{
  "best_metric": 0.24626319110393524,
  "best_model_checkpoint": "faces_age_detection/checkpoint-4864",
  "epoch": 16.0,
  "eval_steps": 500,
  "global_step": 4864,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9048206710374084,
      "eval_loss": 0.25544658303260803,
      "eval_model_preparation_time": 0.0056,
      "eval_runtime": 115.8575,
      "eval_samples_per_second": 111.905,
      "eval_steps_per_second": 3.504,
      "step": 304
    },
    {
      "epoch": 1.6447368421052633,
      "grad_norm": 9.665897369384766,
      "learning_rate": 9.253731343283582e-07,
      "loss": 0.1128,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9051291939838025,
      "eval_loss": 0.25322863459587097,
      "eval_model_preparation_time": 0.0056,
      "eval_runtime": 116.0042,
      "eval_samples_per_second": 111.763,
      "eval_steps_per_second": 3.5,
      "step": 608
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.909371384496722,
      "eval_loss": 0.24770796298980713,
      "eval_model_preparation_time": 0.0056,
      "eval_runtime": 115.4652,
      "eval_samples_per_second": 112.285,
      "eval_steps_per_second": 3.516,
      "step": 912
    },
    {
      "epoch": 3.2894736842105265,
      "grad_norm": 5.963768482208252,
      "learning_rate": 8.424543946932007e-07,
      "loss": 0.1092,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9075973775549556,
      "eval_loss": 0.2508331835269928,
      "eval_model_preparation_time": 0.0056,
      "eval_runtime": 110.7185,
      "eval_samples_per_second": 117.099,
      "eval_steps_per_second": 3.667,
      "step": 1216
    },
    {
      "epoch": 4.934210526315789,
      "grad_norm": 6.369262218475342,
      "learning_rate": 7.595356550580431e-07,
      "loss": 0.1013,
      "step": 1500
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9069803316621674,
      "eval_loss": 0.24949955940246582,
      "eval_model_preparation_time": 0.0056,
      "eval_runtime": 114.7896,
      "eval_samples_per_second": 112.946,
      "eval_steps_per_second": 3.537,
      "step": 1520
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9052834554569996,
      "eval_loss": 0.2557480037212372,
      "eval_model_preparation_time": 0.0056,
      "eval_runtime": 117.3931,
      "eval_samples_per_second": 110.441,
      "eval_steps_per_second": 3.458,
      "step": 1824
    },
    {
      "epoch": 6.578947368421053,
      "grad_norm": 8.901986122131348,
      "learning_rate": 6.766169154228856e-07,
      "loss": 0.097,
      "step": 2000
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9085229463941381,
      "eval_loss": 0.2521224617958069,
      "eval_model_preparation_time": 0.0056,
      "eval_runtime": 116.8685,
      "eval_samples_per_second": 110.937,
      "eval_steps_per_second": 3.474,
      "step": 2128
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9035865792518318,
      "eval_loss": 0.2614166736602783,
      "eval_model_preparation_time": 0.0056,
      "eval_runtime": 117.7658,
      "eval_samples_per_second": 110.091,
      "eval_steps_per_second": 3.448,
      "step": 2432
    },
    {
      "epoch": 8.223684210526315,
      "grad_norm": 9.241392135620117,
      "learning_rate": 5.93698175787728e-07,
      "loss": 0.0981,
      "step": 2500
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9066718087157732,
      "eval_loss": 0.25424298644065857,
      "eval_model_preparation_time": 0.0056,
      "eval_runtime": 117.1049,
      "eval_samples_per_second": 110.713,
      "eval_steps_per_second": 3.467,
      "step": 2736
    },
    {
      "epoch": 9.868421052631579,
      "grad_norm": 15.468152046203613,
      "learning_rate": 5.107794361525704e-07,
      "loss": 0.0928,
      "step": 3000
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.9087543386039336,
      "eval_loss": 0.2496512234210968,
      "eval_model_preparation_time": 0.0056,
      "eval_runtime": 117.518,
      "eval_samples_per_second": 110.324,
      "eval_steps_per_second": 3.455,
      "step": 3040
    },
    {
      "epoch": 11.0,
      "eval_accuracy": 0.9098341689163132,
      "eval_loss": 0.2480880618095398,
      "eval_model_preparation_time": 0.0056,
      "eval_runtime": 119.13,
      "eval_samples_per_second": 108.831,
      "eval_steps_per_second": 3.408,
      "step": 3344
    },
    {
      "epoch": 11.513157894736842,
      "grad_norm": 9.02236557006836,
      "learning_rate": 4.278606965174129e-07,
      "loss": 0.088,
      "step": 3500
    },
    {
      "epoch": 12.0,
      "eval_accuracy": 0.9090628615503278,
      "eval_loss": 0.2512376010417938,
      "eval_model_preparation_time": 0.0056,
      "eval_runtime": 117.373,
      "eval_samples_per_second": 110.46,
      "eval_steps_per_second": 3.459,
      "step": 3648
    },
    {
      "epoch": 13.0,
      "eval_accuracy": 0.9090628615503278,
      "eval_loss": 0.2498735636472702,
      "eval_model_preparation_time": 0.0056,
      "eval_runtime": 116.0104,
      "eval_samples_per_second": 111.757,
      "eval_steps_per_second": 3.5,
      "step": 3952
    },
    {
      "epoch": 13.157894736842104,
      "grad_norm": 10.029730796813965,
      "learning_rate": 3.4494195688225535e-07,
      "loss": 0.0855,
      "step": 4000
    },
    {
      "epoch": 14.0,
      "eval_accuracy": 0.9099112996529117,
      "eval_loss": 0.24805885553359985,
      "eval_model_preparation_time": 0.0056,
      "eval_runtime": 116.2889,
      "eval_samples_per_second": 111.49,
      "eval_steps_per_second": 3.491,
      "step": 4256
    },
    {
      "epoch": 14.802631578947368,
      "grad_norm": 7.256553649902344,
      "learning_rate": 2.620232172470978e-07,
      "loss": 0.0847,
      "step": 4500
    },
    {
      "epoch": 15.0,
      "eval_accuracy": 0.9097570381797146,
      "eval_loss": 0.24851545691490173,
      "eval_model_preparation_time": 0.0056,
      "eval_runtime": 115.2188,
      "eval_samples_per_second": 112.525,
      "eval_steps_per_second": 3.524,
      "step": 4560
    },
    {
      "epoch": 16.0,
      "eval_accuracy": 0.9106054762822985,
      "eval_loss": 0.24626319110393524,
      "eval_model_preparation_time": 0.0056,
      "eval_runtime": 114.9847,
      "eval_samples_per_second": 112.754,
      "eval_steps_per_second": 3.531,
      "step": 4864
    }
  ],
  "logging_steps": 500,
  "max_steps": 6080,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.4112003658884735e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}