{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0013505756828848298,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00013505756828848295,
      "grad_norm": 1.331936240196228,
      "learning_rate": 2e-05,
      "loss": 1.0563,
      "step": 1
    },
    {
      "epoch": 0.00013505756828848295,
      "eval_loss": NaN,
      "eval_runtime": 339.5402,
      "eval_samples_per_second": 36.726,
      "eval_steps_per_second": 4.592,
      "step": 1
    },
    {
      "epoch": 0.0002701151365769659,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 1.1346,
      "step": 2
    },
    {
      "epoch": 0.0004051727048654489,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 1.2151,
      "step": 3
    },
    {
      "epoch": 0.0004051727048654489,
      "eval_loss": NaN,
      "eval_runtime": 339.3066,
      "eval_samples_per_second": 36.751,
      "eval_steps_per_second": 4.595,
      "step": 3
    },
    {
      "epoch": 0.0005402302731539318,
      "grad_norm": 1.0178911685943604,
      "learning_rate": 4e-05,
      "loss": 1.1578,
      "step": 4
    },
    {
      "epoch": 0.0006752878414424149,
      "grad_norm": 0.928001880645752,
      "learning_rate": 6e-05,
      "loss": 0.9478,
      "step": 5
    },
    {
      "epoch": 0.0008103454097308978,
      "grad_norm": 0.6421825885772705,
      "learning_rate": 8e-05,
      "loss": 0.9741,
      "step": 6
    },
    {
      "epoch": 0.0008103454097308978,
      "eval_loss": NaN,
      "eval_runtime": 339.2941,
      "eval_samples_per_second": 36.753,
      "eval_steps_per_second": 4.595,
      "step": 6
    },
    {
      "epoch": 0.0009454029780193808,
      "grad_norm": 0.6331295371055603,
      "learning_rate": 0.0001,
      "loss": 1.0673,
      "step": 7
    },
    {
      "epoch": 0.0010804605463078636,
      "grad_norm": 0.8464885950088501,
      "learning_rate": 0.00012,
      "loss": 1.0411,
      "step": 8
    },
    {
      "epoch": 0.0012155181145963466,
      "grad_norm": 0.6393115520477295,
      "learning_rate": 0.00014,
      "loss": 0.9711,
      "step": 9
    },
    {
      "epoch": 0.0012155181145963466,
      "eval_loss": NaN,
      "eval_runtime": 339.3142,
      "eval_samples_per_second": 36.751,
      "eval_steps_per_second": 4.595,
      "step": 9
    },
    {
      "epoch": 0.0013505756828848298,
      "grad_norm": 0.5168577432632446,
      "learning_rate": 0.00016,
      "loss": 1.0371,
      "step": 10
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.935098268483584e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}