{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 100,
  "global_step": 690,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01451378809869376,
      "grad_norm": 0.6509416103363037,
      "learning_rate": 5.7142857142857145e-06,
      "loss": 1.3988,
      "step": 5
    },
    {
      "epoch": 0.02902757619738752,
      "grad_norm": 0.40639710426330566,
      "learning_rate": 1.2857142857142857e-05,
      "loss": 1.395,
      "step": 10
    },
    {
      "epoch": 0.04354136429608128,
      "grad_norm": 0.4619132876396179,
      "learning_rate": 2e-05,
      "loss": 1.2558,
      "step": 15
    },
    {
      "epoch": 0.05805515239477504,
      "grad_norm": 0.4009605348110199,
      "learning_rate": 2.714285714285714e-05,
      "loss": 1.1799,
      "step": 20
    },
    {
      "epoch": 0.07256894049346879,
      "grad_norm": 0.5741651654243469,
      "learning_rate": 3.428571428571429e-05,
      "loss": 1.0813,
      "step": 25
    },
    {
      "epoch": 0.08708272859216255,
      "grad_norm": 0.5016195178031921,
      "learning_rate": 4.1428571428571437e-05,
      "loss": 0.9022,
      "step": 30
    },
    {
      "epoch": 0.10159651669085631,
      "grad_norm": 0.48848724365234375,
      "learning_rate": 4.8571428571428576e-05,
      "loss": 0.9365,
      "step": 35
    },
    {
      "epoch": 0.11611030478955008,
      "grad_norm": 0.48955002427101135,
      "learning_rate": 4.999539919507037e-05,
      "loss": 0.993,
      "step": 40
    },
    {
      "epoch": 0.13062409288824384,
      "grad_norm": 0.6198442578315735,
      "learning_rate": 4.997671132725569e-05,
      "loss": 0.9726,
      "step": 45
    },
    {
      "epoch": 0.14513788098693758,
      "grad_norm": 1.156268835067749,
      "learning_rate": 4.994365958519782e-05,
      "loss": 0.8953,
      "step": 50
    },
    {
      "epoch": 0.15965166908563136,
      "grad_norm": 0.6930173635482788,
      "learning_rate": 4.989626297664602e-05,
      "loss": 0.9511,
      "step": 55
    },
    {
      "epoch": 0.1741654571843251,
      "grad_norm": 0.497702419757843,
      "learning_rate": 4.983454875894878e-05,
      "loss": 0.8398,
      "step": 60
    },
    {
      "epoch": 0.18867924528301888,
      "grad_norm": 0.6527682542800903,
      "learning_rate": 4.975855242337838e-05,
      "loss": 0.9117,
      "step": 65
    },
    {
      "epoch": 0.20319303338171263,
      "grad_norm": 0.4459102749824524,
      "learning_rate": 4.966831767472015e-05,
      "loss": 0.8948,
      "step": 70
    },
    {
      "epoch": 0.21770682148040638,
      "grad_norm": 0.504393994808197,
      "learning_rate": 4.956389640613828e-05,
      "loss": 0.8303,
      "step": 75
    },
    {
      "epoch": 0.23222060957910015,
      "grad_norm": 0.5637146830558777,
      "learning_rate": 4.944534866933257e-05,
      "loss": 0.8798,
      "step": 80
    },
    {
      "epoch": 0.2467343976777939,
      "grad_norm": 0.5706853866577148,
      "learning_rate": 4.9312742640003216e-05,
      "loss": 0.8788,
      "step": 85
    },
    {
      "epoch": 0.2612481857764877,
      "grad_norm": 0.5111519694328308,
      "learning_rate": 4.9166154578643596e-05,
      "loss": 0.8605,
      "step": 90
    },
    {
      "epoch": 0.2757619738751814,
      "grad_norm": 0.5790703892707825,
      "learning_rate": 4.900566878668362e-05,
      "loss": 0.8254,
      "step": 95
    },
    {
      "epoch": 0.29027576197387517,
      "grad_norm": 0.6373398900032043,
      "learning_rate": 4.883137755800871e-05,
      "loss": 0.8569,
      "step": 100
    },
    {
      "epoch": 0.29027576197387517,
      "eval_loss": 0.8779192566871643,
      "eval_runtime": 19.4516,
