{
  "best_metric": 0.9498144023756496,
  "best_model_checkpoint": "finetune-bert-Med-SST2\\checkpoint-3792",
  "epoch": 5.0,
  "global_step": 4740,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.53,
      "learning_rate": 4.4725738396624474e-05,
      "loss": 0.3201,
      "step": 500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9319970304380104,
      "eval_loss": 0.18009190261363983,
      "eval_runtime": 8.6367,
      "eval_samples_per_second": 779.81,
      "eval_steps_per_second": 12.273,
      "step": 948
    },
    {
      "epoch": 1.05,
      "learning_rate": 3.945147679324895e-05,
      "loss": 0.2192,
      "step": 1000
    },
    {
      "epoch": 1.58,
      "learning_rate": 3.4177215189873416e-05,
      "loss": 0.1468,
      "step": 1500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9452115812917594,
      "eval_loss": 0.16460973024368286,
      "eval_runtime": 9.1827,
      "eval_samples_per_second": 733.445,
      "eval_steps_per_second": 11.543,
      "step": 1896
    },
    {
      "epoch": 2.11,
      "learning_rate": 2.8902953586497894e-05,
      "loss": 0.1255,
      "step": 2000
    },
    {
      "epoch": 2.64,
      "learning_rate": 2.3628691983122365e-05,
      "loss": 0.094,
      "step": 2500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9483296213808463,
      "eval_loss": 0.17333245277404785,
      "eval_runtime": 9.4505,
      "eval_samples_per_second": 712.663,
      "eval_steps_per_second": 11.216,
      "step": 2844
    },
    {
      "epoch": 3.16,
      "learning_rate": 1.8354430379746836e-05,
      "loss": 0.0816,
      "step": 3000
    },
    {
      "epoch": 3.69,
      "learning_rate": 1.308016877637131e-05,
      "loss": 0.0645,
      "step": 3500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9498144023756496,
      "eval_loss": 0.19728632271289825,
      "eval_runtime": 9.0479,
      "eval_samples_per_second": 744.374,
      "eval_steps_per_second": 11.715,
      "step": 3792
    },
    {
      "epoch": 4.22,
      "learning_rate": 7.805907172995782e-06,
      "loss": 0.0538,
      "step": 4000
    },
    {
      "epoch": 4.75,
      "learning_rate": 2.531645569620253e-06,
      "loss": 0.0424,
      "step": 4500
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9484780994803267,
      "eval_loss": 0.2303222268819809,
      "eval_runtime": 9.3041,
      "eval_samples_per_second": 723.873,
      "eval_steps_per_second": 11.393,
      "step": 4740
    }
  ],
  "max_steps": 4740,
  "num_train_epochs": 5,
  "total_flos": 2062420909600608.0,
  "trial_name": null,
  "trial_params": null
}