{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.425531914893617,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0851063829787234,
      "grad_norm": 1.443141222000122,
      "learning_rate": 1e-05,
      "loss": 3.9559,
      "step": 1
    },
    {
      "epoch": 0.0851063829787234,
      "eval_loss": 3.7380523681640625,
      "eval_runtime": 26.962,
      "eval_samples_per_second": 0.742,
      "eval_steps_per_second": 0.371,
      "step": 1
    },
    {
      "epoch": 0.1702127659574468,
      "grad_norm": 1.3870996236801147,
      "learning_rate": 2e-05,
      "loss": 3.8578,
      "step": 2
    },
    {
      "epoch": 0.1702127659574468,
      "eval_loss": 3.7254700660705566,
      "eval_runtime": 0.1558,
      "eval_samples_per_second": 128.397,
      "eval_steps_per_second": 64.198,
      "step": 2
    },
    {
      "epoch": 0.2553191489361702,
      "grad_norm": 1.3563982248306274,
      "learning_rate": 3e-05,
      "loss": 3.8848,
      "step": 3
    },
    {
      "epoch": 0.3404255319148936,
      "grad_norm": 1.3520137071609497,
      "learning_rate": 4e-05,
      "loss": 3.567,
      "step": 4
    },
    {
      "epoch": 0.3404255319148936,
      "eval_loss": 3.7118256092071533,
      "eval_runtime": 0.1541,
      "eval_samples_per_second": 129.788,
      "eval_steps_per_second": 64.894,
      "step": 4
    },
    {
      "epoch": 0.425531914893617,
      "grad_norm": 1.3593170642852783,
      "learning_rate": 5e-05,
      "loss": 3.7083,
      "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": 481091030876160.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}