{
  "best_metric": 0.7660930156707764,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 0.030070666065253344,
  "eval_steps": 50,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00020047110710168898,
      "grad_norm": 0.8395384550094604,
      "learning_rate": 1e-05,
      "loss": 1.2055,
      "step": 1
    },
    {
      "epoch": 0.00020047110710168898,
      "eval_loss": 1.1993074417114258,
      "eval_runtime": 685.6091,
      "eval_samples_per_second": 12.255,
      "eval_steps_per_second": 3.064,
      "step": 1
    },
    {
      "epoch": 0.00040094221420337796,
      "grad_norm": 0.8948485255241394,
      "learning_rate": 2e-05,
      "loss": 1.0574,
      "step": 2
    },
    {
      "epoch": 0.0006014133213050669,
      "grad_norm": 0.7938868999481201,
      "learning_rate": 3e-05,
      "loss": 1.1064,
      "step": 3
    },
    {
      "epoch": 0.0008018844284067559,
      "grad_norm": 0.755268931388855,
      "learning_rate": 4e-05,
      "loss": 1.0475,
      "step": 4
    },
    {
      "epoch": 0.0010023555355084448,
      "grad_norm": 0.6127366423606873,
      "learning_rate": 5e-05,
      "loss": 1.0631,
      "step": 5
    },
    {
      "epoch": 0.0012028266426101339,
      "grad_norm": 0.6037653088569641,
      "learning_rate": 6e-05,
      "loss": 1.0473,
      "step": 6
    },
    {
      "epoch": 0.0014032977497118228,
      "grad_norm": 0.917192816734314,
      "learning_rate": 7e-05,
      "loss": 0.9832,
      "step": 7
    },
    {
      "epoch": 0.0016037688568135118,
      "grad_norm": 0.9301321506500244,
      "learning_rate": 8e-05,
      "loss": 0.9971,
      "step": 8
    },
    {
      "epoch": 0.0018042399639152007,
      "grad_norm": 0.6523141860961914,
      "learning_rate": 9e-05,
      "loss": 0.9502,
      "step": 9
    },
    {
      "epoch": 0.0020047110710168896,
      "grad_norm": 0.6364212036132812,
      "learning_rate": 0.0001,
      "loss": 0.9328,
      "step": 10
    },
    {
      "epoch": 0.0022051821781185785,
      "grad_norm": 0.5896421670913696,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.9569,
      "step": 11
    },
    {
      "epoch": 0.0024056532852202678,
      "grad_norm": 0.6128784418106079,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.8696,
      "step": 12
    },
    {
      "epoch": 0.0026061243923219566,
      "grad_norm": 0.5889639854431152,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.9602,
      "step": 13
    },
    {
      "epoch": 0.0028065954994236455,
      "grad_norm": 0.5264745950698853,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.8813,
      "step": 14
    },
    {
      "epoch": 0.0030070666065253344,
      "grad_norm": 0.5114163756370544,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.8959,
      "step": 15
    },
    {
      "epoch": 0.0032075377136270237,
      "grad_norm": 0.55214923620224,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.9171,
      "step": 16
    },
    {
      "epoch": 0.0034080088207287126,
      "grad_norm": 0.5175560712814331,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.9157,
      "step": 17
    },
    {
      "epoch": 0.0036084799278304014,
      "grad_norm": 0.477830171585083,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.8826,
      "step": 18
    },
    {
      "epoch": 0.0038089510349320903,
      "grad_norm": 0.4910264015197754,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.846,
      "step": 19
    },
    {
      "epoch": 0.004009422142033779,
      "grad_norm": 0.46486103534698486,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.8467,
      "step": 20
    },
    {
      "epoch": 0.0042098932491354685,
      "grad_norm": 0.4944344758987427,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.7881,
      "step": 21
    },
    {
      "epoch": 0.004410364356237157,
      "grad_norm": 0.548256516456604,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.8571,
      "step": 22
    },
    {
      "epoch": 0.004610835463338846,
      "grad_norm": 0.52168208360672,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.8069,
      "step": 23
    },
    {
      "epoch": 0.0048113065704405355,
      "grad_norm": 0.5062702298164368,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.7924,
      "step": 24
    },
    {
      "epoch": 0.005011777677542224,
      "grad_norm": 0.5029427409172058,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.8087,
      "step": 25
    },
    {
      "epoch": 0.005212248784643913,
      "grad_norm": 0.5117804408073425,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.7321,
      "step": 26
    },
    {
      "epoch": 0.005412719891745603,
      "grad_norm": 0.4774559736251831,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.7384,
      "step": 27
    },
    {
      "epoch": 0.005613190998847291,
      "grad_norm": 0.5124812126159668,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.7436,
      "step": 28
    },
    {
      "epoch": 0.00581366210594898,
      "grad_norm": 0.48422589898109436,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.7935,
      "step": 29
    },
    {
      "epoch": 0.006014133213050669,
