{
  "best_metric": 1.8426469564437866,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.03374957813027337,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003374957813027337,
      "grad_norm": 0.659518837928772,
      "learning_rate": 1e-05,
      "loss": 1.7311,
      "step": 1
    },
    {
      "epoch": 0.0003374957813027337,
      "eval_loss": 2.9957451820373535,
      "eval_runtime": 115.497,
      "eval_samples_per_second": 43.205,
      "eval_steps_per_second": 10.805,
      "step": 1
    },
    {
      "epoch": 0.0006749915626054674,
      "grad_norm": 0.7038252353668213,
      "learning_rate": 2e-05,
      "loss": 1.9467,
      "step": 2
    },
    {
      "epoch": 0.0010124873439082012,
      "grad_norm": 0.7937076091766357,
      "learning_rate": 3e-05,
      "loss": 2.1449,
      "step": 3
    },
    {
      "epoch": 0.0013499831252109348,
      "grad_norm": 0.7090626955032349,
      "learning_rate": 4e-05,
      "loss": 2.052,
      "step": 4
    },
    {
      "epoch": 0.0016874789065136687,
      "grad_norm": 0.7988624572753906,
      "learning_rate": 5e-05,
      "loss": 2.3878,
      "step": 5
    },
    {
      "epoch": 0.0020249746878164025,
      "grad_norm": 0.9716485738754272,
      "learning_rate": 6e-05,
      "loss": 2.1794,
      "step": 6
    },
    {
      "epoch": 0.002362470469119136,
      "grad_norm": 0.8470109105110168,
      "learning_rate": 7e-05,
      "loss": 2.2386,
      "step": 7
    },
    {
      "epoch": 0.0026999662504218697,
      "grad_norm": 0.7678182125091553,
      "learning_rate": 8e-05,
      "loss": 2.2977,
      "step": 8
    },
    {
      "epoch": 0.0030374620317246033,
      "grad_norm": 0.7406213283538818,
      "learning_rate": 9e-05,
      "loss": 2.2716,
      "step": 9
    },
    {
      "epoch": 0.0033749578130273373,
      "grad_norm": 0.6096116304397583,
      "learning_rate": 0.0001,
      "loss": 2.4181,
      "step": 10
    },
    {
      "epoch": 0.003712453594330071,
      "grad_norm": 0.6520525217056274,
      "learning_rate": 9.999316524962345e-05,
      "loss": 2.0193,
      "step": 11
    },
    {
      "epoch": 0.004049949375632805,
      "grad_norm": 0.5647959113121033,
      "learning_rate": 9.997266286704631e-05,
      "loss": 2.1552,
      "step": 12
    },
    {
      "epoch": 0.004387445156935539,
      "grad_norm": 0.7149708271026611,
      "learning_rate": 9.993849845741524e-05,
      "loss": 2.3396,
      "step": 13
    },
    {
      "epoch": 0.004724940938238272,
      "grad_norm": 0.6472476720809937,
      "learning_rate": 9.989068136093873e-05,
      "loss": 2.1707,
      "step": 14
    },
    {
      "epoch": 0.005062436719541006,
      "grad_norm": 0.7469307780265808,
      "learning_rate": 9.98292246503335e-05,
      "loss": 2.3344,
      "step": 15
    },
    {
      "epoch": 0.005399932500843739,
      "grad_norm": 0.5477833151817322,
      "learning_rate": 9.975414512725057e-05,
      "loss": 2.1046,
      "step": 16
    },
    {
      "epoch": 0.005737428282146473,
      "grad_norm": 0.6585941314697266,
      "learning_rate": 9.966546331768191e-05,
      "loss": 2.26,
      "step": 17
    },
    {
      "epoch": 0.006074924063449207,
      "grad_norm": 0.6190670728683472,
      "learning_rate": 9.956320346634876e-05,
      "loss": 2.1344,
      "step": 18
    },
    {
      "epoch": 0.00641241984475194,
      "grad_norm": 0.5457659363746643,
      "learning_rate": 9.944739353007344e-05,
      "loss": 2.1121,
      "step": 19
    },
    {
      "epoch": 0.006749915626054675,
