{
  "best_metric": 1.1419742107391357,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.02711864406779661,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00013559322033898305,
      "grad_norm": 0.3472871780395508,
      "learning_rate": 1e-05,
      "loss": 1.104,
      "step": 1
    },
    {
      "epoch": 0.00013559322033898305,
      "eval_loss": 1.4093705415725708,
      "eval_runtime": 164.8529,
      "eval_samples_per_second": 75.346,
      "eval_steps_per_second": 18.841,
      "step": 1
    },
    {
      "epoch": 0.0002711864406779661,
      "grad_norm": 0.30674368143081665,
      "learning_rate": 2e-05,
      "loss": 1.2232,
      "step": 2
    },
    {
      "epoch": 0.00040677966101694915,
      "grad_norm": 0.38134491443634033,
      "learning_rate": 3e-05,
      "loss": 1.1561,
      "step": 3
    },
    {
      "epoch": 0.0005423728813559322,
      "grad_norm": 0.2955525815486908,
      "learning_rate": 4e-05,
      "loss": 1.1297,
      "step": 4
    },
    {
      "epoch": 0.0006779661016949153,
      "grad_norm": 0.28371119499206543,
      "learning_rate": 5e-05,
      "loss": 1.2161,
      "step": 5
    },
    {
      "epoch": 0.0008135593220338983,
      "grad_norm": 0.32533058524131775,
      "learning_rate": 6e-05,
      "loss": 1.1884,
      "step": 6
    },
    {
      "epoch": 0.0009491525423728814,
      "grad_norm": 0.2998424768447876,
      "learning_rate": 7e-05,
      "loss": 1.1351,
      "step": 7
    },
    {
      "epoch": 0.0010847457627118644,
      "grad_norm": 0.28467750549316406,
      "learning_rate": 8e-05,
      "loss": 1.1934,
      "step": 8
    },
    {
      "epoch": 0.0012203389830508474,
      "grad_norm": 0.25154194235801697,
      "learning_rate": 9e-05,
      "loss": 1.2641,
      "step": 9
    },
    {
      "epoch": 0.0013559322033898306,
      "grad_norm": 0.24231034517288208,
      "learning_rate": 0.0001,
      "loss": 1.1547,
      "step": 10
    },
    {
      "epoch": 0.0014915254237288136,
      "grad_norm": 0.3205479383468628,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.2752,
      "step": 11
    },
    {
      "epoch": 0.0016271186440677966,
      "grad_norm": 0.3421994149684906,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.166,
      "step": 12
    },
    {
      "epoch": 0.0017627118644067796,
      "grad_norm": 0.2776763439178467,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.1639,
      "step": 13
    },
    {
      "epoch": 0.0018983050847457628,
      "grad_norm": 0.3790736794471741,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.2754,
      "step": 14
    },
    {
      "epoch": 0.002033898305084746,
      "grad_norm": 0.36936354637145996,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.0804,
      "step": 15
    },
    {
      "epoch": 0.002169491525423729,
      "grad_norm": 0.3711797595024109,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.2593,
      "step": 16
    },
    {
      "epoch": 0.0023050847457627118,
      "grad_norm": 0.34369412064552307,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.2021,
      "step": 17
    },
    {
      "epoch": 0.0024406779661016948,
      "grad_norm": 0.3344467580318451,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.3289,
      "step": 18
    },
    {
      "epoch": 0.0025762711864406778,
      "grad_norm": 0.3132745623588562,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.2519,
      "step": 19
    },
    {
      "epoch": 0.002711864406779661,
      "grad_norm": 0.2732485830783844,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.1452,
      "step": 20
    },
    {
      "epoch": 0.002847457627118644,
      "grad_norm": 0.2935069501399994,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.2532,
      "step": 21
    },
    {
      "epoch": 0.002983050847457627,
      "grad_norm": 0.30393484234809875,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.2879,
      "step": 22
    },
    {
      "epoch": 0.00311864406779661,
      "grad_norm": 0.3036266565322876,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.3877,
      "step": 23
    },
    {
      "epoch": 0.003254237288135593,
      "grad_norm": 0.31354832649230957,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.3247,
      "step": 24
    },
    {
      "epoch": 0.003389830508474576,
      "grad_norm": 0.2824953496456146,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.2761,