      "grad_norm": 0.4835473895072937,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.8535,
      "step": 30
    },
    {
      "epoch": 0.006214604320152358,
      "grad_norm": 0.5212709903717041,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.744,
      "step": 31
    },
    {
      "epoch": 0.006415075427254047,
      "grad_norm": 0.5131075382232666,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.7716,
      "step": 32
    },
    {
      "epoch": 0.006615546534355736,
      "grad_norm": 0.5026133060455322,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.7407,
      "step": 33
    },
    {
      "epoch": 0.006816017641457425,
      "grad_norm": 0.5249520540237427,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.8031,
      "step": 34
    },
    {
      "epoch": 0.0070164887485591135,
      "grad_norm": 0.5142430663108826,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.7486,
      "step": 35
    },
    {
      "epoch": 0.007216959855660803,
      "grad_norm": 0.521611213684082,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.7832,
      "step": 36
    },
    {
      "epoch": 0.007417430962762492,
      "grad_norm": 0.5283540487289429,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.7848,
      "step": 37
    },
    {
      "epoch": 0.007617902069864181,
      "grad_norm": 0.5896772146224976,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.805,
      "step": 38
    },
    {
      "epoch": 0.007818373176965869,
      "grad_norm": 0.5727930068969727,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.8518,
      "step": 39
    },
    {
      "epoch": 0.008018844284067558,
      "grad_norm": 0.5887387990951538,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.7725,
      "step": 40
    },
    {
      "epoch": 0.008219315391169248,
      "grad_norm": 0.6438959836959839,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.8503,
      "step": 41
    },
    {
      "epoch": 0.008419786498270937,
      "grad_norm": 0.6279118657112122,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.8623,
      "step": 42
    },
    {
      "epoch": 0.008620257605372626,
      "grad_norm": 0.6363451480865479,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.7763,
      "step": 43
    },
    {
      "epoch": 0.008820728712474314,
      "grad_norm": 0.6856397986412048,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.8365,
      "step": 44
    },
    {
      "epoch": 0.009021199819576003,
      "grad_norm": 0.6746196746826172,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.8367,
      "step": 45
    },
    {
      "epoch": 0.009221670926677692,
      "grad_norm": 0.7187036871910095,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.8866,
      "step": 46
    },
    {
      "epoch": 0.009422142033779382,
      "grad_norm": 0.7219327688217163,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.8242,
      "step": 47
    },
    {
      "epoch": 0.009622613140881071,
      "grad_norm": 0.7718280553817749,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.9083,
      "step": 48
    },
    {
      "epoch": 0.00982308424798276,
      "grad_norm": 0.9818487763404846,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.9884,
      "step": 49
    },
    {
      "epoch": 0.010023555355084448,
      "grad_norm": 1.4967366456985474,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.9546,
      "step": 50
    },
    {
      "epoch": 0.010023555355084448,
      "eval_loss": 0.8557348847389221,
      "eval_runtime": 687.7232,
      "eval_samples_per_second": 12.217,
      "eval_steps_per_second": 3.055,
      "step": 50
    },
    {
      "epoch": 0.010224026462186137,
      "grad_norm": 0.6224396228790283,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.9203,
      "step": 51
    },
    {
      "epoch": 0.010424497569287827,
      "grad_norm": 0.6248539090156555,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.9478,
      "step": 52
    },
    {
      "epoch": 0.010624968676389516,
      "grad_norm": 0.5116735100746155,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.868,
      "step": 53
    },
    {
      "epoch": 0.010825439783491205,
      "grad_norm": 0.4344223141670227,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.8699,
      "step": 54
    },
    {
      "epoch": 0.011025910890592893,
      "grad_norm": 0.4146479070186615,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.8285,
      "step": 55
    },
    {
      "epoch": 0.011226381997694582,
      "grad_norm": 0.4180496037006378,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.8618,
      "step": 56
    },
    {
      "epoch": 0.011426853104796271,
      "grad_norm": 0.42232587933540344,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.8529,
      "step": 57
    },
    {
      "epoch": 0.01162732421189796,
      "grad_norm": 0.4605618715286255,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.921,
      "step": 58
    },
    {
      "epoch": 0.01182779531899965,
      "grad_norm": 0.4509781301021576,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.817,
      "step": 59
    },
    {
      "epoch": 0.012028266426101338,
