trainer_state.json

{
  "best_metric": 0.8221333333333334,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0759/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": 78.26910400390625,
      "learning_rate": 4.665063509461097e-05,
      "loss": 3.7013,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.4594666666666667,
      "eval_loss": 3.116044282913208,
      "eval_runtime": 16.862,
      "eval_samples_per_second": 222.393,
      "eval_steps_per_second": 3.499,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 114.36479949951172,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 1.9244,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7272,
      "eval_loss": 1.1749392747879028,
      "eval_runtime": 15.4441,
      "eval_samples_per_second": 242.811,
      "eval_steps_per_second": 3.82,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 136.8190460205078,
      "learning_rate": 2.5e-05,
      "loss": 0.8902,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8010666666666667,
      "eval_loss": 0.7293215990066528,
      "eval_runtime": 15.6428,
      "eval_samples_per_second": 239.727,
      "eval_steps_per_second": 3.772,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 89.99472045898438,
      "learning_rate": 1.2500000000000006e-05,
      "loss": 0.6935,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8202666666666667,
      "eval_loss": 0.6586235761642456,
      "eval_runtime": 15.4621,
      "eval_samples_per_second": 242.529,
      "eval_steps_per_second": 3.816,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 116.5846176147461,
      "learning_rate": 3.3493649053890326e-06,
      "loss": 0.6133,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8208,
      "eval_loss": 0.608548104763031,
      "eval_runtime": 15.2103,
      "eval_samples_per_second": 246.544,
      "eval_steps_per_second": 3.879,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 113.60604858398438,
      "learning_rate": 0.0,
      "loss": 0.576,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8221333333333334,
      "eval_loss": 0.6069856882095337,
      "eval_runtime": 15.5046,
      "eval_samples_per_second": 241.864,
      "eval_steps_per_second": 3.805,
      "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
}