{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 88,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.975609756097561,
      "grad_norm": 3.4229159355163574,
      "learning_rate": 0.0002,
      "loss": 4.659366226196289,
      "step": 10
    },
    {
      "epoch": 1.8780487804878048,
      "grad_norm": 1.1556655168533325,
      "learning_rate": 0.00019219658547282067,
      "loss": 2.0287652969360352,
      "step": 20
    },
    {
      "epoch": 2.7804878048780486,
      "grad_norm": 0.8790391683578491,
      "learning_rate": 0.00017000420745694254,
      "loss": 1.2084564208984374,
      "step": 30
    },
    {
      "epoch": 3.682926829268293,
      "grad_norm": 0.981283962726593,
      "learning_rate": 0.00013688639245240078,
      "loss": 1.0302597045898438,
      "step": 40
    },
    {
      "epoch": 4.585365853658536,
      "grad_norm": 1.0220673084259033,
      "learning_rate": 9.801178123349298e-05,
      "loss": 0.8048470497131348,
      "step": 50
    },
    {
      "epoch": 5.487804878048781,
      "grad_norm": 0.9974339008331299,
      "learning_rate": 5.9447467918700614e-05,
      "loss": 0.6644424438476563,
      "step": 60
    },
    {
      "epoch": 6.390243902439025,
      "grad_norm": 1.2583245038986206,
      "learning_rate": 2.7212118963050592e-05,
      "loss": 0.5137343406677246,
      "step": 70
    },
    {
      "epoch": 7.2926829268292686,
      "grad_norm": 1.1937904357910156,
      "learning_rate": 6.336650173127223e-06,
      "loss": 0.4234976291656494,
      "step": 80
    }
  ],
  "logging_steps": 10,
  "max_steps": 88,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "save_steps": 60,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1648669707730944.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}