trainer_state.json

{
  "best_metric": 0.9037333333333334,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0339/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": 6.533836810383375e-05,
      "loss": 1.6533,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8269333333333333,
      "eval_loss": 0.6631975173950195,
      "eval_runtime": 5.2702,
      "eval_samples_per_second": 711.551,
      "eval_steps_per_second": 11.195,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 5.259523309735526e-05,
      "loss": 0.4469,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8581333333333333,
      "eval_loss": 0.4881308674812317,
      "eval_runtime": 5.2668,
      "eval_samples_per_second": 712.009,
      "eval_steps_per_second": 11.202,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.4098989963531494,
      "learning_rate": 3.5110065627270776e-05,
      "loss": 0.2,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8853333333333333,
      "eval_loss": 0.3990730047225952,
      "eval_runtime": 5.259,
      "eval_samples_per_second": 713.058,
      "eval_steps_per_second": 11.219,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 7.797478675842285,
      "learning_rate": 1.7595406161244655e-05,
      "loss": 0.085,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8954666666666666,
      "eval_loss": 0.36978164315223694,
      "eval_runtime": 5.7962,
      "eval_samples_per_second": 646.981,
      "eval_steps_per_second": 10.179,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.10286084562540054,
      "learning_rate": 4.744293558904729e-06,
      "loss": 0.0322,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9016,
      "eval_loss": 0.346883624792099,
      "eval_runtime": 5.5192,
      "eval_samples_per_second": 679.448,
      "eval_steps_per_second": 10.69,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.10503820329904556,
      "learning_rate": 1.7306388939264393e-10,
      "loss": 0.0163,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9037333333333334,
      "eval_loss": 0.3483089804649353,
      "eval_runtime": 5.2524,
      "eval_samples_per_second": 713.96,
      "eval_steps_per_second": 11.233,
      "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
}