trainer_state.json

{
  "best_metric": 0.9338666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0707/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": 2.8013902315014018e-05,
      "loss": 0.8341,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8730666666666667,
      "eval_loss": 0.4385233521461487,
      "eval_runtime": 12.8605,
      "eval_samples_per_second": 291.59,
      "eval_steps_per_second": 4.588,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.886591672897339,
      "learning_rate": 2.2540814184580827e-05,
      "loss": 0.1959,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8936,
      "eval_loss": 0.35622650384902954,
      "eval_runtime": 12.6372,
      "eval_samples_per_second": 296.743,
      "eval_steps_per_second": 4.669,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 2.3111541271209717,
      "learning_rate": 1.5047170983116048e-05,
      "loss": 0.0708,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9117333333333333,
      "eval_loss": 0.34578463435173035,
      "eval_runtime": 12.2744,
      "eval_samples_per_second": 305.513,
      "eval_steps_per_second": 4.807,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.09686257690191269,
      "learning_rate": 7.5408883548191384e-06,
      "loss": 0.0208,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.928,
      "eval_loss": 0.3071032166481018,
      "eval_runtime": 14.3159,
      "eval_samples_per_second": 261.946,
      "eval_steps_per_second": 4.121,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.6218878030776978,
      "learning_rate": 2.0332686681020267e-06,
      "loss": 0.0059,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9290666666666667,
      "eval_loss": 0.29344016313552856,
      "eval_runtime": 11.7459,
      "eval_samples_per_second": 319.26,
      "eval_steps_per_second": 5.023,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.00034725910518318415,
      "learning_rate": 7.417023831113313e-11,
      "loss": 0.0024,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9338666666666666,
      "eval_loss": 0.29329216480255127,
      "eval_runtime": 13.6889,
      "eval_samples_per_second": 273.944,
      "eval_steps_per_second": 4.31,
      "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
}