{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 129,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07751937984496124,
      "grad_norm": 2.245417356491089,
      "learning_rate": 5e-05,
      "loss": 2.1087,
      "step": 10
    },
    {
      "epoch": 0.15503875968992248,
      "grad_norm": 3.3328239917755127,
      "learning_rate": 0.0001,
      "loss": 1.7547,
      "step": 20
    },
    {
      "epoch": 0.23255813953488372,
      "grad_norm": 1.6743243932724,
      "learning_rate": 9.993684783030088e-05,
      "loss": 1.3868,
      "step": 30
    },
    {
      "epoch": 0.31007751937984496,
      "grad_norm": 1.585747480392456,
      "learning_rate": 9.974755084906502e-05,
      "loss": 1.1455,
      "step": 40
    },
    {
      "epoch": 0.3875968992248062,
      "grad_norm": 1.2781128883361816,
      "learning_rate": 9.94325872368957e-05,
      "loss": 1.1394,
      "step": 50
    },
    {
      "epoch": 0.46511627906976744,
      "grad_norm": 1.3732120990753174,
      "learning_rate": 9.899275261921234e-05,
      "loss": 1.0942,
      "step": 60
    },
    {
      "epoch": 0.5426356589147286,
      "grad_norm": 1.4817951917648315,
      "learning_rate": 9.842915805643155e-05,
      "loss": 0.9934,
      "step": 70
    },
    {
      "epoch": 0.6201550387596899,
      "grad_norm": 1.261801838874817,
      "learning_rate": 9.774322723733216e-05,
      "loss": 1.0093,
      "step": 80
    },
    {
      "epoch": 0.6976744186046512,
      "grad_norm": 1.801243782043457,
      "learning_rate": 9.693669288269372e-05,
      "loss": 1.0686,
      "step": 90
    },
    {
      "epoch": 0.7751937984496124,
      "grad_norm": 1.719342827796936,
      "learning_rate": 9.601159236829352e-05,
      "loss": 0.9973,
      "step": 100
    },
    {
      "epoch": 0.8527131782945736,
      "grad_norm": 1.5797449350357056,
      "learning_rate": 9.497026257831855e-05,
      "loss": 1.0002,
      "step": 110
    },
    {
      "epoch": 0.9302325581395349,
      "grad_norm": 1.790971279144287,
      "learning_rate": 9.381533400219318e-05,
      "loss": 0.9484,
      "step": 120
    }
  ],
  "logging_steps": 10,
  "max_steps": 645,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3332260188028928e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}