{
  "best_metric": 1.1598098278045654,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.006944565009809198,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.944565009809199e-05,
      "grad_norm": 57.99919509887695,
      "learning_rate": 1.6666666666666668e-07,
      "loss": 8.4917,
      "step": 1
    },
    {
      "epoch": 6.944565009809199e-05,
      "eval_loss": 2.3346364498138428,
      "eval_runtime": 2224.619,
      "eval_samples_per_second": 10.902,
      "eval_steps_per_second": 1.363,
      "step": 1
    },
    {
      "epoch": 0.00013889130019618397,
      "grad_norm": 58.820064544677734,
      "learning_rate": 3.3333333333333335e-07,
      "loss": 7.5263,
      "step": 2
    },
    {
      "epoch": 0.00020833695029427593,
      "grad_norm": 56.04924774169922,
      "learning_rate": 5.000000000000001e-07,
      "loss": 6.9585,
      "step": 3
    },
    {
      "epoch": 0.00027778260039236795,
      "grad_norm": 64.87261199951172,
      "learning_rate": 6.666666666666667e-07,
      "loss": 8.2777,
      "step": 4
    },
    {
      "epoch": 0.0003472282504904599,
      "grad_norm": 55.593360900878906,
      "learning_rate": 8.333333333333333e-07,
      "loss": 8.0919,
      "step": 5
    },
    {
      "epoch": 0.00041667390058855187,
      "grad_norm": 68.94898986816406,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 7.7907,
      "step": 6
    },
    {
      "epoch": 0.0004861195506866439,
      "grad_norm": 62.95187759399414,
      "learning_rate": 1.1666666666666668e-06,
      "loss": 8.0723,
      "step": 7
    },
    {
      "epoch": 0.0005555652007847359,
      "grad_norm": 68.86846923828125,
      "learning_rate": 1.3333333333333334e-06,
      "loss": 9.0299,
      "step": 8
    },
    {
      "epoch": 0.0006250108508828278,
      "grad_norm": 54.460689544677734,
      "learning_rate": 1.5e-06,
      "loss": 7.4533,
      "step": 9
    },
    {
      "epoch": 0.0006944565009809198,
      "grad_norm": 64.97429656982422,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 7.9471,
      "step": 10
    },
    {
      "epoch": 0.0007639021510790118,
      "grad_norm": 62.297733306884766,
      "learning_rate": 1.8333333333333333e-06,
      "loss": 9.2093,
      "step": 11
    },
    {
      "epoch": 0.0008333478011771037,
      "grad_norm": 66.09642791748047,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 8.3644,
      "step": 12
    },
    {
      "epoch": 0.0009027934512751957,
      "grad_norm": 68.8487548828125,
      "learning_rate": 2.166666666666667e-06,
      "loss": 7.6406,
      "step": 13
    },
    {
      "epoch": 0.0009722391013732878,
      "grad_norm": 54.236751556396484,
      "learning_rate": 2.3333333333333336e-06,
      "loss": 7.5545,
      "step": 14
    },
    {
      "epoch": 0.0010416847514713797,
      "grad_norm": 51.343406677246094,
      "learning_rate": 2.5e-06,
      "loss": 7.49,
      "step": 15
    },
    {
      "epoch": 0.0011111304015694718,
      "grad_norm": 52.90509033203125,
      "learning_rate": 2.666666666666667e-06,
      "loss": 7.4607,
      "step": 16
    },
    {
      "epoch": 0.0011805760516675637,
      "grad_norm": 49.121551513671875,
      "learning_rate": 2.8333333333333335e-06,
      "loss": 7.2417,
      "step": 17
    },
    {
      "epoch": 0.0012500217017656556,
      "grad_norm": 45.887962341308594,
      "learning_rate": 3e-06,
      "loss": 6.7642,
      "step": 18
    },
    {
      "epoch": 0.0013194673518637477,
      "grad_norm": 43.50490951538086,
      "learning_rate": 3.1666666666666667e-06,
      "loss": 6.9811,
      "step": 19
    },
    {
      "epoch": 0.0013889130019618396,
