{
  "best_metric": 3.989581823348999,
  "best_model_checkpoint": "miner_id_24/checkpoint-600",
  "epoch": 1.1320754716981132,
  "eval_steps": 50,
  "global_step": 600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0018867924528301887,
      "eval_loss": 4.477752685546875,
      "eval_runtime": 40.7428,
      "eval_samples_per_second": 21.918,
      "eval_steps_per_second": 5.498,
      "step": 1
    },
    {
      "epoch": 0.018867924528301886,
      "grad_norm": 15.21529483795166,
      "learning_rate": 0.0002,
      "loss": 4.2379,
      "step": 10
    },
    {
      "epoch": 0.03773584905660377,
      "grad_norm": 54.98305130004883,
      "learning_rate": 0.0001998582695676762,
      "loss": 27.8114,
      "step": 20
    },
    {
      "epoch": 0.05660377358490566,
      "grad_norm": 16.903823852539062,
      "learning_rate": 0.00019943348002101371,
      "loss": 25.2762,
      "step": 30
    },
    {
      "epoch": 0.07547169811320754,
      "grad_norm": 172.9484405517578,
      "learning_rate": 0.00019872683547213446,
      "loss": 23.4547,
      "step": 40
    },
    {
      "epoch": 0.09433962264150944,
      "grad_norm": 164.54025268554688,
      "learning_rate": 0.00019774033898178667,
      "loss": 8.2119,
      "step": 50
    },
    {
      "epoch": 0.09433962264150944,
      "eval_loss": 7.419450759887695,
      "eval_runtime": 41.389,
      "eval_samples_per_second": 21.576,
      "eval_steps_per_second": 5.412,
      "step": 50
    },
    {
      "epoch": 0.11320754716981132,
      "grad_norm": 44.91653060913086,
      "learning_rate": 0.0001964767868814516,
      "loss": 30.0243,
      "step": 60
    },
    {
      "epoch": 0.1320754716981132,
      "grad_norm": 9.489733695983887,
      "learning_rate": 0.00019493976084683813,
      "loss": 25.1776,
      "step": 70
    },
    {
      "epoch": 0.1509433962264151,
      "grad_norm": 47.95170211791992,
      "learning_rate": 0.00019313361774523385,
      "loss": 24.4991,
      "step": 80
    },
    {
      "epoch": 0.16981132075471697,
      "grad_norm": 166.98104858398438,
      "learning_rate": 0.00019106347728549135,
      "loss": 16.642,
      "step": 90
    },
    {
      "epoch": 0.18867924528301888,
      "grad_norm": 155.18824768066406,
      "learning_rate": 0.00018873520750565718,
      "loss": 6.9458,
      "step": 100
    },
    {
      "epoch": 0.18867924528301888,
      "eval_loss": 14.900463104248047,
      "eval_runtime": 41.4137,
      "eval_samples_per_second": 21.563,
      "eval_steps_per_second": 5.409,
      "step": 100
    },
    {
      "epoch": 0.20754716981132076,
      "grad_norm": 31.870784759521484,
      "learning_rate": 0.0001861554081393806,
      "loss": 55.9772,
      "step": 110
    },
    {
      "epoch": 0.22641509433962265,
      "grad_norm": 19.77384376525879,
      "learning_rate": 0.0001833313919082515,
      "loss": 25.2894,
      "step": 120
    },
    {
      "epoch": 0.24528301886792453,
      "grad_norm": 71.0095443725586,
      "learning_rate": 0.00018027116379309638,
      "loss": 24.5163,
      "step": 130
    },
    {
      "epoch": 0.2641509433962264,
      "grad_norm": 328.7481384277344,
      "learning_rate": 0.00017698339834299061,
      "loss": 15.8981,
      "step": 140
    },
    {
      "epoch": 0.2830188679245283,
      "grad_norm": 242.60081481933594,
      "learning_rate": 0.00017347741508630672,
      "loss": 6.2023,
