trainer_state.json

{
  "best_metric": 0.8770666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0673/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": 7e-05,
      "loss": 2.0034,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7541333333333333,
      "eval_loss": 0.8917221426963806,
      "eval_runtime": 4.3621,
      "eval_samples_per_second": 859.678,
      "eval_steps_per_second": 13.526,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 7e-05,
      "loss": 0.5983,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8437333333333333,
      "eval_loss": 0.5343182682991028,
      "eval_runtime": 4.6123,
      "eval_samples_per_second": 813.044,
      "eval_steps_per_second": 12.792,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 12.37446117401123,
      "learning_rate": 7e-05,
      "loss": 0.3255,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8389333333333333,
      "eval_loss": 0.5427131056785583,
      "eval_runtime": 5.3587,
      "eval_samples_per_second": 699.793,
      "eval_steps_per_second": 11.01,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": Infinity,
      "learning_rate": 7e-05,
      "loss": 0.2094,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8706666666666667,
      "eval_loss": 0.44181424379348755,
      "eval_runtime": 5.6053,
      "eval_samples_per_second": 669.012,
      "eval_steps_per_second": 10.526,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.080470323562622,
      "learning_rate": 7e-05,
      "loss": 0.1332,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8653333333333333,
      "eval_loss": 0.48651430010795593,
      "eval_runtime": 4.3789,
      "eval_samples_per_second": 856.378,
      "eval_steps_per_second": 13.474,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.5150163769721985,
      "learning_rate": 7e-05,
      "loss": 0.102,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8770666666666667,
      "eval_loss": 0.46564415097236633,
      "eval_runtime": 4.4386,
      "eval_samples_per_second": 844.866,
      "eval_steps_per_second": 13.293,
      "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
}