trainer_state.json

{
  "best_metric": 0.9133333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0669/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": 6.008687496185303,
      "learning_rate": 8.404170694504206e-05,
      "loss": 0.861,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8058666666666666,
      "eval_loss": 0.6357656121253967,
      "eval_runtime": 12.0255,
      "eval_samples_per_second": 311.836,
      "eval_steps_per_second": 4.906,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 4.689060211181641,
      "learning_rate": 6.762244255374248e-05,
      "loss": 0.2963,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8498666666666667,
      "eval_loss": 0.5317696332931519,
      "eval_runtime": 12.0179,
      "eval_samples_per_second": 312.033,
      "eval_steps_per_second": 4.909,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.0006031253724358976,
      "learning_rate": 4.5141512949348145e-05,
      "loss": 0.1184,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8768,
      "eval_loss": 0.44337961077690125,
      "eval_runtime": 11.8186,
      "eval_samples_per_second": 317.296,
      "eval_steps_per_second": 4.992,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.03222905844449997,
      "learning_rate": 2.262266506445742e-05,
      "loss": 0.0421,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8970666666666667,
      "eval_loss": 0.3919253349304199,
      "eval_runtime": 12.2974,
      "eval_samples_per_second": 304.944,
      "eval_steps_per_second": 4.798,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.008216769434511662,
      "learning_rate": 6.099806004306081e-06,
      "loss": 0.0061,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9122666666666667,
      "eval_loss": 0.3478393256664276,
      "eval_runtime": 12.2922,
      "eval_samples_per_second": 305.071,
      "eval_steps_per_second": 4.8,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.003005378879606724,
      "learning_rate": 2.2251071493339937e-10,
      "loss": 0.0006,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9133333333333333,
      "eval_loss": 0.3465730547904968,
      "eval_runtime": 12.0879,
      "eval_samples_per_second": 310.228,
      "eval_steps_per_second": 4.881,
      "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
}