{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9880715705765408,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009940357852882704,
      "grad_norm": 7.53125,
      "learning_rate": 1e-05,
      "loss": 10.9235,
      "step": 5
    },
    {
      "epoch": 0.019880715705765408,
      "grad_norm": 7.125,
      "learning_rate": 2e-05,
      "loss": 10.8542,
      "step": 10
    },
    {
      "epoch": 0.02982107355864811,
      "grad_norm": 5.28125,
      "learning_rate": 3e-05,
      "loss": 10.6296,
      "step": 15
    },
    {
      "epoch": 0.039761431411530816,
      "grad_norm": 3.734375,
      "learning_rate": 4e-05,
      "loss": 10.4421,
      "step": 20
    },
    {
      "epoch": 0.04970178926441352,
      "grad_norm": 3.109375,
      "learning_rate": 5e-05,
      "loss": 10.3131,
      "step": 25
    },
    {
      "epoch": 0.05964214711729622,
      "grad_norm": 2.921875,
      "learning_rate": 6e-05,
      "loss": 10.2138,
      "step": 30
    },
    {
      "epoch": 0.06958250497017893,
      "grad_norm": 2.921875,
      "learning_rate": 7.000000000000001e-05,
      "loss": 10.061,
      "step": 35
    },
    {
      "epoch": 0.07952286282306163,
      "grad_norm": 2.671875,
      "learning_rate": 8e-05,
      "loss": 9.9397,
      "step": 40
    },
    {
      "epoch": 0.08946322067594434,
      "grad_norm": 2.625,
      "learning_rate": 8.999999999999999e-05,
      "loss": 9.7387,
      "step": 45
    },
    {
      "epoch": 0.09940357852882704,
      "grad_norm": 2.59375,
      "learning_rate": 0.0001,
      "loss": 9.5704,
      "step": 50
    },
    {
      "epoch": 0.10934393638170974,
      "grad_norm": 2.375,
      "learning_rate": 0.00011,
      "loss": 9.3733,
      "step": 55
    },
    {
      "epoch": 0.11928429423459244,
      "grad_norm": 2.34375,
      "learning_rate": 0.00012,
      "loss": 9.1876,
      "step": 60
    },
    {
      "epoch": 0.12922465208747516,
      "grad_norm": 1.84375,
      "learning_rate": 0.00013000000000000002,
      "loss": 9.041,
      "step": 65
    },
    {
      "epoch": 0.13916500994035785,
      "grad_norm": 1.671875,
      "learning_rate": 0.00014000000000000001,
      "loss": 8.8545,
      "step": 70
    },
    {
      "epoch": 0.14910536779324055,
      "grad_norm": 1.53125,
      "learning_rate": 0.00015,
      "loss": 8.6955,
      "step": 75
    },
    {
      "epoch": 0.15904572564612326,
      "grad_norm": 1.2421875,
      "learning_rate": 0.00016,
      "loss": 8.5583,
      "step": 80
    },
    {
      "epoch": 0.16898608349900596,
      "grad_norm": 1.046875,
      "learning_rate": 0.00017,
      "loss": 8.4812,
      "step": 85
    },
    {
      "epoch": 0.17892644135188868,
      "grad_norm": 1.28125,
      "learning_rate": 0.00017999999999999998,
      "loss": 8.4265,
      "step": 90
    },
    {
      "epoch": 0.18886679920477137,
      "grad_norm": 1.2109375,
      "learning_rate": 0.00019,
      "loss": 8.4638,
      "step": 95
    },
    {
      "epoch": 0.1988071570576541,
      "grad_norm": 1.2734375,
      "learning_rate": 0.0002,
      "loss": 8.3998,
      "step": 100
    },
    {
      "epoch": 0.20874751491053678,
      "grad_norm": 1.265625,
      "learning_rate": 0.00021,
      "loss": 8.3605,
      "step": 105
    },
    {
      "epoch": 0.21868787276341947,
      "grad_norm": 1.3203125,
      "learning_rate": 0.00022,
      "loss": 8.3752,
      "step": 110
    },
    {
      "epoch": 0.2286282306163022,
      "grad_norm": 1.5,
      "learning_rate": 0.00023,
      "loss": 8.3556,
      "step": 115
    },
    {
      "epoch": 0.23856858846918488,
      "grad_norm": 1.3671875,
      "learning_rate": 0.00024,
      "loss": 8.3474,
      "step": 120
    },
    {
      "epoch": 0.2485089463220676,
      "grad_norm": 1.3203125,
      "learning_rate": 0.00025,
      "loss": 8.2942,
      "step": 125
    },
    {
      "epoch": 0.2584493041749503,
      "grad_norm": 1.65625,
      "learning_rate": 0.00026000000000000003,
      "loss": 8.316,
