trainer_state.json

{
  "best_metric": 0.9322666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0386/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": 11.969748497009277,
      "learning_rate": 9e-05,
      "loss": 0.6302,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9202666666666667,
      "eval_loss": 0.2725251615047455,
      "eval_runtime": 6.0957,
      "eval_samples_per_second": 615.189,
      "eval_steps_per_second": 9.679,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.2887861728668213,
      "learning_rate": 9e-05,
      "loss": 0.1486,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9288,
      "eval_loss": 0.24442024528980255,
      "eval_runtime": 6.4262,
      "eval_samples_per_second": 583.545,
      "eval_steps_per_second": 9.181,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.9848778247833252,
      "learning_rate": 9e-05,
      "loss": 0.0852,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9213333333333333,
      "eval_loss": 0.2781967520713806,
      "eval_runtime": 6.0452,
      "eval_samples_per_second": 620.329,
      "eval_steps_per_second": 9.76,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.08564723283052444,
      "learning_rate": 9e-05,
      "loss": 0.0637,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9178666666666667,
      "eval_loss": 0.3008275032043457,
      "eval_runtime": 8.3138,
      "eval_samples_per_second": 451.056,
      "eval_steps_per_second": 7.097,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.23856432735919952,
      "learning_rate": 9e-05,
      "loss": 0.0408,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9293333333333333,
      "eval_loss": 0.3017295002937317,
      "eval_runtime": 6.0344,
      "eval_samples_per_second": 621.435,
      "eval_steps_per_second": 9.777,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.013570214621722698,
      "learning_rate": 9e-05,
      "loss": 0.0339,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9322666666666667,
      "eval_loss": 0.29720214009284973,
      "eval_runtime": 6.0355,
      "eval_samples_per_second": 621.324,
      "eval_steps_per_second": 9.775,
      "step": 1998
    }
  ],
  "logging_steps": 500,
  "max_steps": 2664,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9.88447923735552e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}