{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.147058823529412,
  "eval_steps": 100,
  "global_step": 700,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.7352941176470589,
      "grad_norm": 2339.16845703125,
      "learning_rate": 9.754901960784315e-06,
      "loss": 234.6293,
      "step": 100
    },
    {
      "epoch": 0.7352941176470589,
      "eval_loss": 105.00587463378906,
      "eval_mae": 8.158556938171387,
      "eval_mse": 105.00587463378906,
      "eval_r": 0.5881958470613986,
      "eval_r2": 0.34597435450027625,
      "eval_rmse": 10.247237205505371,
      "eval_runtime": 134.375,
      "eval_samples_per_second": 1.771,
      "eval_steps_per_second": 0.223,
      "step": 100
    },
    {
      "epoch": 1.4705882352941178,
      "grad_norm": 866.0792846679688,
      "learning_rate": 9.509803921568628e-06,
      "loss": 89.6617,
      "step": 200
    },
    {
      "epoch": 1.4705882352941178,
      "eval_loss": 71.10962677001953,
      "eval_mae": 6.599854469299316,
      "eval_mse": 71.109619140625,
      "eval_r": 0.7463886727166605,
      "eval_r2": 0.5570960507597382,
      "eval_rmse": 8.43265151977539,
      "eval_runtime": 134.3993,
      "eval_samples_per_second": 1.771,
      "eval_steps_per_second": 0.223,
      "step": 200
    },
    {
      "epoch": 2.2058823529411766,
      "grad_norm": 1974.856689453125,
      "learning_rate": 9.264705882352942e-06,
      "loss": 51.7083,
      "step": 300
    },
    {
      "epoch": 2.2058823529411766,
      "eval_loss": 56.539913177490234,
      "eval_mae": 5.843647480010986,
      "eval_mse": 56.53990936279297,
      "eval_r": 0.804886953590405,
      "eval_r2": 0.6478430080600428,
      "eval_rmse": 7.5193023681640625,
      "eval_runtime": 134.5191,
      "eval_samples_per_second": 1.769,
      "eval_steps_per_second": 0.223,
      "step": 300
    },
    {
      "epoch": 2.9411764705882355,
      "grad_norm": 1413.519287109375,
      "learning_rate": 9.019607843137256e-06,
      "loss": 49.0308,
      "step": 400
    },
    {
      "epoch": 2.9411764705882355,
      "eval_loss": 57.29434585571289,
      "eval_mae": 5.7630510330200195,
      "eval_mse": 57.294349670410156,
      "eval_r": 0.8019626185557365,
      "eval_r2": 0.6431440415607736,
      "eval_rmse": 7.569303035736084,
      "eval_runtime": 134.5021,
      "eval_samples_per_second": 1.769,
      "eval_steps_per_second": 0.223,
      "step": 400
    },
    {
      "epoch": 3.6764705882352944,
      "grad_norm": 701.0978393554688,
      "learning_rate": 8.774509803921569e-06,
      "loss": 34.5754,
      "step": 500
    },
    {
      "epoch": 3.6764705882352944,
      "eval_loss": 53.095096588134766,
      "eval_mae": 5.596792697906494,
      "eval_mse": 53.0951042175293,
      "eval_r": 0.8181069057240362,
      "eval_r2": 0.6692989091933571,
      "eval_rmse": 7.2866387367248535,
      "eval_runtime": 134.5073,
      "eval_samples_per_second": 1.769,
      "eval_steps_per_second": 0.223,
      "step": 500
    },
    {
      "epoch": 4.411764705882353,
      "grad_norm": 1168.67529296875,
      "learning_rate": 8.529411764705883e-06,
      "loss": 27.2059,
      "step": 600
    },
    {
      "epoch": 4.411764705882353,
      "eval_loss": 50.413002014160156,
      "eval_mae": 5.489666938781738,
      "eval_mse": 50.41299819946289,
      "eval_r": 0.8282537565427732,
      "eval_r2": 0.6860042852272155,
      "eval_rmse": 7.100211143493652,
      "eval_runtime": 134.4525,
      "eval_samples_per_second": 1.77,
      "eval_steps_per_second": 0.223,
      "step": 600
    },
    {
      "epoch": 5.147058823529412,
      "grad_norm": 582.685791015625,
      "learning_rate": 8.284313725490198e-06,
      "loss": 21.8168,
      "step": 700
    },
    {
      "epoch": 5.147058823529412,
      "eval_loss": 47.175933837890625,
      "eval_mae": 5.249522686004639,
      "eval_mse": 47.17593002319336,
      "eval_r": 0.840336989423733,
      "eval_r2": 0.7061662557937431,
      "eval_rmse": 6.868473529815674,
      "eval_runtime": 135.0633,
      "eval_samples_per_second": 1.762,
      "eval_steps_per_second": 0.222,
      "step": 700
    }
  ],
  "logging_steps": 100,
  "max_steps": 4080,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 30,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.413247702951936e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}