{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0034969620142501203,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000174848100712506,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 8881.3047,
      "step": 1
    },
    {
      "epoch": 0.000174848100712506,
      "eval_loss": NaN,
      "eval_runtime": 685.76,
      "eval_samples_per_second": 14.047,
      "eval_steps_per_second": 7.024,
      "step": 1
    },
    {
      "epoch": 0.000349696201425012,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0005245443021375181,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 4.714,
      "step": 3
    },
    {
      "epoch": 0.000699392402850024,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0008742405035625301,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0008742405035625301,
      "eval_loss": NaN,
      "eval_runtime": 670.617,
      "eval_samples_per_second": 14.364,
      "eval_steps_per_second": 7.183,
      "step": 5
    },
    {
      "epoch": 0.0010490886042750361,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.001223936704987542,
      "grad_norm": NaN,
      "learning_rate": 7e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.001398784805700048,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0015736329064125541,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0017484810071250602,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.0017484810071250602,
      "eval_loss": NaN,
      "eval_runtime": 495.6139,
      "eval_samples_per_second": 19.437,
      "eval_steps_per_second": 9.719,
      "step": 10
    },
    {
      "epoch": 0.001923329107837566,
      "grad_norm": NaN,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.0020981772085500723,
      "grad_norm": NaN,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.002273025309262578,
      "grad_norm": NaN,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.7329,
      "step": 13
    },
    {
      "epoch": 0.002447873409975084,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.00262272151068759,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.00262272151068759,
      "eval_loss": NaN,
      "eval_runtime": 561.3929,
      "eval_samples_per_second": 17.159,
      "eval_steps_per_second": 8.58,
      "step": 15
    },
    {
      "epoch": 0.002797569611400096,
      "grad_norm": NaN,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 938.8581,
      "step": 16
    },
    {
      "epoch": 0.002972417712112602,
      "grad_norm": NaN,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.0031472658128251082,
      "grad_norm": NaN,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.0033221139135376143,
      "grad_norm": NaN,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.0034969620142501203,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.0034969620142501203,
      "eval_loss": NaN,
      "eval_runtime": 437.0956,
      "eval_samples_per_second": 22.039,
      "eval_steps_per_second": 11.02,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.6596794553073664e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}