      "grad_norm": 45.96742248535156,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 7.1328,
      "step": 20
    },
    {
      "epoch": 0.0014583586520599315,
      "grad_norm": 44.12058639526367,
      "learning_rate": 3.5e-06,
      "loss": 7.4511,
      "step": 21
    },
    {
      "epoch": 0.0015278043021580237,
      "grad_norm": 54.125911712646484,
      "learning_rate": 3.6666666666666666e-06,
      "loss": 6.666,
      "step": 22
    },
    {
      "epoch": 0.0015972499522561156,
      "grad_norm": 52.1979866027832,
      "learning_rate": 3.833333333333334e-06,
      "loss": 5.9474,
      "step": 23
    },
    {
      "epoch": 0.0016666956023542075,
      "grad_norm": 54.66168975830078,
      "learning_rate": 4.000000000000001e-06,
      "loss": 5.7697,
      "step": 24
    },
    {
      "epoch": 0.0017361412524522996,
      "grad_norm": 38.93903350830078,
      "learning_rate": 4.166666666666667e-06,
      "loss": 5.6342,
      "step": 25
    },
    {
      "epoch": 0.0018055869025503915,
      "grad_norm": 31.204254150390625,
      "learning_rate": 4.333333333333334e-06,
      "loss": 6.4815,
      "step": 26
    },
    {
      "epoch": 0.0018750325526484834,
      "grad_norm": 32.05744171142578,
      "learning_rate": 4.5e-06,
      "loss": 5.417,
      "step": 27
    },
    {
      "epoch": 0.0019444782027465755,
      "grad_norm": 35.15018081665039,
      "learning_rate": 4.666666666666667e-06,
      "loss": 5.0666,
      "step": 28
    },
    {
      "epoch": 0.0020139238528446676,
      "grad_norm": 31.198720932006836,
      "learning_rate": 4.833333333333333e-06,
      "loss": 5.6771,
      "step": 29
    },
    {
      "epoch": 0.0020833695029427593,
      "grad_norm": 26.646947860717773,
      "learning_rate": 5e-06,
      "loss": 4.6598,
      "step": 30
    },
    {
      "epoch": 0.0021528151530408515,
      "grad_norm": 24.5843448638916,
      "learning_rate": 4.997482666353287e-06,
      "loss": 5.5282,
      "step": 31
    },
    {
      "epoch": 0.0022222608031389436,
      "grad_norm": 35.84235763549805,
      "learning_rate": 4.989935734988098e-06,
      "loss": 5.7435,
      "step": 32
    },
    {
      "epoch": 0.0022917064532370353,
      "grad_norm": 28.750774383544922,
      "learning_rate": 4.977374404419838e-06,
      "loss": 5.621,
      "step": 33
    },
    {
      "epoch": 0.0023611521033351274,
      "grad_norm": 35.598567962646484,
      "learning_rate": 4.959823971496575e-06,
      "loss": 5.1858,
      "step": 34
    },
    {
      "epoch": 0.0024305977534332195,
      "grad_norm": 24.765888214111328,
      "learning_rate": 4.937319780454559e-06,
      "loss": 5.6566,
      "step": 35
    },
    {
      "epoch": 0.002500043403531311,
      "grad_norm": 23.42424964904785,
      "learning_rate": 4.909907151739634e-06,
      "loss": 4.8593,
      "step": 36
    },
    {
      "epoch": 0.0025694890536294033,
      "grad_norm": 25.198575973510742,
      "learning_rate": 4.8776412907378845e-06,
      "loss": 5.0189,
      "step": 37
    },
    {
      "epoch": 0.0026389347037274954,
      "grad_norm": 31.468351364135742,
      "learning_rate": 4.8405871765993435e-06,
      "loss": 5.8011,
      "step": 38
    },
    {
      "epoch": 0.002708380353825587,
      "grad_norm": 36.017425537109375,
      "learning_rate": 4.7988194313786275e-06,
      "loss": 5.739,
      "step": 39
    },
    {
      "epoch": 0.0027778260039236793,
      "grad_norm": 24.822233200073242,
      "learning_rate": 4.752422169756048e-06,
      "loss": 5.3789,
      "step": 40
    },
    {
      "epoch": 0.0028472716540217714,
      "grad_norm": 23.735197067260742,
