run-31/checkpoint-140/trainer_state.json

{
  "best_metric": 0.8530612244897959,
  "best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-31\\checkpoint-140",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 140,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6081632653061224,
      "eval_loss": 1.724165678024292,
      "eval_runtime": 1.389,
      "eval_samples_per_second": 176.386,
      "eval_steps_per_second": 11.519,
      "step": 35
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.689795918367347,
      "eval_loss": 1.23240065574646,
      "eval_runtime": 1.385,
      "eval_samples_per_second": 176.896,
      "eval_steps_per_second": 11.552,
      "step": 70
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8204081632653061,
      "eval_loss": 0.9874038100242615,
      "eval_runtime": 1.321,
      "eval_samples_per_second": 185.465,
      "eval_steps_per_second": 12.112,
      "step": 105
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8530612244897959,
      "eval_loss": 0.8668258786201477,
      "eval_runtime": 1.473,
      "eval_samples_per_second": 166.327,
      "eval_steps_per_second": 10.862,
      "step": 140
    }
  ],
  "logging_steps": 500,
  "max_steps": 175,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 6.662510819793869e-05,
    "num_train_epochs": 5,
    "per_device_train_batch_size": 64,
    "seed": 37
  }
}