{
  "best_metric": 0.9104496240615845,
  "best_model_checkpoint": "miner_id_24/checkpoint-450",
  "epoch": 0.3996802557953637,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007993605115907274,
      "eval_loss": 1.1151251792907715,
      "eval_runtime": 45.2296,
      "eval_samples_per_second": 11.652,
      "eval_steps_per_second": 2.918,
      "step": 1
    },
    {
      "epoch": 0.007993605115907274,
      "grad_norm": 0.5252348780632019,
      "learning_rate": 4.08e-05,
      "loss": 1.0051,
      "step": 10
    },
    {
      "epoch": 0.01598721023181455,
      "grad_norm": 0.43166351318359375,
      "learning_rate": 8.16e-05,
      "loss": 0.9588,
      "step": 20
    },
    {
      "epoch": 0.023980815347721823,
      "grad_norm": 0.44364064931869507,
      "learning_rate": 0.0001224,
      "loss": 1.0191,
      "step": 30
    },
    {
      "epoch": 0.0319744204636291,
      "grad_norm": 0.6872465014457703,
      "learning_rate": 0.0001632,
      "loss": 0.9432,
      "step": 40
    },
    {
      "epoch": 0.03996802557953637,
      "grad_norm": 1.598119854927063,
      "learning_rate": 0.000204,
      "loss": 1.0892,
      "step": 50
    },
    {
      "epoch": 0.03996802557953637,
      "eval_loss": 1.001857876777649,
      "eval_runtime": 45.3776,
      "eval_samples_per_second": 11.614,
      "eval_steps_per_second": 2.909,
      "step": 50
    },
    {
      "epoch": 0.047961630695443645,
      "grad_norm": 0.41707491874694824,
      "learning_rate": 0.00020375153312650207,
      "loss": 0.8922,
      "step": 60
    },
    {
      "epoch": 0.055955235811350916,
      "grad_norm": 0.46729525923728943,
      "learning_rate": 0.00020300734301164017,
      "loss": 0.9199,
      "step": 70
    },
    {
      "epoch": 0.0639488409272582,
      "grad_norm": 0.4598965644836426,
      "learning_rate": 0.00020177105527484818,
      "loss": 0.9851,
      "step": 80
    },
    {
      "epoch": 0.07194244604316546,
      "grad_norm": 0.6346083283424377,
      "learning_rate": 0.00020004869298570854,
      "loss": 0.9267,
      "step": 90
    },
    {
      "epoch": 0.07993605115907274,
      "grad_norm": 1.6799523830413818,
      "learning_rate": 0.00019784864732016265,
      "loss": 1.0308,
      "step": 100
    },
    {
      "epoch": 0.07993605115907274,
      "eval_loss": 0.9804587960243225,
      "eval_runtime": 45.3385,
      "eval_samples_per_second": 11.624,
      "eval_steps_per_second": 2.911,
      "step": 100
    },
    {
      "epoch": 0.08792965627498002,
      "grad_norm": 0.4803275763988495,
      "learning_rate": 0.00019518163667954527,
      "loss": 0.8732,
      "step": 110
    },
    {
      "epoch": 0.09592326139088729,
      "grad_norm": 0.41773363947868347,
      "learning_rate": 0.00019206065447161056,
      "loss": 0.9207,
      "step": 120
    },
    {
      "epoch": 0.10391686650679456,
      "grad_norm": 0.5393093824386597,
      "learning_rate": 0.00018850090580795544,
      "loss": 0.9174,
      "step": 130
    },
    {
      "epoch": 0.11191047162270183,
      "grad_norm": 0.7868286371231079,
      "learning_rate": 0.00018451973342624464,
      "loss": 0.9564,
      "step": 140
    },
    {
      "epoch": 0.11990407673860912,
      "grad_norm": 1.877526879310608,
      "learning_rate": 0.00018013653319813575,
      "loss": 1.0422,
      "step": 150
    },
    {
      "epoch": 0.11990407673860912,
      "eval_loss": 0.9732909202575684,
      "eval_runtime": 45.3744,
      "eval_samples_per_second": 11.614,
      "eval_steps_per_second": 2.909,
      "step": 150
    },
    {
      "epoch": 0.1278976818545164,
      "grad_norm": 0.45178571343421936,
      "learning_rate": 0.0001753726596345424,
      "loss": 0.9106,
      "step": 160
    },
