trainer_state.json

{
  "best_metric": 0.8530666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0324/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": 5e-05,
      "loss": 2.1571,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7397333333333334,
      "eval_loss": 1.0166481733322144,
      "eval_runtime": 7.7373,
      "eval_samples_per_second": 484.662,
      "eval_steps_per_second": 7.625,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 3.6693115234375,
      "learning_rate": 5e-05,
      "loss": 0.6758,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8042666666666667,
      "eval_loss": 0.6653415560722351,
      "eval_runtime": 7.5044,
      "eval_samples_per_second": 499.71,
      "eval_steps_per_second": 7.862,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 16.270126342773438,
      "learning_rate": 5e-05,
      "loss": 0.3945,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8416,
      "eval_loss": 0.5481759309768677,
      "eval_runtime": 7.353,
      "eval_samples_per_second": 509.998,
      "eval_steps_per_second": 8.024,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": Infinity,
      "learning_rate": 5e-05,
      "loss": 0.2528,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8317333333333333,
      "eval_loss": 0.5730020999908447,
      "eval_runtime": 7.2916,
      "eval_samples_per_second": 514.288,
      "eval_steps_per_second": 8.091,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.6828041672706604,
      "learning_rate": 5e-05,
      "loss": 0.1642,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8530666666666666,
      "eval_loss": 0.49891334772109985,
      "eval_runtime": 7.5083,
      "eval_samples_per_second": 499.447,
      "eval_steps_per_second": 7.858,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 2664,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "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
}