trainer_state.json

{
  "best_metric": 0.38666666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0274/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": Infinity,
      "learning_rate": 0.0003,
      "loss": 3.2873,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.21173333333333333,
      "eval_loss": 2.9113073348999023,
      "eval_runtime": 7.3377,
      "eval_samples_per_second": 511.059,
      "eval_steps_per_second": 8.041,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 26.6927547454834,
      "learning_rate": 0.0003,
      "loss": 2.7497,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.2613333333333333,
      "eval_loss": 2.7192745208740234,
      "eval_runtime": 7.2558,
      "eval_samples_per_second": 516.826,
      "eval_steps_per_second": 8.131,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 22.47313690185547,
      "learning_rate": 0.0003,
      "loss": 2.5301,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.29973333333333335,
      "eval_loss": 2.5043954849243164,
      "eval_runtime": 7.1386,
      "eval_samples_per_second": 525.316,
      "eval_steps_per_second": 8.265,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 17.58451271057129,
      "learning_rate": 0.0003,
      "loss": 2.3654,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.3136,
      "eval_loss": 2.5165750980377197,
      "eval_runtime": 7.0996,
      "eval_samples_per_second": 528.199,
      "eval_steps_per_second": 8.31,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 18.429126739501953,
      "learning_rate": 0.0003,
      "loss": 2.2246,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.35706666666666664,
      "eval_loss": 2.3238608837127686,
      "eval_runtime": 7.0652,
      "eval_samples_per_second": 530.769,
      "eval_steps_per_second": 8.351,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 21.04579734802246,
      "learning_rate": 0.0003,
      "loss": 2.101,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.38666666666666666,
      "eval_loss": 2.239400863647461,
      "eval_runtime": 6.9511,
      "eval_samples_per_second": 539.48,
      "eval_steps_per_second": 8.488,
      "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
}