{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9985185185185185,
  "eval_steps": 500,
  "global_step": 337,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "grad_norm": 0.2717343719780384,
      "learning_rate": 5.882352941176471e-06,
      "loss": 0.847,
      "step": 1
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.26018788821527083,
      "learning_rate": 2.9411764705882354e-05,
      "loss": 0.8467,
      "step": 5
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.27409502007154274,
      "learning_rate": 5.882352941176471e-05,
      "loss": 0.7941,
      "step": 10
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.22808596919423202,
      "learning_rate": 8.823529411764706e-05,
      "loss": 0.7851,
      "step": 15
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.23125133584227386,
      "learning_rate": 0.00011764705882352942,
      "loss": 0.7755,
      "step": 20
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.25989189643744065,
      "learning_rate": 0.00014705882352941178,
      "loss": 0.7702,
      "step": 25
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.22753514517272877,
      "learning_rate": 0.00017647058823529413,
      "loss": 0.7686,
      "step": 30
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.21078016758955764,
      "learning_rate": 0.00019999462497359466,
      "loss": 0.7542,
      "step": 35
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.19859081893165376,
      "learning_rate": 0.00019980655971335945,
      "loss": 0.744,
      "step": 40
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.22275641709788552,
      "learning_rate": 0.0001993503206718859,
      "loss": 0.7517,
      "step": 45
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.22776655537972812,
      "learning_rate": 0.0001986271337340182,
      "loss": 0.7463,
      "step": 50
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.1956697700643487,
      "learning_rate": 0.00019763894205636072,
      "loss": 0.7667,
      "step": 55
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.21778385193119887,
      "learning_rate": 0.00019638840084614182,
      "loss": 0.7659,
      "step": 60
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.19072485771807038,
      "learning_rate": 0.00019487887022684336,
      "loss": 0.7262,
      "step": 65
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.18079671941962344,
      "learning_rate": 0.00019311440620976597,
      "loss": 0.7546,
      "step": 70
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.22817732411487154,
      "learning_rate": 0.0001910997497957885,
      "loss": 0.7756,
      "step": 75
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.19704232552273215,
      "learning_rate": 0.0001888403142366049,
      "loss": 0.7571,
      "step": 80
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.1990787596887067,
      "learning_rate": 0.00018634217048966637,
      "loss": 0.717,
      "step": 85
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.20110029651804323,
      "learning_rate": 0.00018361203090591071,
      "loss": 0.7458,
      "step": 90
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.21363148763210577,
      "learning_rate": 0.00018065723119410884,
      "loss": 0.7559,
      "step": 95
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.2092198639953611,
      "learning_rate": 0.000177485710710289,
      "loss": 0.7436,
      "step": 100
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.17379599067649854,
      "learning_rate": 0.0001741059911251997,
      "loss": 0.7565,
      "step": 105
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.1932439427415246,
      "learning_rate": 0.00017052715352713075,
      "loss": 0.7324,
      "step": 110
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.18337486963195299,
      "learning_rate": 0.00016675881402161536,
      "loss": 0.7741,
      "step": 115
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.22099961666277984,
      "learning_rate": 0.0001628110978935756,
      "loss": 0.7671,
      "step": 120
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.19029413993375544,
      "learning_rate": 0.0001586946124013354,
      "loss": 0.7442,
      "step": 125
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.1988371544631114,
      "learning_rate": 0.00015442041827560274,
      "loss": 0.7341,
      "step": 130
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.19987242493132262,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.7042,
      "step": 135
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.21038405028010873,
      "learning_rate": 0.00014544523495299842,
      "loss": 0.7673,
      "step": 140
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.19354699926153257,
      "learning_rate": 0.00014076836149416887,
      "loss": 0.7433,
      "step": 145
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.18066626827397472,
      "learning_rate": 0.0001359819460805001,
      "loss": 0.7197,
      "step": 150
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.18341142655682777,
      "learning_rate": 0.00013109884950114007,
      "loss": 0.722,
      "step": 155
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.20027199179606556,
      "learning_rate": 0.00012613219232128608,
      "loss": 0.7584,
      "step": 160
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.19922644888858893,
      "learning_rate": 0.00012109531962807332,
      "loss": 0.7422,
      "step": 165
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.20849591303721368,
      "learning_rate": 0.00011600176517318741,
      "loss": 0.7368,
      "step": 170
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.17201077230274625,
      "learning_rate": 0.00011086521500854745,
