trainer_state.json

{
  "best_metric": 0.31893333333333335,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0323/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": 21.066829681396484,
      "learning_rate": 0.0005,
      "loss": 3.3548,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.1912,
      "eval_loss": 2.990565299987793,
      "eval_runtime": 14.6415,
      "eval_samples_per_second": 256.121,
      "eval_steps_per_second": 4.03,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 14.305747032165527,
      "learning_rate": 0.0005,
      "loss": 2.8905,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.2168,
      "eval_loss": 2.899216651916504,
      "eval_runtime": 13.6592,
      "eval_samples_per_second": 274.539,
      "eval_steps_per_second": 4.319,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 15.26677131652832,
      "learning_rate": 0.0005,
      "loss": 2.7387,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.2664,
      "eval_loss": 2.715224027633667,
      "eval_runtime": 13.4339,
      "eval_samples_per_second": 279.144,
      "eval_steps_per_second": 4.392,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 22.080951690673828,
      "learning_rate": 0.0005,
      "loss": 2.6384,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.2768,
      "eval_loss": 2.630704641342163,
      "eval_runtime": 13.4468,
      "eval_samples_per_second": 278.877,
      "eval_steps_per_second": 4.388,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 19.945911407470703,
      "learning_rate": 0.0005,
      "loss": 2.5443,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.28373333333333334,
      "eval_loss": 2.6373984813690186,
      "eval_runtime": 13.212,
      "eval_samples_per_second": 283.834,
      "eval_steps_per_second": 4.466,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 19.239683151245117,
      "learning_rate": 0.0005,
      "loss": 2.4456,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.31893333333333335,
      "eval_loss": 2.4676644802093506,
      "eval_runtime": 13.552,
      "eval_samples_per_second": 276.713,
      "eval_steps_per_second": 4.354,
      "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
}