trainer_state.json

{
  "best_metric": 0.8632,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0362/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": 0.000271518691762945,
      "loss": 1.8854,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6938666666666666,
      "eval_loss": 1.0032516717910767,
      "eval_runtime": 6.0335,
      "eval_samples_per_second": 621.527,
      "eval_steps_per_second": 9.779,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.00019689056597036855,
      "loss": 0.7197,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7810666666666667,
      "eval_loss": 0.6870225071907043,
      "eval_runtime": 6.1515,
      "eval_samples_per_second": 609.612,
      "eval_steps_per_second": 9.591,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.7825111150741577,
      "learning_rate": 0.0001041861277497315,
      "loss": 0.3727,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.832,
      "eval_loss": 0.5221274495124817,
      "eval_runtime": 6.1087,
      "eval_samples_per_second": 613.883,
      "eval_steps_per_second": 9.658,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.48551273345947266,
      "learning_rate": 2.8981031572451395e-05,
      "loss": 0.1488,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8594666666666667,
      "eval_loss": 0.45926693081855774,
      "eval_runtime": 5.9672,
      "eval_samples_per_second": 628.433,
      "eval_steps_per_second": 9.887,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.5332058668136597,
      "learning_rate": 1.068051044406104e-09,
      "loss": 0.0522,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8632,
      "eval_loss": 0.4454398453235626,
      "eval_runtime": 5.9242,
      "eval_samples_per_second": 632.998,
      "eval_steps_per_second": 9.959,
      "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
}