{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0017890865719113408,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00019878739687903787,
      "grad_norm": 2.709139585494995,
      "learning_rate": 2e-05,
      "loss": 13.1525,
      "step": 1
    },
    {
      "epoch": 0.00019878739687903787,
      "eval_loss": 3.2820167541503906,
      "eval_runtime": 76.8573,
      "eval_samples_per_second": 27.571,
      "eval_steps_per_second": 13.792,
      "step": 1
    },
    {
      "epoch": 0.00039757479375807575,
      "grad_norm": 2.4468839168548584,
      "learning_rate": 4e-05,
      "loss": 13.7228,
      "step": 2
    },
    {
      "epoch": 0.0005963621906371136,
      "grad_norm": 2.8160054683685303,
      "learning_rate": 6e-05,
      "loss": 14.2335,
      "step": 3
    },
    {
      "epoch": 0.0005963621906371136,
      "eval_loss": 3.278059482574463,
      "eval_runtime": 77.0426,
      "eval_samples_per_second": 27.504,
      "eval_steps_per_second": 13.759,
      "step": 3
    },
    {
      "epoch": 0.0007951495875161515,
      "grad_norm": 2.706402540206909,
      "learning_rate": 8e-05,
      "loss": 12.0832,
      "step": 4
    },
    {
      "epoch": 0.0009939369843951894,
      "grad_norm": 3.3884165287017822,
      "learning_rate": 0.0001,
      "loss": 13.334,
      "step": 5
    },
    {
      "epoch": 0.0011927243812742273,
      "grad_norm": 2.4164562225341797,
      "learning_rate": 0.00012,
      "loss": 13.2106,
      "step": 6
    },
    {
      "epoch": 0.0011927243812742273,
      "eval_loss": 3.2450344562530518,
      "eval_runtime": 77.5961,
      "eval_samples_per_second": 27.308,
      "eval_steps_per_second": 13.66,
      "step": 6
    },
    {
      "epoch": 0.0013915117781532651,
      "grad_norm": 3.4889168739318848,
      "learning_rate": 0.00014,
      "loss": 14.0345,
      "step": 7
    },
    {
      "epoch": 0.001590299175032303,
      "grad_norm": 2.8721933364868164,
      "learning_rate": 0.00016,
      "loss": 13.4382,
      "step": 8
    },
    {
      "epoch": 0.0017890865719113408,
      "grad_norm": 4.49237060546875,
      "learning_rate": 0.00018,
      "loss": 15.2835,
      "step": 9
    },
    {
      "epoch": 0.0017890865719113408,
      "eval_loss": 3.150373935699463,
      "eval_runtime": 77.955,
      "eval_samples_per_second": 27.182,
      "eval_steps_per_second": 13.598,
      "step": 9
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1506578150719488.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}