      "step": 130
    },
    {
      "epoch": 0.268389662027833,
      "grad_norm": 1.5234375,
      "learning_rate": 0.00027,
      "loss": 8.2375,
      "step": 135
    },
    {
      "epoch": 0.2783300198807157,
      "grad_norm": 1.734375,
      "learning_rate": 0.00028000000000000003,
      "loss": 8.2676,
      "step": 140
    },
    {
      "epoch": 0.2882703777335984,
      "grad_norm": 1.9375,
      "learning_rate": 0.00029,
      "loss": 8.1987,
      "step": 145
    },
    {
      "epoch": 0.2982107355864811,
      "grad_norm": 1.96875,
      "learning_rate": 0.0003,
      "loss": 8.1847,
      "step": 150
    },
    {
      "epoch": 0.3081510934393638,
      "grad_norm": 1.703125,
      "learning_rate": 0.00031,
      "loss": 8.2578,
      "step": 155
    },
    {
      "epoch": 0.31809145129224653,
      "grad_norm": 1.578125,
      "learning_rate": 0.00032,
      "loss": 8.1946,
      "step": 160
    },
    {
      "epoch": 0.32803180914512925,
      "grad_norm": 1.5859375,
      "learning_rate": 0.00033,
      "loss": 8.1504,
      "step": 165
    },
    {
      "epoch": 0.3379721669980119,
      "grad_norm": 1.640625,
      "learning_rate": 0.00034,
      "loss": 8.126,
      "step": 170
    },
    {
      "epoch": 0.34791252485089463,
      "grad_norm": 1.3359375,
      "learning_rate": 0.00035,
      "loss": 8.0893,
      "step": 175
    },
    {
      "epoch": 0.35785288270377735,
      "grad_norm": 1.75,
      "learning_rate": 0.00035999999999999997,
      "loss": 8.0522,
      "step": 180
    },
    {
      "epoch": 0.36779324055666,
      "grad_norm": 1.640625,
      "learning_rate": 0.00037,
      "loss": 8.0653,
      "step": 185
    },
    {
      "epoch": 0.37773359840954274,
      "grad_norm": 1.515625,
      "learning_rate": 0.00038,
      "loss": 8.0899,
      "step": 190
    },
    {
      "epoch": 0.38767395626242546,
      "grad_norm": 1.5546875,
      "learning_rate": 0.00039000000000000005,
      "loss": 8.0308,
      "step": 195
    },
    {
      "epoch": 0.3976143141153082,
      "grad_norm": 1.703125,
      "learning_rate": 0.0004,
      "loss": 7.9695,
      "step": 200
    },
    {
      "epoch": 0.40755467196819084,
      "grad_norm": 1.5546875,
      "learning_rate": 0.00041,
      "loss": 7.9639,
      "step": 205
    },
    {
      "epoch": 0.41749502982107356,
      "grad_norm": 2.203125,
      "learning_rate": 0.00042,
      "loss": 7.9662,
      "step": 210
    },
    {
      "epoch": 0.4274353876739563,
      "grad_norm": 1.65625,
      "learning_rate": 0.00043,
      "loss": 7.9049,
      "step": 215
    },
    {
      "epoch": 0.43737574552683894,
      "grad_norm": 1.515625,
      "learning_rate": 0.00044,
      "loss": 7.9815,
      "step": 220
    },
    {
      "epoch": 0.44731610337972166,
      "grad_norm": 1.5,
      "learning_rate": 0.00045000000000000004,
      "loss": 7.9026,
      "step": 225
    },
    {
      "epoch": 0.4572564612326044,
      "grad_norm": 1.6484375,
      "learning_rate": 0.00046,
      "loss": 7.8753,
      "step": 230
    },
    {
      "epoch": 0.4671968190854871,
      "grad_norm": 1.515625,
      "learning_rate": 0.00047,
      "loss": 7.8852,
      "step": 235
    },
    {
      "epoch": 0.47713717693836977,
      "grad_norm": 1.625,
      "learning_rate": 0.00048,
      "loss": 7.9331,
      "step": 240
    },
    {
      "epoch": 0.4870775347912525,
      "grad_norm": 1.78125,
      "learning_rate": 0.00049,
      "loss": 7.7972,
      "step": 245
    },
    {
      "epoch": 0.4970178926441352,
      "grad_norm": 1.5234375,
      "learning_rate": 0.0005,
      "loss": 7.8323,
      "step": 250
    },
    {
      "epoch": 0.5069582504970179,
      "grad_norm": 2.375,
      "learning_rate": 0.00051,
      "loss": 7.8246,
      "step": 255
    },
    {
      "epoch": 0.5168986083499006,
      "grad_norm": 1.5546875,
      "learning_rate": 0.0005200000000000001,
      "loss": 7.864,
      "step": 260
    },
    {
      "epoch": 0.5268389662027833,
      "grad_norm": 1.46875,
