{
  "best_metric": 1.1867649555206299,
  "best_model_checkpoint": "cat_breed_image_detection/checkpoint-7623",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 7623,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.19677292404565133,
      "grad_norm": 15.461106300354004,
      "learning_rate": 8.465205334741845e-07,
      "loss": 1.1454,
      "step": 500
    },
    {
      "epoch": 0.39354584809130266,
      "grad_norm": 22.293109893798828,
      "learning_rate": 7.870989040010564e-07,
      "loss": 1.1528,
      "step": 1000
    },
    {
      "epoch": 0.5903187721369539,
      "grad_norm": 8.640257835388184,
      "learning_rate": 7.276772745279281e-07,
      "loss": 1.1559,
      "step": 1500
    },
    {
      "epoch": 0.7870916961826053,
      "grad_norm": 11.094526290893555,
      "learning_rate": 6.682556450547999e-07,
      "loss": 1.1593,
      "step": 2000
    },
    {
      "epoch": 0.9838646202282566,
      "grad_norm": 11.131674766540527,
      "learning_rate": 6.088340155816718e-07,
      "loss": 1.1221,
      "step": 2500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6807554620608208,
      "eval_loss": 1.2059290409088135,
      "eval_model_preparation_time": 0.0051,
      "eval_runtime": 1193.0691,
      "eval_samples_per_second": 90.845,
      "eval_steps_per_second": 2.839,
      "step": 2541
    },
    {
      "epoch": 1.1806375442739079,
      "grad_norm": 8.923126220703125,
      "learning_rate": 5.494123861085435e-07,
      "loss": 1.1413,
      "step": 3000
    },
    {
      "epoch": 1.3774104683195592,
      "grad_norm": 9.620901107788086,
      "learning_rate": 4.899907566354153e-07,
      "loss": 1.12,
      "step": 3500
    },
    {
      "epoch": 1.5741833923652107,
      "grad_norm": 11.071784019470215,
      "learning_rate": 4.3056912716228705e-07,
      "loss": 1.1305,
      "step": 4000
    },
    {
      "epoch": 1.770956316410862,
      "grad_norm": 9.808845520019531,
      "learning_rate": 3.7114749768915883e-07,
      "loss": 1.1187,
      "step": 4500
    },
    {
      "epoch": 1.9677292404565132,
      "grad_norm": 8.686152458190918,
      "learning_rate": 3.117258682160306e-07,
      "loss": 1.1238,
      "step": 5000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6841415707115441,
      "eval_loss": 1.19118332862854,
      "eval_model_preparation_time": 0.0051,
      "eval_runtime": 1188.9153,
      "eval_samples_per_second": 91.162,
      "eval_steps_per_second": 2.849,
      "step": 5082
    },
    {
      "epoch": 2.1645021645021645,
      "grad_norm": 9.841617584228516,
      "learning_rate": 2.523042387429024e-07,
      "loss": 1.1033,
      "step": 5500
    },
    {
      "epoch": 2.3612750885478158,
      "grad_norm": 10.633978843688965,
      "learning_rate": 1.928826092697742e-07,
      "loss": 1.1176,
      "step": 6000
    },
    {
      "epoch": 2.558048012593467,
      "grad_norm": 8.568585395812988,
      "learning_rate": 1.3346097979664598e-07,
      "loss": 1.1193,
      "step": 6500
    },
    {
      "epoch": 2.7548209366391183,
      "grad_norm": 10.57896900177002,
      "learning_rate": 7.403935032351777e-08,
      "loss": 1.107,
      "step": 7000
    },
    {
      "epoch": 2.9515938606847696,
      "grad_norm": 9.359890937805176,
      "learning_rate": 1.4617720850389543e-08,
      "loss": 1.1133,
      "step": 7500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6847412902273399,
      "eval_loss": 1.1867649555206299,
      "eval_model_preparation_time": 0.0051,
      "eval_runtime": 1192.8682,
      "eval_samples_per_second": 90.86,
      "eval_steps_per_second": 2.839,
      "step": 7623
    }
  ],
  "logging_steps": 500,
  "max_steps": 7623,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 3.781059536914691e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}