      "grad_norm": 0.48350393772125244,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.9028,
      "step": 20
    },
    {
      "epoch": 0.007087411407357408,
      "grad_norm": 0.6461214423179626,
      "learning_rate": 9.917525374361912e-05,
      "loss": 2.166,
      "step": 21
    },
    {
      "epoch": 0.007424907188660142,
      "grad_norm": 0.6612595319747925,
      "learning_rate": 9.901899829374047e-05,
      "loss": 2.2152,
      "step": 22
    },
    {
      "epoch": 0.0077624029699628755,
      "grad_norm": 0.5887338519096375,
      "learning_rate": 9.884934153917997e-05,
      "loss": 2.0533,
      "step": 23
    },
    {
      "epoch": 0.00809989875126561,
      "grad_norm": 0.5120691657066345,
      "learning_rate": 9.86663298624003e-05,
      "loss": 2.1555,
      "step": 24
    },
    {
      "epoch": 0.008437394532568343,
      "grad_norm": 0.5528091788291931,
      "learning_rate": 9.847001329696653e-05,
      "loss": 2.2499,
      "step": 25
    },
    {
      "epoch": 0.008774890313871077,
      "grad_norm": 0.6201184391975403,
      "learning_rate": 9.826044551386744e-05,
      "loss": 2.1444,
      "step": 26
    },
    {
      "epoch": 0.00911238609517381,
      "grad_norm": 0.6279026865959167,
      "learning_rate": 9.803768380684242e-05,
      "loss": 2.2847,
      "step": 27
    },
    {
      "epoch": 0.009449881876476544,
      "grad_norm": 0.6332525014877319,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.958,
      "step": 28
    },
    {
      "epoch": 0.009787377657779277,
      "grad_norm": 0.569353461265564,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.1134,
      "step": 29
    },
    {
      "epoch": 0.010124873439082012,
      "grad_norm": 0.5256232619285583,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.9178,
      "step": 30
    },
    {
      "epoch": 0.010462369220384746,
      "grad_norm": 0.5967089533805847,
      "learning_rate": 9.701596950580806e-05,
      "loss": 2.3453,
      "step": 31
    },
    {
      "epoch": 0.010799865001687479,
      "grad_norm": 0.6425303816795349,
      "learning_rate": 9.672822322997305e-05,
      "loss": 2.1351,
      "step": 32
    },
    {
      "epoch": 0.011137360782990213,
      "grad_norm": 0.5986398458480835,
      "learning_rate": 9.642770192448536e-05,
      "loss": 2.3019,
      "step": 33
    },
    {
      "epoch": 0.011474856564292946,
      "grad_norm": 0.5946639180183411,
      "learning_rate": 9.611448774886924e-05,
      "loss": 2.2574,
      "step": 34
    },
    {
      "epoch": 0.01181235234559568,
      "grad_norm": 0.6006338000297546,
      "learning_rate": 9.578866633275288e-05,
      "loss": 2.3178,
      "step": 35
    },
    {
      "epoch": 0.012149848126898413,
      "grad_norm": 0.5436823964118958,
      "learning_rate": 9.545032675245813e-05,
      "loss": 2.2969,
      "step": 36
    },
    {
      "epoch": 0.012487343908201148,
      "grad_norm": 0.589877724647522,
      "learning_rate": 9.509956150664796e-05,
      "loss": 2.4032,
      "step": 37
    },
    {
      "epoch": 0.01282483968950388,
      "grad_norm": 0.5993760228157043,
      "learning_rate": 9.473646649103818e-05,
      "loss": 2.3421,
      "step": 38
    },
    {
      "epoch": 0.013162335470806615,
      "grad_norm": 0.5923803448677063,
      "learning_rate": 9.43611409721806e-05,
      "loss": 2.3048,
      "step": 39
    },
    {
      "epoch": 0.01349983125210935,
      "grad_norm": 0.6783635020256042,
      "learning_rate": 9.397368756032445e-05,
      "loss": 2.3467,
      "step": 40
    },
    {
      "epoch": 0.013837327033412082,
