trainer_state.json

{
  "best_metric": 0.8458666666666667,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0490/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": 61.20468521118164,
      "learning_rate": 8e-05,
      "loss": 2.9343,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6554666666666666,
      "eval_loss": 1.353907823562622,
      "eval_runtime": 8.8193,
      "eval_samples_per_second": 425.202,
      "eval_steps_per_second": 6.69,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 67.60106658935547,
      "learning_rate": 6e-05,
      "loss": 0.917,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8042666666666667,
      "eval_loss": 0.7032368779182434,
      "eval_runtime": 8.2183,
      "eval_samples_per_second": 456.299,
      "eval_steps_per_second": 7.179,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 172.6485595703125,
      "learning_rate": 4e-05,
      "loss": 0.6119,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8261333333333334,
      "eval_loss": 0.5885595083236694,
      "eval_runtime": 8.0473,
      "eval_samples_per_second": 465.992,
      "eval_steps_per_second": 7.332,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 59.034820556640625,
      "learning_rate": 2e-05,
      "loss": 0.4964,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8432,
      "eval_loss": 0.5382495522499084,
      "eval_runtime": 7.9928,
      "eval_samples_per_second": 469.17,
      "eval_steps_per_second": 7.382,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 75.12092590332031,
      "learning_rate": 0.0,
      "loss": 0.4475,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8458666666666667,
      "eval_loss": 0.5271149277687073,
      "eval_runtime": 7.6246,
      "eval_samples_per_second": 491.828,
      "eval_steps_per_second": 7.738,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 1665,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 4.088214619776e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}