trainer_state.json

{
  "best_metric": 0.6928,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0690/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": 61.960731506347656,
      "learning_rate": 2.7990381056766583e-05,
      "loss": 3.8483,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.33626666666666666,
      "eval_loss": 3.726046323776245,
      "eval_runtime": 13.1313,
      "eval_samples_per_second": 285.576,
      "eval_steps_per_second": 4.493,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 101.42253112792969,
      "learning_rate": 2.25e-05,
      "loss": 3.3347,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5085333333333333,
      "eval_loss": 2.9870963096618652,
      "eval_runtime": 13.1305,
      "eval_samples_per_second": 285.595,
      "eval_steps_per_second": 4.493,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 138.69615173339844,
      "learning_rate": 1.5e-05,
      "loss": 2.3329,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6237333333333334,
      "eval_loss": 1.8692265748977661,
      "eval_runtime": 13.1069,
      "eval_samples_per_second": 286.109,
      "eval_steps_per_second": 4.501,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 102.76213073730469,
      "learning_rate": 7.500000000000004e-06,
      "loss": 1.645,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.6674666666666667,
      "eval_loss": 1.4899879693984985,
      "eval_runtime": 13.2024,
      "eval_samples_per_second": 284.038,
      "eval_steps_per_second": 4.469,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 124.51185607910156,
      "learning_rate": 2.0096189432334194e-06,
      "loss": 1.4235,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.6928,
      "eval_loss": 1.3468869924545288,
      "eval_runtime": 13.1742,
      "eval_samples_per_second": 284.646,
      "eval_steps_per_second": 4.478,
      "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
}