{
  "best_metric": 0.9076287746429443,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 1.4035087719298245,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007017543859649123,
      "grad_norm": 1.2534143924713135,
      "learning_rate": 1e-05,
      "loss": 1.5052,
      "step": 1
    },
    {
      "epoch": 0.007017543859649123,
      "eval_loss": 2.3536324501037598,
      "eval_runtime": 17.4641,
      "eval_samples_per_second": 13.743,
      "eval_steps_per_second": 3.436,
      "step": 1
    },
    {
      "epoch": 0.014035087719298246,
      "grad_norm": 2.172743797302246,
      "learning_rate": 2e-05,
      "loss": 1.9296,
      "step": 2
    },
    {
      "epoch": 0.021052631578947368,
      "grad_norm": 1.9240020513534546,
      "learning_rate": 3e-05,
      "loss": 2.0409,
      "step": 3
    },
    {
      "epoch": 0.028070175438596492,
      "grad_norm": 1.6464014053344727,
      "learning_rate": 4e-05,
      "loss": 1.9708,
      "step": 4
    },
    {
      "epoch": 0.03508771929824561,
      "grad_norm": 1.621195912361145,
      "learning_rate": 5e-05,
      "loss": 1.8814,
      "step": 5
    },
    {
      "epoch": 0.042105263157894736,
      "grad_norm": 1.298203706741333,
      "learning_rate": 6e-05,
      "loss": 1.7908,
      "step": 6
    },
    {
      "epoch": 0.04912280701754386,
      "grad_norm": 1.1572847366333008,
      "learning_rate": 7e-05,
      "loss": 1.7144,
      "step": 7
    },
    {
      "epoch": 0.056140350877192984,
      "grad_norm": 1.131274938583374,
      "learning_rate": 8e-05,
      "loss": 1.6537,
      "step": 8
    },
    {
      "epoch": 0.06315789473684211,
      "grad_norm": 1.1482822895050049,
      "learning_rate": 9e-05,
      "loss": 1.4986,
      "step": 9
    },
    {
      "epoch": 0.07017543859649122,
      "grad_norm": 1.161393404006958,
      "learning_rate": 0.0001,
      "loss": 1.4802,
      "step": 10
    },
    {
      "epoch": 0.07719298245614035,
      "grad_norm": 1.1775438785552979,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.4473,
      "step": 11
    },
    {
      "epoch": 0.08421052631578947,
      "grad_norm": 1.2146342992782593,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.4546,
      "step": 12
    },
    {
      "epoch": 0.0912280701754386,
      "grad_norm": 1.1088521480560303,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.3589,
      "step": 13
    },
    {
      "epoch": 0.09824561403508772,
      "grad_norm": 1.1477882862091064,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.5166,
      "step": 14
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 1.0061062574386597,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.3804,
      "step": 15
    },
    {
      "epoch": 0.11228070175438597,
      "grad_norm": 0.9471473097801208,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.3575,
      "step": 16
    },
    {
      "epoch": 0.11929824561403508,
      "grad_norm": 1.1224294900894165,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.3399,
      "step": 17
    },
    {
      "epoch": 0.12631578947368421,
      "grad_norm": 1.0143804550170898,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.405,
      "step": 18
    },
    {
      "epoch": 0.13333333333333333,
      "grad_norm": 0.9855953454971313,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.2928,
      "step": 19
    },
    {
      "epoch": 0.14035087719298245,
      "grad_norm": 0.9470274448394775,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.3269,
      "step": 20
    },
    {
      "epoch": 0.14736842105263157,
      "grad_norm": 0.886808454990387,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.174,
      "step": 21
    },
    {
      "epoch": 0.1543859649122807,
      "grad_norm": 1.2386423349380493,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.2925,
      "step": 22
    },
    {
      "epoch": 0.16140350877192983,
      "grad_norm": 1.243969202041626,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.2277,
      "step": 23
    },
    {
      "epoch": 0.16842105263157894,
      "grad_norm": 0.9831477403640747,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.1445,
      "step": 24
    },
    {
      "epoch": 0.17543859649122806,
      "grad_norm": 1.192062497138977,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.3057,
      "step": 25
    },
    {
      "epoch": 0.1824561403508772,
      "grad_norm": 1.0774126052856445,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.1172,
      "step": 26
    },
    {
      "epoch": 0.18947368421052632,
      "grad_norm": 1.175700068473816,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.1333,
      "step": 27
    },
    {
      "epoch": 0.19649122807017544,
      "grad_norm": 1.0634829998016357,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.1582,
      "step": 28
