{
  "best_global_step": 100,
  "best_metric": 0.7,
  "best_model_checkpoint": "./models/punctuation/decoder_model_simple/checkpoint-100",
  "epoch": 0.9411764705882353,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09411764705882353,
      "grad_norm": 1.3681155443191528,
      "learning_rate": 2.7272727272727273e-05,
      "loss": 0.7202,
      "step": 10
    },
    {
      "epoch": 0.18823529411764706,
      "grad_norm": 0.7711533308029175,
      "learning_rate": 5.757575757575758e-05,
      "loss": 0.3185,
      "step": 20
    },
    {
      "epoch": 0.2823529411764706,
      "grad_norm": 1.2256836891174316,
      "learning_rate": 8.787878787878789e-05,
      "loss": 0.1827,
      "step": 30
    },
    {
      "epoch": 0.3764705882352941,
      "grad_norm": 0.888201892375946,
      "learning_rate": 9.989294616193017e-05,
      "loss": 0.1346,
      "step": 40
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 0.853918731212616,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.0721,
      "step": 50
    },
    {
      "epoch": 0.47058823529411764,
      "eval_loss": 0.04328128695487976,
      "eval_model_preparation_time": 0.0162,
      "eval_runtime": 2.2686,
      "eval_samples_per_second": 44.081,
      "eval_steps_per_second": 22.04,
      "step": 50
    },
    {
      "epoch": 0.5647058823529412,
      "grad_norm": 0.48631730675697327,
      "learning_rate": 9.800249271929645e-05,
      "loss": 0.042,
      "step": 60
    },
    {
      "epoch": 0.6588235294117647,
      "grad_norm": 0.5516029596328735,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0218,
      "step": 70
    },
    {
      "epoch": 0.7529411764705882,
      "grad_norm": 0.28095027804374695,
      "learning_rate": 9.38363377853754e-05,
      "loss": 0.0127,
      "step": 80
    },
    {
      "epoch": 0.8470588235294118,
      "grad_norm": 0.8756083846092224,
      "learning_rate": 9.09576022144496e-05,
      "loss": 0.0124,
      "step": 90
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 0.5514245629310608,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.0119,
      "step": 100
    },
    {
      "epoch": 0.9411764705882353,
      "eval_loss": 0.004549662582576275,
      "eval_model_preparation_time": 0.0162,
      "eval_runtime": 2.2779,
      "eval_samples_per_second": 43.9,
      "eval_steps_per_second": 21.95,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 321,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 6705100455260160.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}