run-33/checkpoint-5745/trainer_state.json

{
  "best_metric": 0.8752285191956124,
  "best_model_checkpoint": "berttiny-hate_speech18-bothpretrained\\run-33\\checkpoint-5745",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 5745,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 6.504293559544375e-05,
      "loss": 0.475,
      "step": 1915
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8670018281535649,
      "eval_loss": 0.4712733030319214,
      "eval_runtime": 10.7467,
      "eval_samples_per_second": 203.598,
      "eval_steps_per_second": 1.675,
      "step": 1915
    },
    {
      "epoch": 2.0,
      "learning_rate": 3.2521467797721874e-05,
      "loss": 0.4508,
      "step": 3830
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8720292504570384,
      "eval_loss": 0.4779040515422821,
      "eval_runtime": 10.596,
      "eval_samples_per_second": 206.493,
      "eval_steps_per_second": 1.699,
      "step": 3830
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.0,
      "loss": 0.437,
      "step": 5745
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8752285191956124,
      "eval_loss": 0.4793665409088135,
      "eval_runtime": 10.7163,
      "eval_samples_per_second": 204.176,
      "eval_steps_per_second": 1.68,
      "step": 5745
    }
  ],
  "logging_steps": 500,
  "max_steps": 5745,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 2321197668864.0,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 9.756440339316564e-05,
    "num_train_epochs": 3,
    "per_device_train_batch_size": 4,
    "seed": 35
  }
}