{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.007802594362625573,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0015605188725251145,
      "grad_norm": 0.2755284607410431,
      "learning_rate": 1e-05,
      "loss": 0.7998,
      "step": 1
    },
    {
      "epoch": 0.0015605188725251145,
      "eval_loss": 0.840276300907135,
      "eval_runtime": 199.04,
      "eval_samples_per_second": 5.426,
      "eval_steps_per_second": 2.713,
      "step": 1
    },
    {
      "epoch": 0.003121037745050229,
      "grad_norm": 0.29902082681655884,
      "learning_rate": 2e-05,
      "loss": 0.8871,
      "step": 2
    },
    {
      "epoch": 0.003121037745050229,
      "eval_loss": 0.8389456272125244,
      "eval_runtime": 146.8316,
      "eval_samples_per_second": 7.355,
      "eval_steps_per_second": 3.678,
      "step": 2
    },
    {
      "epoch": 0.004681556617575344,
      "grad_norm": 0.28083354234695435,
      "learning_rate": 3e-05,
      "loss": 0.8617,
      "step": 3
    },
    {
      "epoch": 0.006242075490100458,
      "grad_norm": 0.27328819036483765,
      "learning_rate": 4e-05,
      "loss": 0.7454,
      "step": 4
    },
    {
      "epoch": 0.006242075490100458,
      "eval_loss": 0.8350617289543152,
      "eval_runtime": 146.7347,
      "eval_samples_per_second": 7.36,
      "eval_steps_per_second": 3.68,
      "step": 4
    },
    {
      "epoch": 0.007802594362625573,
      "grad_norm": 0.2871127426624298,
      "learning_rate": 5e-05,
      "loss": 0.7878,
      "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": 7166592811008000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}