{
  "best_metric": 0.8852634429931641,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 2.73972602739726,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0136986301369863,
      "grad_norm": 2.3104567527770996,
      "learning_rate": 1e-05,
      "loss": 2.6772,
      "step": 1
    },
    {
      "epoch": 0.0136986301369863,
      "eval_loss": 2.6535723209381104,
      "eval_runtime": 17.3303,
      "eval_samples_per_second": 7.097,
      "eval_steps_per_second": 1.789,
      "step": 1
    },
    {
      "epoch": 0.0273972602739726,
      "grad_norm": 2.2860801219940186,
      "learning_rate": 2e-05,
      "loss": 2.5427,
      "step": 2
    },
    {
      "epoch": 0.0410958904109589,
      "grad_norm": 2.4849393367767334,
      "learning_rate": 3e-05,
      "loss": 2.6223,
      "step": 3
    },
    {
      "epoch": 0.0547945205479452,
      "grad_norm": 1.9940364360809326,
      "learning_rate": 4e-05,
      "loss": 2.4287,
      "step": 4
    },
    {
      "epoch": 0.0684931506849315,
      "grad_norm": 1.7210477590560913,
      "learning_rate": 5e-05,
      "loss": 2.3605,
      "step": 5
    },
    {
      "epoch": 0.0821917808219178,
      "grad_norm": 1.2044246196746826,
      "learning_rate": 6e-05,
      "loss": 2.2256,
      "step": 6
    },
    {
      "epoch": 0.0958904109589041,
      "grad_norm": 0.7198757529258728,
      "learning_rate": 7e-05,
      "loss": 2.0664,
      "step": 7
    },
    {
      "epoch": 0.1095890410958904,
      "grad_norm": 0.5114027261734009,
      "learning_rate": 8e-05,
      "loss": 2.2381,
      "step": 8
    },
    {
      "epoch": 0.1232876712328767,
      "grad_norm": 0.6468356251716614,
      "learning_rate": 9e-05,
      "loss": 2.0742,
      "step": 9
    },
    {
      "epoch": 0.136986301369863,
      "grad_norm": 0.6318015456199646,
      "learning_rate": 0.0001,
      "loss": 1.9805,
      "step": 10
    },
    {
      "epoch": 0.1506849315068493,
      "grad_norm": 0.7080933451652527,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.9232,
      "step": 11
    },
    {
      "epoch": 0.1643835616438356,
      "grad_norm": 0.6762998104095459,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.9994,
      "step": 12
    },
    {
      "epoch": 0.1780821917808219,
      "grad_norm": 0.6594786047935486,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.9786,
      "step": 13
    },
    {
      "epoch": 0.1917808219178082,
      "grad_norm": 0.5222786664962769,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.6868,
      "step": 14
    },
    {
      "epoch": 0.2054794520547945,
      "grad_norm": 0.58636075258255,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.8013,
      "step": 15
    },
    {
      "epoch": 0.2191780821917808,
      "grad_norm": 0.6786454916000366,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.9422,
      "step": 16
    },
    {
      "epoch": 0.2328767123287671,
      "grad_norm": 0.698627769947052,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.8039,
      "step": 17
    },
    {
      "epoch": 0.2465753424657534,
      "grad_norm": 0.8333738446235657,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.7332,
      "step": 18
    },
    {
      "epoch": 0.2602739726027397,
      "grad_norm": 0.5399659276008606,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.6334,
      "step": 19
    },
    {
      "epoch": 0.273972602739726,
      "grad_norm": 0.5942010879516602,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.5734,
      "step": 20
    },
    {
      "epoch": 0.2876712328767123,
      "grad_norm": 0.5469406843185425,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.4613,
      "step": 21
    },
    {
      "epoch": 0.3013698630136986,
      "grad_norm": 0.461607426404953,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.5705,
      "step": 22
    },
    {
      "epoch": 0.3150684931506849,
      "grad_norm": 0.48899999260902405,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.4752,
      "step": 23
    },
    {
      "epoch": 0.3287671232876712,
      "grad_norm": 0.4735804796218872,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.5224,
      "step": 24
    },
    {
      "epoch": 0.3424657534246575,
      "grad_norm": 0.46453773975372314,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.4607,
      "step": 25
    },
    {
      "epoch": 0.3561643835616438,
      "grad_norm": 0.5345879197120667,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.2636,
      "step": 26
    },
    {
      "epoch": 0.3698630136986301,
      "grad_norm": 0.47283685207366943,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.4447,
      "step": 27
    },
    {
      "epoch": 0.3835616438356164,
      "grad_norm": 0.46636468172073364,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.4252,
      "step": 28
    },
    {
