run-4/checkpoint-20/trainer_state.json

{
  "best_metric": 0.13125,
  "best_model_checkpoint": "model/image_classification/run-4/checkpoint-20",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 20,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5,
      "grad_norm": 1.0558984279632568,
      "learning_rate": 1.1573843762670946e-05,
      "loss": 2.0691,
      "step": 10
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.9791191816329956,
      "learning_rate": 9.259075010136756e-06,
      "loss": 2.0787,
      "step": 20
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.13125,
      "eval_loss": 2.066149950027466,
      "eval_runtime": 0.8295,
      "eval_samples_per_second": 192.878,
      "eval_steps_per_second": 12.055,
      "step": 20
    }
  ],
  "logging_steps": 10,
  "max_steps": 60,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.959754037231616e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 1.2499751263684622e-05,
    "per_device_train_batch_size": 16
  }
}