{
  "best_metric": 0.5424528301886793,
  "best_model_checkpoint": "./Validated_Balanced_Raw_Data_model_boost7_outputs/checkpoint-640",
  "epoch": 25.0,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.3490566037735849,
      "eval_loss": 1.3316097259521484,
      "eval_runtime": 1.7234,
      "eval_samples_per_second": 123.011,
      "eval_steps_per_second": 8.123,
      "step": 40
    },
    {
      "epoch": 1.25,
      "grad_norm": 8.837675094604492,
      "learning_rate": 1.5e-05,
      "loss": 1.3694,
      "step": 50
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.37264150943396224,
      "eval_loss": 1.2695280313491821,
      "eval_runtime": 1.7368,
      "eval_samples_per_second": 122.063,
      "eval_steps_per_second": 8.061,
      "step": 80
    },
    {
      "epoch": 2.5,
      "grad_norm": 23.59905433654785,
      "learning_rate": 1.4897709775520418e-05,
      "loss": 1.291,
      "step": 100
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.41509433962264153,
      "eval_loss": 1.2237251996994019,
      "eval_runtime": 1.7278,
      "eval_samples_per_second": 122.701,
      "eval_steps_per_second": 8.103,
      "step": 120
    },
    {
      "epoch": 3.75,
      "grad_norm": 12.828843116760254,
      "learning_rate": 1.4593629312754759e-05,
      "loss": 1.2374,
      "step": 150
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.4481132075471698,
      "eval_loss": 1.1886036396026611,
      "eval_runtime": 1.7269,
      "eval_samples_per_second": 122.761,
      "eval_steps_per_second": 8.107,
      "step": 160
    },
    {
      "epoch": 5.0,
      "grad_norm": 23.113628387451172,
      "learning_rate": 1.4096053134048668e-05,
      "loss": 1.1815,
      "step": 200
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.4386792452830189,
      "eval_loss": 1.1869800090789795,
      "eval_runtime": 1.7412,
      "eval_samples_per_second": 121.752,
      "eval_steps_per_second": 8.04,
      "step": 200
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.4716981132075472,
      "eval_loss": 1.172649621963501,
      "eval_runtime": 1.7177,
      "eval_samples_per_second": 123.418,
      "eval_steps_per_second": 8.15,
      "step": 240
    },
    {
      "epoch": 6.25,
      "grad_norm": 23.421894073486328,
      "learning_rate": 1.3418553820472952e-05,
      "loss": 1.1479,
      "step": 250
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.4858490566037736,
      "eval_loss": 1.12235426902771,
      "eval_runtime": 1.742,
      "eval_samples_per_second": 121.7,
      "eval_steps_per_second": 8.037,
      "step": 280
    },
    {
      "epoch": 7.5,
      "grad_norm": 21.626155853271484,
      "learning_rate": 1.2579611787193059e-05,
      "loss": 1.0818,
      "step": 300
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.4716981132075472,
      "eval_loss": 1.1309412717819214,
      "eval_runtime": 1.7266,
      "eval_samples_per_second": 122.786,
      "eval_steps_per_second": 8.109,
      "step": 320
    },
    {
      "epoch": 8.75,
      "grad_norm": 17.436782836914062,
      "learning_rate": 1.1602111185918205e-05,
      "loss": 1.0507,
      "step": 350
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.4811320754716981,
      "eval_loss": 1.1351451873779297,
      "eval_runtime": 1.7198,
      "eval_samples_per_second": 123.27,
      "eval_steps_per_second": 8.14,
      "step": 360
    },
    {
      "epoch": 10.0,
      "grad_norm": 25.729656219482422,
      "learning_rate": 1.0512715684897273e-05,
      "loss": 1.0198,
      "step": 400
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.5188679245283019,
      "eval_loss": 1.1313749551773071,
      "eval_runtime": 1.7239,
      "eval_samples_per_second": 122.975,
      "eval_steps_per_second": 8.121,
      "step": 400
    },
    {
      "epoch": 11.0,
      "eval_accuracy": 0.5047169811320755,
      "eval_loss": 1.1235365867614746,
      "eval_runtime": 1.7373,
      "eval_samples_per_second": 122.031,
      "eval_steps_per_second": 8.059,
      "step": 440
    },
    {
      "epoch": 11.25,
      "grad_norm": 17.072206497192383,
      "learning_rate": 9.341141153555994e-06,
      "loss": 1.0075,
      "step": 450
    },
    {
      "epoch": 12.0,
      "eval_accuracy": 0.5283018867924528,
      "eval_loss": 1.113572359085083,
      "eval_runtime": 1.7317,
      "eval_samples_per_second": 122.424,
      "eval_steps_per_second": 8.085,
      "step": 480
    },
    {
      "epoch": 12.5,
      "grad_norm": 29.981237411499023,
      "learning_rate": 8.119345091042494e-06,
      "loss": 0.9692,
      "step": 500
    },
    {
      "epoch": 13.0,
      "eval_accuracy": 0.5094339622641509,
      "eval_loss": 1.1230112314224243,
      "eval_runtime": 1.7323,
      "eval_samples_per_second": 122.381,
      "eval_steps_per_second": 8.082,
      "step": 520
    },
    {
      "epoch": 13.75,
      "grad_norm": 23.71090316772461,