      "step": 25
    },
    {
      "epoch": 0.003525423728813559,
      "grad_norm": 0.30284231901168823,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.2901,
      "step": 26
    },
    {
      "epoch": 0.003661016949152542,
      "grad_norm": 0.30390840768814087,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.3624,
      "step": 27
    },
    {
      "epoch": 0.0037966101694915256,
      "grad_norm": 0.28138330578804016,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.2799,
      "step": 28
    },
    {
      "epoch": 0.003932203389830509,
      "grad_norm": 0.28392496705055237,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.2906,
      "step": 29
    },
    {
      "epoch": 0.004067796610169492,
      "grad_norm": 0.2893733084201813,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.3301,
      "step": 30
    },
    {
      "epoch": 0.004203389830508475,
      "grad_norm": 0.291888028383255,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.2995,
      "step": 31
    },
    {
      "epoch": 0.004338983050847458,
      "grad_norm": 0.28934580087661743,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.3089,
      "step": 32
    },
    {
      "epoch": 0.0044745762711864406,
      "grad_norm": 0.31524914503097534,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.2878,
      "step": 33
    },
    {
      "epoch": 0.0046101694915254236,
      "grad_norm": 0.29256364703178406,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.2796,
      "step": 34
    },
    {
      "epoch": 0.0047457627118644066,
      "grad_norm": 0.30874279141426086,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.3537,
      "step": 35
    },
    {
      "epoch": 0.0048813559322033895,
      "grad_norm": 0.3112640976905823,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.1915,
      "step": 36
    },
    {
      "epoch": 0.0050169491525423725,
      "grad_norm": 0.3552054464817047,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.4184,
      "step": 37
    },
    {
      "epoch": 0.0051525423728813555,
      "grad_norm": 0.2998238801956177,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.3364,
      "step": 38
    },
    {
      "epoch": 0.005288135593220339,
      "grad_norm": 0.2989037334918976,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.1257,
      "step": 39
    },
    {
      "epoch": 0.005423728813559322,
      "grad_norm": 0.3198997378349304,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.2587,
      "step": 40
    },
    {
      "epoch": 0.005559322033898305,
      "grad_norm": 0.35159972310066223,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.3514,
      "step": 41
    },
    {
      "epoch": 0.005694915254237288,
      "grad_norm": 0.37372180819511414,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.4254,
      "step": 42
    },
    {
      "epoch": 0.005830508474576271,
      "grad_norm": 0.3670232594013214,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.3645,
      "step": 43
    },
    {
      "epoch": 0.005966101694915254,
      "grad_norm": 0.34875598549842834,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.2866,
      "step": 44
    },
    {
      "epoch": 0.006101694915254237,
      "grad_norm": 0.34978166222572327,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.2584,
      "step": 45
    },
    {
      "epoch": 0.00623728813559322,
      "grad_norm": 0.35276463627815247,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.3766,
      "step": 46
    },
    {
      "epoch": 0.006372881355932203,
      "grad_norm": 0.4063233435153961,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.4154,
      "step": 47
    },
    {
      "epoch": 0.006508474576271186,
      "grad_norm": 0.4501355290412903,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.4348,
      "step": 48
    },
    {
      "epoch": 0.006644067796610169,
      "grad_norm": 0.4426709711551666,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.2287,
      "step": 49
    },
    {
      "epoch": 0.006779661016949152,
      "grad_norm": 0.5209242701530457,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.493,
      "step": 50
    },
    {
      "epoch": 0.006779661016949152,
      "eval_loss": 1.2198525667190552,
      "eval_runtime": 164.5627,
      "eval_samples_per_second": 75.479,
      "eval_steps_per_second": 18.874,
      "step": 50