      "eval_samples_per_second": 14.909,
      "eval_steps_per_second": 3.753,
      "step": 100
    },
    {
      "epoch": 0.3047895500725689,
      "grad_norm": 0.6841389536857605,
      "learning_rate": 4.864338112588245e-05,
      "loss": 0.8342,
      "step": 105
    },
    {
      "epoch": 0.3193033381712627,
      "grad_norm": 0.4855823218822479,
      "learning_rate": 4.8441787605303424e-05,
      "loss": 0.8117,
      "step": 110
    },
    {
      "epoch": 0.33381712626995647,
      "grad_norm": 0.6814753413200378,
      "learning_rate": 4.822671293082922e-05,
      "loss": 0.8199,
      "step": 115
    },
    {
      "epoch": 0.3483309143686502,
      "grad_norm": 0.7033283710479736,
      "learning_rate": 4.799828078990357e-05,
      "loss": 0.9149,
      "step": 120
    },
    {
      "epoch": 0.36284470246734396,
      "grad_norm": 0.634395956993103,
      "learning_rate": 4.775662255172486e-05,
      "loss": 0.813,
      "step": 125
    },
    {
      "epoch": 0.37735849056603776,
      "grad_norm": 0.5601548552513123,
      "learning_rate": 4.750187719169692e-05,
      "loss": 0.804,
      "step": 130
    },
    {
      "epoch": 0.3918722786647315,
      "grad_norm": 0.4911321699619293,
      "learning_rate": 4.723419121150556e-05,
      "loss": 0.7661,
      "step": 135
    },
    {
      "epoch": 0.40638606676342526,
      "grad_norm": 0.824245810508728,
      "learning_rate": 4.6953718554866835e-05,
      "loss": 0.8241,
      "step": 140
    },
    {
      "epoch": 0.420899854862119,
      "grad_norm": 0.63885897397995,
      "learning_rate": 4.666062051899538e-05,
      "loss": 0.8277,
      "step": 145
    },
    {
      "epoch": 0.43541364296081275,
      "grad_norm": 0.7575412392616272,
      "learning_rate": 4.635506566184399e-05,
      "loss": 0.8293,
      "step": 150
    },
    {
      "epoch": 0.44992743105950656,
      "grad_norm": 0.6436033844947815,
      "learning_rate": 4.603722970516741e-05,
      "loss": 0.7338,
      "step": 155
    },
    {
      "epoch": 0.4644412191582003,
      "grad_norm": 0.5583508014678955,
      "learning_rate": 4.570729543346645e-05,
      "loss": 0.8061,
      "step": 160
    },
    {
      "epoch": 0.47895500725689405,
      "grad_norm": 0.6202744245529175,
      "learning_rate": 4.536545258887028e-05,
      "loss": 0.8342,
      "step": 165
    },
    {
      "epoch": 0.4934687953555878,
      "grad_norm": 0.5933547019958496,
      "learning_rate": 4.501189776201755e-05,
      "loss": 0.7869,
      "step": 170
    },
    {
      "epoch": 0.5079825834542816,
      "grad_norm": 0.6718804836273193,
      "learning_rate": 4.4646834278998884e-05,
      "loss": 0.7554,
      "step": 175
    },
    {
      "epoch": 0.5224963715529753,
      "grad_norm": 0.637037456035614,
      "learning_rate": 4.427047208442596e-05,
      "loss": 0.7258,
      "step": 180
    },
    {
      "epoch": 0.5370101596516691,
      "grad_norm": 0.6892711520195007,
      "learning_rate": 4.388302762069435e-05,
      "loss": 0.8281,
      "step": 185
    },
    {
      "epoch": 0.5515239477503628,
      "grad_norm": 0.619770348072052,
      "learning_rate": 4.348472370350946e-05,
      "loss": 0.7811,
      "step": 190
    },
    {
      "epoch": 0.5660377358490566,
      "grad_norm": 0.6049220561981201,
      "learning_rate": 4.3075789393747306e-05,
      "loss": 0.8315,
      "step": 195
    },
    {
      "epoch": 0.5805515239477503,
      "grad_norm": 0.7725363969802856,
      "learning_rate": 4.2656459865723775e-05,
      "loss": 0.8435,
      "step": 200
    },
    {
      "epoch": 0.5805515239477503,
      "eval_loss": 0.8247659802436829,
