{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5063291139240507,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.10126582278481013,
      "grad_norm": 0.6021655201911926,
      "learning_rate": 1e-05,
      "loss": 1.3774,
      "step": 1
    },
    {
      "epoch": 0.10126582278481013,
      "eval_loss": 1.470438838005066,
      "eval_runtime": 100.2272,
      "eval_samples_per_second": 0.17,
      "eval_steps_per_second": 0.09,
      "step": 1
    },
    {
      "epoch": 0.20253164556962025,
      "grad_norm": 0.6656573414802551,
      "learning_rate": 2e-05,
      "loss": 1.3478,
      "step": 2
    },
    {
      "epoch": 0.20253164556962025,
      "eval_loss": 1.4521021842956543,
      "eval_runtime": 2.9067,
      "eval_samples_per_second": 5.848,
      "eval_steps_per_second": 3.096,
      "step": 2
    },
    {
      "epoch": 0.3037974683544304,
      "grad_norm": 0.5850149989128113,
      "learning_rate": 3e-05,
      "loss": 1.475,
      "step": 3
    },
    {
      "epoch": 0.4050632911392405,
      "grad_norm": 0.6346437335014343,
      "learning_rate": 4e-05,
      "loss": 1.364,
      "step": 4
    },
    {
      "epoch": 0.4050632911392405,
      "eval_loss": 1.430355429649353,
      "eval_runtime": 2.9191,
      "eval_samples_per_second": 5.824,
      "eval_steps_per_second": 3.083,
      "step": 4
    },
    {
      "epoch": 0.5063291139240507,
      "grad_norm": 0.5263267755508423,
      "learning_rate": 5e-05,
      "loss": 1.3381,
      "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": 3485272092180480.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}