      "grad_norm": 0.5711936354637146,
      "learning_rate": 9.357421218136386e-05,
      "loss": 2.3039,
      "step": 41
    },
    {
      "epoch": 0.014174822814714817,
      "grad_norm": 0.6027695536613464,
      "learning_rate": 9.316282404787871e-05,
      "loss": 2.2872,
      "step": 42
    },
    {
      "epoch": 0.01451231859601755,
      "grad_norm": 0.6241564750671387,
      "learning_rate": 9.273963562927695e-05,
      "loss": 2.313,
      "step": 43
    },
    {
      "epoch": 0.014849814377320284,
      "grad_norm": 0.6565014123916626,
      "learning_rate": 9.230476262104677e-05,
      "loss": 2.3402,
      "step": 44
    },
    {
      "epoch": 0.015187310158623017,
      "grad_norm": 0.6258305311203003,
      "learning_rate": 9.185832391312644e-05,
      "loss": 2.2641,
      "step": 45
    },
    {
      "epoch": 0.015524805939925751,
      "grad_norm": 0.6962496042251587,
      "learning_rate": 9.140044155740101e-05,
      "loss": 2.5017,
      "step": 46
    },
    {
      "epoch": 0.015862301721228485,
      "grad_norm": 0.643883466720581,
      "learning_rate": 9.093124073433463e-05,
      "loss": 2.4286,
      "step": 47
    },
    {
      "epoch": 0.01619979750253122,
      "grad_norm": 0.6366576552391052,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.3306,
      "step": 48
    },
    {
      "epoch": 0.01653729328383395,
      "grad_norm": 0.723232090473175,
      "learning_rate": 8.995939984474624e-05,
      "loss": 2.4223,
      "step": 49
    },
    {
      "epoch": 0.016874789065136685,
      "grad_norm": 0.8257110118865967,
      "learning_rate": 8.945702546981969e-05,
      "loss": 2.3262,
      "step": 50
    },
    {
      "epoch": 0.016874789065136685,
      "eval_loss": 1.9447404146194458,
      "eval_runtime": 114.5205,
      "eval_samples_per_second": 43.573,
      "eval_steps_per_second": 10.898,
      "step": 50
    },
    {
      "epoch": 0.01721228484643942,
      "grad_norm": 0.47083166241645813,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.2425,
      "step": 51
    },
    {
      "epoch": 0.017549780627742154,
      "grad_norm": 0.5380712747573853,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.3438,
      "step": 52
    },
    {
      "epoch": 0.017887276409044885,
      "grad_norm": 0.4980904757976532,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.3243,
      "step": 53
    },
    {
      "epoch": 0.01822477219034762,
      "grad_norm": 0.5424904823303223,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.3158,
      "step": 54
    },
    {
      "epoch": 0.018562267971650354,
      "grad_norm": 0.5894560217857361,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.6077,
      "step": 55
    },
    {
      "epoch": 0.01889976375295309,
      "grad_norm": 0.601193368434906,
      "learning_rate": 8.622126023955446e-05,
      "loss": 1.6657,
      "step": 56
    },
    {
      "epoch": 0.019237259534255823,
      "grad_norm": 0.5369265675544739,
      "learning_rate": 8.564642241456986e-05,
      "loss": 1.7473,
      "step": 57
    },
    {
      "epoch": 0.019574755315558554,
      "grad_norm": 0.5330817103385925,
      "learning_rate": 8.506183921362443e-05,
      "loss": 1.8135,
      "step": 58
    },
    {
      "epoch": 0.01991225109686129,
      "grad_norm": 0.554940402507782,
      "learning_rate": 8.44676704559283e-05,
      "loss": 1.6549,
      "step": 59
    },
    {
      "epoch": 0.020249746878164023,
      "grad_norm": 0.500688910484314,
      "learning_rate": 8.386407858128706e-05,
      "loss": 2.022,
      "step": 60
    },
    {
