trainer_state.json

{
  "best_metric": 0.8832,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0057/checkpoints/checkpoint-1665",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1665,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 5.10166597366333,
      "learning_rate": 9e-05,
      "loss": 1.3787,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8128,
      "eval_loss": 0.6967366337776184,
      "eval_runtime": 5.8581,
      "eval_samples_per_second": 640.14,
      "eval_steps_per_second": 10.072,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.7218480110168457,
      "learning_rate": 9e-05,
      "loss": 0.4365,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.84,
      "eval_loss": 0.5607734322547913,
      "eval_runtime": 5.8255,
      "eval_samples_per_second": 643.716,
      "eval_steps_per_second": 10.128,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 2.0643389225006104,
      "learning_rate": 9e-05,
      "loss": 0.2664,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8744,
      "eval_loss": 0.434218168258667,
      "eval_runtime": 6.1243,
      "eval_samples_per_second": 612.318,
      "eval_steps_per_second": 9.634,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.07133820652961731,
      "learning_rate": 9e-05,
      "loss": 0.1795,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8821333333333333,
      "eval_loss": 0.43540480732917786,
      "eval_runtime": 7.0602,
      "eval_samples_per_second": 531.149,
      "eval_steps_per_second": 8.357,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": Infinity,
      "learning_rate": 9e-05,
      "loss": 0.1398,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8832,
      "eval_loss": 0.4302780330181122,
      "eval_runtime": 6.4608,
      "eval_samples_per_second": 580.424,
      "eval_steps_per_second": 9.132,
      "step": 1665
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8.2370660311296e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}