    },
    {
      "epoch": 0.006915254237288135,
      "grad_norm": 0.48591750860214233,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.2682,
      "step": 51
    },
    {
      "epoch": 0.007050847457627118,
      "grad_norm": 0.4839187264442444,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.1605,
      "step": 52
    },
    {
      "epoch": 0.007186440677966101,
      "grad_norm": 0.44870924949645996,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.0242,
      "step": 53
    },
    {
      "epoch": 0.007322033898305084,
      "grad_norm": 0.38885319232940674,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.2278,
      "step": 54
    },
    {
      "epoch": 0.007457627118644068,
      "grad_norm": 0.31374967098236084,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.0649,
      "step": 55
    },
    {
      "epoch": 0.007593220338983051,
      "grad_norm": 0.27050304412841797,
      "learning_rate": 8.622126023955446e-05,
      "loss": 1.0684,
      "step": 56
    },
    {
      "epoch": 0.007728813559322034,
      "grad_norm": 0.28226444125175476,
      "learning_rate": 8.564642241456986e-05,
      "loss": 1.1444,
      "step": 57
    },
    {
      "epoch": 0.007864406779661017,
      "grad_norm": 0.2476905882358551,
      "learning_rate": 8.506183921362443e-05,
      "loss": 1.1709,
      "step": 58
    },
    {
      "epoch": 0.008,
      "grad_norm": 0.31584158539772034,
      "learning_rate": 8.44676704559283e-05,
      "loss": 1.3058,
      "step": 59
    },
    {
      "epoch": 0.008135593220338983,
      "grad_norm": 0.263445645570755,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.0456,
      "step": 60
    },
    {
      "epoch": 0.008271186440677966,
      "grad_norm": 0.28080058097839355,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.0805,
      "step": 61
    },
    {
      "epoch": 0.00840677966101695,
      "grad_norm": 0.2922201454639435,
      "learning_rate": 8.262928807620843e-05,
      "loss": 1.0945,
      "step": 62
    },
    {
      "epoch": 0.008542372881355932,
      "grad_norm": 0.2739388644695282,
      "learning_rate": 8.199842702516583e-05,
      "loss": 1.0434,
      "step": 63
    },
    {
      "epoch": 0.008677966101694915,
      "grad_norm": 0.31018057465553284,
      "learning_rate": 8.135881792367686e-05,
      "loss": 1.393,
      "step": 64
    },
    {
      "epoch": 0.008813559322033898,
      "grad_norm": 0.2703317403793335,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.122,
      "step": 65
    },
    {
      "epoch": 0.008949152542372881,
      "grad_norm": 0.26033544540405273,
      "learning_rate": 8.005405736415126e-05,
      "loss": 1.2042,
      "step": 66
    },
    {
      "epoch": 0.009084745762711864,
      "grad_norm": 0.26181912422180176,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.1269,
      "step": 67
    },
    {
      "epoch": 0.009220338983050847,
      "grad_norm": 0.2466246336698532,
      "learning_rate": 7.871643313414718e-05,
      "loss": 1.1736,
      "step": 68
    },
    {
      "epoch": 0.00935593220338983,
      "grad_norm": 0.23977535963058472,
      "learning_rate": 7.803575286758364e-05,
      "loss": 1.0932,
      "step": 69
    },
    {
      "epoch": 0.009491525423728813,
      "grad_norm": 0.2876574695110321,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.2278,
      "step": 70
    },
    {
      "epoch": 0.009627118644067796,
      "grad_norm": 0.2640303373336792,
      "learning_rate": 7.66515864363997e-05,
      "loss": 1.0888,
      "step": 71
    },
    {
      "epoch": 0.009762711864406779,
      "grad_norm": 0.31466183066368103,
      "learning_rate": 7.594847868906076e-05,
      "loss": 1.1862,
      "step": 72
    },
    {
      "epoch": 0.009898305084745762,
      "grad_norm": 0.29163795709609985,
      "learning_rate": 7.52382768867422e-05,
      "loss": 1.1289,
      "step": 73
    },
    {
      "epoch": 0.010033898305084745,
      "grad_norm": 0.30906954407691956,
      "learning_rate": 7.452117519152542e-05,
      "loss": 1.2392,
      "step": 74
    },
    {
      "epoch": 0.010169491525423728,
      "grad_norm": 0.26980963349342346,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.2236,
      "step": 75
    },
    {
      "epoch": 0.010305084745762711,
      "grad_norm": 0.29879602789878845,
      "learning_rate": 7.30670581489344e-05,
      "loss": 1.2715,
