{
  "best_metric": 1.566010594367981,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 1.8181818181818183,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00909090909090909,
      "grad_norm": 0.27334141731262207,
      "learning_rate": 1e-05,
      "loss": 1.7034,
      "step": 1
    },
    {
      "epoch": 0.00909090909090909,
      "eval_loss": 1.9522194862365723,
      "eval_runtime": 39.6629,
      "eval_samples_per_second": 18.682,
      "eval_steps_per_second": 1.185,
      "step": 1
    },
    {
      "epoch": 0.01818181818181818,
      "grad_norm": 0.36351078748703003,
      "learning_rate": 2e-05,
      "loss": 1.739,
      "step": 2
    },
    {
      "epoch": 0.02727272727272727,
      "grad_norm": 0.3662008047103882,
      "learning_rate": 3e-05,
      "loss": 1.7198,
      "step": 3
    },
    {
      "epoch": 0.03636363636363636,
      "grad_norm": 0.6483047008514404,
      "learning_rate": 4e-05,
      "loss": 1.721,
      "step": 4
    },
    {
      "epoch": 0.045454545454545456,
      "grad_norm": 0.4620528519153595,
      "learning_rate": 5e-05,
      "loss": 1.7522,
      "step": 5
    },
    {
      "epoch": 0.05454545454545454,
      "grad_norm": 0.5257095694541931,
      "learning_rate": 6e-05,
      "loss": 1.776,
      "step": 6
    },
    {
      "epoch": 0.06363636363636363,
      "grad_norm": 0.658363938331604,
      "learning_rate": 7e-05,
      "loss": 1.7493,
      "step": 7
    },
    {
      "epoch": 0.07272727272727272,
      "grad_norm": 0.7645014524459839,
      "learning_rate": 8e-05,
      "loss": 1.8118,
      "step": 8
    },
    {
      "epoch": 0.08181818181818182,
      "grad_norm": 0.8591474294662476,
      "learning_rate": 9e-05,
      "loss": 1.7837,
      "step": 9
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 1.0647271871566772,
      "learning_rate": 0.0001,
      "loss": 1.7844,
      "step": 10
    },
    {
      "epoch": 0.1,
      "grad_norm": 1.2166738510131836,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.7452,
      "step": 11
    },
    {
      "epoch": 0.10909090909090909,
      "grad_norm": 1.405843734741211,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.758,
      "step": 12
    },
    {
      "epoch": 0.11818181818181818,
      "grad_norm": 0.6587836742401123,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.7335,
      "step": 13
    },
    {
      "epoch": 0.12727272727272726,
      "grad_norm": 0.6507381200790405,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.7548,
      "step": 14
    },
    {
      "epoch": 0.13636363636363635,
      "grad_norm": 0.5447920560836792,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.7257,
      "step": 15
    },
    {
      "epoch": 0.14545454545454545,
      "grad_norm": 0.5138877630233765,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.7014,
      "step": 16
    },
    {
      "epoch": 0.15454545454545454,
      "grad_norm": 0.5481241345405579,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.6654,
      "step": 17
    },
    {
      "epoch": 0.16363636363636364,
      "grad_norm": 0.4878271818161011,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.6412,
      "step": 18
    },
    {
      "epoch": 0.17272727272727273,
      "grad_norm": 0.5206863284111023,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.6054,
      "step": 19
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 0.60885089635849,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.66,
      "step": 20
    },
    {
      "epoch": 0.19090909090909092,
      "grad_norm": 0.7293643951416016,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.6772,
      "step": 21
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.7861894369125366,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.7033,
      "step": 22
    },
    {
      "epoch": 0.20909090909090908,
      "grad_norm": 0.8479618430137634,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.5976,
      "step": 23
    },
    {
      "epoch": 0.21818181818181817,
      "grad_norm": 1.0858114957809448,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.7205,
      "step": 24
    },
    {
      "epoch": 0.22727272727272727,
      "grad_norm": 1.7521491050720215,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.9271,
      "step": 25
