trainer_state.json

{
  "best_metric": 0.9146666666666666,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0899/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": 21.998661041259766,
      "learning_rate": 0.0004809698831278217,
      "loss": 1.3537,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8370666666666666,
      "eval_loss": 0.557547926902771,
      "eval_runtime": 9.4308,
      "eval_samples_per_second": 397.633,
      "eval_steps_per_second": 6.256,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 21.124452590942383,
      "learning_rate": 0.00042677669529663686,
      "loss": 0.4578,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8541333333333333,
      "eval_loss": 0.4996621608734131,
      "eval_runtime": 9.3592,
      "eval_samples_per_second": 400.677,
      "eval_steps_per_second": 6.304,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 37.180789947509766,
      "learning_rate": 0.0003456708580912725,
      "loss": 0.2948,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.88,
      "eval_loss": 0.3973759710788727,
      "eval_runtime": 9.4293,
      "eval_samples_per_second": 397.697,
      "eval_steps_per_second": 6.257,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 49.003746032714844,
      "learning_rate": 0.00025,
      "loss": 0.182,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8946666666666667,
      "eval_loss": 0.3756262958049774,
      "eval_runtime": 9.3852,
      "eval_samples_per_second": 399.563,
      "eval_steps_per_second": 6.286,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 38.07117462158203,
      "learning_rate": 0.00015432914190872756,
      "loss": 0.1117,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8970666666666667,
      "eval_loss": 0.4064522087574005,
      "eval_runtime": 9.2756,
      "eval_samples_per_second": 404.285,
      "eval_steps_per_second": 6.361,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 24.329132080078125,
      "learning_rate": 7.322330470336314e-05,
      "loss": 0.0695,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.908,
      "eval_loss": 0.3512488901615143,
      "eval_runtime": 9.6965,
      "eval_samples_per_second": 386.738,
      "eval_steps_per_second": 6.085,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 24.07823944091797,
      "learning_rate": 1.9030116872178316e-05,
      "loss": 0.0384,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9128,
      "eval_loss": 0.3578130900859833,
      "eval_runtime": 9.397,
      "eval_samples_per_second": 399.064,
      "eval_steps_per_second": 6.279,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 22.751253128051758,
      "learning_rate": 0.0,
      "loss": 0.0351,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9146666666666666,
      "eval_loss": 0.3479357361793518,
      "eval_runtime": 8.9365,
      "eval_samples_per_second": 419.626,
      "eval_steps_per_second": 6.602,
      "step": 2664
    }
  ],
  "logging_steps": 500,
  "max_steps": 2664,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.5411433916416e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}