    },
    {
      "epoch": 0.20350877192982456,
      "grad_norm": 1.0939011573791504,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.2174,
      "step": 29
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 1.1425526142120361,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.0679,
      "step": 30
    },
    {
      "epoch": 0.21754385964912282,
      "grad_norm": 1.2740651369094849,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.2954,
      "step": 31
    },
    {
      "epoch": 0.22456140350877193,
      "grad_norm": 1.1120084524154663,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.0927,
      "step": 32
    },
    {
      "epoch": 0.23157894736842105,
      "grad_norm": 1.2857849597930908,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.0326,
      "step": 33
    },
    {
      "epoch": 0.23859649122807017,
      "grad_norm": 1.1726669073104858,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.8581,
      "step": 34
    },
    {
      "epoch": 0.24561403508771928,
      "grad_norm": 1.6155519485473633,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.0291,
      "step": 35
    },
    {
      "epoch": 0.25263157894736843,
      "grad_norm": 1.5612523555755615,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.3342,
      "step": 36
    },
    {
      "epoch": 0.2596491228070175,
      "grad_norm": 1.5053577423095703,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.3751,
      "step": 37
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 1.0807280540466309,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.2875,
      "step": 38
    },
    {
      "epoch": 0.2736842105263158,
      "grad_norm": 0.7876899242401123,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.2533,
      "step": 39
    },
    {
      "epoch": 0.2807017543859649,
      "grad_norm": 0.6304153203964233,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.1544,
      "step": 40
    },
    {
      "epoch": 0.28771929824561404,
      "grad_norm": 0.6947687864303589,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.1314,
      "step": 41
    },
    {
      "epoch": 0.29473684210526313,
      "grad_norm": 0.7577316164970398,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.1655,
      "step": 42
    },
    {
      "epoch": 0.3017543859649123,
      "grad_norm": 0.8332154154777527,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.0858,
      "step": 43
    },
    {
      "epoch": 0.3087719298245614,
      "grad_norm": 0.7522755265235901,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.1915,
      "step": 44
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 0.7094581127166748,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.1053,
      "step": 45
    },
    {
      "epoch": 0.32280701754385965,
      "grad_norm": 0.6133998036384583,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.0306,
      "step": 46
    },
    {
      "epoch": 0.3298245614035088,
      "grad_norm": 0.6958840489387512,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.1278,
      "step": 47
    },
    {
      "epoch": 0.3368421052631579,
      "grad_norm": 0.6898043155670166,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.0137,
      "step": 48
    },
    {
      "epoch": 0.34385964912280703,
      "grad_norm": 0.6915181875228882,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.0956,
      "step": 49
    },
    {
      "epoch": 0.3508771929824561,
      "grad_norm": 0.8360801935195923,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.0467,
      "step": 50
    },
    {
      "epoch": 0.3508771929824561,
      "eval_loss": 1.092663288116455,
      "eval_runtime": 17.9761,
      "eval_samples_per_second": 13.351,
      "eval_steps_per_second": 3.338,
      "step": 50
    },
    {
      "epoch": 0.35789473684210527,
      "grad_norm": 0.8495941758155823,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.1047,
      "step": 51
    },
    {
      "epoch": 0.3649122807017544,
      "grad_norm": 0.810507595539093,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.0814,
      "step": 52
    },
    {
      "epoch": 0.3719298245614035,
      "grad_norm": 0.6672687530517578,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.0052,
      "step": 53
    },
    {
      "epoch": 0.37894736842105264,
      "grad_norm": 0.7475104928016663,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.0324,
      "step": 54
    },
    {
      "epoch": 0.38596491228070173,
      "grad_norm": 0.7777146100997925,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.971,
      "step": 55
    },
    {
      "epoch": 0.3929824561403509,
      "grad_norm": 0.8431249856948853,
      "learning_rate": 8.622126023955446e-05,
      "loss": 1.091,
      "step": 56
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.8101990222930908,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.993,