      "step": 150
    },
    {
      "epoch": 0.2830188679245283,
      "eval_loss": 11.450271606445312,
      "eval_runtime": 41.4022,
      "eval_samples_per_second": 21.569,
      "eval_steps_per_second": 5.41,
      "step": 150
    },
    {
      "epoch": 0.3018867924528302,
      "grad_norm": 31.868478775024414,
      "learning_rate": 0.0001697631521134985,
      "loss": 38.3331,
      "step": 160
    },
    {
      "epoch": 0.32075471698113206,
      "grad_norm": 25.038724899291992,
      "learning_rate": 0.00016585113790650388,
      "loss": 24.7657,
      "step": 170
    },
    {
      "epoch": 0.33962264150943394,
      "grad_norm": 53.333683013916016,
      "learning_rate": 0.0001617524614946192,
      "loss": 23.8673,
      "step": 180
    },
    {
      "epoch": 0.3584905660377358,
      "grad_norm": 183.1505889892578,
      "learning_rate": 0.0001574787410214407,
      "loss": 12.851,
      "step": 190
    },
    {
      "epoch": 0.37735849056603776,
      "grad_norm": 199.62698364257812,
      "learning_rate": 0.00015304209081197425,
      "loss": 3.7041,
      "step": 200
    },
    {
      "epoch": 0.37735849056603776,
      "eval_loss": 10.561553001403809,
      "eval_runtime": 41.4742,
      "eval_samples_per_second": 21.531,
      "eval_steps_per_second": 5.401,
      "step": 200
    },
    {
      "epoch": 0.39622641509433965,
      "grad_norm": 30.381412506103516,
      "learning_rate": 0.00014845508703326504,
      "loss": 36.4437,
      "step": 210
    },
    {
      "epoch": 0.41509433962264153,
      "grad_norm": 25.108572006225586,
      "learning_rate": 0.00014373073204588556,
      "loss": 24.811,
      "step": 220
    },
    {
      "epoch": 0.4339622641509434,
      "grad_norm": 25.86770248413086,
      "learning_rate": 0.00013888241754733208,
      "loss": 22.9303,
      "step": 230
    },
    {
      "epoch": 0.4528301886792453,
      "grad_norm": 83.9566650390625,
      "learning_rate": 0.00013392388661180303,
      "loss": 14.6497,
      "step": 240
    },
    {
      "epoch": 0.4716981132075472,
      "grad_norm": 46.80604934692383,
      "learning_rate": 0.0001288691947339621,
      "loss": 3.5489,
      "step": 250
    },
    {
      "epoch": 0.4716981132075472,
      "eval_loss": 13.115553855895996,
      "eval_runtime": 41.4443,
      "eval_samples_per_second": 21.547,
      "eval_steps_per_second": 5.405,
      "step": 250
    },
    {
      "epoch": 0.49056603773584906,
      "grad_norm": 60.517303466796875,
      "learning_rate": 0.0001237326699871115,
      "loss": 52.7818,
      "step": 260
    },
    {
      "epoch": 0.5094339622641509,
      "grad_norm": 88.43193817138672,
      "learning_rate": 0.00011852887240871145,
      "loss": 28.1595,
      "step": 270
    },
    {
      "epoch": 0.5283018867924528,
      "grad_norm": 39.37873458862305,
      "learning_rate": 0.00011327255272837221,
      "loss": 23.8529,
      "step": 280
    },
    {
      "epoch": 0.5471698113207547,
      "grad_norm": 118.77758026123047,
      "learning_rate": 0.00010797861055530831,
      "loss": 14.4378,
      "step": 290
    },
    {
      "epoch": 0.5660377358490566,
      "grad_norm": 136.2257537841797,
      "learning_rate": 0.00010266205214377748,
      "loss": 4.6485,
      "step": 300
    },
    {
      "epoch": 0.5660377358490566,
      "eval_loss": 15.816683769226074,
      "eval_runtime": 41.4418,
