{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.4,
"eval_steps": 500,
"global_step": 2000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.001,
"grad_norm": 45.34572219848633,
"learning_rate": 1.6000000000000001e-06,
"loss": 319.578,
"step": 5
},
{
"epoch": 0.002,
"grad_norm": 35.23944091796875,
"learning_rate": 3.6e-06,
"loss": 321.7812,
"step": 10
},
{
"epoch": 0.003,
"grad_norm": 31.629674911499023,
"learning_rate": 5.600000000000001e-06,
"loss": 321.7244,
"step": 15
},
{
"epoch": 0.004,
"grad_norm": 37.21824264526367,
"learning_rate": 7.6e-06,
"loss": 327.2896,
"step": 20
},
{
"epoch": 0.005,
"grad_norm": 41.95133972167969,
"learning_rate": 9.600000000000001e-06,
"loss": 327.3718,
"step": 25
},
{
"epoch": 0.006,
"grad_norm": 41.561954498291016,
"learning_rate": 1.16e-05,
"loss": 315.5146,
"step": 30
},
{
"epoch": 0.007,
"grad_norm": 38.29129409790039,
"learning_rate": 1.3600000000000002e-05,
"loss": 318.5627,
"step": 35
},
{
"epoch": 0.008,
"grad_norm": 44.10498046875,
"learning_rate": 1.56e-05,
"loss": 312.3329,
"step": 40
},
{
"epoch": 0.009,
"grad_norm": 44.040958404541016,
"learning_rate": 1.76e-05,
"loss": 316.1487,
"step": 45
},
{
"epoch": 0.01,
"grad_norm": 48.966148376464844,
"learning_rate": 1.9600000000000002e-05,
"loss": 328.8573,
"step": 50
},
{
"epoch": 0.011,
"grad_norm": 48.719276428222656,
"learning_rate": 2.16e-05,
"loss": 314.682,
"step": 55
},
{
"epoch": 0.012,
"grad_norm": 56.17375946044922,
"learning_rate": 2.36e-05,
"loss": 315.3329,
"step": 60
},
{
"epoch": 0.013,
"grad_norm": 48.65364456176758,
"learning_rate": 2.5600000000000002e-05,
"loss": 320.5187,
"step": 65
},
{
"epoch": 0.014,
"grad_norm": 54.523563385009766,
"learning_rate": 2.7600000000000003e-05,
"loss": 309.5268,
"step": 70
},
{
"epoch": 0.015,
"grad_norm": 55.36623764038086,
"learning_rate": 2.96e-05,
"loss": 303.3225,
"step": 75
},
{
"epoch": 0.016,
"grad_norm": 49.912227630615234,
"learning_rate": 3.16e-05,
"loss": 307.5293,
"step": 80
},
{
"epoch": 0.017,
"grad_norm": 44.767608642578125,
"learning_rate": 3.3600000000000004e-05,
"loss": 321.9792,
"step": 85
},
{
"epoch": 0.018,
"grad_norm": 51.926937103271484,
"learning_rate": 3.56e-05,
"loss": 316.3215,
"step": 90
},
{
"epoch": 0.019,
"grad_norm": 44.54217529296875,
"learning_rate": 3.76e-05,
"loss": 317.4295,
"step": 95
},
{
"epoch": 0.02,
"grad_norm": 55.681034088134766,
"learning_rate": 3.960000000000001e-05,
"loss": 310.2048,
"step": 100
},
{
"epoch": 0.021,
"grad_norm": 49.07088088989258,
"learning_rate": 4.16e-05,
"loss": 314.7998,
"step": 105
},
{
"epoch": 0.022,
"grad_norm": 47.265907287597656,
"learning_rate": 4.36e-05,
"loss": 309.1314,
"step": 110
},
{
"epoch": 0.023,
"grad_norm": 54.9495849609375,
"learning_rate": 4.5600000000000004e-05,
"loss": 311.1284,
"step": 115
},
{
"epoch": 0.024,
"grad_norm": 50.552181243896484,
"learning_rate": 4.76e-05,
"loss": 313.6828,
"step": 120
},
{
"epoch": 0.025,
"grad_norm": 49.1966552734375,
"learning_rate": 4.96e-05,
"loss": 307.6977,
"step": 125
},
{
"epoch": 0.026,
"grad_norm": 51.342525482177734,
"learning_rate": 5.16e-05,
"loss": 310.0091,
"step": 130
},
{
"epoch": 0.027,
"grad_norm": 53.15058517456055,
"learning_rate": 5.360000000000001e-05,
"loss": 309.2304,
"step": 135
},
{
"epoch": 0.028,
"grad_norm": 70.3136978149414,
"learning_rate": 5.560000000000001e-05,
"loss": 305.1431,
"step": 140
},
{
"epoch": 0.029,
"grad_norm": 55.63601303100586,
"learning_rate": 5.76e-05,
"loss": 302.008,
"step": 145
},
{
"epoch": 0.03,
"grad_norm": 51.00766372680664,
"learning_rate": 5.96e-05,
"loss": 310.5994,
"step": 150
},
{
"epoch": 0.031,
"grad_norm": 56.53638458251953,
"learning_rate": 6.16e-05,
"loss": 292.5251,
"step": 155
},
{
"epoch": 0.032,
"grad_norm": 56.440975189208984,
"learning_rate": 6.36e-05,
"loss": 305.7293,
"step": 160
},
{
"epoch": 0.033,
"grad_norm": 59.819984436035156,
"learning_rate": 6.560000000000001e-05,
"loss": 312.4643,
"step": 165
},
{
"epoch": 0.034,
"grad_norm": 75.7228775024414,
"learning_rate": 6.76e-05,
"loss": 245.8394,
"step": 170
},
{
"epoch": 0.035,
"grad_norm": 53.55135726928711,
"learning_rate": 6.96e-05,
"loss": 243.8362,
"step": 175
},
{
"epoch": 0.036,
"grad_norm": 62.67115783691406,
"learning_rate": 7.16e-05,
"loss": 287.5416,
"step": 180
},
{
"epoch": 0.037,
"grad_norm": 52.979793548583984,
"learning_rate": 7.36e-05,
"loss": 293.3803,
"step": 185
},
{
"epoch": 0.038,
"grad_norm": 52.290279388427734,
"learning_rate": 7.560000000000001e-05,
"loss": 306.6807,
"step": 190
},
{
"epoch": 0.039,
"grad_norm": 67.30998992919922,
"learning_rate": 7.76e-05,
"loss": 298.3368,
"step": 195
},
{
"epoch": 0.04,
"grad_norm": 55.25843048095703,
"learning_rate": 7.960000000000001e-05,
"loss": 278.7369,
"step": 200
},
{
"epoch": 0.041,
"grad_norm": 65.67536163330078,
"learning_rate": 8.16e-05,
"loss": 312.0075,
"step": 205
},
{
"epoch": 0.042,
"grad_norm": 63.201416015625,
"learning_rate": 8.36e-05,
"loss": 308.4547,
"step": 210
},
{
"epoch": 0.043,
"grad_norm": 57.8333854675293,
"learning_rate": 8.560000000000001e-05,
"loss": 294.3108,
"step": 215
},
{
"epoch": 0.044,
"grad_norm": 58.91765594482422,
"learning_rate": 8.76e-05,
"loss": 299.3354,
"step": 220
},
{
"epoch": 0.045,
"grad_norm": 52.42339324951172,
"learning_rate": 8.960000000000001e-05,
"loss": 300.8906,
"step": 225
},
{
"epoch": 0.046,
"grad_norm": 54.68716812133789,
"learning_rate": 9.16e-05,
"loss": 310.6755,
"step": 230
},
{
"epoch": 0.047,
"grad_norm": 212.18890380859375,
"learning_rate": 9.360000000000001e-05,
"loss": 311.8085,
"step": 235
},
{
"epoch": 0.048,
"grad_norm": 68.8354263305664,
"learning_rate": 9.56e-05,
"loss": 300.4505,
"step": 240
},
{
"epoch": 0.049,
"grad_norm": 60.16633605957031,
"learning_rate": 9.76e-05,
"loss": 305.0702,
"step": 245
},
{
"epoch": 0.05,
"grad_norm": 68.25749206542969,
"learning_rate": 9.960000000000001e-05,
"loss": 263.8476,
"step": 250
},
{
"epoch": 0.051,
"grad_norm": 78.63923645019531,
"learning_rate": 0.0001016,
"loss": 292.9125,
"step": 255
},
{
"epoch": 0.052,
"grad_norm": 52.39205551147461,
"learning_rate": 0.00010360000000000001,
"loss": 298.1621,
"step": 260
},
{
"epoch": 0.053,
"grad_norm": 71.4918212890625,
"learning_rate": 0.0001056,
"loss": 304.5437,
"step": 265
},
{
"epoch": 0.054,
"grad_norm": 68.6222152709961,
"learning_rate": 0.00010760000000000001,
"loss": 246.9947,
"step": 270
},
{
