trainer_state.json

{
  "best_metric": 0.8962666666666667,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0976/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": 92.3934555053711,
      "learning_rate": 8.397114317029975e-05,
      "loss": 2.86,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7610666666666667,
      "eval_loss": 0.9605636596679688,
      "eval_runtime": 8.2159,
      "eval_samples_per_second": 456.434,
      "eval_steps_per_second": 7.181,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 232.306640625,
      "learning_rate": 6.75e-05,
      "loss": 0.6583,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8589333333333333,
      "eval_loss": 0.46219030022621155,
      "eval_runtime": 8.3254,
      "eval_samples_per_second": 450.43,
      "eval_steps_per_second": 7.087,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 72.78318786621094,
      "learning_rate": 4.5e-05,
      "loss": 0.3971,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8837333333333334,
      "eval_loss": 0.3716278672218323,
      "eval_runtime": 8.1274,
      "eval_samples_per_second": 461.4,
      "eval_steps_per_second": 7.259,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 116.12120819091797,
      "learning_rate": 2.250000000000001e-05,
      "loss": 0.2979,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8866666666666667,
      "eval_loss": 0.3521459400653839,
      "eval_runtime": 8.2725,
      "eval_samples_per_second": 453.311,
      "eval_steps_per_second": 7.132,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 145.1870574951172,
      "learning_rate": 6.028856829700258e-06,
      "loss": 0.2423,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8933333333333333,
      "eval_loss": 0.33127161860466003,
      "eval_runtime": 8.0962,
      "eval_samples_per_second": 463.181,
      "eval_steps_per_second": 7.287,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 144.8201141357422,
      "learning_rate": 0.0,
      "loss": 0.2297,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8962666666666667,
      "eval_loss": 0.33027923107147217,
      "eval_runtime": 8.3695,
      "eval_samples_per_second": 448.053,
      "eval_steps_per_second": 7.049,
      "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
}