    {
      "epoch": 0.13589128697042366,
      "grad_norm": 0.43420538306236267,
      "learning_rate": 0.00017025132184860355,
      "loss": 0.9065,
      "step": 170
    },
    {
      "epoch": 0.14388489208633093,
      "grad_norm": 0.5061016082763672,
      "learning_rate": 0.00016479747048321714,
      "loss": 0.9256,
      "step": 180
    },
    {
      "epoch": 0.1518784972022382,
      "grad_norm": 0.5303362607955933,
      "learning_rate": 0.00015903767615401616,
      "loss": 0.965,
      "step": 190
    },
    {
      "epoch": 0.15987210231814547,
      "grad_norm": 1.220606803894043,
      "learning_rate": 0.000153,
      "loss": 1.0099,
      "step": 200
    },
    {
      "epoch": 0.15987210231814547,
      "eval_loss": 0.9468146562576294,
      "eval_runtime": 45.3675,
      "eval_samples_per_second": 11.616,
      "eval_steps_per_second": 2.91,
      "step": 200
    },
    {
      "epoch": 0.16786570743405277,
      "grad_norm": 0.4396389126777649,
      "learning_rate": 0.0001467138569724859,
      "loss": 0.9369,
      "step": 210
    },
    {
      "epoch": 0.17585931254996004,
      "grad_norm": 0.4094694256782532,
      "learning_rate": 0.00014020987252842305,
      "loss": 0.9071,
      "step": 220
    },
    {
      "epoch": 0.1838529176658673,
      "grad_norm": 0.4506022036075592,
      "learning_rate": 0.00013351973342624464,
      "loss": 0.8989,
      "step": 230
    },
    {
      "epoch": 0.19184652278177458,
      "grad_norm": 0.6226677298545837,
      "learning_rate": 0.00012667603335116609,
      "loss": 0.862,
      "step": 240
    },
    {
      "epoch": 0.19984012789768185,
      "grad_norm": 2.199631929397583,
      "learning_rate": 0.00011971211412202691,
      "loss": 1.0221,
      "step": 250
    },
    {
      "epoch": 0.19984012789768185,
      "eval_loss": 0.9447011351585388,
      "eval_runtime": 45.3598,
      "eval_samples_per_second": 11.618,
      "eval_steps_per_second": 2.91,
      "step": 250
    },
    {
      "epoch": 0.20783373301358912,
      "grad_norm": 0.3497827649116516,
      "learning_rate": 0.00011266190325330066,
      "loss": 0.9247,
      "step": 260
    },
    {
      "epoch": 0.2158273381294964,
      "grad_norm": 0.3851601779460907,
      "learning_rate": 0.00010555974866365511,
      "loss": 0.8747,
      "step": 270
    },
    {
      "epoch": 0.22382094324540366,
      "grad_norm": 0.413096159696579,
      "learning_rate": 9.844025133634492e-05,
      "loss": 0.9604,
      "step": 280
    },
    {
      "epoch": 0.23181454836131096,
      "grad_norm": 0.5563271641731262,
      "learning_rate": 9.133809674669937e-05,
      "loss": 0.8887,
      "step": 290
    },
    {
      "epoch": 0.23980815347721823,
      "grad_norm": 1.2481112480163574,
      "learning_rate": 8.428788587797311e-05,
      "loss": 0.991,
      "step": 300
    },
    {
      "epoch": 0.23980815347721823,
      "eval_loss": 0.9229258298873901,
      "eval_runtime": 45.3785,
      "eval_samples_per_second": 11.613,
      "eval_steps_per_second": 2.909,
      "step": 300
    },
    {
      "epoch": 0.2478017585931255,
      "grad_norm": 0.38026103377342224,
      "learning_rate": 7.73239666488339e-05,
      "loss": 0.907,
      "step": 310
    },
    {
      "epoch": 0.2557953637090328,
      "grad_norm": 0.4172312021255493,
      "learning_rate": 7.048026657375537e-05,
      "loss": 0.9205,
      "step": 320
    },
    {
      "epoch": 0.2637889688249401,
      "grad_norm": 0.4673878252506256,
      "learning_rate": 6.379012747157697e-05,
      "loss": 0.9441,
      "step": 330
    },
    {
      "epoch": 0.2717825739408473,
      "grad_norm": 0.5677220821380615,
      "learning_rate": 5.7286143027514095e-05,
      "loss": 0.8108,
