trainer_state.json

{
  "best_metric": 0.8906666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0284/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": 1.5406,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7917333333333333,
      "eval_loss": 0.7240369915962219,
      "eval_runtime": 5.4127,
      "eval_samples_per_second": 692.813,
      "eval_steps_per_second": 10.9,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.7563444972038269,
      "learning_rate": 6.756124916644227e-05,
      "loss": 0.5176,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8373333333333334,
      "eval_loss": 0.5275281667709351,
      "eval_runtime": 6.0385,
      "eval_samples_per_second": 621.017,
      "eval_steps_per_second": 9.771,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 4.5141512949348145e-05,
      "loss": 0.2826,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8568,
      "eval_loss": 0.4534045159816742,
      "eval_runtime": 5.8778,
      "eval_samples_per_second": 637.994,
      "eval_steps_per_second": 10.038,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": Infinity,
      "learning_rate": 2.268408065920248e-05,
      "loss": 0.147,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.872,
      "eval_loss": 0.41847583651542664,
      "eval_runtime": 5.9616,
      "eval_samples_per_second": 629.024,
      "eval_steps_per_second": 9.897,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.08427120745182037,
      "learning_rate": 6.135424897443279e-06,
      "loss": 0.0636,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.888,
      "eval_loss": 0.3915782868862152,
      "eval_runtime": 5.3973,
      "eval_samples_per_second": 694.788,
      "eval_steps_per_second": 10.931,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.471602439880371,
      "learning_rate": 5.006485928676918e-10,
      "loss": 0.0326,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8906666666666667,
      "eval_loss": 0.3845917284488678,
      "eval_runtime": 5.4475,
      "eval_samples_per_second": 688.392,
      "eval_steps_per_second": 10.831,
      "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
}