trainer_state.json

{
  "best_metric": 0.26666666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0635/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": 19.52773666381836,
      "learning_rate": 0.0005,
      "loss": 3.4561,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.1608,
      "eval_loss": 3.17899489402771,
      "eval_runtime": 12.3335,
      "eval_samples_per_second": 304.05,
      "eval_steps_per_second": 4.784,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 14.297720909118652,
      "learning_rate": 0.0005,
      "loss": 3.0117,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.21333333333333335,
      "eval_loss": 2.95660400390625,
      "eval_runtime": 12.2237,
      "eval_samples_per_second": 306.78,
      "eval_steps_per_second": 4.827,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 10.587782859802246,
      "learning_rate": 0.0005,
      "loss": 2.8372,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.24373333333333333,
      "eval_loss": 2.8288707733154297,
      "eval_runtime": 12.3685,
      "eval_samples_per_second": 303.19,
      "eval_steps_per_second": 4.77,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 13.81818962097168,
      "learning_rate": 0.0005,
      "loss": 2.7475,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.25626666666666664,
      "eval_loss": 2.783125162124634,
      "eval_runtime": 12.1778,
      "eval_samples_per_second": 307.939,
      "eval_steps_per_second": 4.845,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 15.933025360107422,
      "learning_rate": 0.0005,
      "loss": 2.646,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.26666666666666666,
      "eval_loss": 2.6899280548095703,
      "eval_runtime": 12.5653,
      "eval_samples_per_second": 298.441,
      "eval_steps_per_second": 4.695,
      "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
}