      "eval_samples_per_second": 21.548,
      "eval_steps_per_second": 5.405,
      "step": 300
    },
    {
      "epoch": 0.5849056603773585,
      "grad_norm": 54.89567947387695,
      "learning_rate": 9.733794785622253e-05,
      "loss": 53.7256,
      "step": 310
    },
    {
      "epoch": 0.6037735849056604,
      "grad_norm": 32.46332931518555,
      "learning_rate": 9.202138944469168e-05,
      "loss": 24.7777,
      "step": 320
    },
    {
      "epoch": 0.6226415094339622,
      "grad_norm": 23.78044319152832,
      "learning_rate": 8.672744727162781e-05,
      "loss": 23.3428,
      "step": 330
    },
    {
      "epoch": 0.6415094339622641,
      "grad_norm": 223.9010467529297,
      "learning_rate": 8.147112759128859e-05,
      "loss": 17.2469,
      "step": 340
    },
    {
      "epoch": 0.660377358490566,
      "grad_norm": 55.03976821899414,
      "learning_rate": 7.626733001288851e-05,
      "loss": 1.8853,
      "step": 350
    },
    {
      "epoch": 0.660377358490566,
      "eval_loss": 12.180185317993164,
      "eval_runtime": 41.5042,
      "eval_samples_per_second": 21.516,
      "eval_steps_per_second": 5.397,
      "step": 350
    },
    {
      "epoch": 0.6792452830188679,
      "grad_norm": 707.2769775390625,
      "learning_rate": 7.113080526603792e-05,
      "loss": 68.5596,
      "step": 360
    },
    {
      "epoch": 0.6981132075471698,
      "grad_norm": 32.202911376953125,
      "learning_rate": 6.607611338819697e-05,
      "loss": 27.5274,
      "step": 370
    },
    {
      "epoch": 0.7169811320754716,
      "grad_norm": 32.115299224853516,
      "learning_rate": 6.111758245266794e-05,
      "loss": 22.6553,
      "step": 380
    },
    {
      "epoch": 0.7358490566037735,
      "grad_norm": 260.97906494140625,
      "learning_rate": 5.626926795411447e-05,
      "loss": 17.7957,
      "step": 390
    },
    {
      "epoch": 0.7547169811320755,
      "grad_norm": 19.01742935180664,
      "learning_rate": 5.1544912966734994e-05,
      "loss": 1.821,
      "step": 400
    },
    {
      "epoch": 0.7547169811320755,
      "eval_loss": 10.776637077331543,
      "eval_runtime": 41.3976,
      "eval_samples_per_second": 21.571,
      "eval_steps_per_second": 5.411,
      "step": 400
    },
    {
      "epoch": 0.7735849056603774,
      "grad_norm": 814.9197998046875,
      "learning_rate": 4.695790918802576e-05,
      "loss": 66.7377,
      "step": 410
    },
    {
      "epoch": 0.7924528301886793,
      "grad_norm": 30.05072784423828,
      "learning_rate": 4.252125897855932e-05,
      "loss": 30.2499,
      "step": 420
    },
    {
      "epoch": 0.8113207547169812,
      "grad_norm": 24.943675994873047,
      "learning_rate": 3.824753850538082e-05,
      "loss": 23.6266,
      "step": 430
    },
    {
      "epoch": 0.8301886792452831,
      "grad_norm": 178.87713623046875,
      "learning_rate": 3.414886209349615e-05,
      "loss": 11.4625,
      "step": 440
    },
    {
      "epoch": 0.8490566037735849,
      "grad_norm": 0.000857223873026669,
      "learning_rate": 3.0236847886501542e-05,
      "loss": 1.0218,
      "step": 450
    },
    {
      "epoch": 0.8490566037735849,
      "eval_loss": 20.48834991455078,
      "eval_runtime": 41.5021,
      "eval_samples_per_second": 21.517,
      "eval_steps_per_second": 5.397,
      "step": 450
    },
    {
      "epoch": 0.8679245283018868,
