trainer_state.json

{
  "best_metric": 0.8904,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0215/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": 1.5618,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7877333333333333,
      "eval_loss": 0.7533043026924133,
      "eval_runtime": 6.3346,
      "eval_samples_per_second": 591.991,
      "eval_steps_per_second": 9.314,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.4356204271316528,
      "learning_rate": 6.554054685128856e-05,
      "loss": 0.5096,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8429333333333333,
      "eval_loss": 0.5287975668907166,
      "eval_runtime": 6.321,
      "eval_samples_per_second": 593.258,
      "eval_steps_per_second": 9.334,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 3.2158467769622803,
      "learning_rate": 3.463890242149672e-05,
      "loss": 0.2511,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8661333333333333,
      "eval_loss": 0.43497154116630554,
      "eval_runtime": 6.3925,
      "eval_samples_per_second": 586.627,
      "eval_steps_per_second": 9.23,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.17899739742279053,
      "learning_rate": 9.604675162189414e-06,
      "loss": 0.1128,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8848,
      "eval_loss": 0.3871922194957733,
      "eval_runtime": 6.3308,
      "eval_samples_per_second": 592.34,
      "eval_steps_per_second": 9.319,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.16846045851707458,
      "learning_rate": 8.900433292047261e-11,
      "loss": 0.0542,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8904,
      "eval_loss": 0.37928444147109985,
      "eval_runtime": 6.2801,
      "eval_samples_per_second": 597.122,
      "eval_steps_per_second": 9.395,
      "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
}