trainer_state.json

{
  "best_metric": 0.9269333333333334,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0537/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": 9.341871565471464e-05,
      "loss": 0.832,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8482666666666666,
      "eval_loss": 0.49634113907814026,
      "eval_runtime": 6.4842,
      "eval_samples_per_second": 578.329,
      "eval_steps_per_second": 9.099,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 103.29092407226562,
      "learning_rate": 7.520397778956622e-05,
      "loss": 0.2767,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8616,
      "eval_loss": 0.4562292993068695,
      "eval_runtime": 6.3827,
      "eval_samples_per_second": 587.522,
      "eval_steps_per_second": 9.244,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.2869776487350464,
      "learning_rate": 5.023585442965162e-05,
      "loss": 0.1264,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8877333333333334,
      "eval_loss": 0.39961713552474976,
      "eval_runtime": 6.4103,
      "eval_samples_per_second": 584.992,
      "eval_steps_per_second": 9.204,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.0009306150022894144,
      "learning_rate": 2.5204534065780533e-05,
      "loss": 0.0479,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9098666666666667,
      "eval_loss": 0.32313138246536255,
      "eval_runtime": 6.3566,
      "eval_samples_per_second": 589.941,
      "eval_steps_per_second": 9.282,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.1418924629688263,
      "learning_rate": 6.817138774936977e-06,
      "loss": 0.0088,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9253333333333333,
      "eval_loss": 0.2923603653907776,
      "eval_runtime": 6.3498,
      "eval_samples_per_second": 590.569,
      "eval_steps_per_second": 9.292,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.01012352667748928,
      "learning_rate": 5.562762142974353e-10,
      "loss": 0.0011,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9269333333333334,
      "eval_loss": 0.28509101271629333,
      "eval_runtime": 6.6025,
      "eval_samples_per_second": 567.967,
      "eval_steps_per_second": 8.936,
      "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
}