      "epoch": 0.020587242659466758,
      "grad_norm": 0.44095098972320557,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.5022,
      "step": 61
    },
    {
      "epoch": 0.020924738440769492,
      "grad_norm": 0.48454850912094116,
      "learning_rate": 8.262928807620843e-05,
      "loss": 1.8577,
      "step": 62
    },
    {
      "epoch": 0.021262234222072223,
      "grad_norm": 0.48471105098724365,
      "learning_rate": 8.199842702516583e-05,
      "loss": 1.8668,
      "step": 63
    },
    {
      "epoch": 0.021599730003374958,
      "grad_norm": 0.4809412360191345,
      "learning_rate": 8.135881792367686e-05,
      "loss": 1.7112,
      "step": 64
    },
    {
      "epoch": 0.021937225784677692,
      "grad_norm": 0.5266463160514832,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.5309,
      "step": 65
    },
    {
      "epoch": 0.022274721565980427,
      "grad_norm": 0.4586962163448334,
      "learning_rate": 8.005405736415126e-05,
      "loss": 1.9233,
      "step": 66
    },
    {
      "epoch": 0.022612217347283158,
      "grad_norm": 0.46809718012809753,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.8757,
      "step": 67
    },
    {
      "epoch": 0.022949713128585892,
      "grad_norm": 0.5924503207206726,
      "learning_rate": 7.871643313414718e-05,
      "loss": 1.726,
      "step": 68
    },
    {
      "epoch": 0.023287208909888626,
      "grad_norm": 0.5335246920585632,
      "learning_rate": 7.803575286758364e-05,
      "loss": 1.9682,
      "step": 69
    },
    {
      "epoch": 0.02362470469119136,
      "grad_norm": 0.5980493426322937,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.93,
      "step": 70
    },
    {
      "epoch": 0.023962200472494095,
      "grad_norm": 0.5206842422485352,
      "learning_rate": 7.66515864363997e-05,
      "loss": 1.9585,
      "step": 71
    },
    {
      "epoch": 0.024299696253796826,
      "grad_norm": 0.541953444480896,
      "learning_rate": 7.594847868906076e-05,
      "loss": 1.8451,
      "step": 72
    },
    {
      "epoch": 0.02463719203509956,
      "grad_norm": 0.4906903803348541,
      "learning_rate": 7.52382768867422e-05,
      "loss": 2.1014,
      "step": 73
    },
    {
      "epoch": 0.024974687816402295,
      "grad_norm": 0.49488648772239685,
      "learning_rate": 7.452117519152542e-05,
      "loss": 1.8397,
      "step": 74
    },
    {
      "epoch": 0.02531218359770503,
      "grad_norm": 0.49567532539367676,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.7313,
      "step": 75
    },
    {
      "epoch": 0.02564967937900776,
      "grad_norm": 0.5103468298912048,
      "learning_rate": 7.30670581489344e-05,
      "loss": 1.8343,
      "step": 76
    },
    {
      "epoch": 0.025987175160310495,
      "grad_norm": 0.4970777630805969,
      "learning_rate": 7.233044034264034e-05,
      "loss": 1.6868,
      "step": 77
    },
    {
      "epoch": 0.02632467094161323,
      "grad_norm": 0.5564061403274536,
      "learning_rate": 7.158771761692464e-05,
      "loss": 2.0077,
      "step": 78
    },
    {
      "epoch": 0.026662166722915964,
      "grad_norm": 0.5906986594200134,
      "learning_rate": 7.083909302476453e-05,
      "loss": 1.9044,
      "step": 79
    },
    {
      "epoch": 0.0269996625042187,
      "grad_norm": 0.5161340236663818,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.8798,
      "step": 80
    },
    {
      "epoch": 0.02733715828552143,
      "grad_norm": 0.5620460510253906,
      "learning_rate": 6.932495846462261e-05,
      "loss": 1.8767,
      "step": 81
