trainer_state.json

{
  "best_metric": 0.8746666666666667,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0667/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": 163.8097381591797,
      "learning_rate": 0.0001,
      "loss": 2.9188,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7072,
      "eval_loss": 1.0759508609771729,
      "eval_runtime": 7.9756,
      "eval_samples_per_second": 470.183,
      "eval_steps_per_second": 7.398,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 64.71575927734375,
      "learning_rate": 0.0001,
      "loss": 0.8056,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.816,
      "eval_loss": 0.5734072923660278,
      "eval_runtime": 8.1628,
      "eval_samples_per_second": 459.404,
      "eval_steps_per_second": 7.228,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 151.46343994140625,
      "learning_rate": 0.0001,
      "loss": 0.5063,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8474666666666667,
      "eval_loss": 0.4969766139984131,
      "eval_runtime": 7.9794,
      "eval_samples_per_second": 469.958,
      "eval_steps_per_second": 7.394,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 91.64566040039062,
      "learning_rate": 0.0001,
      "loss": 0.3679,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8618666666666667,
      "eval_loss": 0.44146865606307983,
      "eval_runtime": 8.0206,
      "eval_samples_per_second": 467.548,
      "eval_steps_per_second": 7.356,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 50.29618453979492,
      "learning_rate": 0.0001,
      "loss": 0.2769,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8621333333333333,
      "eval_loss": 0.4368409514427185,
      "eval_runtime": 7.9857,
      "eval_samples_per_second": 469.588,
      "eval_steps_per_second": 7.388,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 52.80767059326172,
      "learning_rate": 0.0001,
      "loss": 0.2174,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8746666666666667,
      "eval_loss": 0.424191415309906,
      "eval_runtime": 8.0315,
      "eval_samples_per_second": 466.911,
      "eval_steps_per_second": 7.346,
      "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
}