trainer_state.json

{
  "best_metric": 0.9093333333333333,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0616/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": 58.05323791503906,
      "learning_rate": 0.00025,
      "loss": 1.4658,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8541333333333333,
      "eval_loss": 0.47440052032470703,
      "eval_runtime": 12.9839,
      "eval_samples_per_second": 288.82,
      "eval_steps_per_second": 4.544,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 69.8543701171875,
      "learning_rate": 0.00019999999999999998,
      "loss": 0.3834,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8858666666666667,
      "eval_loss": 0.3671484887599945,
      "eval_runtime": 12.9195,
      "eval_samples_per_second": 290.259,
      "eval_steps_per_second": 4.567,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 124.00447845458984,
      "learning_rate": 0.00015,
      "loss": 0.2173,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8930666666666667,
      "eval_loss": 0.33850058913230896,
      "eval_runtime": 13.0297,
      "eval_samples_per_second": 287.804,
      "eval_steps_per_second": 4.528,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 47.014678955078125,
      "learning_rate": 9.999999999999999e-05,
      "loss": 0.1246,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9021333333333333,
      "eval_loss": 0.33687344193458557,
      "eval_runtime": 13.4855,
      "eval_samples_per_second": 278.077,
      "eval_steps_per_second": 4.375,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 39.29249954223633,
      "learning_rate": 4.9999999999999996e-05,
      "loss": 0.0774,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9093333333333333,
      "eval_loss": 0.31986188888549805,
      "eval_runtime": 13.1647,
      "eval_samples_per_second": 284.852,
      "eval_steps_per_second": 4.482,
      "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
}