run-5/checkpoint-1319/trainer_state.json

{
  "best_metric": 0.7748294162244125,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-multiclass-classification/run-5/checkpoint-1319",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 1319,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.37907505686125853,
      "grad_norm": 8.771978378295898,
      "learning_rate": 3.260044405980062e-05,
      "loss": 4.6874,
      "step": 500
    },
    {
      "epoch": 0.7581501137225171,
      "grad_norm": 5.153038024902344,
      "learning_rate": 1.2697853058701342e-05,
      "loss": 2.3845,
      "step": 1000
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7748294162244125,
      "eval_loss": 1.6632747650146484,
      "eval_runtime": 243.8181,
      "eval_samples_per_second": 10.82,
      "eval_steps_per_second": 0.677,
      "step": 1319
    }
  ],
  "logging_steps": 500,
  "max_steps": 1319,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 73159059439616.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 5.2503035060899905e-05,
    "num_train_epochs": 1,
    "per_device_train_batch_size": 8,
    "seed": 16
  }
}