{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 30.0,
  "eval_steps": 500,
  "global_step": 3000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 1.4591705799102783,
      "learning_rate": 9.982023428222962e-05,
      "loss": 2.6337,
      "step": 100
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.8328539133071899,
      "learning_rate": 9.91045243455787e-05,
      "loss": 1.5372,
      "step": 200
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.8647604584693909,
      "learning_rate": 9.785081496441527e-05,
      "loss": 1.1526,
      "step": 300
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.6284393072128296,
      "learning_rate": 9.607284204107493e-05,
      "loss": 0.7283,
      "step": 400
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.7794511318206787,
      "learning_rate": 9.379008541897054e-05,
      "loss": 0.3829,
      "step": 500
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.7847722768783569,
      "learning_rate": 9.102755545735141e-05,
      "loss": 0.2319,
      "step": 600
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.7915834784507751,
      "learning_rate": 8.78155190125736e-05,
      "loss": 0.1744,
      "step": 700
    },
    {
      "epoch": 8.0,
      "grad_norm": 1.0084211826324463,
      "learning_rate": 8.418916782808795e-05,
      "loss": 0.1513,
      "step": 800
    },
    {
      "epoch": 9.0,
      "grad_norm": 1.6660008430480957,
      "learning_rate": 8.018823296633441e-05,
      "loss": 0.1396,
      "step": 900
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.6257602572441101,
      "learning_rate": 7.585654950690786e-05,
      "loss": 0.1256,
      "step": 1000
    },
    {
      "epoch": 11.0,
      "grad_norm": 0.7090705633163452,
      "learning_rate": 7.124157628025278e-05,
      "loss": 0.1179,
      "step": 1100
    },
    {
      "epoch": 12.0,
      "grad_norm": 0.4159357249736786,
      "learning_rate": 6.639387589878566e-05,
      "loss": 0.1166,
      "step": 1200
    },
    {
      "epoch": 13.0,
      "grad_norm": 0.3188364505767822,
      "learning_rate": 6.136656078233232e-05,
      "loss": 0.114,
      "step": 1300
    },
    {
      "epoch": 14.0,
      "grad_norm": 0.34499579668045044,
      "learning_rate": 5.621471124734201e-05,
      "loss": 0.1101,
      "step": 1400
    },
    {
      "epoch": 15.0,
      "grad_norm": 0.6969137787818909,
      "learning_rate": 5.09947720354139e-05,
      "loss": 0.1092,
      "step": 1500
    },
    {
      "epoch": 16.0,
      "grad_norm": 0.8777207136154175,
      "learning_rate": 4.576393389289633e-05,
      "loss": 0.1072,
      "step": 1600
    },
    {
      "epoch": 17.0,
      "grad_norm": 0.34652048349380493,
      "learning_rate": 4.0579506977102036e-05,
      "loss": 0.1063,
      "step": 1700
    },
    {
      "epoch": 18.0,
      "grad_norm": 0.2864055931568146,
      "learning_rate": 3.5498292954231496e-05,
      "loss": 0.1062,
      "step": 1800
    },
    {
      "epoch": 19.0,
      "grad_norm": 0.5659065842628479,
      "learning_rate": 3.05759626684317e-05,
      "loss": 0.1036,
      "step": 1900
    },
    {
      "epoch": 20.0,
      "grad_norm": 0.37669795751571655,
      "learning_rate": 2.5866446200377688e-05,
      "loss": 0.1021,
      "step": 2000
    },
    {
      "epoch": 21.0,
      "grad_norm": 0.2888871133327484,
      "learning_rate": 2.1421341998023163e-05,
      "loss": 0.0996,
      "step": 2100
    },
    {
      "epoch": 22.0,
      "grad_norm": 0.5899520516395569,
      "learning_rate": 1.7289351553206952e-05,
      "loss": 0.0983,
      "step": 2200
    },
    {
      "epoch": 23.0,
      "grad_norm": 0.4493533968925476,
      "learning_rate": 1.3515745817917069e-05,
      "loss": 0.0977,
      "step": 2300
    },
    {
      "epoch": 24.0,
      "grad_norm": 0.3612530529499054,
      "learning_rate": 1.0141869206267095e-05,
      "loss": 0.0965,
      "step": 2400
    },
    {
      "epoch": 25.0,
      "grad_norm": 0.22373980283737183,
      "learning_rate": 7.204686616443351e-06,
      "loss": 0.0958,
      "step": 2500
    },
    {
      "epoch": 26.0,
      "grad_norm": 0.44540122151374817,
      "learning_rate": 4.73637843554493e-06,
      "loss": 0.0948,
      "step": 2600
    },
    {
      "epoch": 27.0,
      "grad_norm": 0.4003278613090515,
      "learning_rate": 2.763987964528425e-06,
      "loss": 0.0943,
      "step": 2700
    },
    {
      "epoch": 28.0,
      "grad_norm": 0.4109736979007721,
      "learning_rate": 1.3091251261435566e-06,
      "loss": 0.0937,
      "step": 2800
    },
    {
      "epoch": 29.0,
      "grad_norm": 0.4337215721607208,
      "learning_rate": 3.877297020972781e-07,
      "loss": 0.0933,
      "step": 2900
    },
    {
      "epoch": 30.0,
      "grad_norm": 0.4439603090286255,
      "learning_rate": 9.896693469829688e-09,
      "loss": 0.093,
      "step": 3000
    }
  ],
  "logging_steps": 500,
  "max_steps": 3000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 30,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5757808997376000.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}