trainer_state.json

{
  "best_metric": 0.86,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0733/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": 74.54644775390625,
      "learning_rate": 4.166666666666667e-05,
      "loss": 3.6941,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5018666666666667,
      "eval_loss": 3.1740572452545166,
      "eval_runtime": 7.317,
      "eval_samples_per_second": 512.504,
      "eval_steps_per_second": 8.063,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 124.19330596923828,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.9204,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7525333333333334,
      "eval_loss": 1.0439846515655518,
      "eval_runtime": 7.3959,
      "eval_samples_per_second": 507.041,
      "eval_steps_per_second": 7.977,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 95.4197006225586,
      "learning_rate": 2.5e-05,
      "loss": 0.861,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8274666666666667,
      "eval_loss": 0.6555474400520325,
      "eval_runtime": 7.0297,
      "eval_samples_per_second": 533.451,
      "eval_steps_per_second": 8.393,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 93.04365539550781,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.6281,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8466666666666667,
      "eval_loss": 0.5427197217941284,
      "eval_runtime": 7.1789,
      "eval_samples_per_second": 522.367,
      "eval_steps_per_second": 8.219,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 48.07441329956055,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.5376,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8584,
      "eval_loss": 0.5122101306915283,
      "eval_runtime": 7.0997,
      "eval_samples_per_second": 528.188,
      "eval_steps_per_second": 8.31,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 115.93987274169922,
      "learning_rate": 0.0,
      "loss": 0.4938,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.86,
      "eval_loss": 0.4956072270870209,
      "eval_runtime": 7.0131,
      "eval_samples_per_second": 534.712,
      "eval_steps_per_second": 8.413,
      "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
}