trainer_state.json

{
  "best_metric": 0.404,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0014/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": Infinity,
      "learning_rate": 0.0002803729487402998,
      "loss": 3.4202,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.204,
      "eval_loss": 2.9660468101501465,
      "eval_runtime": 7.4429,
      "eval_samples_per_second": 503.834,
      "eval_steps_per_second": 7.927,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 38.98969268798828,
      "learning_rate": 0.00022581553795296964,
      "loss": 2.8187,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.2650666666666667,
      "eval_loss": 2.753192663192749,
      "eval_runtime": 6.5322,
      "eval_samples_per_second": 574.075,
      "eval_steps_per_second": 9.032,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 25.565353393554688,
      "learning_rate": 0.00015094341499741014,
      "loss": 2.5256,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.3234666666666667,
      "eval_loss": 2.4441893100738525,
      "eval_runtime": 6.6444,
      "eval_samples_per_second": 564.388,
      "eval_steps_per_second": 8.88,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": Infinity,
      "learning_rate": 7.602359071507889e-05,
      "loss": 2.2343,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.3562666666666667,
      "eval_loss": 2.2929699420928955,
      "eval_runtime": 6.9267,
      "eval_samples_per_second": 541.384,
      "eval_steps_per_second": 8.518,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 40.058528900146484,
      "learning_rate": 2.0689836183586285e-05,
      "loss": 1.9184,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.3954666666666667,
      "eval_loss": 2.1694955825805664,
      "eval_runtime": 6.6028,
      "eval_samples_per_second": 567.942,
      "eval_steps_per_second": 8.936,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 54.54169464111328,
      "learning_rate": 4.63561983797267e-09,
      "loss": 1.6599,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.404,
      "eval_loss": 2.1859347820281982,
      "eval_runtime": 6.8964,
      "eval_samples_per_second": 543.765,
      "eval_steps_per_second": 8.555,
      "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
}