      "grad_norm": 695.1412353515625,
      "learning_rate": 2.6522584913693294e-05,
      "loss": 73.7925,
      "step": 460
    },
    {
      "epoch": 0.8867924528301887,
      "grad_norm": 118.63365936279297,
      "learning_rate": 2.301660165700936e-05,
      "loss": 34.6368,
      "step": 470
    },
    {
      "epoch": 0.9056603773584906,
      "grad_norm": 50.097171783447266,
      "learning_rate": 1.9728836206903656e-05,
      "loss": 23.91,
      "step": 480
    },
    {
      "epoch": 0.9245283018867925,
      "grad_norm": 127.65890502929688,
      "learning_rate": 1.6668608091748495e-05,
      "loss": 9.4513,
      "step": 490
    },
    {
      "epoch": 0.9433962264150944,
      "grad_norm": 3.7929797172546387,
      "learning_rate": 1.3844591860619383e-05,
      "loss": 1.6077,
      "step": 500
    },
    {
      "epoch": 0.9433962264150944,
      "eval_loss": 4.622971534729004,
      "eval_runtime": 41.3713,
      "eval_samples_per_second": 21.585,
      "eval_steps_per_second": 5.414,
      "step": 500
    },
    {
      "epoch": 0.9622641509433962,
      "grad_norm": 320.5762634277344,
      "learning_rate": 1.1264792494342857e-05,
      "loss": 31.4437,
      "step": 510
    },
    {
      "epoch": 0.9811320754716981,
      "grad_norm": 46.00068664550781,
      "learning_rate": 8.936522714508678e-06,
      "loss": 23.0031,
      "step": 520
    },
    {
      "epoch": 1.0,
      "grad_norm": 4.2149858474731445,
      "learning_rate": 6.866382254766157e-06,
      "loss": 0.5552,
      "step": 530
    },
    {
      "epoch": 1.0188679245283019,
      "grad_norm": 88.85747528076172,
      "learning_rate": 5.060239153161872e-06,
      "loss": 27.1639,
      "step": 540
    },
    {
      "epoch": 1.0377358490566038,
      "grad_norm": 45.806617736816406,
      "learning_rate": 3.5232131185484076e-06,
      "loss": 24.8611,
      "step": 550
    },
    {
      "epoch": 1.0377358490566038,
      "eval_loss": 3.9979488849639893,
      "eval_runtime": 41.4471,
      "eval_samples_per_second": 21.546,
      "eval_steps_per_second": 5.404,
      "step": 550
    },
    {
      "epoch": 1.0566037735849056,
      "grad_norm": 22.6519832611084,
      "learning_rate": 2.259661018213333e-06,
      "loss": 22.9177,
      "step": 560
    },
    {
      "epoch": 1.0754716981132075,
      "grad_norm": 48.2337760925293,
      "learning_rate": 1.2731645278655445e-06,
      "loss": 3.576,
      "step": 570
    },
    {
      "epoch": 1.0943396226415094,
      "grad_norm": 13.664042472839355,
      "learning_rate": 5.665199789862907e-07,
      "loss": 0.382,
      "step": 580
    },
    {
      "epoch": 1.1132075471698113,
      "grad_norm": 96.89643096923828,
      "learning_rate": 1.4173043232380557e-07,
      "loss": 25.7203,
      "step": 590
    },
    {
      "epoch": 1.1320754716981132,
      "grad_norm": 19.166614532470703,
      "learning_rate": 0.0,
      "loss": 24.3324,
      "step": 600
    },
    {
      "epoch": 1.1320754716981132,
      "eval_loss": 3.989581823348999,
      "eval_runtime": 41.5204,
      "eval_samples_per_second": 21.507,
      "eval_steps_per_second": 5.395,
      "step": 600
    }
  ],
  "logging_steps": 10,
  "max_steps": 600,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 150,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": 4.6255532515157606e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}