{
  "best_metric": 0.7653852105140686,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.17053933063312726,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008526966531656363,
      "grad_norm": 2.2121095657348633,
      "learning_rate": 1e-05,
      "loss": 1.1498,
      "step": 1
    },
    {
      "epoch": 0.0008526966531656363,
      "eval_loss": 1.1091666221618652,
      "eval_runtime": 57.9671,
      "eval_samples_per_second": 34.071,
      "eval_steps_per_second": 8.522,
      "step": 1
    },
    {
      "epoch": 0.0017053933063312726,
      "grad_norm": 2.3430404663085938,
      "learning_rate": 2e-05,
      "loss": 1.1136,
      "step": 2
    },
    {
      "epoch": 0.002558089959496909,
      "grad_norm": 2.0547478199005127,
      "learning_rate": 3e-05,
      "loss": 1.1236,
      "step": 3
    },
    {
      "epoch": 0.003410786612662545,
      "grad_norm": 1.16932213306427,
      "learning_rate": 4e-05,
      "loss": 1.0641,
      "step": 4
    },
    {
      "epoch": 0.004263483265828182,
      "grad_norm": 0.851873517036438,
      "learning_rate": 5e-05,
      "loss": 1.0265,
      "step": 5
    },
    {
      "epoch": 0.005116179918993818,
      "grad_norm": 0.5991683602333069,
      "learning_rate": 6e-05,
      "loss": 0.9646,
      "step": 6
    },
    {
      "epoch": 0.005968876572159454,
      "grad_norm": 0.41888970136642456,
      "learning_rate": 7e-05,
      "loss": 0.9079,
      "step": 7
    },
    {
      "epoch": 0.00682157322532509,
      "grad_norm": 0.33489808440208435,
      "learning_rate": 8e-05,
      "loss": 0.889,
      "step": 8
    },
    {
      "epoch": 0.007674269878490727,
      "grad_norm": 0.4220258593559265,
      "learning_rate": 9e-05,
      "loss": 0.8959,
      "step": 9
    },
    {
      "epoch": 0.008526966531656363,
      "grad_norm": 0.30891895294189453,
      "learning_rate": 0.0001,
      "loss": 0.874,
      "step": 10
    },
    {
      "epoch": 0.009379663184822,
      "grad_norm": 0.33336496353149414,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.8661,
      "step": 11
    },
    {
      "epoch": 0.010232359837987636,
      "grad_norm": 0.5345136523246765,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.8652,
      "step": 12
    },
    {
      "epoch": 0.011085056491153272,
      "grad_norm": 0.34686779975891113,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.8583,
      "step": 13
    },
    {
      "epoch": 0.011937753144318908,
      "grad_norm": 3.1073367595672607,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.8623,
      "step": 14
    },
    {
      "epoch": 0.012790449797484544,
      "grad_norm": 4.609995365142822,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.8755,
      "step": 15
    },
    {
      "epoch": 0.01364314645065018,
      "grad_norm": 0.33146166801452637,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.8247,
      "step": 16
    },
    {
      "epoch": 0.014495843103815818,
      "grad_norm": 0.33563122153282166,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.806,
      "step": 17
    },
    {
      "epoch": 0.015348539756981455,
      "grad_norm": 0.47450077533721924,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.8412,
      "step": 18
    },
    {
      "epoch": 0.01620123641014709,
      "grad_norm": 0.5012130737304688,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.8217,
      "step": 19
    },
    {
      "epoch": 0.017053933063312727,
      "grad_norm": 0.49373531341552734,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.8116,
      "step": 20
    },
    {
      "epoch": 0.017906629716478363,
      "grad_norm": 0.4133968651294708,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.8279,
      "step": 21
    },
    {
      "epoch": 0.018759326369644,
      "grad_norm": 0.393618106842041,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.8099,
      "step": 22
    },
    {
      "epoch": 0.019612023022809635,
      "grad_norm": 0.32826492190361023,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.7996,
      "step": 23
    },
    {
      "epoch": 0.02046471967597527,
      "grad_norm": 0.39680951833724976,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.7927,
      "step": 24
    },
    {
      "epoch": 0.021317416329140908,
      "grad_norm": 0.3103278577327728,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.7882,
      "step": 25
    },
    {
      "epoch": 0.022170112982306544,
      "grad_norm": 0.242430180311203,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.7953,
      "step": 26
    },
    {
      "epoch": 0.02302280963547218,
      "grad_norm": 0.3237176239490509,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.7964,
      "step": 27
    },
    {
      "epoch": 0.023875506288637816,
      "grad_norm": 0.2409476786851883,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.8027,
      "step": 28
    },
