{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 1,
  "global_step": 4,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.25,
      "grad_norm": 0.8683049082756042,
      "learning_rate": 0.00017071067811865476,
      "loss": 1.2487,
      "step": 1
    },
    {
      "epoch": 0.25,
      "eval_loss": 1.2632912397384644,
      "eval_runtime": 24.3805,
      "eval_samples_per_second": 23.913,
      "eval_steps_per_second": 2.994,
      "step": 1
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.8950231671333313,
      "learning_rate": 0.0001,
      "loss": 1.195,
      "step": 2
    },
    {
      "epoch": 0.5,
      "eval_loss": 1.1117289066314697,
      "eval_runtime": 24.4547,
      "eval_samples_per_second": 23.84,
      "eval_steps_per_second": 2.985,
      "step": 2
    },
    {
      "epoch": 0.75,
      "grad_norm": 1.0543603897094727,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 1.0191,
      "step": 3
    },
    {
      "epoch": 0.75,
      "eval_loss": 1.0158419609069824,
      "eval_runtime": 24.6106,
      "eval_samples_per_second": 23.689,
      "eval_steps_per_second": 2.966,
      "step": 3
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.264427900314331,
      "learning_rate": 0.0,
      "loss": 0.9721,
      "step": 4
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.9845411777496338,
      "eval_runtime": 24.6993,
      "eval_samples_per_second": 23.604,
      "eval_steps_per_second": 2.956,
      "step": 4
    }
  ],
  "logging_steps": 1,
  "max_steps": 4,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1181203650576384.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}