{
  "best_metric": 1.0223731994628906,
  "best_model_checkpoint": "mgh6/TCS_MLM_All/checkpoint-700",
  "epoch": 10.0,
  "eval_steps": 100,
  "global_step": 1050,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 0.18039299547672272,
      "learning_rate": 0.0009047619047619047,
      "loss": 1.5254,
      "step": 100
    },
    {
      "epoch": 0.9523809523809523,
      "eval_loss": 1.250386118888855,
      "eval_runtime": 0.218,
      "eval_samples_per_second": 87.168,
      "eval_steps_per_second": 4.588,
      "step": 100
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 0.17264288663864136,
      "learning_rate": 0.0008095238095238096,
      "loss": 1.3281,
      "step": 200
    },
    {
      "epoch": 1.9047619047619047,
      "eval_loss": 1.1765815019607544,
      "eval_runtime": 0.2181,
      "eval_samples_per_second": 87.116,
      "eval_steps_per_second": 4.585,
      "step": 200
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.16163380444049835,
      "learning_rate": 0.0007142857142857143,
      "loss": 1.2854,
      "step": 300
    },
    {
      "epoch": 2.857142857142857,
      "eval_loss": 1.1724227666854858,
      "eval_runtime": 0.2192,
      "eval_samples_per_second": 86.662,
      "eval_steps_per_second": 4.561,
      "step": 300
    },
    {
      "epoch": 3.8095238095238093,
      "grad_norm": 0.17432411015033722,
      "learning_rate": 0.0006190476190476191,
      "loss": 1.2553,
      "step": 400
    },
    {
      "epoch": 3.8095238095238093,
      "eval_loss": 1.1775765419006348,
      "eval_runtime": 0.2186,
      "eval_samples_per_second": 86.925,
      "eval_steps_per_second": 4.575,
      "step": 400
    },
    {
      "epoch": 4.761904761904762,
      "grad_norm": 0.18052713572978973,
      "learning_rate": 0.0005238095238095238,
      "loss": 1.235,
      "step": 500
    },
    {
      "epoch": 4.761904761904762,
      "eval_loss": 1.0535513162612915,
      "eval_runtime": 0.2161,
      "eval_samples_per_second": 87.904,
      "eval_steps_per_second": 4.627,
      "step": 500
    },
    {
      "epoch": 5.714285714285714,
      "grad_norm": 0.1662505716085434,
      "learning_rate": 0.00042857142857142855,
      "loss": 1.2114,
      "step": 600
    },
    {
      "epoch": 5.714285714285714,
      "eval_loss": 1.035285234451294,
      "eval_runtime": 0.2191,
      "eval_samples_per_second": 86.713,
      "eval_steps_per_second": 4.564,
      "step": 600
    },
    {
      "epoch": 6.666666666666667,
      "grad_norm": 0.16807609796524048,
      "learning_rate": 0.0003333333333333333,
      "loss": 1.1944,
      "step": 700
    },
    {
      "epoch": 6.666666666666667,
      "eval_loss": 1.0223731994628906,
      "eval_runtime": 0.2174,
      "eval_samples_per_second": 87.385,
      "eval_steps_per_second": 4.599,
      "step": 700
    },
    {
      "epoch": 7.619047619047619,
      "grad_norm": 0.20244956016540527,
      "learning_rate": 0.0002380952380952381,
      "loss": 1.1797,
      "step": 800
    },
    {
      "epoch": 7.619047619047619,
      "eval_loss": 1.049731731414795,
      "eval_runtime": 0.2231,
      "eval_samples_per_second": 85.156,
      "eval_steps_per_second": 4.482,
      "step": 800
    },
    {
      "epoch": 8.571428571428571,
      "grad_norm": 0.182796448469162,
      "learning_rate": 0.00014285714285714284,
      "loss": 1.1605,
      "step": 900
    },
    {
      "epoch": 8.571428571428571,
      "eval_loss": 1.0446473360061646,
      "eval_runtime": 0.2185,
      "eval_samples_per_second": 86.964,
      "eval_steps_per_second": 4.577,
      "step": 900
    },
    {
      "epoch": 9.523809523809524,
      "grad_norm": 0.17410966753959656,
      "learning_rate": 4.761904761904762e-05,
      "loss": 1.1496,
      "step": 1000
    },
    {
      "epoch": 9.523809523809524,
      "eval_loss": 1.027449131011963,
      "eval_runtime": 0.217,
      "eval_samples_per_second": 87.54,
      "eval_steps_per_second": 4.607,
      "step": 1000
    }
  ],
  "logging_steps": 100,
  "max_steps": 1050,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 100,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 3
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.078313589342208e+16,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}