trainer_state.json

{
  "best_metric": 0.31466666666666665,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0534/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": 18.903831481933594,
      "learning_rate": 0.00045280733623674006,
      "loss": 3.5395,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.15333333333333332,
      "eval_loss": 3.2064297199249268,
      "eval_runtime": 5.4446,
      "eval_samples_per_second": 688.762,
      "eval_steps_per_second": 10.837,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 19.28752899169922,
      "learning_rate": 0.0003281509432839476,
      "loss": 3.0423,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.20826666666666666,
      "eval_loss": 2.961078643798828,
      "eval_runtime": 5.3693,
      "eval_samples_per_second": 698.411,
      "eval_steps_per_second": 10.988,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 15.257349014282227,
      "learning_rate": 0.0001736435462495525,
      "loss": 2.7946,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.26,
      "eval_loss": 2.7415125370025635,
      "eval_runtime": 5.6521,
      "eval_samples_per_second": 663.466,
      "eval_steps_per_second": 10.439,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 20.708126068115234,
      "learning_rate": 4.8301719287419e-05,
      "loss": 2.5551,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.308,
      "eval_loss": 2.5724639892578125,
      "eval_runtime": 5.7509,
      "eval_samples_per_second": 652.066,
      "eval_steps_per_second": 10.259,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 26.43875503540039,
      "learning_rate": 1.7800850740101736e-09,
      "loss": 2.3588,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.31466666666666665,
      "eval_loss": 2.5401830673217773,
      "eval_runtime": 5.3179,
      "eval_samples_per_second": 705.169,
      "eval_steps_per_second": 11.095,
      "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
}