{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01697792869269949,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00033955857385398983,
      "eval_loss": NaN,
      "eval_runtime": 85.5346,
      "eval_samples_per_second": 14.497,
      "eval_steps_per_second": 7.249,
      "step": 1
    },
    {
      "epoch": 0.001697792869269949,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.003395585738539898,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.003395585738539898,
      "eval_loss": NaN,
      "eval_runtime": 87.9719,
      "eval_samples_per_second": 14.095,
      "eval_steps_per_second": 7.048,
      "step": 10
    },
    {
      "epoch": 0.0050933786078098476,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.006791171477079796,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.006791171477079796,
      "eval_loss": NaN,
      "eval_runtime": 89.1861,
      "eval_samples_per_second": 13.904,
      "eval_steps_per_second": 6.952,
      "step": 20
    },
    {
      "epoch": 0.008488964346349746,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.010186757215619695,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.010186757215619695,
      "eval_loss": NaN,
      "eval_runtime": 87.5572,
      "eval_samples_per_second": 14.162,
      "eval_steps_per_second": 7.081,
      "step": 30
    },
    {
      "epoch": 0.011884550084889643,
      "grad_norm": NaN,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.013582342954159592,
      "grad_norm": NaN,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.013582342954159592,
      "eval_loss": NaN,
      "eval_runtime": 91.4195,
      "eval_samples_per_second": 13.564,
      "eval_steps_per_second": 6.782,
      "step": 40
    },
    {
      "epoch": 0.015280135823429542,
      "grad_norm": NaN,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.01697792869269949,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.01697792869269949,
      "eval_loss": NaN,
      "eval_runtime": 94.5532,
      "eval_samples_per_second": 13.114,
      "eval_steps_per_second": 6.557,
      "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": 1278959891251200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}