trainer_state.json

{
  "best_metric": 0.6002666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0773/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": 0.00041691691691691694,
      "loss": 3.1453,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.2416,
      "eval_loss": 2.746941089630127,
      "eval_runtime": 10.7051,
      "eval_samples_per_second": 350.3,
      "eval_steps_per_second": 5.511,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.00033383383383383386,
      "loss": 2.4428,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.36906666666666665,
      "eval_loss": 2.2701306343078613,
      "eval_runtime": 11.2395,
      "eval_samples_per_second": 333.644,
      "eval_steps_per_second": 5.249,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0002507507507507508,
      "loss": 1.9392,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.48106666666666664,
      "eval_loss": 1.8533110618591309,
      "eval_runtime": 11.3718,
      "eval_samples_per_second": 329.763,
      "eval_steps_per_second": 5.188,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 19.89180564880371,
      "learning_rate": 0.00016741741741741742,
      "loss": 1.4712,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.5256,
      "eval_loss": 1.6872214078903198,
      "eval_runtime": 10.8993,
      "eval_samples_per_second": 344.059,
      "eval_steps_per_second": 5.413,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.0979578495025635,
      "learning_rate": 8.408408408408409e-05,
      "loss": 0.9745,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.5794666666666667,
      "eval_loss": 1.499136209487915,
      "eval_runtime": 11.0702,
      "eval_samples_per_second": 338.748,
      "eval_steps_per_second": 5.33,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 6.8000617027282715,
      "learning_rate": 7.507507507507508e-07,
      "loss": 0.475,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.6002666666666666,
      "eval_loss": 1.4534858465194702,
      "eval_runtime": 10.6793,
      "eval_samples_per_second": 351.148,
      "eval_steps_per_second": 5.525,
      "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
}