trainer_state.json

{
  "best_metric": 0.9010666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0597/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": 2.997169256210327,
      "learning_rate": 8.140576474687264e-05,
      "loss": 1.6315,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8,
      "eval_loss": 0.7182118892669678,
      "eval_runtime": 6.1628,
      "eval_samples_per_second": 608.492,
      "eval_steps_per_second": 9.574,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.808795690536499,
      "learning_rate": 5.890576474687264e-05,
      "loss": 0.5318,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8506666666666667,
      "eval_loss": 0.5241841077804565,
      "eval_runtime": 6.1846,
      "eval_samples_per_second": 606.347,
      "eval_steps_per_second": 9.54,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.3037436008453369,
      "learning_rate": 3.1094235253127374e-05,
      "loss": 0.2718,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8808,
      "eval_loss": 0.4136993885040283,
      "eval_runtime": 6.1228,
      "eval_samples_per_second": 612.467,
      "eval_steps_per_second": 9.636,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.43228679895401,
      "learning_rate": 8.59423525312737e-06,
      "loss": 0.1265,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9005333333333333,
      "eval_loss": 0.34535422921180725,
      "eval_runtime": 6.6242,
      "eval_samples_per_second": 566.105,
      "eval_steps_per_second": 8.907,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": Infinity,
      "learning_rate": 8.010389962842535e-11,
      "loss": 0.0632,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9010666666666667,
      "eval_loss": 0.3307790160179138,
      "eval_runtime": 6.5789,
      "eval_samples_per_second": 570.0,
      "eval_steps_per_second": 8.968,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 1665,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 8.2370660311296e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}