      "step": 57
    },
    {
      "epoch": 0.4070175438596491,
      "grad_norm": 0.929724931716919,
      "learning_rate": 8.506183921362443e-05,
      "loss": 1.0346,
      "step": 58
    },
    {
      "epoch": 0.41403508771929826,
      "grad_norm": 0.8052439093589783,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.9349,
      "step": 59
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 0.915140688419342,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.0095,
      "step": 60
    },
    {
      "epoch": 0.4280701754385965,
      "grad_norm": 0.9385674595832825,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.0242,
      "step": 61
    },
    {
      "epoch": 0.43508771929824563,
      "grad_norm": 0.903053343296051,
      "learning_rate": 8.262928807620843e-05,
      "loss": 1.0158,
      "step": 62
    },
    {
      "epoch": 0.4421052631578947,
      "grad_norm": 0.900728702545166,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.9395,
      "step": 63
    },
    {
      "epoch": 0.44912280701754387,
      "grad_norm": 0.8996999263763428,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.9317,
      "step": 64
    },
    {
      "epoch": 0.45614035087719296,
      "grad_norm": 1.1214122772216797,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.0497,
      "step": 65
    },
    {
      "epoch": 0.4631578947368421,
      "grad_norm": 0.963810384273529,
      "learning_rate": 8.005405736415126e-05,
      "loss": 1.0173,
      "step": 66
    },
    {
      "epoch": 0.47017543859649125,
      "grad_norm": 0.9837822318077087,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.9198,
      "step": 67
    },
    {
      "epoch": 0.47719298245614034,
      "grad_norm": 1.1001050472259521,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.9345,
      "step": 68
    },
    {
      "epoch": 0.4842105263157895,
      "grad_norm": 1.168784260749817,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.9159,
      "step": 69
    },
    {
      "epoch": 0.49122807017543857,
      "grad_norm": 1.4707549810409546,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.8189,
      "step": 70
    },
    {
      "epoch": 0.4982456140350877,
      "grad_norm": 0.8413581252098083,
      "learning_rate": 7.66515864363997e-05,
      "loss": 1.1741,
      "step": 71
    },
    {
      "epoch": 0.5052631578947369,
      "grad_norm": 0.8746647238731384,
      "learning_rate": 7.594847868906076e-05,
      "loss": 1.1757,
      "step": 72
    },
    {
      "epoch": 0.512280701754386,
      "grad_norm": 0.8882333636283875,
      "learning_rate": 7.52382768867422e-05,
      "loss": 1.1614,
      "step": 73
    },
    {
      "epoch": 0.519298245614035,
      "grad_norm": 0.6879501342773438,
      "learning_rate": 7.452117519152542e-05,
      "loss": 1.0444,
      "step": 74
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 0.6688600182533264,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.0188,
      "step": 75
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.5875242352485657,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.9841,
      "step": 76
    },
    {
      "epoch": 0.5403508771929825,
      "grad_norm": 0.6024107336997986,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.9383,
      "step": 77
    },
    {
      "epoch": 0.5473684210526316,
      "grad_norm": 0.6331109404563904,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.9401,
      "step": 78
    },
    {
      "epoch": 0.5543859649122806,
      "grad_norm": 0.7286727428436279,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.9829,
      "step": 79
    },
    {
      "epoch": 0.5614035087719298,
      "grad_norm": 0.711800754070282,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.074,
      "step": 80
    },
    {
      "epoch": 0.5684210526315789,
      "grad_norm": 0.7032061219215393,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.9458,
      "step": 81
    },
    {
      "epoch": 0.5754385964912281,
      "grad_norm": 0.6800862550735474,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.9177,
      "step": 82
    },
    {
      "epoch": 0.5824561403508772,
      "grad_norm": 0.7012315392494202,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.9998,
      "step": 83
    },
    {
      "epoch": 0.5894736842105263,
      "grad_norm": 0.6711164712905884,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.9011,
      "step": 84
    },
    {
      "epoch": 0.5964912280701754,
      "grad_norm": 0.7472687363624573,
      "learning_rate": 6.623497346023418e-05,
      "loss": 1.0577,
      "step": 85
    },
    {
      "epoch": 0.6035087719298246,
      "grad_norm": 0.681303083896637,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.9537,
      "step": 86
    },
    {
