trainer_state.json

{
  "best_metric": 0.8773333333333333,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0881/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": 55.55165100097656,
      "learning_rate": 7.714285714285714e-05,
      "loss": 2.8113,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7408,
      "eval_loss": 0.9853889346122742,
      "eval_runtime": 7.2493,
      "eval_samples_per_second": 517.29,
      "eval_steps_per_second": 8.139,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 136.68572998046875,
      "learning_rate": 6.428571428571429e-05,
      "loss": 0.6803,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8322666666666667,
      "eval_loss": 0.5555428266525269,
      "eval_runtime": 7.2256,
      "eval_samples_per_second": 518.987,
      "eval_steps_per_second": 8.165,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 91.24752044677734,
      "learning_rate": 5.142857142857143e-05,
      "loss": 0.3975,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8634666666666667,
      "eval_loss": 0.45081251859664917,
      "eval_runtime": 7.855,
      "eval_samples_per_second": 477.405,
      "eval_steps_per_second": 7.511,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 40.76348114013672,
      "learning_rate": 3.857142857142857e-05,
      "loss": 0.2683,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.868,
      "eval_loss": 0.42737242579460144,
      "eval_runtime": 7.1998,
      "eval_samples_per_second": 520.849,
      "eval_steps_per_second": 8.195,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 120.5693359375,
      "learning_rate": 2.5714285714285714e-05,
      "loss": 0.2025,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8773333333333333,
      "eval_loss": 0.41064807772636414,
      "eval_runtime": 7.2658,
      "eval_samples_per_second": 516.117,
      "eval_steps_per_second": 8.12,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 2331,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "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
}