      "grad_norm": 0.42849937081336975,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.8101,
      "step": 60
    },
    {
      "epoch": 0.012228737533203027,
      "grad_norm": 0.4194338917732239,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.8751,
      "step": 61
    },
    {
      "epoch": 0.012429208640304716,
      "grad_norm": 0.44792598485946655,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.8459,
      "step": 62
    },
    {
      "epoch": 0.012629679747406405,
      "grad_norm": 0.3823595941066742,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.8347,
      "step": 63
    },
    {
      "epoch": 0.012830150854508095,
      "grad_norm": 0.3972877562046051,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.8107,
      "step": 64
    },
    {
      "epoch": 0.013030621961609782,
      "grad_norm": 0.39951252937316895,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.7745,
      "step": 65
    },
    {
      "epoch": 0.013231093068711472,
      "grad_norm": 0.44492796063423157,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.799,
      "step": 66
    },
    {
      "epoch": 0.013431564175813161,
      "grad_norm": 0.40693098306655884,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.7857,
      "step": 67
    },
    {
      "epoch": 0.01363203528291485,
      "grad_norm": 0.4578515291213989,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.8043,
      "step": 68
    },
    {
      "epoch": 0.01383250639001654,
      "grad_norm": 0.4164541959762573,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.725,
      "step": 69
    },
    {
      "epoch": 0.014032977497118227,
      "grad_norm": 0.417854905128479,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.7717,
      "step": 70
    },
    {
      "epoch": 0.014233448604219916,
      "grad_norm": 0.443906307220459,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.7686,
      "step": 71
    },
    {
      "epoch": 0.014433919711321606,
      "grad_norm": 0.43706703186035156,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.694,
      "step": 72
    },
    {
      "epoch": 0.014634390818423295,
      "grad_norm": 0.4687156081199646,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.7084,
      "step": 73
    },
    {
      "epoch": 0.014834861925524984,
      "grad_norm": 0.4360148310661316,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.7347,
      "step": 74
    },
    {
      "epoch": 0.015035333032626672,
      "grad_norm": 0.46548962593078613,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.6908,
      "step": 75
    },
    {
      "epoch": 0.015235804139728361,
      "grad_norm": 0.45094600319862366,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.7146,
      "step": 76
    },
    {
      "epoch": 0.01543627524683005,
      "grad_norm": 0.4609590768814087,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.7803,
      "step": 77
    },
    {
      "epoch": 0.015636746353931738,
      "grad_norm": 0.46388593316078186,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.7517,
      "step": 78
    },
    {
      "epoch": 0.015837217461033427,
      "grad_norm": 0.4653104245662689,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.747,
      "step": 79
    },
    {
      "epoch": 0.016037688568135117,
      "grad_norm": 0.47856080532073975,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.7043,
      "step": 80
    },
    {
      "epoch": 0.016238159675236806,
      "grad_norm": 0.47672954201698303,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.8364,
      "step": 81
    },
    {
      "epoch": 0.016438630782338495,
      "grad_norm": 0.49898359179496765,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.777,
      "step": 82
    },
    {
      "epoch": 0.016639101889440185,
      "grad_norm": 0.4857921302318573,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.7157,
      "step": 83
    },
    {
      "epoch": 0.016839572996541874,
      "grad_norm": 0.4987119436264038,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.7355,
      "step": 84
    },
    {
      "epoch": 0.017040044103643563,
      "grad_norm": 0.48658257722854614,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.7436,
      "step": 85
    },
    {
      "epoch": 0.017240515210745253,
      "grad_norm": 0.5253781676292419,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.7737,
      "step": 86
    },
    {
      "epoch": 0.017440986317846942,
      "grad_norm": 0.5535750985145569,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.766,
      "step": 87
    },
    {
      "epoch": 0.017641457424948628,
      "grad_norm": 0.5258573293685913,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.7948,
      "step": 88
    },
    {
      "epoch": 0.017841928532050317,
      "grad_norm": 0.528154730796814,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.7089,
      "step": 89
    },
    {
      "epoch": 0.018042399639152006,
      "grad_norm": 0.5404923558235168,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.7653,
      "step": 90
    },
    {
      "epoch": 0.018242870746253696,
      "grad_norm": 0.561104416847229,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.8398,