      "learning_rate": 6.8806549089575084e-06,
      "loss": 0.919,
      "step": 550
    },
    {
      "epoch": 14.0,
      "eval_accuracy": 0.5,
      "eval_loss": 1.1158391237258911,
      "eval_runtime": 1.7323,
      "eval_samples_per_second": 122.38,
      "eval_steps_per_second": 8.082,
      "step": 560
    },
    {
      "epoch": 15.0,
      "grad_norm": 20.237754821777344,
      "learning_rate": 5.658858846444007e-06,
      "loss": 0.9306,
      "step": 600
    },
    {
      "epoch": 15.0,
      "eval_accuracy": 0.5235849056603774,
      "eval_loss": 1.108890175819397,
      "eval_runtime": 1.7314,
      "eval_samples_per_second": 122.444,
      "eval_steps_per_second": 8.086,
      "step": 600
    },
    {
      "epoch": 16.0,
      "eval_accuracy": 0.5424528301886793,
      "eval_loss": 1.1008423566818237,
      "eval_runtime": 1.7198,
      "eval_samples_per_second": 123.273,
      "eval_steps_per_second": 8.141,
      "step": 640
    },
    {
      "epoch": 16.25,
      "grad_norm": 15.5910062789917,
      "learning_rate": 4.487284315102731e-06,
      "loss": 0.89,
      "step": 650
    },
    {
      "epoch": 17.0,
      "eval_accuracy": 0.5235849056603774,
      "eval_loss": 1.1071282625198364,
      "eval_runtime": 1.7351,
      "eval_samples_per_second": 122.185,
      "eval_steps_per_second": 8.069,
      "step": 680
    },
    {
      "epoch": 17.5,
      "grad_norm": 19.464712142944336,
      "learning_rate": 3.3978888140817996e-06,
      "loss": 0.8853,
      "step": 700
    },
    {
      "epoch": 18.0,
      "eval_accuracy": 0.5235849056603774,
      "eval_loss": 1.1110377311706543,
      "eval_runtime": 1.7376,
      "eval_samples_per_second": 122.008,
      "eval_steps_per_second": 8.057,
      "step": 720
    },
    {
      "epoch": 18.75,
      "grad_norm": 24.714292526245117,
      "learning_rate": 2.4203882128069435e-06,
      "loss": 0.8852,
      "step": 750
    },
    {
      "epoch": 19.0,
      "eval_accuracy": 0.5330188679245284,
      "eval_loss": 1.102632761001587,
      "eval_runtime": 1.7735,
      "eval_samples_per_second": 119.541,
      "eval_steps_per_second": 7.894,
      "step": 760
    },
    {
      "epoch": 20.0,
      "grad_norm": 19.79788589477539,
      "learning_rate": 1.581446179527049e-06,
      "loss": 0.824,
      "step": 800
    },
    {
      "epoch": 20.0,
      "eval_accuracy": 0.5377358490566038,
      "eval_loss": 1.1056451797485352,
      "eval_runtime": 1.7219,
      "eval_samples_per_second": 123.121,
      "eval_steps_per_second": 8.131,
      "step": 800
    },
    {
      "epoch": 21.0,
      "eval_accuracy": 0.5283018867924528,
      "eval_loss": 1.1087795495986938,
      "eval_runtime": 1.7345,
      "eval_samples_per_second": 122.225,
      "eval_steps_per_second": 8.071,
      "step": 840
    },
    {
      "epoch": 21.25,
      "grad_norm": 35.61381912231445,
      "learning_rate": 9.039468659513328e-07,
      "loss": 0.8327,
      "step": 850
    },
    {
      "epoch": 22.0,
      "eval_accuracy": 0.5283018867924528,
      "eval_loss": 1.1064716577529907,
      "eval_runtime": 1.7395,
      "eval_samples_per_second": 121.872,
      "eval_steps_per_second": 8.048,
      "step": 880
    },
    {
      "epoch": 22.5,
      "grad_norm": 19.63943099975586,
      "learning_rate": 4.0637068724524024e-07,
      "loss": 0.832,
      "step": 900
    },
    {
      "epoch": 23.0,
      "eval_accuracy": 0.5330188679245284,
      "eval_loss": 1.1062887907028198,
      "eval_runtime": 1.7199,
      "eval_samples_per_second": 123.265,
      "eval_steps_per_second": 8.14,
      "step": 920
    },
    {
      "epoch": 23.75,
      "grad_norm": 16.668516159057617,
      "learning_rate": 1.0229022447958258e-07,
      "loss": 0.8801,
      "step": 950
    },
    {
      "epoch": 24.0,
      "eval_accuracy": 0.5330188679245284,
      "eval_loss": 1.106476902961731,
      "eval_runtime": 1.7268,
      "eval_samples_per_second": 122.771,
      "eval_steps_per_second": 8.108,
      "step": 960
    },
    {
      "epoch": 25.0,
      "grad_norm": 17.07996368408203,
      "learning_rate": 0.0,
      "loss": 0.8372,
      "step": 1000
    },
    {
      "epoch": 25.0,
      "eval_accuracy": 0.5330188679245284,
      "eval_loss": 1.1065127849578857,
      "eval_runtime": 3.038,
      "eval_samples_per_second": 69.784,
      "eval_steps_per_second": 4.608,
      "step": 1000
    },
    {
      "epoch": 25.0,
      "step": 1000,
      "total_flos": 1.2575458052333568e+18,
      "train_loss": 1.0036159286499022,
      "train_runtime": 496.6689,
      "train_samples_per_second": 32.013,
      "train_steps_per_second": 2.013
    }
  ],
  "logging_steps": 50,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 25,
  "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": 1.2575458052333568e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}