      "step": 76
    },
    {
      "epoch": 0.010440677966101694,
      "grad_norm": 0.28606700897216797,
      "learning_rate": 7.233044034264034e-05,
      "loss": 1.1628,
      "step": 77
    },
    {
      "epoch": 0.010576271186440679,
      "grad_norm": 0.2949655055999756,
      "learning_rate": 7.158771761692464e-05,
      "loss": 1.111,
      "step": 78
    },
    {
      "epoch": 0.010711864406779662,
      "grad_norm": 0.298816978931427,
      "learning_rate": 7.083909302476453e-05,
      "loss": 1.2531,
      "step": 79
    },
    {
      "epoch": 0.010847457627118645,
      "grad_norm": 0.310584157705307,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.4387,
      "step": 80
    },
    {
      "epoch": 0.010983050847457628,
      "grad_norm": 0.2809377610683441,
      "learning_rate": 6.932495846462261e-05,
      "loss": 1.3546,
      "step": 81
    },
    {
      "epoch": 0.01111864406779661,
      "grad_norm": 0.2834746241569519,
      "learning_rate": 6.855986244591104e-05,
      "loss": 1.168,
      "step": 82
    },
    {
      "epoch": 0.011254237288135594,
      "grad_norm": 0.32055801153182983,
      "learning_rate": 6.778969234612584e-05,
      "loss": 1.2911,
      "step": 83
    },
    {
      "epoch": 0.011389830508474577,
      "grad_norm": 0.2884746789932251,
      "learning_rate": 6.701465872208216e-05,
      "loss": 1.1259,
      "step": 84
    },
    {
      "epoch": 0.01152542372881356,
      "grad_norm": 0.31328436732292175,
      "learning_rate": 6.623497346023418e-05,
      "loss": 1.2497,
      "step": 85
    },
    {
      "epoch": 0.011661016949152543,
      "grad_norm": 0.32582178711891174,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.2957,
      "step": 86
    },
    {
      "epoch": 0.011796610169491526,
      "grad_norm": 0.3048870265483856,
      "learning_rate": 6.466250186922325e-05,
      "loss": 1.1959,
      "step": 87
    },
    {
      "epoch": 0.011932203389830509,
      "grad_norm": 0.30789071321487427,
      "learning_rate": 6.387014543809223e-05,
      "loss": 1.1931,
      "step": 88
    },
    {
      "epoch": 0.012067796610169492,
      "grad_norm": 0.30434927344322205,
      "learning_rate": 6.307399704769099e-05,
      "loss": 1.2794,
      "step": 89
    },
    {
      "epoch": 0.012203389830508475,
      "grad_norm": 0.3304508328437805,
      "learning_rate": 6.227427435703997e-05,
      "loss": 1.162,
      "step": 90
    },
    {
      "epoch": 0.012338983050847458,
      "grad_norm": 0.35907384753227234,
      "learning_rate": 6.147119600233758e-05,
      "loss": 1.2675,
      "step": 91
    },
    {
      "epoch": 0.01247457627118644,
      "grad_norm": 0.35253170132637024,
      "learning_rate": 6.066498153718735e-05,
      "loss": 1.1771,
      "step": 92
    },
    {
      "epoch": 0.012610169491525424,
      "grad_norm": 0.3238564133644104,
      "learning_rate": 5.985585137257401e-05,
      "loss": 1.2109,
      "step": 93
    },
    {
      "epoch": 0.012745762711864407,
      "grad_norm": 0.3277183473110199,
      "learning_rate": 5.90440267166055e-05,
      "loss": 1.2283,
      "step": 94
    },
    {
      "epoch": 0.01288135593220339,
      "grad_norm": 0.35235458612442017,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 1.2553,
      "step": 95
    },
    {
      "epoch": 0.013016949152542373,
      "grad_norm": 0.3947640359401703,
      "learning_rate": 5.74131823855921e-05,
      "loss": 1.2889,
      "step": 96
    },
    {
      "epoch": 0.013152542372881356,
      "grad_norm": 0.38760635256767273,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 1.3181,
      "step": 97
    },
    {
      "epoch": 0.013288135593220339,
      "grad_norm": 0.422651469707489,
      "learning_rate": 5.577423184847932e-05,
      "loss": 1.353,
      "step": 98
    },
    {
      "epoch": 0.013423728813559322,
      "grad_norm": 0.45040181279182434,
      "learning_rate": 5.495227651252315e-05,
      "loss": 1.378,
      "step": 99
    },
    {
      "epoch": 0.013559322033898305,
      "grad_norm": 0.4888378977775574,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 1.5123,
      "step": 100
    },
    {
      "epoch": 0.013559322033898305,
      "eval_loss": 1.1681721210479736,
      "eval_runtime": 164.9238,
      "eval_samples_per_second": 75.314,
      "eval_steps_per_second": 18.833,
      "step": 100
    },
    {