      "learning_rate": 0.0005300000000000001,
      "loss": 7.9518,
      "step": 265
    },
    {
      "epoch": 0.536779324055666,
      "grad_norm": 1.703125,
      "learning_rate": 0.00054,
      "loss": 7.7417,
      "step": 270
    },
    {
      "epoch": 0.5467196819085487,
      "grad_norm": 1.5078125,
      "learning_rate": 0.00055,
      "loss": 7.7927,
      "step": 275
    },
    {
      "epoch": 0.5566600397614314,
      "grad_norm": 1.546875,
      "learning_rate": 0.0005600000000000001,
      "loss": 7.7389,
      "step": 280
    },
    {
      "epoch": 0.5666003976143141,
      "grad_norm": 1.5625,
      "learning_rate": 0.00057,
      "loss": 7.7131,
      "step": 285
    },
    {
      "epoch": 0.5765407554671969,
      "grad_norm": 1.3125,
      "learning_rate": 0.00058,
      "loss": 7.6988,
      "step": 290
    },
    {
      "epoch": 0.5864811133200796,
      "grad_norm": 1.7421875,
      "learning_rate": 0.00059,
      "loss": 7.7104,
      "step": 295
    },
    {
      "epoch": 0.5964214711729622,
      "grad_norm": 1.859375,
      "learning_rate": 0.0006,
      "loss": 7.6605,
      "step": 300
    },
    {
      "epoch": 0.6063618290258449,
      "grad_norm": 1.59375,
      "learning_rate": 0.00061,
      "loss": 7.7188,
      "step": 305
    },
    {
      "epoch": 0.6163021868787276,
      "grad_norm": 1.734375,
      "learning_rate": 0.00062,
      "loss": 7.6618,
      "step": 310
    },
    {
      "epoch": 0.6262425447316103,
      "grad_norm": 1.46875,
      "learning_rate": 0.00063,
      "loss": 7.7635,
      "step": 315
    },
    {
      "epoch": 0.6361829025844931,
      "grad_norm": 2.265625,
      "learning_rate": 0.00064,
      "loss": 7.6721,
      "step": 320
    },
    {
      "epoch": 0.6461232604373758,
      "grad_norm": 2.953125,
      "learning_rate": 0.0006500000000000001,
      "loss": 7.6399,
      "step": 325
    },
    {
      "epoch": 0.6560636182902585,
      "grad_norm": 1.578125,
      "learning_rate": 0.00066,
      "loss": 7.5828,
      "step": 330
    },
    {
      "epoch": 0.6660039761431411,
      "grad_norm": 1.515625,
      "learning_rate": 0.00067,
      "loss": 7.6427,
      "step": 335
    },
    {
      "epoch": 0.6759443339960238,
      "grad_norm": 1.515625,
      "learning_rate": 0.00068,
      "loss": 7.4545,
      "step": 340
    },
    {
      "epoch": 0.6858846918489065,
      "grad_norm": 1.59375,
      "learning_rate": 0.00069,
      "loss": 7.5338,
      "step": 345
    },
    {
      "epoch": 0.6958250497017893,
      "grad_norm": 1.7265625,
      "learning_rate": 0.0007,
      "loss": 7.5311,
      "step": 350
    },
    {
      "epoch": 0.705765407554672,
      "grad_norm": 2.171875,
      "learning_rate": 0.00071,
      "loss": 7.5899,
      "step": 355
    },
    {
      "epoch": 0.7157057654075547,
      "grad_norm": 1.4375,
      "learning_rate": 0.0007199999999999999,
      "loss": 7.5128,
      "step": 360
    },
    {
      "epoch": 0.7256461232604374,
      "grad_norm": 1.671875,
      "learning_rate": 0.00073,
      "loss": 7.4893,
      "step": 365
    },
    {
      "epoch": 0.73558648111332,
      "grad_norm": 1.59375,
      "learning_rate": 0.00074,
      "loss": 7.5447,
      "step": 370
    },
    {
      "epoch": 0.7455268389662028,
      "grad_norm": 1.609375,
      "learning_rate": 0.00075,
      "loss": 7.4271,
      "step": 375
    },
    {
      "epoch": 0.7554671968190855,
      "grad_norm": 1.46875,
      "learning_rate": 0.00076,
      "loss": 7.5216,
      "step": 380
    },
    {
      "epoch": 0.7654075546719682,
      "grad_norm": 1.515625,
      "learning_rate": 0.0007700000000000001,
      "loss": 7.4923,
      "step": 385
    },
    {
      "epoch": 0.7753479125248509,
      "grad_norm": 1.4453125,
      "learning_rate": 0.0007800000000000001,
      "loss": 7.4305,
      "step": 390
    },
    {
      "epoch": 0.7852882703777336,
      "grad_norm": 1.484375,
      "learning_rate": 0.00079,
      "loss": 7.4223,
