trainer_state.json

{
  "best_metric": 0.8666666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0439/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": 0.00025030030030030026,
      "loss": 2.2916,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6554666666666666,
      "eval_loss": 1.155665397644043,
      "eval_runtime": 10.8664,
      "eval_samples_per_second": 345.101,
      "eval_steps_per_second": 5.43,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.00020045045045045043,
      "loss": 0.8315,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7816,
      "eval_loss": 0.7282127737998962,
      "eval_runtime": 11.3416,
      "eval_samples_per_second": 330.642,
      "eval_steps_per_second": 5.202,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.9284171462059021,
      "learning_rate": 0.00015045045045045046,
      "loss": 0.425,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.82,
      "eval_loss": 0.5987082123756409,
      "eval_runtime": 11.427,
      "eval_samples_per_second": 328.17,
      "eval_steps_per_second": 5.163,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.07290951162576675,
      "learning_rate": 0.00010045045045045045,
      "loss": 0.2053,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8352,
      "eval_loss": 0.532309889793396,
      "eval_runtime": 11.0578,
      "eval_samples_per_second": 339.126,
      "eval_steps_per_second": 5.336,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.19341649115085602,
      "learning_rate": 5.045045045045045e-05,
      "loss": 0.0792,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8589333333333333,
      "eval_loss": 0.5047021508216858,
      "eval_runtime": 12.1101,
      "eval_samples_per_second": 309.658,
      "eval_steps_per_second": 4.872,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.07258327305316925,
      "learning_rate": 4.5045045045045043e-07,
      "loss": 0.0225,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8666666666666667,
      "eval_loss": 0.4848056137561798,
      "eval_runtime": 12.2428,
      "eval_samples_per_second": 306.302,
      "eval_steps_per_second": 4.819,
      "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
}