      "loss": 0.7272,
      "step": 175
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.18753041018578614,
      "learning_rate": 0.00010569947071276847,
      "loss": 0.761,
      "step": 180
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.18564005055748792,
      "learning_rate": 0.00010051841230721065,
      "loss": 0.7608,
      "step": 185
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.1747173048066143,
      "learning_rate": 9.533596096125825e-05,
      "loss": 0.7325,
      "step": 190
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.19529055457131958,
      "learning_rate": 9.016604158703654e-05,
      "loss": 0.7303,
      "step": 195
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.2027646421694916,
      "learning_rate": 8.502254542407186e-05,
      "loss": 0.7515,
      "step": 200
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.19223473249089806,
      "learning_rate": 7.991929271442817e-05,
      "loss": 0.7382,
      "step": 205
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.20451742081231966,
      "learning_rate": 7.48699955686089e-05,
      "loss": 0.7504,
      "step": 210
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.1727556645914323,
      "learning_rate": 6.988822112200156e-05,
      "loss": 0.7534,
      "step": 215
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.23190942342053106,
      "learning_rate": 6.498735508086093e-05,
      "loss": 0.6892,
      "step": 220
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.17583534871896528,
      "learning_rate": 6.018056575578075e-05,
      "loss": 0.7492,
      "step": 225
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.21014816624881175,
      "learning_rate": 5.54807686792933e-05,
      "loss": 0.7713,
      "step": 230
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.20047733135183723,
      "learning_rate": 5.090059190266779e-05,
      "loss": 0.7637,
      "step": 235
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.19019165847288602,
      "learning_rate": 4.645234206515171e-05,
      "loss": 0.7845,
      "step": 240
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.18613224531948466,
      "learning_rate": 4.2147971326825966e-05,
      "loss": 0.7334,
      "step": 245
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.19683435034398994,
      "learning_rate": 3.79990452539225e-05,
      "loss": 0.7909,
      "step": 250
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.177800719796391,
      "learning_rate": 3.401671174289469e-05,
      "loss": 0.7215,
      "step": 255
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.19168634263783946,
      "learning_rate": 3.021167106673928e-05,
      "loss": 0.7022,
      "step": 260
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.17373439631284035,
      "learning_rate": 2.659414712405398e-05,
      "loss": 0.7326,
      "step": 265
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.18782667184307175,
      "learning_rate": 2.3173859968081944e-05,
      "loss": 0.7299,
      "step": 270
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.19915630586934951,
      "learning_rate": 1.995999968955641e-05,
      "loss": 0.732,
      "step": 275
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.19916604130709076,
      "learning_rate": 1.696120172352025e-05,
      "loss": 0.7713,
      "step": 280
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.20283567913811978,
      "learning_rate": 1.4185523646469822e-05,
      "loss": 0.7341,
      "step": 285
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.21959421872850948,
      "learning_rate": 1.1640423526166988e-05,
      "loss": 0.7579,
      "step": 290
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.19157855468733032,
      "learning_rate": 9.332739882292752e-06,
      "loss": 0.7292,
      "step": 295
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.20178584215661483,
      "learning_rate": 7.2686733117863784e-06,
      "loss": 0.7353,
      "step": 300
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.17123631964579586,
      "learning_rate": 5.453769828241872e-06,
      "loss": 0.7462,
      "step": 305
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.1859656607316761,
      "learning_rate": 3.892905960127546e-06,
      "loss": 0.7362,
      "step": 310
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.17627934517882088,
      "learning_rate": 2.590275647868867e-06,
      "loss": 0.7334,
      "step": 315
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.17595304767126693,
      "learning_rate": 1.5493789750014031e-06,
      "loss": 0.7682,
      "step": 320
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.1792788588282141,
      "learning_rate": 7.730127636723539e-07,
      "loss": 0.7459,
      "step": 325
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.18307997089659053,
      "learning_rate": 2.6326305976001055e-07,
      "loss": 0.7503,
      "step": 330
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.20226484823840446,
      "learning_rate": 2.1499527803214846e-08,
      "loss": 0.7345,
      "step": 335
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.916692852973938,
      "eval_runtime": 455.1769,
      "eval_samples_per_second": 5.075,
      "eval_steps_per_second": 0.319,
      "step": 337
    },
    {
      "epoch": 1.0,
      "step": 337,
      "total_flos": 5038810416021504.0,
      "train_loss": 0.749147473527699,
      "train_runtime": 12638.7542,
      "train_samples_per_second": 1.709,
      "train_steps_per_second": 0.027
    }
  ],
  "logging_steps": 5,
  "max_steps": 337,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 5038810416021504.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}