{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2663115845539281,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0013315579227696406,
      "eval_loss": 11.091023445129395,
      "eval_runtime": 1.6209,
      "eval_samples_per_second": 98.094,
      "eval_steps_per_second": 49.356,
      "step": 1
    },
    {
      "epoch": 0.013315579227696404,
      "grad_norm": 0.8809579014778137,
      "learning_rate": 0.0002,
      "loss": 22.1639,
      "step": 10
    },
    {
      "epoch": 0.02663115845539281,
      "grad_norm": 0.821391224861145,
      "learning_rate": 0.0002,
      "loss": 22.1332,
      "step": 20
    },
    {
      "epoch": 0.03994673768308921,
      "grad_norm": 0.863199770450592,
      "learning_rate": 0.0002,
      "loss": 22.0906,
      "step": 30
    },
    {
      "epoch": 0.05326231691078562,
      "grad_norm": 1.169640064239502,
      "learning_rate": 0.0002,
      "loss": 22.0633,
      "step": 40
    },
    {
      "epoch": 0.06657789613848203,
      "grad_norm": 0.8766728043556213,
      "learning_rate": 0.0002,
      "loss": 22.0108,
      "step": 50
    },
    {
      "epoch": 0.06657789613848203,
      "eval_loss": 10.995157241821289,
      "eval_runtime": 0.4627,
      "eval_samples_per_second": 343.665,
      "eval_steps_per_second": 172.913,
      "step": 50
    },
    {
      "epoch": 0.07989347536617843,
      "grad_norm": 0.7364636063575745,
      "learning_rate": 0.0002,
      "loss": 21.9144,
      "step": 60
    },
    {
      "epoch": 0.09320905459387484,
      "grad_norm": 0.8527082800865173,
      "learning_rate": 0.0002,
      "loss": 21.974,
      "step": 70
    },
    {
      "epoch": 0.10652463382157124,
      "grad_norm": 0.7260386347770691,
      "learning_rate": 0.0002,
      "loss": 22.0004,
      "step": 80
    },
    {
      "epoch": 0.11984021304926765,
      "grad_norm": 0.7889769077301025,
      "learning_rate": 0.0002,
      "loss": 21.9855,
      "step": 90
    },
    {
      "epoch": 0.13315579227696406,
      "grad_norm": 0.8119962215423584,
      "learning_rate": 0.0002,
      "loss": 21.9748,
      "step": 100
    },
    {
      "epoch": 0.13315579227696406,
      "eval_loss": 10.955042839050293,
      "eval_runtime": 0.4877,
      "eval_samples_per_second": 325.998,
      "eval_steps_per_second": 164.024,
      "step": 100
    },
    {
      "epoch": 0.14647137150466044,
      "grad_norm": 0.7654256820678711,
      "learning_rate": 0.0002,
      "loss": 21.9045,
      "step": 110
    },
    {
      "epoch": 0.15978695073235685,
      "grad_norm": 0.7582597732543945,
      "learning_rate": 0.0002,
      "loss": 21.8757,
      "step": 120
    },
    {
      "epoch": 0.17310252996005326,
      "grad_norm": 0.7560115456581116,
      "learning_rate": 0.0002,
      "loss": 21.8915,
      "step": 130
    },
    {
      "epoch": 0.18641810918774968,
      "grad_norm": 0.8035630583763123,
      "learning_rate": 0.0002,
      "loss": 21.8995,
      "step": 140
    },
    {
      "epoch": 0.19973368841544606,
      "grad_norm": 0.9448879957199097,
      "learning_rate": 0.0002,
      "loss": 21.817,
      "step": 150
    },
    {
      "epoch": 0.19973368841544606,
      "eval_loss": 10.934608459472656,
      "eval_runtime": 0.4706,
      "eval_samples_per_second": 337.856,
      "eval_steps_per_second": 169.99,
      "step": 150
    },
    {
      "epoch": 0.21304926764314247,
      "grad_norm": 0.8676323890686035,
      "learning_rate": 0.0002,
      "loss": 21.9072,
      "step": 160
    },
    {
      "epoch": 0.22636484687083888,
      "grad_norm": 0.8595561385154724,
      "learning_rate": 0.0002,
      "loss": 21.9161,
      "step": 170
    },
    {
      "epoch": 0.2396804260985353,
      "grad_norm": 0.8619910478591919,
      "learning_rate": 0.0002,
      "loss": 21.8431,
      "step": 180
    },
    {
      "epoch": 0.2529960053262317,
      "grad_norm": 0.8252401947975159,
      "learning_rate": 0.0002,
      "loss": 21.8738,
      "step": 190
    },
    {
      "epoch": 0.2663115845539281,
      "grad_norm": 0.8227563500404358,
      "learning_rate": 0.0002,
      "loss": 21.8141,
      "step": 200
    },
    {
      "epoch": 0.2663115845539281,
      "eval_loss": 10.927712440490723,
      "eval_runtime": 0.4592,
      "eval_samples_per_second": 346.264,
      "eval_steps_per_second": 174.221,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 179683983360.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}