{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.10075566750629723,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0020151133501259445,
      "eval_loss": 11.928855895996094,
      "eval_runtime": 2.8749,
      "eval_samples_per_second": 72.699,
      "eval_steps_per_second": 36.523,
      "step": 1
    },
    {
      "epoch": 0.010075566750629723,
      "grad_norm": 0.01261623203754425,
      "learning_rate": 5e-05,
      "loss": 11.9283,
      "step": 5
    },
    {
      "epoch": 0.020151133501259445,
      "grad_norm": 0.008780092932283878,
      "learning_rate": 0.0001,
      "loss": 11.9228,
      "step": 10
    },
    {
      "epoch": 0.020151133501259445,
      "eval_loss": 11.928825378417969,
      "eval_runtime": 2.8934,
      "eval_samples_per_second": 72.232,
      "eval_steps_per_second": 36.289,
      "step": 10
    },
    {
      "epoch": 0.030226700251889168,
      "grad_norm": 0.01207203883677721,
      "learning_rate": 9.619397662556435e-05,
      "loss": 11.9282,
      "step": 15
    },
    {
      "epoch": 0.04030226700251889,
      "grad_norm": 0.006873443257063627,
      "learning_rate": 8.535533905932738e-05,
      "loss": 11.9286,
      "step": 20
    },
    {
      "epoch": 0.04030226700251889,
      "eval_loss": 11.92874813079834,
      "eval_runtime": 2.9679,
      "eval_samples_per_second": 70.421,
      "eval_steps_per_second": 35.379,
      "step": 20
    },
    {
      "epoch": 0.05037783375314862,
      "grad_norm": 0.007669125683605671,
      "learning_rate": 6.91341716182545e-05,
      "loss": 11.9293,
      "step": 25
    },
    {
      "epoch": 0.060453400503778336,
      "grad_norm": 0.008746370673179626,
      "learning_rate": 5e-05,
      "loss": 11.929,
      "step": 30
    },
    {
      "epoch": 0.060453400503778336,
      "eval_loss": 11.928698539733887,
      "eval_runtime": 2.928,
      "eval_samples_per_second": 71.381,
      "eval_steps_per_second": 35.861,
      "step": 30
    },
    {
      "epoch": 0.07052896725440806,
      "grad_norm": 0.004675919655710459,
      "learning_rate": 3.086582838174551e-05,
      "loss": 11.9269,
      "step": 35
    },
    {
      "epoch": 0.08060453400503778,
      "grad_norm": 0.006607264745980501,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 11.9291,
      "step": 40
    },
    {
      "epoch": 0.08060453400503778,
      "eval_loss": 11.928670883178711,
      "eval_runtime": 2.9468,
      "eval_samples_per_second": 70.923,
      "eval_steps_per_second": 35.631,
      "step": 40
    },
    {
      "epoch": 0.0906801007556675,
      "grad_norm": 0.011314083822071552,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 11.9277,
      "step": 45
    },
    {
      "epoch": 0.10075566750629723,
      "grad_norm": 0.010369797237217426,
      "learning_rate": 0.0,
      "loss": 11.9283,
      "step": 50
    },
    {
      "epoch": 0.10075566750629723,
      "eval_loss": 11.928665161132812,
      "eval_runtime": 2.8895,
      "eval_samples_per_second": 72.33,
      "eval_steps_per_second": 36.338,
      "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": 11048091648.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}