      "step": 340
    },
    {
      "epoch": 0.2797761790567546,
      "grad_norm": 2.141495943069458,
      "learning_rate": 5.100000000000002e-05,
      "loss": 0.9879,
      "step": 350
    },
    {
      "epoch": 0.2797761790567546,
      "eval_loss": 0.9187855124473572,
      "eval_runtime": 45.4156,
      "eval_samples_per_second": 11.604,
      "eval_steps_per_second": 2.906,
      "step": 350
    },
    {
      "epoch": 0.28776978417266186,
      "grad_norm": 0.371738463640213,
      "learning_rate": 4.496232384598384e-05,
      "loss": 0.8332,
      "step": 360
    },
    {
      "epoch": 0.29576338928856916,
      "grad_norm": 0.4007952809333801,
      "learning_rate": 3.9202529516782854e-05,
      "loss": 0.8705,
      "step": 370
    },
    {
      "epoch": 0.3037569944044764,
      "grad_norm": 0.5161947011947632,
      "learning_rate": 3.374867815139649e-05,
      "loss": 0.8854,
      "step": 380
    },
    {
      "epoch": 0.3117505995203837,
      "grad_norm": 0.6701123714447021,
      "learning_rate": 2.8627340365457602e-05,
      "loss": 0.8572,
      "step": 390
    },
    {
      "epoch": 0.31974420463629094,
      "grad_norm": 1.3086506128311157,
      "learning_rate": 2.3863466801864254e-05,
      "loss": 0.981,
      "step": 400
    },
    {
      "epoch": 0.31974420463629094,
      "eval_loss": 0.9123491644859314,
      "eval_runtime": 45.6151,
      "eval_samples_per_second": 11.553,
      "eval_steps_per_second": 2.894,
      "step": 400
    },
    {
      "epoch": 0.32773780975219824,
      "grad_norm": 0.39428800344467163,
      "learning_rate": 1.9480266573755372e-05,
      "loss": 0.8043,
      "step": 410
    },
    {
      "epoch": 0.33573141486810554,
      "grad_norm": 0.35040971636772156,
      "learning_rate": 1.5499094192044554e-05,
      "loss": 0.8753,
      "step": 420
    },
    {
      "epoch": 0.3437250199840128,
      "grad_norm": 0.4119766354560852,
      "learning_rate": 1.1939345528389446e-05,
      "loss": 0.9301,
      "step": 430
    },
    {
      "epoch": 0.3517186250999201,
      "grad_norm": 0.5748882293701172,
      "learning_rate": 8.818363320454701e-06,
      "loss": 0.8807,
      "step": 440
    },
    {
      "epoch": 0.3597122302158273,
      "grad_norm": 1.0422980785369873,
      "learning_rate": 6.1513526798373514e-06,
      "loss": 0.9851,
      "step": 450
    },
    {
      "epoch": 0.3597122302158273,
      "eval_loss": 0.9104496240615845,
      "eval_runtime": 45.2223,
      "eval_samples_per_second": 11.654,
      "eval_steps_per_second": 2.919,
      "step": 450
    },
    {
      "epoch": 0.3677058353317346,
      "grad_norm": 0.4546515643596649,
      "learning_rate": 3.9513070142914725e-06,
      "loss": 0.8285,
      "step": 460
    },
    {
      "epoch": 0.37569944044764186,
      "grad_norm": 0.4213729500770569,
      "learning_rate": 2.2289447251518195e-06,
      "loss": 0.8871,
      "step": 470
    },
    {
      "epoch": 0.38369304556354916,
      "grad_norm": 0.39084315299987793,
      "learning_rate": 9.92656988359823e-07,
      "loss": 0.9132,
      "step": 480
    },
    {
      "epoch": 0.39168665067945646,
      "grad_norm": 0.6356387734413147,
      "learning_rate": 2.4846687349793185e-07,
      "loss": 0.8769,
      "step": 490
    },
    {
      "epoch": 0.3996802557953637,
      "grad_norm": 1.5205575227737427,
      "learning_rate": 0.0,
      "loss": 0.9026,
      "step": 500
    },
    {
      "epoch": 0.3996802557953637,
      "eval_loss": 0.9150660037994385,
      "eval_runtime": 45.1962,
      "eval_samples_per_second": 11.66,
      "eval_steps_per_second": 2.921,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3612634890410394e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}