{
  "best_global_step": null,
  "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": [
    {
      "entropy": 1.3350626245141028,
      "epoch": 0.02666666666666667,
      "grad_norm": 1.2209417819976807,
      "learning_rate": 1.9783783783783786e-05,
      "loss": 3.4751,
      "mean_token_accuracy": 0.4370182503014803,
      "num_tokens": 12866.0,
      "step": 10
    },
    {
      "entropy": 1.3571727886795997,
      "epoch": 0.05333333333333334,
      "grad_norm": 1.6984230279922485,
      "learning_rate": 1.9243243243243244e-05,
      "loss": 3.2031,
      "mean_token_accuracy": 0.4396053273230791,
      "num_tokens": 25807.0,
      "step": 20
    },
    {
      "entropy": 1.471608152985573,
      "epoch": 0.08,
      "grad_norm": 1.014086127281189,
      "learning_rate": 1.8702702702702706e-05,
      "loss": 2.7028,
      "mean_token_accuracy": 0.46664220802485945,
      "num_tokens": 38578.0,
      "step": 30
    },
    {
      "entropy": 1.5595325112342835,
      "epoch": 0.10666666666666667,
      "grad_norm": 0.7482319474220276,
      "learning_rate": 1.8162162162162164e-05,
      "loss": 2.3153,
      "mean_token_accuracy": 0.5029693856835366,
      "num_tokens": 51538.0,
      "step": 40
    },
    {
      "entropy": 1.6449722349643707,
      "epoch": 0.13333333333333333,
      "grad_norm": 0.7101708650588989,
      "learning_rate": 1.7621621621621622e-05,
      "loss": 2.1109,
      "mean_token_accuracy": 0.5171717956662178,
      "num_tokens": 64387.0,
      "step": 50
    },
    {
      "entropy": 1.6670852690935134,
      "epoch": 0.16,
      "grad_norm": 0.7259413599967957,
      "learning_rate": 1.7081081081081083e-05,
      "loss": 1.9278,
      "mean_token_accuracy": 0.5485030759125948,
      "num_tokens": 77276.0,
      "step": 60
    },
    {
      "entropy": 1.6381909385323525,
      "epoch": 0.18666666666666668,
      "grad_norm": 0.7174317836761475,
      "learning_rate": 1.654054054054054e-05,
      "loss": 1.7939,
      "mean_token_accuracy": 0.5677109852433204,
      "num_tokens": 90149.0,
      "step": 70
    },
    {
      "entropy": 1.6385898187756538,
      "epoch": 0.21333333333333335,
      "grad_norm": 0.8067219257354736,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.6666,
      "mean_token_accuracy": 0.5853360824286937,
      "num_tokens": 102995.0,
      "step": 80
    },
    {
      "entropy": 1.5796676367521285,
      "epoch": 0.24,
      "grad_norm": 0.800731897354126,
      "learning_rate": 1.545945945945946e-05,
      "loss": 1.5881,
      "mean_token_accuracy": 0.597806416451931,
      "num_tokens": 115839.0,
      "step": 90
    },
    {
      "entropy": 1.5752710282802582,
      "epoch": 0.26666666666666666,
      "grad_norm": 0.8465399146080017,
      "learning_rate": 1.491891891891892e-05,
      "loss": 1.5702,
      "mean_token_accuracy": 0.5995256647467613,
      "num_tokens": 128611.0,
      "step": 100
    },
    {
      "entropy": 1.5265976443886757,
      "epoch": 0.29333333333333333,
      "grad_norm": 0.8720120787620544,
      "learning_rate": 1.4378378378378378e-05,
      "loss": 1.5057,
      "mean_token_accuracy": 0.6056284785270691,
      "num_tokens": 141383.0,
      "step": 110
    },
    {
      "entropy": 1.4974668100476265,
      "epoch": 0.32,
      "grad_norm": 0.9546942710876465,
      "learning_rate": 1.383783783783784e-05,
      "loss": 1.4441,
      "mean_token_accuracy": 0.6172919377684594,
      "num_tokens": 154276.0,
      "step": 120
    },
    {
      "entropy": 1.4532102927565576,
      "epoch": 0.3466666666666667,
      "grad_norm": 0.972088098526001,