    },
    {
      "epoch": 0.23636363636363636,
      "grad_norm": 0.2629496455192566,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.6558,
      "step": 26
    },
    {
      "epoch": 0.24545454545454545,
      "grad_norm": 0.3440329432487488,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.5828,
      "step": 27
    },
    {
      "epoch": 0.2545454545454545,
      "grad_norm": 0.4303309917449951,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.6825,
      "step": 28
    },
    {
      "epoch": 0.2636363636363636,
      "grad_norm": 0.5641345381736755,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.6574,
      "step": 29
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 0.46685269474983215,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.6503,
      "step": 30
    },
    {
      "epoch": 0.2818181818181818,
      "grad_norm": 0.5108544230461121,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.6176,
      "step": 31
    },
    {
      "epoch": 0.2909090909090909,
      "grad_norm": 0.5643579959869385,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.6213,
      "step": 32
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.5380235314369202,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.6357,
      "step": 33
    },
    {
      "epoch": 0.3090909090909091,
      "grad_norm": 0.627714991569519,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.677,
      "step": 34
    },
    {
      "epoch": 0.3181818181818182,
      "grad_norm": 0.7961784601211548,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.6461,
      "step": 35
    },
    {
      "epoch": 0.32727272727272727,
      "grad_norm": 0.8769607543945312,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.4948,
      "step": 36
    },
    {
      "epoch": 0.33636363636363636,
      "grad_norm": 1.0253502130508423,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.7346,
      "step": 37
    },
    {
      "epoch": 0.34545454545454546,
      "grad_norm": 0.25720086693763733,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.6523,
      "step": 38
    },
    {
      "epoch": 0.35454545454545455,
      "grad_norm": 0.24011823534965515,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.6352,
      "step": 39
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.29697853326797485,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.5878,
      "step": 40
    },
    {
      "epoch": 0.37272727272727274,
      "grad_norm": 0.3182009756565094,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.5952,
      "step": 41
    },
    {
      "epoch": 0.38181818181818183,
      "grad_norm": 0.3914555609226227,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.6096,
      "step": 42
    },
    {
      "epoch": 0.39090909090909093,
      "grad_norm": 0.4357691705226898,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.5352,
      "step": 43
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.4717869162559509,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.5477,
      "step": 44
    },
    {
      "epoch": 0.4090909090909091,
      "grad_norm": 0.5312885046005249,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.5766,
      "step": 45
    },
    {
      "epoch": 0.41818181818181815,
      "grad_norm": 0.5182300806045532,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.6572,
      "step": 46
    },
    {
      "epoch": 0.42727272727272725,
      "grad_norm": 0.6158595085144043,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.5913,
      "step": 47
    },
    {
      "epoch": 0.43636363636363634,
      "grad_norm": 0.7384253740310669,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.5652,
      "step": 48
    },
    {
      "epoch": 0.44545454545454544,
      "grad_norm": 0.9697166681289673,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.5869,
      "step": 49
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 1.5988574028015137,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.923,
      "step": 50
    },
    {
      "epoch": 0.45454545454545453,
      "eval_loss": 1.6573060750961304,
      "eval_runtime": 7.0201,
      "eval_samples_per_second": 105.554,
      "eval_steps_per_second": 6.695,
      "step": 50
    },
    {
      "epoch": 0.4636363636363636,
