{
  "best_metric": 1.203418254852295,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.24289531212047608,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00048579062424095217,
      "eval_loss": 2.597476005554199,
      "eval_runtime": 51.8065,
      "eval_samples_per_second": 16.735,
      "eval_steps_per_second": 4.189,
      "step": 1
    },
    {
      "epoch": 0.004857906242409522,
      "grad_norm": 12.25637435913086,
      "learning_rate": 4.0600000000000004e-05,
      "loss": 3.1277,
      "step": 10
    },
    {
      "epoch": 0.009715812484819043,
      "grad_norm": 15.654220581054688,
      "learning_rate": 8.120000000000001e-05,
      "loss": 2.4062,
      "step": 20
    },
    {
      "epoch": 0.014573718727228565,
      "grad_norm": 15.304265022277832,
      "learning_rate": 0.00012179999999999999,
      "loss": 2.406,
      "step": 30
    },
    {
      "epoch": 0.019431624969638087,
      "grad_norm": 16.849159240722656,
      "learning_rate": 0.00016240000000000002,
      "loss": 2.9756,
      "step": 40
    },
    {
      "epoch": 0.024289531212047608,
      "grad_norm": 18.647008895874023,
      "learning_rate": 0.000203,
      "loss": 2.9989,
      "step": 50
    },
    {
      "epoch": 0.024289531212047608,
      "eval_loss": 1.6901915073394775,
      "eval_runtime": 51.7466,
      "eval_samples_per_second": 16.755,
      "eval_steps_per_second": 4.194,
      "step": 50
    },
    {
      "epoch": 0.02914743745445713,
      "grad_norm": 13.382312774658203,
      "learning_rate": 0.00020275275110137215,
      "loss": 2.9041,
      "step": 60
    },
    {
      "epoch": 0.03400534369686665,
      "grad_norm": 11.256575584411621,
      "learning_rate": 0.00020201220897726938,
      "loss": 2.3314,
      "step": 70
    },
    {
      "epoch": 0.03886324993927617,
      "grad_norm": 19.787755966186523,
      "learning_rate": 0.00020078198147448128,
      "loss": 3.2341,
      "step": 80
    },
    {
      "epoch": 0.04372115618168569,
      "grad_norm": 25.911598205566406,
      "learning_rate": 0.00019906806213773937,
      "loss": 3.3715,
      "step": 90
    },
    {
      "epoch": 0.048579062424095217,
      "grad_norm": 18.073326110839844,
      "learning_rate": 0.0001968788010097697,
      "loss": 3.3957,
      "step": 100
    },
    {
      "epoch": 0.048579062424095217,
      "eval_loss": 1.8113958835601807,
      "eval_runtime": 51.8565,
      "eval_samples_per_second": 16.719,
      "eval_steps_per_second": 4.185,
      "step": 100
    },
    {
      "epoch": 0.053436968666504735,
      "grad_norm": 13.869400978088379,
      "learning_rate": 0.00019422486395072398,
      "loss": 2.8832,
      "step": 110
    },
    {
      "epoch": 0.05829487490891426,
      "grad_norm": 14.071908950805664,
      "learning_rate": 0.0001911191806751811,
      "loss": 2.2136,
      "step": 120
    },
    {
      "epoch": 0.06315278115132378,
      "grad_norm": 18.943180084228516,
      "learning_rate": 0.00018757688175987723,
      "loss": 2.9134,
      "step": 130
    },
    {
      "epoch": 0.0680106873937333,
      "grad_norm": 22.638784408569336,
      "learning_rate": 0.00018361522492905716,
      "loss": 3.348,
      "step": 140
    },
    {
      "epoch": 0.07286859363614283,
      "grad_norm": 23.163434982299805,
      "learning_rate": 0.00017925351097657625,
      "loss": 3.1821,
      "step": 150
    },
    {
      "epoch": 0.07286859363614283,
      "eval_loss": 1.734904170036316,
      "eval_runtime": 51.755,
      "eval_samples_per_second": 16.752,
      "eval_steps_per_second": 4.193,
      "step": 150
    },
    {
      "epoch": 0.07772649987855235,
      "grad_norm": 13.139738082885742,
      "learning_rate": 0.00017451298973437308,
      "loss": 3.0728,
      "step": 160
