{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.014044943820224719,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0028089887640449437,
      "grad_norm": 0.14378267526626587,
      "learning_rate": 1e-05,
      "loss": 11.7594,
      "step": 1
    },
    {
      "epoch": 0.0028089887640449437,
      "eval_loss": 11.740790367126465,
      "eval_runtime": 26.7813,
      "eval_samples_per_second": 22.404,
      "eval_steps_per_second": 11.202,
      "step": 1
    },
    {
      "epoch": 0.0056179775280898875,
      "grad_norm": 0.14740274846553802,
      "learning_rate": 2e-05,
      "loss": 11.7645,
      "step": 2
    },
    {
      "epoch": 0.0056179775280898875,
      "eval_loss": 11.740753173828125,
      "eval_runtime": 2.2853,
      "eval_samples_per_second": 262.548,
      "eval_steps_per_second": 131.274,
      "step": 2
    },
    {
      "epoch": 0.008426966292134831,
      "grad_norm": 0.14215214550495148,
      "learning_rate": 3e-05,
      "loss": 11.7433,
      "step": 3
    },
    {
      "epoch": 0.011235955056179775,
      "grad_norm": 0.14502564072608948,
      "learning_rate": 4e-05,
      "loss": 11.7504,
      "step": 4
    },
    {
      "epoch": 0.011235955056179775,
      "eval_loss": 11.74059772491455,
      "eval_runtime": 2.2997,
      "eval_samples_per_second": 260.9,
      "eval_steps_per_second": 130.45,
      "step": 4
    },
    {
      "epoch": 0.014044943820224719,
      "grad_norm": 0.11788108199834824,
      "learning_rate": 5e-05,
      "loss": 11.7459,
      "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": 1028301225984.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}