      "step": 91
    },
    {
      "epoch": 0.018443341853355385,
      "grad_norm": 0.5464400053024292,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.7721,
      "step": 92
    },
    {
      "epoch": 0.018643812960457074,
      "grad_norm": 0.5629717111587524,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.7695,
      "step": 93
    },
    {
      "epoch": 0.018844284067558763,
      "grad_norm": 0.6296807527542114,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.8469,
      "step": 94
    },
    {
      "epoch": 0.019044755174660453,
      "grad_norm": 0.6088625192642212,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.816,
      "step": 95
    },
    {
      "epoch": 0.019245226281762142,
      "grad_norm": 0.6467829346656799,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.8508,
      "step": 96
    },
    {
      "epoch": 0.01944569738886383,
      "grad_norm": 0.6873995661735535,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.8342,
      "step": 97
    },
    {
      "epoch": 0.01964616849596552,
      "grad_norm": 0.7378100752830505,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.912,
      "step": 98
    },
    {
      "epoch": 0.019846639603067207,
      "grad_norm": 0.8778892159461975,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.8792,
      "step": 99
    },
    {
      "epoch": 0.020047110710168896,
      "grad_norm": 1.2133814096450806,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.9658,
      "step": 100
    },
    {
      "epoch": 0.020047110710168896,
      "eval_loss": 0.7986238598823547,
      "eval_runtime": 688.4391,
      "eval_samples_per_second": 12.204,
      "eval_steps_per_second": 3.052,
      "step": 100
    },
    {
      "epoch": 0.020247581817270585,
      "grad_norm": 0.4868101477622986,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.9316,
      "step": 101
    },
    {
      "epoch": 0.020448052924372274,
      "grad_norm": 0.49930644035339355,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.8776,
      "step": 102
    },
    {
      "epoch": 0.020648524031473964,
      "grad_norm": 0.4405224919319153,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.8923,
      "step": 103
    },
    {
      "epoch": 0.020848995138575653,
      "grad_norm": 0.4402744770050049,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.8354,
      "step": 104
    },
    {
      "epoch": 0.021049466245677342,
      "grad_norm": 0.4408913254737854,
      "learning_rate": 5e-05,
      "loss": 0.8409,
      "step": 105
    },
    {
      "epoch": 0.02124993735277903,
      "grad_norm": 0.4233299195766449,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.8442,
      "step": 106
    },
    {
      "epoch": 0.02145040845988072,
      "grad_norm": 0.37894466519355774,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.8305,
      "step": 107
    },
    {
      "epoch": 0.02165087956698241,
      "grad_norm": 0.39356476068496704,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.9412,
      "step": 108
    },
    {
      "epoch": 0.021851350674084096,
      "grad_norm": 0.34564244747161865,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.8435,
      "step": 109
    },
    {
      "epoch": 0.022051821781185785,
      "grad_norm": 0.3752840459346771,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.8261,
      "step": 110
    },
    {
      "epoch": 0.022252292888287475,
      "grad_norm": 0.4003555178642273,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.8078,
      "step": 111
    },
    {
      "epoch": 0.022452763995389164,
      "grad_norm": 0.41098564863204956,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.8397,
      "step": 112
    },
    {
      "epoch": 0.022653235102490853,
      "grad_norm": 0.39858096837997437,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.7818,
      "step": 113
    },
    {
      "epoch": 0.022853706209592543,
      "grad_norm": 0.4122288227081299,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.7395,
      "step": 114
    },
    {
      "epoch": 0.023054177316694232,
      "grad_norm": 0.3953876495361328,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.8314,
      "step": 115
    },
    {
      "epoch": 0.02325464842379592,
      "grad_norm": 0.4030442237854004,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.6877,
      "step": 116
    },
    {
      "epoch": 0.02345511953089761,
      "grad_norm": 0.4044947624206543,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.7646,
      "step": 117
    },
    {
      "epoch": 0.0236555906379993,
      "grad_norm": 0.4531426727771759,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.7015,
      "step": 118
    },
    {
      "epoch": 0.023856061745100986,
      "grad_norm": 0.4006672203540802,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.7566,
      "step": 119
    },
    {
      "epoch": 0.024056532852202675,
      "grad_norm": 0.42156991362571716,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.7131,
      "step": 120
    },
    {
      "epoch": 0.024257003959304364,
      "grad_norm": 0.42404821515083313,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.7639,