    {
      "epoch": 0.024728202941803452,
      "grad_norm": 0.34497204422950745,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.8055,
      "step": 29
    },
    {
      "epoch": 0.02558089959496909,
      "grad_norm": 0.29693499207496643,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.7939,
      "step": 30
    },
    {
      "epoch": 0.026433596248134725,
      "grad_norm": 0.23105859756469727,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.7577,
      "step": 31
    },
    {
      "epoch": 0.02728629290130036,
      "grad_norm": 0.27222439646720886,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.7982,
      "step": 32
    },
    {
      "epoch": 0.028138989554465997,
      "grad_norm": 0.30352282524108887,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.7751,
      "step": 33
    },
    {
      "epoch": 0.028991686207631637,
      "grad_norm": 0.2205560803413391,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.7573,
      "step": 34
    },
    {
      "epoch": 0.029844382860797273,
      "grad_norm": 0.2312527745962143,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.7605,
      "step": 35
    },
    {
      "epoch": 0.03069707951396291,
      "grad_norm": 0.24350321292877197,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.7604,
      "step": 36
    },
    {
      "epoch": 0.03154977616712854,
      "grad_norm": 0.3367908000946045,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.752,
      "step": 37
    },
    {
      "epoch": 0.03240247282029418,
      "grad_norm": 0.39444592595100403,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.7628,
      "step": 38
    },
    {
      "epoch": 0.033255169473459814,
      "grad_norm": 0.2798435688018799,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.7563,
      "step": 39
    },
    {
      "epoch": 0.034107866126625454,
      "grad_norm": 0.3995003402233124,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.7966,
      "step": 40
    },
    {
      "epoch": 0.034960562779791086,
      "grad_norm": 0.37491467595100403,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.7763,
      "step": 41
    },
    {
      "epoch": 0.035813259432956726,
      "grad_norm": 0.22317229211330414,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.7441,
      "step": 42
    },
    {
      "epoch": 0.03666595608612236,
      "grad_norm": 0.3582092225551605,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.7867,
      "step": 43
    },
    {
      "epoch": 0.037518652739288,
      "grad_norm": 0.30545198917388916,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.7385,
      "step": 44
    },
    {
      "epoch": 0.03837134939245364,
      "grad_norm": 0.2698105573654175,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.7181,
      "step": 45
    },
    {
      "epoch": 0.03922404604561927,
      "grad_norm": 0.24215708673000336,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.7531,
      "step": 46
    },
    {
      "epoch": 0.04007674269878491,
      "grad_norm": 0.28581029176712036,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.7463,
      "step": 47
    },
    {
      "epoch": 0.04092943935195054,
      "grad_norm": 0.24805696308612823,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.7394,
      "step": 48
    },
    {
      "epoch": 0.04178213600511618,
      "grad_norm": 0.2741754651069641,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.7397,
      "step": 49
    },
    {
      "epoch": 0.042634832658281815,
      "grad_norm": 0.2898100018501282,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.6554,
      "step": 50
    },
    {
      "epoch": 0.042634832658281815,
      "eval_loss": 0.8124762773513794,
      "eval_runtime": 58.1981,
      "eval_samples_per_second": 33.936,
      "eval_steps_per_second": 8.488,
      "step": 50
    },
    {
      "epoch": 0.043487529311447455,
      "grad_norm": 0.5274108052253723,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.8853,
      "step": 51
    },
    {
      "epoch": 0.04434022596461309,
      "grad_norm": 0.33259961009025574,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.8799,
      "step": 52
    },
    {
      "epoch": 0.04519292261777873,
      "grad_norm": 0.24594545364379883,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.8628,
      "step": 53
    },
    {
      "epoch": 0.04604561927094436,
      "grad_norm": 0.26643481850624084,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.8569,
      "step": 54
    },
    {
      "epoch": 0.04689831592411,
      "grad_norm": 0.2917613089084625,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.8605,
      "step": 55
    },
    {
      "epoch": 0.04775101257727563,
      "grad_norm": 0.2499927282333374,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.8414,
      "step": 56
    },
    {
      "epoch": 0.04860370923044127,
