trainer_state.json

{
  "best_metric": 0.8706666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0940/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": 2.0494513511657715,
      "learning_rate": 0.0001,
      "loss": 1.4659,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7882666666666667,
      "eval_loss": 0.7099961638450623,
      "eval_runtime": 5.5958,
      "eval_samples_per_second": 670.144,
      "eval_steps_per_second": 10.544,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0001,
      "loss": 0.4991,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8309333333333333,
      "eval_loss": 0.5604985952377319,
      "eval_runtime": 5.5837,
      "eval_samples_per_second": 671.6,
      "eval_steps_per_second": 10.567,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0001,
      "loss": 0.3141,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8413333333333334,
      "eval_loss": 0.5070641040802002,
      "eval_runtime": 5.3519,
      "eval_samples_per_second": 700.686,
      "eval_steps_per_second": 11.024,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.4092743694782257,
      "learning_rate": 0.0001,
      "loss": 0.2214,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8669333333333333,
      "eval_loss": 0.4551438093185425,
      "eval_runtime": 5.8194,
      "eval_samples_per_second": 644.397,
      "eval_steps_per_second": 10.139,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.3775405883789062,
      "learning_rate": 0.0001,
      "loss": 0.1636,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8706666666666667,
      "eval_loss": 0.4442083537578583,
      "eval_runtime": 5.3775,
      "eval_samples_per_second": 697.346,
      "eval_steps_per_second": 10.972,
      "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
}