trainer_state.json

{
  "best_metric": 0.9045333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0933/checkpoints/checkpoint-1998",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 1998,
  "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": 4.667026293130983e-05,
      "loss": 2.0139,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7898666666666667,
      "eval_loss": 0.880171000957489,
      "eval_runtime": 6.3766,
      "eval_samples_per_second": 588.087,
      "eval_steps_per_second": 9.253,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 3.7568023640968045e-05,
      "loss": 0.6013,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8546666666666667,
      "eval_loss": 0.5458696484565735,
      "eval_runtime": 6.1382,
      "eval_samples_per_second": 610.928,
      "eval_steps_per_second": 9.612,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 2.511792721482581e-05,
      "loss": 0.3151,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8765333333333334,
      "eval_loss": 0.43392670154571533,
      "eval_runtime": 6.4814,
      "eval_samples_per_second": 578.579,
      "eval_steps_per_second": 9.103,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.9991635084152222,
      "learning_rate": 1.2602267032890267e-05,
      "loss": 0.1706,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8976,
      "eval_loss": 0.3659414052963257,
      "eval_runtime": 6.7474,
      "eval_samples_per_second": 555.771,
      "eval_steps_per_second": 8.744,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.16245365142822266,
      "learning_rate": 3.4085693874684883e-06,
      "loss": 0.0914,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8962666666666667,
      "eval_loss": 0.3597579300403595,
      "eval_runtime": 6.196,
      "eval_samples_per_second": 605.227,
      "eval_steps_per_second": 9.522,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.1129230260849,
      "learning_rate": 2.7813810714871767e-10,
      "loss": 0.0605,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9045333333333333,
      "eval_loss": 0.3509753942489624,
      "eval_runtime": 7.0662,
      "eval_samples_per_second": 530.695,
      "eval_steps_per_second": 8.35,
      "step": 1998
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.88447923735552e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}