      "step": 395
    },
    {
      "epoch": 0.7952286282306164,
      "grad_norm": 1.5703125,
      "learning_rate": 0.0008,
      "loss": 7.4875,
      "step": 400
    },
    {
      "epoch": 0.805168986083499,
      "grad_norm": 1.4921875,
      "learning_rate": 0.0008100000000000001,
      "loss": 7.4465,
      "step": 405
    },
    {
      "epoch": 0.8151093439363817,
      "grad_norm": 1.5625,
      "learning_rate": 0.00082,
      "loss": 7.4046,
      "step": 410
    },
    {
      "epoch": 0.8250497017892644,
      "grad_norm": 1.5,
      "learning_rate": 0.00083,
      "loss": 7.384,
      "step": 415
    },
    {
      "epoch": 0.8349900596421471,
      "grad_norm": 1.5546875,
      "learning_rate": 0.00084,
      "loss": 7.3318,
      "step": 420
    },
    {
      "epoch": 0.8449304174950298,
      "grad_norm": 1.421875,
      "learning_rate": 0.00085,
      "loss": 7.4465,
      "step": 425
    },
    {
      "epoch": 0.8548707753479126,
      "grad_norm": 1.4296875,
      "learning_rate": 0.00086,
      "loss": 7.3554,
      "step": 430
    },
    {
      "epoch": 0.8648111332007953,
      "grad_norm": 1.5078125,
      "learning_rate": 0.00087,
      "loss": 7.348,
      "step": 435
    },
    {
      "epoch": 0.8747514910536779,
      "grad_norm": 1.4921875,
      "learning_rate": 0.00088,
      "loss": 7.3536,
      "step": 440
    },
    {
      "epoch": 0.8846918489065606,
      "grad_norm": 1.59375,
      "learning_rate": 0.0008900000000000001,
      "loss": 7.3074,
      "step": 445
    },
    {
      "epoch": 0.8946322067594433,
      "grad_norm": 1.546875,
      "learning_rate": 0.0009000000000000001,
      "loss": 7.4301,
      "step": 450
    },
    {
      "epoch": 0.904572564612326,
      "grad_norm": 1.5625,
      "learning_rate": 0.00091,
      "loss": 7.2948,
      "step": 455
    },
    {
      "epoch": 0.9145129224652088,
      "grad_norm": 1.6953125,
      "learning_rate": 0.00092,
      "loss": 7.4022,
      "step": 460
    },
    {
      "epoch": 0.9244532803180915,
      "grad_norm": 1.78125,
      "learning_rate": 0.00093,
      "loss": 7.3491,
      "step": 465
    },
    {
      "epoch": 0.9343936381709742,
      "grad_norm": 1.4140625,
      "learning_rate": 0.00094,
      "loss": 7.3304,
      "step": 470
    },
    {
      "epoch": 0.9443339960238568,
      "grad_norm": 1.4296875,
      "learning_rate": 0.00095,
      "loss": 7.3213,
      "step": 475
    },
    {
      "epoch": 0.9542743538767395,
      "grad_norm": 1.53125,
      "learning_rate": 0.00096,
      "loss": 7.3184,
      "step": 480
    },
    {
      "epoch": 0.9642147117296223,
      "grad_norm": 1.4609375,
      "learning_rate": 0.0009699999999999999,
      "loss": 7.2904,
      "step": 485
    },
    {
      "epoch": 0.974155069582505,
      "grad_norm": 1.3671875,
      "learning_rate": 0.00098,
      "loss": 7.2904,
      "step": 490
    },
    {
      "epoch": 0.9840954274353877,
      "grad_norm": 1.3359375,
      "learning_rate": 0.00099,
      "loss": 7.2536,
      "step": 495
    },
    {
      "epoch": 0.9940357852882704,
      "grad_norm": 1.859375,
      "learning_rate": 0.001,
      "loss": 7.2545,
      "step": 500
    },
    {
      "epoch": 0.9940357852882704,
      "eval_loss": 7.392611503601074,
      "eval_runtime": 0.9938,
      "eval_samples_per_second": 3486.498,
      "eval_steps_per_second": 436.693,
      "step": 500
    },
    {
      "epoch": 1.0039761431411531,
      "grad_norm": 1.546875,
      "learning_rate": 0.0009999972946377045,
      "loss": 7.1713,
      "step": 505
    },
    {
      "epoch": 1.0139165009940359,
      "grad_norm": 1.5390625,
      "learning_rate": 0.0009999891785833469,
      "loss": 7.0401,
      "step": 510
    },
    {
      "epoch": 1.0238568588469186,
      "grad_norm": 1.40625,
      "learning_rate": 0.0009999756519345133,
      "loss": 7.0191,
      "step": 515
    },
    {
      "epoch": 1.0337972166998013,
      "grad_norm": 1.453125,
      "learning_rate": 0.0009999567148538456,
