{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.9083492159843445,
      "learning_rate": 1e-05,
      "loss": 4.9918,
      "step": 1
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.969480037689209,
      "learning_rate": 8.888888888888888e-06,
      "loss": 4.6192,
      "step": 2
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.9994485378265381,
      "learning_rate": 7.77777777777778e-06,
      "loss": 4.8328,
      "step": 3
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.8605744242668152,
      "learning_rate": 6.666666666666667e-06,
      "loss": 4.9017,
      "step": 4
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.118040919303894,
      "learning_rate": 5.555555555555557e-06,
      "loss": 4.9943,
      "step": 5
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.9468250870704651,
      "learning_rate": 4.444444444444444e-06,
      "loss": 4.9743,
      "step": 6
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.9659126996994019,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 4.9676,
      "step": 7
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.9898912906646729,
      "learning_rate": 2.222222222222222e-06,
      "loss": 5.0618,
      "step": 8
    },
    {
      "epoch": 9.0,
      "grad_norm": 1.0184844732284546,
      "learning_rate": 1.111111111111111e-06,
      "loss": 4.7525,
      "step": 9
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.9544917941093445,
      "learning_rate": 0.0,
      "loss": 4.8533,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 63945216000.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}