trainer_state.json

{
  "best_metric": 0.8645333333333334,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0288/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": 63.68782043457031,
      "learning_rate": 7e-05,
      "loss": 3.2702,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6645333333333333,
      "eval_loss": 1.6915680170059204,
      "eval_runtime": 7.6779,
      "eval_samples_per_second": 488.414,
      "eval_steps_per_second": 7.684,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 136.26808166503906,
      "learning_rate": 7e-05,
      "loss": 1.0023,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8061333333333334,
      "eval_loss": 0.6754140853881836,
      "eval_runtime": 7.6557,
      "eval_samples_per_second": 489.833,
      "eval_steps_per_second": 7.707,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 162.81399536132812,
      "learning_rate": 7e-05,
      "loss": 0.5544,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8402666666666667,
      "eval_loss": 0.5214203000068665,
      "eval_runtime": 7.659,
      "eval_samples_per_second": 489.62,
      "eval_steps_per_second": 7.703,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 284.3952331542969,
      "learning_rate": 7e-05,
      "loss": 0.371,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8490666666666666,
      "eval_loss": 0.48902252316474915,
      "eval_runtime": 7.6558,
      "eval_samples_per_second": 489.822,
      "eval_steps_per_second": 7.707,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 109.03778076171875,
      "learning_rate": 7e-05,
      "loss": 0.2624,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8632,
      "eval_loss": 0.4753594696521759,
      "eval_runtime": 7.6455,
      "eval_samples_per_second": 490.485,
      "eval_steps_per_second": 7.717,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 113.0327377319336,
      "learning_rate": 7e-05,
      "loss": 0.1876,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8645333333333334,
      "eval_loss": 0.45688575506210327,
      "eval_runtime": 7.5836,
      "eval_samples_per_second": 494.487,
      "eval_steps_per_second": 7.78,
      "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
}