      "loss": 7.0774,
      "step": 520
    },
    {
      "epoch": 1.0437375745526838,
      "grad_norm": 1.5703125,
      "learning_rate": 0.0009999323675690406,
      "loss": 7.1122,
      "step": 525
    },
    {
      "epoch": 1.0536779324055665,
      "grad_norm": 1.65625,
      "learning_rate": 0.0009999026103728454,
      "loss": 7.0297,
      "step": 530
    },
    {
      "epoch": 1.0636182902584492,
      "grad_norm": 1.6875,
      "learning_rate": 0.0009998674436230558,
      "loss": 7.0478,
      "step": 535
    },
    {
      "epoch": 1.073558648111332,
      "grad_norm": 1.5234375,
      "learning_rate": 0.000999826867742511,
      "loss": 7.0749,
      "step": 540
    },
    {
      "epoch": 1.0834990059642147,
      "grad_norm": 1.3984375,
      "learning_rate": 0.0009997808832190884,
      "loss": 6.9982,
      "step": 545
    },
    {
      "epoch": 1.0934393638170974,
      "grad_norm": 1.5,
      "learning_rate": 0.0009997294906056982,
      "loss": 7.0269,
      "step": 550
    },
    {
      "epoch": 1.10337972166998,
      "grad_norm": 1.328125,
      "learning_rate": 0.000999672690520277,
      "loss": 7.0031,
      "step": 555
    },
    {
      "epoch": 1.1133200795228628,
      "grad_norm": 1.28125,
      "learning_rate": 0.000999610483645779,
      "loss": 6.9229,
      "step": 560
    },
    {
      "epoch": 1.1232604373757455,
      "grad_norm": 1.421875,
      "learning_rate": 0.0009995428707301694,
      "loss": 6.989,
      "step": 565
    },
    {
      "epoch": 1.1332007952286283,
      "grad_norm": 1.421875,
      "learning_rate": 0.0009994698525864147,
      "loss": 7.0723,
      "step": 570
    },
    {
      "epoch": 1.143141153081511,
      "grad_norm": 1.453125,
      "learning_rate": 0.0009993914300924726,
      "loss": 7.0914,
      "step": 575
    },
    {
      "epoch": 1.1530815109343937,
      "grad_norm": 1.4609375,
      "learning_rate": 0.000999307604191282,
      "loss": 6.9886,
      "step": 580
    },
    {
      "epoch": 1.1630218687872764,
      "grad_norm": 1.4609375,
      "learning_rate": 0.0009992183758907518,
      "loss": 6.993,
      "step": 585
    },
    {
      "epoch": 1.1729622266401591,
      "grad_norm": 1.4453125,
      "learning_rate": 0.0009991237462637478,
      "loss": 6.9879,
      "step": 590
    },
    {
      "epoch": 1.1829025844930419,
      "grad_norm": 1.328125,
      "learning_rate": 0.000999023716448081,
      "loss": 7.034,
      "step": 595
    },
    {
      "epoch": 1.1928429423459244,
      "grad_norm": 1.5390625,
      "learning_rate": 0.0009989182876464931,
      "loss": 6.9752,
      "step": 600
    },
    {
      "epoch": 1.202783300198807,
      "grad_norm": 1.546875,
      "learning_rate": 0.0009988074611266423,
      "loss": 6.8754,
      "step": 605
    },
    {
      "epoch": 1.2127236580516898,
      "grad_norm": 1.4453125,
      "learning_rate": 0.000998691238221088,
      "loss": 6.9923,
      "step": 610
    },
    {
      "epoch": 1.2226640159045725,
      "grad_norm": 1.375,
      "learning_rate": 0.0009985696203272752,
      "loss": 6.885,
      "step": 615
    },
    {
      "epoch": 1.2326043737574552,
      "grad_norm": 1.53125,
      "learning_rate": 0.0009984426089075168,
      "loss": 6.9113,
      "step": 620
    },
    {
      "epoch": 1.242544731610338,
      "grad_norm": 1.5,
      "learning_rate": 0.000998310205488977,
      "loss": 6.9467,
      "step": 625
    },
    {
      "epoch": 1.2524850894632207,
      "grad_norm": 1.421875,
      "learning_rate": 0.0009981724116636525,
      "loss": 6.91,
      "step": 630
    },
    {
      "epoch": 1.2624254473161034,
      "grad_norm": 1.390625,
      "learning_rate": 0.0009980292290883526,
      "loss": 6.9814,
      "step": 635
    },
    {
      "epoch": 1.2723658051689861,
      "grad_norm": 1.3515625,
      "learning_rate": 0.000997880659484681,
      "loss": 6.9393,
      "step": 640
    },
    {
      "epoch": 1.2823061630218688,
      "grad_norm": 1.5234375,
