trainer_state.json

{
  "best_metric": 0.8981333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0409/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": Infinity,
      "learning_rate": 3e-05,
      "loss": 0.7873,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.872,
      "eval_loss": 0.39735156297683716,
      "eval_runtime": 11.3407,
      "eval_samples_per_second": 330.668,
      "eval_steps_per_second": 5.203,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 13.334736824035645,
      "learning_rate": 3e-05,
      "loss": 0.2197,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8802666666666666,
      "eval_loss": 0.3751755356788635,
      "eval_runtime": 10.9964,
      "eval_samples_per_second": 341.021,
      "eval_steps_per_second": 5.365,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 3e-05,
      "loss": 0.1168,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8914666666666666,
      "eval_loss": 0.37416237592697144,
      "eval_runtime": 10.958,
      "eval_samples_per_second": 342.214,
      "eval_steps_per_second": 5.384,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.11007500439882278,
      "learning_rate": 3e-05,
      "loss": 0.0712,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8946666666666667,
      "eval_loss": 0.3905999958515167,
      "eval_runtime": 12.416,
      "eval_samples_per_second": 302.029,
      "eval_steps_per_second": 4.752,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 5.574729919433594,
      "learning_rate": 3e-05,
      "loss": 0.0505,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8981333333333333,
      "eval_loss": 0.39801353216171265,
      "eval_runtime": 11.1246,
      "eval_samples_per_second": 337.091,
      "eval_steps_per_second": 5.304,
      "step": 1665
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8.2370660311296e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}