trainer_state.json

{
  "best_metric": 0.8954666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0598/checkpoints/checkpoint-1665",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1665,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": Infinity,
      "learning_rate": 6.335436141135384e-05,
      "loss": 1.6532,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8146666666666667,
      "eval_loss": 0.7137821316719055,
      "eval_runtime": 6.5798,
      "eval_samples_per_second": 569.923,
      "eval_steps_per_second": 8.967,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.2562587261199951,
      "learning_rate": 4.587838279590199e-05,
      "loss": 0.5096,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8496,
      "eval_loss": 0.5254548192024231,
      "eval_runtime": 7.1811,
      "eval_samples_per_second": 522.201,
      "eval_steps_per_second": 8.216,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.0973687171936035,
      "learning_rate": 2.4247231695047696e-05,
      "loss": 0.2796,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.884,
      "eval_loss": 0.39951789379119873,
      "eval_runtime": 8.2562,
      "eval_samples_per_second": 454.202,
      "eval_steps_per_second": 7.146,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.990700900554657,
      "learning_rate": 6.723272613532589e-06,
      "loss": 0.152,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8898666666666667,
      "eval_loss": 0.37312182784080505,
      "eval_runtime": 6.4755,
      "eval_samples_per_second": 579.105,
      "eval_steps_per_second": 9.111,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.3880186080932617,
      "learning_rate": 6.230303304433081e-11,
      "loss": 0.0923,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8954666666666666,
      "eval_loss": 0.3690910041332245,
      "eval_runtime": 6.5835,
      "eval_samples_per_second": 569.609,
      "eval_steps_per_second": 8.962,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 1665,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 8.2370660311296e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}