trainer_state.json

{
  "best_metric": 0.8618666666666667,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0079/checkpoints/checkpoint-1665",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1665,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 23.530372619628906,
      "learning_rate": 0.0005,
      "loss": 1.3984,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7981333333333334,
      "eval_loss": 0.6681093573570251,
      "eval_runtime": 15.1921,
      "eval_samples_per_second": 246.839,
      "eval_steps_per_second": 3.884,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 30.48270034790039,
      "learning_rate": 0.0005,
      "loss": 0.526,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8325333333333333,
      "eval_loss": 0.5630276203155518,
      "eval_runtime": 15.409,
      "eval_samples_per_second": 243.365,
      "eval_steps_per_second": 3.829,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 57.79594039916992,
      "learning_rate": 0.0005,
      "loss": 0.3737,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8528,
      "eval_loss": 0.5193114876747131,
      "eval_runtime": 15.4808,
      "eval_samples_per_second": 242.236,
      "eval_steps_per_second": 3.811,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 19.71271324157715,
      "learning_rate": 0.0005,
      "loss": 0.2758,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8522666666666666,
      "eval_loss": 0.5335282683372498,
      "eval_runtime": 15.3885,
      "eval_samples_per_second": 243.688,
      "eval_steps_per_second": 3.834,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 21.426544189453125,
      "learning_rate": 0.0005,
      "loss": 0.2116,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8618666666666667,
      "eval_loss": 0.5258660912513733,
      "eval_runtime": 15.516,
      "eval_samples_per_second": 241.686,
      "eval_steps_per_second": 3.803,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 2997,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.088214619776e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}