      "eval_runtime": 19.311,
      "eval_samples_per_second": 15.017,
      "eval_steps_per_second": 3.78,
      "step": 200
    },
    {
      "epoch": 0.5950653120464441,
      "grad_norm": 0.5748031735420227,
      "learning_rate": 4.222697627194803e-05,
      "loss": 0.7336,
      "step": 205
    },
    {
      "epoch": 0.6095791001451378,
      "grad_norm": 0.8104192018508911,
      "learning_rate": 4.1787585604437926e-05,
      "loss": 0.7715,
      "step": 210
    },
    {
      "epoch": 0.6240928882438317,
      "grad_norm": 0.6528811454772949,
      "learning_rate": 4.133854055267725e-05,
      "loss": 0.725,
      "step": 215
    },
    {
      "epoch": 0.6386066763425254,
      "grad_norm": 0.681361973285675,
      "learning_rate": 4.088009935829631e-05,
      "loss": 0.7568,
      "step": 220
    },
    {
      "epoch": 0.6531204644412192,
      "grad_norm": 0.9072317481040955,
      "learning_rate": 4.0412525666559596e-05,
      "loss": 0.8035,
      "step": 225
    },
    {
      "epoch": 0.6676342525399129,
      "grad_norm": 0.7364740371704102,
      "learning_rate": 3.993608837474585e-05,
      "loss": 0.7497,
      "step": 230
    },
    {
      "epoch": 0.6821480406386067,
      "grad_norm": 0.793581485748291,
      "learning_rate": 3.9451061477507715e-05,
      "loss": 0.752,
      "step": 235
    },
    {
      "epoch": 0.6966618287373004,
      "grad_norm": 0.7835913896560669,
      "learning_rate": 3.895772390929996e-05,
      "loss": 0.7866,
      "step": 240
    },
    {
      "epoch": 0.7111756168359942,
      "grad_norm": 0.7025692462921143,
      "learning_rate": 3.8456359383966934e-05,
      "loss": 0.8149,
      "step": 245
    },
    {
      "epoch": 0.7256894049346879,
      "grad_norm": 0.9281949400901794,
      "learning_rate": 3.7947256231581296e-05,
      "loss": 0.8159,
      "step": 250
    },
    {
      "epoch": 0.7402031930333817,
      "grad_norm": 0.6731794476509094,
      "learning_rate": 3.743070723262809e-05,
      "loss": 0.809,
      "step": 255
    },
    {
      "epoch": 0.7547169811320755,
      "grad_norm": 0.7136901021003723,
      "learning_rate": 3.690700944962947e-05,
      "loss": 0.7652,
      "step": 260
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 0.7964262366294861,
      "learning_rate": 3.637646405630673e-05,
      "loss": 0.7275,
      "step": 265
    },
    {
      "epoch": 0.783744557329463,
      "grad_norm": 0.6035962700843811,
      "learning_rate": 3.583937616437816e-05,
      "loss": 0.7794,
      "step": 270
    },
    {
      "epoch": 0.7982583454281568,
      "grad_norm": 0.5344620943069458,
      "learning_rate": 3.529605464809208e-05,
      "loss": 0.7496,
      "step": 275
    },
    {
      "epoch": 0.8127721335268505,
      "grad_norm": 0.6882227063179016,
      "learning_rate": 3.4746811966596196e-05,
      "loss": 0.7894,
      "step": 280
    },
    {
      "epoch": 0.8272859216255443,
      "grad_norm": 0.6256474256515503,
      "learning_rate": 3.419196398424521e-05,
      "loss": 0.7222,
      "step": 285
    },
    {
      "epoch": 0.841799709724238,
      "grad_norm": 0.7505126595497131,
      "learning_rate": 3.363182978895019e-05,
      "loss": 0.7631,
      "step": 290
    },
    {
      "epoch": 0.8563134978229318,
      "grad_norm": 0.6608067154884338,
      "learning_rate": 3.306673150867407e-05,
      "loss": 0.7486,
      "step": 295
    },
    {
      "epoch": 0.8708272859216255,
      "grad_norm": 0.9496079087257385,
      "learning_rate": 3.249699412617883e-05,
      "loss": 0.7267,
      "step": 300
    },
    {
      "epoch": 0.8708272859216255,
      "eval_loss": 0.8032158613204956,
