trainer_state.json

{
  "best_metric": 0.896,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0734/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": 2.5646755695343018,
      "learning_rate": 4.665063509461097e-05,
      "loss": 1.8505,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7757333333333334,
      "eval_loss": 0.8534433841705322,
      "eval_runtime": 10.4993,
      "eval_samples_per_second": 357.168,
      "eval_steps_per_second": 5.619,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 6.862090587615967,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 0.5506,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8578666666666667,
      "eval_loss": 0.5024764537811279,
      "eval_runtime": 11.9729,
      "eval_samples_per_second": 313.208,
      "eval_steps_per_second": 4.928,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 2.5039309201189614e-05,
      "loss": 0.2949,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8770666666666667,
      "eval_loss": 0.43375879526138306,
      "eval_runtime": 11.0111,
      "eval_samples_per_second": 340.564,
      "eval_steps_per_second": 5.358,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 10.572489738464355,
      "learning_rate": 1.253405821897521e-05,
      "loss": 0.1596,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8813333333333333,
      "eval_loss": 0.39627134799957275,
      "eval_runtime": 10.2801,
      "eval_samples_per_second": 364.782,
      "eval_steps_per_second": 5.739,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 10.406059265136719,
      "learning_rate": 3.3690462698797944e-06,
      "loss": 0.0805,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8938666666666667,
      "eval_loss": 0.3608650863170624,
      "eval_runtime": 10.5739,
      "eval_samples_per_second": 354.645,
      "eval_steps_per_second": 5.58,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 2.107614278793335,
      "learning_rate": 3.0904285064359275e-11,
      "loss": 0.0497,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.896,
      "eval_loss": 0.3598763942718506,
      "eval_runtime": 10.3468,
      "eval_samples_per_second": 362.433,
      "eval_steps_per_second": 5.702,
      "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
}