trainer_state.json

{
  "best_metric": 0.4594666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0909/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": 0.0005,
      "loss": 3.2491,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.228,
      "eval_loss": 2.868464231491089,
      "eval_runtime": 7.6533,
      "eval_samples_per_second": 489.985,
      "eval_steps_per_second": 7.709,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0005,
      "loss": 2.6354,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.3248,
      "eval_loss": 2.4372525215148926,
      "eval_runtime": 8.0315,
      "eval_samples_per_second": 466.913,
      "eval_steps_per_second": 7.346,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0005,
      "loss": 2.291,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.3608,
      "eval_loss": 2.2995755672454834,
      "eval_runtime": 7.8744,
      "eval_samples_per_second": 476.23,
      "eval_steps_per_second": 7.493,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 12.255844116210938,
      "learning_rate": 0.0005,
      "loss": 2.0526,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.3928,
      "eval_loss": 2.1924009323120117,
      "eval_runtime": 7.5969,
      "eval_samples_per_second": 493.625,
      "eval_steps_per_second": 7.766,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 11.782167434692383,
      "learning_rate": 0.0005,
      "loss": 1.8514,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.4245333333333333,
      "eval_loss": 2.0262539386749268,
      "eval_runtime": 7.4538,
      "eval_samples_per_second": 503.097,
      "eval_steps_per_second": 7.915,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 7.587841510772705,
      "learning_rate": 0.0005,
      "loss": 1.6707,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.4594666666666667,
      "eval_loss": 1.9070229530334473,
      "eval_runtime": 7.7136,
      "eval_samples_per_second": 486.153,
      "eval_steps_per_second": 7.649,
      "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
}