trainer_state.json

{
  "best_metric": 0.2866666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0096/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": 18.05211639404297,
      "learning_rate": 0.0005,
      "loss": 3.4786,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.17013333333333333,
      "eval_loss": 3.1218314170837402,
      "eval_runtime": 6.7286,
      "eval_samples_per_second": 557.324,
      "eval_steps_per_second": 8.769,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 18.08905792236328,
      "learning_rate": 0.0005,
      "loss": 3.0285,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.2136,
      "eval_loss": 2.9907190799713135,
      "eval_runtime": 5.9364,
      "eval_samples_per_second": 631.7,
      "eval_steps_per_second": 9.939,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 20.191009521484375,
      "learning_rate": 0.0005,
      "loss": 2.8883,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.228,
      "eval_loss": 2.8460140228271484,
      "eval_runtime": 6.0814,
      "eval_samples_per_second": 616.637,
      "eval_steps_per_second": 9.702,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 21.748201370239258,
      "learning_rate": 0.0005,
      "loss": 2.7675,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.25893333333333335,
      "eval_loss": 2.7487900257110596,
      "eval_runtime": 5.9216,
      "eval_samples_per_second": 633.271,
      "eval_steps_per_second": 9.963,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 17.646074295043945,
      "learning_rate": 0.0005,
      "loss": 2.6775,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.26106666666666667,
      "eval_loss": 2.7286477088928223,
      "eval_runtime": 6.0383,
      "eval_samples_per_second": 621.04,
      "eval_steps_per_second": 9.771,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 14.903458595275879,
      "learning_rate": 0.0005,
      "loss": 2.5656,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.2866666666666667,
      "eval_loss": 2.5900521278381348,
      "eval_runtime": 7.295,
      "eval_samples_per_second": 514.051,
      "eval_steps_per_second": 8.088,
      "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
}