{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.020537395173712135,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006845798391237378,
      "eval_loss": NaN,
      "eval_runtime": 73.0764,
      "eval_samples_per_second": 8.416,
      "eval_steps_per_second": 4.215,
      "step": 1
    },
    {
      "epoch": 0.0020537395173712133,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.004107479034742427,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.005476638712989902,
      "eval_loss": NaN,
      "eval_runtime": 71.9089,
      "eval_samples_per_second": 8.552,
      "eval_steps_per_second": 4.283,
      "step": 8
    },
    {
      "epoch": 0.00616121855211364,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.008214958069484853,
      "grad_norm": NaN,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.010268697586856067,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.010953277425979804,
      "eval_loss": NaN,
      "eval_runtime": 72.0921,
      "eval_samples_per_second": 8.531,
      "eval_steps_per_second": 4.272,
      "step": 16
    },
    {
      "epoch": 0.01232243710422728,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.014376176621598494,
      "grad_norm": NaN,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.016429916138969707,
      "grad_norm": NaN,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.016429916138969707,
      "eval_loss": NaN,
      "eval_runtime": 72.034,
      "eval_samples_per_second": 8.538,
      "eval_steps_per_second": 4.276,
      "step": 24
    },
    {
      "epoch": 0.01848365565634092,
      "grad_norm": NaN,
      "learning_rate": 5.449673790581611e-06,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.020537395173712135,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "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": 1.0292068148576256e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}