trainer_state.json

{
  "best_metric": 0.8816,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0867/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": 8.145560752888351e-05,
      "loss": 1.5837,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7773333333333333,
      "eval_loss": 0.7936049699783325,
      "eval_runtime": 13.5046,
      "eval_samples_per_second": 277.684,
      "eval_steps_per_second": 4.369,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 5.9067169791110576e-05,
      "loss": 0.5419,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8309333333333333,
      "eval_loss": 0.559667706489563,
      "eval_runtime": 14.1316,
      "eval_samples_per_second": 265.362,
      "eval_steps_per_second": 4.175,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.35125258564949036,
      "learning_rate": 3.125583832491945e-05,
      "loss": 0.3009,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.86,
      "eval_loss": 0.4793495535850525,
      "eval_runtime": 13.197,
      "eval_samples_per_second": 284.154,
      "eval_steps_per_second": 4.471,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 2.8207499980926514,
      "learning_rate": 8.69430947173542e-06,
      "loss": 0.1614,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8765333333333334,
      "eval_loss": 0.40925365686416626,
      "eval_runtime": 13.5404,
      "eval_samples_per_second": 276.948,
      "eval_steps_per_second": 4.357,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.6444017887115479,
      "learning_rate": 3.204153133218313e-10,
      "loss": 0.0976,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8816,
      "eval_loss": 0.40040379762649536,
      "eval_runtime": 13.186,
      "eval_samples_per_second": 284.393,
      "eval_steps_per_second": 4.474,
      "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
}