trainer_state.json

{
  "best_metric": 0.6405333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0165/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": 0.0005,
      "loss": 2.8514,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.33413333333333334,
      "eval_loss": 2.472294807434082,
      "eval_runtime": 5.6252,
      "eval_samples_per_second": 666.64,
      "eval_steps_per_second": 10.488,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 8.597536087036133,
      "learning_rate": 0.0005,
      "loss": 2.0372,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.4496,
      "eval_loss": 1.9174447059631348,
      "eval_runtime": 6.5307,
      "eval_samples_per_second": 574.214,
      "eval_steps_per_second": 9.034,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0005,
      "loss": 1.5185,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.5413333333333333,
      "eval_loss": 1.5955629348754883,
      "eval_runtime": 5.8374,
      "eval_samples_per_second": 642.414,
      "eval_steps_per_second": 10.107,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 13.44753360748291,
      "learning_rate": 0.0005,
      "loss": 1.1735,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.5994666666666667,
      "eval_loss": 1.3905518054962158,
      "eval_runtime": 7.3651,
      "eval_samples_per_second": 509.16,
      "eval_steps_per_second": 8.011,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 8.137077331542969,
      "learning_rate": 0.0005,
      "loss": 0.9222,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.6405333333333333,
      "eval_loss": 1.2264741659164429,
      "eval_runtime": 6.6339,
      "eval_samples_per_second": 565.278,
      "eval_steps_per_second": 8.894,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 1998,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "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": 8.2370660311296e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}