      "grad_norm": 0.28645575046539307,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.8457,
      "step": 57
    },
    {
      "epoch": 0.049456405883606905,
      "grad_norm": 0.21827077865600586,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.8083,
      "step": 58
    },
    {
      "epoch": 0.050309102536772544,
      "grad_norm": 0.2010735720396042,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.8216,
      "step": 59
    },
    {
      "epoch": 0.05116179918993818,
      "grad_norm": 0.1909765750169754,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.8048,
      "step": 60
    },
    {
      "epoch": 0.05201449584310382,
      "grad_norm": 0.24219320714473724,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.7889,
      "step": 61
    },
    {
      "epoch": 0.05286719249626945,
      "grad_norm": 0.17573778331279755,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.814,
      "step": 62
    },
    {
      "epoch": 0.05371988914943509,
      "grad_norm": 0.23709945380687714,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.8261,
      "step": 63
    },
    {
      "epoch": 0.05457258580260072,
      "grad_norm": 0.21676595509052277,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.7994,
      "step": 64
    },
    {
      "epoch": 0.05542528245576636,
      "grad_norm": 0.17138059437274933,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.8102,
      "step": 65
    },
    {
      "epoch": 0.056277979108931994,
      "grad_norm": 0.18411117792129517,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.804,
      "step": 66
    },
    {
      "epoch": 0.057130675762097634,
      "grad_norm": 0.19111822545528412,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.8327,
      "step": 67
    },
    {
      "epoch": 0.05798337241526327,
      "grad_norm": 0.19528895616531372,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.7985,
      "step": 68
    },
    {
      "epoch": 0.058836069068428906,
      "grad_norm": 0.1888338029384613,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.8167,
      "step": 69
    },
    {
      "epoch": 0.059688765721594546,
      "grad_norm": 0.22683273255825043,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.7919,
      "step": 70
    },
    {
      "epoch": 0.06054146237476018,
      "grad_norm": 0.15248703956604004,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.792,
      "step": 71
    },
    {
      "epoch": 0.06139415902792582,
      "grad_norm": 0.18784311413764954,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.7936,
      "step": 72
    },
    {
      "epoch": 0.06224685568109145,
      "grad_norm": 0.17048968374729156,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.7831,
      "step": 73
    },
    {
      "epoch": 0.06309955233425708,
      "grad_norm": 0.23277565836906433,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.7738,
      "step": 74
    },
    {
      "epoch": 0.06395224898742273,
      "grad_norm": 0.20944736897945404,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.7691,
      "step": 75
    },
    {
      "epoch": 0.06480494564058836,
      "grad_norm": 0.2625070810317993,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.767,
      "step": 76
    },
    {
      "epoch": 0.065657642293754,
      "grad_norm": 0.2656240165233612,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.7851,
      "step": 77
    },
    {
      "epoch": 0.06651033894691963,
      "grad_norm": 0.2506884038448334,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.7849,
      "step": 78
    },
    {
      "epoch": 0.06736303560008527,
      "grad_norm": 0.26329290866851807,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.7634,
      "step": 79
    },
    {
      "epoch": 0.06821573225325091,
      "grad_norm": 0.2922832667827606,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.7789,
      "step": 80
    },
    {
      "epoch": 0.06906842890641654,
      "grad_norm": 0.2070065587759018,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.7471,
      "step": 81
    },
    {
      "epoch": 0.06992112555958217,
      "grad_norm": 0.22126182913780212,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.7526,
      "step": 82
    },
    {
      "epoch": 0.07077382221274782,
      "grad_norm": 0.24803754687309265,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.7666,
      "step": 83
    },
    {
      "epoch": 0.07162651886591345,
      "grad_norm": 0.22475339472293854,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.7343,
      "step": 84
    },
    {
      "epoch": 0.07247921551907908,
      "grad_norm": 0.28123778104782104,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.7358,
      "step": 85
    },
    {
      "epoch": 0.07333191217224472,
      "grad_norm": 0.18979664146900177,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.7297,
      "step": 86
    },
    {
