{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3755868544600939,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07511737089201878,
      "grad_norm": 24.863981246948242,
      "learning_rate": 1e-05,
      "loss": 32657.6465,
      "step": 1
    },
    {
      "epoch": 0.07511737089201878,
      "eval_loss": NaN,
      "eval_runtime": 14.6184,
      "eval_samples_per_second": 1.573,
      "eval_steps_per_second": 0.821,
      "step": 1
    },
    {
      "epoch": 0.15023474178403756,
      "grad_norm": 18.32345962524414,
      "learning_rate": 2e-05,
      "loss": 82271.3047,
      "step": 2
    },
    {
      "epoch": 0.15023474178403756,
      "eval_loss": NaN,
      "eval_runtime": 0.8556,
      "eval_samples_per_second": 26.881,
      "eval_steps_per_second": 14.025,
      "step": 2
    },
    {
      "epoch": 0.22535211267605634,
      "grad_norm": 20.61446762084961,
      "learning_rate": 3e-05,
      "loss": 15297.4092,
      "step": 3
    },
    {
      "epoch": 0.3004694835680751,
      "grad_norm": 16.823139190673828,
      "learning_rate": 4e-05,
      "loss": 96.5391,
      "step": 4
    },
    {
      "epoch": 0.3004694835680751,
      "eval_loss": NaN,
      "eval_runtime": 0.8477,
      "eval_samples_per_second": 27.132,
      "eval_steps_per_second": 14.156,
      "step": 4
    },
    {
      "epoch": 0.3755868544600939,
      "grad_norm": 23.5028076171875,
      "learning_rate": 5e-05,
      "loss": 1188.2882,
      "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": 6794734731264000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}