trainer_state.json

{
  "best_metric": 0.2733333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0812/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": 22.1275634765625,
      "learning_rate": 0.0005,
      "loss": 3.4891,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.1808,
      "eval_loss": 3.072533369064331,
      "eval_runtime": 12.0121,
      "eval_samples_per_second": 312.185,
      "eval_steps_per_second": 4.912,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 19.392213821411133,
      "learning_rate": 0.0005,
      "loss": 2.9984,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.18986666666666666,
      "eval_loss": 2.9651596546173096,
      "eval_runtime": 11.1495,
      "eval_samples_per_second": 336.338,
      "eval_steps_per_second": 5.292,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 19.647382736206055,
      "learning_rate": 0.0005,
      "loss": 2.8432,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.24586666666666668,
      "eval_loss": 2.779160499572754,
      "eval_runtime": 11.2252,
      "eval_samples_per_second": 334.068,
      "eval_steps_per_second": 5.256,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 22.40318489074707,
      "learning_rate": 0.0005,
      "loss": 2.7288,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.25493333333333335,
      "eval_loss": 2.7899370193481445,
      "eval_runtime": 11.3061,
      "eval_samples_per_second": 331.679,
      "eval_steps_per_second": 5.218,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 18.036577224731445,
      "learning_rate": 0.0005,
      "loss": 2.6248,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.2733333333333333,
      "eval_loss": 2.688206195831299,
      "eval_runtime": 11.0445,
      "eval_samples_per_second": 339.536,
      "eval_steps_per_second": 5.342,
      "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
}