{
  "best_metric": 5.114246505399933e-06,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 1.2944983818770226,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.012944983818770227,
      "grad_norm": 1.0203962326049805,
      "learning_rate": 1e-05,
      "loss": 0.1373,
      "step": 1
    },
    {
      "epoch": 0.012944983818770227,
      "eval_loss": 0.2981894910335541,
      "eval_runtime": 9.5643,
      "eval_samples_per_second": 13.592,
      "eval_steps_per_second": 3.45,
      "step": 1
    },
    {
      "epoch": 0.025889967637540454,
      "grad_norm": 1.2321498394012451,
      "learning_rate": 2e-05,
      "loss": 0.1639,
      "step": 2
    },
    {
      "epoch": 0.038834951456310676,
      "grad_norm": 1.2425283193588257,
      "learning_rate": 3e-05,
      "loss": 0.1687,
      "step": 3
    },
    {
      "epoch": 0.05177993527508091,
      "grad_norm": 1.0462325811386108,
      "learning_rate": 4e-05,
      "loss": 0.1525,
      "step": 4
    },
    {
      "epoch": 0.06472491909385113,
      "grad_norm": 0.6241796016693115,
      "learning_rate": 5e-05,
      "loss": 0.0971,
      "step": 5
    },
    {
      "epoch": 0.07766990291262135,
      "grad_norm": 0.5437662601470947,
      "learning_rate": 6e-05,
      "loss": 0.0619,
      "step": 6
    },
    {
      "epoch": 0.09061488673139159,
      "grad_norm": 0.6059942245483398,
      "learning_rate": 7e-05,
      "loss": 0.0309,
      "step": 7
    },
    {
      "epoch": 0.10355987055016182,
      "grad_norm": 0.2637348473072052,
      "learning_rate": 8e-05,
      "loss": 0.0107,
      "step": 8
    },
    {
      "epoch": 0.11650485436893204,
      "grad_norm": 0.12676547467708588,
      "learning_rate": 9e-05,
      "loss": 0.0039,
      "step": 9
    },
    {
      "epoch": 0.12944983818770225,
      "grad_norm": 0.07366133481264114,
      "learning_rate": 0.0001,
      "loss": 0.0013,
      "step": 10
    },
    {
      "epoch": 0.1423948220064725,
      "grad_norm": 0.06091802567243576,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.0008,
      "step": 11
    },
    {
      "epoch": 0.1553398058252427,
      "grad_norm": 0.09185962378978729,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.0005,
      "step": 12
    },
    {
      "epoch": 0.16828478964401294,
      "grad_norm": 0.007255407050251961,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.0001,
      "step": 13
    },
    {
      "epoch": 0.18122977346278318,
      "grad_norm": 0.19597330689430237,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.0009,
      "step": 14
    },
    {
      "epoch": 0.1941747572815534,
      "grad_norm": 0.002528818789869547,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.20711974110032363,
      "grad_norm": 0.0019764695316553116,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.22006472491909385,
      "grad_norm": 0.004141903482377529,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.0001,
      "step": 17
    },
    {
      "epoch": 0.23300970873786409,
      "grad_norm": 0.24057364463806152,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.0001,
      "step": 18
    },
    {
      "epoch": 0.2459546925566343,
      "grad_norm": 0.007576645351946354,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.0001,
      "step": 19
    },
    {
      "epoch": 0.2588996763754045,
      "grad_norm": 0.11651884764432907,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.0008,
      "step": 20
    },
    {
      "epoch": 0.27184466019417475,
      "grad_norm": 0.05754302814602852,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.0003,
      "step": 21
    },
    {
      "epoch": 0.284789644012945,
      "grad_norm": 0.05541009455919266,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.0002,
      "step": 22
    },
    {
      "epoch": 0.2977346278317152,
      "grad_norm": 0.002488422906026244,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.3106796116504854,
      "grad_norm": 0.0021644814405590296,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.32362459546925565,
      "grad_norm": 0.003139674663543701,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.3365695792880259,
      "grad_norm": 0.0062321946024894714,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.34951456310679613,
      "grad_norm": 0.0015530330128967762,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.36245954692556637,
      "grad_norm": 0.0009751790203154087,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.37540453074433655,
      "grad_norm": 0.0011889493325725198,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.3883495145631068,
      "grad_norm": 0.0020521723199635744,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.40129449838187703,
      "grad_norm": 0.001421238761395216,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.41423948220064727,
      "grad_norm": 0.0026180348359048367,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.42718446601941745,
      "grad_norm": 0.001268848660402,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.4401294498381877,
      "grad_norm": 0.0014048975426703691,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.45307443365695793,
