trainer_state.json

{
  "best_metric": 0.8885333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0349/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": 2.8002157758785897e-05,
      "loss": 2.2038,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7536,
      "eval_loss": 1.0483369827270508,
      "eval_runtime": 7.1874,
      "eval_samples_per_second": 521.748,
      "eval_steps_per_second": 8.209,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 58.82948303222656,
      "learning_rate": 2.2520416388814085e-05,
      "loss": 0.7583,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8354666666666667,
      "eval_loss": 0.6260860562324524,
      "eval_runtime": 7.0659,
      "eval_samples_per_second": 530.716,
      "eval_steps_per_second": 8.35,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 1.5047170983116048e-05,
      "loss": 0.448,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8648,
      "eval_loss": 0.4907089173793793,
      "eval_runtime": 6.8663,
      "eval_samples_per_second": 546.143,
      "eval_steps_per_second": 8.593,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 34.82240676879883,
      "learning_rate": 7.5408883548191384e-06,
      "loss": 0.2974,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8744,
      "eval_loss": 0.4564052224159241,
      "eval_runtime": 6.8753,
      "eval_samples_per_second": 545.433,
      "eval_steps_per_second": 8.581,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 27.78203582763672,
      "learning_rate": 2.0332686681020267e-06,
      "loss": 0.2135,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.88,
      "eval_loss": 0.41614866256713867,
      "eval_runtime": 6.904,
      "eval_samples_per_second": 543.165,
      "eval_steps_per_second": 8.546,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 7.4255900382995605,
      "learning_rate": 7.417023831113313e-11,
      "loss": 0.1775,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8885333333333333,
      "eval_loss": 0.4059748351573944,
      "eval_runtime": 6.7993,
      "eval_samples_per_second": 551.525,
      "eval_steps_per_second": 8.677,
      "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
}