trainer_state.json

{
  "best_metric": 0.8930666666666667,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0331/checkpoints/checkpoint-1665",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1665,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 109.197021484375,
      "learning_rate": 7e-05,
      "loss": 3.1303,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6994666666666667,
      "eval_loss": 1.3332197666168213,
      "eval_runtime": 4.9793,
      "eval_samples_per_second": 753.117,
      "eval_steps_per_second": 11.849,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 105.04508209228516,
      "learning_rate": 7e-05,
      "loss": 0.7879,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8474666666666667,
      "eval_loss": 0.5386773943901062,
      "eval_runtime": 4.9274,
      "eval_samples_per_second": 761.054,
      "eval_steps_per_second": 11.974,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 103.01712799072266,
      "learning_rate": 7e-05,
      "loss": 0.4257,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8709333333333333,
      "eval_loss": 0.4235272705554962,
      "eval_runtime": 4.9799,
      "eval_samples_per_second": 753.028,
      "eval_steps_per_second": 11.848,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 107.04472351074219,
      "learning_rate": 7e-05,
      "loss": 0.2855,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8725333333333334,
      "eval_loss": 0.3947259783744812,
      "eval_runtime": 5.0145,
      "eval_samples_per_second": 747.833,
      "eval_steps_per_second": 11.766,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 104.84961700439453,
      "learning_rate": 7e-05,
      "loss": 0.2052,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8930666666666667,
      "eval_loss": 0.3659745454788208,
      "eval_runtime": 4.9134,
      "eval_samples_per_second": 763.211,
      "eval_steps_per_second": 12.008,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 1665,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 4.088214619776e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}