{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03430531732418525,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011435105774728416,
      "eval_loss": 1.5013447999954224,
      "eval_runtime": 119.6501,
      "eval_samples_per_second": 3.084,
      "eval_steps_per_second": 1.546,
      "step": 1
    },
    {
      "epoch": 0.003430531732418525,
      "grad_norm": 0.21735821664333344,
      "learning_rate": 6e-05,
      "loss": 1.3261,
      "step": 3
    },
    {
      "epoch": 0.00686106346483705,
      "grad_norm": 0.1980198174715042,
      "learning_rate": 0.00012,
      "loss": 1.333,
      "step": 6
    },
    {
      "epoch": 0.009148084619782733,
      "eval_loss": 1.473357081413269,
      "eval_runtime": 120.2031,
      "eval_samples_per_second": 3.07,
      "eval_steps_per_second": 1.539,
      "step": 8
    },
    {
      "epoch": 0.010291595197255575,
      "grad_norm": 0.19998854398727417,
      "learning_rate": 0.00018,
      "loss": 1.5086,
      "step": 9
    },
    {
      "epoch": 0.0137221269296741,
      "grad_norm": 0.32009994983673096,
      "learning_rate": 0.00019510565162951537,
      "loss": 1.3773,
      "step": 12
    },
    {
      "epoch": 0.017152658662092625,
      "grad_norm": 0.36632490158081055,
      "learning_rate": 0.00017071067811865476,
      "loss": 1.4576,
      "step": 15
    },
    {
      "epoch": 0.018296169239565466,
      "eval_loss": 1.4213716983795166,
      "eval_runtime": 120.4405,
      "eval_samples_per_second": 3.064,
      "eval_steps_per_second": 1.536,
      "step": 16
    },
    {
      "epoch": 0.02058319039451115,
      "grad_norm": 0.3036954700946808,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.305,
      "step": 18
    },
    {
      "epoch": 0.024013722126929673,
      "grad_norm": 0.3348039388656616,
      "learning_rate": 8.435655349597689e-05,
      "loss": 1.569,
      "step": 21
    },
    {
      "epoch": 0.0274442538593482,
      "grad_norm": 0.26266416907310486,
      "learning_rate": 4.12214747707527e-05,
      "loss": 1.381,
      "step": 24
    },
    {
      "epoch": 0.0274442538593482,
      "eval_loss": 1.4037752151489258,
      "eval_runtime": 120.3465,
      "eval_samples_per_second": 3.066,
      "eval_steps_per_second": 1.537,
      "step": 24
    },
    {
      "epoch": 0.030874785591766724,
      "grad_norm": 0.27952611446380615,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 1.3386,
      "step": 27
    },
    {
      "epoch": 0.03430531732418525,
      "grad_norm": 0.34170231223106384,
      "learning_rate": 0.0,
      "loss": 1.3603,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 70,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9672282773913600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}