trainer_state.json

{
  "best_metric": 0.8802666666666666,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0194/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": 105.63937377929688,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.6622,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.74,
      "eval_loss": 0.9289666414260864,
      "eval_runtime": 7.7384,
      "eval_samples_per_second": 484.598,
      "eval_steps_per_second": 7.624,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 141.2833709716797,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.7066,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8298666666666666,
      "eval_loss": 0.5334078669548035,
      "eval_runtime": 7.8715,
      "eval_samples_per_second": 476.405,
      "eval_steps_per_second": 7.495,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 118.03437805175781,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.4323,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8586666666666667,
      "eval_loss": 0.4483139216899872,
      "eval_runtime": 7.6556,
      "eval_samples_per_second": 489.838,
      "eval_steps_per_second": 7.707,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 99.06718444824219,
      "learning_rate": 5e-05,
      "loss": 0.3141,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.872,
      "eval_loss": 0.41143152117729187,
      "eval_runtime": 7.7327,
      "eval_samples_per_second": 484.955,
      "eval_steps_per_second": 7.63,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 127.16712951660156,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.2348,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8802666666666666,
      "eval_loss": 0.39300593733787537,
      "eval_runtime": 7.726,
      "eval_samples_per_second": 485.373,
      "eval_steps_per_second": 7.637,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 2664,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "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
}