{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0003389859236095221,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.3898592360952214e-05,
      "grad_norm": 1.1320422887802124,
      "learning_rate": 2e-05,
      "loss": 4.9511,
      "step": 1
    },
    {
      "epoch": 3.3898592360952214e-05,
      "eval_loss": 1.405200719833374,
      "eval_runtime": 721.5461,
      "eval_samples_per_second": 17.214,
      "eval_steps_per_second": 8.608,
      "step": 1
    },
    {
      "epoch": 6.779718472190443e-05,
      "grad_norm": 1.0682722330093384,
      "learning_rate": 4e-05,
      "loss": 4.6739,
      "step": 2
    },
    {
      "epoch": 0.00010169577708285663,
      "grad_norm": 0.8649938106536865,
      "learning_rate": 6e-05,
      "loss": 5.513,
      "step": 3
    },
    {
      "epoch": 0.00010169577708285663,
      "eval_loss": 1.4037784337997437,
      "eval_runtime": 721.5276,
      "eval_samples_per_second": 17.215,
      "eval_steps_per_second": 8.608,
      "step": 3
    },
    {
      "epoch": 0.00013559436944380885,
      "grad_norm": 1.0291898250579834,
      "learning_rate": 8e-05,
      "loss": 5.342,
      "step": 4
    },
    {
      "epoch": 0.00016949296180476106,
      "grad_norm": 0.9754419326782227,
      "learning_rate": 0.0001,
      "loss": 5.0035,
      "step": 5
    },
    {
      "epoch": 0.00020339155416571327,
      "grad_norm": 1.2995450496673584,
      "learning_rate": 0.00012,
      "loss": 5.8586,
      "step": 6
    },
    {
      "epoch": 0.00020339155416571327,
      "eval_loss": 1.3888883590698242,
      "eval_runtime": 721.5365,
      "eval_samples_per_second": 17.215,
      "eval_steps_per_second": 8.608,
      "step": 6
    },
    {
      "epoch": 0.00023729014652666548,
      "grad_norm": 1.5968364477157593,
      "learning_rate": 0.00014,
      "loss": 5.8282,
      "step": 7
    },
    {
      "epoch": 0.0002711887388876177,
      "grad_norm": 1.8604395389556885,
      "learning_rate": 0.00016,
      "loss": 6.7412,
      "step": 8
    },
    {
      "epoch": 0.0003050873312485699,
      "grad_norm": 5.173710346221924,
      "learning_rate": 0.00018,
      "loss": 5.3501,
      "step": 9
    },
    {
      "epoch": 0.0003050873312485699,
      "eval_loss": 1.2827191352844238,
      "eval_runtime": 720.7405,
      "eval_samples_per_second": 17.234,
      "eval_steps_per_second": 8.618,
      "step": 9
    },
    {
      "epoch": 0.0003389859236095221,
      "grad_norm": 2.9018757343292236,
      "learning_rate": 0.0002,
      "loss": 4.9559,
      "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": 3397367365632000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}