trainer_state.json

{
  "best_metric": 0.8848,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0528/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": 0.0002800215775878589,
      "loss": 1.9179,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6858666666666666,
      "eval_loss": 1.0575342178344727,
      "eval_runtime": 6.858,
      "eval_samples_per_second": 546.806,
      "eval_steps_per_second": 8.603,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.61930251121521,
      "learning_rate": 0.00022520416388814083,
      "loss": 0.7425,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7808,
      "eval_loss": 0.7285048365592957,
      "eval_runtime": 7.0596,
      "eval_samples_per_second": 531.189,
      "eval_steps_per_second": 8.357,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 0.00015047170983116046,
      "loss": 0.4353,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8386666666666667,
      "eval_loss": 0.5344311594963074,
      "eval_runtime": 6.8061,
      "eval_samples_per_second": 550.978,
      "eval_steps_per_second": 8.669,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.036257125437259674,
      "learning_rate": 7.540888354819138e-05,
      "loss": 0.2148,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8650666666666667,
      "eval_loss": 0.46326661109924316,
      "eval_runtime": 6.8237,
      "eval_samples_per_second": 549.551,
      "eval_steps_per_second": 8.646,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.10640757530927658,
      "learning_rate": 2.0332686681020267e-05,
      "loss": 0.0877,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8802666666666666,
      "eval_loss": 0.4102603793144226,
      "eval_runtime": 6.2577,
      "eval_samples_per_second": 599.263,
      "eval_steps_per_second": 9.428,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.10732537508010864,
      "learning_rate": 7.417023831113311e-10,
      "loss": 0.0366,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8848,
      "eval_loss": 0.39989733695983887,
      "eval_runtime": 7.088,
      "eval_samples_per_second": 529.061,
      "eval_steps_per_second": 8.324,
      "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
}