run-2/checkpoint-660/trainer_state.json

{
  "best_metric": 0.7759666413949962,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-multiclass-classification/run-2/checkpoint-660",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 660,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6830932524639879,
      "eval_loss": 2.5022740364074707,
      "eval_runtime": 47.3562,
      "eval_samples_per_second": 55.705,
      "eval_steps_per_second": 3.484,
      "step": 330
    },
    {
      "epoch": 1.5151515151515151,
      "grad_norm": 4.026289939880371,
      "learning_rate": 1.3223614385440867e-05,
      "loss": 3.5953,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7759666413949962,
      "eval_loss": 1.721029281616211,
      "eval_runtime": 41.6218,
      "eval_samples_per_second": 63.38,
      "eval_steps_per_second": 3.964,
      "step": 660
    }
  ],
  "logging_steps": 500,
  "max_steps": 660,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 168004625104896.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 5.454740933994357e-05,
    "num_train_epochs": 2,
    "per_device_train_batch_size": 32,
    "seed": 6
  }
}