"epoch": 0.055,
"grad_norm": 84.32728576660156,
"learning_rate": 0.00010960000000000001,
"loss": 306.641,
"step": 275
},
{
"epoch": 0.056,
"grad_norm": 55.64327621459961,
"learning_rate": 0.00011160000000000002,
"loss": 312.2386,
"step": 280
},
{
"epoch": 0.057,
"grad_norm": 61.93655776977539,
"learning_rate": 0.0001136,
"loss": 315.9132,
"step": 285
},
{
"epoch": 0.058,
"grad_norm": 64.90775299072266,
"learning_rate": 0.00011559999999999999,
"loss": 312.8616,
"step": 290
},
{
"epoch": 0.059,
"grad_norm": 60.436927795410156,
"learning_rate": 0.0001176,
"loss": 270.7869,
"step": 295
},
{
"epoch": 0.06,
"grad_norm": 61.79182052612305,
"learning_rate": 0.00011960000000000001,
"loss": 283.6043,
"step": 300
},
{
"epoch": 0.061,
"grad_norm": 67.95398712158203,
"learning_rate": 0.0001216,
"loss": 264.2303,
"step": 305
},
{
"epoch": 0.062,
"grad_norm": 67.74212646484375,
"learning_rate": 0.0001236,
"loss": 310.1396,
"step": 310
},
{
"epoch": 0.063,
"grad_norm": 69.19473266601562,
"learning_rate": 0.00012560000000000002,
"loss": 266.4937,
"step": 315
},
{
"epoch": 0.064,
"grad_norm": 74.57992553710938,
"learning_rate": 0.0001276,
"loss": 246.7177,
"step": 320
},
{
"epoch": 0.065,
"grad_norm": 60.20479965209961,
"learning_rate": 0.0001296,
"loss": 270.1338,
"step": 325
},
{
"epoch": 0.066,
"grad_norm": 60.080810546875,
"learning_rate": 0.0001316,
"loss": 303.0598,
"step": 330
},
{
"epoch": 0.067,
"grad_norm": 76.45138549804688,
"learning_rate": 0.00013360000000000002,
"loss": 270.1677,
"step": 335
},
{
"epoch": 0.068,
"grad_norm": 63.76318359375,
"learning_rate": 0.00013560000000000002,
"loss": 302.7615,
"step": 340
},
{
"epoch": 0.069,
"grad_norm": 62.31223678588867,
"learning_rate": 0.00013759999999999998,
"loss": 304.4131,
"step": 345
},
{
"epoch": 0.07,
"grad_norm": 107.39306640625,
"learning_rate": 0.0001396,
"loss": 289.8084,
"step": 350
},
{
"epoch": 0.071,
"grad_norm": 93.32718658447266,
"learning_rate": 0.0001416,
"loss": 300.6559,
"step": 355
},
{
"epoch": 0.072,
"grad_norm": 62.93545150756836,
"learning_rate": 0.0001436,
"loss": 283.2586,
"step": 360
},
{
"epoch": 0.073,
"grad_norm": 83.80622863769531,
"learning_rate": 0.00014560000000000002,
"loss": 262.5127,
"step": 365
},
{
"epoch": 0.074,
"grad_norm": 73.85086822509766,
"learning_rate": 0.0001476,
"loss": 304.2611,
"step": 370
},
{
"epoch": 0.075,
"grad_norm": 67.023193359375,
"learning_rate": 0.0001496,
"loss": 290.3278,
"step": 375
},
{
"epoch": 0.076,
"grad_norm": 99.57097625732422,
"learning_rate": 0.0001516,
"loss": 296.524,
"step": 380
},
{
"epoch": 0.077,
"grad_norm": 77.39230346679688,
"learning_rate": 0.00015360000000000002,
"loss": 263.7685,
"step": 385
},
{
"epoch": 0.078,
"grad_norm": 62.08967971801758,
"learning_rate": 0.00015560000000000001,
"loss": 289.5857,
"step": 390
},
{
"epoch": 0.079,
"grad_norm": 57.07795333862305,
"learning_rate": 0.0001576,
"loss": 296.4371,
"step": 395
},
{
"epoch": 0.08,
"grad_norm": 67.80342102050781,
"learning_rate": 0.0001596,
"loss": 292.5985,
"step": 400
},
{
"epoch": 0.081,
"grad_norm": 102.50914764404297,
"learning_rate": 0.00016160000000000002,
"loss": 245.5858,
"step": 405
},
{
"epoch": 0.082,
"grad_norm": 73.23768615722656,
"learning_rate": 0.0001636,
"loss": 269.5067,
"step": 410
},
{
"epoch": 0.083,
"grad_norm": 55.31161117553711,
"learning_rate": 0.0001656,
"loss": 284.2472,
"step": 415
},
{
"epoch": 0.084,
"grad_norm": 69.93988037109375,
"learning_rate": 0.0001676,
"loss": 268.031,
"step": 420
},
{
"epoch": 0.085,
"grad_norm": 71.37139129638672,
"learning_rate": 0.0001696,
"loss": 298.9601,
"step": 425
},
{
"epoch": 0.086,
"grad_norm": 71.84090423583984,
"learning_rate": 0.0001716,
"loss": 269.1097,
"step": 430
},
{
"epoch": 0.087,
"grad_norm": 52.79533386230469,
"learning_rate": 0.00017360000000000002,
"loss": 302.7409,
"step": 435
},
{
"epoch": 0.088,
"grad_norm": 59.18761444091797,
"learning_rate": 0.0001756,
"loss": 296.5794,
"step": 440
},
{
"epoch": 0.089,
"grad_norm": 69.19998168945312,
"learning_rate": 0.0001776,
"loss": 295.1216,
"step": 445
},
{
"epoch": 0.09,
"grad_norm": 75.6047134399414,
"learning_rate": 0.0001796,
"loss": 289.3482,
"step": 450
},
{
"epoch": 0.091,
"grad_norm": 63.364139556884766,
"learning_rate": 0.00018160000000000002,
"loss": 292.5362,
"step": 455
},
{
"epoch": 0.092,
"grad_norm": 63.57888412475586,
"learning_rate": 0.00018360000000000002,
"loss": 300.7526,
"step": 460
},
{
"epoch": 0.093,
"grad_norm": 71.47926330566406,
"learning_rate": 0.0001856,
"loss": 310.7431,
"step": 465
},
{
"epoch": 0.094,
"grad_norm": 65.70227813720703,
"learning_rate": 0.0001876,
"loss": 297.2938,
"step": 470
},
{
"epoch": 0.095,
"grad_norm": 59.69890594482422,
"learning_rate": 0.0001896,
"loss": 270.1979,
"step": 475
},
{
"epoch": 0.096,
"grad_norm": 79.22998046875,
"learning_rate": 0.0001916,
"loss": 277.9732,
"step": 480
},
{
"epoch": 0.097,
"grad_norm": 66.13664245605469,
"learning_rate": 0.00019360000000000002,
"loss": 302.6306,
"step": 485
},
{
"epoch": 0.098,
"grad_norm": 57.03192138671875,
"learning_rate": 0.0001956,
"loss": 286.4015,
"step": 490
},
{
"epoch": 0.099,
"grad_norm": 55.27619171142578,
"learning_rate": 0.0001976,
"loss": 298.0568,
"step": 495
},
{
"epoch": 0.1,
"grad_norm": 55.16793441772461,
"learning_rate": 0.0001996,
"loss": 296.1483,
"step": 500
},
{
"epoch": 0.101,
"grad_norm": 58.84857940673828,
"learning_rate": 0.00019999961008995606,
"loss": 309.4064,
"step": 505
},
{
"epoch": 0.102,
"grad_norm": 62.985347747802734,
"learning_rate": 0.0001999980260856137,
"loss": 294.9958,
"step": 510
},
{
"epoch": 0.103,
"grad_norm": 59.40795135498047,
"learning_rate": 0.000199995223636881,
"loss": 281.1267,
"step": 515
},
{
"epoch": 0.104,
"grad_norm": 54.28294372558594,
"learning_rate": 0.00019999120277790477,
"loss": 305.6373,
"step": 520
},
{
"epoch": 0.105,
"grad_norm": 56.23757553100586,
"learning_rate": 0.00019998596355767805,
"loss": 293.8239,
"step": 525
},
{
"epoch": 0.106,
"grad_norm": 52.75642776489258,
"learning_rate": 0.000199979506040039,
"loss": 299.8164,
"step": 530
},
{
"epoch": 0.107,
"grad_norm": 55.38374710083008,
"learning_rate": 0.00019997183030367048,
"loss": 291.3248,
"step": 535
},
{
"epoch": 0.108,
"grad_norm": 57.35643768310547,
"learning_rate": 0.00019996293644209887,
"loss": 296.516,
"step": 540
},
{
"epoch": 0.109,
"grad_norm": 59.5279426574707,