      "learning_rate": 1.3297297297297298e-05,
      "loss": 1.4033,
      "mean_token_accuracy": 0.6191255763173104,
      "num_tokens": 167141.0,
      "step": 130
    },
    {
      "entropy": 1.4425522044301033,
      "epoch": 0.37333333333333335,
      "grad_norm": 1.0836657285690308,
      "learning_rate": 1.2756756756756758e-05,
      "loss": 1.3799,
      "mean_token_accuracy": 0.6284476429224014,
      "num_tokens": 179968.0,
      "step": 140
    },
    {
      "entropy": 1.4219948261976243,
      "epoch": 0.4,
      "grad_norm": 1.1330499649047852,
      "learning_rate": 1.2216216216216217e-05,
      "loss": 1.3888,
      "mean_token_accuracy": 0.6221960082650184,
      "num_tokens": 192836.0,
      "step": 150
    },
    {
      "entropy": 1.4194561198353768,
      "epoch": 0.4266666666666667,
      "grad_norm": 1.092614769935608,
      "learning_rate": 1.1675675675675677e-05,
      "loss": 1.3462,
      "mean_token_accuracy": 0.6329536609351635,
      "num_tokens": 205774.0,
      "step": 160
    },
    {
      "entropy": 1.3868110164999963,
      "epoch": 0.4533333333333333,
      "grad_norm": 1.253973126411438,
      "learning_rate": 1.1135135135135135e-05,
      "loss": 1.3243,
      "mean_token_accuracy": 0.6337448269128799,
      "num_tokens": 218615.0,
      "step": 170
    },
    {
      "entropy": 1.382253359258175,
      "epoch": 0.48,
      "grad_norm": 1.1929072141647339,
      "learning_rate": 1.0594594594594597e-05,
      "loss": 1.3163,
      "mean_token_accuracy": 0.6397944167256355,
      "num_tokens": 231525.0,
      "step": 180
    },
    {
      "entropy": 1.3482940062880515,
      "epoch": 0.5066666666666667,
      "grad_norm": 1.3486591577529907,
      "learning_rate": 1.0054054054054055e-05,
      "loss": 1.2625,
      "mean_token_accuracy": 0.6505386248230934,
      "num_tokens": 244338.0,
      "step": 190
    },
    {
      "entropy": 1.340237122774124,
      "epoch": 0.5333333333333333,
      "grad_norm": 1.400648593902588,
      "learning_rate": 9.513513513513514e-06,
      "loss": 1.2572,
      "mean_token_accuracy": 0.6538930542767047,
      "num_tokens": 257295.0,
      "step": 200
    },
    {
      "entropy": 1.3297127082943916,
      "epoch": 0.56,
      "grad_norm": 1.3606442213058472,
      "learning_rate": 8.972972972972974e-06,
      "loss": 1.251,
      "mean_token_accuracy": 0.6457924202084542,
      "num_tokens": 270252.0,
      "step": 210
    },
    {
      "entropy": 1.294735921919346,
      "epoch": 0.5866666666666667,
      "grad_norm": 0.9780547618865967,
      "learning_rate": 8.432432432432434e-06,
      "loss": 1.2329,
      "mean_token_accuracy": 0.6493118166923523,
      "num_tokens": 283027.0,
      "step": 220
    },
    {
      "entropy": 1.275549191236496,
      "epoch": 0.6133333333333333,
      "grad_norm": 0.7589144110679626,
      "learning_rate": 7.891891891891894e-06,
      "loss": 1.2215,
      "mean_token_accuracy": 0.6486652858555317,
      "num_tokens": 295938.0,
      "step": 230
    },
    {
      "entropy": 1.2352376490831376,
      "epoch": 0.64,
      "grad_norm": 0.590903103351593,
      "learning_rate": 7.3513513513513525e-06,
      "loss": 1.2032,
      "mean_token_accuracy": 0.6558617919683456,
      "num_tokens": 308573.0,
      "step": 240
    },
    {
      "entropy": 1.2297846719622612,
      "epoch": 0.6666666666666666,
      "grad_norm": 0.4950984716415405,
      "learning_rate": 6.810810810810811e-06,
      "loss": 1.2186,
      "mean_token_accuracy": 0.6527085661888122,
      "num_tokens": 321351.0,
      "step": 250