      "eval_runtime": 19.3267,
      "eval_samples_per_second": 15.005,
      "eval_steps_per_second": 3.777,
      "step": 300
    },
    {
      "epoch": 0.8853410740203193,
      "grad_norm": 0.7171178460121155,
      "learning_rate": 3.1922945292131006e-05,
      "loss": 0.7453,
      "step": 305
    },
    {
      "epoch": 0.8998548621190131,
      "grad_norm": 0.8150624632835388,
      "learning_rate": 3.1344915136672784e-05,
      "loss": 0.7828,
      "step": 310
    },
    {
      "epoch": 0.9143686502177069,
      "grad_norm": 0.5487958788871765,
      "learning_rate": 3.076323607956723e-05,
      "loss": 0.7636,
      "step": 315
    },
    {
      "epoch": 0.9288824383164006,
      "grad_norm": 0.8114864230155945,
      "learning_rate": 3.0178242639026792e-05,
      "loss": 0.7274,
      "step": 320
    },
    {
      "epoch": 0.9433962264150944,
      "grad_norm": 0.6911133527755737,
      "learning_rate": 2.959027123933501e-05,
      "loss": 0.7282,
      "step": 325
    },
    {
      "epoch": 0.9579100145137881,
      "grad_norm": 0.8376756310462952,
      "learning_rate": 2.899966001737199e-05,
      "loss": 0.7825,
      "step": 330
    },
    {
      "epoch": 0.9724238026124818,
      "grad_norm": 0.9565706849098206,
      "learning_rate": 2.840674862815506e-05,
      "loss": 0.7657,
      "step": 335
    },
    {
      "epoch": 0.9869375907111756,
      "grad_norm": 0.7867807149887085,
      "learning_rate": 2.7811878049506362e-05,
      "loss": 0.7861,
      "step": 340
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.7989873886108398,
      "learning_rate": 2.7215390385959598e-05,
      "loss": 0.7343,
      "step": 345
    },
    {
      "epoch": 1.0145137880986939,
      "grad_norm": 0.6233828663825989,
      "learning_rate": 2.6617628672018997e-05,
      "loss": 0.665,
      "step": 350
    },
    {
      "epoch": 1.0290275761973875,
      "grad_norm": 0.6964126825332642,
      "learning_rate": 2.6018936674883277e-05,
      "loss": 0.6674,
      "step": 355
    },
    {
      "epoch": 1.0435413642960814,
      "grad_norm": 0.5633028149604797,
      "learning_rate": 2.541965869674838e-05,
      "loss": 0.7013,
      "step": 360
    },
    {
      "epoch": 1.058055152394775,
      "grad_norm": 0.6417669653892517,
      "learning_rate": 2.482013937680245e-05,
      "loss": 0.6625,
      "step": 365
    },
    {
      "epoch": 1.0725689404934688,
      "grad_norm": 0.5850866436958313,
      "learning_rate": 2.4220723493027087e-05,
      "loss": 0.6697,
      "step": 370
    },
    {
      "epoch": 1.0870827285921625,
      "grad_norm": 0.6280177235603333,
      "learning_rate": 2.3621755763918688e-05,
      "loss": 0.7241,
      "step": 375
    },
    {
      "epoch": 1.1015965166908563,
      "grad_norm": 0.6016490459442139,
      "learning_rate": 2.302358065024409e-05,
      "loss": 0.6989,
      "step": 380
    },
    {
      "epoch": 1.11611030478955,
      "grad_norm": 0.6168230772018433,
      "learning_rate": 2.242654215694435e-05,
      "loss": 0.6757,
      "step": 385
    },
    {
      "epoch": 1.1306240928882438,
      "grad_norm": 0.7942184209823608,
      "learning_rate": 2.183098363530076e-05,
      "loss": 0.7151,
      "step": 390
    },
    {
      "epoch": 1.1451378809869377,
      "grad_norm": 0.6211004853248596,
      "learning_rate": 2.123724758547664e-05,
      "loss": 0.7134,
      "step": 395
    },
    {
      "epoch": 1.1596516690856313,
      "grad_norm": 0.7150187492370605,
      "learning_rate": 2.0645675459548757e-05,
      "loss": 0.7409,
      "step": 400
    },
    {
      "epoch": 1.1596516690856313,
      "eval_loss": 0.7901310324668884,
