{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 117,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.042735042735042736,
      "grad_norm": 4.884984970092773,
      "learning_rate": 3.6363636363636366e-06,
      "loss": 0.2805,
      "step": 5
    },
    {
      "epoch": 0.08547008547008547,
      "grad_norm": 3.8989036083221436,
      "learning_rate": 8.181818181818183e-06,
      "loss": 0.2371,
      "step": 10
    },
    {
      "epoch": 0.1282051282051282,
      "grad_norm": 3.5579559803009033,
      "learning_rate": 9.998079135987437e-06,
      "loss": 0.243,
      "step": 15
    },
    {
      "epoch": 0.17094017094017094,
      "grad_norm": 4.4413347244262695,
      "learning_rate": 9.98634586692894e-06,
      "loss": 0.2425,
      "step": 20
    },
    {
      "epoch": 0.21367521367521367,
      "grad_norm": 4.2704386711120605,
      "learning_rate": 9.963971484502247e-06,
      "loss": 0.2579,
      "step": 25
    },
    {
      "epoch": 0.2564102564102564,
      "grad_norm": 3.503924608230591,
      "learning_rate": 9.931003736767013e-06,
      "loss": 0.241,
      "step": 30
    },
    {
      "epoch": 0.29914529914529914,
      "grad_norm": 3.716705083847046,
      "learning_rate": 9.887512978558329e-06,
      "loss": 0.2511,
      "step": 35
    },
    {
      "epoch": 0.3418803418803419,
      "grad_norm": 3.202826738357544,
      "learning_rate": 9.833592021345938e-06,
      "loss": 0.2389,
      "step": 40
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 4.339502811431885,
      "learning_rate": 9.76935593516989e-06,
      "loss": 0.258,
      "step": 45
    },
    {
      "epoch": 0.42735042735042733,
      "grad_norm": 3.6700973510742188,
      "learning_rate": 9.694941803075285e-06,
      "loss": 0.2323,
      "step": 50
    },
    {
      "epoch": 0.4700854700854701,
      "grad_norm": 3.2889957427978516,
      "learning_rate": 9.610508428570122e-06,
      "loss": 0.2685,
      "step": 55
    },
    {
      "epoch": 0.5128205128205128,
      "grad_norm": 3.249929666519165,
      "learning_rate": 9.516235996730645e-06,
      "loss": 0.2455,
      "step": 60
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 3.139861822128296,
      "learning_rate": 9.41232568967728e-06,
      "loss": 0.2509,
      "step": 65
    },
    {
      "epoch": 0.5982905982905983,
      "grad_norm": 3.1881346702575684,
      "learning_rate": 9.298999257241862e-06,
      "loss": 0.2322,
      "step": 70
    },
    {
      "epoch": 0.6410256410256411,
      "grad_norm": 3.5317623615264893,
      "learning_rate": 9.176498543742328e-06,
      "loss": 0.2334,
      "step": 75
    },
    {
      "epoch": 0.6837606837606838,
      "grad_norm": 3.0199837684631348,
      "learning_rate": 9.045084971874738e-06,
      "loss": 0.2331,
      "step": 80
    },
    {
      "epoch": 0.7264957264957265,
      "grad_norm": 3.8516860008239746,
      "learning_rate": 8.905038984824079e-06,
      "loss": 0.252,
      "step": 85
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 3.244687795639038,
      "learning_rate": 8.756659447784367e-06,
      "loss": 0.2558,
      "step": 90
    },
    {
      "epoch": 0.811965811965812,
      "grad_norm": 4.6248884201049805,
      "learning_rate": 8.600263010165275e-06,
      "loss": 0.2455,
      "step": 95
    },
    {
      "epoch": 0.8547008547008547,
      "grad_norm": 2.914029121398926,
      "learning_rate": 8.436183429846314e-06,
      "loss": 0.2539,
      "step": 100
    },
    {
      "epoch": 0.8974358974358975,
      "grad_norm": 3.7247676849365234,
      "learning_rate": 8.264770860920722e-06,
      "loss": 0.2604,
      "step": 105
    },
    {
      "epoch": 0.9401709401709402,
      "grad_norm": 3.5662894248962402,
      "learning_rate": 8.086391106448965e-06,
      "loss": 0.2432,
      "step": 110
    },
    {
      "epoch": 0.9829059829059829,
      "grad_norm": 3.140153408050537,
      "learning_rate": 7.90142483781658e-06,
      "loss": 0.2617,
      "step": 115
    }
  ],
  "logging_steps": 5,
  "max_steps": 351,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9.096235537399808e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}