    },
    {
      "entropy": 1.234605258703232,
      "epoch": 0.6933333333333334,
      "grad_norm": 0.5501531958580017,
      "learning_rate": 6.270270270270271e-06,
      "loss": 1.2074,
      "mean_token_accuracy": 0.6517517618834973,
      "num_tokens": 334282.0,
      "step": 260
    },
    {
      "entropy": 1.2171380445361137,
      "epoch": 0.72,
      "grad_norm": 0.5207800269126892,
      "learning_rate": 5.729729729729731e-06,
      "loss": 1.212,
      "mean_token_accuracy": 0.6510008379817009,
      "num_tokens": 347108.0,
      "step": 270
    },
    {
      "entropy": 1.1763642460107804,
      "epoch": 0.7466666666666667,
      "grad_norm": 0.5053102970123291,
      "learning_rate": 5.18918918918919e-06,
      "loss": 1.1744,
      "mean_token_accuracy": 0.6574446760118008,
      "num_tokens": 359894.0,
      "step": 280
    },
    {
      "entropy": 1.2101906329393386,
      "epoch": 0.7733333333333333,
      "grad_norm": 0.4792664647102356,
      "learning_rate": 4.6486486486486495e-06,
      "loss": 1.2127,
      "mean_token_accuracy": 0.65442885607481,
      "num_tokens": 372746.0,
      "step": 290
    },
    {
      "entropy": 1.1929027184844017,
      "epoch": 0.8,
      "grad_norm": 0.5656186938285828,
      "learning_rate": 4.108108108108108e-06,
      "loss": 1.1815,
      "mean_token_accuracy": 0.6556121528148651,
      "num_tokens": 385472.0,
      "step": 300
    },
    {
      "entropy": 1.187587819993496,
      "epoch": 0.8266666666666667,
      "grad_norm": 0.5197432041168213,
      "learning_rate": 3.567567567567568e-06,
      "loss": 1.1972,
      "mean_token_accuracy": 0.6531499087810516,
      "num_tokens": 398386.0,
      "step": 310
    },
    {
      "entropy": 1.1810954853892326,
      "epoch": 0.8533333333333334,
      "grad_norm": 0.5143433213233948,
      "learning_rate": 3.0270270270270274e-06,
      "loss": 1.18,
      "mean_token_accuracy": 0.6557211861014366,
      "num_tokens": 411252.0,
      "step": 320
    },
    {
      "entropy": 1.2191567361354827,
      "epoch": 0.88,
      "grad_norm": 0.4793160855770111,
      "learning_rate": 2.4864864864864867e-06,
      "loss": 1.2256,
      "mean_token_accuracy": 0.6478217862546444,
      "num_tokens": 424185.0,
      "step": 330
    },
    {
      "entropy": 1.2220171764492989,
      "epoch": 0.9066666666666666,
      "grad_norm": 0.5613325238227844,
      "learning_rate": 1.945945945945946e-06,
      "loss": 1.1912,
      "mean_token_accuracy": 0.6575871229171752,
      "num_tokens": 437188.0,
      "step": 340
    },
    {
      "entropy": 1.1927517160773278,
      "epoch": 0.9333333333333333,
      "grad_norm": 0.4704723656177521,
      "learning_rate": 1.4054054054054056e-06,
      "loss": 1.1849,
      "mean_token_accuracy": 0.6561981976032257,
      "num_tokens": 449996.0,
      "step": 350
    },
    {
      "entropy": 1.190693587809801,
      "epoch": 0.96,
      "grad_norm": 0.5744921565055847,
      "learning_rate": 8.64864864864865e-07,
      "loss": 1.1868,
      "mean_token_accuracy": 0.6580364957451821,
      "num_tokens": 462917.0,
      "step": 360
    },
    {
      "entropy": 1.1880986839532852,
      "epoch": 0.9866666666666667,
      "grad_norm": 0.5150167942047119,
      "learning_rate": 3.2432432432432436e-07,
      "loss": 1.1759,
      "mean_token_accuracy": 0.6571345932781696,
      "num_tokens": 475686.0,
      "step": 370
    }
  ],
  "logging_steps": 10,
  "max_steps": 375,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.278856023687168e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}