{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0574345883854499,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0019144862795149968,
      "eval_loss": NaN,
      "eval_runtime": 8.5946,
      "eval_samples_per_second": 19.198,
      "eval_steps_per_second": 9.657,
      "step": 1
    },
    {
      "epoch": 0.00574345883854499,
      "grad_norm": NaN,
      "learning_rate": 8.999999999999999e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.01148691767708998,
      "grad_norm": NaN,
      "learning_rate": 0.00017999999999999998,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.015315890236119975,
      "eval_loss": NaN,
      "eval_runtime": 7.5352,
      "eval_samples_per_second": 21.897,
      "eval_steps_per_second": 11.015,
      "step": 8
    },
    {
      "epoch": 0.01723037651563497,
      "grad_norm": NaN,
      "learning_rate": 0.00027,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.02297383535417996,
      "grad_norm": NaN,
      "learning_rate": 0.00029265847744427303,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.02871729419272495,
      "grad_norm": NaN,
      "learning_rate": 0.00025606601717798207,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.03063178047223995,
      "eval_loss": NaN,
      "eval_runtime": 7.5649,
      "eval_samples_per_second": 21.811,
      "eval_steps_per_second": 10.972,
      "step": 16
    },
    {
      "epoch": 0.03446075303126994,
      "grad_norm": NaN,
      "learning_rate": 0.0001963525491562421,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.04020421186981493,
      "grad_norm": NaN,
      "learning_rate": 0.00012653483024396533,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.04594767070835992,
      "grad_norm": NaN,
      "learning_rate": 6.183221215612904e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.04594767070835992,
      "eval_loss": NaN,
      "eval_runtime": 7.5799,
      "eval_samples_per_second": 21.768,
      "eval_steps_per_second": 10.95,
      "step": 24
    },
    {
      "epoch": 0.05169112954690491,
      "grad_norm": NaN,
      "learning_rate": 1.634902137174483e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.0574345883854499,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3144198295388160.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}