{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2537764350453172,
  "eval_steps": 21,
  "global_step": 21,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.012084592145015106,
      "eval_loss": 10.387871742248535,
      "eval_runtime": 0.2615,
      "eval_samples_per_second": 535.336,
      "eval_steps_per_second": 68.829,
      "step": 1
    },
    {
      "epoch": 0.03625377643504532,
      "grad_norm": 0.13119755685329437,
      "learning_rate": 3e-05,
      "loss": 10.3886,
      "step": 3
    },
    {
      "epoch": 0.07250755287009064,
      "grad_norm": 0.10730081051588058,
      "learning_rate": 6e-05,
      "loss": 10.3847,
      "step": 6
    },
    {
      "epoch": 0.10876132930513595,
      "grad_norm": 0.09705545753240585,
      "learning_rate": 9e-05,
      "loss": 10.3871,
      "step": 9
    },
    {
      "epoch": 0.14501510574018128,
      "grad_norm": 0.12139848619699478,
      "learning_rate": 9.998272257842641e-05,
      "loss": 10.3874,
      "step": 12
    },
    {
      "epoch": 0.18126888217522658,
      "grad_norm": 0.11973798274993896,
      "learning_rate": 9.989204876292688e-05,
      "loss": 10.3781,
      "step": 15
    },
    {
      "epoch": 0.2175226586102719,
      "grad_norm": 0.13775140047073364,
      "learning_rate": 9.972379999624936e-05,
      "loss": 10.3777,
      "step": 18
    },
    {
      "epoch": 0.2537764350453172,
      "grad_norm": 0.12977235019207,
      "learning_rate": 9.947823788099753e-05,
      "loss": 10.3796,
      "step": 21
    },
    {
      "epoch": 0.2537764350453172,
      "eval_loss": 10.373146057128906,
      "eval_runtime": 0.2637,
      "eval_samples_per_second": 530.958,
      "eval_steps_per_second": 68.266,
      "step": 21
    }
  ],
  "logging_steps": 3,
  "max_steps": 249,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 21,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2342563872768.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}