{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0026003105926541226,
  "eval_steps": 2,
  "global_step": 18,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001444616995918957,
      "grad_norm": 29.741775512695312,
      "learning_rate": 1e-05,
      "loss": 21.916,
      "step": 1
    },
    {
      "epoch": 0.0001444616995918957,
      "eval_loss": 4.278669834136963,
      "eval_runtime": 411.0727,
      "eval_samples_per_second": 7.091,
      "eval_steps_per_second": 3.547,
      "step": 1
    },
    {
      "epoch": 0.0002889233991837914,
      "grad_norm": 28.80156707763672,
      "learning_rate": 2e-05,
      "loss": 18.1093,
      "step": 2
    },
    {
      "epoch": 0.0002889233991837914,
      "eval_loss": 4.272582054138184,
      "eval_runtime": 412.4395,
      "eval_samples_per_second": 7.068,
      "eval_steps_per_second": 3.535,
      "step": 2
    },
    {
      "epoch": 0.0004333850987756871,
      "grad_norm": 27.65138816833496,
      "learning_rate": 3e-05,
      "loss": 11.7399,
      "step": 3
    },
    {
      "epoch": 0.0005778467983675828,
      "grad_norm": 33.123443603515625,
      "learning_rate": 4e-05,
      "loss": 15.397,
      "step": 4
    },
    {
      "epoch": 0.0005778467983675828,
      "eval_loss": 4.1736063957214355,
      "eval_runtime": 412.3727,
      "eval_samples_per_second": 7.069,
      "eval_steps_per_second": 3.536,
      "step": 4
    },
    {
      "epoch": 0.0007223084979594785,
      "grad_norm": 48.433624267578125,
      "learning_rate": 5e-05,
      "loss": 16.1812,
      "step": 5
    },
    {
      "epoch": 0.0008667701975513742,
      "grad_norm": 30.907163619995117,
      "learning_rate": 6e-05,
      "loss": 13.8531,
      "step": 6
    },
    {
      "epoch": 0.0008667701975513742,
      "eval_loss": 3.9675278663635254,
      "eval_runtime": 412.3112,
      "eval_samples_per_second": 7.07,
      "eval_steps_per_second": 3.536,
      "step": 6
    },
    {
      "epoch": 0.0010112318971432699,
      "grad_norm": 25.792160034179688,
      "learning_rate": 7e-05,
      "loss": 22.1435,
      "step": 7
    },
    {
      "epoch": 0.0011556935967351656,
      "grad_norm": 22.48407745361328,
      "learning_rate": 8e-05,
      "loss": 17.8129,
      "step": 8
    },
    {
      "epoch": 0.0011556935967351656,
      "eval_loss": 3.734724998474121,
      "eval_runtime": 412.2645,
      "eval_samples_per_second": 7.071,
      "eval_steps_per_second": 3.537,
      "step": 8
    },
    {
      "epoch": 0.0013001552963270613,
      "grad_norm": 21.80668830871582,
      "learning_rate": 9e-05,
      "loss": 13.4756,
      "step": 9
    },
    {
      "epoch": 0.001444616995918957,
      "grad_norm": 18.533721923828125,
      "learning_rate": 0.0001,
      "loss": 12.6123,
      "step": 10
    },
    {
      "epoch": 0.001444616995918957,
      "eval_loss": 3.4023940563201904,
      "eval_runtime": 412.1148,
      "eval_samples_per_second": 7.073,
      "eval_steps_per_second": 3.538,
      "step": 10
    },
    {
      "epoch": 0.0015890786955108527,
      "grad_norm": 12.594943046569824,
      "learning_rate": 9.755282581475769e-05,
      "loss": 9.2502,
      "step": 11
    },
    {
      "epoch": 0.0017335403951027485,
      "grad_norm": 28.27761459350586,
      "learning_rate": 9.045084971874738e-05,
      "loss": 14.809,
      "step": 12
    },
    {
      "epoch": 0.0017335403951027485,
      "eval_loss": 2.9927456378936768,
      "eval_runtime": 412.4787,
      "eval_samples_per_second": 7.067,
      "eval_steps_per_second": 3.535,
      "step": 12
    },
    {
      "epoch": 0.001878002094694644,
      "grad_norm": 24.574901580810547,
      "learning_rate": 7.938926261462366e-05,
      "loss": 13.8176,
      "step": 13
    },
    {
      "epoch": 0.0020224637942865397,
      "grad_norm": 49.8048210144043,
      "learning_rate": 6.545084971874738e-05,
      "loss": 16.2677,
      "step": 14
    },
    {
      "epoch": 0.0020224637942865397,
      "eval_loss": 2.5962870121002197,
      "eval_runtime": 412.0906,
      "eval_samples_per_second": 7.074,
      "eval_steps_per_second": 3.538,
      "step": 14
    },
    {
      "epoch": 0.0021669254938784356,
      "grad_norm": 12.992769241333008,
      "learning_rate": 5e-05,
      "loss": 8.358,
      "step": 15
    },
    {
      "epoch": 0.002311387193470331,
      "grad_norm": 10.932060241699219,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 9.3938,
      "step": 16
    },
    {
      "epoch": 0.002311387193470331,
      "eval_loss": 2.366903066635132,
      "eval_runtime": 412.0962,
      "eval_samples_per_second": 7.074,
      "eval_steps_per_second": 3.538,
      "step": 16
    },
    {
      "epoch": 0.002455848893062227,
      "grad_norm": 34.9987907409668,
      "learning_rate": 2.061073738537635e-05,
      "loss": 12.4402,
      "step": 17
    },
    {
      "epoch": 0.0026003105926541226,
      "grad_norm": 39.801536560058594,
      "learning_rate": 9.549150281252633e-06,
      "loss": 9.872,
      "step": 18
    },
    {
      "epoch": 0.0026003105926541226,
      "eval_loss": 2.25581955909729,
      "eval_runtime": 412.3441,
      "eval_samples_per_second": 7.069,
      "eval_steps_per_second": 3.536,
      "step": 18
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5881181799186432.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}