trainer_state.json

{
  "best_metric": 0.8784,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0210/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": 5e-05,
      "loss": 1.8104,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8045333333333333,
      "eval_loss": 0.7570825815200806,
      "eval_runtime": 13.5131,
      "eval_samples_per_second": 277.509,
      "eval_steps_per_second": 4.366,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.8238067626953125,
      "learning_rate": 5e-05,
      "loss": 0.5214,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8490666666666666,
      "eval_loss": 0.5092848539352417,
      "eval_runtime": 13.0953,
      "eval_samples_per_second": 286.363,
      "eval_steps_per_second": 4.505,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 5e-05,
      "loss": 0.3151,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8605333333333334,
      "eval_loss": 0.47479185461997986,
      "eval_runtime": 13.355,
      "eval_samples_per_second": 280.794,
      "eval_steps_per_second": 4.418,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.3803671598434448,
      "learning_rate": 5e-05,
      "loss": 0.2077,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8762666666666666,
      "eval_loss": 0.4316200911998749,
      "eval_runtime": 13.5902,
      "eval_samples_per_second": 275.934,
      "eval_steps_per_second": 4.341,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 13.11129379272461,
      "learning_rate": 5e-05,
      "loss": 0.1463,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8765333333333334,
      "eval_loss": 0.44060391187667847,
      "eval_runtime": 12.9739,
      "eval_samples_per_second": 289.043,
      "eval_steps_per_second": 4.548,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.12740100920200348,
      "learning_rate": 5e-05,
      "loss": 0.111,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8784,
      "eval_loss": 0.44260144233703613,
      "eval_runtime": 13.1948,
      "eval_samples_per_second": 284.203,
      "eval_steps_per_second": 4.471,
      "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
}