trainer_state.json

{
  "best_metric": 0.8824,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0433/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": 9.050623058764834e-05,
      "loss": 1.8265,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7645333333333333,
      "eval_loss": 0.8377467393875122,
      "eval_runtime": 13.5712,
      "eval_samples_per_second": 276.321,
      "eval_steps_per_second": 4.347,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.6916622519493103,
      "learning_rate": 6.554054685128856e-05,
      "loss": 0.5699,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8317333333333333,
      "eval_loss": 0.5516128540039062,
      "eval_runtime": 13.8149,
      "eval_samples_per_second": 271.446,
      "eval_steps_per_second": 4.271,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 4.642654895782471,
      "learning_rate": 3.463890242149672e-05,
      "loss": 0.3126,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8592,
      "eval_loss": 0.439180850982666,
      "eval_runtime": 13.5015,
      "eval_samples_per_second": 277.747,
      "eval_steps_per_second": 4.37,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 3.929929256439209,
      "learning_rate": 9.604675162189414e-06,
      "loss": 0.1571,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8776,
      "eval_loss": 0.4001615047454834,
      "eval_runtime": 14.0952,
      "eval_samples_per_second": 266.048,
      "eval_steps_per_second": 4.186,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.5508679151535034,
      "learning_rate": 8.900433292047261e-11,
      "loss": 0.0882,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8824,
      "eval_loss": 0.38422995805740356,
      "eval_runtime": 13.134,
      "eval_samples_per_second": 285.519,
      "eval_steps_per_second": 4.492,
      "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
}