trainer_state.json

{
  "best_metric": 0.8549333333333333,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0044/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": 96.16437530517578,
      "learning_rate": 3e-05,
      "loss": 3.8471,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.36773333333333336,
      "eval_loss": 3.7270679473876953,
      "eval_runtime": 8.6768,
      "eval_samples_per_second": 432.189,
      "eval_steps_per_second": 6.8,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 377.6429443359375,
      "learning_rate": 3e-05,
      "loss": 3.1585,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.56,
      "eval_loss": 2.25150728225708,
      "eval_runtime": 8.5863,
      "eval_samples_per_second": 436.743,
      "eval_steps_per_second": 6.871,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 207.6896209716797,
      "learning_rate": 3e-05,
      "loss": 1.5106,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7637333333333334,
      "eval_loss": 0.9617313742637634,
      "eval_runtime": 8.6388,
      "eval_samples_per_second": 434.09,
      "eval_steps_per_second": 6.83,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 239.11688232421875,
      "learning_rate": 3e-05,
      "loss": 0.8037,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8146666666666667,
      "eval_loss": 0.6765750050544739,
      "eval_runtime": 8.5729,
      "eval_samples_per_second": 437.425,
      "eval_steps_per_second": 6.882,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 91.22789001464844,
      "learning_rate": 3e-05,
      "loss": 0.6131,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.836,
      "eval_loss": 0.5540485382080078,
      "eval_runtime": 8.6161,
      "eval_samples_per_second": 435.23,
      "eval_steps_per_second": 6.848,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 126.85383605957031,
      "learning_rate": 3e-05,
      "loss": 0.5191,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8549333333333333,
      "eval_loss": 0.5059124827384949,
      "eval_runtime": 8.8365,
      "eval_samples_per_second": 424.377,
      "eval_steps_per_second": 6.677,
      "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": 4.9058575437312e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}