      "learning_rate": 4.701488829641845e-06,
      "loss": 5.1168,
      "step": 41
    },
    {
      "epoch": 0.002916717304119863,
      "grad_norm": 31.22846221923828,
      "learning_rate": 4.646121984004666e-06,
      "loss": 5.9325,
      "step": 42
    },
    {
      "epoch": 0.002986162954217955,
      "grad_norm": 23.26053810119629,
      "learning_rate": 4.586433134303257e-06,
      "loss": 4.8404,
      "step": 43
    },
    {
      "epoch": 0.0030556086043160473,
      "grad_norm": 30.344331741333008,
      "learning_rate": 4.522542485937369e-06,
      "loss": 5.4497,
      "step": 44
    },
    {
      "epoch": 0.003125054254414139,
      "grad_norm": 26.371152877807617,
      "learning_rate": 4.454578706170075e-06,
      "loss": 4.7377,
      "step": 45
    },
    {
      "epoch": 0.003194499904512231,
      "grad_norm": 29.86260414123535,
      "learning_rate": 4.382678665009028e-06,
      "loss": 5.9814,
      "step": 46
    },
    {
      "epoch": 0.0032639455546103232,
      "grad_norm": 30.244312286376953,
      "learning_rate": 4.3069871595684795e-06,
      "loss": 5.2366,
      "step": 47
    },
    {
      "epoch": 0.003333391204708415,
      "grad_norm": 24.537878036499023,
      "learning_rate": 4.227656622467162e-06,
      "loss": 5.1262,
      "step": 48
    },
    {
      "epoch": 0.003402836854806507,
      "grad_norm": 35.21415710449219,
      "learning_rate": 4.144846814849282e-06,
      "loss": 5.9274,
      "step": 49
    },
    {
      "epoch": 0.003472282504904599,
      "grad_norm": 38.00114059448242,
      "learning_rate": 4.058724504646834e-06,
      "loss": 6.1489,
      "step": 50
    },
    {
      "epoch": 0.003472282504904599,
      "eval_loss": 1.2252222299575806,
      "eval_runtime": 2231.1566,
      "eval_samples_per_second": 10.87,
      "eval_steps_per_second": 1.359,
      "step": 50
    },
    {
      "epoch": 0.003541728155002691,
      "grad_norm": 26.02019691467285,
      "learning_rate": 3.969463130731183e-06,
      "loss": 4.9606,
      "step": 51
    },
    {
      "epoch": 0.003611173805100783,
      "grad_norm": 27.602750778198242,
      "learning_rate": 3.8772424536302565e-06,
      "loss": 5.0621,
      "step": 52
    },
    {
      "epoch": 0.003680619455198875,
      "grad_norm": 23.657602310180664,
      "learning_rate": 3.782248193514766e-06,
      "loss": 4.5891,
      "step": 53
    },
    {
      "epoch": 0.003750065105296967,
      "grad_norm": 24.33047103881836,
      "learning_rate": 3.684671656182497e-06,
      "loss": 5.011,
      "step": 54
    },
    {
      "epoch": 0.003819510755395059,
      "grad_norm": 20.79547119140625,
      "learning_rate": 3.5847093477938955e-06,
      "loss": 4.2932,
      "step": 55
    },
    {
      "epoch": 0.003888956405493151,
      "grad_norm": 21.947898864746094,
      "learning_rate": 3.4825625791348093e-06,
      "loss": 4.9364,
      "step": 56
    },
    {
      "epoch": 0.003958402055591243,
      "grad_norm": 24.627059936523438,
      "learning_rate": 3.3784370602033572e-06,
      "loss": 4.489,
      "step": 57
    },
    {
      "epoch": 0.004027847705689335,
      "grad_norm": 17.064987182617188,
      "learning_rate": 3.272542485937369e-06,
      "loss": 4.566,
      "step": 58
    },
    {
      "epoch": 0.0040972933557874265,
      "grad_norm": 21.63456153869629,
      "learning_rate": 3.165092113916688e-06,
      "loss": 4.414,
      "step": 59
    },
    {
      "epoch": 0.004166739005885519,
      "grad_norm": 20.844581604003906,
      "learning_rate": 3.056302334890786e-06,
      "loss": 5.1632,
      "step": 60
    },
    {
