{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.029865604778496764,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009955201592832255,
      "eval_loss": 1.872341275215149,
      "eval_runtime": 28.9167,
      "eval_samples_per_second": 14.628,
      "eval_steps_per_second": 7.331,
      "step": 1
    },
    {
      "epoch": 0.0029865604778496766,
      "grad_norm": 13.878497123718262,
      "learning_rate": 6e-05,
      "loss": 7.1228,
      "step": 3
    },
    {
      "epoch": 0.005973120955699353,
      "grad_norm": 19.81745147705078,
      "learning_rate": 0.00012,
      "loss": 6.72,
      "step": 6
    },
    {
      "epoch": 0.007964161274265804,
      "eval_loss": 1.4684226512908936,
      "eval_runtime": 29.1251,
      "eval_samples_per_second": 14.524,
      "eval_steps_per_second": 7.279,
      "step": 8
    },
    {
      "epoch": 0.008959681433549029,
      "grad_norm": 15.048240661621094,
      "learning_rate": 0.00018,
      "loss": 6.0814,
      "step": 9
    },
    {
      "epoch": 0.011946241911398706,
      "grad_norm": 12.190631866455078,
      "learning_rate": 0.00019510565162951537,
      "loss": 5.536,
      "step": 12
    },
    {
      "epoch": 0.014932802389248382,
      "grad_norm": 10.199469566345215,
      "learning_rate": 0.00017071067811865476,
      "loss": 5.1363,
      "step": 15
    },
    {
      "epoch": 0.015928322548531607,
      "eval_loss": 1.364620327949524,
      "eval_runtime": 28.9498,
      "eval_samples_per_second": 14.612,
      "eval_steps_per_second": 7.323,
      "step": 16
    },
    {
      "epoch": 0.017919362867098058,
      "grad_norm": 12.294973373413086,
      "learning_rate": 0.00013090169943749476,
      "loss": 5.943,
      "step": 18
    },
    {
      "epoch": 0.020905923344947737,
      "grad_norm": 10.412511825561523,
      "learning_rate": 8.435655349597689e-05,
      "loss": 5.6715,
      "step": 21
    },
    {
      "epoch": 0.023892483822797413,
      "grad_norm": 9.245460510253906,
      "learning_rate": 4.12214747707527e-05,
      "loss": 5.223,
      "step": 24
    },
    {
      "epoch": 0.023892483822797413,
      "eval_loss": 1.3107273578643799,
      "eval_runtime": 29.0089,
      "eval_samples_per_second": 14.582,
      "eval_steps_per_second": 7.308,
      "step": 24
    },
    {
      "epoch": 0.02687904430064709,
      "grad_norm": 9.331769943237305,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 5.6038,
      "step": 27
    },
    {
      "epoch": 0.029865604778496764,
      "grad_norm": 8.921256065368652,
      "learning_rate": 0.0,
      "loss": 5.3554,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.054694248022016e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}