      "epoch": 0.3972602739726027,
      "grad_norm": 0.5225064158439636,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.3312,
      "step": 29
    },
    {
      "epoch": 0.410958904109589,
      "grad_norm": 0.5501663684844971,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.2208,
      "step": 30
    },
    {
      "epoch": 0.4246575342465753,
      "grad_norm": 0.566003680229187,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.369,
      "step": 31
    },
    {
      "epoch": 0.4383561643835616,
      "grad_norm": 0.5202441215515137,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.2976,
      "step": 32
    },
    {
      "epoch": 0.4520547945205479,
      "grad_norm": 0.518156886100769,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.2891,
      "step": 33
    },
    {
      "epoch": 0.4657534246575342,
      "grad_norm": 0.6312072277069092,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.2836,
      "step": 34
    },
    {
      "epoch": 0.4794520547945205,
      "grad_norm": 0.6018211841583252,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.3762,
      "step": 35
    },
    {
      "epoch": 0.4931506849315068,
      "grad_norm": 0.7894740104675293,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.3325,
      "step": 36
    },
    {
      "epoch": 0.5068493150684932,
      "grad_norm": 0.5007014870643616,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.3137,
      "step": 37
    },
    {
      "epoch": 0.5205479452054794,
      "grad_norm": 0.4664342403411865,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.2576,
      "step": 38
    },
    {
      "epoch": 0.5342465753424658,
      "grad_norm": 0.5222160816192627,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.2053,
      "step": 39
    },
    {
      "epoch": 0.547945205479452,
      "grad_norm": 0.45446133613586426,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.1862,
      "step": 40
    },
    {
      "epoch": 0.5616438356164384,
      "grad_norm": 0.5213246941566467,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.1884,
      "step": 41
    },
    {
      "epoch": 0.5753424657534246,
      "grad_norm": 0.4332996904850006,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.2503,
      "step": 42
    },
    {
      "epoch": 0.589041095890411,
      "grad_norm": 0.45690229535102844,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.2862,
      "step": 43
    },
    {
      "epoch": 0.6027397260273972,
      "grad_norm": 0.4400925040245056,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.1974,
      "step": 44
    },
    {
      "epoch": 0.6164383561643836,
      "grad_norm": 0.39044520258903503,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.0507,
      "step": 45
    },
    {
      "epoch": 0.6301369863013698,
      "grad_norm": 0.4855286180973053,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.0906,
      "step": 46
    },
    {
      "epoch": 0.6438356164383562,
      "grad_norm": 0.4984034597873688,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.2483,
      "step": 47
    },
    {
      "epoch": 0.6575342465753424,
      "grad_norm": 0.44656309485435486,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.1795,
      "step": 48
    },
    {
      "epoch": 0.6712328767123288,
      "grad_norm": 0.4836941659450531,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.1595,
      "step": 49
    },
    {
      "epoch": 0.684931506849315,
      "grad_norm": 0.4639911949634552,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.0114,
      "step": 50
    },
    {
      "epoch": 0.684931506849315,
      "eval_loss": 1.1611876487731934,
      "eval_runtime": 17.7314,
      "eval_samples_per_second": 6.937,
      "eval_steps_per_second": 1.748,
      "step": 50
    },
    {
      "epoch": 0.6986301369863014,
      "grad_norm": 0.512341320514679,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.3056,
      "step": 51
    },
    {
      "epoch": 0.7123287671232876,
      "grad_norm": 0.5826106071472168,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.4377,
      "step": 52
    },
    {
      "epoch": 0.726027397260274,
      "grad_norm": 0.5555780529975891,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.1425,
      "step": 53
    },
    {
      "epoch": 0.7397260273972602,
      "grad_norm": 0.711355984210968,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.1823,
      "step": 54
    },
    {
      "epoch": 0.7534246575342466,
      "grad_norm": 0.48095622658729553,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.1175,
      "step": 55
    },
    {
      "epoch": 0.7671232876712328,
      "grad_norm": 0.4780822992324829,
      "learning_rate": 8.622126023955446e-05,
      "loss": 1.1418,
      "step": 56
    },
    {
      "epoch": 0.7808219178082192,
      "grad_norm": 0.4301621615886688,
