{
  "best_metric": 1.0447938442230225,
  "best_model_checkpoint": "fairface_age_image_detection/checkpoint-8752",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 8752,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.22851919561243145,
      "grad_norm": 2.228593587875366,
      "learning_rate": 3.7931509997701674e-06,
      "loss": 1.8122,
      "step": 500
    },
    {
      "epoch": 0.4570383912248629,
      "grad_norm": 3.4612433910369873,
      "learning_rate": 3.5633187772925763e-06,
      "loss": 1.4177,
      "step": 1000
    },
    {
      "epoch": 0.6855575868372943,
      "grad_norm": 5.7468061447143555,
      "learning_rate": 3.333486554814985e-06,
      "loss": 1.3017,
      "step": 1500
    },
    {
      "epoch": 0.9140767824497258,
      "grad_norm": 4.807565212249756,
      "learning_rate": 3.1036543323373935e-06,
      "loss": 1.2187,
      "step": 2000
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5457,
      "eval_loss": 1.1929566860198975,
      "eval_model_preparation_time": 0.0035,
      "eval_runtime": 876.5594,
      "eval_samples_per_second": 11.408,
      "eval_steps_per_second": 1.426,
      "step": 2188
    },
    {
      "epoch": 1.1425959780621573,
      "grad_norm": 3.004606246948242,
      "learning_rate": 2.873822109859802e-06,
      "loss": 1.1713,
      "step": 2500
    },
    {
      "epoch": 1.3711151736745886,
      "grad_norm": 4.531455039978027,
      "learning_rate": 2.643989887382211e-06,
      "loss": 1.1284,
      "step": 3000
    },
    {
      "epoch": 1.59963436928702,
      "grad_norm": 3.8209729194641113,
      "learning_rate": 2.4141576649046196e-06,
      "loss": 1.105,
      "step": 3500
    },
    {
      "epoch": 1.8281535648994516,
      "grad_norm": 3.4607913494110107,
      "learning_rate": 2.184325442427028e-06,
      "loss": 1.0773,
      "step": 4000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5754,
      "eval_loss": 1.085502028465271,
      "eval_model_preparation_time": 0.0035,
      "eval_runtime": 892.4566,
      "eval_samples_per_second": 11.205,
      "eval_steps_per_second": 1.401,
      "step": 4376
    },
    {
      "epoch": 2.056672760511883,
      "grad_norm": 4.261874675750732,
      "learning_rate": 1.954493219949437e-06,
      "loss": 1.0657,
      "step": 4500
    },
    {
      "epoch": 2.2851919561243146,
      "grad_norm": 3.815229654312134,
      "learning_rate": 1.7246609974718455e-06,
      "loss": 1.036,
      "step": 5000
    },
    {
      "epoch": 2.5137111517367456,
      "grad_norm": 4.119363307952881,
      "learning_rate": 1.494828774994254e-06,
      "loss": 1.0255,
      "step": 5500
    },
    {
      "epoch": 2.742230347349177,
      "grad_norm": 4.172023296356201,
      "learning_rate": 1.2649965525166627e-06,
      "loss": 1.0126,
      "step": 6000
    },
    {
      "epoch": 2.9707495429616086,
      "grad_norm": 3.792961597442627,
      "learning_rate": 1.0351643300390714e-06,
      "loss": 1.008,
      "step": 6500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.5792,
      "eval_loss": 1.0549699068069458,
      "eval_model_preparation_time": 0.0035,
      "eval_runtime": 902.9283,
      "eval_samples_per_second": 11.075,
      "eval_steps_per_second": 1.384,
      "step": 6564
    },
    {
      "epoch": 3.19926873857404,
      "grad_norm": 6.58300256729126,
      "learning_rate": 8.053321075614801e-07,
      "loss": 0.9923,
      "step": 7000
    },
    {
      "epoch": 3.4277879341864717,
      "grad_norm": 7.9831223487854,
      "learning_rate": 5.754998850838887e-07,
      "loss": 0.9792,
      "step": 7500
    },
    {
      "epoch": 3.656307129798903,
      "grad_norm": 6.074549198150635,
      "learning_rate": 3.456676626062974e-07,
      "loss": 0.9826,
      "step": 8000
    },
    {
      "epoch": 3.8848263254113347,
      "grad_norm": 6.298589706420898,
      "learning_rate": 1.1583544012870603e-07,
      "loss": 0.9858,
      "step": 8500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.5809,
      "eval_loss": 1.0447938442230225,
      "eval_model_preparation_time": 0.0035,
      "eval_runtime": 893.1973,
      "eval_samples_per_second": 11.196,
      "eval_steps_per_second": 1.399,
      "step": 8752
    }
  ],
  "logging_steps": 500,
  "max_steps": 8752,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": 2.169911838302208e+19,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}