trainer_state.json

{
  "best_metric": 0.8888,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0165/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": 50.119293212890625,
      "learning_rate": 0.00046650635094610973,
      "loss": 1.4403,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8125333333333333,
      "eval_loss": 0.649817705154419,
      "eval_runtime": 15.7047,
      "eval_samples_per_second": 238.781,
      "eval_steps_per_second": 3.757,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 30.476037979125977,
      "learning_rate": 0.000375,
      "loss": 0.5089,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8474666666666667,
      "eval_loss": 0.5022464394569397,
      "eval_runtime": 15.9114,
      "eval_samples_per_second": 235.68,
      "eval_steps_per_second": 3.708,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 40.05959701538086,
      "learning_rate": 0.00025,
      "loss": 0.3055,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8733333333333333,
      "eval_loss": 0.4422416388988495,
      "eval_runtime": 15.6074,
      "eval_samples_per_second": 240.271,
      "eval_steps_per_second": 3.78,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 44.5186653137207,
      "learning_rate": 0.00012500000000000006,
      "loss": 0.1828,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8850666666666667,
      "eval_loss": 0.41415292024612427,
      "eval_runtime": 15.6485,
      "eval_samples_per_second": 239.64,
      "eval_steps_per_second": 3.77,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 28.03150177001953,
      "learning_rate": 3.3493649053890325e-05,
      "loss": 0.1111,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8888,
      "eval_loss": 0.41267129778862,
      "eval_runtime": 15.7454,
      "eval_samples_per_second": 238.164,
      "eval_steps_per_second": 3.747,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 1998,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "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
}