      "learning_rate": 8.564642241456986e-05,
      "loss": 1.037,
      "step": 57
    },
    {
      "epoch": 0.7945205479452054,
      "grad_norm": 0.4613475799560547,
      "learning_rate": 8.506183921362443e-05,
      "loss": 1.1247,
      "step": 58
    },
    {
      "epoch": 0.8082191780821918,
      "grad_norm": 0.4640677273273468,
      "learning_rate": 8.44676704559283e-05,
      "loss": 1.1819,
      "step": 59
    },
    {
      "epoch": 0.821917808219178,
      "grad_norm": 0.4535015821456909,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.1822,
      "step": 60
    },
    {
      "epoch": 0.8356164383561644,
      "grad_norm": 0.43138375878334045,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.0331,
      "step": 61
    },
    {
      "epoch": 0.8493150684931506,
      "grad_norm": 0.4065261483192444,
      "learning_rate": 8.262928807620843e-05,
      "loss": 1.0627,
      "step": 62
    },
    {
      "epoch": 0.863013698630137,
      "grad_norm": 0.4334150552749634,
      "learning_rate": 8.199842702516583e-05,
      "loss": 1.1372,
      "step": 63
    },
    {
      "epoch": 0.8767123287671232,
      "grad_norm": 0.43922698497772217,
      "learning_rate": 8.135881792367686e-05,
      "loss": 1.1841,
      "step": 64
    },
    {
      "epoch": 0.8904109589041096,
      "grad_norm": 0.4033384621143341,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.0808,
      "step": 65
    },
    {
      "epoch": 0.9041095890410958,
      "grad_norm": 0.4910394847393036,
      "learning_rate": 8.005405736415126e-05,
      "loss": 1.0448,
      "step": 66
    },
    {
      "epoch": 0.9178082191780822,
      "grad_norm": 0.42739400267601013,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.0965,
      "step": 67
    },
    {
      "epoch": 0.9315068493150684,
      "grad_norm": 0.41515880823135376,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.9814,
      "step": 68
    },
    {
      "epoch": 0.9452054794520548,
      "grad_norm": 0.4886678159236908,
      "learning_rate": 7.803575286758364e-05,
      "loss": 1.0774,
      "step": 69
    },
    {
      "epoch": 0.958904109589041,
      "grad_norm": 0.5378843545913696,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.1657,
      "step": 70
    },
    {
      "epoch": 0.9726027397260274,
      "grad_norm": 0.6070383191108704,
      "learning_rate": 7.66515864363997e-05,
      "loss": 1.0322,
      "step": 71
    },
    {
      "epoch": 0.9863013698630136,
      "grad_norm": 0.7307769060134888,
      "learning_rate": 7.594847868906076e-05,
      "loss": 1.0442,
      "step": 72
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.5021775960922241,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.9663,
      "step": 73
    },
    {
      "epoch": 1.0136986301369864,
      "grad_norm": 0.4482825994491577,
      "learning_rate": 7.452117519152542e-05,
      "loss": 1.0233,
      "step": 74
    },
    {
      "epoch": 1.0273972602739727,
      "grad_norm": 0.5086010694503784,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.0217,
      "step": 75
    },
    {
      "epoch": 1.0410958904109588,
      "grad_norm": 0.4074973165988922,
      "learning_rate": 7.30670581489344e-05,
      "loss": 1.0699,
      "step": 76
    },
    {
      "epoch": 1.0547945205479452,
      "grad_norm": 0.4410340189933777,
      "learning_rate": 7.233044034264034e-05,
      "loss": 1.0412,
      "step": 77
    },
    {
      "epoch": 1.0684931506849316,
      "grad_norm": 0.4779570400714874,
      "learning_rate": 7.158771761692464e-05,
      "loss": 1.0199,
      "step": 78
    },
    {
      "epoch": 1.0821917808219177,
      "grad_norm": 0.40746673941612244,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.8661,
      "step": 79
    },
    {
      "epoch": 1.095890410958904,
      "grad_norm": 0.4582931101322174,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.0316,
      "step": 80
    },
    {
      "epoch": 1.1095890410958904,
      "grad_norm": 0.4575212299823761,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.9536,
      "step": 81
    },
    {
      "epoch": 1.1232876712328768,
      "grad_norm": 0.44885629415512085,
      "learning_rate": 6.855986244591104e-05,
      "loss": 1.0879,
      "step": 82
    },
    {
      "epoch": 1.1369863013698631,
      "grad_norm": 0.4383758008480072,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.8652,
      "step": 83
    },
    {
      "epoch": 1.1506849315068493,
      "grad_norm": 0.44274815917015076,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.9339,
      "step": 84
    },
    {
      "epoch": 1.1643835616438356,
      "grad_norm": 0.4281717836856842,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.9946,
      "step": 85
    },
    {
      "epoch": 1.178082191780822,
      "grad_norm": 0.44562020897865295,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.8694,
