{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.026975991367682764,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005395198273536552,
      "eval_loss": 2.106476306915283,
      "eval_runtime": 48.6094,
      "eval_samples_per_second": 16.067,
      "eval_steps_per_second": 8.044,
      "step": 1
    },
    {
      "epoch": 0.002697599136768276,
      "grad_norm": 6.120480537414551,
      "learning_rate": 5e-05,
      "loss": 8.6306,
      "step": 5
    },
    {
      "epoch": 0.005395198273536552,
      "grad_norm": 6.749674320220947,
      "learning_rate": 0.0001,
      "loss": 8.3859,
      "step": 10
    },
    {
      "epoch": 0.005395198273536552,
      "eval_loss": 2.0521886348724365,
      "eval_runtime": 48.7895,
      "eval_samples_per_second": 16.008,
      "eval_steps_per_second": 8.014,
      "step": 10
    },
    {
      "epoch": 0.008092797410304829,
      "grad_norm": 8.042634010314941,
      "learning_rate": 9.619397662556435e-05,
      "loss": 8.0356,
      "step": 15
    },
    {
      "epoch": 0.010790396547073105,
      "grad_norm": 8.283008575439453,
      "learning_rate": 8.535533905932738e-05,
      "loss": 8.5589,
      "step": 20
    },
    {
      "epoch": 0.010790396547073105,
      "eval_loss": 2.0524401664733887,
      "eval_runtime": 48.9662,
      "eval_samples_per_second": 15.95,
      "eval_steps_per_second": 7.985,
      "step": 20
    },
    {
      "epoch": 0.013487995683841382,
      "grad_norm": 6.977921009063721,
      "learning_rate": 6.91341716182545e-05,
      "loss": 8.3495,
      "step": 25
    },
    {
      "epoch": 0.016185594820609658,
      "grad_norm": 6.890524387359619,
      "learning_rate": 5e-05,
      "loss": 8.221,
      "step": 30
    },
    {
      "epoch": 0.016185594820609658,
      "eval_loss": 2.0468971729278564,
      "eval_runtime": 49.111,
      "eval_samples_per_second": 15.903,
      "eval_steps_per_second": 7.962,
      "step": 30
    },
    {
      "epoch": 0.018883193957377933,
      "grad_norm": 8.00633430480957,
      "learning_rate": 3.086582838174551e-05,
      "loss": 7.7307,
      "step": 35
    },
    {
      "epoch": 0.02158079309414621,
      "grad_norm": 6.9984517097473145,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 8.3198,
      "step": 40
    },
    {
      "epoch": 0.02158079309414621,
      "eval_loss": 2.045804738998413,
      "eval_runtime": 49.2119,
      "eval_samples_per_second": 15.87,
      "eval_steps_per_second": 7.945,
      "step": 40
    },
    {
      "epoch": 0.024278392230914485,
      "grad_norm": 7.2769575119018555,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 8.3315,
      "step": 45
    },
    {
      "epoch": 0.026975991367682764,
      "grad_norm": 6.36322546005249,
      "learning_rate": 0.0,
      "loss": 7.8378,
      "step": 50
    },
    {
      "epoch": 0.026975991367682764,
      "eval_loss": 2.045538902282715,
      "eval_runtime": 49.0903,
      "eval_samples_per_second": 15.909,
      "eval_steps_per_second": 7.965,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8850982419038208.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}