run-39/checkpoint-1100/trainer_state.json

{
  "best_metric": 0.9306122448979591,
  "best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-39\\checkpoint-1100",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 1100,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8653061224489796,
      "eval_loss": 0.5870106220245361,
      "eval_runtime": 1.459,
      "eval_samples_per_second": 167.923,
      "eval_steps_per_second": 10.966,
      "step": 275
    },
    {
      "epoch": 1.82,
      "learning_rate": 3.829606216423644e-05,
      "loss": 0.9249,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8979591836734694,
      "eval_loss": 0.38964176177978516,
      "eval_runtime": 1.361,
      "eval_samples_per_second": 180.015,
      "eval_steps_per_second": 11.756,
      "step": 550
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9142857142857143,
      "eval_loss": 0.3397238254547119,
      "eval_runtime": 1.452,
      "eval_samples_per_second": 168.733,
      "eval_steps_per_second": 11.019,
      "step": 825
    },
    {
      "epoch": 3.64,
      "learning_rate": 6.382677027372741e-06,
      "loss": 0.2985,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9306122448979591,
      "eval_loss": 0.3207901120185852,
      "eval_runtime": 1.266,
      "eval_samples_per_second": 193.523,
      "eval_steps_per_second": 12.638,
      "step": 1100
    }
  ],
  "logging_steps": 500,
  "max_steps": 1100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "total_flos": 5124210082950.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 7.020944730110015e-05,
    "num_train_epochs": 4,
    "per_device_train_batch_size": 8,
    "seed": 33
  }
}