{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 375,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "grad_norm": 1.65970778465271,
      "learning_rate": 4.9985889393594345e-05,
      "loss": 1.3397,
      "step": 5
    },
    {
      "epoch": 0.03,
      "grad_norm": 1.8339558839797974,
      "learning_rate": 4.992859235371958e-05,
      "loss": 1.2413,
      "step": 10
    },
    {
      "epoch": 0.04,
      "grad_norm": 1.599440336227417,
      "learning_rate": 4.9827327946335875e-05,
      "loss": 1.0141,
      "step": 15
    },
    {
      "epoch": 0.05,
      "grad_norm": 1.4671368598937988,
      "learning_rate": 4.968227477476554e-05,
      "loss": 0.9878,
      "step": 20
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.9982190728187561,
      "learning_rate": 4.949368867399567e-05,
      "loss": 1.0212,
      "step": 25
    },
    {
      "epoch": 0.08,
      "grad_norm": 1.0809102058410645,
      "learning_rate": 4.9261902259453614e-05,
      "loss": 0.7766,
      "step": 30
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.9444558620452881,
      "learning_rate": 4.898732434036244e-05,
      "loss": 0.8701,
      "step": 35
    },
    {
      "epoch": 0.11,
      "grad_norm": 1.0244667530059814,
      "learning_rate": 4.867043919871076e-05,
      "loss": 0.6978,
      "step": 40
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.7848422527313232,
      "learning_rate": 4.8311805735108894e-05,
      "loss": 0.754,
      "step": 45
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.9545549154281616,
      "learning_rate": 4.791205648303775e-05,
      "loss": 0.6599,
      "step": 50
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.6984307765960693,
      "learning_rate": 4.747189649322894e-05,
      "loss": 0.6316,
      "step": 55
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.7565098404884338,
      "learning_rate": 4.699210209014394e-05,
      "loss": 0.7531,
      "step": 60
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.5942355990409851,
      "learning_rate": 4.6473519502745476e-05,
      "loss": 0.4528,
      "step": 65
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.7522299885749817,
      "learning_rate": 4.591706337197597e-05,
      "loss": 0.565,
      "step": 70
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.8787449598312378,
      "learning_rate": 4.532371513757564e-05,
      "loss": 0.6038,
      "step": 75
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.6031142473220825,
      "learning_rate": 4.469452130708543e-05,
      "loss": 0.6498,
      "step": 80
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.838216245174408,
      "learning_rate": 4.4030591610087624e-05,
      "loss": 0.5324,
      "step": 85
    },
    {
      "epoch": 0.24,
      "grad_norm": 1.0710391998291016,
      "learning_rate": 4.3333097040939764e-05,
      "loss": 0.5354,
      "step": 90
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.9150385856628418,
      "learning_rate": 4.260326779345393e-05,
      "loss": 0.5865,
      "step": 95
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.8779798746109009,
      "learning_rate": 4.184239109116393e-05,
      "loss": 0.5894,
      "step": 100
    },
    {
      "epoch": 0.28,
      "grad_norm": 2.170987844467163,
      "learning_rate": 4.105180891700746e-05,
      "loss": 0.5148,
      "step": 105
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.8440865874290466,
      "learning_rate": 4.023291564642711e-05,
      "loss": 0.437,
      "step": 110
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.8862484693527222,
      "learning_rate": 3.938715558806525e-05,
      "loss": 0.5527,
      "step": 115
    },
    {
      "epoch": 0.32,
      "grad_norm": 1.1455185413360596,
      "learning_rate": 3.851602043638994e-05,
      "loss": 0.5582,
      "step": 120
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.8740842938423157,
      "learning_rate": 3.7621046640744975e-05,
      "loss": 0.528,
      "step": 125
    },
    {
      "epoch": 0.35,
      "grad_norm": 1.2668254375457764,
      "learning_rate": 3.670381269546429e-05,
