad_norm": 0.22726012766361237,
"learning_rate": 6.7928887541789055e-06,
"loss": 5.1502,
"step": 4470
},
{
"epoch": 0.895,
"grad_norm": 0.26654765009880066,
"learning_rate": 6.666998901648203e-06,
"loss": 5.1571,
"step": 4475
},
{
"epoch": 0.896,
"grad_norm": 0.22968906164169312,
"learning_rate": 6.542246282281772e-06,
"loss": 5.0884,
"step": 4480
},
{
"epoch": 0.897,
"grad_norm": 0.22456640005111694,
"learning_rate": 6.418632416150927e-06,
"loss": 5.1072,
"step": 4485
},
{
"epoch": 0.898,
"grad_norm": 0.2621786296367645,
"learning_rate": 6.296158809451602e-06,
"loss": 5.0955,
"step": 4490
},
{
"epoch": 0.899,
"grad_norm": 0.3561532199382782,
"learning_rate": 6.174826954486068e-06,
"loss": 5.1559,
"step": 4495
},
{
"epoch": 0.9,
"grad_norm": 0.22242926061153412,
"learning_rate": 6.054638329644657e-06,
"loss": 5.0386,
"step": 4500
},
{
"epoch": 0.901,
"grad_norm": 0.4509942829608917,
"learning_rate": 5.935594399387856e-06,
"loss": 5.0997,
"step": 4505
},
{
"epoch": 0.902,
"grad_norm": 0.31875094771385193,
"learning_rate": 5.8176966142283965e-06,
"loss": 5.0594,
"step": 4510
},
{
"epoch": 0.903,
"grad_norm": 0.18587560951709747,
"learning_rate": 5.700946410713548e-06,
"loss": 5.0573,
"step": 4515
},
{
"epoch": 0.904,
"grad_norm": 0.2304026335477829,
"learning_rate": 5.585345211407733e-06,
"loss": 5.0469,
"step": 4520
},
{
"epoch": 0.905,
"grad_norm": 0.6561840772628784,
"learning_rate": 5.470894424875062e-06,
"loss": 5.1178,
"step": 4525
},
{
"epoch": 0.906,
"grad_norm": 0.2817283570766449,
"learning_rate": 5.357595445662267e-06,
"loss": 5.1955,
"step": 4530
},
{
"epoch": 0.907,
"grad_norm": 0.2137559950351715,
"learning_rate": 5.245449654281631e-06,
"loss": 5.0801,
"step": 4535
},
{
"epoch": 0.908,
"grad_norm": 0.29070359468460083,
"learning_rate": 5.134458417194254e-06,
"loss": 5.0965,
"step": 4540
},
{
"epoch": 0.909,
"grad_norm": 0.32578277587890625,
"learning_rate": 5.024623086793323e-06,
"loss": 5.0862,
"step": 4545
},
{
"epoch": 0.91,
"grad_norm": 0.21135179698467255,
"learning_rate": 4.915945001387667e-06,
"loss": 5.0681,
"step": 4550
},
{
"epoch": 0.911,
"grad_norm": 0.22728188335895538,
"learning_rate": 4.808425485185486e-06,
"loss": 5.0061,
"step": 4555
},
{
"epoch": 0.912,
"grad_norm": 0.27983295917510986,
"learning_rate": 4.702065848278126e-06,
"loss": 5.0609,
"step": 4560
},
{
"epoch": 0.913,
"grad_norm": 0.2516406178474426,
"learning_rate": 4.596867386624215e-06,
"loss": 5.1075,
"step": 4565
},
{
"epoch": 0.914,
"grad_norm": 0.25222429633140564,
"learning_rate": 4.492831382033791e-06,
"loss": 5.1692,
"step": 4570
},
{
"epoch": 0.915,
"grad_norm": 0.2541888654232025,
"learning_rate": 4.389959102152774e-06,
"loss": 5.0879,
"step": 4575
},
{
"epoch": 0.916,
"grad_norm": 0.23486195504665375,
"learning_rate": 4.288251800447385e-06,
"loss": 5.1151,
"step": 4580
},
{
"epoch": 0.917,
"grad_norm": 0.23812493681907654,
"learning_rate": 4.187710716189042e-06,
"loss": 5.0637,
"step": 4585
