run-0/checkpoint-10/trainer_state.json

{
  "best_metric": 0.19375,
  "best_model_checkpoint": "model/image_classification/run-0/checkpoint-10",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 10,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.125,
      "eval_loss": 2.0665345191955566,
      "eval_runtime": 1.0008,
      "eval_samples_per_second": 159.877,
      "eval_steps_per_second": 9.992,
      "step": 5
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.5518031120300293,
      "learning_rate": 1.2223590254554655e-05,
      "loss": 2.0611,
      "step": 10
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.19375,
      "eval_loss": 2.0526061058044434,
      "eval_runtime": 1.6216,
      "eval_samples_per_second": 98.67,
      "eval_steps_per_second": 6.167,
      "step": 10
    }
  ],
  "logging_steps": 10,
  "max_steps": 15,
  "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": 9.919508074463232e+16,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 3.17813346618421e-05,
    "per_device_train_batch_size": 64
  }
}