trainer_state.json

{
  "best_metric": 0.9221333333333334,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0604/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": 64.39850616455078,
      "learning_rate": 0.0002851453301853628,
      "loss": 1.5274,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.856,
      "eval_loss": 0.49596723914146423,
      "eval_runtime": 14.1537,
      "eval_samples_per_second": 264.948,
      "eval_steps_per_second": 4.169,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 42.67170333862305,
      "learning_rate": 0.00024352347027881003,
      "loss": 0.3786,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8952,
      "eval_loss": 0.37319323420524597,
      "eval_runtime": 13.9255,
      "eval_samples_per_second": 269.29,
      "eval_steps_per_second": 4.237,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 46.753196716308594,
      "learning_rate": 0.00018337814009344714,
      "loss": 0.2002,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9096,
      "eval_loss": 0.333363801240921,
      "eval_runtime": 13.7185,
      "eval_samples_per_second": 273.353,
      "eval_steps_per_second": 4.301,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 37.59427261352539,
      "learning_rate": 0.00011662185990655284,
      "loss": 0.1143,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9194666666666667,
      "eval_loss": 0.32029759883880615,
      "eval_runtime": 13.853,
      "eval_samples_per_second": 270.7,
      "eval_steps_per_second": 4.259,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 36.47831726074219,
      "learning_rate": 5.6476529721189974e-05,
      "loss": 0.0736,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9221333333333334,
      "eval_loss": 0.3208913207054138,
      "eval_runtime": 14.333,
      "eval_samples_per_second": 261.634,
      "eval_steps_per_second": 4.116,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 2331,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "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
}