},
{
"epoch": 0.918,
"grad_norm": 0.24248802661895752,
"learning_rate": 4.088337074439097e-06,
"loss": 5.1273,
"step": 4590
},
{
"epoch": 0.919,
"grad_norm": 0.23870691657066345,
"learning_rate": 3.990132086034026e-06,
"loss": 5.052,
"step": 4595
},
{
"epoch": 0.92,
"grad_norm": 0.25752246379852295,
"learning_rate": 3.893096947570618e-06,
"loss": 5.061,
"step": 4600
},
{
"epoch": 0.921,
"grad_norm": 0.3598933815956116,
"learning_rate": 3.797232841391407e-06,
"loss": 5.0993,
"step": 4605
},
{
"epoch": 0.922,
"grad_norm": 0.20714561641216278,
"learning_rate": 3.7025409355702976e-06,
"loss": 5.1042,
"step": 4610
},
{
"epoch": 0.923,
"grad_norm": 0.37252742052078247,
"learning_rate": 3.6090223838982417e-06,
"loss": 5.085,
"step": 4615
},
{
"epoch": 0.924,
"grad_norm": 0.23721784353256226,
"learning_rate": 3.516678325869316e-06,
"loss": 5.0469,
"step": 4620
},
{
"epoch": 0.925,
"grad_norm": 0.3685450255870819,
"learning_rate": 3.425509886666711e-06,
"loss": 5.0085,
"step": 4625
},
{
"epoch": 0.926,
"grad_norm": 0.3412356376647949,
"learning_rate": 3.3355181771490772e-06,
"loss": 5.0142,
"step": 4630
},
{
"epoch": 0.927,
"grad_norm": 0.20389394462108612,
"learning_rate": 3.246704293837011e-06,
"loss": 5.06,
"step": 4635
},
{
"epoch": 0.928,
"grad_norm": 0.27703946828842163,
"learning_rate": 3.1590693188996323e-06,
"loss": 5.0265,
"step": 4640
},
{
"epoch": 0.929,
"grad_norm": 0.24961715936660767,
"learning_rate": 3.072614320141487e-06,
"loss": 5.0439,
"step": 4645
},
{
"epoch": 0.93,
"grad_norm": 0.22278626263141632,
"learning_rate": 2.9873403509894203e-06,
"loss": 5.0369,
"step": 4650
},
{
"epoch": 0.931,
"grad_norm": 0.20248129963874817,
"learning_rate": 2.9032484504798452e-06,
"loss": 5.0992,
"step": 4655
},
{
"epoch": 0.932,
"grad_norm": 0.21499867737293243,
"learning_rate": 2.8203396432460506e-06,
"loss": 5.0399,
"step": 4660
},
{
"epoch": 0.933,
"grad_norm": 0.20902930200099945,
"learning_rate": 2.738614939505646e-06,
"loss": 5.0908,
"step": 4665
},
{
"epoch": 0.934,
"grad_norm": 0.32367953658103943,
"learning_rate": 2.6580753350484046e-06,
"loss": 5.0812,
"step": 4670
},
{
"epoch": 0.935,
"grad_norm": 0.2480151206254959,
"learning_rate": 2.5787218112239496e-06,
"loss": 5.0669,
"step": 4675
},
{
"epoch": 0.936,
"grad_norm": 0.2491266280412674,
"learning_rate": 2.5005553349299547e-06,
"loss": 5.1347,
"step": 4680
},
{
"epoch": 0.937,
"grad_norm": 0.2383667230606079,
"learning_rate": 2.4235768586002517e-06,
"loss": 5.0588,
"step": 4685
},
{
"epoch": 0.938,
"grad_norm": 0.2206917554140091,
"learning_rate": 2.3477873201932734e-06,
"loss": 5.1281,
"step": 4690
},
{
"epoch": 0.939,
"grad_norm": 0.233530655503273,
"learning_rate": 2.273187643180652e-06,
"loss": 5.0666,
"step": 4695
},
{
"epoch": 0.94,
"grad_norm": 0.2189059555530548,
"learning_rate": 2.1997787365358958e-06,
"loss": 5.074,
"step": 4700
},
{
"epoch": 0.941,
"grad_norm": 0.23790404200553894,
"learning_rate": 2.1275614947233624e-06,