      "loss": 0.4583,
      "step": 130
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.8675268292427063,
      "learning_rate": 3.5765936355830356e-05,
      "loss": 0.4325,
      "step": 135
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.9672185182571411,
      "learning_rate": 3.480907178478654e-05,
      "loss": 0.5655,
      "step": 140
    },
    {
      "epoch": 0.39,
      "grad_norm": 1.1447197198867798,
      "learning_rate": 3.383490663543635e-05,
      "loss": 0.5477,
      "step": 145
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.7843021750450134,
      "learning_rate": 3.2845159074474806e-05,
      "loss": 0.673,
      "step": 150
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.8366529941558838,
      "learning_rate": 3.1841574751802076e-05,
      "loss": 0.539,
      "step": 155
    },
    {
      "epoch": 0.43,
      "grad_norm": 1.1384434700012207,
      "learning_rate": 3.082592372166412e-05,
      "loss": 0.511,
      "step": 160
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.7654138803482056,
      "learning_rate": 2.9799997320750507e-05,
      "loss": 0.402,
      "step": 165
    },
    {
      "epoch": 0.45,
      "grad_norm": 1.1874901056289673,
      "learning_rate": 2.87656050087558e-05,
      "loss": 0.453,
      "step": 170
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.9217435717582703,
      "learning_rate": 2.7724571176976732e-05,
      "loss": 0.5608,
      "step": 175
    },
    {
      "epoch": 0.48,
      "grad_norm": 1.0420029163360596,
      "learning_rate": 2.667873193057407e-05,
      "loss": 0.4598,
      "step": 180
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.8808046579360962,
      "learning_rate": 2.562993185017431e-05,
      "loss": 0.4952,
      "step": 185
    },
    {
      "epoch": 0.51,
      "grad_norm": 1.2101999521255493,
      "learning_rate": 2.4580020738523e-05,
      "loss": 0.4087,
      "step": 190
    },
    {
      "epoch": 0.52,
      "grad_norm": 1.3266472816467285,
      "learning_rate": 2.353085035792756e-05,
      "loss": 0.5781,
      "step": 195
    },
    {
      "epoch": 0.53,
      "grad_norm": 1.5473909378051758,
      "learning_rate": 2.2484271164243996e-05,
      "loss": 0.4127,
      "step": 200
    },
    {
      "epoch": 0.55,
      "grad_norm": 1.1306591033935547,
      "learning_rate": 2.1442129043167874e-05,
      "loss": 0.5682,
      "step": 205
    },
    {
      "epoch": 0.56,
      "grad_norm": 1.0642080307006836,
      "learning_rate": 2.0406262054585738e-05,
      "loss": 0.6413,
      "step": 210
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.9475000500679016,
      "learning_rate": 1.937849719072931e-05,
      "loss": 0.4034,
      "step": 215
    },
    {
      "epoch": 0.59,
      "grad_norm": 1.3008495569229126,
      "learning_rate": 1.836064715384989e-05,
      "loss": 0.5331,
      "step": 220
    },
    {
      "epoch": 0.6,
      "grad_norm": 1.1625583171844482,
      "learning_rate": 1.7354507159096647e-05,
      "loss": 0.4308,
      "step": 225
    },
    {
      "epoch": 0.61,
      "grad_norm": 1.3643542528152466,
      "learning_rate": 1.6361851768237324e-05,
      "loss": 0.474,
      "step": 230
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.6814500093460083,
      "learning_rate": 1.5384431759806083e-05,
      "loss": 0.4306,
      "step": 235
    },
    {
      "epoch": 0.64,
      "grad_norm": 1.1910830736160278,
      "learning_rate": 1.4423971041198556e-05,
      "loss": 0.5352,
      "step": 240
    },
    {
      "epoch": 0.65,
      "grad_norm": 1.0804316997528076,
      "learning_rate": 1.3482163608160408e-05,
      "loss": 0.436,
      "step": 245
    },
    {
      "epoch": 0.67,
      "grad_norm": 1.1781166791915894,
      "learning_rate": 1.2560670557032108e-05,
      "loss": 0.4172,
      "step": 250
    },
    {
      "epoch": 0.68,
      "grad_norm": 1.1555372476577759,
      "learning_rate": 1.1661117155019293e-05,
      "loss": 0.3712,
      "step": 255
    },
    {
      "epoch": 0.69,
      "grad_norm": 1.105285882949829,
      "learning_rate": 1.0785089973656337e-05,
