trainer_state.json

{
  "best_metric": 0.8688,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0998/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": 0.0002501501501501501,
      "loss": 2.1096,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6746666666666666,
      "eval_loss": 1.1002172231674194,
      "eval_runtime": 11.171,
      "eval_samples_per_second": 335.69,
      "eval_steps_per_second": 5.282,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0002003003003003003,
      "loss": 0.7833,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7786666666666666,
      "eval_loss": 0.7001126408576965,
      "eval_runtime": 11.3596,
      "eval_samples_per_second": 330.116,
      "eval_steps_per_second": 5.194,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.1563899964094162,
      "learning_rate": 0.00015030030030030027,
      "loss": 0.4594,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8082666666666667,
      "eval_loss": 0.6198049187660217,
      "eval_runtime": 11.8942,
      "eval_samples_per_second": 315.28,
      "eval_steps_per_second": 4.96,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.06947039812803268,
      "learning_rate": 0.00010030030030030029,
      "loss": 0.2774,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8266666666666667,
      "eval_loss": 0.5258684158325195,
      "eval_runtime": 11.6835,
      "eval_samples_per_second": 320.966,
      "eval_steps_per_second": 5.05,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.423464298248291,
      "learning_rate": 5.0300300300300295e-05,
      "loss": 0.1427,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8554666666666667,
      "eval_loss": 0.4791199862957001,
      "eval_runtime": 11.6715,
      "eval_samples_per_second": 321.296,
      "eval_steps_per_second": 5.055,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 6.976574420928955,
      "learning_rate": 3.0030030030030027e-07,
      "loss": 0.0648,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8688,
      "eval_loss": 0.4418744146823883,
      "eval_runtime": 11.1471,
      "eval_samples_per_second": 336.41,
      "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
}