"loss": 5.0598,
"step": 4705
},
{
"epoch": 0.942,
"grad_norm": 0.21796126663684845,
"learning_rate": 2.0565367976873584e-06,
"loss": 5.063,
"step": 4710
},
{
"epoch": 0.943,
"grad_norm": 0.21157915890216827,
"learning_rate": 1.986705510841402e-06,
"loss": 5.0856,
"step": 4715
},
{
"epoch": 0.944,
"grad_norm": 0.21599438786506653,
"learning_rate": 1.918068485057689e-06,
"loss": 5.0823,
"step": 4720
},
{
"epoch": 0.945,
"grad_norm": 0.23867011070251465,
"learning_rate": 1.8506265566567094e-06,
"loss": 5.0877,
"step": 4725
},
{
"epoch": 0.946,
"grad_norm": 0.2665407061576843,
"learning_rate": 1.7843805473970798e-06,
"loss": 5.0857,
"step": 4730
},
{
"epoch": 0.947,
"grad_norm": 0.3465604782104492,
"learning_rate": 1.719331264465529e-06,
"loss": 5.1193,
"step": 4735
},
{
"epoch": 0.948,
"grad_norm": 0.2804303765296936,
"learning_rate": 1.6554795004670388e-06,
"loss": 5.0738,
"step": 4740
},
{
"epoch": 0.949,
"grad_norm": 0.31609681248664856,
"learning_rate": 1.5928260334151845e-06,
"loss": 5.0888,
"step": 4745
},
{
"epoch": 0.95,
"grad_norm": 0.3094084858894348,
"learning_rate": 1.5313716267226996e-06,
"loss": 5.1448,
"step": 4750
},
{
"epoch": 0.951,
"grad_norm": 0.22568446397781372,
"learning_rate": 1.4711170291921484e-06,
"loss": 5.1426,
"step": 4755
},
{
"epoch": 0.952,
"grad_norm": 0.23813877999782562,
"learning_rate": 1.412062975006767e-06,
"loss": 5.0757,
"step": 4760
},
{
"epoch": 0.953,
"grad_norm": 0.3022629916667938,
"learning_rate": 1.3542101837215826e-06,
"loss": 5.1092,
"step": 4765
},
{
"epoch": 0.954,
"grad_norm": 0.41990604996681213,
"learning_rate": 1.2975593602545965e-06,
"loss": 5.1528,
"step": 4770
},
{
"epoch": 0.955,
"grad_norm": 0.27166977524757385,
"learning_rate": 1.2421111948782149e-06,
"loss": 5.0259,
"step": 4775
},
{
"epoch": 0.956,
"grad_norm": 0.22497738897800446,
"learning_rate": 1.1878663632108322e-06,
"loss": 5.0043,
"step": 4780
},
{
"epoch": 0.957,
"grad_norm": 0.2617851793766022,
"learning_rate": 1.134825526208605e-06,
"loss": 5.1149,
"step": 4785
},
{
"epoch": 0.958,
"grad_norm": 0.20539118349552155,
"learning_rate": 1.0829893301573913e-06,
"loss": 5.0631,
"step": 4790
},
{
"epoch": 0.959,
"grad_norm": 0.23467594385147095,
"learning_rate": 1.0323584066648795e-06,
"loss": 5.0166,
"step": 4795
},
{
"epoch": 0.96,
"grad_norm": 0.3386589586734772,
"learning_rate": 9.829333726529056e-07,
"loss": 5.0376,
"step": 4800
},
{
"epoch": 0.961,
"grad_norm": 0.2032572478055954,
"learning_rate": 9.347148303499142e-07,
"loss": 5.0399,
"step": 4805
},
{
"epoch": 0.962,
"grad_norm": 0.8042163848876953,
"learning_rate": 8.877033672835988e-07,
"loss": 5.1074,
"step": 4810
},
{
"epoch": 0.963,
"grad_norm": 0.35133257508277893,
"learning_rate": 8.418995562738285e-07,
"loss": 5.0773,
"step": 4815
},
{
"epoch": 0.964,
"grad_norm": 0.7319326400756836,
"learning_rate": 7.973039554255768e-07,
"loss": 5.2504,
"step": 4820
},
{
"epoch": 0.965,
"grad_norm": 0.23363058269023895,