      "grad_norm": 0.2109682410955429,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.6191,
      "step": 51
    },
    {
      "epoch": 0.4727272727272727,
      "grad_norm": 0.23274514079093933,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.6123,
      "step": 52
    },
    {
      "epoch": 0.4818181818181818,
      "grad_norm": 0.29903581738471985,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.6161,
      "step": 53
    },
    {
      "epoch": 0.4909090909090909,
      "grad_norm": 0.3372276723384857,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.5746,
      "step": 54
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.36295413970947266,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.5788,
      "step": 55
    },
    {
      "epoch": 0.509090909090909,
      "grad_norm": 0.38236600160598755,
      "learning_rate": 8.622126023955446e-05,
      "loss": 1.5464,
      "step": 56
    },
    {
      "epoch": 0.5181818181818182,
      "grad_norm": 0.4454088509082794,
      "learning_rate": 8.564642241456986e-05,
      "loss": 1.6011,
      "step": 57
    },
    {
      "epoch": 0.5272727272727272,
      "grad_norm": 0.4965706765651703,
      "learning_rate": 8.506183921362443e-05,
      "loss": 1.587,
      "step": 58
    },
    {
      "epoch": 0.5363636363636364,
      "grad_norm": 0.608468234539032,
      "learning_rate": 8.44676704559283e-05,
      "loss": 1.5758,
      "step": 59
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 0.6737092137336731,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.5509,
      "step": 60
    },
    {
      "epoch": 0.5545454545454546,
      "grad_norm": 0.752474844455719,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.5751,
      "step": 61
    },
    {
      "epoch": 0.5636363636363636,
      "grad_norm": 1.0845879316329956,
      "learning_rate": 8.262928807620843e-05,
      "loss": 1.7716,
      "step": 62
    },
    {
      "epoch": 0.5727272727272728,
      "grad_norm": 0.2760830521583557,
      "learning_rate": 8.199842702516583e-05,
      "loss": 1.621,
      "step": 63
    },
    {
      "epoch": 0.5818181818181818,
      "grad_norm": 0.23105846345424652,
      "learning_rate": 8.135881792367686e-05,
      "loss": 1.6361,
      "step": 64
    },
    {
      "epoch": 0.5909090909090909,
      "grad_norm": 0.28794723749160767,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.6002,
      "step": 65
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.30997979640960693,
      "learning_rate": 8.005405736415126e-05,
      "loss": 1.5581,
      "step": 66
    },
    {
      "epoch": 0.6090909090909091,
      "grad_norm": 0.35087406635284424,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.5549,
      "step": 67
    },
    {
      "epoch": 0.6181818181818182,
      "grad_norm": 0.39407429099082947,
      "learning_rate": 7.871643313414718e-05,
      "loss": 1.5539,
      "step": 68
    },
    {
      "epoch": 0.6272727272727273,
      "grad_norm": 0.44571980834007263,
      "learning_rate": 7.803575286758364e-05,
      "loss": 1.512,
      "step": 69
    },
    {
      "epoch": 0.6363636363636364,
      "grad_norm": 0.46417665481567383,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.5185,
      "step": 70
    },
    {
      "epoch": 0.6454545454545455,
      "grad_norm": 0.5833612680435181,
      "learning_rate": 7.66515864363997e-05,
      "loss": 1.539,
      "step": 71
    },
    {
      "epoch": 0.6545454545454545,
      "grad_norm": 0.5966383814811707,
      "learning_rate": 7.594847868906076e-05,
      "loss": 1.5777,
      "step": 72
    },
    {
      "epoch": 0.6636363636363637,
      "grad_norm": 0.788000226020813,
      "learning_rate": 7.52382768867422e-05,
      "loss": 1.5001,
      "step": 73
    },
    {
      "epoch": 0.6727272727272727,
      "grad_norm": 0.854478120803833,
      "learning_rate": 7.452117519152542e-05,
      "loss": 1.4253,
      "step": 74
    },
    {
      "epoch": 0.6818181818181818,
      "grad_norm": 1.2467149496078491,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.845,
      "step": 75
    },
    {
      "epoch": 0.6909090909090909,
      "grad_norm": 0.20379644632339478,
      "learning_rate": 7.30670581489344e-05,
      "loss": 1.6839,
      "step": 76
