{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 125,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "grad_norm": 0.6921696066856384,
      "learning_rate": 0.0001856,
      "loss": 1.593,
      "step": 10
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.6577253341674805,
      "learning_rate": 0.0001696,
      "loss": 1.3572,
      "step": 20
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.4804594814777374,
      "learning_rate": 0.00015360000000000002,
      "loss": 1.28,
      "step": 30
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.3516864478588104,
      "learning_rate": 0.00013759999999999998,
      "loss": 1.191,
      "step": 40
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.5060459971427917,
      "learning_rate": 0.0001216,
      "loss": 1.3117,
      "step": 50
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.3955352008342743,
      "learning_rate": 0.0001056,
      "loss": 1.3089,
      "step": 60
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.3805406391620636,
      "learning_rate": 8.960000000000001e-05,
      "loss": 1.2157,
      "step": 70
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.405851811170578,
      "learning_rate": 7.36e-05,
      "loss": 1.3118,
      "step": 80
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.3721686899662018,
      "learning_rate": 5.76e-05,
      "loss": 1.2033,
      "step": 90
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.5105984807014465,
      "learning_rate": 4.16e-05,
      "loss": 1.2716,
      "step": 100
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.5118499398231506,
      "learning_rate": 2.5600000000000002e-05,
      "loss": 1.3137,
      "step": 110
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.36947008967399597,
      "learning_rate": 9.600000000000001e-06,
      "loss": 1.2903,
      "step": 120
    }
  ],
  "logging_steps": 10,
  "max_steps": 125,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 1.534148608352256e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}