trainer_state.json

{
  "best_metric": 0.9088,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0420/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": 7.509009009009009e-05,
      "loss": 0.8835,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8384,
      "eval_loss": 0.5359704494476318,
      "eval_runtime": 10.1749,
      "eval_samples_per_second": 368.555,
      "eval_steps_per_second": 5.799,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 41.7404670715332,
      "learning_rate": 6.00900900900901e-05,
      "loss": 0.2695,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8653333333333333,
      "eval_loss": 0.4593779742717743,
      "eval_runtime": 11.0015,
      "eval_samples_per_second": 340.863,
      "eval_steps_per_second": 5.363,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.7410584092140198,
      "learning_rate": 4.509009009009009e-05,
      "loss": 0.1062,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8797333333333334,
      "eval_loss": 0.4381968379020691,
      "eval_runtime": 11.8079,
      "eval_samples_per_second": 317.584,
      "eval_steps_per_second": 4.997,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 16.4133358001709,
      "learning_rate": 3.0090090090090093e-05,
      "loss": 0.0431,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8912,
      "eval_loss": 0.43796828389167786,
      "eval_runtime": 10.4463,
      "eval_samples_per_second": 358.98,
      "eval_steps_per_second": 5.648,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.0029467714484781027,
      "learning_rate": 1.5090090090090091e-05,
      "loss": 0.0127,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9053333333333333,
      "eval_loss": 0.39549577236175537,
      "eval_runtime": 10.7374,
      "eval_samples_per_second": 349.246,
      "eval_steps_per_second": 5.495,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.01270991750061512,
      "learning_rate": 9.00900900900901e-08,
      "loss": 0.0017,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9088,
      "eval_loss": 0.3720873296260834,
      "eval_runtime": 10.4854,
      "eval_samples_per_second": 357.639,
      "eval_steps_per_second": 5.627,
      "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
}