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.25373998284339905,
      "learning_rate": 7.233044034264034e-05,
      "loss": 1.6247,
      "step": 77
    },
    {
      "epoch": 0.7090909090909091,
      "grad_norm": 0.3033841550350189,
      "learning_rate": 7.158771761692464e-05,
      "loss": 1.5957,
      "step": 78
    },
    {
      "epoch": 0.7181818181818181,
      "grad_norm": 0.3326650559902191,
      "learning_rate": 7.083909302476453e-05,
      "loss": 1.5064,
      "step": 79
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.37131884694099426,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.5801,
      "step": 80
    },
    {
      "epoch": 0.7363636363636363,
      "grad_norm": 0.4183734953403473,
      "learning_rate": 6.932495846462261e-05,
      "loss": 1.5355,
      "step": 81
    },
    {
      "epoch": 0.7454545454545455,
      "grad_norm": 0.5078173875808716,
      "learning_rate": 6.855986244591104e-05,
      "loss": 1.5561,
      "step": 82
    },
    {
      "epoch": 0.7545454545454545,
      "grad_norm": 0.5390819311141968,
      "learning_rate": 6.778969234612584e-05,
      "loss": 1.4116,
      "step": 83
    },
    {
      "epoch": 0.7636363636363637,
      "grad_norm": 0.6023460030555725,
      "learning_rate": 6.701465872208216e-05,
      "loss": 1.508,
      "step": 84
    },
    {
      "epoch": 0.7727272727272727,
      "grad_norm": 0.7686478495597839,
      "learning_rate": 6.623497346023418e-05,
      "loss": 1.5362,
      "step": 85
    },
    {
      "epoch": 0.7818181818181819,
      "grad_norm": 0.7677623629570007,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.4101,
      "step": 86
    },
    {
      "epoch": 0.7909090909090909,
      "grad_norm": 1.112106204032898,
      "learning_rate": 6.466250186922325e-05,
      "loss": 1.5629,
      "step": 87
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.25881725549697876,
      "learning_rate": 6.387014543809223e-05,
      "loss": 1.6659,
      "step": 88
    },
    {
      "epoch": 0.8090909090909091,
      "grad_norm": 0.22736859321594238,
      "learning_rate": 6.307399704769099e-05,
      "loss": 1.5845,
      "step": 89
    },
    {
      "epoch": 0.8181818181818182,
      "grad_norm": 0.27788057923316956,
      "learning_rate": 6.227427435703997e-05,
      "loss": 1.6006,
      "step": 90
    },
    {
      "epoch": 0.8272727272727273,
      "grad_norm": 0.3123621344566345,
      "learning_rate": 6.147119600233758e-05,
      "loss": 1.5372,
      "step": 91
    },
    {
      "epoch": 0.8363636363636363,
      "grad_norm": 0.3698670566082001,
      "learning_rate": 6.066498153718735e-05,
      "loss": 1.5267,
      "step": 92
    },
    {
      "epoch": 0.8454545454545455,
      "grad_norm": 0.3917481005191803,
      "learning_rate": 5.985585137257401e-05,
      "loss": 1.5409,
      "step": 93
    },
    {
      "epoch": 0.8545454545454545,
      "grad_norm": 0.47551408410072327,
      "learning_rate": 5.90440267166055e-05,
      "loss": 1.529,
      "step": 94
    },
    {
      "epoch": 0.8636363636363636,
      "grad_norm": 0.5327534675598145,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 1.5591,
      "step": 95
    },
    {
      "epoch": 0.8727272727272727,
      "grad_norm": 0.5812963247299194,
      "learning_rate": 5.74131823855921e-05,
      "loss": 1.4886,
      "step": 96
    },
    {
      "epoch": 0.8818181818181818,
      "grad_norm": 0.664090096950531,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 1.5451,
      "step": 97
    },
    {
      "epoch": 0.8909090909090909,
      "grad_norm": 0.7177919745445251,
      "learning_rate": 5.577423184847932e-05,
      "loss": 1.4718,
      "step": 98
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.967860221862793,
      "learning_rate": 5.495227651252315e-05,
      "loss": 1.4838,
      "step": 99
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 1.4533907175064087,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 1.8906,
      "step": 100
    },
    {
      "epoch": 0.9090909090909091,
      "eval_loss": 1.607083797454834,
      "eval_runtime": 7.0354,
      "eval_samples_per_second": 105.325,
      "eval_steps_per_second": 6.681,
      "step": 100
    },
    {
      "epoch": 0.9181818181818182,
      "grad_norm": 0.19696490466594696,