"learning_rate": 0.0001999528245636931,
"loss": 297.022,
"step": 545
},
{
"epoch": 0.11,
"grad_norm": 94.40937805175781,
"learning_rate": 0.00019994149479166324,
"loss": 269.0631,
"step": 550
},
{
"epoch": 0.111,
"grad_norm": 56.67276382446289,
"learning_rate": 0.00019992894726405893,
"loss": 229.5338,
"step": 555
},
{
"epoch": 0.112,
"grad_norm": 65.58580017089844,
"learning_rate": 0.00019991518213376787,
"loss": 299.0329,
"step": 560
},
{
"epoch": 0.113,
"grad_norm": 122.42597198486328,
"learning_rate": 0.00019990019956851382,
"loss": 284.2142,
"step": 565
},
{
"epoch": 0.114,
"grad_norm": 48.66897201538086,
"learning_rate": 0.0001998839997508546,
"loss": 290.9123,
"step": 570
},
{
"epoch": 0.115,
"grad_norm": 52.7710075378418,
"learning_rate": 0.00019986658287817987,
"loss": 282.9158,
"step": 575
},
{
"epoch": 0.116,
"grad_norm": 59.78569412231445,
"learning_rate": 0.00019984794916270876,
"loss": 264.0346,
"step": 580
},
{
"epoch": 0.117,
"grad_norm": 51.239498138427734,
"learning_rate": 0.00019982809883148722,
"loss": 278.2119,
"step": 585
},
{
"epoch": 0.118,
"grad_norm": 45.771385192871094,
"learning_rate": 0.00019980703212638522,
"loss": 256.8016,
"step": 590
},
{
"epoch": 0.119,
"grad_norm": 68.36455535888672,
"learning_rate": 0.00019978474930409395,
"loss": 283.7405,
"step": 595
},
{
"epoch": 0.12,
"grad_norm": 66.43222045898438,
"learning_rate": 0.00019976125063612252,
"loss": 280.3201,
"step": 600
},
{
"epoch": 0.121,
"grad_norm": 47.34906768798828,
"learning_rate": 0.00019973653640879485,
"loss": 286.8456,
"step": 605
},
{
"epoch": 0.122,
"grad_norm": 62.890262603759766,
"learning_rate": 0.00019971060692324598,
"loss": 278.1488,
"step": 610
},
{
"epoch": 0.123,
"grad_norm": 67.57910919189453,
"learning_rate": 0.00019968346249541846,
"loss": 280.0852,
"step": 615
},
{
"epoch": 0.124,
"grad_norm": 67.44754028320312,
"learning_rate": 0.00019965510345605866,
"loss": 273.1637,
"step": 620
},
{
"epoch": 0.125,
"grad_norm": 48.47514724731445,
"learning_rate": 0.0001996255301507125,
"loss": 286.6736,
"step": 625
},
{
"epoch": 0.126,
"grad_norm": 58.169986724853516,
"learning_rate": 0.00019959474293972129,
"loss": 288.5007,
"step": 630
},
{
"epoch": 0.127,
"grad_norm": 55.11975860595703,
"learning_rate": 0.00019956274219821757,
"loss": 269.6669,
"step": 635
},
{
"epoch": 0.128,
"grad_norm": 47.872779846191406,
"learning_rate": 0.00019952952831612026,
"loss": 290.3256,
"step": 640
},
{
"epoch": 0.129,
"grad_norm": 53.464073181152344,
"learning_rate": 0.00019949510169813003,
"loss": 302.1444,
"step": 645
},
{
"epoch": 0.13,
"grad_norm": 44.54434585571289,
"learning_rate": 0.00019945946276372434,
"loss": 274.0604,
"step": 650
},
{
"epoch": 0.131,
"grad_norm": 58.98426055908203,
"learning_rate": 0.00019942261194715236,
"loss": 264.3285,
"step": 655
},
{
"epoch": 0.132,
"grad_norm": 51.247642517089844,
"learning_rate": 0.00019938454969742968,
"loss": 293.6523,
"step": 660
},
{
"epoch": 0.133,
"grad_norm": 53.057464599609375,
"learning_rate": 0.00019934527647833276,
"loss": 286.6662,
"step": 665
},
{
"epoch": 0.134,
"grad_norm": 53.00550842285156,
"learning_rate": 0.00019930479276839344,
"loss": 295.9922,
"step": 670
},
{
"epoch": 0.135,
"grad_norm": 51.69222640991211,
"learning_rate": 0.0001992630990608929,
"loss": 280.5888,
"step": 675
},
{
"epoch": 0.136,
"grad_norm": 47.168575286865234,
"learning_rate": 0.00019922019586385585,
"loss": 282.3569,
"step": 680
},
{
"epoch": 0.137,
"grad_norm": 57.80231857299805,
"learning_rate": 0.00019917608370004417,
"loss": 251.5682,
"step": 685
},
{
"epoch": 0.138,
"grad_norm": 54.561805725097656,
"learning_rate": 0.00019913076310695068,
"loss": 250.5393,
"step": 690
},
{
"epoch": 0.139,
"grad_norm": 46.58423614501953,
"learning_rate": 0.00019908423463679248,
"loss": 279.3385,
"step": 695
},
{
"epoch": 0.14,
"grad_norm": 73.98703002929688,
"learning_rate": 0.0001990364988565043,
"loss": 302.6732,
"step": 700
},
{
"epoch": 0.141,
"grad_norm": 46.092376708984375,
"learning_rate": 0.00019898755634773158,
"loss": 287.1832,
"step": 705
},
{
"epoch": 0.142,
"grad_norm": 73.5405044555664,
"learning_rate": 0.00019893740770682335,
"loss": 286.9068,
"step": 710
},
{
"epoch": 0.143,
"grad_norm": 43.50495529174805,
"learning_rate": 0.0001988860535448249,
"loss": 266.0364,
"step": 715
},
{
"epoch": 0.144,
"grad_norm": 54.091922760009766,
"learning_rate": 0.00019883349448747062,
"loss": 286.2805,
"step": 720
},
{
"epoch": 0.145,
"grad_norm": 69.53164672851562,
"learning_rate": 0.0001987797311751759,
"loss": 286.9355,
"step": 725
},
{
"epoch": 0.146,
"grad_norm": 50.866058349609375,
"learning_rate": 0.00019872476426302982,
"loss": 294.4804,
"step": 730
},
{
"epoch": 0.147,
"grad_norm": 46.98020553588867,
"learning_rate": 0.0001986685944207868,
"loss": 286.8734,
"step": 735
},
{
"epoch": 0.148,
"grad_norm": 47.238983154296875,
"learning_rate": 0.0001986112223328587,
"loss": 291.3399,
"step": 740
},
{
"epoch": 0.149,
"grad_norm": 61.37972640991211,
"learning_rate": 0.00019855264869830629,
"loss": 283.7323,
"step": 745
},
{
"epoch": 0.15,
"grad_norm": 55.343414306640625,
"learning_rate": 0.00019849287423083078,
"loss": 283.7294,
"step": 750
},
{
"epoch": 0.151,
"grad_norm": 73.07318115234375,
"learning_rate": 0.00019843189965876526,
"loss": 278.8252,
"step": 755
},
{
"epoch": 0.152,
"grad_norm": 59.20526123046875,
"learning_rate": 0.00019836972572506557,
"loss": 292.6097,
"step": 760
},
{
"epoch": 0.153,
"grad_norm": 61.79401397705078,
"learning_rate": 0.00019830635318730154,
"loss": 274.8011,
"step": 765
},
{
"epoch": 0.154,
"grad_norm": 51.76266860961914,
"learning_rate": 0.00019824178281764753,
"loss": 296.1988,
"step": 770
},
{
"epoch": 0.155,
"grad_norm": 48.1161994934082,
"learning_rate": 0.00019817601540287306,
"loss": 275.1525,
"step": 775
},
{
"epoch": 0.156,
"grad_norm": 56.47291946411133,
"learning_rate": 0.0001981090517443334,
"loss": 282.4003,
"step": 780
},
{
"epoch": 0.157,
"grad_norm": 45.93486785888672,
"learning_rate": 0.0001980408926579596,
"loss": 271.6085,
"step": 785
},
{
"epoch": 0.158,
"grad_norm": 48.26741409301758,
"learning_rate": 0.00019797153897424852,
"loss": 286.9994,
"step": 790
},
{
"epoch": 0.159,
"grad_norm": 47.9412956237793,
"learning_rate": 0.000197900991538253,
"loss": 273.9757,
"step": 795
},
{
"epoch": 0.16,
"grad_norm": 60.08948516845703,
"learning_rate": 0.00019782925120957124,
