trainer_state.json

{
  "best_metric": 0.932,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0423/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": 23.8089599609375,
      "learning_rate": 4.667026293130983e-05,
      "loss": 0.7442,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8888,
      "eval_loss": 0.3777564465999603,
      "eval_runtime": 10.709,
      "eval_samples_per_second": 350.172,
      "eval_steps_per_second": 5.509,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.4598880410194397,
      "learning_rate": 3.7534027314690145e-05,
      "loss": 0.1882,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8784,
      "eval_loss": 0.4103926420211792,
      "eval_runtime": 10.6751,
      "eval_samples_per_second": 351.286,
      "eval_steps_per_second": 5.527,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 18.158994674682617,
      "learning_rate": 2.5039309201189614e-05,
      "loss": 0.0718,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9026666666666666,
      "eval_loss": 0.3656056225299835,
      "eval_runtime": 11.2288,
      "eval_samples_per_second": 333.961,
      "eval_steps_per_second": 5.254,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.001552536035887897,
      "learning_rate": 1.253405821897521e-05,
      "loss": 0.0212,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9186666666666666,
      "eval_loss": 0.3247263729572296,
      "eval_runtime": 10.9316,
      "eval_samples_per_second": 343.043,
      "eval_steps_per_second": 5.397,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.06416814774274826,
      "learning_rate": 3.3690462698797944e-06,
      "loss": 0.0037,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9274666666666667,
      "eval_loss": 0.2917698919773102,
      "eval_runtime": 11.4498,
      "eval_samples_per_second": 327.517,
      "eval_steps_per_second": 5.153,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.0054644253104925156,
      "learning_rate": 3.0904285064359275e-11,
      "loss": 0.0008,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.932,
      "eval_loss": 0.28301966190338135,
      "eval_runtime": 10.7345,
      "eval_samples_per_second": 349.341,
      "eval_steps_per_second": 5.496,
      "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
}