"learning_rate": 7.539171081221596e-07,
"loss": 5.2244,
"step": 4825
},
{
"epoch": 0.966,
"grad_norm": 0.2833423912525177,
"learning_rate": 7.117395430186414e-07,
"loss": 5.0875,
"step": 4830
},
{
"epoch": 0.967,
"grad_norm": 0.2671878933906555,
"learning_rate": 6.707717740353059e-07,
"loss": 5.0726,
"step": 4835
},
{
"epoch": 0.968,
"grad_norm": 0.21520812809467316,
"learning_rate": 6.310143003515179e-07,
"loss": 5.0901,
"step": 4840
},
{
"epoch": 0.969,
"grad_norm": 0.256833553314209,
"learning_rate": 5.924676063995382e-07,
"loss": 5.1132,
"step": 4845
},
{
"epoch": 0.97,
"grad_norm": 0.20577143132686615,
"learning_rate": 5.551321618586736e-07,
"loss": 5.0896,
"step": 4850
},
{
"epoch": 0.971,
"grad_norm": 0.23326168954372406,
"learning_rate": 5.190084216495361e-07,
"loss": 5.1573,
"step": 4855
},
{
"epoch": 0.972,
"grad_norm": 0.2375091165304184,
"learning_rate": 4.840968259284817e-07,
"loss": 5.1437,
"step": 4860
},
{
"epoch": 0.973,
"grad_norm": 0.21946437656879425,
"learning_rate": 4.503978000823028e-07,
"loss": 5.0571,
"step": 4865
},
{
"epoch": 0.974,
"grad_norm": 0.2568575441837311,
"learning_rate": 4.179117547229883e-07,
"loss": 5.1249,
"step": 4870
},
{
"epoch": 0.975,
"grad_norm": 0.2227672040462494,
"learning_rate": 3.866390856827495e-07,
"loss": 5.0706,
"step": 4875
},
{
"epoch": 0.976,
"grad_norm": 0.2719704508781433,
"learning_rate": 3.565801740092023e-07,
"loss": 5.065,
"step": 4880
},
{
"epoch": 0.977,
"grad_norm": 0.4805198907852173,
"learning_rate": 3.277353859606813e-07,
"loss": 5.1143,
"step": 4885
},
{
"epoch": 0.978,
"grad_norm": 0.36212193965911865,
"learning_rate": 3.001050730018218e-07,
"loss": 5.1354,
"step": 4890
},
{
"epoch": 0.979,
"grad_norm": 0.21157288551330566,
"learning_rate": 2.73689571799296e-07,
"loss": 5.0797,
"step": 4895
},
{
"epoch": 0.98,
"grad_norm": 0.24859297275543213,
"learning_rate": 2.484892042176279e-07,
"loss": 5.0754,
"step": 4900
},
{
"epoch": 0.981,
"grad_norm": 0.38999709486961365,
"learning_rate": 2.2450427731534053e-07,
"loss": 5.0209,
"step": 4905
},
{
"epoch": 0.982,
"grad_norm": 0.3511657118797302,
"learning_rate": 2.017350833412146e-07,
"loss": 5.0425,
"step": 4910
},
{
"epoch": 0.983,
"grad_norm": 0.3107496201992035,
"learning_rate": 1.8018189973069143e-07,
"loss": 5.0769,
"step": 4915
},
{
"epoch": 0.984,
"grad_norm": 0.2202475666999817,
"learning_rate": 1.598449891024978e-07,
"loss": 5.0868,
"step": 4920
},
{
"epoch": 0.985,
"grad_norm": 0.20785170793533325,
"learning_rate": 1.4072459925548177e-07,
"loss": 5.0446,
"step": 4925
},
{
"epoch": 0.986,
"grad_norm": 0.21900968253612518,
"learning_rate": 1.2282096316554858e-07,
"loss": 5.0934,
"step": 4930
},
{
"epoch": 0.987,
"grad_norm": 0.20460066199302673,
"learning_rate": 1.0613429898287398e-07,
"loss": 5.0905,
"step": 4935
},
{
"epoch": 0.988,
"grad_norm": 0.4558361768722534,
"learning_rate": 9.066481002918403e-08,
"loss": 5.0812,
"step": 4940
},
{
"epoch": 0.989,
"grad_norm": 0.27589476108551025,