      "epoch": 0.004236184655983611,
      "grad_norm": 20.495439529418945,
      "learning_rate": 2.946392236996592e-06,
      "loss": 3.9125,
      "step": 61
    },
    {
      "epoch": 0.004305630306081703,
      "grad_norm": 18.964275360107422,
      "learning_rate": 2.835583164544139e-06,
      "loss": 3.8756,
      "step": 62
    },
    {
      "epoch": 0.004375075956179795,
      "grad_norm": 20.54064178466797,
      "learning_rate": 2.724098272258584e-06,
      "loss": 4.4273,
      "step": 63
    },
    {
      "epoch": 0.004444521606277887,
      "grad_norm": 19.636096954345703,
      "learning_rate": 2.6121620758762877e-06,
      "loss": 5.1823,
      "step": 64
    },
    {
      "epoch": 0.004513967256375978,
      "grad_norm": 18.76691246032715,
      "learning_rate": 2.5e-06,
      "loss": 4.5282,
      "step": 65
    },
    {
      "epoch": 0.0045834129064740705,
      "grad_norm": 21.243412017822266,
      "learning_rate": 2.3878379241237136e-06,
      "loss": 4.6716,
      "step": 66
    },
    {
      "epoch": 0.004652858556572163,
      "grad_norm": 19.991161346435547,
      "learning_rate": 2.2759017277414165e-06,
      "loss": 4.9848,
      "step": 67
    },
    {
      "epoch": 0.004722304206670255,
      "grad_norm": 20.23773193359375,
      "learning_rate": 2.1644168354558623e-06,
      "loss": 4.9668,
      "step": 68
    },
    {
      "epoch": 0.004791749856768347,
      "grad_norm": 19.373884201049805,
      "learning_rate": 2.053607763003409e-06,
      "loss": 4.8817,
      "step": 69
    },
    {
      "epoch": 0.004861195506866439,
      "grad_norm": 22.937284469604492,
      "learning_rate": 1.9436976651092143e-06,
      "loss": 4.8936,
      "step": 70
    },
    {
      "epoch": 0.00493064115696453,
      "grad_norm": 21.041000366210938,
      "learning_rate": 1.8349078860833125e-06,
      "loss": 4.7213,
      "step": 71
    },
    {
      "epoch": 0.005000086807062622,
      "grad_norm": 19.949390411376953,
      "learning_rate": 1.7274575140626318e-06,
      "loss": 5.0686,
      "step": 72
    },
    {
      "epoch": 0.0050695324571607145,
      "grad_norm": 19.30895233154297,
      "learning_rate": 1.6215629397966432e-06,
      "loss": 4.4509,
      "step": 73
    },
    {
      "epoch": 0.005138978107258807,
      "grad_norm": 21.176286697387695,
      "learning_rate": 1.5174374208651913e-06,
      "loss": 4.4727,
      "step": 74
    },
    {
      "epoch": 0.005208423757356899,
      "grad_norm": 20.409286499023438,
      "learning_rate": 1.415290652206105e-06,
      "loss": 4.7167,
      "step": 75
    },
    {
      "epoch": 0.005277869407454991,
      "grad_norm": 22.04141616821289,
      "learning_rate": 1.3153283438175036e-06,
      "loss": 5.1919,
      "step": 76
    },
    {
      "epoch": 0.005347315057553082,
      "grad_norm": 19.59886360168457,
      "learning_rate": 1.217751806485235e-06,
      "loss": 4.925,
      "step": 77
    },
    {
      "epoch": 0.005416760707651174,
      "grad_norm": 21.676176071166992,
      "learning_rate": 1.122757546369744e-06,
      "loss": 5.0204,
      "step": 78
    },
    {
      "epoch": 0.005486206357749266,
      "grad_norm": 23.305850982666016,
      "learning_rate": 1.0305368692688175e-06,
      "loss": 4.2981,
      "step": 79
    },
    {
      "epoch": 0.0055556520078473585,
      "grad_norm": 19.65032958984375,
      "learning_rate": 9.412754953531664e-07,
      "loss": 3.8816,
      "step": 80
    },
    {
      "epoch": 0.005625097657945451,
      "grad_norm": 22.556602478027344,
      "learning_rate": 8.551531851507186e-07,
      "loss": 4.8851,
      "step": 81
    },
    {