      "grad_norm": 0.0029678246937692165,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.46601941747572817,
      "grad_norm": 0.0025685736909508705,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.47896440129449835,
      "grad_norm": 0.003125803079456091,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.4919093851132686,
      "grad_norm": 0.007677475456148386,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.5048543689320388,
      "grad_norm": 0.0005735827726311982,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.517799352750809,
      "grad_norm": 0.01382033433765173,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.5307443365695793,
      "grad_norm": 0.00015104783233255148,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.5436893203883495,
      "grad_norm": 0.0015415921807289124,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.5566343042071198,
      "grad_norm": 0.0002161674783565104,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.56957928802589,
      "grad_norm": 0.00024602553457953036,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.5825242718446602,
      "grad_norm": 0.0005134981474839151,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.5954692556634305,
      "grad_norm": 0.00012119917664676905,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.6084142394822006,
      "grad_norm": 0.00011360419739503413,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.6213592233009708,
      "grad_norm": 0.0001089339202735573,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.6343042071197411,
      "grad_norm": 0.00019188143778592348,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.6472491909385113,
      "grad_norm": 0.0002130446519004181,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.6472491909385113,
      "eval_loss": 5.114246505399933e-06,
      "eval_runtime": 9.8014,
      "eval_samples_per_second": 13.263,
      "eval_steps_per_second": 3.367,
      "step": 50
    },
    {
      "epoch": 0.6601941747572816,
      "grad_norm": 0.0008072551572695374,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.0,
      "step": 51
    },
    {
      "epoch": 0.6731391585760518,
      "grad_norm": 0.0003115938452538103,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.0,
      "step": 52
    },
    {
      "epoch": 0.686084142394822,
      "grad_norm": 0.0003803007130045444,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.0,
      "step": 53
    },
    {
      "epoch": 0.6990291262135923,
      "grad_norm": 0.001679311622865498,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.0,
      "step": 54
    },
    {
      "epoch": 0.7119741100323624,
      "grad_norm": 0.0014463587431237102,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.0,
      "step": 55
    },
    {
      "epoch": 0.7249190938511327,
      "grad_norm": 0.00020687367941718549,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.0,
      "step": 56
    },
    {
      "epoch": 0.7378640776699029,
      "grad_norm": 0.00012489533401094377,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.0,
      "step": 57
    },
    {
      "epoch": 0.7508090614886731,
      "grad_norm": 0.0011946961749345064,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.0,
      "step": 58
    },
    {
      "epoch": 0.7637540453074434,
      "grad_norm": 0.0034886086359620094,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.0,
      "step": 59
    },
    {
      "epoch": 0.7766990291262136,
      "grad_norm": 0.019774286076426506,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.7896440129449838,
      "grad_norm": 0.00012018957932014018,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.0,
      "step": 61
    },
    {
      "epoch": 0.8025889967637541,
      "grad_norm": 0.0008413722389377654,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.0,
      "step": 62
    },
    {
      "epoch": 0.8155339805825242,
      "grad_norm": 7.062353688525036e-05,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.0,
      "step": 63
    },
    {
      "epoch": 0.8284789644012945,
      "grad_norm": 0.0010793240508064628,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.0,
      "step": 64
    },
    {
      "epoch": 0.8414239482200647,
      "grad_norm": 0.00023476831847801805,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.0,
      "step": 65
    },
    {
      "epoch": 0.8543689320388349,
      "grad_norm": 0.00031458126613870263,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.0,
      "step": 66
    },
    {
      "epoch": 0.8673139158576052,
      "grad_norm": 0.0001667094766162336,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0,
      "step": 67
    },
    {
      "epoch": 0.8802588996763754,
      "grad_norm": 0.00017667474457994103,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.0,
      "step": 68
    },
    {
      "epoch": 0.8932038834951457,
      "grad_norm": 0.0005229483940638602,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.0,
      "step": 69
    },
    {
      "epoch": 0.9061488673139159,
      "grad_norm": 0.00027375674108043313,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.0,
