trainer_state.json

{
  "best_metric": 0.8933333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0936/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": Infinity,
      "learning_rate": 8.400647327635769e-05,
      "loss": 1.764,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7957333333333333,
      "eval_loss": 0.775936484336853,
      "eval_runtime": 12.6466,
      "eval_samples_per_second": 296.523,
      "eval_steps_per_second": 4.665,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 6.762244255374248e-05,
      "loss": 0.5162,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8424,
      "eval_loss": 0.5428018569946289,
      "eval_runtime": 14.1544,
      "eval_samples_per_second": 264.935,
      "eval_steps_per_second": 4.168,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 33.494781494140625,
      "learning_rate": 4.5141512949348145e-05,
      "loss": 0.2675,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.86,
      "eval_loss": 0.46088823676109314,
      "eval_runtime": 11.3093,
      "eval_samples_per_second": 331.584,
      "eval_steps_per_second": 5.217,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.3234175443649292,
      "learning_rate": 2.262266506445742e-05,
      "loss": 0.1267,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.888,
      "eval_loss": 0.3797580301761627,
      "eval_runtime": 11.0715,
      "eval_samples_per_second": 338.708,
      "eval_steps_per_second": 5.329,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.2962189018726349,
      "learning_rate": 6.099806004306081e-06,
      "loss": 0.0572,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8909333333333334,
      "eval_loss": 0.3844778537750244,
      "eval_runtime": 10.9798,
      "eval_samples_per_second": 341.535,
      "eval_steps_per_second": 5.373,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.06927304714918137,
      "learning_rate": 2.2251071493339937e-10,
      "loss": 0.0292,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8933333333333333,
      "eval_loss": 0.3605734407901764,
      "eval_runtime": 12.086,
      "eval_samples_per_second": 310.277,
      "eval_steps_per_second": 4.882,
      "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
}