      "epoch": 0.6105263157894737,
      "grad_norm": 0.663417637348175,
      "learning_rate": 6.466250186922325e-05,
      "loss": 1.0518,
      "step": 87
    },
    {
      "epoch": 0.6175438596491228,
      "grad_norm": 0.7229124903678894,
      "learning_rate": 6.387014543809223e-05,
      "loss": 1.0031,
      "step": 88
    },
    {
      "epoch": 0.624561403508772,
      "grad_norm": 0.8156726360321045,
      "learning_rate": 6.307399704769099e-05,
      "loss": 1.028,
      "step": 89
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 0.7930503487586975,
      "learning_rate": 6.227427435703997e-05,
      "loss": 1.0919,
      "step": 90
    },
    {
      "epoch": 0.6385964912280702,
      "grad_norm": 0.7723600268363953,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.9823,
      "step": 91
    },
    {
      "epoch": 0.6456140350877193,
      "grad_norm": 0.7948516011238098,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.9977,
      "step": 92
    },
    {
      "epoch": 0.6526315789473685,
      "grad_norm": 0.8094050884246826,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.9924,
      "step": 93
    },
    {
      "epoch": 0.6596491228070176,
      "grad_norm": 0.8022911548614502,
      "learning_rate": 5.90440267166055e-05,
      "loss": 1.0067,
      "step": 94
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.8208826780319214,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.9652,
      "step": 95
    },
    {
      "epoch": 0.6736842105263158,
      "grad_norm": 0.8704277276992798,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.9403,
      "step": 96
    },
    {
      "epoch": 0.6807017543859649,
      "grad_norm": 0.8088537454605103,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.9538,
      "step": 97
    },
    {
      "epoch": 0.6877192982456141,
      "grad_norm": 0.8382421135902405,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.8948,
      "step": 98
    },
    {
      "epoch": 0.6947368421052632,
      "grad_norm": 0.8086569309234619,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.817,
      "step": 99
    },
    {
      "epoch": 0.7017543859649122,
      "grad_norm": 0.9123827815055847,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.9708,
      "step": 100
    },
    {
      "epoch": 0.7017543859649122,
      "eval_loss": 0.9763481020927429,
      "eval_runtime": 17.9572,
      "eval_samples_per_second": 13.365,
      "eval_steps_per_second": 3.341,
      "step": 100
    },
    {
      "epoch": 0.7087719298245614,
      "grad_norm": 0.9373496770858765,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.8625,
      "step": 101
    },
    {
      "epoch": 0.7157894736842105,
      "grad_norm": 0.9252601265907288,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.837,
      "step": 102
    },
    {
      "epoch": 0.7228070175438597,
      "grad_norm": 0.9916710257530212,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.8396,
      "step": 103
    },
    {
      "epoch": 0.7298245614035088,
      "grad_norm": 1.039979100227356,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.8395,
      "step": 104
    },
    {
      "epoch": 0.7368421052631579,
      "grad_norm": 1.1511530876159668,
      "learning_rate": 5e-05,
      "loss": 0.9004,
      "step": 105
    },
    {
      "epoch": 0.743859649122807,
      "grad_norm": 0.6468256711959839,
      "learning_rate": 4.917330276168208e-05,
      "loss": 1.145,
      "step": 106
    },
    {
      "epoch": 0.7508771929824561,
      "grad_norm": 0.7610668540000916,
      "learning_rate": 4.834683153413459e-05,
      "loss": 1.1162,
      "step": 107
    },
    {
      "epoch": 0.7578947368421053,
      "grad_norm": 0.6794210076332092,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 1.1339,
      "step": 108
    },
    {
      "epoch": 0.7649122807017544,
      "grad_norm": 0.697980523109436,
      "learning_rate": 4.669547078371504e-05,
      "loss": 1.0336,
      "step": 109
    },
    {
      "epoch": 0.7719298245614035,
      "grad_norm": 0.6164118051528931,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.9961,
      "step": 110
    },
    {
      "epoch": 0.7789473684210526,
      "grad_norm": 0.6285886168479919,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.9219,
      "step": 111
    },
    {
      "epoch": 0.7859649122807018,
      "grad_norm": 0.6246762871742249,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.9666,
      "step": 112
    },
    {
      "epoch": 0.7929824561403509,
      "grad_norm": 0.6051075458526611,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.9359,
      "step": 113
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.6134659647941589,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 1.0095,
      "step": 114
    },
    {
      "epoch": 0.8070175438596491,