      "epoch": 0.013694915254237288,
      "grad_norm": 0.3346395492553711,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.8667,
      "step": 101
    },
    {
      "epoch": 0.01383050847457627,
      "grad_norm": 0.3718145787715912,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.9797,
      "step": 102
    },
    {
      "epoch": 0.013966101694915254,
      "grad_norm": 0.3399723470211029,
      "learning_rate": 5.165316846586541e-05,
      "loss": 1.0023,
      "step": 103
    },
    {
      "epoch": 0.014101694915254237,
      "grad_norm": 0.3279365301132202,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.9986,
      "step": 104
    },
    {
      "epoch": 0.01423728813559322,
      "grad_norm": 0.29312729835510254,
      "learning_rate": 5e-05,
      "loss": 1.0964,
      "step": 105
    },
    {
      "epoch": 0.014372881355932203,
      "grad_norm": 0.2888731062412262,
      "learning_rate": 4.917330276168208e-05,
      "loss": 1.0551,
      "step": 106
    },
    {
      "epoch": 0.014508474576271186,
      "grad_norm": 0.2886713445186615,
      "learning_rate": 4.834683153413459e-05,
      "loss": 1.1594,
      "step": 107
    },
    {
      "epoch": 0.014644067796610169,
      "grad_norm": 0.2683737277984619,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 1.0152,
      "step": 108
    },
    {
      "epoch": 0.014779661016949153,
      "grad_norm": 0.239290252327919,
      "learning_rate": 4.669547078371504e-05,
      "loss": 1.0595,
      "step": 109
    },
    {
      "epoch": 0.014915254237288136,
      "grad_norm": 0.23605266213417053,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.9852,
      "step": 110
    },
    {
      "epoch": 0.01505084745762712,
      "grad_norm": 0.2700364589691162,
      "learning_rate": 4.504772348747687e-05,
      "loss": 1.1281,
      "step": 111
    },
    {
      "epoch": 0.015186440677966102,
      "grad_norm": 0.26605910062789917,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 1.1427,
      "step": 112
    },
    {
      "epoch": 0.015322033898305085,
      "grad_norm": 0.2468234747648239,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 1.0516,
      "step": 113
    },
    {
      "epoch": 0.015457627118644068,
      "grad_norm": 0.26857519149780273,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 1.0934,
      "step": 114
    },
    {
      "epoch": 0.015593220338983051,
      "grad_norm": 0.2991141974925995,
      "learning_rate": 4.17702704859633e-05,
      "loss": 1.1925,
      "step": 115
    },
    {
      "epoch": 0.015728813559322034,
      "grad_norm": 0.2659930884838104,
      "learning_rate": 4.095597328339452e-05,
      "loss": 1.0208,
      "step": 116
    },
    {
      "epoch": 0.015864406779661017,
      "grad_norm": 0.2698308229446411,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 1.0946,
      "step": 117
    },
    {
      "epoch": 0.016,
      "grad_norm": 0.285630464553833,
      "learning_rate": 3.933501846281267e-05,
      "loss": 1.1473,
      "step": 118
    },
    {
      "epoch": 0.016135593220338983,
      "grad_norm": 0.27481284737586975,
      "learning_rate": 3.852880399766243e-05,
      "loss": 1.0881,
      "step": 119
    },
    {
      "epoch": 0.016271186440677966,
      "grad_norm": 0.2705250680446625,
      "learning_rate": 3.772572564296005e-05,
      "loss": 1.1091,
      "step": 120
    },
    {
      "epoch": 0.01640677966101695,
      "grad_norm": 0.2979089021682739,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 1.1212,
      "step": 121
    },
    {
      "epoch": 0.016542372881355932,
      "grad_norm": 0.3011801540851593,
      "learning_rate": 3.612985456190778e-05,
      "loss": 1.1689,
      "step": 122
    },
    {
      "epoch": 0.016677966101694915,
      "grad_norm": 0.275231271982193,
      "learning_rate": 3.533749813077677e-05,
      "loss": 1.1429,
      "step": 123
    },
    {
      "epoch": 0.0168135593220339,
      "grad_norm": 0.2825208008289337,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.0404,
      "step": 124
    },
    {
      "epoch": 0.01694915254237288,
      "grad_norm": 0.28478601574897766,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 1.1791,
      "step": 125
    },
    {
      "epoch": 0.017084745762711864,
      "grad_norm": 0.29243284463882446,
      "learning_rate": 3.298534127791785e-05,
      "loss": 1.164,
      "step": 126