      "step": 86
    },
    {
      "epoch": 1.191780821917808,
      "grad_norm": 0.4684397578239441,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.8661,
      "step": 87
    },
    {
      "epoch": 1.2054794520547945,
      "grad_norm": 0.5205891132354736,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.8513,
      "step": 88
    },
    {
      "epoch": 1.2191780821917808,
      "grad_norm": 0.46425750851631165,
      "learning_rate": 6.307399704769099e-05,
      "loss": 1.0054,
      "step": 89
    },
    {
      "epoch": 1.2328767123287672,
      "grad_norm": 0.5829333066940308,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.8968,
      "step": 90
    },
    {
      "epoch": 1.2465753424657535,
      "grad_norm": 0.6800022125244141,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.8185,
      "step": 91
    },
    {
      "epoch": 1.2602739726027397,
      "grad_norm": 0.5547052025794983,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.9072,
      "step": 92
    },
    {
      "epoch": 1.273972602739726,
      "grad_norm": 0.5414283275604248,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.9893,
      "step": 93
    },
    {
      "epoch": 1.2876712328767124,
      "grad_norm": 0.5985580086708069,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.8959,
      "step": 94
    },
    {
      "epoch": 1.3013698630136985,
      "grad_norm": 0.43421244621276855,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.8962,
      "step": 95
    },
    {
      "epoch": 1.3150684931506849,
      "grad_norm": 0.4751519560813904,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.9721,
      "step": 96
    },
    {
      "epoch": 1.3287671232876712,
      "grad_norm": 0.4949586093425751,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.851,
      "step": 97
    },
    {
      "epoch": 1.3424657534246576,
      "grad_norm": 0.443632572889328,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.8569,
      "step": 98
    },
    {
      "epoch": 1.356164383561644,
      "grad_norm": 0.4481355547904968,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.9008,
      "step": 99
    },
    {
      "epoch": 1.36986301369863,
      "grad_norm": 0.4246158301830292,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.9007,
      "step": 100
    },
    {
      "epoch": 1.36986301369863,
      "eval_loss": 0.9667438268661499,
      "eval_runtime": 17.7104,
      "eval_samples_per_second": 6.945,
      "eval_steps_per_second": 1.75,
      "step": 100
    },
    {
      "epoch": 1.3835616438356164,
      "grad_norm": 0.4706757962703705,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.921,
      "step": 101
    },
    {
      "epoch": 1.3972602739726028,
      "grad_norm": 0.44695258140563965,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.8156,
      "step": 102
    },
    {
      "epoch": 1.410958904109589,
      "grad_norm": 0.4904194176197052,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.9468,
      "step": 103
    },
    {
      "epoch": 1.4246575342465753,
      "grad_norm": 0.4590471386909485,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.7876,
      "step": 104
    },
    {
      "epoch": 1.4383561643835616,
      "grad_norm": 0.4899277091026306,
      "learning_rate": 5e-05,
      "loss": 0.7743,
      "step": 105
    },
    {
      "epoch": 1.452054794520548,
      "grad_norm": 0.6832799315452576,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.9999,
      "step": 106
    },
    {
      "epoch": 1.4657534246575343,
      "grad_norm": 0.5903638601303101,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.9089,
      "step": 107
    },
    {
      "epoch": 1.4794520547945205,
      "grad_norm": 0.6132621765136719,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.9061,
      "step": 108
    },
    {
      "epoch": 1.4931506849315068,
      "grad_norm": 0.8069959878921509,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.8017,
      "step": 109
    },
    {
      "epoch": 1.5068493150684932,
      "grad_norm": 0.4573930501937866,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 1.0055,
      "step": 110
    },
    {
      "epoch": 1.5205479452054793,
      "grad_norm": 0.446062296628952,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.9394,
      "step": 111
    },
    {
      "epoch": 1.5342465753424657,
      "grad_norm": 0.5781521797180176,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.8688,
      "step": 112
    },
    {
      "epoch": 1.547945205479452,
      "grad_norm": 0.5024420022964478,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.9995,
      "step": 113
    },
    {
      "epoch": 1.5616438356164384,
      "grad_norm": 0.4697863459587097,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.9577,
      "step": 114
    },
    {