      "grad_norm": 0.5803300142288208,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.8944,
      "step": 115
    },
    {
      "epoch": 0.8140350877192982,
      "grad_norm": 0.6679065227508545,
      "learning_rate": 4.095597328339452e-05,
      "loss": 1.0066,
      "step": 116
    },
    {
      "epoch": 0.8210526315789474,
      "grad_norm": 0.6148210167884827,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.8775,
      "step": 117
    },
    {
      "epoch": 0.8280701754385965,
      "grad_norm": 0.6846412420272827,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.9164,
      "step": 118
    },
    {
      "epoch": 0.8350877192982457,
      "grad_norm": 0.6519080400466919,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.9535,
      "step": 119
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 0.6708475351333618,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.9434,
      "step": 120
    },
    {
      "epoch": 0.8491228070175438,
      "grad_norm": 0.6707360148429871,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.9237,
      "step": 121
    },
    {
      "epoch": 0.856140350877193,
      "grad_norm": 0.7108855843544006,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.951,
      "step": 122
    },
    {
      "epoch": 0.8631578947368421,
      "grad_norm": 0.6853576302528381,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.976,
      "step": 123
    },
    {
      "epoch": 0.8701754385964913,
      "grad_norm": 0.6899964213371277,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.9665,
      "step": 124
    },
    {
      "epoch": 0.8771929824561403,
      "grad_norm": 0.7322463393211365,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.9188,
      "step": 125
    },
    {
      "epoch": 0.8842105263157894,
      "grad_norm": 0.7695757746696472,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.9111,
      "step": 126
    },
    {
      "epoch": 0.8912280701754386,
      "grad_norm": 0.7958988547325134,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.9095,
      "step": 127
    },
    {
      "epoch": 0.8982456140350877,
      "grad_norm": 0.8245905637741089,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.9467,
      "step": 128
    },
    {
      "epoch": 0.9052631578947369,
      "grad_norm": 0.852338433265686,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.9753,
      "step": 129
    },
    {
      "epoch": 0.9122807017543859,
      "grad_norm": 0.9559686779975891,
      "learning_rate": 2.991522876735154e-05,
      "loss": 1.0218,
      "step": 130
    },
    {
      "epoch": 0.9192982456140351,
      "grad_norm": 0.7618393898010254,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.9331,
      "step": 131
    },
    {
      "epoch": 0.9263157894736842,
      "grad_norm": 0.8673140406608582,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.934,
      "step": 132
    },
    {
      "epoch": 0.9333333333333333,
      "grad_norm": 0.8643515110015869,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.8688,
      "step": 133
    },
    {
      "epoch": 0.9403508771929825,
      "grad_norm": 0.8512769341468811,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.8686,
      "step": 134
    },
    {
      "epoch": 0.9473684210526315,
      "grad_norm": 1.0109984874725342,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.952,
      "step": 135
    },
    {
      "epoch": 0.9543859649122807,
      "grad_norm": 0.8950226902961731,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.7683,
      "step": 136
    },
    {
      "epoch": 0.9614035087719298,
      "grad_norm": 0.8459332585334778,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.8297,
      "step": 137
    },
    {
      "epoch": 0.968421052631579,
      "grad_norm": 1.0293787717819214,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.8902,
      "step": 138
    },
    {
      "epoch": 0.9754385964912281,
      "grad_norm": 0.9704686403274536,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.8104,
      "step": 139
    },
    {
      "epoch": 0.9824561403508771,
      "grad_norm": 1.26128089427948,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.7869,
      "step": 140
    },
    {
      "epoch": 0.9894736842105263,
      "grad_norm": 0.6623982787132263,
      "learning_rate": 2.196424713241637e-05,
      "loss": 1.051,
      "step": 141
    },
    {
      "epoch": 0.9964912280701754,
      "grad_norm": 0.7292494773864746,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.92,
      "step": 142
    },
    {
      "epoch": 1.0035087719298246,
      "grad_norm": 1.3493958711624146,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.4583,
      "step": 143
    },
    {
      "epoch": 1.0105263157894737,
      "grad_norm": 0.4380977749824524,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.8509,
