trainer_state.json

{
  "best_metric": 0.8706666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0155/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": Infinity,
      "learning_rate": 3e-05,
      "loss": 2.4431,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7154666666666667,
      "eval_loss": 1.2240197658538818,
      "eval_runtime": 5.5378,
      "eval_samples_per_second": 677.16,
      "eval_steps_per_second": 10.654,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 3.959838390350342,
      "learning_rate": 3e-05,
      "loss": 0.8176,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8189333333333333,
      "eval_loss": 0.6805731058120728,
      "eval_runtime": 5.4723,
      "eval_samples_per_second": 685.265,
      "eval_steps_per_second": 10.782,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 3e-05,
      "loss": 0.4069,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8522666666666666,
      "eval_loss": 0.5127201080322266,
      "eval_runtime": 5.5848,
      "eval_samples_per_second": 671.463,
      "eval_steps_per_second": 10.564,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 2.1050069332122803,
      "learning_rate": 3e-05,
      "loss": 0.2155,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8578666666666667,
      "eval_loss": 0.4668915271759033,
      "eval_runtime": 6.0637,
      "eval_samples_per_second": 618.437,
      "eval_steps_per_second": 9.73,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 44.38123321533203,
      "learning_rate": 3e-05,
      "loss": 0.1223,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8706666666666667,
      "eval_loss": 0.4404924809932709,
      "eval_runtime": 5.637,
      "eval_samples_per_second": 665.249,
      "eval_steps_per_second": 10.467,
      "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
}