      "epoch": 0.005694543308043543,
      "grad_norm": 20.84819221496582,
      "learning_rate": 7.723433775328385e-07,
      "loss": 4.7379,
      "step": 82
    },
    {
      "epoch": 0.005763988958141634,
      "grad_norm": 22.757490158081055,
      "learning_rate": 6.930128404315214e-07,
      "loss": 4.4146,
      "step": 83
    },
    {
      "epoch": 0.005833434608239726,
      "grad_norm": 23.608304977416992,
      "learning_rate": 6.17321334990973e-07,
      "loss": 4.6309,
      "step": 84
    },
    {
      "epoch": 0.005902880258337818,
      "grad_norm": 23.365802764892578,
      "learning_rate": 5.454212938299256e-07,
      "loss": 5.3139,
      "step": 85
    },
    {
      "epoch": 0.00597232590843591,
      "grad_norm": 21.471818923950195,
      "learning_rate": 4.774575140626317e-07,
      "loss": 4.0731,
      "step": 86
    },
    {
      "epoch": 0.0060417715585340025,
      "grad_norm": 20.544567108154297,
      "learning_rate": 4.1356686569674344e-07,
      "loss": 4.5634,
      "step": 87
    },
    {
      "epoch": 0.006111217208632095,
      "grad_norm": 20.132556915283203,
      "learning_rate": 3.538780159953348e-07,
      "loss": 4.7335,
      "step": 88
    },
    {
      "epoch": 0.006180662858730186,
      "grad_norm": 24.553869247436523,
      "learning_rate": 2.98511170358155e-07,
      "loss": 4.3985,
      "step": 89
    },
    {
      "epoch": 0.006250108508828278,
      "grad_norm": 23.55926513671875,
      "learning_rate": 2.4757783024395244e-07,
      "loss": 4.853,
      "step": 90
    },
    {
      "epoch": 0.00631955415892637,
      "grad_norm": 22.498533248901367,
      "learning_rate": 2.0118056862137358e-07,
      "loss": 5.0627,
      "step": 91
    },
    {
      "epoch": 0.006388999809024462,
      "grad_norm": 23.05436134338379,
      "learning_rate": 1.59412823400657e-07,
      "loss": 4.4592,
      "step": 92
    },
    {
      "epoch": 0.006458445459122554,
      "grad_norm": 22.92341423034668,
      "learning_rate": 1.223587092621162e-07,
      "loss": 5.0885,
      "step": 93
    },
    {
      "epoch": 0.0065278911092206465,
      "grad_norm": 21.84902000427246,
      "learning_rate": 9.00928482603669e-08,
      "loss": 4.746,
      "step": 94
    },
    {
      "epoch": 0.006597336759318738,
      "grad_norm": 27.136032104492188,
      "learning_rate": 6.268021954544095e-08,
      "loss": 5.4861,
      "step": 95
    },
    {
      "epoch": 0.00666678240941683,
      "grad_norm": 22.971391677856445,
      "learning_rate": 4.017602850342584e-08,
      "loss": 4.7522,
      "step": 96
    },
    {
      "epoch": 0.006736228059514922,
      "grad_norm": 22.49424171447754,
      "learning_rate": 2.262559558016325e-08,
      "loss": 4.975,
      "step": 97
    },
    {
      "epoch": 0.006805673709613014,
      "grad_norm": 29.4676513671875,
      "learning_rate": 1.006426501190233e-08,
      "loss": 5.651,
      "step": 98
    },
    {
      "epoch": 0.006875119359711106,
      "grad_norm": 25.18215560913086,
      "learning_rate": 2.5173336467135266e-09,
      "loss": 4.7655,
      "step": 99
    },
    {
      "epoch": 0.006944565009809198,
      "grad_norm": 39.18954086303711,
      "learning_rate": 0.0,
      "loss": 6.7356,
      "step": 100
    },
    {
      "epoch": 0.006944565009809198,
      "eval_loss": 1.1598098278045654,
      "eval_runtime": 2231.8266,
      "eval_samples_per_second": 10.866,
      "eval_steps_per_second": 1.359,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "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": 1.4381529990325862e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}