trainer_state.json

{
  "best_metric": 0.9064,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0868/checkpoints/checkpoint-2664",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 2664,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 101.3674087524414,
      "learning_rate": 7e-05,
      "loss": 3.1831,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7005333333333333,
      "eval_loss": 1.5176186561584473,
      "eval_runtime": 8.4113,
      "eval_samples_per_second": 445.826,
      "eval_steps_per_second": 7.014,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 146.1080780029297,
      "learning_rate": 7e-05,
      "loss": 0.8692,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8450666666666666,
      "eval_loss": 0.5522176027297974,
      "eval_runtime": 7.809,
      "eval_samples_per_second": 480.214,
      "eval_steps_per_second": 7.555,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 58.24928665161133,
      "learning_rate": 7e-05,
      "loss": 0.49,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8765333333333334,
      "eval_loss": 0.4139595329761505,
      "eval_runtime": 7.8359,
      "eval_samples_per_second": 478.565,
      "eval_steps_per_second": 7.529,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 289.7763977050781,
      "learning_rate": 7e-05,
      "loss": 0.3473,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8837333333333334,
      "eval_loss": 0.3747752904891968,
      "eval_runtime": 7.8462,
      "eval_samples_per_second": 477.939,
      "eval_steps_per_second": 7.52,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 102.9919204711914,
      "learning_rate": 7e-05,
      "loss": 0.2646,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9029333333333334,
      "eval_loss": 0.32736802101135254,
      "eval_runtime": 7.7608,
      "eval_samples_per_second": 483.201,
      "eval_steps_per_second": 7.602,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 114.98345947265625,
      "learning_rate": 7e-05,
      "loss": 0.1936,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9045333333333333,
      "eval_loss": 0.33243605494499207,
      "eval_runtime": 7.8075,
      "eval_samples_per_second": 480.31,
      "eval_steps_per_second": 7.557,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 118.31366729736328,
      "learning_rate": 7e-05,
      "loss": 0.1606,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9061333333333333,
      "eval_loss": 0.31925544142723083,
      "eval_runtime": 7.734,
      "eval_samples_per_second": 484.874,
      "eval_steps_per_second": 7.629,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 95.88990783691406,
      "learning_rate": 7e-05,
      "loss": 0.118,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9064,
      "eval_loss": 0.3418484926223755,
      "eval_runtime": 7.7749,
      "eval_samples_per_second": 482.32,
      "eval_steps_per_second": 7.589,
      "step": 2664
    }
  ],
  "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": 6.5411433916416e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}