{
  "best_metric": 0.8256880733944955,
  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-2/checkpoint-3162",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 3162,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 7.996350288391113,
      "learning_rate": 4.4413546405567984e-05,
      "loss": 0.7876,
      "step": 527
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7981651376146789,
      "eval_loss": 0.6943275928497314,
      "eval_runtime": 2.3933,
      "eval_samples_per_second": 364.358,
      "eval_steps_per_second": 2.925,
      "step": 527
    },
    {
      "epoch": 2.0,
      "grad_norm": 13.94997501373291,
      "learning_rate": 3.5530837124454385e-05,
      "loss": 0.5209,
      "step": 1054
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8073394495412844,
      "eval_loss": 0.6490799188613892,
      "eval_runtime": 2.4002,
      "eval_samples_per_second": 363.309,
      "eval_steps_per_second": 2.916,
      "step": 1054
    },
    {
      "epoch": 3.0,
      "grad_norm": 19.503337860107422,
      "learning_rate": 2.664812784334079e-05,
      "loss": 0.424,
      "step": 1581
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8176605504587156,
      "eval_loss": 0.6499952077865601,
      "eval_runtime": 2.4027,
      "eval_samples_per_second": 362.926,
      "eval_steps_per_second": 2.913,
      "step": 1581
    },
    {
      "epoch": 4.0,
      "grad_norm": 9.7010498046875,
      "learning_rate": 1.7765418562227192e-05,
      "loss": 0.3755,
      "step": 2108
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8245412844036697,
      "eval_loss": 0.6426727771759033,
      "eval_runtime": 2.4119,
      "eval_samples_per_second": 361.543,
      "eval_steps_per_second": 2.902,
      "step": 2108
    },
    {
      "epoch": 5.0,
      "grad_norm": 4.362422466278076,
      "learning_rate": 8.882709281113596e-06,
      "loss": 0.3458,
      "step": 2635
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8222477064220184,
      "eval_loss": 0.6740634441375732,
      "eval_runtime": 2.4095,
      "eval_samples_per_second": 361.895,
      "eval_steps_per_second": 2.905,
      "step": 2635
    },
    {
      "epoch": 6.0,
      "grad_norm": 8.87090015411377,
      "learning_rate": 0.0,
      "loss": 0.33,
      "step": 3162
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8256880733944955,
      "eval_loss": 0.6871433258056641,
      "eval_runtime": 2.3947,
      "eval_samples_per_second": 364.141,
      "eval_steps_per_second": 2.923,
      "step": 3162
    }
  ],
  "logging_steps": 500,
  "max_steps": 3162,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 48527917525620.0,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.9051524134827537,
    "learning_rate": 5.329625568668158e-05,
    "num_train_epochs": 6,
    "temperature": 18
  }
}