{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.08322929671244278,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0016645859342488557,
      "eval_loss": NaN,
      "eval_runtime": 6.7372,
      "eval_samples_per_second": 37.553,
      "eval_steps_per_second": 18.851,
      "step": 1
    },
    {
      "epoch": 0.008322929671244279,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 172.363,
      "step": 5
    },
    {
      "epoch": 0.016645859342488557,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.016645859342488557,
      "eval_loss": NaN,
      "eval_runtime": 5.5847,
      "eval_samples_per_second": 45.302,
      "eval_steps_per_second": 22.741,
      "step": 10
    },
    {
      "epoch": 0.024968789013732832,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.033291718684977115,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.033291718684977115,
      "eval_loss": NaN,
      "eval_runtime": 5.7578,
      "eval_samples_per_second": 43.94,
      "eval_steps_per_second": 22.057,
      "step": 20
    },
    {
      "epoch": 0.04161464835622139,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.049937578027465665,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.049937578027465665,
      "eval_loss": NaN,
      "eval_runtime": 5.5951,
      "eval_samples_per_second": 45.219,
      "eval_steps_per_second": 22.699,
      "step": 30
    },
    {
      "epoch": 0.05826050769870995,
      "grad_norm": NaN,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.06658343736995423,
      "grad_norm": NaN,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.06658343736995423,
      "eval_loss": NaN,
      "eval_runtime": 5.8771,
      "eval_samples_per_second": 43.048,
      "eval_steps_per_second": 21.609,
      "step": 40
    },
    {
      "epoch": 0.0749063670411985,
      "grad_norm": NaN,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.08322929671244278,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.08322929671244278,
      "eval_loss": NaN,
      "eval_runtime": 5.5208,
      "eval_samples_per_second": 45.827,
      "eval_steps_per_second": 23.004,
      "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": 531052049203200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}