      "eval_runtime": 19.3786,
      "eval_samples_per_second": 14.965,
      "eval_steps_per_second": 3.767,
      "step": 400
    },
    {
      "epoch": 1.1741654571843252,
      "grad_norm": 0.801150918006897,
      "learning_rate": 2.005660746514138e-05,
      "loss": 0.7311,
      "step": 405
    },
    {
      "epoch": 1.1886792452830188,
      "grad_norm": 0.9648299217224121,
      "learning_rate": 1.9470382369776034e-05,
      "loss": 0.7251,
      "step": 410
    },
    {
      "epoch": 1.2031930333817127,
      "grad_norm": 0.7957742810249329,
      "learning_rate": 1.8887337306049473e-05,
      "loss": 0.6886,
      "step": 415
    },
    {
      "epoch": 1.2177068214804063,
      "grad_norm": 0.8583821654319763,
      "learning_rate": 1.830780757775185e-05,
      "loss": 0.6796,
      "step": 420
    },
    {
      "epoch": 1.2322206095791002,
      "grad_norm": 0.6850968599319458,
      "learning_rate": 1.773212646703662e-05,
      "loss": 0.6463,
      "step": 425
    },
    {
      "epoch": 1.2467343976777938,
      "grad_norm": 0.7404685020446777,
      "learning_rate": 1.7160625042753088e-05,
      "loss": 0.7149,
      "step": 430
    },
    {
      "epoch": 1.2612481857764877,
      "grad_norm": 0.7231425642967224,
      "learning_rate": 1.6593631970051792e-05,
      "loss": 0.7487,
      "step": 435
    },
    {
      "epoch": 1.2757619738751815,
      "grad_norm": 0.6353718638420105,
      "learning_rate": 1.6031473321372215e-05,
      "loss": 0.7117,
      "step": 440
    },
    {
      "epoch": 1.2902757619738752,
      "grad_norm": 0.7064281702041626,
      "learning_rate": 1.547447238892159e-05,
      "loss": 0.6477,
      "step": 445
    },
    {
      "epoch": 1.3047895500725688,
      "grad_norm": 0.7414827942848206,
      "learning_rate": 1.492294949875255e-05,
      "loss": 0.6712,
      "step": 450
    },
    {
      "epoch": 1.3193033381712627,
      "grad_norm": 0.6992132067680359,
      "learning_rate": 1.437722182654659e-05,
      "loss": 0.7064,
      "step": 455
    },
    {
      "epoch": 1.3338171262699565,
      "grad_norm": 0.9635509848594666,
      "learning_rate": 1.3837603215209272e-05,
      "loss": 0.732,
      "step": 460
    },
    {
      "epoch": 1.3483309143686502,
      "grad_norm": 0.9681680798530579,
      "learning_rate": 1.3304403994382125e-05,
      "loss": 0.7432,
      "step": 465
    },
    {
      "epoch": 1.362844702467344,
      "grad_norm": 0.961907148361206,
      "learning_rate": 1.2777930801974917e-05,
      "loss": 0.7288,
      "step": 470
    },
    {
      "epoch": 1.3773584905660377,
      "grad_norm": 0.8563053011894226,
      "learning_rate": 1.2258486407821082e-05,
      "loss": 0.6967,
      "step": 475
    },
    {
      "epoch": 1.3918722786647315,
      "grad_norm": 1.0022865533828735,
      "learning_rate": 1.1746369539557606e-05,
      "loss": 0.7243,
      "step": 480
    },
    {
      "epoch": 1.4063860667634254,
      "grad_norm": 0.6587550640106201,
      "learning_rate": 1.124187471082947e-05,
      "loss": 0.7066,
      "step": 485
    },
    {
      "epoch": 1.420899854862119,
      "grad_norm": 0.6341676712036133,
      "learning_rate": 1.0745292051917716e-05,
      "loss": 0.6855,
      "step": 490
    },
    {
      "epoch": 1.4354136429608126,
      "grad_norm": 0.8433622121810913,
      "learning_rate": 1.0256907142888111e-05,
      "loss": 0.7094,
      "step": 495
    },
    {
      "epoch": 1.4499274310595065,
      "grad_norm": 0.8516818284988403,
      "learning_rate": 9.777000849356785e-06,
      "loss": 0.663,
      "step": 500
    },
    {
      "epoch": 1.4499274310595065,
      "eval_loss": 0.7801858186721802,
