{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07401924500370097,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014803849000740192,
      "eval_loss": 10.37421703338623,
      "eval_runtime": 1.9912,
      "eval_samples_per_second": 143.126,
      "eval_steps_per_second": 71.814,
      "step": 1
    },
    {
      "epoch": 0.007401924500370096,
      "grad_norm": 0.02240617945790291,
      "learning_rate": 5e-05,
      "loss": 10.3744,
      "step": 5
    },
    {
      "epoch": 0.014803849000740192,
      "grad_norm": 0.027036666870117188,
      "learning_rate": 0.0001,
      "loss": 10.3739,
      "step": 10
    },
    {
      "epoch": 0.014803849000740192,
      "eval_loss": 10.374021530151367,
      "eval_runtime": 2.0314,
      "eval_samples_per_second": 140.297,
      "eval_steps_per_second": 70.395,
      "step": 10
    },
    {
      "epoch": 0.02220577350111029,
      "grad_norm": 0.024142151698470116,
      "learning_rate": 9.619397662556435e-05,
      "loss": 10.3732,
      "step": 15
    },
    {
      "epoch": 0.029607698001480384,
      "grad_norm": 0.020294418558478355,
      "learning_rate": 8.535533905932738e-05,
      "loss": 10.3749,
      "step": 20
    },
    {
      "epoch": 0.029607698001480384,
      "eval_loss": 10.373614311218262,
      "eval_runtime": 2.087,
      "eval_samples_per_second": 136.562,
      "eval_steps_per_second": 68.52,
      "step": 20
    },
    {
      "epoch": 0.037009622501850484,
      "grad_norm": 0.020632833242416382,
      "learning_rate": 6.91341716182545e-05,
      "loss": 10.3731,
      "step": 25
    },
    {
      "epoch": 0.04441154700222058,
      "grad_norm": 0.02504877932369709,
      "learning_rate": 5e-05,
      "loss": 10.3723,
      "step": 30
    },
    {
      "epoch": 0.04441154700222058,
      "eval_loss": 10.373309135437012,
      "eval_runtime": 2.147,
      "eval_samples_per_second": 132.74,
      "eval_steps_per_second": 66.603,
      "step": 30
    },
    {
      "epoch": 0.05181347150259067,
      "grad_norm": 0.022444354370236397,
      "learning_rate": 3.086582838174551e-05,
      "loss": 10.373,
      "step": 35
    },
    {
      "epoch": 0.05921539600296077,
      "grad_norm": 0.028981929644942284,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 10.3734,
      "step": 40
    },
    {
      "epoch": 0.05921539600296077,
      "eval_loss": 10.373154640197754,
      "eval_runtime": 2.0802,
      "eval_samples_per_second": 137.004,
      "eval_steps_per_second": 68.743,
      "step": 40
    },
    {
      "epoch": 0.06661732050333087,
      "grad_norm": 0.022452278062701225,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 10.3721,
      "step": 45
    },
    {
      "epoch": 0.07401924500370097,
      "grad_norm": 0.023130293935537338,
      "learning_rate": 0.0,
      "loss": 10.3744,
      "step": 50
    },
    {
      "epoch": 0.07401924500370097,
      "eval_loss": 10.373126983642578,
      "eval_runtime": 2.0562,
      "eval_samples_per_second": 138.606,
      "eval_steps_per_second": 69.546,
      "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": 1293090816000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}