trainer_state.json

{
  "best_metric": 0.3797333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0327/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": 0.0004672882479004997,
      "loss": 3.4288,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.1824,
      "eval_loss": 3.0537383556365967,
      "eval_runtime": 6.5246,
      "eval_samples_per_second": 574.748,
      "eval_steps_per_second": 9.043,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 22.870532989501953,
      "learning_rate": 0.0003763592299216161,
      "loss": 2.8909,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.2312,
      "eval_loss": 2.8414385318756104,
      "eval_runtime": 6.9208,
      "eval_samples_per_second": 541.848,
      "eval_steps_per_second": 8.525,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 21.67360496520996,
      "learning_rate": 0.00025157235832901694,
      "loss": 2.6536,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.2968,
      "eval_loss": 2.587167739868164,
      "eval_runtime": 6.6082,
      "eval_samples_per_second": 567.477,
      "eval_steps_per_second": 8.928,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 16.258691787719727,
      "learning_rate": 0.00012636417459194535,
      "loss": 2.4134,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.3408,
      "eval_loss": 2.420621871948242,
      "eval_runtime": 6.4244,
      "eval_samples_per_second": 583.712,
      "eval_steps_per_second": 9.184,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 24.15997886657715,
      "learning_rate": 3.4284110428517254e-05,
      "loss": 2.1659,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.37173333333333336,
      "eval_loss": 2.2828712463378906,
      "eval_runtime": 6.7442,
      "eval_samples_per_second": 556.035,
      "eval_steps_per_second": 8.748,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 29.36591148376465,
      "learning_rate": 4.944670329187772e-09,
      "loss": 1.9562,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.3797333333333333,
      "eval_loss": 2.268617630004883,
      "eval_runtime": 6.929,
      "eval_samples_per_second": 541.204,
      "eval_steps_per_second": 8.515,
      "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
}