{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02902757619738752,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005805515239477504,
      "grad_norm": 0.02747248113155365,
      "learning_rate": 1e-05,
      "loss": 10.3776,
      "step": 1
    },
    {
      "epoch": 0.005805515239477504,
      "eval_loss": 10.377151489257812,
      "eval_runtime": 29.442,
      "eval_samples_per_second": 9.884,
      "eval_steps_per_second": 4.959,
      "step": 1
    },
    {
      "epoch": 0.011611030478955007,
      "grad_norm": 0.028352981433272362,
      "learning_rate": 2e-05,
      "loss": 10.3759,
      "step": 2
    },
    {
      "epoch": 0.011611030478955007,
      "eval_loss": 10.377142906188965,
      "eval_runtime": 0.6078,
      "eval_samples_per_second": 478.776,
      "eval_steps_per_second": 240.21,
      "step": 2
    },
    {
      "epoch": 0.01741654571843251,
      "grad_norm": 0.04375547543168068,
      "learning_rate": 3e-05,
      "loss": 10.3773,
      "step": 3
    },
    {
      "epoch": 0.023222060957910014,
      "grad_norm": 0.026691030710935593,
      "learning_rate": 4e-05,
      "loss": 10.3777,
      "step": 4
    },
    {
      "epoch": 0.023222060957910014,
      "eval_loss": 10.377105712890625,
      "eval_runtime": 0.6298,
      "eval_samples_per_second": 462.039,
      "eval_steps_per_second": 231.813,
      "step": 4
    },
    {
      "epoch": 0.02902757619738752,
      "grad_norm": 0.029750756919384003,
      "learning_rate": 5e-05,
      "loss": 10.3789,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 514003599360.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}