      "step": 121
    },
    {
      "epoch": 0.024457475066406054,
      "grad_norm": 0.42018404603004456,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.6944,
      "step": 122
    },
    {
      "epoch": 0.024657946173507743,
      "grad_norm": 0.41678738594055176,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.66,
      "step": 123
    },
    {
      "epoch": 0.024858417280609432,
      "grad_norm": 0.43670549988746643,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.7946,
      "step": 124
    },
    {
      "epoch": 0.02505888838771112,
      "grad_norm": 0.42546412348747253,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.7335,
      "step": 125
    },
    {
      "epoch": 0.02525935949481281,
      "grad_norm": 0.42231953144073486,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.7107,
      "step": 126
    },
    {
      "epoch": 0.0254598306019145,
      "grad_norm": 0.4315146803855896,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.6982,
      "step": 127
    },
    {
      "epoch": 0.02566030170901619,
      "grad_norm": 0.4526367485523224,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.7054,
      "step": 128
    },
    {
      "epoch": 0.025860772816117875,
      "grad_norm": 0.443099707365036,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.6683,
      "step": 129
    },
    {
      "epoch": 0.026061243923219565,
      "grad_norm": 0.44703754782676697,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.6773,
      "step": 130
    },
    {
      "epoch": 0.026261715030321254,
      "grad_norm": 0.45242762565612793,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.663,
      "step": 131
    },
    {
      "epoch": 0.026462186137422943,
      "grad_norm": 0.47624993324279785,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.7102,
      "step": 132
    },
    {
      "epoch": 0.026662657244524633,
      "grad_norm": 0.5007295608520508,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.7517,
      "step": 133
    },
    {
      "epoch": 0.026863128351626322,
      "grad_norm": 0.5087299942970276,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.7517,
      "step": 134
    },
    {
      "epoch": 0.02706359945872801,
      "grad_norm": 0.4999999701976776,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.7799,
      "step": 135
    },
    {
      "epoch": 0.0272640705658297,
      "grad_norm": 0.520560085773468,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.7654,
      "step": 136
    },
    {
      "epoch": 0.02746454167293139,
      "grad_norm": 0.49053311347961426,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.7608,
      "step": 137
    },
    {
      "epoch": 0.02766501278003308,
      "grad_norm": 0.5456017255783081,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.733,
      "step": 138
    },
    {
      "epoch": 0.02786548388713477,
      "grad_norm": 0.5285861492156982,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.7388,
      "step": 139
    },
    {
      "epoch": 0.028065954994236454,
      "grad_norm": 0.5213586688041687,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.7293,
      "step": 140
    },
    {
      "epoch": 0.028266426101338143,
      "grad_norm": 0.5256751179695129,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.7755,
      "step": 141
    },
    {
      "epoch": 0.028466897208439833,
      "grad_norm": 0.5142960548400879,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.7222,
      "step": 142
    },
    {
      "epoch": 0.028667368315541522,
      "grad_norm": 0.5569576621055603,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.7883,
      "step": 143
    },
    {
      "epoch": 0.02886783942264321,
      "grad_norm": 0.5263428688049316,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.7604,
      "step": 144
    },
    {
      "epoch": 0.0290683105297449,
      "grad_norm": 0.5664807558059692,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.7805,
      "step": 145
    },
    {
      "epoch": 0.02926878163684659,
      "grad_norm": 0.5974829196929932,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.7621,
      "step": 146
    },
    {
      "epoch": 0.02946925274394828,
      "grad_norm": 0.6496215462684631,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.9089,
      "step": 147
    },
    {
      "epoch": 0.02966972385104997,
      "grad_norm": 0.7033149600028992,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.7796,
      "step": 148
    },
    {
      "epoch": 0.029870194958151658,
      "grad_norm": 0.8038272261619568,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.9111,
      "step": 149
    },
    {
      "epoch": 0.030070666065253344,
      "grad_norm": 1.1144033670425415,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.8875,
      "step": 150
    },
    {
      "epoch": 0.030070666065253344,
      "eval_loss": 0.7660930156707764,
      "eval_runtime": 688.9502,
      "eval_samples_per_second": 12.195,
      "eval_steps_per_second": 3.05,
      "step": 150
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.3947653062590464e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}