"loss": 286.7509,
"step": 800
},
{
"epoch": 0.161,
"grad_norm": 48.55828857421875,
"learning_rate": 0.00019775631886233654,
"loss": 278.9955,
"step": 805
},
{
"epoch": 0.162,
"grad_norm": 57.64690017700195,
"learning_rate": 0.0001976821953852065,
"loss": 276.8143,
"step": 810
},
{
"epoch": 0.163,
"grad_norm": 58.00476837158203,
"learning_rate": 0.00019760688168135232,
"loss": 277.4751,
"step": 815
},
{
"epoch": 0.164,
"grad_norm": 57.093963623046875,
"learning_rate": 0.00019753037866844771,
"loss": 262.7667,
"step": 820
},
{
"epoch": 0.165,
"grad_norm": 56.95517349243164,
"learning_rate": 0.00019745268727865774,
"loss": 269.5826,
"step": 825
},
{
"epoch": 0.166,
"grad_norm": 50.23096466064453,
"learning_rate": 0.00019737380845862745,
"loss": 285.1032,
"step": 830
},
{
"epoch": 0.167,
"grad_norm": 50.731136322021484,
"learning_rate": 0.0001972937431694704,
"loss": 268.6636,
"step": 835
},
{
"epoch": 0.168,
"grad_norm": 58.02402877807617,
"learning_rate": 0.00019721249238675688,
"loss": 275.4251,
"step": 840
},
{
"epoch": 0.169,
"grad_norm": 69.00015258789062,
"learning_rate": 0.000197130057100502,
"loss": 285.3165,
"step": 845
},
{
"epoch": 0.17,
"grad_norm": 46.96028518676758,
"learning_rate": 0.00019704643831515374,
"loss": 285.7622,
"step": 850
},
{
"epoch": 0.171,
"grad_norm": 58.708492279052734,
"learning_rate": 0.0001969616370495806,
"loss": 278.9549,
"step": 855
},
{
"epoch": 0.172,
"grad_norm": 43.957550048828125,
"learning_rate": 0.00019687565433705926,
"loss": 285.4878,
"step": 860
},
{
"epoch": 0.173,
"grad_norm": 47.97303771972656,
"learning_rate": 0.00019678849122526187,
"loss": 264.2698,
"step": 865
},
{
"epoch": 0.174,
"grad_norm": 49.05190658569336,
"learning_rate": 0.00019670014877624353,
"loss": 263.6371,
"step": 870
},
{
"epoch": 0.175,
"grad_norm": 47.07678985595703,
"learning_rate": 0.00019661062806642903,
"loss": 271.3718,
"step": 875
},
{
"epoch": 0.176,
"grad_norm": 59.09493637084961,
"learning_rate": 0.0001965199301866,
"loss": 262.7315,
"step": 880
},
{
"epoch": 0.177,
"grad_norm": 44.131996154785156,
"learning_rate": 0.00019642805624188147,
"loss": 265.7331,
"step": 885
},
{
"epoch": 0.178,
"grad_norm": 61.45351791381836,
"learning_rate": 0.0001963350073517285,
"loss": 255.2025,
"step": 890
},
{
"epoch": 0.179,
"grad_norm": 57.042808532714844,
"learning_rate": 0.0001962407846499124,
"loss": 268.0531,
"step": 895
},
{
"epoch": 0.18,
"grad_norm": 51.4085693359375,
"learning_rate": 0.0001961453892845071,
"loss": 261.5828,
"step": 900
},
{
"epoch": 0.181,
"grad_norm": 51.26783752441406,
"learning_rate": 0.00019604882241787498,
"loss": 262.4921,
"step": 905
},
{
"epoch": 0.182,
"grad_norm": 64.2865982055664,
"learning_rate": 0.0001959510852266529,
"loss": 279.2708,
"step": 910
},
{
"epoch": 0.183,
"grad_norm": 50.644039154052734,
"learning_rate": 0.0001958521789017376,
"loss": 276.3466,
"step": 915
},
{
"epoch": 0.184,
"grad_norm": 51.023094177246094,
"learning_rate": 0.00019575210464827149,
"loss": 288.5591,
"step": 920
},
{
"epoch": 0.185,
"grad_norm": 48.759307861328125,
"learning_rate": 0.0001956508636856278,
"loss": 276.0183,
"step": 925
},
{
"epoch": 0.186,
"grad_norm": 52.664642333984375,
"learning_rate": 0.00019554845724739566,
"loss": 270.6455,
"step": 930
},
{
"epoch": 0.187,
"grad_norm": 48.79008865356445,
"learning_rate": 0.00019544488658136523,
"loss": 284.0267,
"step": 935
},
{
"epoch": 0.188,
"grad_norm": 48.21590042114258,
"learning_rate": 0.00019534015294951233,
"loss": 282.7852,
"step": 940
},
{
"epoch": 0.189,
"grad_norm": 55.6912727355957,
"learning_rate": 0.00019523425762798329,
"loss": 284.7149,
"step": 945
},
{
"epoch": 0.19,
"grad_norm": 76.09707641601562,
"learning_rate": 0.00019512720190707913,
"loss": 266.0458,
"step": 950
},
{
"epoch": 0.191,
"grad_norm": 70.18879699707031,
"learning_rate": 0.00019501898709124008,
"loss": 281.1459,
"step": 955
},
{
"epoch": 0.192,
"grad_norm": 47.123775482177734,
"learning_rate": 0.00019490961449902946,
"loss": 282.8954,
"step": 960
},
{
"epoch": 0.193,
"grad_norm": 46.44071960449219,
"learning_rate": 0.00019479908546311781,
"loss": 283.2815,
"step": 965
},
{
"epoch": 0.194,
"grad_norm": 48.01999282836914,
"learning_rate": 0.0001946874013302666,
"loss": 279.4495,
"step": 970
},
{
"epoch": 0.195,
"grad_norm": 54.30856704711914,
"learning_rate": 0.0001945745634613117,
"loss": 281.8633,
"step": 975
},
{
"epoch": 0.196,
"grad_norm": 60.08113098144531,
"learning_rate": 0.0001944605732311469,
"loss": 284.9872,
"step": 980
},
{
"epoch": 0.197,
"grad_norm": 61.01625442504883,
"learning_rate": 0.00019434543202870725,
"loss": 274.5333,
"step": 985
},
{
"epoch": 0.198,
"grad_norm": 47.403377532958984,
"learning_rate": 0.0001942291412569519,
"loss": 281.1945,
"step": 990
},
{
"epoch": 0.199,
"grad_norm": 42.819091796875,
"learning_rate": 0.00019411170233284727,
"loss": 288.0547,
"step": 995
},
{
"epoch": 0.2,
"grad_norm": 44.18984603881836,
"learning_rate": 0.00019399311668734956,
"loss": 285.208,
"step": 1000
},
{
"epoch": 0.201,
"grad_norm": 46.686588287353516,
"learning_rate": 0.00019387338576538744,
"loss": 289.4717,
"step": 1005
},
{
"epoch": 0.202,
"grad_norm": 54.98046112060547,
"learning_rate": 0.0001937525110258444,
"loss": 280.2115,
"step": 1010
},
{
"epoch": 0.203,
"grad_norm": 45.183387756347656,
"learning_rate": 0.00019363049394154094,
"loss": 285.319,
"step": 1015
},
{
"epoch": 0.204,
"grad_norm": 49.63119888305664,
"learning_rate": 0.00019350733599921683,
"loss": 270.5074,
"step": 1020
},
{
"epoch": 0.205,
"grad_norm": 47.29715347290039,
"learning_rate": 0.00019338303869951269,
"loss": 275.1198,
"step": 1025
},
{
"epoch": 0.206,
"grad_norm": 60.79301834106445,
"learning_rate": 0.00019325760355695188,
"loss": 284.8178,
"step": 1030
},
{
"epoch": 0.207,
"grad_norm": 52.7172966003418,
"learning_rate": 0.00019313103209992204,
"loss": 272.2249,
"step": 1035
},
{
"epoch": 0.208,
"grad_norm": 43.442115783691406,
"learning_rate": 0.0001930033258706564,
"loss": 280.1849,
"step": 1040
},
{
"epoch": 0.209,
"grad_norm": 69.27387237548828,
"learning_rate": 0.00019287448642521513,
"loss": 285.6339,
"step": 1045
},
{
"epoch": 0.21,
"grad_norm": 82.95686340332031,
"learning_rate": 0.00019274451533346615,
"loss": 281.9283,
"step": 1050
},
{
"epoch": 0.211,
"grad_norm": 54.01242446899414,
"learning_rate": 0.00019261341417906621,
"loss": 283.1166,
"step": 1055
