{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0989010989010989,
  "eval_steps": 500,
  "global_step": 15,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 1.0638142824172974,
      "learning_rate": 0.0,
      "loss": 1.0777,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 0.9542151689529419,
      "learning_rate": 9.56e-05,
      "loss": 1.1025,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.0668847560882568,
      "learning_rate": 0.0001912,
      "loss": 1.0405,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.0646922588348389,
      "learning_rate": 0.0002868,
      "loss": 0.9056,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 0.6475369334220886,
      "learning_rate": 0.0003824,
      "loss": 0.8513,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 0.653504490852356,
      "learning_rate": 0.000478,
      "loss": 0.9432,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 0.5652804374694824,
      "learning_rate": 0.00047694013303769406,
      "loss": 0.8951,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 0.38114824891090393,
      "learning_rate": 0.00047588026607538804,
      "loss": 0.8546,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 0.3202402591705322,
      "learning_rate": 0.0004748203991130821,
      "loss": 0.9013,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 0.3632391095161438,
      "learning_rate": 0.00047376053215077607,
      "loss": 0.7981,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.38180795311927795,
      "learning_rate": 0.00047270066518847006,
      "loss": 0.8034,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.44034814834594727,
      "learning_rate": 0.0004716407982261641,
      "loss": 0.8194,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.5649089217185974,
      "learning_rate": 0.00047058093126385814,
      "loss": 0.7964,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.4905894994735718,
      "learning_rate": 0.0004695210643015521,
      "loss": 0.7767,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.5945530533790588,
      "learning_rate": 0.00046846119733924617,
      "loss": 0.7485,
      "step": 15
    }
  ],
  "logging_steps": 1,
  "max_steps": 456,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 15,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6887922133542912.0,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}