    },
    {
      "epoch": 0.08258440612096186,
      "grad_norm": 14.566117286682129,
      "learning_rate": 0.0001694167565454241,
      "loss": 2.2269,
      "step": 170
    },
    {
      "epoch": 0.08744231236337138,
      "grad_norm": 14.927955627441406,
      "learning_rate": 0.0001639896397455543,
      "loss": 2.9797,
      "step": 180
    },
    {
      "epoch": 0.09230021860578091,
      "grad_norm": 21.02972412109375,
      "learning_rate": 0.0001582580797022808,
      "loss": 3.4754,
      "step": 190
    },
    {
      "epoch": 0.09715812484819043,
      "grad_norm": 18.39568328857422,
      "learning_rate": 0.00015225,
      "loss": 2.9795,
      "step": 200
    },
    {
      "epoch": 0.09715812484819043,
      "eval_loss": 1.6877731084823608,
      "eval_runtime": 51.7681,
      "eval_samples_per_second": 16.748,
      "eval_steps_per_second": 4.192,
      "step": 200
    },
    {
      "epoch": 0.10201603109059995,
      "grad_norm": 15.680115699768066,
      "learning_rate": 0.00014599467139909136,
      "loss": 2.9233,
      "step": 210
    },
    {
      "epoch": 0.10687393733300947,
      "grad_norm": 14.90787410736084,
      "learning_rate": 0.0001395225692317151,
      "loss": 2.299,
      "step": 220
    },
    {
      "epoch": 0.11173184357541899,
      "grad_norm": 24.221662521362305,
      "learning_rate": 0.00013286522492905717,
      "loss": 3.2907,
      "step": 230
    },
    {
      "epoch": 0.11658974981782852,
      "grad_norm": 21.316699981689453,
      "learning_rate": 0.00012605507240336626,
      "loss": 3.3841,
      "step": 240
    },
    {
      "epoch": 0.12144765606023804,
      "grad_norm": 24.28824234008789,
      "learning_rate": 0.00011912529003319345,
      "loss": 2.8327,
      "step": 250
    },
    {
      "epoch": 0.12144765606023804,
      "eval_loss": 1.6964420080184937,
      "eval_runtime": 51.7608,
      "eval_samples_per_second": 16.75,
      "eval_steps_per_second": 4.192,
      "step": 250
    },
    {
      "epoch": 0.12630556230264756,
      "grad_norm": 12.285757064819336,
      "learning_rate": 0.00011210963902166683,
      "loss": 2.9801,
      "step": 260
    },
    {
      "epoch": 0.1311634685450571,
      "grad_norm": 22.15928077697754,
      "learning_rate": 0.00010504229891530386,
      "loss": 2.1664,
      "step": 270
    },
    {
      "epoch": 0.1360213747874666,
      "grad_norm": 17.29761505126953,
      "learning_rate": 9.795770108469618e-05,
      "loss": 2.964,
      "step": 280
    },
    {
      "epoch": 0.14087928102987612,
      "grad_norm": 18.979280471801758,
      "learning_rate": 9.08903609783332e-05,
      "loss": 2.8507,
      "step": 290
    },
    {
      "epoch": 0.14573718727228566,
      "grad_norm": 16.6581974029541,
      "learning_rate": 8.387470996680658e-05,
      "loss": 3.0645,
      "step": 300
    },
    {
      "epoch": 0.14573718727228566,
      "eval_loss": 1.4894201755523682,
      "eval_runtime": 51.8231,
      "eval_samples_per_second": 16.73,
      "eval_steps_per_second": 4.187,
      "step": 300
    },
    {
      "epoch": 0.15059509351469516,
      "grad_norm": 9.372559547424316,
      "learning_rate": 7.694492759663374e-05,
      "loss": 2.9475,
      "step": 310
    },
    {
      "epoch": 0.1554529997571047,
      "grad_norm": 10.691730499267578,
      "learning_rate": 7.013477507094284e-05,
      "loss": 2.1435,
      "step": 320
    },
    {
      "epoch": 0.1603109059995142,
      "grad_norm": 17.997329711914062,
      "learning_rate": 6.347743076828492e-05,
      "loss": 2.7516,
      "step": 330
    },
    {
      "epoch": 0.16516881224192373,
      "grad_norm": 16.696796417236328,
      "learning_rate": 5.700532860090863e-05,
      "loss": 3.2521,
      "step": 340
    },
    {
