{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.09823182711198428,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0019646365422396855,
      "eval_loss": 2.3531432151794434,
      "eval_runtime": 16.8745,
      "eval_samples_per_second": 12.741,
      "eval_steps_per_second": 6.4,
      "step": 1
    },
    {
      "epoch": 0.009823182711198428,
      "grad_norm": 1.4596558809280396,
      "learning_rate": 5e-05,
      "loss": 2.3064,
      "step": 5
    },
    {
      "epoch": 0.019646365422396856,
      "grad_norm": 1.4307489395141602,
      "learning_rate": 0.0001,
      "loss": 2.1891,
      "step": 10
    },
    {
      "epoch": 0.019646365422396856,
      "eval_loss": 2.1915218830108643,
      "eval_runtime": 16.5757,
      "eval_samples_per_second": 12.971,
      "eval_steps_per_second": 6.516,
      "step": 10
    },
    {
      "epoch": 0.029469548133595286,
      "grad_norm": 1.6501655578613281,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.8926,
      "step": 15
    },
    {
      "epoch": 0.03929273084479371,
      "grad_norm": 1.7971864938735962,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.799,
      "step": 20
    },
    {
      "epoch": 0.03929273084479371,
      "eval_loss": 1.8568884134292603,
      "eval_runtime": 16.8987,
      "eval_samples_per_second": 12.723,
      "eval_steps_per_second": 6.391,
      "step": 20
    },
    {
      "epoch": 0.04911591355599214,
      "grad_norm": 2.209705352783203,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.7321,
      "step": 25
    },
    {
      "epoch": 0.05893909626719057,
      "grad_norm": 1.5547527074813843,
      "learning_rate": 5e-05,
      "loss": 1.7006,
      "step": 30
    },
    {
      "epoch": 0.05893909626719057,
      "eval_loss": 1.8206154108047485,
      "eval_runtime": 17.2551,
      "eval_samples_per_second": 12.46,
      "eval_steps_per_second": 6.259,
      "step": 30
    },
    {
      "epoch": 0.068762278978389,
      "grad_norm": 2.453782320022583,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.7895,
      "step": 35
    },
    {
      "epoch": 0.07858546168958742,
      "grad_norm": 2.1744861602783203,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.9341,
      "step": 40
    },
    {
      "epoch": 0.07858546168958742,
      "eval_loss": 1.802941083908081,
      "eval_runtime": 16.9939,
      "eval_samples_per_second": 12.652,
      "eval_steps_per_second": 6.355,
      "step": 40
    },
    {
      "epoch": 0.08840864440078586,
      "grad_norm": 1.8390296697616577,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.6821,
      "step": 45
    },
    {
      "epoch": 0.09823182711198428,
      "grad_norm": 1.8868811130523682,
      "learning_rate": 0.0,
      "loss": 1.8628,
      "step": 50
    },
    {
      "epoch": 0.09823182711198428,
      "eval_loss": 1.7986162900924683,
      "eval_runtime": 17.0449,
      "eval_samples_per_second": 12.614,
      "eval_steps_per_second": 6.336,
      "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": 3478615228416000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}