    },
    {
      "epoch": 0.027674654066824164,
      "grad_norm": 0.5983588695526123,
      "learning_rate": 6.855986244591104e-05,
      "loss": 2.0385,
      "step": 82
    },
    {
      "epoch": 0.0280121498481269,
      "grad_norm": 0.5406123995780945,
      "learning_rate": 6.778969234612584e-05,
      "loss": 1.9357,
      "step": 83
    },
    {
      "epoch": 0.028349645629429633,
      "grad_norm": 0.5965004563331604,
      "learning_rate": 6.701465872208216e-05,
      "loss": 1.846,
      "step": 84
    },
    {
      "epoch": 0.028687141410732364,
      "grad_norm": 0.5949670076370239,
      "learning_rate": 6.623497346023418e-05,
      "loss": 1.9988,
      "step": 85
    },
    {
      "epoch": 0.0290246371920351,
      "grad_norm": 0.646133303642273,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.8797,
      "step": 86
    },
    {
      "epoch": 0.029362132973337833,
      "grad_norm": 0.5879825949668884,
      "learning_rate": 6.466250186922325e-05,
      "loss": 2.0766,
      "step": 87
    },
    {
      "epoch": 0.029699628754640568,
      "grad_norm": 0.7212510108947754,
      "learning_rate": 6.387014543809223e-05,
      "loss": 1.9622,
      "step": 88
    },
    {
      "epoch": 0.030037124535943302,
      "grad_norm": 0.5758910775184631,
      "learning_rate": 6.307399704769099e-05,
      "loss": 2.0455,
      "step": 89
    },
    {
      "epoch": 0.030374620317246033,
      "grad_norm": 0.648313581943512,
      "learning_rate": 6.227427435703997e-05,
      "loss": 2.0323,
      "step": 90
    },
    {
      "epoch": 0.030712116098548767,
      "grad_norm": 0.6412401795387268,
      "learning_rate": 6.147119600233758e-05,
      "loss": 2.2864,
      "step": 91
    },
    {
      "epoch": 0.031049611879851502,
      "grad_norm": 0.6075218915939331,
      "learning_rate": 6.066498153718735e-05,
      "loss": 2.0373,
      "step": 92
    },
    {
      "epoch": 0.03138710766115423,
      "grad_norm": 0.614220142364502,
      "learning_rate": 5.985585137257401e-05,
      "loss": 2.1688,
      "step": 93
    },
    {
      "epoch": 0.03172460344245697,
      "grad_norm": 0.6434118151664734,
      "learning_rate": 5.90440267166055e-05,
      "loss": 2.1976,
      "step": 94
    },
    {
      "epoch": 0.0320620992237597,
      "grad_norm": 0.6182180643081665,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 2.2718,
      "step": 95
    },
    {
      "epoch": 0.03239959500506244,
      "grad_norm": 0.6811787486076355,
      "learning_rate": 5.74131823855921e-05,
      "loss": 2.2379,
      "step": 96
    },
    {
      "epoch": 0.03273709078636517,
      "grad_norm": 0.6939035654067993,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 2.2805,
      "step": 97
    },
    {
      "epoch": 0.0330745865676679,
      "grad_norm": 0.7259014248847961,
      "learning_rate": 5.577423184847932e-05,
      "loss": 2.2849,
      "step": 98
    },
    {
      "epoch": 0.03341208234897064,
      "grad_norm": 0.6974567174911499,
      "learning_rate": 5.495227651252315e-05,
      "loss": 2.3273,
      "step": 99
    },
    {
      "epoch": 0.03374957813027337,
      "grad_norm": 0.8715429902076721,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 2.2911,
      "step": 100
    },
    {
      "epoch": 0.03374957813027337,
      "eval_loss": 1.8426469564437866,
      "eval_runtime": 115.1302,
      "eval_samples_per_second": 43.342,
      "eval_steps_per_second": 10.84,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6868879540224000.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}