{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "aux_loss": 2.3257370829582213,
      "entropy": 3.6007017314434053,
      "epoch": 0.04,
      "grad_norm": 1.0625,
      "learning_rate": 1.9280000000000002e-05,
      "loss": 3.8956069946289062,
      "mean_token_accuracy": 0.3586781073361635,
      "num_tokens": 72397.0,
      "step": 10
    },
    {
      "aux_loss": 2.3277345478534697,
      "entropy": 3.6272001445293425,
      "epoch": 0.08,
      "grad_norm": 1.0625,
      "learning_rate": 1.8480000000000003e-05,
      "loss": 3.896469497680664,
      "mean_token_accuracy": 0.3564587336033583,
      "num_tokens": 143657.0,
      "step": 20
    },
    {
      "aux_loss": 2.323074048757553,
      "entropy": 3.601874440908432,
      "epoch": 0.12,
      "grad_norm": 1.0390625,
      "learning_rate": 1.768e-05,
      "loss": 3.902561569213867,
      "mean_token_accuracy": 0.3605616968125105,
      "num_tokens": 215509.0,
      "step": 30
    },
    {
      "aux_loss": 2.3261504590511324,
      "entropy": 3.6270964324474333,
      "epoch": 0.16,
      "grad_norm": 1.09375,
      "learning_rate": 1.688e-05,
      "loss": 3.8741905212402346,
      "mean_token_accuracy": 0.3614043775945902,
      "num_tokens": 288789.0,
      "step": 40
    },
    {
      "aux_loss": 2.324697870016098,
      "entropy": 3.5004548013210295,
      "epoch": 0.2,
      "grad_norm": 0.99609375,
      "learning_rate": 1.6080000000000002e-05,
      "loss": 3.795322799682617,
      "mean_token_accuracy": 0.37013124153017996,
      "num_tokens": 361289.0,
      "step": 50
    },
    {
      "aux_loss": 2.3249743819236754,
      "entropy": 3.499809369444847,
      "epoch": 0.24,
      "grad_norm": 0.9921875,
      "learning_rate": 1.5280000000000003e-05,
      "loss": 3.755328369140625,
      "mean_token_accuracy": 0.37386555671691896,
      "num_tokens": 433139.0,
      "step": 60
    },
    {
      "aux_loss": 2.324633425474167,
      "entropy": 3.6745675444602965,
      "epoch": 0.28,
      "grad_norm": 0.9609375,
      "learning_rate": 1.448e-05,
      "loss": 3.902497100830078,
      "mean_token_accuracy": 0.36646418645977974,
      "num_tokens": 504919.0,
      "step": 70
    },
    {
      "aux_loss": 2.3186131000518797,
      "entropy": 3.470395928621292,
      "epoch": 0.32,
      "grad_norm": 0.9921875,
      "learning_rate": 1.3680000000000003e-05,
      "loss": 3.723850631713867,
      "mean_token_accuracy": 0.3796745929867029,
      "num_tokens": 576593.0,
      "step": 80
    },
    {
      "aux_loss": 2.3274434208869934,
      "entropy": 3.6475940525531767,
      "epoch": 0.36,
      "grad_norm": 0.94921875,
      "learning_rate": 1.2880000000000002e-05,
      "loss": 3.898761749267578,
      "mean_token_accuracy": 0.3605402667075396,
      "num_tokens": 650395.0,
      "step": 90
    },
    {
      "aux_loss": 2.3328470826148986,
      "entropy": 3.5895772576332092,
      "epoch": 0.4,
      "grad_norm": 1.125,
      "learning_rate": 1.2080000000000001e-05,
      "loss": 3.7831195831298827,
      "mean_token_accuracy": 0.3730145484209061,
      "num_tokens": 720132.0,
      "step": 100
    },
    {
      "aux_loss": 2.331581395864487,
      "entropy": 3.670157164335251,
      "epoch": 0.44,
      "grad_norm": 1.03125,
      "learning_rate": 1.128e-05,
      "loss": 3.955718231201172,
      "mean_token_accuracy": 0.35614234730601313,
      "num_tokens": 791175.0,
      "step": 110
    },
    {
      "aux_loss": 2.3278864681720735,
      "entropy": 3.564240163564682,
      "epoch": 0.48,
      "grad_norm": 1.0078125,
      "learning_rate": 1.0480000000000001e-05,
      "loss": 3.7921863555908204,
      "mean_token_accuracy": 0.37363966181874275,
      "num_tokens": 864007.0,
      "step": 120
    },
    {
      "aux_loss": 2.333659642934799,
      "entropy": 3.6451989471912385,
      "epoch": 0.52,
      "grad_norm": 0.95703125,
      "learning_rate": 9.68e-06,
      "loss": 3.894023132324219,
