trainer_state.json

{
  "best_metric": 0.9002666666666667,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0943/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": 24.235097885131836,
      "learning_rate": 0.00046650635094610973,
      "loss": 1.3601,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8034666666666667,
      "eval_loss": 0.6407457590103149,
      "eval_runtime": 15.5644,
      "eval_samples_per_second": 240.934,
      "eval_steps_per_second": 3.791,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 30.703170776367188,
      "learning_rate": 0.000375,
      "loss": 0.4904,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8490666666666666,
      "eval_loss": 0.4816593825817108,
      "eval_runtime": 15.6709,
      "eval_samples_per_second": 239.297,
      "eval_steps_per_second": 3.765,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 23.69101905822754,
      "learning_rate": 0.00025,
      "loss": 0.2954,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8778666666666667,
      "eval_loss": 0.4078393280506134,
      "eval_runtime": 14.7983,
      "eval_samples_per_second": 253.407,
      "eval_steps_per_second": 3.987,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 31.134763717651367,
      "learning_rate": 0.00012500000000000006,
      "loss": 0.1723,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8904,
      "eval_loss": 0.38653549551963806,
      "eval_runtime": 14.5905,
      "eval_samples_per_second": 257.016,
      "eval_steps_per_second": 4.044,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 23.319026947021484,
      "learning_rate": 3.3493649053890325e-05,
      "loss": 0.1125,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9002666666666667,
      "eval_loss": 0.35433050990104675,
      "eval_runtime": 15.86,
      "eval_samples_per_second": 236.444,
      "eval_steps_per_second": 3.72,
      "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
}