    },
    {
      "epoch": 0.017220338983050847,
      "grad_norm": 0.3116801679134369,
      "learning_rate": 3.221030765387417e-05,
      "loss": 1.1603,
      "step": 127
    },
    {
      "epoch": 0.01735593220338983,
      "grad_norm": 0.31198954582214355,
      "learning_rate": 3.144013755408895e-05,
      "loss": 1.169,
      "step": 128
    },
    {
      "epoch": 0.017491525423728813,
      "grad_norm": 0.3150678873062134,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 1.1783,
      "step": 129
    },
    {
      "epoch": 0.017627118644067796,
      "grad_norm": 0.34025710821151733,
      "learning_rate": 2.991522876735154e-05,
      "loss": 1.0847,
      "step": 130
    },
    {
      "epoch": 0.01776271186440678,
      "grad_norm": 0.3076338469982147,
      "learning_rate": 2.916090697523549e-05,
      "loss": 1.2102,
      "step": 131
    },
    {
      "epoch": 0.017898305084745762,
      "grad_norm": 0.3179541230201721,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 1.1723,
      "step": 132
    },
    {
      "epoch": 0.018033898305084745,
      "grad_norm": 0.3099156320095062,
      "learning_rate": 2.766955965735968e-05,
      "loss": 1.119,
      "step": 133
    },
    {
      "epoch": 0.018169491525423728,
      "grad_norm": 0.31253954768180847,
      "learning_rate": 2.693294185106562e-05,
      "loss": 1.1941,
      "step": 134
    },
    {
      "epoch": 0.01830508474576271,
      "grad_norm": 0.3192349076271057,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 1.232,
      "step": 135
    },
    {
      "epoch": 0.018440677966101694,
      "grad_norm": 0.3139921724796295,
      "learning_rate": 2.547882480847461e-05,
      "loss": 1.1986,
      "step": 136
    },
    {
      "epoch": 0.018576271186440677,
      "grad_norm": 0.3000154197216034,
      "learning_rate": 2.476172311325783e-05,
      "loss": 1.1026,
      "step": 137
    },
    {
      "epoch": 0.01871186440677966,
      "grad_norm": 0.3189956843852997,
      "learning_rate": 2.405152131093926e-05,
      "loss": 1.1639,
      "step": 138
    },
    {
      "epoch": 0.018847457627118643,
      "grad_norm": 0.32820379734039307,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 1.1677,
      "step": 139
    },
    {
      "epoch": 0.018983050847457626,
      "grad_norm": 0.3308604955673218,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 1.1301,
      "step": 140
    },
    {
      "epoch": 0.01911864406779661,
      "grad_norm": 0.3575458526611328,
      "learning_rate": 2.196424713241637e-05,
      "loss": 1.2032,
      "step": 141
    },
    {
      "epoch": 0.019254237288135592,
      "grad_norm": 0.3604236841201782,
      "learning_rate": 2.128356686585282e-05,
      "loss": 1.2515,
      "step": 142
    },
    {
      "epoch": 0.019389830508474575,
      "grad_norm": 0.3599156439304352,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.2296,
      "step": 143
    },
    {
      "epoch": 0.019525423728813558,
      "grad_norm": 0.3833460211753845,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 1.2147,
      "step": 144
    },
    {
      "epoch": 0.01966101694915254,
      "grad_norm": 0.35572659969329834,
      "learning_rate": 1.928936436551661e-05,
      "loss": 1.1994,
      "step": 145
    },
    {
      "epoch": 0.019796610169491524,
      "grad_norm": 0.3848327398300171,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 1.183,
      "step": 146
    },
    {
      "epoch": 0.019932203389830507,
      "grad_norm": 0.42949309945106506,
      "learning_rate": 1.800157297483417e-05,
      "loss": 1.3339,
      "step": 147
    },
    {
      "epoch": 0.02006779661016949,
      "grad_norm": 0.40530502796173096,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 1.22,
      "step": 148
    },
    {
      "epoch": 0.020203389830508473,
      "grad_norm": 0.43298110365867615,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 1.2602,
      "step": 149
    },
    {
      "epoch": 0.020338983050847456,
      "grad_norm": 0.5253007411956787,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 1.478,
      "step": 150
    },
    {
      "epoch": 0.020338983050847456,
      "eval_loss": 1.1474329233169556,
      "eval_runtime": 165.126,
      "eval_samples_per_second": 75.221,
      "eval_steps_per_second": 18.81,
      "step": 150
    },
    {
      "epoch": 0.02047457627118644,