      "step": 144
    },
    {
      "epoch": 1.0175438596491229,
      "grad_norm": 0.5646017789840698,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.9696,
      "step": 145
    },
    {
      "epoch": 1.024561403508772,
      "grad_norm": 0.5136839151382446,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.8997,
      "step": 146
    },
    {
      "epoch": 1.0315789473684212,
      "grad_norm": 0.5556675791740417,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.9231,
      "step": 147
    },
    {
      "epoch": 1.03859649122807,
      "grad_norm": 0.5332583785057068,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.8516,
      "step": 148
    },
    {
      "epoch": 1.0456140350877192,
      "grad_norm": 0.5246683359146118,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.7514,
      "step": 149
    },
    {
      "epoch": 1.0526315789473684,
      "grad_norm": 0.5743148326873779,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.8412,
      "step": 150
    },
    {
      "epoch": 1.0526315789473684,
      "eval_loss": 0.9281483888626099,
      "eval_runtime": 17.9643,
      "eval_samples_per_second": 13.36,
      "eval_steps_per_second": 3.34,
      "step": 150
    },
    {
      "epoch": 1.0596491228070175,
      "grad_norm": 0.5499259233474731,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.7959,
      "step": 151
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.6059480309486389,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.9236,
      "step": 152
    },
    {
      "epoch": 1.0736842105263158,
      "grad_norm": 0.5743237137794495,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.7699,
      "step": 153
    },
    {
      "epoch": 1.080701754385965,
      "grad_norm": 0.5667473673820496,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.8163,
      "step": 154
    },
    {
      "epoch": 1.087719298245614,
      "grad_norm": 0.5733652710914612,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.7968,
      "step": 155
    },
    {
      "epoch": 1.0947368421052632,
      "grad_norm": 0.5713925361633301,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.7238,
      "step": 156
    },
    {
      "epoch": 1.1017543859649124,
      "grad_norm": 0.6577221751213074,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.8864,
      "step": 157
    },
    {
      "epoch": 1.1087719298245613,
      "grad_norm": 0.6452422142028809,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.8557,
      "step": 158
    },
    {
      "epoch": 1.1157894736842104,
      "grad_norm": 0.6251900792121887,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.8445,
      "step": 159
    },
    {
      "epoch": 1.1228070175438596,
      "grad_norm": 0.6201114654541016,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.7963,
      "step": 160
    },
    {
      "epoch": 1.1298245614035087,
      "grad_norm": 0.6169941425323486,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.7736,
      "step": 161
    },
    {
      "epoch": 1.1368421052631579,
      "grad_norm": 0.6466110348701477,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.7778,
      "step": 162
    },
    {
      "epoch": 1.143859649122807,
      "grad_norm": 0.6716749668121338,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.7267,
      "step": 163
    },
    {
      "epoch": 1.1508771929824562,
      "grad_norm": 0.6812232136726379,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.7752,
      "step": 164
    },
    {
      "epoch": 1.1578947368421053,
      "grad_norm": 0.7721582651138306,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.8028,
      "step": 165
    },
    {
      "epoch": 1.1649122807017545,
      "grad_norm": 0.6924811601638794,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.7015,
      "step": 166
    },
    {
      "epoch": 1.1719298245614036,
      "grad_norm": 0.6537291407585144,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.6301,
      "step": 167
    },
    {
      "epoch": 1.1789473684210527,
      "grad_norm": 0.7873263359069824,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.7494,
      "step": 168
    },
    {
      "epoch": 1.1859649122807017,
      "grad_norm": 0.785182535648346,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.7273,
      "step": 169
    },
    {
      "epoch": 1.1929824561403508,
      "grad_norm": 0.8364277482032776,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.8051,
      "step": 170
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.8193267583847046,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.7886,
      "step": 171
    },
    {
      "epoch": 1.207017543859649,
      "grad_norm": 0.8230605125427246,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.6667,
      "step": 172
    },
    {
      "epoch": 1.2140350877192982,
