{
  "best_metric": 0.8302752293577982,
  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-12/checkpoint-527",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 1054,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 9.690923690795898,
      "learning_rate": 0.0003321213172401304,
      "loss": 1.3202,
      "step": 527
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8302752293577982,
      "eval_loss": 1.4912840127944946,
      "eval_runtime": 2.8077,
      "eval_samples_per_second": 310.575,
      "eval_steps_per_second": 2.493,
      "step": 527
    },
    {
      "epoch": 2.0,
      "grad_norm": 8.249791145324707,
      "learning_rate": 0.0002767677643667753,
      "loss": 0.5967,
      "step": 1054
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8107798165137615,
      "eval_loss": 1.6795676946640015,
      "eval_runtime": 2.8151,
      "eval_samples_per_second": 309.763,
      "eval_steps_per_second": 2.487,
      "step": 1054
    }
  ],
  "logging_steps": 500,
  "max_steps": 3689,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "save_steps": 500,
  "total_flos": 16141525436100.0,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.3539642822905392,
    "learning_rate": 0.00038747487011348545,
    "num_train_epochs": 7,
    "temperature": 26
  }
}