      "epoch": 0.07418460882541036,
      "grad_norm": 0.25829166173934937,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.7398,
      "step": 87
    },
    {
      "epoch": 0.075037305478576,
      "grad_norm": 0.26326870918273926,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.7444,
      "step": 88
    },
    {
      "epoch": 0.07589000213174163,
      "grad_norm": 0.3127356767654419,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.7195,
      "step": 89
    },
    {
      "epoch": 0.07674269878490728,
      "grad_norm": 0.2700917720794678,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.7342,
      "step": 90
    },
    {
      "epoch": 0.07759539543807291,
      "grad_norm": 0.27919384837150574,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.7388,
      "step": 91
    },
    {
      "epoch": 0.07844809209123854,
      "grad_norm": 0.3218565285205841,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.765,
      "step": 92
    },
    {
      "epoch": 0.07930078874440417,
      "grad_norm": 0.2563426196575165,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.7267,
      "step": 93
    },
    {
      "epoch": 0.08015348539756982,
      "grad_norm": 0.36784499883651733,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.7639,
      "step": 94
    },
    {
      "epoch": 0.08100618205073545,
      "grad_norm": 0.2592979669570923,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.7315,
      "step": 95
    },
    {
      "epoch": 0.08185887870390109,
      "grad_norm": 0.254527747631073,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.718,
      "step": 96
    },
    {
      "epoch": 0.08271157535706672,
      "grad_norm": 0.2726317346096039,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.7653,
      "step": 97
    },
    {
      "epoch": 0.08356427201023237,
      "grad_norm": 0.2646251320838928,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.7521,
      "step": 98
    },
    {
      "epoch": 0.084416968663398,
      "grad_norm": 0.2835654616355896,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.7306,
      "step": 99
    },
    {
      "epoch": 0.08526966531656363,
      "grad_norm": 0.39553532004356384,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.6667,
      "step": 100
    },
    {
      "epoch": 0.08526966531656363,
      "eval_loss": 0.8160770535469055,
      "eval_runtime": 58.2628,
      "eval_samples_per_second": 33.898,
      "eval_steps_per_second": 8.479,
      "step": 100
    },
    {
      "epoch": 0.08612236196972926,
      "grad_norm": 0.7576678991317749,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.9012,
      "step": 101
    },
    {
      "epoch": 0.08697505862289491,
      "grad_norm": 0.4447210431098938,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.8608,
      "step": 102
    },
    {
      "epoch": 0.08782775527606054,
      "grad_norm": 0.25141364336013794,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.8526,
      "step": 103
    },
    {
      "epoch": 0.08868045192922618,
      "grad_norm": 0.2661792039871216,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.8525,
      "step": 104
    },
    {
      "epoch": 0.08953314858239181,
      "grad_norm": 0.22340400516986847,
      "learning_rate": 5e-05,
      "loss": 0.8387,
      "step": 105
    },
    {
      "epoch": 0.09038584523555745,
      "grad_norm": 0.30319744348526,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.8483,
      "step": 106
    },
    {
      "epoch": 0.09123854188872309,
      "grad_norm": 0.35070303082466125,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.8548,
      "step": 107
    },
    {
      "epoch": 0.09209123854188872,
      "grad_norm": 0.28073790669441223,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.8273,
      "step": 108
    },
    {
      "epoch": 0.09294393519505435,
      "grad_norm": 0.2680320739746094,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.832,
      "step": 109
    },
    {
      "epoch": 0.09379663184822,
      "grad_norm": 0.2709615230560303,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.8192,
      "step": 110
    },
    {
      "epoch": 0.09464932850138563,
      "grad_norm": 0.20404793322086334,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.8058,
      "step": 111
    },
    {
      "epoch": 0.09550202515455126,
      "grad_norm": 0.18862052261829376,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.8086,
      "step": 112
    },
    {
      "epoch": 0.09635472180771691,
      "grad_norm": 0.22307908535003662,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.7942,
      "step": 113
    },
    {
      "epoch": 0.09720741846088254,
      "grad_norm": 0.22101634740829468,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.802,
      "step": 114
    },
    {
      "epoch": 0.09806011511404818,