      "learning_rate": 5.330452921628497e-05,
      "loss": 1.621,
      "step": 101
    },
    {
      "epoch": 0.9272727272727272,
      "grad_norm": 0.27355989813804626,
      "learning_rate": 5.247918773366112e-05,
      "loss": 1.5859,
      "step": 102
    },
    {
      "epoch": 0.9363636363636364,
      "grad_norm": 0.31778624653816223,
      "learning_rate": 5.165316846586541e-05,
      "loss": 1.5206,
      "step": 103
    },
    {
      "epoch": 0.9454545454545454,
      "grad_norm": 0.40454769134521484,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 1.5601,
      "step": 104
    },
    {
      "epoch": 0.9545454545454546,
      "grad_norm": 0.4619913101196289,
      "learning_rate": 5e-05,
      "loss": 1.5208,
      "step": 105
    },
    {
      "epoch": 0.9636363636363636,
      "grad_norm": 0.6000276803970337,
      "learning_rate": 4.917330276168208e-05,
      "loss": 1.5876,
      "step": 106
    },
    {
      "epoch": 0.9727272727272728,
      "grad_norm": 0.60955810546875,
      "learning_rate": 4.834683153413459e-05,
      "loss": 1.5261,
      "step": 107
    },
    {
      "epoch": 0.9818181818181818,
      "grad_norm": 0.8125905394554138,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 1.5086,
      "step": 108
    },
    {
      "epoch": 0.990909090909091,
      "grad_norm": 0.9143168330192566,
      "learning_rate": 4.669547078371504e-05,
      "loss": 1.4412,
      "step": 109
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.4070168733596802,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 1.7024,
      "step": 110
    },
    {
      "epoch": 1.009090909090909,
      "grad_norm": 0.19341616332530975,
      "learning_rate": 4.504772348747687e-05,
      "loss": 1.6395,
      "step": 111
    },
    {
      "epoch": 1.018181818181818,
      "grad_norm": 0.25132858753204346,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 1.6015,
      "step": 112
    },
    {
      "epoch": 1.0272727272727273,
      "grad_norm": 0.3063439428806305,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 1.532,
      "step": 113
    },
    {
      "epoch": 1.0363636363636364,
      "grad_norm": 0.346793532371521,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 1.519,
      "step": 114
    },
    {
      "epoch": 1.0454545454545454,
      "grad_norm": 0.3660779893398285,
      "learning_rate": 4.17702704859633e-05,
      "loss": 1.5273,
      "step": 115
    },
    {
      "epoch": 1.0545454545454545,
      "grad_norm": 0.4079892337322235,
      "learning_rate": 4.095597328339452e-05,
      "loss": 1.4652,
      "step": 116
    },
    {
      "epoch": 1.0636363636363637,
      "grad_norm": 0.4765719175338745,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 1.4899,
      "step": 117
    },
    {
      "epoch": 1.0727272727272728,
      "grad_norm": 0.5500777959823608,
      "learning_rate": 3.933501846281267e-05,
      "loss": 1.4505,
      "step": 118
    },
    {
      "epoch": 1.0818181818181818,
      "grad_norm": 0.5707745552062988,
      "learning_rate": 3.852880399766243e-05,
      "loss": 1.426,
      "step": 119
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 0.7157875895500183,
      "learning_rate": 3.772572564296005e-05,
      "loss": 1.4468,
      "step": 120
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.8291390538215637,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 1.2169,
      "step": 121
    },
    {
      "epoch": 1.1090909090909091,
      "grad_norm": 1.060056447982788,
      "learning_rate": 3.612985456190778e-05,
      "loss": 1.5584,
      "step": 122
    },
    {
      "epoch": 1.1181818181818182,
      "grad_norm": 0.24830403923988342,
      "learning_rate": 3.533749813077677e-05,
      "loss": 1.5831,
      "step": 123
    },
    {
      "epoch": 1.1272727272727272,
      "grad_norm": 0.23286068439483643,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.5657,
      "step": 124
    },
    {
      "epoch": 1.1363636363636362,
      "grad_norm": 0.28456342220306396,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 1.5382,
      "step": 125
    },
    {
      "epoch": 1.1454545454545455,
      "grad_norm": 0.335363507270813,
      "learning_rate": 3.298534127791785e-05,
      "loss": 1.4677,
      "step": 126
    },
    {
      "epoch": 1.1545454545454545,