      "epoch": 0.17002671848433326,
      "grad_norm": 28.0440673828125,
      "learning_rate": 5.075000000000002e-05,
      "loss": 2.8703,
      "step": 350
    },
    {
      "epoch": 0.17002671848433326,
      "eval_loss": 1.369873285293579,
      "eval_runtime": 51.81,
      "eval_samples_per_second": 16.734,
      "eval_steps_per_second": 4.188,
      "step": 350
    },
    {
      "epoch": 0.17488462472674277,
      "grad_norm": 12.38694953918457,
      "learning_rate": 4.4741920297719214e-05,
      "loss": 2.8135,
      "step": 360
    },
    {
      "epoch": 0.1797425309691523,
      "grad_norm": 13.077108383178711,
      "learning_rate": 3.901036025444568e-05,
      "loss": 2.2428,
      "step": 370
    },
    {
      "epoch": 0.18460043721156183,
      "grad_norm": 12.912416458129883,
      "learning_rate": 3.358324345457592e-05,
      "loss": 2.7104,
      "step": 380
    },
    {
      "epoch": 0.18945834345397133,
      "grad_norm": 17.72833824157715,
      "learning_rate": 2.8487010265626928e-05,
      "loss": 3.0005,
      "step": 390
    },
    {
      "epoch": 0.19431624969638087,
      "grad_norm": 14.066707611083984,
      "learning_rate": 2.3746489023423744e-05,
      "loss": 2.4628,
      "step": 400
    },
    {
      "epoch": 0.19431624969638087,
      "eval_loss": 1.2493934631347656,
      "eval_runtime": 51.9117,
      "eval_samples_per_second": 16.701,
      "eval_steps_per_second": 4.18,
      "step": 400
    },
    {
      "epoch": 0.19917415593879037,
      "grad_norm": 7.286698341369629,
      "learning_rate": 1.9384775070942844e-05,
      "loss": 2.6138,
      "step": 410
    },
    {
      "epoch": 0.2040320621811999,
      "grad_norm": 11.685407638549805,
      "learning_rate": 1.5423118240122765e-05,
      "loss": 2.108,
      "step": 420
    },
    {
      "epoch": 0.20888996842360943,
      "grad_norm": 19.53931427001953,
      "learning_rate": 1.188081932481891e-05,
      "loss": 2.7771,
      "step": 430
    },
    {
      "epoch": 0.21374787466601894,
      "grad_norm": 13.099770545959473,
      "learning_rate": 8.775136049276001e-06,
      "loss": 2.7575,
      "step": 440
    },
    {
      "epoch": 0.21860578090842847,
      "grad_norm": 14.228134155273438,
      "learning_rate": 6.121198990230306e-06,
      "loss": 2.6866,
      "step": 450
    },
    {
      "epoch": 0.21860578090842847,
      "eval_loss": 1.212476134300232,
      "eval_runtime": 51.7835,
      "eval_samples_per_second": 16.743,
      "eval_steps_per_second": 4.191,
      "step": 450
    },
    {
      "epoch": 0.22346368715083798,
      "grad_norm": 11.355395317077637,
      "learning_rate": 3.931937862260632e-06,
      "loss": 2.4105,
      "step": 460
    },
    {
      "epoch": 0.2283215933932475,
      "grad_norm": 12.874826431274414,
      "learning_rate": 2.2180185255187225e-06,
      "loss": 2.0398,
      "step": 470
    },
    {
      "epoch": 0.23317949963565704,
      "grad_norm": 12.14913558959961,
      "learning_rate": 9.877910227306082e-07,
      "loss": 2.3378,
      "step": 480
    },
    {
      "epoch": 0.23803740587806654,
      "grad_norm": 13.777284622192383,
      "learning_rate": 2.472488986278439e-07,
      "loss": 2.6441,
      "step": 490
    },
    {
      "epoch": 0.24289531212047608,
      "grad_norm": 13.6741361618042,
      "learning_rate": 0.0,
      "loss": 2.2741,
      "step": 500
    },
    {
      "epoch": 0.24289531212047608,
      "eval_loss": 1.203418254852295,
      "eval_runtime": 51.91,
      "eval_samples_per_second": 16.702,
      "eval_steps_per_second": 4.18,
      "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": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8.9437375561728e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}