      "epoch": 1.5753424657534247,
      "grad_norm": 0.47331348061561584,
      "learning_rate": 4.17702704859633e-05,
      "loss": 1.0023,
      "step": 115
    },
    {
      "epoch": 1.589041095890411,
      "grad_norm": 0.4437616765499115,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.8376,
      "step": 116
    },
    {
      "epoch": 1.6027397260273972,
      "grad_norm": 0.43482112884521484,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.9088,
      "step": 117
    },
    {
      "epoch": 1.6164383561643836,
      "grad_norm": 0.41529685258865356,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.9271,
      "step": 118
    },
    {
      "epoch": 1.6301369863013697,
      "grad_norm": 0.4500505328178406,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.9108,
      "step": 119
    },
    {
      "epoch": 1.643835616438356,
      "grad_norm": 0.42425259947776794,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.8784,
      "step": 120
    },
    {
      "epoch": 1.6575342465753424,
      "grad_norm": 0.4351794123649597,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.8761,
      "step": 121
    },
    {
      "epoch": 1.6712328767123288,
      "grad_norm": 0.4875510632991791,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.9418,
      "step": 122
    },
    {
      "epoch": 1.6849315068493151,
      "grad_norm": 0.468164324760437,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.7464,
      "step": 123
    },
    {
      "epoch": 1.6986301369863015,
      "grad_norm": 0.5441304445266724,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.912,
      "step": 124
    },
    {
      "epoch": 1.7123287671232876,
      "grad_norm": 0.6000600457191467,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.917,
      "step": 125
    },
    {
      "epoch": 1.726027397260274,
      "grad_norm": 0.5635849237442017,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.7562,
      "step": 126
    },
    {
      "epoch": 1.7397260273972601,
      "grad_norm": 0.7503162026405334,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.7748,
      "step": 127
    },
    {
      "epoch": 1.7534246575342465,
      "grad_norm": 0.5164412260055542,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.9248,
      "step": 128
    },
    {
      "epoch": 1.7671232876712328,
      "grad_norm": 0.5084578990936279,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.8714,
      "step": 129
    },
    {
      "epoch": 1.7808219178082192,
      "grad_norm": 0.4800652265548706,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.9039,
      "step": 130
    },
    {
      "epoch": 1.7945205479452055,
      "grad_norm": 0.46519795060157776,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.8373,
      "step": 131
    },
    {
      "epoch": 1.808219178082192,
      "grad_norm": 0.495684951543808,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.9882,
      "step": 132
    },
    {
      "epoch": 1.821917808219178,
      "grad_norm": 0.4558713436126709,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.8209,
      "step": 133
    },
    {
      "epoch": 1.8356164383561644,
      "grad_norm": 0.45472729206085205,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.7999,
      "step": 134
    },
    {
      "epoch": 1.8493150684931505,
      "grad_norm": 0.4365823268890381,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.8152,
      "step": 135
    },
    {
      "epoch": 1.8630136986301369,
      "grad_norm": 0.48378491401672363,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.8732,
      "step": 136
    },
    {
      "epoch": 1.8767123287671232,
      "grad_norm": 0.4269355833530426,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.8344,
      "step": 137
    },
    {
      "epoch": 1.8904109589041096,
      "grad_norm": 0.4657435119152069,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.8597,
      "step": 138
    },
    {
      "epoch": 1.904109589041096,
      "grad_norm": 0.43430280685424805,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.8464,
      "step": 139
    },
    {
      "epoch": 1.9178082191780823,
      "grad_norm": 0.46137768030166626,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.8788,
      "step": 140
    },
    {
      "epoch": 1.9315068493150684,
      "grad_norm": 0.46057605743408203,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.8454,
      "step": 141
    },
    {
      "epoch": 1.9452054794520548,
      "grad_norm": 0.45767173171043396,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.8869,
      "step": 142
    },
    {
      "epoch": 1.958904109589041,
      "grad_norm": 0.6618921160697937,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.9462,
      "step": 143
    },
    {
      "epoch": 1.9726027397260273,
      "grad_norm": 0.5900852084159851,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.8091,
