{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00856971462850287,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001713942925700574,
      "eval_loss": NaN,
      "eval_runtime": 268.0941,
      "eval_samples_per_second": 9.165,
      "eval_steps_per_second": 4.584,
      "step": 1
    },
    {
      "epoch": 0.0008569714628502871,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0017139429257005741,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.0017139429257005741,
      "eval_loss": NaN,
      "eval_runtime": 267.7599,
      "eval_samples_per_second": 9.176,
      "eval_steps_per_second": 4.59,
      "step": 10
    },
    {
      "epoch": 0.0025709143885508613,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0034278858514011482,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.0034278858514011482,
      "eval_loss": NaN,
      "eval_runtime": 267.5278,
      "eval_samples_per_second": 9.184,
      "eval_steps_per_second": 4.594,
      "step": 20
    },
    {
      "epoch": 0.004284857314251435,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.005141828777101723,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.005141828777101723,
      "eval_loss": NaN,
      "eval_runtime": 267.5067,
      "eval_samples_per_second": 9.185,
      "eval_steps_per_second": 4.594,
      "step": 30
    },
    {
      "epoch": 0.00599880023995201,
      "grad_norm": NaN,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.0068557717028022965,
      "grad_norm": NaN,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.0068557717028022965,
      "eval_loss": NaN,
      "eval_runtime": 267.3077,
      "eval_samples_per_second": 9.192,
      "eval_steps_per_second": 4.598,
      "step": 40
    },
    {
      "epoch": 0.007712743165652584,
      "grad_norm": NaN,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.00856971462850287,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.00856971462850287,
      "eval_loss": NaN,
      "eval_runtime": 267.347,
      "eval_samples_per_second": 9.19,
      "eval_steps_per_second": 4.597,
      "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": 1.7493516865241088e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}