trainer_state.json

{
  "best_metric": 0.8650666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0464/checkpoints/checkpoint-1998",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 1998,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 5.867852687835693,
      "learning_rate": 9e-05,
      "loss": 1.7525,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7981333333333334,
      "eval_loss": 0.7311855554580688,
      "eval_runtime": 11.0657,
      "eval_samples_per_second": 338.884,
      "eval_steps_per_second": 5.332,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 9e-05,
      "loss": 0.5501,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8213333333333334,
      "eval_loss": 0.5947279930114746,
      "eval_runtime": 11.0785,
      "eval_samples_per_second": 338.494,
      "eval_steps_per_second": 5.326,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 2.405623435974121,
      "learning_rate": 9e-05,
      "loss": 0.3256,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8424,
      "eval_loss": 0.5241888761520386,
      "eval_runtime": 11.1294,
      "eval_samples_per_second": 336.946,
      "eval_steps_per_second": 5.301,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.09708582609891891,
      "learning_rate": 9e-05,
      "loss": 0.2153,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8458666666666667,
      "eval_loss": 0.5240779519081116,
      "eval_runtime": 11.6357,
      "eval_samples_per_second": 322.285,
      "eval_steps_per_second": 5.071,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 4.0553765296936035,
      "learning_rate": 9e-05,
      "loss": 0.153,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8461333333333333,
      "eval_loss": 0.5316107869148254,
      "eval_runtime": 11.0224,
      "eval_samples_per_second": 340.218,
      "eval_steps_per_second": 5.353,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.2897823750972748,
      "learning_rate": 9e-05,
      "loss": 0.1232,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8650666666666667,
      "eval_loss": 0.49945124983787537,
      "eval_runtime": 11.5973,
      "eval_samples_per_second": 323.35,
      "eval_steps_per_second": 5.087,
      "step": 1998
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.88447923735552e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}