trainer_state.json

{
  "best_metric": 0.9296,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0489/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": 0.4056747555732727,
      "learning_rate": 4.667026293130983e-05,
      "loss": 0.7215,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8824,
      "eval_loss": 0.38403046131134033,
      "eval_runtime": 11.1615,
      "eval_samples_per_second": 335.977,
      "eval_steps_per_second": 5.286,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 3.7568023640968045e-05,
      "loss": 0.1981,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8869333333333334,
      "eval_loss": 0.3632645905017853,
      "eval_runtime": 10.9393,
      "eval_samples_per_second": 342.8,
      "eval_steps_per_second": 5.393,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.9745341539382935,
      "learning_rate": 2.5078618305193415e-05,
      "loss": 0.0785,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.904,
      "eval_loss": 0.3154156804084778,
      "eval_runtime": 10.9858,
      "eval_samples_per_second": 341.35,
      "eval_steps_per_second": 5.371,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.22294935584068298,
      "learning_rate": 1.2568147258031899e-05,
      "loss": 0.0316,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9234666666666667,
      "eval_loss": 0.2704072594642639,
      "eval_runtime": 11.0695,
      "eval_samples_per_second": 338.767,
      "eval_steps_per_second": 5.33,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.10824675112962723,
      "learning_rate": 3.388781113503378e-06,
      "loss": 0.0059,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9293333333333333,
      "eval_loss": 0.2626698911190033,
      "eval_runtime": 11.6077,
      "eval_samples_per_second": 323.062,
      "eval_steps_per_second": 5.083,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.6241434812545776,
      "learning_rate": 1.2361706385188855e-10,
      "loss": 0.0013,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9296,
      "eval_loss": 0.26904812455177307,
      "eval_runtime": 11.1461,
      "eval_samples_per_second": 336.442,
      "eval_steps_per_second": 5.293,
      "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
}