      "learning_rate": 0.0009977267046390138,
      "loss": 6.9344,
      "step": 645
    },
    {
      "epoch": 1.2922465208747516,
      "grad_norm": 1.484375,
      "learning_rate": 0.000997567366402478,
      "loss": 6.8575,
      "step": 650
    },
    {
      "epoch": 1.302186878727634,
      "grad_norm": 1.3125,
      "learning_rate": 0.0009974026466909299,
      "loss": 6.85,
      "step": 655
    },
    {
      "epoch": 1.3121272365805168,
      "grad_norm": 1.3984375,
      "learning_rate": 0.000997232547484932,
      "loss": 6.9196,
      "step": 660
    },
    {
      "epoch": 1.3220675944333995,
      "grad_norm": 1.6875,
      "learning_rate": 0.0009970570708297281,
      "loss": 6.8259,
      "step": 665
    },
    {
      "epoch": 1.3320079522862822,
      "grad_norm": 1.5390625,
      "learning_rate": 0.0009968762188352208,
      "loss": 6.8472,
      "step": 670
    },
    {
      "epoch": 1.341948310139165,
      "grad_norm": 1.3828125,
      "learning_rate": 0.0009966899936759436,
      "loss": 6.8573,
      "step": 675
    },
    {
      "epoch": 1.3518886679920477,
      "grad_norm": 2.78125,
      "learning_rate": 0.0009964983975910369,
      "loss": 6.9833,
      "step": 680
    },
    {
      "epoch": 1.3618290258449304,
      "grad_norm": 1.3125,
      "learning_rate": 0.0009963014328842196,
      "loss": 6.9976,
      "step": 685
    },
    {
      "epoch": 1.371769383697813,
      "grad_norm": 1.4296875,
      "learning_rate": 0.0009960991019237627,
      "loss": 6.8598,
      "step": 690
    },
    {
      "epoch": 1.3817097415506958,
      "grad_norm": 1.359375,
      "learning_rate": 0.0009958914071424596,
      "loss": 6.8171,
      "step": 695
    },
    {
      "epoch": 1.3916500994035785,
      "grad_norm": 1.578125,
      "learning_rate": 0.0009956783510375975,
      "loss": 6.8734,
      "step": 700
    },
    {
      "epoch": 1.4015904572564613,
      "grad_norm": 1.328125,
      "learning_rate": 0.0009954599361709276,
      "loss": 6.8877,
      "step": 705
    },
    {
      "epoch": 1.411530815109344,
      "grad_norm": 1.34375,
      "learning_rate": 0.0009952361651686331,
      "loss": 6.7897,
      "step": 710
    },
    {
      "epoch": 1.4214711729622267,
      "grad_norm": 1.5546875,
      "learning_rate": 0.0009950070407212996,
      "loss": 6.9605,
      "step": 715
    },
    {
      "epoch": 1.4314115308151094,
      "grad_norm": 1.4140625,
      "learning_rate": 0.0009947725655838806,
      "loss": 6.8834,
      "step": 720
    },
    {
      "epoch": 1.4413518886679921,
      "grad_norm": 1.3984375,
      "learning_rate": 0.0009945327425756661,
      "loss": 6.8195,
      "step": 725
    },
    {
      "epoch": 1.4512922465208749,
      "grad_norm": 1.3828125,
      "learning_rate": 0.000994287574580248,
      "loss": 6.8148,
      "step": 730
    },
    {
      "epoch": 1.4612326043737576,
      "grad_norm": 1.421875,
      "learning_rate": 0.0009940370645454848,
      "loss": 6.8626,
      "step": 735
    },
    {
      "epoch": 1.4711729622266403,
      "grad_norm": 1.453125,
      "learning_rate": 0.000993781215483467,
      "loss": 6.8765,
      "step": 740
    },
    {
      "epoch": 1.4811133200795228,
      "grad_norm": 1.46875,
      "learning_rate": 0.0009935200304704815,
      "loss": 6.7831,
      "step": 745
    },
    {
      "epoch": 1.4910536779324055,
      "grad_norm": 1.4765625,
      "learning_rate": 0.0009932535126469725,
      "loss": 6.8274,
      "step": 750
    },
    {
      "epoch": 1.5009940357852882,
      "grad_norm": 1.515625,
      "learning_rate": 0.0009929816652175063,
      "loss": 6.8189,
      "step": 755
    },
    {
      "epoch": 1.510934393638171,
      "grad_norm": 1.328125,
      "learning_rate": 0.00099270449145073,
      "loss": 6.7934,
      "step": 760
    },
    {
      "epoch": 1.5208747514910537,
      "grad_norm": 1.4140625,
      "learning_rate": 0.0009924219946793353,
      "loss": 6.6405,
      "step": 765
    },
    {
      "epoch": 1.5308151093439364,
