{
  "best_metric": 0.5091743119266054,
  "best_model_checkpoint": "electra-distilled-sst\\run-2\\checkpoint-527",
  "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": 3.510751485824585,
      "learning_rate": 0.0007235764985208607,
      "loss": 4.9041,
      "step": 527
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5091743119266054,
      "eval_loss": 4.841418266296387,
      "eval_runtime": 1.4537,
      "eval_samples_per_second": 599.861,
      "eval_steps_per_second": 4.815,
      "step": 527
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.5188323259353638,
      "learning_rate": 0.0005789160983992775,
      "loss": 4.9002,
      "step": 1054
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5091743119266054,
      "eval_loss": 4.816441059112549,
      "eval_runtime": 1.4412,
      "eval_samples_per_second": 605.042,
      "eval_steps_per_second": 4.857,
      "step": 1054
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.3247452974319458,
      "learning_rate": 0.00043425569827769417,
      "loss": 4.9,
      "step": 1581
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.5091743119266054,
      "eval_loss": 4.82835054397583,
      "eval_runtime": 1.4366,
      "eval_samples_per_second": 606.994,
      "eval_steps_per_second": 4.873,
      "step": 1581
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.6336215734481812,
      "learning_rate": 0.0002895952981561108,
      "loss": 4.893,
      "step": 2108
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.5091743119266054,
      "eval_loss": 4.868070602416992,
      "eval_runtime": 1.4415,
      "eval_samples_per_second": 604.928,
      "eval_steps_per_second": 4.856,
      "step": 2108
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.2643113136291504,
      "learning_rate": 0.0001449348980345275,
      "loss": 4.8991,
      "step": 2635
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.5091743119266054,
      "eval_loss": 4.832038879394531,
      "eval_runtime": 1.448,
      "eval_samples_per_second": 602.191,
      "eval_steps_per_second": 4.834,
      "step": 2635
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.2564785480499268,
      "learning_rate": 2.744979129441809e-07,
      "loss": 4.8938,
      "step": 3162
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.5091743119266054,
      "eval_loss": 4.896666526794434,
      "eval_runtime": 1.4438,
      "eval_samples_per_second": 603.96,
      "eval_steps_per_second": 4.848,
      "step": 3162
    }
  ],
  "logging_steps": 500,
  "max_steps": 3162,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 500,
  "total_flos": 1123721737396596.0,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.2011698337552854,
    "learning_rate": 0.0008679624007294999,
    "num_train_epochs": 6,
    "temperature": 5
  }
}