      "grad_norm": 0.20295991003513336,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.8199,
      "step": 115
    },
    {
      "epoch": 0.09891281176721381,
      "grad_norm": 0.22898121178150177,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.7997,
      "step": 116
    },
    {
      "epoch": 0.09976550842037946,
      "grad_norm": 0.20215141773223877,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.8044,
      "step": 117
    },
    {
      "epoch": 0.10061820507354509,
      "grad_norm": 0.19842548668384552,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.7892,
      "step": 118
    },
    {
      "epoch": 0.10147090172671072,
      "grad_norm": 0.20657557249069214,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.7896,
      "step": 119
    },
    {
      "epoch": 0.10232359837987635,
      "grad_norm": 0.15474191308021545,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.7945,
      "step": 120
    },
    {
      "epoch": 0.103176295033042,
      "grad_norm": 0.2063993662595749,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.7769,
      "step": 121
    },
    {
      "epoch": 0.10402899168620763,
      "grad_norm": 0.15230098366737366,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.7645,
      "step": 122
    },
    {
      "epoch": 0.10488168833937327,
      "grad_norm": 0.19912318885326385,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.7597,
      "step": 123
    },
    {
      "epoch": 0.1057343849925389,
      "grad_norm": 0.20145124197006226,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.7839,
      "step": 124
    },
    {
      "epoch": 0.10658708164570455,
      "grad_norm": 0.18647728860378265,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.7534,
      "step": 125
    },
    {
      "epoch": 0.10743977829887018,
      "grad_norm": 0.17908966541290283,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.752,
      "step": 126
    },
    {
      "epoch": 0.10829247495203581,
      "grad_norm": 0.16662199795246124,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.7625,
      "step": 127
    },
    {
      "epoch": 0.10914517160520144,
      "grad_norm": 0.20034712553024292,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.7569,
      "step": 128
    },
    {
      "epoch": 0.10999786825836709,
      "grad_norm": 0.19829131662845612,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.7445,
      "step": 129
    },
    {
      "epoch": 0.11085056491153272,
      "grad_norm": 0.23078025877475739,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.7534,
      "step": 130
    },
    {
      "epoch": 0.11170326156469836,
      "grad_norm": 0.17581824958324432,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.7637,
      "step": 131
    },
    {
      "epoch": 0.11255595821786399,
      "grad_norm": 0.20379100739955902,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.7728,
      "step": 132
    },
    {
      "epoch": 0.11340865487102963,
      "grad_norm": 0.18298354744911194,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.7206,
      "step": 133
    },
    {
      "epoch": 0.11426135152419527,
      "grad_norm": 0.21282990276813507,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.7348,
      "step": 134
    },
    {
      "epoch": 0.1151140481773609,
      "grad_norm": 0.19001737236976624,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.7359,
      "step": 135
    },
    {
      "epoch": 0.11596674483052655,
      "grad_norm": 0.24438133835792542,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.7452,
      "step": 136
    },
    {
      "epoch": 0.11681944148369218,
      "grad_norm": 0.1935417801141739,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.7286,
      "step": 137
    },
    {
      "epoch": 0.11767213813685781,
      "grad_norm": 0.23781456053256989,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.7576,
      "step": 138
    },
    {
      "epoch": 0.11852483479002345,
      "grad_norm": 0.2633705735206604,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.7612,
      "step": 139
    },
    {
      "epoch": 0.11937753144318909,
      "grad_norm": 0.23522379994392395,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.7542,
      "step": 140
    },
    {
      "epoch": 0.12023022809635472,
      "grad_norm": 0.24488364160060883,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.7185,
      "step": 141
    },
    {
      "epoch": 0.12108292474952036,
      "grad_norm": 0.2533498704433441,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.7268,
      "step": 142
    },
    {
      "epoch": 0.12193562140268599,
      "grad_norm": 0.27828148007392883,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.7146,
      "step": 143
    },
    {
      "epoch": 0.12278831805585164,
      "grad_norm": 0.23861391842365265,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.7124,
      "step": 144
    },
    {