      "step": 144
    },
    {
      "epoch": 1.9863013698630136,
      "grad_norm": 0.7364968657493591,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.7941,
      "step": 145
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.512842059135437,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.8132,
      "step": 146
    },
    {
      "epoch": 2.0136986301369864,
      "grad_norm": 0.42484575510025024,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.7998,
      "step": 147
    },
    {
      "epoch": 2.0273972602739727,
      "grad_norm": 0.458027184009552,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.8505,
      "step": 148
    },
    {
      "epoch": 2.041095890410959,
      "grad_norm": 0.458528071641922,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.8125,
      "step": 149
    },
    {
      "epoch": 2.0547945205479454,
      "grad_norm": 0.45877528190612793,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.7932,
      "step": 150
    },
    {
      "epoch": 2.0547945205479454,
      "eval_loss": 0.8967676162719727,
      "eval_runtime": 17.7245,
      "eval_samples_per_second": 6.94,
      "eval_steps_per_second": 1.749,
      "step": 150
    },
    {
      "epoch": 2.0684931506849313,
      "grad_norm": 0.4684918224811554,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.9385,
      "step": 151
    },
    {
      "epoch": 2.0821917808219177,
      "grad_norm": 0.4085583984851837,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.8107,
      "step": 152
    },
    {
      "epoch": 2.095890410958904,
      "grad_norm": 0.4363419711589813,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.8901,
      "step": 153
    },
    {
      "epoch": 2.1095890410958904,
      "grad_norm": 0.4404650032520294,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.8955,
      "step": 154
    },
    {
      "epoch": 2.1232876712328768,
      "grad_norm": 0.40605801343917847,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.7995,
      "step": 155
    },
    {
      "epoch": 2.136986301369863,
      "grad_norm": 0.3902886211872101,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.6817,
      "step": 156
    },
    {
      "epoch": 2.1506849315068495,
      "grad_norm": 0.39264345169067383,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.7877,
      "step": 157
    },
    {
      "epoch": 2.1643835616438354,
      "grad_norm": 0.38682812452316284,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.7807,
      "step": 158
    },
    {
      "epoch": 2.1780821917808217,
      "grad_norm": 0.4562668800354004,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.8809,
      "step": 159
    },
    {
      "epoch": 2.191780821917808,
      "grad_norm": 0.3981066048145294,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.7346,
      "step": 160
    },
    {
      "epoch": 2.2054794520547945,
      "grad_norm": 0.46391740441322327,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.7966,
      "step": 161
    },
    {
      "epoch": 2.219178082191781,
      "grad_norm": 0.5633515119552612,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.7696,
      "step": 162
    },
    {
      "epoch": 2.232876712328767,
      "grad_norm": 0.5778986215591431,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.7406,
      "step": 163
    },
    {
      "epoch": 2.2465753424657535,
      "grad_norm": 0.7640504837036133,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.6598,
      "step": 164
    },
    {
      "epoch": 2.26027397260274,
      "grad_norm": 0.4655100703239441,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.775,
      "step": 165
    },
    {
      "epoch": 2.2739726027397262,
      "grad_norm": 0.4217069149017334,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.7851,
      "step": 166
    },
    {
      "epoch": 2.287671232876712,
      "grad_norm": 0.45443060994148254,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.8334,
      "step": 167
    },
    {
      "epoch": 2.3013698630136985,
      "grad_norm": 0.4881836771965027,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.8109,
      "step": 168
    },
    {
      "epoch": 2.315068493150685,
      "grad_norm": 0.3960385322570801,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.7021,
      "step": 169
    },
    {
      "epoch": 2.328767123287671,
      "grad_norm": 0.4290691614151001,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.8202,
      "step": 170
    },
    {
      "epoch": 2.3424657534246576,
      "grad_norm": 0.45308971405029297,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.7751,
      "step": 171
    },
    {
      "epoch": 2.356164383561644,
      "grad_norm": 0.4518820345401764,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.7705,
      "step": 172
    },
    {
      "epoch": 2.3698630136986303,
