trainer_state.json

{
  "best_metric": 0.9434666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0967/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": 0.18886063992977142,
      "learning_rate": 8.333333333333334e-05,
      "loss": 0.5856,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9250666666666667,
      "eval_loss": 0.2292613387107849,
      "eval_runtime": 10.1684,
      "eval_samples_per_second": 368.79,
      "eval_steps_per_second": 5.802,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.2626243531703949,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.1166,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9304,
      "eval_loss": 0.23832467198371887,
      "eval_runtime": 10.1295,
      "eval_samples_per_second": 370.206,
      "eval_steps_per_second": 5.825,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.13141611218452454,
      "learning_rate": 5e-05,
      "loss": 0.0461,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9344,
      "eval_loss": 0.23220688104629517,
      "eval_runtime": 10.1628,
      "eval_samples_per_second": 368.992,
      "eval_steps_per_second": 5.805,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 9.573881149291992,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.0175,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9408,
      "eval_loss": 0.226756289601326,
      "eval_runtime": 10.2879,
      "eval_samples_per_second": 364.505,
      "eval_steps_per_second": 5.735,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.021322954446077347,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.0064,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9429333333333333,
      "eval_loss": 0.20967642962932587,
      "eval_runtime": 10.1857,
      "eval_samples_per_second": 368.165,
      "eval_steps_per_second": 5.792,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.04203646257519722,
      "learning_rate": 0.0,
      "loss": 0.0028,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9434666666666667,
      "eval_loss": 0.20965971052646637,
      "eval_runtime": 9.9233,
      "eval_samples_per_second": 377.899,
      "eval_steps_per_second": 5.946,
      "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
}