      "mean_token_accuracy": 0.35798243805766106,
      "num_tokens": 935475.0,
      "step": 130
    },
    {
      "aux_loss": 2.3140768826007845,
      "entropy": 3.50389506816864,
      "epoch": 0.56,
      "grad_norm": 1.0703125,
      "learning_rate": 8.880000000000001e-06,
      "loss": 3.7427852630615233,
      "mean_token_accuracy": 0.38606042340397834,
      "num_tokens": 1002776.0,
      "step": 140
    },
    {
      "aux_loss": 2.323524034023285,
      "entropy": 3.62218790948391,
      "epoch": 0.6,
      "grad_norm": 1.0078125,
      "learning_rate": 8.08e-06,
      "loss": 3.8935062408447267,
      "mean_token_accuracy": 0.36692074611783027,
      "num_tokens": 1074485.0,
      "step": 150
    },
    {
      "aux_loss": 2.319421482086182,
      "entropy": 3.6522460520267486,
      "epoch": 0.64,
      "grad_norm": 1.0546875,
      "learning_rate": 7.280000000000001e-06,
      "loss": 3.938425064086914,
      "mean_token_accuracy": 0.3640777923166752,
      "num_tokens": 1148295.0,
      "step": 160
    },
    {
      "aux_loss": 2.3238328874111174,
      "entropy": 3.635464870929718,
      "epoch": 0.68,
      "grad_norm": 0.9765625,
      "learning_rate": 6.480000000000001e-06,
      "loss": 3.839573287963867,
      "mean_token_accuracy": 0.3715536307543516,
      "num_tokens": 1220134.0,
      "step": 170
    },
    {
      "aux_loss": 2.3195456326007844,
      "entropy": 3.4972031474113465,
      "epoch": 0.72,
      "grad_norm": 0.921875,
      "learning_rate": 5.68e-06,
      "loss": 3.700027084350586,
      "mean_token_accuracy": 0.37758239097893237,
      "num_tokens": 1291904.0,
      "step": 180
    },
    {
      "aux_loss": 2.331765002012253,
      "entropy": 3.6483884513378144,
      "epoch": 0.76,
      "grad_norm": 0.8984375,
      "learning_rate": 4.880000000000001e-06,
      "loss": 3.873792266845703,
      "mean_token_accuracy": 0.36337695084512234,
      "num_tokens": 1363374.0,
      "step": 190
    },
    {
      "aux_loss": 2.3272350072860717,
      "entropy": 3.674150836467743,
      "epoch": 0.8,
      "grad_norm": 0.9609375,
      "learning_rate": 4.08e-06,
      "loss": 3.885345458984375,
      "mean_token_accuracy": 0.3636812623590231,
      "num_tokens": 1433716.0,
      "step": 200
    },
    {
      "aux_loss": 2.32773614525795,
      "entropy": 3.635636830329895,
      "epoch": 0.84,
      "grad_norm": 1.0078125,
      "learning_rate": 3.2800000000000004e-06,
      "loss": 3.8587207794189453,
      "mean_token_accuracy": 0.36572874560952184,
      "num_tokens": 1506681.0,
      "step": 210
    },
    {
      "aux_loss": 2.325718504190445,
      "entropy": 3.5308443903923035,
      "epoch": 0.88,
      "grad_norm": 0.95703125,
      "learning_rate": 2.4800000000000004e-06,
      "loss": 3.72619514465332,
      "mean_token_accuracy": 0.37508156448602675,
      "num_tokens": 1575868.0,
      "step": 220
    },
    {
      "aux_loss": 2.3259211778640747,
      "entropy": 3.433101177215576,
      "epoch": 0.92,
      "grad_norm": 0.9140625,
      "learning_rate": 1.6800000000000002e-06,
      "loss": 3.593972015380859,
      "mean_token_accuracy": 0.3888819687068462,
      "num_tokens": 1648038.0,
      "step": 230
    },
    {
      "aux_loss": 2.3294626414775848,
      "entropy": 3.597357761859894,
      "epoch": 0.96,
      "grad_norm": 0.9296875,
      "learning_rate": 8.8e-07,
      "loss": 3.8016372680664063,
      "mean_token_accuracy": 0.36985846906900405,
      "num_tokens": 1720626.0,
      "step": 240
    },
    {
      "aux_loss": 2.319813519716263,
      "entropy": 3.5566279590129852,
      "epoch": 1.0,
      "grad_norm": 1.0234375,
      "learning_rate": 8e-08,
      "loss": 3.757618713378906,
      "mean_token_accuracy": 0.3740091536194086,
      "num_tokens": 1788925.0,
      "step": 250
    }
  ],
  "logging_steps": 10,
  "max_steps": 250,
  "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": 6391876233437184.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}