run-49/checkpoint-1437/trainer_state.json

{
  "best_metric": 0.8779707495429616,
  "best_model_checkpoint": "berttiny-hate_speech18-bothpretrained\\run-49\\checkpoint-1437",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 1437,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 5.71543010766675e-05,
      "loss": 0.4804,
      "step": 479
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8624314442413162,
      "eval_loss": 0.47775161266326904,
      "eval_runtime": 10.8435,
      "eval_samples_per_second": 201.78,
      "eval_steps_per_second": 1.66,
      "step": 479
    },
    {
      "epoch": 2.0,
      "learning_rate": 3.8102867384445e-05,
      "loss": 0.4592,
      "step": 958
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8761425959780622,
      "eval_loss": 0.46876460313796997,
      "eval_runtime": 10.9195,
      "eval_samples_per_second": 200.376,
      "eval_steps_per_second": 1.648,
      "step": 958
    },
    {
      "epoch": 3.0,
      "learning_rate": 1.90514336922225e-05,
      "loss": 0.4471,
      "step": 1437
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8779707495429616,
      "eval_loss": 0.46814361214637756,
      "eval_runtime": 10.7926,
      "eval_samples_per_second": 202.732,
      "eval_steps_per_second": 1.668,
      "step": 1437
    }
  ],
  "logging_steps": 500,
  "max_steps": 1916,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "total_flos": 3716168818752.0,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 7.620573476889e-05,
    "num_train_epochs": 4,
    "per_device_train_batch_size": 16,
    "seed": 30
  }
}