      "grad_norm": 0.3733579218387604,
      "learning_rate": 3.221030765387417e-05,
      "loss": 1.4804,
      "step": 127
    },
    {
      "epoch": 1.1636363636363636,
      "grad_norm": 0.4048534035682678,
      "learning_rate": 3.144013755408895e-05,
      "loss": 1.4697,
      "step": 128
    },
    {
      "epoch": 1.1727272727272728,
      "grad_norm": 0.4617495536804199,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 1.4251,
      "step": 129
    },
    {
      "epoch": 1.1818181818181819,
      "grad_norm": 0.5494787693023682,
      "learning_rate": 2.991522876735154e-05,
      "loss": 1.4722,
      "step": 130
    },
    {
      "epoch": 1.190909090909091,
      "grad_norm": 0.592727541923523,
      "learning_rate": 2.916090697523549e-05,
      "loss": 1.5131,
      "step": 131
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.7208784222602844,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 1.4192,
      "step": 132
    },
    {
      "epoch": 1.209090909090909,
      "grad_norm": 0.8039544820785522,
      "learning_rate": 2.766955965735968e-05,
      "loss": 1.4898,
      "step": 133
    },
    {
      "epoch": 1.2181818181818183,
      "grad_norm": 0.7555994391441345,
      "learning_rate": 2.693294185106562e-05,
      "loss": 1.3255,
      "step": 134
    },
    {
      "epoch": 1.2272727272727273,
      "grad_norm": 1.1523597240447998,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 1.5946,
      "step": 135
    },
    {
      "epoch": 1.2363636363636363,
      "grad_norm": 0.1947619616985321,
      "learning_rate": 2.547882480847461e-05,
      "loss": 1.6294,
      "step": 136
    },
    {
      "epoch": 1.2454545454545454,
      "grad_norm": 0.27387577295303345,
      "learning_rate": 2.476172311325783e-05,
      "loss": 1.5575,
      "step": 137
    },
    {
      "epoch": 1.2545454545454544,
      "grad_norm": 0.3011581301689148,
      "learning_rate": 2.405152131093926e-05,
      "loss": 1.5043,
      "step": 138
    },
    {
      "epoch": 1.2636363636363637,
      "grad_norm": 0.3687533438205719,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 1.4962,
      "step": 139
    },
    {
      "epoch": 1.2727272727272727,
      "grad_norm": 0.41046422719955444,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 1.4529,
      "step": 140
    },
    {
      "epoch": 1.2818181818181817,
      "grad_norm": 0.4458724856376648,
      "learning_rate": 2.196424713241637e-05,
      "loss": 1.4885,
      "step": 141
    },
    {
      "epoch": 1.290909090909091,
      "grad_norm": 0.48569661378860474,
      "learning_rate": 2.128356686585282e-05,
      "loss": 1.5074,
      "step": 142
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.5772014260292053,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.48,
      "step": 143
    },
    {
      "epoch": 1.309090909090909,
      "grad_norm": 0.6232538819313049,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 1.4375,
      "step": 144
    },
    {
      "epoch": 1.3181818181818181,
      "grad_norm": 0.77461177110672,
      "learning_rate": 1.928936436551661e-05,
      "loss": 1.4178,
      "step": 145
    },
    {
      "epoch": 1.3272727272727272,
      "grad_norm": 0.822654128074646,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 1.1562,
      "step": 146
    },
    {
      "epoch": 1.3363636363636364,
      "grad_norm": 1.1225616931915283,
      "learning_rate": 1.800157297483417e-05,
      "loss": 1.4794,
      "step": 147
    },
    {
      "epoch": 1.3454545454545455,
      "grad_norm": 0.25710177421569824,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 1.541,
      "step": 148
    },
    {
      "epoch": 1.3545454545454545,
      "grad_norm": 0.2558896243572235,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 1.5758,
      "step": 149
    },
    {
      "epoch": 1.3636363636363638,
      "grad_norm": 0.29814964532852173,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 1.5326,
      "step": 150
    },
    {
      "epoch": 1.3636363636363638,
      "eval_loss": 1.5815321207046509,
      "eval_runtime": 7.032,
      "eval_samples_per_second": 105.375,
      "eval_steps_per_second": 6.684,
      "step": 150
    },
    {
      "epoch": 1.3727272727272728,
      "grad_norm": 0.3305523097515106,
