{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.025,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0025,
      "grad_norm": 7.581125259399414,
      "learning_rate": 1.6e-07,
      "loss": 86.44205322265626,
      "step": 5
    },
    {
      "epoch": 0.005,
      "grad_norm": 870.7899169921875,
      "learning_rate": 3.6e-07,
      "loss": 305.9718505859375,
      "step": 10
    },
    {
      "epoch": 0.005,
      "eval_accuracy": 0.029019607843137254,
      "eval_loss": 68.04701232910156,
      "eval_runtime": 35.4394,
      "eval_samples_per_second": 14.109,
      "eval_steps_per_second": 1.778,
      "step": 10
    },
    {
      "epoch": 0.0075,
      "grad_norm": 225.20162963867188,
      "learning_rate": 5.6e-07,
      "loss": 179.27216796875,
      "step": 15
    },
    {
      "epoch": 0.01,
      "grad_norm": 79.13408660888672,
      "learning_rate": 7.599999999999999e-07,
      "loss": 130.82646484375,
      "step": 20
    },
    {
      "epoch": 0.01,
      "eval_accuracy": 0.02961176470588235,
      "eval_loss": 31.59725570678711,
      "eval_runtime": 36.9264,
      "eval_samples_per_second": 13.54,
      "eval_steps_per_second": 1.706,
      "step": 20
    },
    {
      "epoch": 0.0125,
      "grad_norm": 72.2133560180664,
      "learning_rate": 9.6e-07,
      "loss": 124.6850830078125,
      "step": 25
    },
    {
      "epoch": 0.015,
      "grad_norm": 94.8714828491211,
      "learning_rate": 1.16e-06,
      "loss": 123.9353515625,
      "step": 30
    },
    {
      "epoch": 0.015,
      "eval_accuracy": 0.04030196078431372,
      "eval_loss": 30.649425506591797,
      "eval_runtime": 38.2598,
      "eval_samples_per_second": 13.069,
      "eval_steps_per_second": 1.647,
      "step": 30
    },
    {
      "epoch": 0.0175,
      "grad_norm": 54.928829193115234,
      "learning_rate": 1.3600000000000001e-06,
      "loss": 125.992138671875,
      "step": 35
    },
    {
      "epoch": 0.02,
      "grad_norm": 70.58757019042969,
      "learning_rate": 1.5599999999999999e-06,
      "loss": 120.77716064453125,
      "step": 40
    },
    {
      "epoch": 0.02,
      "eval_accuracy": 0.04015686274509804,
      "eval_loss": 29.560930252075195,
      "eval_runtime": 37.9793,
      "eval_samples_per_second": 13.165,
      "eval_steps_per_second": 1.659,
      "step": 40
    },
    {
      "epoch": 0.0225,
      "grad_norm": 81.62490844726562,
      "learning_rate": 1.7599999999999999e-06,
      "loss": 121.851220703125,
      "step": 45
    },
    {
      "epoch": 0.025,
      "grad_norm": 65.93287658691406,
      "learning_rate": 1.96e-06,
      "loss": 120.95302734375,
      "step": 50
    },
    {
      "epoch": 0.025,
      "eval_accuracy": 0.04131764705882353,
      "eval_loss": 28.05109977722168,
      "eval_runtime": 38.147,
      "eval_samples_per_second": 13.107,
      "eval_steps_per_second": 1.652,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 2000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}