      "grad_norm": 0.2498561441898346,
      "learning_rate": 1.553232954407171e-05,
      "loss": 1.0598,
      "step": 151
    },
    {
      "epoch": 0.020610169491525422,
      "grad_norm": 0.28272855281829834,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 1.1082,
      "step": 152
    },
    {
      "epoch": 0.020745762711864405,
      "grad_norm": 0.29553964734077454,
      "learning_rate": 1.435357758543015e-05,
      "loss": 1.1164,
      "step": 153
    },
    {
      "epoch": 0.020881355932203388,
      "grad_norm": 0.2729560434818268,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 1.0013,
      "step": 154
    },
    {
      "epoch": 0.021016949152542375,
      "grad_norm": 0.2801288366317749,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.9478,
      "step": 155
    },
    {
      "epoch": 0.021152542372881358,
      "grad_norm": 0.27261924743652344,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.9808,
      "step": 156
    },
    {
      "epoch": 0.02128813559322034,
      "grad_norm": 0.25815898180007935,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.9914,
      "step": 157
    },
    {
      "epoch": 0.021423728813559324,
      "grad_norm": 0.2933312654495239,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.9287,
      "step": 158
    },
    {
      "epoch": 0.021559322033898307,
      "grad_norm": 0.2835666835308075,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 1.1039,
      "step": 159
    },
    {
      "epoch": 0.02169491525423729,
      "grad_norm": 0.29037341475486755,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 1.1327,
      "step": 160
    },
    {
      "epoch": 0.021830508474576273,
      "grad_norm": 0.27324846386909485,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 1.0897,
      "step": 161
    },
    {
      "epoch": 0.021966101694915256,
      "grad_norm": 0.278764933347702,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.0723,
      "step": 162
    },
    {
      "epoch": 0.02210169491525424,
      "grad_norm": 0.264383465051651,
      "learning_rate": 9.068759265665384e-06,
      "loss": 1.1287,
      "step": 163
    },
    {
      "epoch": 0.02223728813559322,
      "grad_norm": 0.28780031204223633,
      "learning_rate": 8.599558442598998e-06,
      "loss": 1.0421,
      "step": 164
    },
    {
      "epoch": 0.022372881355932205,
      "grad_norm": 0.2898831367492676,
      "learning_rate": 8.141676086873572e-06,
      "loss": 1.1443,
      "step": 165
    },
    {
      "epoch": 0.022508474576271188,
      "grad_norm": 0.2826436161994934,
      "learning_rate": 7.695237378953223e-06,
      "loss": 1.0322,
      "step": 166
    },
    {
      "epoch": 0.02264406779661017,
      "grad_norm": 0.3284930884838104,
      "learning_rate": 7.260364370723044e-06,
      "loss": 1.1824,
      "step": 167
    },
    {
      "epoch": 0.022779661016949154,
      "grad_norm": 0.2938554286956787,
      "learning_rate": 6.837175952121306e-06,
      "loss": 1.2391,
      "step": 168
    },
    {
      "epoch": 0.022915254237288137,
      "grad_norm": 0.2690979540348053,
      "learning_rate": 6.425787818636131e-06,
      "loss": 1.003,
      "step": 169
    },
    {
      "epoch": 0.02305084745762712,
      "grad_norm": 0.2821996212005615,
      "learning_rate": 6.026312439675552e-06,
      "loss": 1.0837,
      "step": 170
    },
    {
      "epoch": 0.023186440677966103,
      "grad_norm": 0.2555193603038788,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.9892,
      "step": 171
    },
    {
      "epoch": 0.023322033898305086,
      "grad_norm": 0.2881105840206146,
      "learning_rate": 5.263533508961827e-06,
      "loss": 1.178,
      "step": 172
    },
    {
      "epoch": 0.02345762711864407,
      "grad_norm": 0.3018070459365845,
      "learning_rate": 4.900438493352055e-06,
      "loss": 1.1878,
      "step": 173
    },
    {
      "epoch": 0.02359322033898305,
      "grad_norm": 0.29498761892318726,
      "learning_rate": 4.549673247541875e-06,
      "loss": 1.113,
      "step": 174
    },
    {
      "epoch": 0.023728813559322035,
      "grad_norm": 0.2750340700149536,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 1.0868,
      "step": 175
    },
    {
      "epoch": 0.023864406779661018,
      "grad_norm": 0.2883802652359009,
      "learning_rate": 3.885512251130763e-06,
      "loss": 1.1548,
      "step": 176
    },