      "learning_rate": 1.553232954407171e-05,
      "loss": 1.5439,
      "step": 151
    },
    {
      "epoch": 1.3818181818181818,
      "grad_norm": 0.371360719203949,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 1.4646,
      "step": 152
    },
    {
      "epoch": 1.3909090909090909,
      "grad_norm": 0.44892507791519165,
      "learning_rate": 1.435357758543015e-05,
      "loss": 1.4668,
      "step": 153
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.4470708668231964,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 1.406,
      "step": 154
    },
    {
      "epoch": 1.4090909090909092,
      "grad_norm": 0.5549824833869934,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 1.4956,
      "step": 155
    },
    {
      "epoch": 1.4181818181818182,
      "grad_norm": 0.5967565774917603,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 1.5051,
      "step": 156
    },
    {
      "epoch": 1.4272727272727272,
      "grad_norm": 0.6843442916870117,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 1.403,
      "step": 157
    },
    {
      "epoch": 1.4363636363636363,
      "grad_norm": 0.7750641703605652,
      "learning_rate": 1.157994445715706e-05,
      "loss": 1.3522,
      "step": 158
    },
    {
      "epoch": 1.4454545454545453,
      "grad_norm": 1.1304163932800293,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 1.3548,
      "step": 159
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 1.4879887104034424,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 1.5592,
      "step": 160
    },
    {
      "epoch": 1.4636363636363636,
      "grad_norm": 0.20014530420303345,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 1.5446,
      "step": 161
    },
    {
      "epoch": 1.4727272727272727,
      "grad_norm": 0.2731146812438965,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.5838,
      "step": 162
    },
    {
      "epoch": 1.481818181818182,
      "grad_norm": 0.3155849874019623,
      "learning_rate": 9.068759265665384e-06,
      "loss": 1.5176,
      "step": 163
    },
    {
      "epoch": 1.490909090909091,
      "grad_norm": 0.35746926069259644,
      "learning_rate": 8.599558442598998e-06,
      "loss": 1.5077,
      "step": 164
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.4008142948150635,
      "learning_rate": 8.141676086873572e-06,
      "loss": 1.5457,
      "step": 165
    },
    {
      "epoch": 1.509090909090909,
      "grad_norm": 0.47248971462249756,
      "learning_rate": 7.695237378953223e-06,
      "loss": 1.4529,
      "step": 166
    },
    {
      "epoch": 1.518181818181818,
      "grad_norm": 0.5173071622848511,
      "learning_rate": 7.260364370723044e-06,
      "loss": 1.5371,
      "step": 167
    },
    {
      "epoch": 1.5272727272727273,
      "grad_norm": 0.6199659705162048,
      "learning_rate": 6.837175952121306e-06,
      "loss": 1.4001,
      "step": 168
    },
    {
      "epoch": 1.5363636363636364,
      "grad_norm": 0.6448993682861328,
      "learning_rate": 6.425787818636131e-06,
      "loss": 1.4187,
      "step": 169
    },
    {
      "epoch": 1.5454545454545454,
      "grad_norm": 0.7205504179000854,
      "learning_rate": 6.026312439675552e-06,
      "loss": 1.3456,
      "step": 170
    },
    {
      "epoch": 1.5545454545454547,
      "grad_norm": 0.8862988948822021,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 1.3794,
      "step": 171
    },
    {
      "epoch": 1.5636363636363635,
      "grad_norm": 1.0340073108673096,
      "learning_rate": 5.263533508961827e-06,
      "loss": 1.4381,
      "step": 172
    },
    {
      "epoch": 1.5727272727272728,
      "grad_norm": 0.2841588258743286,
      "learning_rate": 4.900438493352055e-06,
      "loss": 1.5841,
      "step": 173
    },
    {
      "epoch": 1.5818181818181818,
      "grad_norm": 0.23268909752368927,
      "learning_rate": 4.549673247541875e-06,
      "loss": 1.5879,
      "step": 174
    },
    {
      "epoch": 1.5909090909090908,
      "grad_norm": 0.29230713844299316,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 1.5414,
      "step": 175
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.3435336649417877,
      "learning_rate": 3.885512251130763e-06,
      "loss": 1.49,
      "step": 176
    },
    {
