trainer_state.json

{
  "best_metric": 0.2866666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0785/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": 18.042631149291992,
      "learning_rate": 0.0005,
      "loss": 3.4731,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.16266666666666665,
      "eval_loss": 3.18806529045105,
      "eval_runtime": 11.0611,
      "eval_samples_per_second": 339.026,
      "eval_steps_per_second": 5.334,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 14.660234451293945,
      "learning_rate": 0.0005,
      "loss": 3.0159,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.20373333333333332,
      "eval_loss": 2.978257656097412,
      "eval_runtime": 10.7014,
      "eval_samples_per_second": 350.422,
      "eval_steps_per_second": 5.513,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 16.496593475341797,
      "learning_rate": 0.0005,
      "loss": 2.8602,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.2168,
      "eval_loss": 2.908806562423706,
      "eval_runtime": 10.608,
      "eval_samples_per_second": 353.507,
      "eval_steps_per_second": 5.562,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 9.442628860473633,
      "learning_rate": 0.0005,
      "loss": 2.7382,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.244,
      "eval_loss": 2.794710874557495,
      "eval_runtime": 10.2984,
      "eval_samples_per_second": 364.136,
      "eval_steps_per_second": 5.729,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 17.433849334716797,
      "learning_rate": 0.0005,
      "loss": 2.6475,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.2592,
      "eval_loss": 2.746866226196289,
      "eval_runtime": 10.2402,
      "eval_samples_per_second": 366.202,
      "eval_steps_per_second": 5.762,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 20.95793914794922,
      "learning_rate": 0.0005,
      "loss": 2.5634,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.2866666666666667,
      "eval_loss": 2.6342804431915283,
      "eval_runtime": 10.3791,
      "eval_samples_per_second": 361.304,
      "eval_steps_per_second": 5.685,
      "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
}