trainer_state.json

{
  "best_metric": 0.8658666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0608/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": 2.886495269365963e-05,
      "loss": 2.2656,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7578666666666667,
      "eval_loss": 1.1132102012634277,
      "eval_runtime": 6.9075,
      "eval_samples_per_second": 542.888,
      "eval_steps_per_second": 8.541,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 8.983711242675781,
      "learning_rate": 2.5619102456015873e-05,
      "loss": 0.765,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8109333333333333,
      "eval_loss": 0.7142021059989929,
      "eval_runtime": 6.1477,
      "eval_samples_per_second": 609.981,
      "eval_steps_per_second": 9.597,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 2.0772920772568672e-05,
      "loss": 0.4125,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8461333333333333,
      "eval_loss": 0.5443850755691528,
      "eval_runtime": 6.2127,
      "eval_samples_per_second": 603.605,
      "eval_steps_per_second": 9.497,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 23.110733032226562,
      "learning_rate": 1.5035378262848308e-05,
      "loss": 0.2276,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8610666666666666,
      "eval_loss": 0.50003981590271,
      "eval_runtime": 6.139,
      "eval_samples_per_second": 610.853,
      "eval_steps_per_second": 9.611,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 8.78666877746582,
      "learning_rate": 9.292449733314041e-06,
      "loss": 0.1218,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8658666666666667,
      "eval_loss": 0.48771336674690247,
      "eval_runtime": 6.4413,
      "eval_samples_per_second": 582.18,
      "eval_steps_per_second": 9.16,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 2664,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "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
}