trainer_state.json

{
  "best_metric": 0.9506666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0727/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": 3.6473844051361084,
      "learning_rate": 6.531088913245535e-05,
      "loss": 0.675,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9341333333333334,
      "eval_loss": 0.24193497002124786,
      "eval_runtime": 12.543,
      "eval_samples_per_second": 298.972,
      "eval_steps_per_second": 4.704,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.09529048949480057,
      "learning_rate": 5.2499999999999995e-05,
      "loss": 0.1153,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9330666666666667,
      "eval_loss": 0.222574383020401,
      "eval_runtime": 11.82,
      "eval_samples_per_second": 317.259,
      "eval_steps_per_second": 4.992,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.025126328691840172,
      "learning_rate": 3.5e-05,
      "loss": 0.0501,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9365333333333333,
      "eval_loss": 0.22774511575698853,
      "eval_runtime": 11.8645,
      "eval_samples_per_second": 316.07,
      "eval_steps_per_second": 4.973,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.07763098925352097,
      "learning_rate": 1.7500000000000005e-05,
      "loss": 0.0201,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.948,
      "eval_loss": 0.18827080726623535,
      "eval_runtime": 11.8793,
      "eval_samples_per_second": 315.676,
      "eval_steps_per_second": 4.967,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.2677260637283325,
      "learning_rate": 4.689110867544645e-06,
      "loss": 0.0089,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.948,
      "eval_loss": 0.18316158652305603,
      "eval_runtime": 11.4211,
      "eval_samples_per_second": 328.339,
      "eval_steps_per_second": 5.166,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.08500359952449799,
      "learning_rate": 0.0,
      "loss": 0.0053,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9506666666666667,
      "eval_loss": 0.18236041069030762,
      "eval_runtime": 11.4696,
      "eval_samples_per_second": 326.952,
      "eval_steps_per_second": 5.144,
      "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
}