      "epoch": 0.12364101470901727,
      "grad_norm": 0.2751621901988983,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.7378,
      "step": 145
    },
    {
      "epoch": 0.1244937113621829,
      "grad_norm": 0.24389289319515228,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.695,
      "step": 146
    },
    {
      "epoch": 0.12534640801534855,
      "grad_norm": 0.3306761384010315,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.7176,
      "step": 147
    },
    {
      "epoch": 0.12619910466851417,
      "grad_norm": 0.31437769532203674,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.7203,
      "step": 148
    },
    {
      "epoch": 0.1270518013216798,
      "grad_norm": 0.23937474191188812,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.7012,
      "step": 149
    },
    {
      "epoch": 0.12790449797484546,
      "grad_norm": 0.3032478392124176,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.7027,
      "step": 150
    },
    {
      "epoch": 0.12790449797484546,
      "eval_loss": 0.7924306392669678,
      "eval_runtime": 58.2921,
      "eval_samples_per_second": 33.881,
      "eval_steps_per_second": 8.475,
      "step": 150
    },
    {
      "epoch": 0.12875719462801108,
      "grad_norm": 0.5834566354751587,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.8668,
      "step": 151
    },
    {
      "epoch": 0.12960989128117673,
      "grad_norm": 0.4908558428287506,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.8683,
      "step": 152
    },
    {
      "epoch": 0.13046258793434234,
      "grad_norm": 0.5277212262153625,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.8442,
      "step": 153
    },
    {
      "epoch": 0.131315284587508,
      "grad_norm": 0.39518606662750244,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.8447,
      "step": 154
    },
    {
      "epoch": 0.13216798124067364,
      "grad_norm": 0.32473742961883545,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.8325,
      "step": 155
    },
    {
      "epoch": 0.13302067789383926,
      "grad_norm": 0.27383479475975037,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.8191,
      "step": 156
    },
    {
      "epoch": 0.1338733745470049,
      "grad_norm": 0.21901287138462067,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.8285,
      "step": 157
    },
    {
      "epoch": 0.13472607120017055,
      "grad_norm": 0.22791799902915955,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.8229,
      "step": 158
    },
    {
      "epoch": 0.13557876785333617,
      "grad_norm": 0.20088116824626923,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.7966,
      "step": 159
    },
    {
      "epoch": 0.13643146450650182,
      "grad_norm": 0.1682681292295456,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.7981,
      "step": 160
    },
    {
      "epoch": 0.13728416115966746,
      "grad_norm": 0.24641159176826477,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.7961,
      "step": 161
    },
    {
      "epoch": 0.13813685781283308,
      "grad_norm": 0.1815796047449112,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.8053,
      "step": 162
    },
    {
      "epoch": 0.13898955446599873,
      "grad_norm": 0.2448711395263672,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.8092,
      "step": 163
    },
    {
      "epoch": 0.13984225111916435,
      "grad_norm": 0.22450482845306396,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.7904,
      "step": 164
    },
    {
      "epoch": 0.14069494777233,
      "grad_norm": 0.21843770146369934,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.8023,
      "step": 165
    },
    {
      "epoch": 0.14154764442549564,
      "grad_norm": 0.2439671903848648,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.8158,
      "step": 166
    },
    {
      "epoch": 0.14240034107866126,
      "grad_norm": 0.25153136253356934,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.8096,
      "step": 167
    },
    {
      "epoch": 0.1432530377318269,
      "grad_norm": 0.2515774369239807,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.7969,
      "step": 168
    },
    {
      "epoch": 0.14410573438499255,
      "grad_norm": 0.21411442756652832,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.7721,
      "step": 169
    },
    {
      "epoch": 0.14495843103815817,
      "grad_norm": 0.21481217443943024,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.7992,
      "step": 170
    },
    {
      "epoch": 0.14581112769132382,
      "grad_norm": 0.2631784975528717,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.7818,
      "step": 171
    },
    {
      "epoch": 0.14666382434448944,
      "grad_norm": 0.20941950380802155,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.7591,
      "step": 172
    },
    {
      "epoch": 0.14751652099765508,