      "eval_runtime": 19.3376,
      "eval_samples_per_second": 14.997,
      "eval_steps_per_second": 3.775,
      "step": 500
    },
    {
      "epoch": 1.4644412191582004,
      "grad_norm": 0.8840969204902649,
      "learning_rate": 9.305849160966994e-06,
      "loss": 0.7131,
      "step": 505
    },
    {
      "epoch": 1.478955007256894,
      "grad_norm": 0.9732634425163269,
      "learning_rate": 8.843723032670036e-06,
      "loss": 0.6971,
      "step": 510
    },
    {
      "epoch": 1.4934687953555879,
      "grad_norm": 0.9561111330986023,
      "learning_rate": 8.390888228901615e-06,
      "loss": 0.6897,
      "step": 515
    },
    {
      "epoch": 1.5079825834542815,
      "grad_norm": 1.558250069618225,
      "learning_rate": 7.947605170743138e-06,
      "loss": 0.751,
      "step": 520
    },
    {
      "epoch": 1.5224963715529753,
      "grad_norm": 0.9507877230644226,
      "learning_rate": 7.514128786156052e-06,
      "loss": 0.676,
      "step": 525
    },
    {
      "epoch": 1.5370101596516692,
      "grad_norm": 0.5772367119789124,
      "learning_rate": 7.090708363375026e-06,
      "loss": 0.6759,
      "step": 530
    },
    {
      "epoch": 1.5515239477503628,
      "grad_norm": 0.6241354942321777,
      "learning_rate": 6.677587407544739e-06,
      "loss": 0.6602,
      "step": 535
    },
    {
      "epoch": 1.5660377358490565,
      "grad_norm": 0.9422394037246704,
      "learning_rate": 6.275003500682258e-06,
      "loss": 0.6924,
      "step": 540
    },
    {
      "epoch": 1.5805515239477503,
      "grad_norm": 0.7861585021018982,
      "learning_rate": 5.8831881650458414e-06,
      "loss": 0.6922,
      "step": 545
    },
    {
      "epoch": 1.5950653120464442,
      "grad_norm": 0.8256082534790039,
      "learning_rate": 5.502366729988662e-06,
      "loss": 0.6655,
      "step": 550
    },
    {
      "epoch": 1.6095791001451378,
      "grad_norm": 0.8732887506484985,
      "learning_rate": 5.132758202373972e-06,
      "loss": 0.6586,
      "step": 555
    },
    {
      "epoch": 1.6240928882438317,
      "grad_norm": 0.852661669254303,
      "learning_rate": 4.7745751406263165e-06,
      "loss": 0.6834,
      "step": 560
    },
    {
      "epoch": 1.6386066763425253,
      "grad_norm": 1.0740787982940674,
      "learning_rate": 4.428023532491138e-06,
      "loss": 0.6767,
      "step": 565
    },
    {
      "epoch": 1.6531204644412192,
      "grad_norm": 0.7671570181846619,
      "learning_rate": 4.093302676573154e-06,
      "loss": 0.6365,
      "step": 570
    },
    {
      "epoch": 1.667634252539913,
      "grad_norm": 0.8762299418449402,
      "learning_rate": 3.7706050677215944e-06,
      "loss": 0.717,
      "step": 575
    },
    {
      "epoch": 1.6821480406386067,
      "grad_norm": 0.7622076272964478,
      "learning_rate": 3.4601162863281746e-06,
      "loss": 0.68,
      "step": 580
    },
    {
      "epoch": 1.6966618287373003,
      "grad_norm": 0.7803418040275574,
      "learning_rate": 3.162014891601575e-06,
      "loss": 0.7526,
      "step": 585
    },
    {
      "epoch": 1.7111756168359942,
      "grad_norm": 0.7567455768585205,
      "learning_rate": 2.876472318879675e-06,
      "loss": 0.648,
      "step": 590
    },
    {
      "epoch": 1.725689404934688,
      "grad_norm": 0.8395769000053406,
      "learning_rate": 2.6036527810387012e-06,
      "loss": 0.697,
      "step": 595
    },
    {
      "epoch": 1.7402031930333817,
      "grad_norm": 1.0212631225585938,
      "learning_rate": 2.343713174055917e-06,
      "loss": 0.7083,
      "step": 600
    },
    {
      "epoch": 1.7402031930333817,
      "eval_loss": 0.7767183780670166,