"learning_rate": 7.641268479531283e-08,
"loss": 5.0829,
"step": 4945
},
{
"epoch": 0.99,
"grad_norm": 0.21348121762275696,
"learning_rate": 6.337809693891527e-08,
"loss": 5.0338,
"step": 4950
},
{
"epoch": 0.991,
"grad_norm": 0.2553495764732361,
"learning_rate": 5.1561205282335547e-08,
"loss": 5.0622,
"step": 4955
},
{
"epoch": 0.992,
"grad_norm": 0.24432596564292908,
"learning_rate": 4.096215381066415e-08,
"loss": 5.0487,
"step": 4960
},
{
"epoch": 0.993,
"grad_norm": 0.3182646334171295,
"learning_rate": 3.1581071670006015e-08,
"loss": 5.0797,
"step": 4965
},
{
"epoch": 0.994,
"grad_norm": 0.2423093467950821,
"learning_rate": 2.3418073165870636e-08,
"loss": 5.1379,
"step": 4970
},
{
"epoch": 0.995,
"grad_norm": 0.25184163451194763,
"learning_rate": 1.6473257761828732e-08,
"loss": 5.0994,
"step": 4975
},
{
"epoch": 0.996,
"grad_norm": 0.3037627041339874,
"learning_rate": 1.074671007825767e-08,
"loss": 5.205,
"step": 4980
},
{
"epoch": 0.997,
"grad_norm": 0.2720518708229065,
"learning_rate": 6.238499891353389e-09,
"loss": 5.052,
"step": 4985
},
{
"epoch": 0.998,
"grad_norm": 0.3502713143825531,
"learning_rate": 2.948682132208891e-09,
"loss": 4.9614,
"step": 4990
},
{
"epoch": 0.999,
"grad_norm": 0.33826667070388794,
"learning_rate": 8.772968862369446e-10,
"loss": 4.9434,
"step": 4995
},
{
"epoch": 1.0,
"grad_norm": 0.26663097739219666,
"learning_rate": 2.4369392592760164e-11,
"loss": 5.0864,
"step": 5000
}
],
"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": 1.2604342699050903,
"learning_rate": 1.6000000000000001e-06,
"loss": 10.9732,
"step": 5
},
{
"epoch": 0.002,
"grad_norm": 1.1417402029037476,
"learning_rate": 3.6e-06,
"loss": 10.9292,
"step": 10
},
{
"epoch": 0.003,
"grad_norm": 1.0900236368179321,
"learning_rate": 5.600000000000001e-06,
"loss": 10.9342,
"step": 15
},
{
"epoch": 0.004,
"grad_norm": 1.0668010711669922,
"learning_rate": 7.6e-06,
"loss": 10.8892,
"step": 20
},
{
"epoch": 0.005,
"grad_norm": 0.85555499792099,
"learning_rate": 9.600000000000001e-06,
"loss": 10.6586,
"step": 25
},
{
"epoch": 0.006,
"grad_norm": 0.9816857576370239,
"learning_rate": 1.16e-05,
"loss": 10.6141,
"step": 30
},
{
"epoch": 0.007,
"grad_norm": 1.0871800184249878,
"learning_rate": 1.3600000000000002e-05,
"loss": 10.6435,
"step": 35
},
{
"epoch": 0.008,
"grad_norm": 0.9939376711845398,
"learning_rate": 1.56e-05,
"loss": 10.2936,
"step": 40
},
{
"epoch": 0.009,
"grad_norm": 1.0439313650131226,
"learning_rate": 1.76e-05,
"loss": 9.9938,
"step": 45
},
{
"epoch": 0.01,
"grad_norm": 1.1758387088775635,
"learning_rate": 1.9600000000000002e-05,
"loss": 10.0906,
"step": 50
},
{
"epoch": 0.011,
"grad_norm": 1.1925978660583496,
"learning_rate": 2.16e-05,
"loss": 9.6833,
"step": 55
},
{
"epoch": 0.012,
"grad_norm": 0.9983498454093933,
"learning_rate": 2.36e-05,
"loss": 9.7356,
"step": 60
},
{
"epoch": 0.013,
"grad_norm": 1.0689743757247925,
"learning_rate": 2.5600000000000002e-05,
"loss": 9.5145,