      "grad_norm": 0.20896439254283905,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.7728,
      "step": 173
    },
    {
      "epoch": 0.14836921765082073,
      "grad_norm": 0.2100289911031723,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.7754,
      "step": 174
    },
    {
      "epoch": 0.14922191430398635,
      "grad_norm": 0.2179926484823227,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.7656,
      "step": 175
    },
    {
      "epoch": 0.150074610957152,
      "grad_norm": 0.19529153406620026,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.7632,
      "step": 176
    },
    {
      "epoch": 0.15092730761031764,
      "grad_norm": 0.19807685911655426,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.7587,
      "step": 177
    },
    {
      "epoch": 0.15178000426348326,
      "grad_norm": 0.21307672560214996,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.7463,
      "step": 178
    },
    {
      "epoch": 0.1526327009166489,
      "grad_norm": 0.2136138379573822,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.7427,
      "step": 179
    },
    {
      "epoch": 0.15348539756981455,
      "grad_norm": 0.21334142982959747,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.7501,
      "step": 180
    },
    {
      "epoch": 0.15433809422298017,
      "grad_norm": 0.2069474160671234,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.7452,
      "step": 181
    },
    {
      "epoch": 0.15519079087614582,
      "grad_norm": 0.21321307122707367,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.7665,
      "step": 182
    },
    {
      "epoch": 0.15604348752931144,
      "grad_norm": 0.2502729892730713,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.7108,
      "step": 183
    },
    {
      "epoch": 0.15689618418247708,
      "grad_norm": 0.24035628139972687,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.7167,
      "step": 184
    },
    {
      "epoch": 0.15774888083564273,
      "grad_norm": 0.20366396009922028,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.7464,
      "step": 185
    },
    {
      "epoch": 0.15860157748880835,
      "grad_norm": 0.21428947150707245,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.7493,
      "step": 186
    },
    {
      "epoch": 0.159454274141974,
      "grad_norm": 0.21699705719947815,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.7578,
      "step": 187
    },
    {
      "epoch": 0.16030697079513964,
      "grad_norm": 0.2295570969581604,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.7546,
      "step": 188
    },
    {
      "epoch": 0.16115966744830526,
      "grad_norm": 0.21301276981830597,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.7397,
      "step": 189
    },
    {
      "epoch": 0.1620123641014709,
      "grad_norm": 0.2429417073726654,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.705,
      "step": 190
    },
    {
      "epoch": 0.16286506075463653,
      "grad_norm": 0.376483291387558,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.7336,
      "step": 191
    },
    {
      "epoch": 0.16371775740780217,
      "grad_norm": 0.28167665004730225,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.7194,
      "step": 192
    },
    {
      "epoch": 0.16457045406096782,
      "grad_norm": 0.2790934443473816,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.7083,
      "step": 193
    },
    {
      "epoch": 0.16542315071413344,
      "grad_norm": 0.2976372539997101,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.7047,
      "step": 194
    },
    {
      "epoch": 0.16627584736729908,
      "grad_norm": 0.3269420266151428,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.6844,
      "step": 195
    },
    {
      "epoch": 0.16712854402046473,
      "grad_norm": 0.33335623145103455,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.7471,
      "step": 196
    },
    {
      "epoch": 0.16798124067363035,
      "grad_norm": 0.43295735120773315,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.7264,
      "step": 197
    },
    {
      "epoch": 0.168833937326796,
      "grad_norm": 0.47900182008743286,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.7577,
      "step": 198
    },
    {
      "epoch": 0.16968663397996162,
      "grad_norm": 0.5003798604011536,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.7443,
      "step": 199
    },
    {
      "epoch": 0.17053933063312726,
      "grad_norm": 0.4132130444049835,
      "learning_rate": 0.0,
      "loss": 0.6872,
      "step": 200
    },
    {
      "epoch": 0.17053933063312726,
      "eval_loss": 0.7653852105140686,
      "eval_runtime": 58.2395,
      "eval_samples_per_second": 33.912,
      "eval_steps_per_second": 8.482,
      "step": 200
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.4428946137088e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}