},
{
"epoch": 0.212,
"grad_norm": 50.461769104003906,
"learning_rate": 0.0001924811845594415,
"loss": 268.7808,
"step": 1060
},
{
"epoch": 0.213,
"grad_norm": 50.19092559814453,
"learning_rate": 0.00019234782808576824,
"loss": 282.247,
"step": 1065
},
{
"epoch": 0.214,
"grad_norm": 48.89931106567383,
"learning_rate": 0.00019221334638295294,
"loss": 271.4232,
"step": 1070
},
{
"epoch": 0.215,
"grad_norm": 60.72257995605469,
"learning_rate": 0.00019207774108961272,
"loss": 278.4014,
"step": 1075
},
{
"epoch": 0.216,
"grad_norm": 54.485374450683594,
"learning_rate": 0.0001919410138580553,
"loss": 278.6501,
"step": 1080
},
{
"epoch": 0.217,
"grad_norm": 60.64812469482422,
"learning_rate": 0.0001918031663542588,
"loss": 274.0851,
"step": 1085
},
{
"epoch": 0.218,
"grad_norm": 48.138248443603516,
"learning_rate": 0.00019166420025785164,
"loss": 282.6086,
"step": 1090
},
{
"epoch": 0.219,
"grad_norm": 55.088932037353516,
"learning_rate": 0.00019152411726209176,
"loss": 281.5728,
"step": 1095
},
{
"epoch": 0.22,
"grad_norm": 56.48404312133789,
"learning_rate": 0.0001913829190738463,
"loss": 259.0733,
"step": 1100
},
{
"epoch": 0.221,
"grad_norm": 51.37434768676758,
"learning_rate": 0.00019124060741357063,
"loss": 285.3994,
"step": 1105
},
{
"epoch": 0.222,
"grad_norm": 54.788936614990234,
"learning_rate": 0.0001910971840152874,
"loss": 278.9071,
"step": 1110
},
{
"epoch": 0.223,
"grad_norm": 80.36026000976562,
"learning_rate": 0.00019095265062656544,
"loss": 273.4703,
"step": 1115
},
{
"epoch": 0.224,
"grad_norm": 46.11319351196289,
"learning_rate": 0.00019080700900849851,
"loss": 271.8554,
"step": 1120
},
{
"epoch": 0.225,
"grad_norm": 56.28084182739258,
"learning_rate": 0.00019066026093568378,
"loss": 277.7285,
"step": 1125
},
{
"epoch": 0.226,
"grad_norm": 45.574974060058594,
"learning_rate": 0.00019051240819620014,
"loss": 278.846,
"step": 1130
},
{
"epoch": 0.227,
"grad_norm": 46.18704605102539,
"learning_rate": 0.00019036345259158667,
"loss": 278.5995,
"step": 1135
},
{
"epoch": 0.228,
"grad_norm": 45.617332458496094,
"learning_rate": 0.00019021339593682028,
"loss": 277.3522,
"step": 1140
},
{
"epoch": 0.229,
"grad_norm": 55.12424087524414,
"learning_rate": 0.00019006224006029406,
"loss": 265.3224,
"step": 1145
},
{
"epoch": 0.23,
"grad_norm": 52.34011459350586,
"learning_rate": 0.00018990998680379456,
"loss": 277.6808,
"step": 1150
},
{
"epoch": 0.231,
"grad_norm": 61.056175231933594,
"learning_rate": 0.00018975663802247976,
"loss": 291.6425,
"step": 1155
},
{
"epoch": 0.232,
"grad_norm": 57.907012939453125,
"learning_rate": 0.0001896021955848561,
"loss": 275.2473,
"step": 1160
},
{
"epoch": 0.233,
"grad_norm": 67.78964233398438,
"learning_rate": 0.000189446661372756,
"loss": 276.914,
"step": 1165
},
{
"epoch": 0.234,
"grad_norm": 43.24968338012695,
"learning_rate": 0.0001892900372813147,
"loss": 285.2484,
"step": 1170
},
{
"epoch": 0.235,
"grad_norm": 40.49110794067383,
"learning_rate": 0.00018913232521894732,
"loss": 276.8971,
"step": 1175
},
{
"epoch": 0.236,
"grad_norm": 49.47333526611328,
"learning_rate": 0.00018897352710732564,
"loss": 276.965,
"step": 1180
},
{
"epoch": 0.237,
"grad_norm": 102.49535369873047,
"learning_rate": 0.00018881364488135448,
"loss": 285.3501,
"step": 1185
},
{
"epoch": 0.238,
"grad_norm": 59.885005950927734,
"learning_rate": 0.00018865268048914828,
"loss": 272.4432,
"step": 1190
},
{
"epoch": 0.239,
"grad_norm": 48.78818893432617,
"learning_rate": 0.00018849063589200743,
"loss": 280.503,
"step": 1195
},
{
"epoch": 0.24,
"grad_norm": 61.330631256103516,
"learning_rate": 0.00018832751306439418,
"loss": 271.4646,
"step": 1200
},
{
"epoch": 0.241,
"grad_norm": 51.42898178100586,
"learning_rate": 0.0001881633139939087,
"loss": 281.2951,
"step": 1205
},
{
"epoch": 0.242,
"grad_norm": 46.34280014038086,
"learning_rate": 0.00018799804068126485,
"loss": 273.7546,
"step": 1210
},
{
"epoch": 0.243,
"grad_norm": 49.210784912109375,
"learning_rate": 0.00018783169514026578,
"loss": 275.4605,
"step": 1215
},
{
"epoch": 0.244,
"grad_norm": 46.695472717285156,
"learning_rate": 0.00018766427939777945,
"loss": 277.2047,
"step": 1220
},
{
"epoch": 0.245,
"grad_norm": 47.742740631103516,
"learning_rate": 0.0001874957954937138,
"loss": 280.9094,
"step": 1225
},
{
"epoch": 0.246,
"grad_norm": 51.13950729370117,
"learning_rate": 0.00018732624548099204,
"loss": 278.3534,
"step": 1230
},
{
"epoch": 0.247,
"grad_norm": 79.51956939697266,
"learning_rate": 0.00018715563142552758,
"loss": 275.2643,
"step": 1235
},
{
"epoch": 0.248,
"grad_norm": 42.83713912963867,
"learning_rate": 0.0001869839554061988,
"loss": 274.9076,
"step": 1240
},
{
"epoch": 0.249,
"grad_norm": 45.978050231933594,
"learning_rate": 0.00018681121951482393,
"loss": 279.4208,
"step": 1245
},
{
"epoch": 0.25,
"grad_norm": 48.35042190551758,
"learning_rate": 0.00018663742585613518,
"loss": 279.4141,
"step": 1250
},
{
"epoch": 0.251,
"grad_norm": 42.03864669799805,
"learning_rate": 0.0001864625765477535,
"loss": 279.2781,
"step": 1255
},
{
"epoch": 0.252,
"grad_norm": 39.96771240234375,
"learning_rate": 0.0001862866737201625,
"loss": 275.7363,
"step": 1260
},
{
"epoch": 0.253,
"grad_norm": 49.38249588012695,
"learning_rate": 0.00018610971951668265,
"loss": 288.1274,
"step": 1265
},
{
"epoch": 0.254,
"grad_norm": 46.85017395019531,
"learning_rate": 0.00018593171609344503,
"loss": 270.1588,
"step": 1270
},
{
"epoch": 0.255,
"grad_norm": 52.7684211730957,
"learning_rate": 0.00018575266561936523,
"loss": 280.1056,
"step": 1275
},
{
"epoch": 0.256,
"grad_norm": 48.299522399902344,
"learning_rate": 0.00018557257027611675,
"loss": 278.6028,
"step": 1280
},
{
"epoch": 0.257,
"grad_norm": 48.681549072265625,
"learning_rate": 0.0001853914322581045,
"loss": 276.8517,
"step": 1285
},
{
"epoch": 0.258,
"grad_norm": 64.33309936523438,
"learning_rate": 0.0001852092537724381,
"loss": 262.0452,
"step": 1290
},
{
"epoch": 0.259,
"grad_norm": 61.493751525878906,
"learning_rate": 0.00018502603703890488,
"loss": 269.412,
"step": 1295
},
{
"epoch": 0.26,
"grad_norm": 47.19992446899414,
"learning_rate": 0.0001848417842899429,
"loss": 276.7448,
"step": 1300
},
{
"epoch": 0.261,
"grad_norm": 53.078758239746094,
"learning_rate": 0.0001846564977706138,
"loss": 271.0328,
"step": 1305
},
{
"epoch": 0.262,
"grad_norm": 48.62588882446289,
"learning_rate": 0.00018447017973857532,