      "loss": 0.5507,
      "step": 260
    },
    {
      "epoch": 0.71,
      "grad_norm": 1.9189614057540894,
      "learning_rate": 9.934134090518593e-06,
      "loss": 0.5309,
      "step": 265
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.8669947981834412,
      "learning_rate": 9.109750364118924e-06,
      "loss": 0.4294,
      "step": 270
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.755587637424469,
      "learning_rate": 8.313392786794833e-06,
      "loss": 0.4236,
      "step": 275
    },
    {
      "epoch": 0.75,
      "grad_norm": 1.1405256986618042,
      "learning_rate": 7.546465920254974e-06,
      "loss": 0.555,
      "step": 280
    },
    {
      "epoch": 0.76,
      "grad_norm": 1.6737154722213745,
      "learning_rate": 6.810322418308085e-06,
      "loss": 0.5034,
      "step": 285
    },
    {
      "epoch": 0.77,
      "grad_norm": 1.107371211051941,
      "learning_rate": 6.106260641143546e-06,
      "loss": 0.4616,
      "step": 290
    },
    {
      "epoch": 0.79,
      "grad_norm": 1.2634700536727905,
      "learning_rate": 5.435522365371376e-06,
      "loss": 0.456,
      "step": 295
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.8122715950012207,
      "learning_rate": 4.799290593860525e-06,
      "loss": 0.4582,
      "step": 300
    },
    {
      "epoch": 0.81,
      "grad_norm": 1.333025336265564,
      "learning_rate": 4.198687469238297e-06,
      "loss": 0.3826,
      "step": 305
    },
    {
      "epoch": 0.83,
      "grad_norm": 1.5998661518096924,
      "learning_rate": 3.6347722947309843e-06,
      "loss": 0.4933,
      "step": 310
    },
    {
      "epoch": 0.84,
      "grad_norm": 1.3631378412246704,
      "learning_rate": 3.108539665836388e-06,
      "loss": 0.5099,
      "step": 315
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.714860200881958,
      "learning_rate": 2.6209177161234445e-06,
      "loss": 0.57,
      "step": 320
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.5441424250602722,
      "learning_rate": 2.1727664802529216e-06,
      "loss": 0.4737,
      "step": 325
    },
    {
      "epoch": 0.88,
      "grad_norm": 1.4750747680664062,
      "learning_rate": 1.7648763771063837e-06,
      "loss": 0.4315,
      "step": 330
    },
    {
      "epoch": 0.89,
      "grad_norm": 1.6141853332519531,
      "learning_rate": 1.3979668156987425e-06,
      "loss": 0.4254,
      "step": 335
    },
    {
      "epoch": 0.91,
      "grad_norm": 1.2416565418243408,
      "learning_rate": 1.0726849263332256e-06,
      "loss": 0.3288,
      "step": 340
    },
    {
      "epoch": 0.92,
      "grad_norm": 1.2494091987609863,
      "learning_rate": 7.896044192366586e-07,
      "loss": 0.2477,
      "step": 345
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.9337052702903748,
      "learning_rate": 5.492245726881201e-07,
      "loss": 0.453,
      "step": 350
    },
    {
      "epoch": 0.95,
      "grad_norm": 1.0654840469360352,
      "learning_rate": 3.51969352425624e-07,
      "loss": 0.4833,
      "step": 355
    },
    {
      "epoch": 0.96,
      "grad_norm": 1.7972078323364258,
      "learning_rate": 1.981866638839952e-07,
      "loss": 0.5507,
      "step": 360
    },
    {
      "epoch": 0.97,
      "grad_norm": 1.450646996498108,
      "learning_rate": 8.814773858275004e-08,
      "loss": 0.379,
      "step": 365
    },
    {
      "epoch": 0.99,
      "grad_norm": 1.490728497505188,
      "learning_rate": 2.2046655746280064e-08,
      "loss": 0.4705,
      "step": 370
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.9804399609565735,
      "learning_rate": 0.0,
      "loss": 0.4502,
      "step": 375
    },
    {
      "epoch": 1.0,
      "step": 375,
      "total_flos": 6.701975198539776e+16,
      "train_loss": 0.5547979205449423,
      "train_runtime": 23630.1849,
      "train_samples_per_second": 0.127,
      "train_steps_per_second": 0.016
    }
  ],
  "logging_steps": 5,
  "max_steps": 375,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "total_flos": 6.701975198539776e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}