run-32/checkpoint-1650/trainer_state.json

{
  "best_metric": 0.9306122448979591,
  "best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-32\\checkpoint-1100",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 1650,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.91,
      "learning_rate": 7.264057606305507e-05,
      "loss": 0.9695,
      "step": 500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9020408163265307,
      "eval_loss": 0.38033971190452576,
      "eval_runtime": 2.0971,
      "eval_samples_per_second": 116.827,
      "eval_steps_per_second": 7.63,
      "step": 550
    },
    {
      "epoch": 1.82,
      "learning_rate": 5.1275700750391815e-05,
      "loss": 0.3376,
      "step": 1000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9306122448979591,
      "eval_loss": 0.34555086493492126,
      "eval_runtime": 1.233,
      "eval_samples_per_second": 198.702,
      "eval_steps_per_second": 12.976,
      "step": 1100
    },
    {
      "epoch": 2.73,
      "learning_rate": 2.9910825437728558e-05,
      "loss": 0.2431,
      "step": 1500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9183673469387755,
      "eval_loss": 0.36502838134765625,
      "eval_runtime": 1.309,
      "eval_samples_per_second": 187.166,
      "eval_steps_per_second": 12.223,
      "step": 1650
    }
  ],
  "logging_steps": 500,
  "max_steps": 2200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "total_flos": 2875206111750.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 9.400545137571833e-05,
    "num_train_epochs": 4,
    "per_device_train_batch_size": 4,
    "seed": 37
  }
}