trainer_state.json

{
  "best_metric": 0.8698666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0726/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": 0.9529489278793335,
      "learning_rate": 7e-05,
      "loss": 0.7541,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8645333333333334,
      "eval_loss": 0.44687390327453613,
      "eval_runtime": 11.1233,
      "eval_samples_per_second": 337.13,
      "eval_steps_per_second": 5.304,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.980046033859253,
      "learning_rate": 7e-05,
      "loss": 0.2529,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8653333333333333,
      "eval_loss": 0.45164477825164795,
      "eval_runtime": 11.0943,
      "eval_samples_per_second": 338.01,
      "eval_steps_per_second": 5.318,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.06635447591543198,
      "learning_rate": 7e-05,
      "loss": 0.1586,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8536,
      "eval_loss": 0.5128637552261353,
      "eval_runtime": 11.0646,
      "eval_samples_per_second": 338.918,
      "eval_steps_per_second": 5.332,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.055631011724472046,
      "learning_rate": 7e-05,
      "loss": 0.1139,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8629333333333333,
      "eval_loss": 0.5581709742546082,
      "eval_runtime": 10.8874,
      "eval_samples_per_second": 344.436,
      "eval_steps_per_second": 5.419,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.1237434521317482,
      "learning_rate": 7e-05,
      "loss": 0.0972,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8698666666666667,
      "eval_loss": 0.52906733751297,
      "eval_runtime": 10.9347,
      "eval_samples_per_second": 342.946,
      "eval_steps_per_second": 5.396,
      "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
}