"loss": 265.8279,
"step": 1310
},
{
"epoch": 0.263,
"grad_norm": 45.19000244140625,
"learning_rate": 0.0001842828324640539,
"loss": 282.4244,
"step": 1315
},
{
"epoch": 0.264,
"grad_norm": 51.99223709106445,
"learning_rate": 0.00018409445822981693,
"loss": 277.7068,
"step": 1320
},
{
"epoch": 0.265,
"grad_norm": 63.16470718383789,
"learning_rate": 0.000183905059331145,
"loss": 275.4358,
"step": 1325
},
{
"epoch": 0.266,
"grad_norm": 62.11888885498047,
"learning_rate": 0.000183714638075804,
"loss": 274.494,
"step": 1330
},
{
"epoch": 0.267,
"grad_norm": 57.818546295166016,
"learning_rate": 0.00018352319678401676,
"loss": 274.5423,
"step": 1335
},
{
"epoch": 0.268,
"grad_norm": 53.74748611450195,
"learning_rate": 0.000183330737788435,
"loss": 278.6121,
"step": 1340
},
{
"epoch": 0.269,
"grad_norm": 50.203853607177734,
"learning_rate": 0.00018313726343411086,
"loss": 271.9252,
"step": 1345
},
{
"epoch": 0.27,
"grad_norm": 65.44813537597656,
"learning_rate": 0.00018294277607846832,
"loss": 267.8632,
"step": 1350
},
{
"epoch": 0.271,
"grad_norm": 48.04423141479492,
"learning_rate": 0.00018274727809127438,
"loss": 267.5536,
"step": 1355
},
{
"epoch": 0.272,
"grad_norm": 59.265811920166016,
"learning_rate": 0.00018255077185461038,
"loss": 268.4268,
"step": 1360
},
{
"epoch": 0.273,
"grad_norm": 47.52214050292969,
"learning_rate": 0.00018235325976284275,
"loss": 265.7156,
"step": 1365
},
{
"epoch": 0.274,
"grad_norm": 49.38442611694336,
"learning_rate": 0.00018215474422259402,
"loss": 262.0943,
"step": 1370
},
{
"epoch": 0.275,
"grad_norm": 49.31957244873047,
"learning_rate": 0.0001819552276527134,
"loss": 264.2624,
"step": 1375
},
{
"epoch": 0.276,
"grad_norm": 46.64031219482422,
"learning_rate": 0.0001817547124842473,
"loss": 271.314,
"step": 1380
},
{
"epoch": 0.277,
"grad_norm": 59.608097076416016,
"learning_rate": 0.00018155320116040982,
"loss": 278.4709,
"step": 1385
},
{
"epoch": 0.278,
"grad_norm": 44.36711120605469,
"learning_rate": 0.0001813506961365528,
"loss": 267.9179,
"step": 1390
},
{
"epoch": 0.279,
"grad_norm": 44.03354263305664,
"learning_rate": 0.00018114719988013612,
"loss": 276.3737,
"step": 1395
},
{
"epoch": 0.28,
"grad_norm": 46.73600387573242,
"learning_rate": 0.00018094271487069735,
"loss": 281.1463,
"step": 1400
},
{
"epoch": 0.281,
"grad_norm": 47.62178421020508,
"learning_rate": 0.00018073724359982186,
"loss": 284.8451,
"step": 1405
},
{
"epoch": 0.282,
"grad_norm": 52.94386291503906,
"learning_rate": 0.0001805307885711122,
"loss": 278.9838,
"step": 1410
},
{
"epoch": 0.283,
"grad_norm": 50.47867965698242,
"learning_rate": 0.0001803233523001578,
"loss": 260.8532,
"step": 1415
},
{
"epoch": 0.284,
"grad_norm": 43.788631439208984,
"learning_rate": 0.00018011493731450413,
"loss": 270.927,
"step": 1420
},
{
"epoch": 0.285,
"grad_norm": 48.58649444580078,
"learning_rate": 0.00017990554615362198,
"loss": 290.5723,
"step": 1425
},
{
"epoch": 0.286,
"grad_norm": 41.595149993896484,
"learning_rate": 0.00017969518136887663,
"loss": 275.7107,
"step": 1430
},
{
"epoch": 0.287,
"grad_norm": 66.20713806152344,
"learning_rate": 0.00017948384552349657,
"loss": 271.6039,
"step": 1435
},
{
"epoch": 0.288,
"grad_norm": 50.655662536621094,
"learning_rate": 0.00017927154119254236,
"loss": 256.8604,
"step": 1440
},
{
"epoch": 0.289,
"grad_norm": 46.8124885559082,
"learning_rate": 0.0001790582709628753,
"loss": 262.3076,
"step": 1445
},
{
"epoch": 0.29,
"grad_norm": 50.67826461791992,
"learning_rate": 0.00017884403743312582,
"loss": 271.3517,
"step": 1450
},
{
"epoch": 0.291,
"grad_norm": 49.34907913208008,
"learning_rate": 0.00017862884321366188,
"loss": 263.9629,
"step": 1455
},
{
"epoch": 0.292,
"grad_norm": 142.8138885498047,
"learning_rate": 0.00017841269092655715,
"loss": 261.0857,
"step": 1460
},
{
"epoch": 0.293,
"grad_norm": 49.53968048095703,
"learning_rate": 0.000178195583205559,
"loss": 254.2599,
"step": 1465
},
{
"epoch": 0.294,
"grad_norm": 46.59897232055664,
"learning_rate": 0.00017797752269605653,
"loss": 256.6566,
"step": 1470
},
{
"epoch": 0.295,
"grad_norm": 57.85300064086914,
"learning_rate": 0.0001777585120550482,
"loss": 271.6792,
"step": 1475
},
{
"epoch": 0.296,
"grad_norm": 46.9395866394043,
"learning_rate": 0.0001775385539511096,
"loss": 248.5841,
"step": 1480
},
{
"epoch": 0.297,
"grad_norm": 52.38425064086914,
"learning_rate": 0.00017731765106436073,
"loss": 256.4067,
"step": 1485
},
{
"epoch": 0.298,
"grad_norm": 56.25849151611328,
"learning_rate": 0.00017709580608643363,
"loss": 258.4175,
"step": 1490
},
{
"epoch": 0.299,
"grad_norm": 44.94255447387695,
"learning_rate": 0.00017687302172043933,
"loss": 260.0202,
"step": 1495
},
{
"epoch": 0.3,
"grad_norm": 48.517120361328125,
"learning_rate": 0.00017664930068093498,
"loss": 265.9558,
"step": 1500
},
{
"epoch": 0.301,
"grad_norm": 48.20281982421875,
"learning_rate": 0.0001764246456938909,
"loss": 278.9301,
"step": 1505
},
{
"epoch": 0.302,
"grad_norm": 58.53182601928711,
"learning_rate": 0.0001761990594966572,
"loss": 283.6035,
"step": 1510
},
{
"epoch": 0.303,
"grad_norm": 53.574710845947266,
"learning_rate": 0.00017597254483793048,
"loss": 273.2,
"step": 1515
},
{
"epoch": 0.304,
"grad_norm": 45.98015213012695,
"learning_rate": 0.00017574510447772039,
"loss": 276.9031,
"step": 1520
},
{
"epoch": 0.305,
"grad_norm": 49.6352424621582,
"learning_rate": 0.00017551674118731591,
"loss": 273.3175,
"step": 1525
},
{
"epoch": 0.306,
"grad_norm": 45.53011703491211,
"learning_rate": 0.00017528745774925172,
"loss": 266.4909,
"step": 1530
},
{
"epoch": 0.307,
"grad_norm": 42.180625915527344,
"learning_rate": 0.00017505725695727412,
"loss": 270.1266,
"step": 1535
},
{
"epoch": 0.308,
"grad_norm": 42.45751953125,
"learning_rate": 0.00017482614161630714,
"loss": 282.3553,
"step": 1540
},
{
"epoch": 0.309,
"grad_norm": 47.69794464111328,
"learning_rate": 0.00017459411454241822,
"loss": 284.4227,
"step": 1545
},
{
"epoch": 0.31,
"grad_norm": 47.662376403808594,
"learning_rate": 0.0001743611785627841,
"loss": 264.2081,
"step": 1550
},
{
"epoch": 0.311,
"grad_norm": 52.77998352050781,
"learning_rate": 0.0001741273365156561,
"loss": 275.133,
"step": 1555
},
{
"epoch": 0.312,
"grad_norm": 61.724395751953125,
"learning_rate": 0.0001738925912503259,
"loss": 278.4467,
"step": 1560
},
{
"epoch": 0.313,
"grad_norm": 69.30736541748047,
"learning_rate": 0.00017365694562709034,
