trainer_state.json

{
  "best_metric": 0.8981333333333333,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0873/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": 133.18862915039062,
      "learning_rate": 8.397114317029975e-05,
      "loss": 2.8508,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7634666666666666,
      "eval_loss": 0.9641450643539429,
      "eval_runtime": 9.026,
      "eval_samples_per_second": 415.466,
      "eval_steps_per_second": 6.537,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 108.99188232421875,
      "learning_rate": 6.75e-05,
      "loss": 0.6604,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8648,
      "eval_loss": 0.48545923829078674,
      "eval_runtime": 8.9906,
      "eval_samples_per_second": 417.102,
      "eval_steps_per_second": 6.562,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 104.87564849853516,
      "learning_rate": 4.5e-05,
      "loss": 0.42,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8896,
      "eval_loss": 0.37471920251846313,
      "eval_runtime": 9.0073,
      "eval_samples_per_second": 416.331,
      "eval_steps_per_second": 6.55,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 106.07954406738281,
      "learning_rate": 2.250000000000001e-05,
      "loss": 0.312,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8917333333333334,
      "eval_loss": 0.3572552800178528,
      "eval_runtime": 8.9526,
      "eval_samples_per_second": 418.872,
      "eval_steps_per_second": 6.59,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 301.56622314453125,
      "learning_rate": 6.028856829700258e-06,
      "loss": 0.257,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8965333333333333,
      "eval_loss": 0.338148832321167,
      "eval_runtime": 8.8344,
      "eval_samples_per_second": 424.475,
      "eval_steps_per_second": 6.678,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 53.218231201171875,
      "learning_rate": 0.0,
      "loss": 0.2324,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8981333333333333,
      "eval_loss": 0.34444573521614075,
      "eval_runtime": 8.8182,
      "eval_samples_per_second": 425.256,
      "eval_steps_per_second": 6.691,
      "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
}