      "grad_norm": 1.71875,
      "learning_rate": 0.0009921341783000158,
      "loss": 6.6862,
      "step": 770
    },
    {
      "epoch": 1.540755467196819,
      "grad_norm": 1.3671875,
      "learning_rate": 0.000991841045773427,
      "loss": 6.7518,
      "step": 775
    },
    {
      "epoch": 1.5506958250497018,
      "grad_norm": 1.4296875,
      "learning_rate": 0.000991542600624146,
      "loss": 6.7292,
      "step": 780
    },
    {
      "epoch": 1.5606361829025845,
      "grad_norm": 1.546875,
      "learning_rate": 0.0009912388464406265,
      "loss": 6.7062,
      "step": 785
    },
    {
      "epoch": 1.570576540755467,
      "grad_norm": 1.5,
      "learning_rate": 0.0009909297868751585,
      "loss": 6.6082,
      "step": 790
    },
    {
      "epoch": 1.5805168986083498,
      "grad_norm": 1.3203125,
      "learning_rate": 0.0009906154256438223,
      "loss": 6.7426,
      "step": 795
    },
    {
      "epoch": 1.5904572564612325,
      "grad_norm": 1.484375,
      "learning_rate": 0.0009902957665264443,
      "loss": 6.8086,
      "step": 800
    },
    {
      "epoch": 1.6003976143141152,
      "grad_norm": 1.78125,
      "learning_rate": 0.0009899708133665529,
      "loss": 6.736,
      "step": 805
    },
    {
      "epoch": 1.610337972166998,
      "grad_norm": 1.3203125,
      "learning_rate": 0.0009896405700713295,
      "loss": 6.7488,
      "step": 810
    },
    {
      "epoch": 1.6202783300198806,
      "grad_norm": 1.3203125,
      "learning_rate": 0.000989305040611565,
      "loss": 6.7246,
      "step": 815
    },
    {
      "epoch": 1.6302186878727634,
      "grad_norm": 1.3984375,
      "learning_rate": 0.0009889642290216085,
      "loss": 6.7968,
      "step": 820
    },
    {
      "epoch": 1.640159045725646,
      "grad_norm": 1.4453125,
      "learning_rate": 0.0009886181393993223,
      "loss": 6.6922,
      "step": 825
    },
    {
      "epoch": 1.6500994035785288,
      "grad_norm": 1.4140625,
      "learning_rate": 0.0009882667759060298,
      "loss": 6.6635,
      "step": 830
    },
    {
      "epoch": 1.6600397614314115,
      "grad_norm": 1.3515625,
      "learning_rate": 0.0009879101427664662,
      "loss": 6.6233,
      "step": 835
    },
    {
      "epoch": 1.6699801192842942,
      "grad_norm": 1.375,
      "learning_rate": 0.0009875482442687294,
      "loss": 6.7173,
      "step": 840
    },
    {
      "epoch": 1.679920477137177,
      "grad_norm": 2.03125,
      "learning_rate": 0.0009871810847642258,
      "loss": 6.7099,
      "step": 845
    },
    {
      "epoch": 1.6898608349900597,
      "grad_norm": 1.453125,
      "learning_rate": 0.00098680866866762,
      "loss": 6.6863,
      "step": 850
    },
    {
      "epoch": 1.6998011928429424,
      "grad_norm": 1.3984375,
      "learning_rate": 0.0009864310004567807,
      "loss": 6.728,
      "step": 855
    },
    {
      "epoch": 1.7097415506958251,
      "grad_norm": 1.4296875,
      "learning_rate": 0.000986048084672727,
      "loss": 6.6503,
      "step": 860
    },
    {
      "epoch": 1.7196819085487078,
      "grad_norm": 1.265625,
      "learning_rate": 0.0009856599259195741,
      "loss": 6.6758,
      "step": 865
    },
    {
      "epoch": 1.7296222664015906,
      "grad_norm": 1.4609375,
      "learning_rate": 0.0009852665288644783,
      "loss": 6.6894,
      "step": 870
    },
    {
      "epoch": 1.7395626242544733,
      "grad_norm": 1.5078125,
      "learning_rate": 0.000984867898237579,
      "loss": 6.6299,
      "step": 875
    },
    {
      "epoch": 1.749502982107356,
      "grad_norm": 1.3203125,
      "learning_rate": 0.000984464038831945,
      "loss": 6.6652,
      "step": 880
    },
    {
      "epoch": 1.7594433399602387,
      "grad_norm": 1.53125,
      "learning_rate": 0.0009840549555035136,
      "loss": 6.6375,
      "step": 885
    },
    {
      "epoch": 1.7693836978131214,
      "grad_norm": 1.34375,
      "learning_rate": 0.0009836406531710342,
      "loss": 6.6245,
      "step": 890
    },
    {