      "grad_norm": 0.47027093172073364,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.8866,
      "step": 173
    },
    {
      "epoch": 2.383561643835616,
      "grad_norm": 0.3881768584251404,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.7596,
      "step": 174
    },
    {
      "epoch": 2.3972602739726026,
      "grad_norm": 0.4463714063167572,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.8111,
      "step": 175
    },
    {
      "epoch": 2.410958904109589,
      "grad_norm": 0.4486948549747467,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.8752,
      "step": 176
    },
    {
      "epoch": 2.4246575342465753,
      "grad_norm": 0.4119676947593689,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.6728,
      "step": 177
    },
    {
      "epoch": 2.4383561643835616,
      "grad_norm": 0.6820387244224548,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.7223,
      "step": 178
    },
    {
      "epoch": 2.452054794520548,
      "grad_norm": 0.4337317943572998,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.743,
      "step": 179
    },
    {
      "epoch": 2.4657534246575343,
      "grad_norm": 0.5609345436096191,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.9684,
      "step": 180
    },
    {
      "epoch": 2.4794520547945207,
      "grad_norm": 0.5748194456100464,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.6644,
      "step": 181
    },
    {
      "epoch": 2.493150684931507,
      "grad_norm": 0.7168641090393066,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.6977,
      "step": 182
    },
    {
      "epoch": 2.506849315068493,
      "grad_norm": 0.4464932978153229,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.8468,
      "step": 183
    },
    {
      "epoch": 2.5205479452054793,
      "grad_norm": 0.39643359184265137,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.7687,
      "step": 184
    },
    {
      "epoch": 2.5342465753424657,
      "grad_norm": 0.39493218064308167,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.8325,
      "step": 185
    },
    {
      "epoch": 2.547945205479452,
      "grad_norm": 0.426866739988327,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.9032,
      "step": 186
    },
    {
      "epoch": 2.5616438356164384,
      "grad_norm": 0.4211372137069702,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.8924,
      "step": 187
    },
    {
      "epoch": 2.5753424657534247,
      "grad_norm": 0.42485058307647705,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.857,
      "step": 188
    },
    {
      "epoch": 2.589041095890411,
      "grad_norm": 0.396638423204422,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.7824,
      "step": 189
    },
    {
      "epoch": 2.602739726027397,
      "grad_norm": 0.3970295190811157,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.8303,
      "step": 190
    },
    {
      "epoch": 2.616438356164384,
      "grad_norm": 0.4068600833415985,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.766,
      "step": 191
    },
    {
      "epoch": 2.6301369863013697,
      "grad_norm": 0.42520228028297424,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.7813,
      "step": 192
    },
    {
      "epoch": 2.643835616438356,
      "grad_norm": 0.41068243980407715,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.7711,
      "step": 193
    },
    {
      "epoch": 2.6575342465753424,
      "grad_norm": 0.4389426112174988,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.8603,
      "step": 194
    },
    {
      "epoch": 2.671232876712329,
      "grad_norm": 0.45316433906555176,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.7813,
      "step": 195
    },
    {
      "epoch": 2.684931506849315,
      "grad_norm": 0.44930869340896606,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.6417,
      "step": 196
    },
    {
      "epoch": 2.6986301369863015,
      "grad_norm": 0.47548985481262207,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.7268,
      "step": 197
    },
    {
      "epoch": 2.712328767123288,
      "grad_norm": 0.46080678701400757,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.6835,
      "step": 198
    },
    {
      "epoch": 2.7260273972602738,
      "grad_norm": 0.5882464647293091,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.7656,
      "step": 199
    },
    {
      "epoch": 2.73972602739726,
      "grad_norm": 0.6079519987106323,
      "learning_rate": 0.0,
      "loss": 0.6355,
      "step": 200
    },
    {
      "epoch": 2.73972602739726,
      "eval_loss": 0.8852634429931641,
      "eval_runtime": 17.6905,
      "eval_samples_per_second": 6.953,
      "eval_steps_per_second": 1.752,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.495599768849613e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}