      "grad_norm": 1.0363166332244873,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.7513,
      "step": 173
    },
    {
      "epoch": 1.2210526315789474,
      "grad_norm": 0.9317636489868164,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.7462,
      "step": 174
    },
    {
      "epoch": 1.2280701754385965,
      "grad_norm": 0.9311665892601013,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.5978,
      "step": 175
    },
    {
      "epoch": 1.2350877192982457,
      "grad_norm": 1.0501644611358643,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.5987,
      "step": 176
    },
    {
      "epoch": 1.2421052631578948,
      "grad_norm": 1.2949151992797852,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.6707,
      "step": 177
    },
    {
      "epoch": 1.2491228070175437,
      "grad_norm": 0.8944113254547119,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.7692,
      "step": 178
    },
    {
      "epoch": 1.256140350877193,
      "grad_norm": 0.5296733975410461,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.9933,
      "step": 179
    },
    {
      "epoch": 1.263157894736842,
      "grad_norm": 0.5125278830528259,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.8396,
      "step": 180
    },
    {
      "epoch": 1.2701754385964912,
      "grad_norm": 0.5590841174125671,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.9083,
      "step": 181
    },
    {
      "epoch": 1.2771929824561403,
      "grad_norm": 0.5412476658821106,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.8745,
      "step": 182
    },
    {
      "epoch": 1.2842105263157895,
      "grad_norm": 0.5504629611968994,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.7852,
      "step": 183
    },
    {
      "epoch": 1.2912280701754386,
      "grad_norm": 0.5634346604347229,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.8092,
      "step": 184
    },
    {
      "epoch": 1.2982456140350878,
      "grad_norm": 0.560708224773407,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.7971,
      "step": 185
    },
    {
      "epoch": 1.305263157894737,
      "grad_norm": 0.5519462823867798,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.7858,
      "step": 186
    },
    {
      "epoch": 1.312280701754386,
      "grad_norm": 0.6115373969078064,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.8217,
      "step": 187
    },
    {
      "epoch": 1.3192982456140352,
      "grad_norm": 0.5158211588859558,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.6622,
      "step": 188
    },
    {
      "epoch": 1.3263157894736843,
      "grad_norm": 0.6618140935897827,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.9301,
      "step": 189
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.560624897480011,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.6885,
      "step": 190
    },
    {
      "epoch": 1.3403508771929824,
      "grad_norm": 0.6196048855781555,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.8074,
      "step": 191
    },
    {
      "epoch": 1.3473684210526315,
      "grad_norm": 0.6217392683029175,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.764,
      "step": 192
    },
    {
      "epoch": 1.3543859649122807,
      "grad_norm": 0.6826891899108887,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.8396,
      "step": 193
    },
    {
      "epoch": 1.3614035087719298,
      "grad_norm": 0.6853489875793457,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.7989,
      "step": 194
    },
    {
      "epoch": 1.368421052631579,
      "grad_norm": 0.7113683819770813,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.8386,
      "step": 195
    },
    {
      "epoch": 1.3754385964912281,
      "grad_norm": 0.7370263934135437,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.7918,
      "step": 196
    },
    {
      "epoch": 1.3824561403508773,
      "grad_norm": 0.7088052034378052,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.747,
      "step": 197
    },
    {
      "epoch": 1.3894736842105262,
      "grad_norm": 0.7878530025482178,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.8511,
      "step": 198
    },
    {
      "epoch": 1.3964912280701753,
      "grad_norm": 0.7332770824432373,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.8095,
      "step": 199
    },
    {
      "epoch": 1.4035087719298245,
      "grad_norm": 0.7343062162399292,
      "learning_rate": 0.0,
      "loss": 0.7285,
      "step": 200
    },
    {
      "epoch": 1.4035087719298245,
      "eval_loss": 0.9076287746429443,
      "eval_runtime": 17.9653,
      "eval_samples_per_second": 13.359,
      "eval_steps_per_second": 3.34,
      "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": 2.66764564203307e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}