trainer_state.json

{
  "best_metric": 0.9125333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0472/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": 0.00046670262931309826,
      "loss": 0.8005,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8397333333333333,
      "eval_loss": 0.5688510537147522,
      "eval_runtime": 13.0815,
      "eval_samples_per_second": 286.665,
      "eval_steps_per_second": 4.51,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.027869345620274544,
      "learning_rate": 0.00037534027314690147,
      "loss": 0.4243,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8352,
      "eval_loss": 0.5624595284461975,
      "eval_runtime": 12.084,
      "eval_samples_per_second": 310.329,
      "eval_steps_per_second": 4.883,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 9.766608238220215,
      "learning_rate": 0.00025039309201189616,
      "loss": 0.2218,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8624,
      "eval_loss": 0.4994051158428192,
      "eval_runtime": 12.1154,
      "eval_samples_per_second": 309.524,
      "eval_steps_per_second": 4.87,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.0030344396363943815,
      "learning_rate": 0.00012534058218975207,
      "loss": 0.0886,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8906666666666667,
      "eval_loss": 0.4213123321533203,
      "eval_runtime": 12.2669,
      "eval_samples_per_second": 305.701,
      "eval_steps_per_second": 4.81,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.3121671676635742,
      "learning_rate": 3.369046269879794e-05,
      "loss": 0.0206,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9082666666666667,
      "eval_loss": 0.3612917959690094,
      "eval_runtime": 12.0221,
      "eval_samples_per_second": 311.924,
      "eval_steps_per_second": 4.908,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.007079241797327995,
      "learning_rate": 3.090428506435927e-10,
      "loss": 0.0056,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9125333333333333,
      "eval_loss": 0.358335018157959,
      "eval_runtime": 12.2596,
      "eval_samples_per_second": 305.883,
      "eval_steps_per_second": 4.813,
      "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
}