"loss": 265.1142,
"step": 1565
},
{
"epoch": 0.314,
"grad_norm": 54.34204864501953,
"learning_rate": 0.00017342040251721702,
"loss": 273.0908,
"step": 1570
},
{
"epoch": 0.315,
"grad_norm": 47.92331314086914,
"learning_rate": 0.0001731829648029091,
"loss": 280.243,
"step": 1575
},
{
"epoch": 0.316,
"grad_norm": 49.99816131591797,
"learning_rate": 0.00017294463537727024,
"loss": 276.6516,
"step": 1580
},
{
"epoch": 0.317,
"grad_norm": 47.963836669921875,
"learning_rate": 0.0001727054171442692,
"loss": 270.2112,
"step": 1585
},
{
"epoch": 0.318,
"grad_norm": 48.09587478637695,
"learning_rate": 0.0001724653130187047,
"loss": 252.1641,
"step": 1590
},
{
"epoch": 0.319,
"grad_norm": 43.35991287231445,
"learning_rate": 0.0001722243259261697,
"loss": 263.0384,
"step": 1595
},
{
"epoch": 0.32,
"grad_norm": 52.25444793701172,
"learning_rate": 0.0001719824588030159,
"loss": 267.607,
"step": 1600
},
{
"epoch": 0.321,
"grad_norm": 60.11662292480469,
"learning_rate": 0.00017173971459631787,
"loss": 268.7409,
"step": 1605
},
{
"epoch": 0.322,
"grad_norm": 44.59310531616211,
"learning_rate": 0.00017149609626383717,
"loss": 279.788,
"step": 1610
},
{
"epoch": 0.323,
"grad_norm": 47.14988327026367,
"learning_rate": 0.00017125160677398626,
"loss": 275.7,
"step": 1615
},
{
"epoch": 0.324,
"grad_norm": 43.87659454345703,
"learning_rate": 0.0001710062491057925,
"loss": 269.5364,
"step": 1620
},
{
"epoch": 0.325,
"grad_norm": 45.793251037597656,
"learning_rate": 0.00017076002624886154,
"loss": 264.7808,
"step": 1625
},
{
"epoch": 0.326,
"grad_norm": 46.89291763305664,
"learning_rate": 0.00017051294120334125,
"loss": 258.7566,
"step": 1630
},
{
"epoch": 0.327,
"grad_norm": 45.81279754638672,
"learning_rate": 0.00017026499697988493,
"loss": 269.7484,
"step": 1635
},
{
"epoch": 0.328,
"grad_norm": 40.50094223022461,
"learning_rate": 0.00017001619659961467,
"loss": 259.5116,
"step": 1640
},
{
"epoch": 0.329,
"grad_norm": 54.01460266113281,
"learning_rate": 0.00016976654309408464,
"loss": 247.8254,
"step": 1645
},
{
"epoch": 0.33,
"grad_norm": 71.55792236328125,
"learning_rate": 0.000169516039505244,
"loss": 265.0982,
"step": 1650
},
{
"epoch": 0.331,
"grad_norm": 48.39525604248047,
"learning_rate": 0.0001692646888853999,
"loss": 270.6932,
"step": 1655
},
{
"epoch": 0.332,
"grad_norm": 50.999610900878906,
"learning_rate": 0.00016901249429718032,
"loss": 258.0283,
"step": 1660
},
{
"epoch": 0.333,
"grad_norm": 51.788673400878906,
"learning_rate": 0.00016875945881349676,
"loss": 259.6249,
"step": 1665
},
{
"epoch": 0.334,
"grad_norm": 48.77846908569336,
"learning_rate": 0.0001685055855175067,
"loss": 249.0381,
"step": 1670
},
{
"epoch": 0.335,
"grad_norm": 41.93663024902344,
"learning_rate": 0.0001682508775025762,
"loss": 276.623,
"step": 1675
},
{
"epoch": 0.336,
"grad_norm": 42.32875061035156,
"learning_rate": 0.00016799533787224192,
"loss": 270.7933,
"step": 1680
},
{
"epoch": 0.337,
"grad_norm": 43.655128479003906,
"learning_rate": 0.00016773896974017373,
"loss": 267.1175,
"step": 1685
},
{
"epoch": 0.338,
"grad_norm": 46.489009857177734,
"learning_rate": 0.00016748177623013638,
"loss": 255.5338,
"step": 1690
},
{
"epoch": 0.339,
"grad_norm": 42.454551696777344,
"learning_rate": 0.00016722376047595164,
"loss": 263.2208,
"step": 1695
},
{
"epoch": 0.34,
"grad_norm": 43.79629135131836,
"learning_rate": 0.00016696492562145996,
"loss": 266.7905,
"step": 1700
},
{
"epoch": 0.341,
"grad_norm": 67.76934051513672,
"learning_rate": 0.00016670527482048246,
"loss": 262.0689,
"step": 1705
},
{
"epoch": 0.342,
"grad_norm": 46.36932373046875,
"learning_rate": 0.00016644481123678217,
"loss": 257.5991,
"step": 1710
},
{
"epoch": 0.343,
"grad_norm": 48.82585906982422,
"learning_rate": 0.00016618353804402568,
"loss": 248.5159,
"step": 1715
},
{
"epoch": 0.344,
"grad_norm": 39.46201705932617,
"learning_rate": 0.00016592145842574433,
"loss": 260.2951,
"step": 1720
},
{
"epoch": 0.345,
"grad_norm": 43.358558654785156,
"learning_rate": 0.00016565857557529566,
"loss": 278.8751,
"step": 1725
},
{
"epoch": 0.346,
"grad_norm": 38.60557556152344,
"learning_rate": 0.00016539489269582416,
"loss": 272.6581,
"step": 1730
},
{
"epoch": 0.347,
"grad_norm": 48.5496940612793,
"learning_rate": 0.00016513041300022255,
"loss": 267.7874,
"step": 1735
},
{
"epoch": 0.348,
"grad_norm": 43.05610656738281,
"learning_rate": 0.00016486513971109243,
"loss": 276.9668,
"step": 1740
},
{
"epoch": 0.349,
"grad_norm": 39.59821319580078,
"learning_rate": 0.0001645990760607051,
"loss": 257.0475,
"step": 1745
},
{
"epoch": 0.35,
"grad_norm": 39.866703033447266,
"learning_rate": 0.0001643322252909622,
"loss": 268.2825,
"step": 1750
},
{
"epoch": 0.351,
"grad_norm": 42.79712677001953,
"learning_rate": 0.00016406459065335615,
"loss": 250.6996,
"step": 1755
},
{
"epoch": 0.352,
"grad_norm": 45.14170837402344,
"learning_rate": 0.00016379617540893056,
"loss": 253.5547,
"step": 1760
},
{
"epoch": 0.353,
"grad_norm": 42.09737777709961,
"learning_rate": 0.00016352698282824044,
"loss": 258.4789,
"step": 1765
},
{
"epoch": 0.354,
"grad_norm": 42.384578704833984,
"learning_rate": 0.00016325701619131246,
"loss": 263.2515,
"step": 1770
},
{
"epoch": 0.355,
"grad_norm": 41.00054931640625,
"learning_rate": 0.00016298627878760487,
"loss": 256.0611,
"step": 1775
},
{
"epoch": 0.356,
"grad_norm": 47.38276672363281,
"learning_rate": 0.00016271477391596753,
"loss": 273.1083,
"step": 1780
},
{
"epoch": 0.357,
"grad_norm": 41.749542236328125,
"learning_rate": 0.00016244250488460158,
"loss": 267.0974,
"step": 1785
},
{
"epoch": 0.358,
"grad_norm": 64.88787078857422,
"learning_rate": 0.0001621694750110193,
"loss": 267.0445,
"step": 1790
},
{
"epoch": 0.359,
"grad_norm": 39.5011100769043,
"learning_rate": 0.00016189568762200348,
"loss": 252.6451,
"step": 1795
},
{
"epoch": 0.36,
"grad_norm": 85.52110290527344,
"learning_rate": 0.00016162114605356703,
"loss": 258.4725,
"step": 1800
},
{
"epoch": 0.361,
"grad_norm": 43.748374938964844,
"learning_rate": 0.00016134585365091243,
"loss": 255.776,
"step": 1805
},
{
"epoch": 0.362,
"grad_norm": 46.779014587402344,
"learning_rate": 0.00016106981376839066,
"loss": 256.4178,
"step": 1810
},
{
"epoch": 0.363,
"grad_norm": 42.715553283691406,
"learning_rate": 0.00016079302976946055,
"loss": 262.5154,
"step": 1815
},
{
"epoch": 0.364,
"grad_norm": 135.9436492919922,
"learning_rate": 0.0001605155050266478,
