trainer_state.json

{
  "best_metric": 0.8661333333333333,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0378/checkpoints/checkpoint-1998",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 1998,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 351.08154296875,
      "learning_rate": 5.833333333333333e-05,
      "loss": 3.338,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.616,
      "eval_loss": 1.8797506093978882,
      "eval_runtime": 7.9636,
      "eval_samples_per_second": 470.894,
      "eval_steps_per_second": 7.409,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 200.6509552001953,
      "learning_rate": 4.666666666666666e-05,
      "loss": 1.036,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8117333333333333,
      "eval_loss": 0.6812692880630493,
      "eval_runtime": 7.7354,
      "eval_samples_per_second": 484.782,
      "eval_steps_per_second": 7.627,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 227.67933654785156,
      "learning_rate": 3.5e-05,
      "loss": 0.5579,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8456,
      "eval_loss": 0.5318609476089478,
      "eval_runtime": 7.7905,
      "eval_samples_per_second": 481.358,
      "eval_steps_per_second": 7.573,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 102.95213317871094,
      "learning_rate": 2.333333333333333e-05,
      "loss": 0.4081,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8517333333333333,
      "eval_loss": 0.47886979579925537,
      "eval_runtime": 8.9399,
      "eval_samples_per_second": 419.466,
      "eval_steps_per_second": 6.6,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 315.458740234375,
      "learning_rate": 1.1666666666666665e-05,
      "loss": 0.3307,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8586666666666667,
      "eval_loss": 0.4576277434825897,
      "eval_runtime": 8.0824,
      "eval_samples_per_second": 463.97,
      "eval_steps_per_second": 7.3,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 333.52325439453125,
      "learning_rate": 0.0,
      "loss": 0.292,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8661333333333333,
      "eval_loss": 0.44635719060897827,
      "eval_runtime": 7.9883,
      "eval_samples_per_second": 469.438,
      "eval_steps_per_second": 7.386,
      "step": 1998
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.9058575437312e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}