trainer_state.json

{
  "best_metric": 0.8450666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0183/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": 2.4567,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.688,
      "eval_loss": 1.3375349044799805,
      "eval_runtime": 5.825,
      "eval_samples_per_second": 643.776,
      "eval_steps_per_second": 10.129,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 3e-05,
      "loss": 0.8912,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8010666666666667,
      "eval_loss": 0.7536471486091614,
      "eval_runtime": 5.7444,
      "eval_samples_per_second": 652.811,
      "eval_steps_per_second": 10.271,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.7255068421363831,
      "learning_rate": 3e-05,
      "loss": 0.4674,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8322666666666667,
      "eval_loss": 0.5833407640457153,
      "eval_runtime": 5.7073,
      "eval_samples_per_second": 657.057,
      "eval_steps_per_second": 10.338,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": Infinity,
      "learning_rate": 3e-05,
      "loss": 0.2696,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8426666666666667,
      "eval_loss": 0.5301695466041565,
      "eval_runtime": 5.7902,
      "eval_samples_per_second": 647.641,
      "eval_steps_per_second": 10.19,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.0417327880859375,
      "learning_rate": 3e-05,
      "loss": 0.1573,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8450666666666666,
      "eval_loss": 0.5314071178436279,
      "eval_runtime": 5.7934,
      "eval_samples_per_second": 647.283,
      "eval_steps_per_second": 10.184,
      "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
}