"loss": 254.0172,
"step": 1820
},
{
"epoch": 0.365,
"grad_norm": 54.12862014770508,
"learning_rate": 0.00016023724292150385,
"loss": 257.7888,
"step": 1825
},
{
"epoch": 0.366,
"grad_norm": 42.86738204956055,
"learning_rate": 0.00015995824684456465,
"loss": 262.0852,
"step": 1830
},
{
"epoch": 0.367,
"grad_norm": 40.034828186035156,
"learning_rate": 0.00015967852019530926,
"loss": 271.1969,
"step": 1835
},
{
"epoch": 0.368,
"grad_norm": 42.3065071105957,
"learning_rate": 0.0001593980663821187,
"loss": 259.7493,
"step": 1840
},
{
"epoch": 0.369,
"grad_norm": 39.868247985839844,
"learning_rate": 0.0001591168888222342,
"loss": 266.7453,
"step": 1845
},
{
"epoch": 0.37,
"grad_norm": 43.598350524902344,
"learning_rate": 0.00015883499094171554,
"loss": 279.6421,
"step": 1850
},
{
"epoch": 0.371,
"grad_norm": 40.77791976928711,
"learning_rate": 0.0001585523761753994,
"loss": 254.4231,
"step": 1855
},
{
"epoch": 0.372,
"grad_norm": 39.09046936035156,
"learning_rate": 0.00015826904796685762,
"loss": 269.4206,
"step": 1860
},
{
"epoch": 0.373,
"grad_norm": 58.26347732543945,
"learning_rate": 0.00015798500976835493,
"loss": 274.995,
"step": 1865
},
{
"epoch": 0.374,
"grad_norm": 46.25054931640625,
"learning_rate": 0.00015770026504080718,
"loss": 268.3262,
"step": 1870
},
{
"epoch": 0.375,
"grad_norm": 52.09050369262695,
"learning_rate": 0.000157414817253739,
"loss": 255.2382,
"step": 1875
},
{
"epoch": 0.376,
"grad_norm": 50.76063537597656,
"learning_rate": 0.00015712866988524155,
"loss": 269.2449,
"step": 1880
},
{
"epoch": 0.377,
"grad_norm": 49.88444519042969,
"learning_rate": 0.0001568418264219303,
"loss": 258.9195,
"step": 1885
},
{
"epoch": 0.378,
"grad_norm": 39.796630859375,
"learning_rate": 0.0001565542903589023,
"loss": 238.988,
"step": 1890
},
{
"epoch": 0.379,
"grad_norm": 37.72733688354492,
"learning_rate": 0.0001562660651996937,
"loss": 269.7818,
"step": 1895
},
{
"epoch": 0.38,
"grad_norm": 37.415443420410156,
"learning_rate": 0.00015597715445623712,
"loss": 263.4218,
"step": 1900
},
{
"epoch": 0.381,
"grad_norm": 39.50199508666992,
"learning_rate": 0.00015568756164881882,
"loss": 256.9902,
"step": 1905
},
{
"epoch": 0.382,
"grad_norm": 58.79146194458008,
"learning_rate": 0.00015539729030603574,
"loss": 257.8866,
"step": 1910
},
{
"epoch": 0.383,
"grad_norm": 43.52664566040039,
"learning_rate": 0.0001551063439647526,
"loss": 256.392,
"step": 1915
},
{
"epoch": 0.384,
"grad_norm": 38.189552307128906,
"learning_rate": 0.00015481472617005876,
"loss": 257.9,
"step": 1920
},
{
"epoch": 0.385,
"grad_norm": 37.94824981689453,
"learning_rate": 0.00015452244047522502,
"loss": 254.5535,
"step": 1925
},
{
"epoch": 0.386,
"grad_norm": 56.582923889160156,
"learning_rate": 0.0001542294904416603,
"loss": 258.4363,
"step": 1930
},
{
"epoch": 0.387,
"grad_norm": 39.287269592285156,
"learning_rate": 0.00015393587963886835,
"loss": 252.0892,
"step": 1935
},
{
"epoch": 0.388,
"grad_norm": 46.01531982421875,
"learning_rate": 0.0001536416116444041,
"loss": 268.6771,
"step": 1940
},
{
"epoch": 0.389,
"grad_norm": 46.73694610595703,
"learning_rate": 0.0001533466900438303,
"loss": 278.8018,
"step": 1945
},
{
"epoch": 0.39,
"grad_norm": 42.86819839477539,
"learning_rate": 0.0001530511184306734,
"loss": 275.2447,
"step": 1950
},
{
"epoch": 0.391,
"grad_norm": 45.710994720458984,
"learning_rate": 0.00015275490040638038,
"loss": 269.1281,
"step": 1955
},
{
"epoch": 0.392,
"grad_norm": 53.895023345947266,
"learning_rate": 0.00015245803958027434,
"loss": 259.0909,
"step": 1960
},
{
"epoch": 0.393,
"grad_norm": 45.87960433959961,
"learning_rate": 0.0001521605395695108,
"loss": 263.3782,
"step": 1965
},
{
"epoch": 0.394,
"grad_norm": 47.00539016723633,
"learning_rate": 0.00015186240399903342,
"loss": 262.2372,
"step": 1970
},
{
"epoch": 0.395,
"grad_norm": 43.53969192504883,
"learning_rate": 0.00015156363650153012,
"loss": 269.2971,
"step": 1975
},
{
"epoch": 0.396,
"grad_norm": 43.114707946777344,
"learning_rate": 0.0001512642407173885,
"loss": 270.7597,
"step": 1980
},
{
"epoch": 0.397,
"grad_norm": 56.77632141113281,
"learning_rate": 0.00015096422029465178,
"loss": 265.8668,
"step": 1985
},
{
"epoch": 0.398,
"grad_norm": 41.698387145996094,
"learning_rate": 0.0001506635788889741,
"loss": 239.4794,
"step": 1990
},
{
"epoch": 0.399,
"grad_norm": 45.86994934082031,
"learning_rate": 0.0001503623201635761,
"loss": 269.7941,
"step": 1995
},
{
"epoch": 0.4,
"grad_norm": 55.51190948486328,
"learning_rate": 0.0001500604477892003,
"loss": 267.3379,
"step": 2000
}
],
"logging_steps": 5,
"max_steps": 5000,
"num_input_tokens_seen": 0,
"num_train_epochs": 9223372036854775807,
"save_steps": 1000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 9.574790725632e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.4,
"eval_steps": 500,
"global_step": 2000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.001,
"grad_norm": 45.34572219848633,
"learning_rate": 1.6000000000000001e-06,
"loss": 319.578,
"step": 5
},
{
"epoch": 0.002,
"grad_norm": 35.23944091796875,
"learning_rate": 3.6e-06,
"loss": 321.7812,
"step": 10
},
{
"epoch": 0.003,
"grad_norm": 31.629674911499023,
"learning_rate": 5.600000000000001e-06,
"loss": 321.7244,
"step": 15
},
{
"epoch": 0.004,
"grad_norm": 37.21824264526367,
"learning_rate": 7.6e-06,
"loss": 327.2896,
"step": 20
},
{
"epoch": 0.005,
"grad_norm": 41.95133972167969,
"learning_rate": 9.600000000000001e-06,
"loss": 327.3718,
"step": 25
},
{
"epoch": 0.006,
"grad_norm": 41.561954498291016,
"learning_rate": 1.16e-05,
"loss": 315.5146,
"step": 30
},
{
"epoch": 0.007,
"grad_norm": 38.29129409790039,
"learning_rate": 1.3600000000000002e-05,
"loss": 318.5627,
"step": 35
},
{
"epoch": 0.008,
"grad_norm": 44.10498046875,
"learning_rate": 1.56e-05,
"loss": 312.3329,
"step": 40
},
{
"epoch": 0.009,
"grad_norm": 44.040958404541016,
"learning_rate": 1.76e-05,
"loss": 316.1487,
"step": 45
},
{
"epoch": 0.01,
"grad_norm": 48.966148376464844,
"learning_rate": 1.9600000000000002e-05,
"loss": 328.8573,
"step": 50
},
{
"epoch": 0.011,
"grad_norm": 48.719276428222656,
"learning_rate": 2.16e-05,
"loss": 314.682,
"step": 55
},
{
"epoch": 0.012,
"grad_norm": 56.17375946044922,
"learning_rate": 2.36e-05,
"loss": 315.3329,
"step": 60
},
{
"epoch": 0.013,
"grad_norm": 48.65364456176758,
"learning_rate": 2.5600000000000002e-05,
"loss": 320.5187,