trainer_state.json

{
  "best_metric": 0.8826666666666667,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0748/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": 165.5404510498047,
      "learning_rate": 8.333333333333334e-05,
      "loss": 2.8057,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7408,
      "eval_loss": 0.9799200296401978,
      "eval_runtime": 12.389,
      "eval_samples_per_second": 302.687,
      "eval_steps_per_second": 4.762,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 104.72116088867188,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.7251,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.84,
      "eval_loss": 0.5352976322174072,
      "eval_runtime": 12.3385,
      "eval_samples_per_second": 303.926,
      "eval_steps_per_second": 4.782,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 126.62652587890625,
      "learning_rate": 5e-05,
      "loss": 0.4375,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8634666666666667,
      "eval_loss": 0.45735782384872437,
      "eval_runtime": 12.2657,
      "eval_samples_per_second": 305.732,
      "eval_steps_per_second": 4.81,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 152.77053833007812,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.2972,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8778666666666667,
      "eval_loss": 0.3989119231700897,
      "eval_runtime": 12.2451,
      "eval_samples_per_second": 306.246,
      "eval_steps_per_second": 4.818,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 42.61225128173828,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.226,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8797333333333334,
      "eval_loss": 0.39763718843460083,
      "eval_runtime": 12.2314,
      "eval_samples_per_second": 306.588,
      "eval_steps_per_second": 4.824,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 92.87071228027344,
      "learning_rate": 0.0,
      "loss": 0.1899,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8826666666666667,
      "eval_loss": 0.39044544100761414,
      "eval_runtime": 12.2364,
      "eval_samples_per_second": 306.462,
      "eval_steps_per_second": 4.822,
      "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
}