{
  "best_global_step": 102,
  "best_metric": 0.613166332244873,
  "best_model_checkpoint": "distilbert_rand_100_v2_cola/checkpoint-102",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 272,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 1.0599257946014404,
      "learning_rate": 4.9e-05,
      "loss": 0.6127,
      "step": 34
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6912751793861389,
      "eval_loss": 0.61478590965271,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 0.4384,
      "eval_samples_per_second": 2379.274,
      "eval_steps_per_second": 11.406,
      "step": 34
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.9703173637390137,
      "learning_rate": 4.8e-05,
      "loss": 0.591,
      "step": 68
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6883988380432129,
      "eval_loss": 0.6217056512832642,
      "eval_matthews_correlation": -0.016334423518002312,
      "eval_runtime": 0.4757,
      "eval_samples_per_second": 2192.413,
      "eval_steps_per_second": 10.51,
      "step": 68
    },
    {
      "epoch": 3.0,
      "grad_norm": 2.5333664417266846,
      "learning_rate": 4.7e-05,
      "loss": 0.5421,
      "step": 102
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6826462149620056,
      "eval_loss": 0.613166332244873,
      "eval_matthews_correlation": 0.07482349006947582,
      "eval_runtime": 0.4492,
      "eval_samples_per_second": 2321.947,
      "eval_steps_per_second": 11.131,
      "step": 102
    },
    {
      "epoch": 4.0,
      "grad_norm": 4.39423942565918,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.4864,
      "step": 136
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.6596356630325317,
      "eval_loss": 0.7308068871498108,
      "eval_matthews_correlation": 0.1075004609011948,
      "eval_runtime": 0.4584,
      "eval_samples_per_second": 2275.494,
      "eval_steps_per_second": 10.908,
      "step": 136
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.305387020111084,
      "learning_rate": 4.5e-05,
      "loss": 0.4232,
      "step": 170
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.6577181220054626,
      "eval_loss": 0.752271831035614,
      "eval_matthews_correlation": 0.1393279362508076,
      "eval_runtime": 0.4369,
      "eval_samples_per_second": 2387.23,
      "eval_steps_per_second": 11.444,
      "step": 170
    },
    {
      "epoch": 6.0,
      "grad_norm": 2.593329906463623,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.3623,
      "step": 204
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.6500479578971863,
      "eval_loss": 0.8274661898612976,
      "eval_matthews_correlation": 0.11024544231549166,
      "eval_runtime": 0.5541,
      "eval_samples_per_second": 1882.371,
      "eval_steps_per_second": 9.024,
      "step": 204
    },
    {
      "epoch": 7.0,
      "grad_norm": 3.920320987701416,
      "learning_rate": 4.3e-05,
      "loss": 0.3196,
      "step": 238
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.6327900290489197,
      "eval_loss": 0.9465068578720093,
      "eval_matthews_correlation": 0.10253787164332456,
      "eval_runtime": 0.4519,
      "eval_samples_per_second": 2307.818,
      "eval_steps_per_second": 11.063,
      "step": 238
    },
    {
      "epoch": 8.0,
      "grad_norm": 3.7900238037109375,
      "learning_rate": 4.2e-05,
      "loss": 0.2848,
      "step": 272
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.6481304168701172,
      "eval_loss": 1.0343079566955566,
      "eval_matthews_correlation": 0.1313945052317705,
      "eval_runtime": 0.4753,
      "eval_samples_per_second": 2194.285,
      "eval_steps_per_second": 10.519,
      "step": 272
    },
    {
      "epoch": 8.0,
      "step": 272,
      "total_flos": 4530914903629824.0,
      "train_loss": 0.4527585190885207,
      "train_runtime": 77.9805,
      "train_samples_per_second": 5482.781,
      "train_steps_per_second": 21.8
    }
  ],
  "logging_steps": 1,
  "max_steps": 1700,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 50,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 5
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4530914903629824.0,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}