trainer_state.json

{
  "best_metric": 0.3781333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0986/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": 0.0003,
      "loss": 3.3096,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.20986666666666667,
      "eval_loss": 2.9822781085968018,
      "eval_runtime": 7.8551,
      "eval_samples_per_second": 477.395,
      "eval_steps_per_second": 7.511,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0003,
      "loss": 2.7935,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.2712,
      "eval_loss": 2.6845099925994873,
      "eval_runtime": 6.8122,
      "eval_samples_per_second": 550.481,
      "eval_steps_per_second": 8.661,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 27.177631378173828,
      "learning_rate": 0.0003,
      "loss": 2.5675,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.3178666666666667,
      "eval_loss": 2.5167083740234375,
      "eval_runtime": 11.5926,
      "eval_samples_per_second": 323.483,
      "eval_steps_per_second": 5.089,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 25.309585571289062,
      "learning_rate": 0.0003,
      "loss": 2.3725,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.3509333333333333,
      "eval_loss": 2.4060797691345215,
      "eval_runtime": 6.2154,
      "eval_samples_per_second": 603.341,
      "eval_steps_per_second": 9.493,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 24.136070251464844,
      "learning_rate": 0.0003,
      "loss": 2.2009,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.3544,
      "eval_loss": 2.3295741081237793,
      "eval_runtime": 6.3114,
      "eval_samples_per_second": 594.166,
      "eval_steps_per_second": 9.348,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 16.585060119628906,
      "learning_rate": 0.0003,
      "loss": 2.0578,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.3781333333333333,
      "eval_loss": 2.2600655555725098,
      "eval_runtime": 6.2415,
      "eval_samples_per_second": 600.819,
      "eval_steps_per_second": 9.453,
      "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
}