      "eval_runtime": 19.3284,
      "eval_samples_per_second": 15.004,
      "eval_steps_per_second": 3.777,
      "step": 600
    },
    {
      "epoch": 1.7547169811320755,
      "grad_norm": 0.6623890399932861,
      "learning_rate": 2.0968029867802245e-06,
      "loss": 0.6615,
      "step": 605
    },
    {
      "epoch": 1.7692307692307692,
      "grad_norm": 0.7819314002990723,
      "learning_rate": 1.8630642149624984e-06,
      "loss": 0.6918,
      "step": 610
    },
    {
      "epoch": 1.783744557329463,
      "grad_norm": 0.942303478717804,
      "learning_rate": 1.642631279595161e-06,
      "loss": 0.7056,
      "step": 615
    },
    {
      "epoch": 1.7982583454281569,
      "grad_norm": 0.8424070477485657,
      "learning_rate": 1.435630949607933e-06,
      "loss": 0.6898,
      "step": 620
    },
    {
      "epoch": 1.8127721335268505,
      "grad_norm": 0.7361651659011841,
      "learning_rate": 1.2421822689641704e-06,
      "loss": 0.6623,
      "step": 625
    },
    {
      "epoch": 1.8272859216255442,
      "grad_norm": 0.9292670488357544,
      "learning_rate": 1.0623964881998267e-06,
      "loss": 0.7124,
      "step": 630
    },
    {
      "epoch": 1.841799709724238,
      "grad_norm": 1.093030333518982,
      "learning_rate": 8.963770004442707e-07,
      "loss": 0.6846,
      "step": 635
    },
    {
      "epoch": 1.8563134978229319,
      "grad_norm": 0.9066946506500244,
      "learning_rate": 7.44219281959882e-07,
      "loss": 0.6931,
      "step": 640
    },
    {
      "epoch": 1.8708272859216255,
      "grad_norm": 0.9136037230491638,
      "learning_rate": 6.060108372345358e-07,
      "loss": 0.6756,
      "step": 645
    },
    {
      "epoch": 1.8853410740203191,
      "grad_norm": 0.9907564520835876,
      "learning_rate": 4.818311486585791e-07,
      "loss": 0.6955,
      "step": 650
    },
    {
      "epoch": 1.899854862119013,
      "grad_norm": 0.7532995343208313,
      "learning_rate": 3.7175163081526187e-07,
      "loss": 0.6549,
      "step": 655
    },
    {
      "epoch": 1.9143686502177069,
      "grad_norm": 1.002290964126587,
      "learning_rate": 2.758355894108555e-07,
      "loss": 0.6645,
      "step": 660
    },
    {
      "epoch": 1.9288824383164007,
      "grad_norm": 1.0136343240737915,
      "learning_rate": 1.941381848681506e-07,
      "loss": 0.675,
      "step": 665
    },
    {
      "epoch": 1.9433962264150944,
      "grad_norm": 0.6687794327735901,
      "learning_rate": 1.267064006041957e-07,
      "loss": 0.6556,
      "step": 670
    },
    {
      "epoch": 1.957910014513788,
      "grad_norm": 0.7404929399490356,
      "learning_rate": 7.357901601058037e-08,
      "loss": 0.7047,
      "step": 675
    },
    {
      "epoch": 1.9724238026124818,
      "grad_norm": 0.89998459815979,
      "learning_rate": 3.4786584151766386e-08,
      "loss": 0.669,
      "step": 680
    },
    {
      "epoch": 1.9869375907111757,
      "grad_norm": 0.6326516270637512,
      "learning_rate": 1.0351414194298414e-08,
      "loss": 0.6589,
      "step": 685
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.7286436557769775,
      "learning_rate": 2.8755857701956436e-10,
      "loss": 0.7122,
      "step": 690
    },
    {
      "epoch": 2.0,
      "step": 690,
      "total_flos": 1.1655000700143206e+18,
      "train_loss": 0.7663022487059884,
      "train_runtime": 2488.9062,
      "train_samples_per_second": 4.428,
      "train_steps_per_second": 0.277
    }
  ],
  "logging_steps": 5,
  "max_steps": 690,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1655000700143206e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}