trainer_state.json

{
  "best_metric": 0.7496,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0391/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": 0.0003,
      "loss": 3.0249,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.3506666666666667,
      "eval_loss": 2.3267626762390137,
      "eval_runtime": 11.2687,
      "eval_samples_per_second": 332.781,
      "eval_steps_per_second": 5.236,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 7.46132230758667,
      "learning_rate": 0.0003,
      "loss": 1.7069,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6194666666666667,
      "eval_loss": 1.2621716260910034,
      "eval_runtime": 11.1529,
      "eval_samples_per_second": 336.235,
      "eval_steps_per_second": 5.29,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0003,
      "loss": 0.9717,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7168,
      "eval_loss": 0.9524840116500854,
      "eval_runtime": 11.2393,
      "eval_samples_per_second": 333.65,
      "eval_steps_per_second": 5.249,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 4.284194469451904,
      "learning_rate": 0.0003,
      "loss": 0.6168,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7229333333333333,
      "eval_loss": 0.933780312538147,
      "eval_runtime": 11.2274,
      "eval_samples_per_second": 334.005,
      "eval_steps_per_second": 5.255,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 3.2248847484588623,
      "learning_rate": 0.0003,
      "loss": 0.4175,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.7496,
      "eval_loss": 0.8305134177207947,
      "eval_runtime": 11.0801,
      "eval_samples_per_second": 338.443,
      "eval_steps_per_second": 5.325,
      "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
}