    {
      "epoch": 0.024,
      "grad_norm": 0.27978596091270447,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.9776,
      "step": 177
    },
    {
      "epoch": 0.024135593220338983,
      "grad_norm": 0.314546674489975,
      "learning_rate": 3.271776770026963e-06,
      "loss": 1.1755,
      "step": 178
    },
    {
      "epoch": 0.024271186440677966,
      "grad_norm": 0.2897436320781708,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 1.1746,
      "step": 179
    },
    {
      "epoch": 0.02440677966101695,
      "grad_norm": 0.31206774711608887,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 1.2086,
      "step": 180
    },
    {
      "epoch": 0.024542372881355932,
      "grad_norm": 0.2825358808040619,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.1086,
      "step": 181
    },
    {
      "epoch": 0.024677966101694915,
      "grad_norm": 0.31676626205444336,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 1.2473,
      "step": 182
    },
    {
      "epoch": 0.0248135593220339,
      "grad_norm": 0.3169511556625366,
      "learning_rate": 1.962316193157593e-06,
      "loss": 1.1243,
      "step": 183
    },
    {
      "epoch": 0.02494915254237288,
      "grad_norm": 0.30261096358299255,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 1.1921,
      "step": 184
    },
    {
      "epoch": 0.025084745762711864,
      "grad_norm": 0.3011153042316437,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 1.1921,
      "step": 185
    },
    {
      "epoch": 0.025220338983050847,
      "grad_norm": 0.300214558839798,
      "learning_rate": 1.333670137599713e-06,
      "loss": 1.152,
      "step": 186
    },
    {
      "epoch": 0.02535593220338983,
      "grad_norm": 0.2953938841819763,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 1.1493,
      "step": 187
    },
    {
      "epoch": 0.025491525423728813,
      "grad_norm": 0.32733941078186035,
      "learning_rate": 9.810017062595322e-07,
      "loss": 1.2888,
      "step": 188
    },
    {
      "epoch": 0.025627118644067796,
      "grad_norm": 0.3120397925376892,
      "learning_rate": 8.247462563808817e-07,
      "loss": 1.0559,
      "step": 189
    },
    {
      "epoch": 0.02576271186440678,
      "grad_norm": 0.3438621461391449,
      "learning_rate": 6.819348298638839e-07,
      "loss": 1.232,
      "step": 190
    },
    {
      "epoch": 0.025898305084745762,
      "grad_norm": 0.33304664492607117,
      "learning_rate": 5.526064699265753e-07,
      "loss": 1.3103,
      "step": 191
    },
    {
      "epoch": 0.026033898305084745,
      "grad_norm": 0.3621855676174164,
      "learning_rate": 4.367965336512403e-07,
      "loss": 1.2837,
      "step": 192
    },
    {
      "epoch": 0.02616949152542373,
      "grad_norm": 0.3472006618976593,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 1.1273,
      "step": 193
    },
    {
      "epoch": 0.02630508474576271,
      "grad_norm": 0.3519177734851837,
      "learning_rate": 2.458548727494292e-07,
      "loss": 1.1966,
      "step": 194
    },
    {
      "epoch": 0.026440677966101694,
      "grad_norm": 0.40637272596359253,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 1.2417,
      "step": 195
    },
    {
      "epoch": 0.026576271186440677,
      "grad_norm": 0.37683430314064026,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 1.1547,
      "step": 196
    },
    {
      "epoch": 0.02671186440677966,
      "grad_norm": 0.39114663004875183,
      "learning_rate": 6.150154258476315e-08,
      "loss": 1.2434,
      "step": 197
    },
    {
      "epoch": 0.026847457627118643,
      "grad_norm": 0.41517066955566406,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 1.1913,
      "step": 198
    },
    {
      "epoch": 0.026983050847457626,
      "grad_norm": 0.46081817150115967,
      "learning_rate": 6.834750376549792e-09,
      "loss": 1.2313,
      "step": 199
    },
    {
      "epoch": 0.02711864406779661,
      "grad_norm": 0.6523765325546265,
      "learning_rate": 0.0,
      "loss": 1.5668,
      "step": 200
    },
    {
      "epoch": 0.02711864406779661,
      "eval_loss": 1.1419742107391357,
      "eval_runtime": 164.8921,
      "eval_samples_per_second": 75.328,
      "eval_steps_per_second": 18.837,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4962893410861056.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}