{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 140,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03571428571428571,
      "grad_norm": 7.25,
      "learning_rate": 1.5694620482055434e-05,
      "loss": 2.4763,
      "step": 5
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 4.21875,
      "learning_rate": 3.5312896084624725e-05,
      "loss": 2.1691,
      "step": 10
    },
    {
      "epoch": 0.10714285714285714,
      "grad_norm": 2.5625,
      "learning_rate": 5.493117168719402e-05,
      "loss": 1.8697,
      "step": 15
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 2.40625,
      "learning_rate": 7.454944728976331e-05,
      "loss": 1.7589,
      "step": 20
    },
    {
      "epoch": 0.17857142857142858,
      "grad_norm": 2.25,
      "learning_rate": 9.41677228923326e-05,
      "loss": 1.6928,
      "step": 25
    },
    {
      "epoch": 0.21428571428571427,
      "grad_norm": 2.25,
      "learning_rate": 0.00011378599849490191,
      "loss": 1.7305,
      "step": 30
    },
    {
      "epoch": 0.25,
      "grad_norm": 2.03125,
      "learning_rate": 0.0001334042740974712,
      "loss": 1.6926,
      "step": 35
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 1.8828125,
      "learning_rate": 0.00013729501366912194,
      "loss": 1.725,
      "step": 40
    },
    {
      "epoch": 0.32142857142857145,
      "grad_norm": 1.84375,
      "learning_rate": 0.00013716135434454804,
      "loss": 1.6931,
      "step": 45
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 1.890625,
      "learning_rate": 0.00013692511631397978,
      "loss": 1.6906,
      "step": 50
    },
    {
      "epoch": 0.39285714285714285,
      "grad_norm": 1.6875,
      "learning_rate": 0.00013658669277230492,
      "loss": 1.7308,
      "step": 55
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 1.84375,
      "learning_rate": 0.0001361466469921098,
      "loss": 1.681,
      "step": 60
    },
    {
      "epoch": 0.4642857142857143,
      "grad_norm": 1.9140625,
      "learning_rate": 0.00013560571138616784,
      "loss": 1.7386,
      "step": 65
    },
    {
      "epoch": 0.5,
      "grad_norm": 1.6015625,
      "learning_rate": 0.00013496478628841066,
      "loss": 1.6742,
      "step": 70
    },
    {
      "epoch": 0.5357142857142857,
      "grad_norm": 1.6953125,
      "learning_rate": 0.0001342249384554111,
      "loss": 1.6831,
      "step": 75
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 1.640625,
      "learning_rate": 0.00013338739929087223,
      "loss": 1.6664,
      "step": 80
    },
    {
      "epoch": 0.6071428571428571,
      "grad_norm": 1.578125,
      "learning_rate": 0.00013245356279607736,
      "loss": 1.6827,
      "step": 85
    },
    {
      "epoch": 0.6428571428571429,
      "grad_norm": 2.0,
      "learning_rate": 0.00013142498324971255,
      "loss": 1.6647,
      "step": 90
    },
    {
      "epoch": 0.6785714285714286,
      "grad_norm": 1.6015625,
      "learning_rate": 0.00013030337262092307,
      "loss": 1.6842,
      "step": 95
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 1.765625,
      "learning_rate": 0.00012909059771990967,
      "loss": 1.6335,
      "step": 100
    },
    {
      "epoch": 0.75,
      "grad_norm": 1.6171875,
      "learning_rate": 0.0001277886770908074,
      "loss": 1.6338,
      "step": 105
    },
    {
      "epoch": 0.7857142857142857,
      "grad_norm": 1.515625,
      "learning_rate": 0.00012639977765201797,
      "loss": 1.6366,
      "step": 110
    },
    {
      "epoch": 0.8214285714285714,
      "grad_norm": 1.609375,
      "learning_rate": 0.00012492621108958784,
      "loss": 1.5962,
      "step": 115
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 1.4765625,
      "learning_rate": 0.00012337043000963516,
      "loss": 1.6343,
      "step": 120
    },
    {
      "epoch": 0.8928571428571429,
      "grad_norm": 1.546875,
      "learning_rate": 0.00012173502385622879,
      "loss": 1.6466,
      "step": 125
    },
    {
      "epoch": 0.9285714285714286,
      "grad_norm": 1.40625,
      "learning_rate": 0.00012002271460151416,
      "loss": 1.5999,
      "step": 130
    },
    {
      "epoch": 0.9642857142857143,
      "grad_norm": 1.5859375,
      "learning_rate": 0.00011823635221525941,
      "loss": 1.6032,
      "step": 135
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.4921875,
      "learning_rate": 0.00011637890992136184,
      "loss": 1.5929,
      "step": 140
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.6064611673355103,
      "eval_runtime": 0.5875,
      "eval_samples_per_second": 8.511,
      "eval_steps_per_second": 8.511,
      "step": 140
    }
  ],
  "logging_steps": 5,
  "max_steps": 420,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 3.3941343147393024e+17,
  "train_batch_size": 53,
  "trial_name": null,
  "trial_params": null
}