trainer_state.json

{
  "best_metric": 0.3914666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0714/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": 26.085092544555664,
      "learning_rate": 0.00027184967850358286,
      "loss": 3.3639,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.18,
      "eval_loss": 3.01604962348938,
      "eval_runtime": 11.1691,
      "eval_samples_per_second": 335.748,
      "eval_steps_per_second": 5.282,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 20.363000869750977,
      "learning_rate": 0.00019715932444832964,
      "loss": 2.7366,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.2784,
      "eval_loss": 2.623009443283081,
      "eval_runtime": 10.419,
      "eval_samples_per_second": 359.918,
      "eval_steps_per_second": 5.663,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 43.61204147338867,
      "learning_rate": 0.00010445571134029838,
      "loss": 2.4221,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.3336,
      "eval_loss": 2.397761344909668,
      "eval_runtime": 12.0623,
      "eval_samples_per_second": 310.886,
      "eval_steps_per_second": 4.891,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 54.87336349487305,
      "learning_rate": 2.9148468506836763e-05,
      "loss": 2.1383,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.3778666666666667,
      "eval_loss": 2.2015457153320312,
      "eval_runtime": 10.4139,
      "eval_samples_per_second": 360.096,
      "eval_steps_per_second": 5.666,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 34.69906997680664,
      "learning_rate": 2.4031112851152778e-09,
      "loss": 1.8721,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.3914666666666667,
      "eval_loss": 2.184919834136963,
      "eval_runtime": 10.5291,
      "eval_samples_per_second": 356.154,
      "eval_steps_per_second": 5.603,
      "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
}