      "step": 70
    },
    {
      "epoch": 0.919093851132686,
      "grad_norm": 0.00028505577938631177,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.0,
      "step": 71
    },
    {
      "epoch": 0.9320388349514563,
      "grad_norm": 0.002035663463175297,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.0,
      "step": 72
    },
    {
      "epoch": 0.9449838187702265,
      "grad_norm": 0.0007079575443640351,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.0,
      "step": 73
    },
    {
      "epoch": 0.9579288025889967,
      "grad_norm": 0.0003011709777638316,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.0,
      "step": 74
    },
    {
      "epoch": 0.970873786407767,
      "grad_norm": 0.0004272864025551826,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.0,
      "step": 75
    },
    {
      "epoch": 0.9838187702265372,
      "grad_norm": 0.0001912742154672742,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.0,
      "step": 76
    },
    {
      "epoch": 0.9967637540453075,
      "grad_norm": 0.0001855505834100768,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.0,
      "step": 77
    },
    {
      "epoch": 1.0097087378640777,
      "grad_norm": 0.000368554494343698,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.0,
      "step": 78
    },
    {
      "epoch": 1.022653721682848,
      "grad_norm": 0.0005397357745096087,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.0,
      "step": 79
    },
    {
      "epoch": 1.035598705501618,
      "grad_norm": 9.197810140904039e-05,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 1.0485436893203883,
      "grad_norm": 0.0047591556794941425,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.0,
      "step": 81
    },
    {
      "epoch": 1.0614886731391586,
      "grad_norm": 9.622135985409841e-05,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.0,
      "step": 82
    },
    {
      "epoch": 1.074433656957929,
      "grad_norm": 0.0002235884458059445,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.0,
      "step": 83
    },
    {
      "epoch": 1.087378640776699,
      "grad_norm": 6.833249790361151e-05,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.0,
      "step": 84
    },
    {
      "epoch": 1.1003236245954693,
      "grad_norm": 0.0005551163922064006,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.0,
      "step": 85
    },
    {
      "epoch": 1.1132686084142396,
      "grad_norm": 0.00010846730583580211,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0,
      "step": 86
    },
    {
      "epoch": 1.1262135922330097,
      "grad_norm": 5.773642988060601e-05,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.0,
      "step": 87
    },
    {
      "epoch": 1.13915857605178,
      "grad_norm": 0.00016505061648786068,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.0,
      "step": 88
    },
    {
      "epoch": 1.1521035598705502,
      "grad_norm": 0.008876933716237545,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.0,
      "step": 89
    },
    {
      "epoch": 1.1650485436893203,
      "grad_norm": 0.16270585358142853,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.0007,
      "step": 90
    },
    {
      "epoch": 1.1779935275080906,
      "grad_norm": 0.00022468912356998771,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.0,
      "step": 91
    },
    {
      "epoch": 1.190938511326861,
      "grad_norm": 9.756765211932361e-05,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.0,
      "step": 92
    },
    {
      "epoch": 1.203883495145631,
      "grad_norm": 0.00018813037604559213,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.0,
      "step": 93
    },
    {
      "epoch": 1.2168284789644013,
      "grad_norm": 0.0003693510952871293,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.0,
      "step": 94
    },
    {
      "epoch": 1.2297734627831716,
      "grad_norm": 0.0021898068953305483,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.0,
      "step": 95
    },
    {
      "epoch": 1.2427184466019416,
      "grad_norm": 0.37865975499153137,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.0006,
      "step": 96
    },
    {
      "epoch": 1.255663430420712,
      "grad_norm": 0.0014068527380004525,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.0,
      "step": 97
    },
    {
      "epoch": 1.2686084142394822,
      "grad_norm": 0.0009542718180455267,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.0,
      "step": 98
    },
    {
      "epoch": 1.2815533980582523,
      "grad_norm": 0.09191913157701492,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.0001,
      "step": 99
    },
    {
      "epoch": 1.2944983818770226,
      "grad_norm": 0.004437869414687157,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.0,
      "step": 100
    },
    {
      "epoch": 1.2944983818770226,
      "eval_loss": 7.178713531175163e-06,
      "eval_runtime": 9.7892,
      "eval_samples_per_second": 13.28,
      "eval_steps_per_second": 3.371,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.50757075775914e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}