      "epoch": 1.6090909090909091,
      "grad_norm": 0.3711763024330139,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 1.5543,
      "step": 177
    },
    {
      "epoch": 1.6181818181818182,
      "grad_norm": 0.4170873165130615,
      "learning_rate": 3.271776770026963e-06,
      "loss": 1.4335,
      "step": 178
    },
    {
      "epoch": 1.6272727272727274,
      "grad_norm": 0.4740619659423828,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 1.4608,
      "step": 179
    },
    {
      "epoch": 1.6363636363636362,
      "grad_norm": 0.48094651103019714,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 1.3803,
      "step": 180
    },
    {
      "epoch": 1.6454545454545455,
      "grad_norm": 0.6339503526687622,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.4094,
      "step": 181
    },
    {
      "epoch": 1.6545454545454545,
      "grad_norm": 0.6177853941917419,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 1.3906,
      "step": 182
    },
    {
      "epoch": 1.6636363636363636,
      "grad_norm": 0.8423618078231812,
      "learning_rate": 1.962316193157593e-06,
      "loss": 1.4231,
      "step": 183
    },
    {
      "epoch": 1.6727272727272728,
      "grad_norm": 0.8755652904510498,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 1.3193,
      "step": 184
    },
    {
      "epoch": 1.6818181818181817,
      "grad_norm": 1.3242055177688599,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 1.5555,
      "step": 185
    },
    {
      "epoch": 1.690909090909091,
      "grad_norm": 0.19381852447986603,
      "learning_rate": 1.333670137599713e-06,
      "loss": 1.5804,
      "step": 186
    },
    {
      "epoch": 1.7,
      "grad_norm": 0.2594815790653229,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 1.5322,
      "step": 187
    },
    {
      "epoch": 1.709090909090909,
      "grad_norm": 0.3053761422634125,
      "learning_rate": 9.810017062595322e-07,
      "loss": 1.5495,
      "step": 188
    },
    {
      "epoch": 1.7181818181818183,
      "grad_norm": 0.358294278383255,
      "learning_rate": 8.247462563808817e-07,
      "loss": 1.4985,
      "step": 189
    },
    {
      "epoch": 1.7272727272727273,
      "grad_norm": 0.3971862494945526,
      "learning_rate": 6.819348298638839e-07,
      "loss": 1.5039,
      "step": 190
    },
    {
      "epoch": 1.7363636363636363,
      "grad_norm": 0.4480580985546112,
      "learning_rate": 5.526064699265753e-07,
      "loss": 1.4566,
      "step": 191
    },
    {
      "epoch": 1.7454545454545456,
      "grad_norm": 0.5466722846031189,
      "learning_rate": 4.367965336512403e-07,
      "loss": 1.5203,
      "step": 192
    },
    {
      "epoch": 1.7545454545454544,
      "grad_norm": 0.6187264323234558,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 1.4044,
      "step": 193
    },
    {
      "epoch": 1.7636363636363637,
      "grad_norm": 0.7276005148887634,
      "learning_rate": 2.458548727494292e-07,
      "loss": 1.5041,
      "step": 194
    },
    {
      "epoch": 1.7727272727272727,
      "grad_norm": 0.7174268960952759,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 1.5206,
      "step": 195
    },
    {
      "epoch": 1.7818181818181817,
      "grad_norm": 0.7668031454086304,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 1.2282,
      "step": 196
    },
    {
      "epoch": 1.790909090909091,
      "grad_norm": 0.9456127882003784,
      "learning_rate": 6.150154258476315e-08,
      "loss": 1.2702,
      "step": 197
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.26271384954452515,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 1.6184,
      "step": 198
    },
    {
      "epoch": 1.809090909090909,
      "grad_norm": 0.24971067905426025,
      "learning_rate": 6.834750376549792e-09,
      "loss": 1.5635,
      "step": 199
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 0.2917591631412506,
      "learning_rate": 0.0,
      "loss": 1.5407,
      "step": 200
    },
    {
      "epoch": 1.8181818181818183,
      "eval_loss": 1.566010594367981,
      "eval_runtime": 7.042,
      "eval_samples_per_second": 105.225,
      "eval_steps_per_second": 6.674,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 1.0893434183305134e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}