trainer_state.json

{
  "best_metric": 0.9248,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0512/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": 1.0106037855148315,
      "learning_rate": 8.404170694504206e-05,
      "loss": 0.8362,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8336,
      "eval_loss": 0.5404272079467773,
      "eval_runtime": 7.5789,
      "eval_samples_per_second": 494.794,
      "eval_steps_per_second": 7.785,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.3250303864479065,
      "learning_rate": 6.762244255374248e-05,
      "loss": 0.2978,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8528,
      "eval_loss": 0.5146347284317017,
      "eval_runtime": 7.04,
      "eval_samples_per_second": 532.667,
      "eval_steps_per_second": 8.381,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 5.118779182434082,
      "learning_rate": 4.5141512949348145e-05,
      "loss": 0.1473,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8802666666666666,
      "eval_loss": 0.4075815677642822,
      "eval_runtime": 6.8843,
      "eval_samples_per_second": 544.722,
      "eval_steps_per_second": 8.57,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.01781146414577961,
      "learning_rate": 2.262266506445742e-05,
      "loss": 0.0576,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9088,
      "eval_loss": 0.341423898935318,
      "eval_runtime": 7.3297,
      "eval_samples_per_second": 511.62,
      "eval_steps_per_second": 8.049,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 18.115467071533203,
      "learning_rate": 6.099806004306081e-06,
      "loss": 0.0156,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.92,
      "eval_loss": 0.29605841636657715,
      "eval_runtime": 6.9151,
      "eval_samples_per_second": 542.288,
      "eval_steps_per_second": 8.532,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.017432982102036476,
      "learning_rate": 2.2251071493339937e-10,
      "loss": 0.0047,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9248,
      "eval_loss": 0.29131951928138733,
      "eval_runtime": 7.5394,
      "eval_samples_per_second": 497.39,
      "eval_steps_per_second": 7.826,
      "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
}