      "epoch": 1.779324055666004,
      "grad_norm": 1.359375,
      "learning_rate": 0.0009832211368160087,
      "loss": 6.6434,
      "step": 895
    },
    {
      "epoch": 1.7892644135188867,
      "grad_norm": 1.4375,
      "learning_rate": 0.0009827964114826314,
      "loss": 6.5907,
      "step": 900
    },
    {
      "epoch": 1.7992047713717694,
      "grad_norm": 1.3359375,
      "learning_rate": 0.0009823664822777285,
      "loss": 6.6743,
      "step": 905
    },
    {
      "epoch": 1.809145129224652,
      "grad_norm": 1.3203125,
      "learning_rate": 0.000981931354370697,
      "loss": 6.6238,
      "step": 910
    },
    {
      "epoch": 1.8190854870775348,
      "grad_norm": 1.3828125,
      "learning_rate": 0.0009814910329934414,
      "loss": 6.5983,
      "step": 915
    },
    {
      "epoch": 1.8290258449304175,
      "grad_norm": 1.3984375,
      "learning_rate": 0.0009810455234403126,
      "loss": 6.6457,
      "step": 920
    },
    {
      "epoch": 1.8389662027833003,
      "grad_norm": 1.3125,
      "learning_rate": 0.000980594831068043,
      "loss": 6.4873,
      "step": 925
    },
    {
      "epoch": 1.8489065606361827,
      "grad_norm": 1.234375,
      "learning_rate": 0.0009801389612956815,
      "loss": 6.5629,
      "step": 930
    },
    {
      "epoch": 1.8588469184890655,
      "grad_norm": 1.4921875,
      "learning_rate": 0.0009796779196045303,
      "loss": 6.6765,
      "step": 935
    },
    {
      "epoch": 1.8687872763419482,
      "grad_norm": 1.5234375,
      "learning_rate": 0.0009792117115380774,
      "loss": 6.5999,
      "step": 940
    },
    {
      "epoch": 1.878727634194831,
      "grad_norm": 1.390625,
      "learning_rate": 0.0009787403427019303,
      "loss": 6.6639,
      "step": 945
    },
    {
      "epoch": 1.8886679920477136,
      "grad_norm": 1.3359375,
      "learning_rate": 0.000978263818763749,
      "loss": 6.6352,
      "step": 950
    },
    {
      "epoch": 1.8986083499005963,
      "grad_norm": 1.5859375,
      "learning_rate": 0.0009777821454531775,
      "loss": 6.6011,
      "step": 955
    },
    {
      "epoch": 1.908548707753479,
      "grad_norm": 1.3984375,
      "learning_rate": 0.0009772953285617748,
      "loss": 6.5817,
      "step": 960
    },
    {
      "epoch": 1.9184890656063618,
      "grad_norm": 1.40625,
      "learning_rate": 0.0009768033739429459,
      "loss": 6.6113,
      "step": 965
    },
    {
      "epoch": 1.9284294234592445,
      "grad_norm": 1.328125,
      "learning_rate": 0.0009763062875118706,
      "loss": 6.5931,
      "step": 970
    },
    {
      "epoch": 1.9383697813121272,
      "grad_norm": 1.46875,
      "learning_rate": 0.0009758040752454326,
      "loss": 6.6421,
      "step": 975
    },
    {
      "epoch": 1.94831013916501,
      "grad_norm": 1.234375,
      "learning_rate": 0.0009752967431821485,
      "loss": 6.6209,
      "step": 980
    },
    {
      "epoch": 1.9582504970178927,
      "grad_norm": 1.515625,
      "learning_rate": 0.0009747842974220936,
      "loss": 6.5526,
      "step": 985
    },
    {
      "epoch": 1.9681908548707754,
      "grad_norm": 1.4609375,
      "learning_rate": 0.00097426674412683,
      "loss": 6.6085,
      "step": 990
    },
    {
      "epoch": 1.978131212723658,
      "grad_norm": 1.40625,
      "learning_rate": 0.0009737440895193317,
      "loss": 6.548,
      "step": 995
    },
    {
      "epoch": 1.9880715705765408,
      "grad_norm": 1.3515625,
      "learning_rate": 0.0009732163398839106,
      "loss": 6.5648,
      "step": 1000
    },
    {
      "epoch": 1.9880715705765408,
      "eval_loss": 6.81672477722168,
      "eval_runtime": 0.9933,
      "eval_samples_per_second": 3488.505,
      "eval_steps_per_second": 436.944,
      "step": 1000
    }
  ],
  "logging_steps": 5,
  "max_steps": 5030,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "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": 1380849812951040.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}