{
  "best_metric": 0.9148275852203369,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 3.0,
  "eval_steps": 50,
  "global_step": 177,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01694915254237288,
      "grad_norm": 0.9787123203277588,
      "learning_rate": 1e-05,
      "loss": 3.0209,
      "step": 1
    },
    {
      "epoch": 0.01694915254237288,
      "eval_loss": 4.1999897956848145,
      "eval_runtime": 1.4503,
      "eval_samples_per_second": 68.951,
      "eval_steps_per_second": 17.238,
      "step": 1
    },
    {
      "epoch": 0.03389830508474576,
      "grad_norm": 2.4502038955688477,
      "learning_rate": 2e-05,
      "loss": 4.4497,
      "step": 2
    },
    {
      "epoch": 0.05084745762711865,
      "grad_norm": 2.665430784225464,
      "learning_rate": 3e-05,
      "loss": 4.639,
      "step": 3
    },
    {
      "epoch": 0.06779661016949153,
      "grad_norm": 2.4935710430145264,
      "learning_rate": 4e-05,
      "loss": 4.4997,
      "step": 4
    },
    {
      "epoch": 0.0847457627118644,
      "grad_norm": 2.3885178565979004,
      "learning_rate": 5e-05,
      "loss": 4.3788,
      "step": 5
    },
    {
      "epoch": 0.1016949152542373,
      "grad_norm": 2.521230459213257,
      "learning_rate": 6e-05,
      "loss": 4.4601,
      "step": 6
    },
    {
      "epoch": 0.11864406779661017,
      "grad_norm": 2.408069133758545,
      "learning_rate": 7e-05,
      "loss": 4.3255,
      "step": 7
    },
    {
      "epoch": 0.13559322033898305,
      "grad_norm": 1.1387848854064941,
      "learning_rate": 8e-05,
      "loss": 3.355,
      "step": 8
    },
    {
      "epoch": 0.15254237288135594,
      "grad_norm": 1.0923254489898682,
      "learning_rate": 9e-05,
      "loss": 3.0777,
      "step": 9
    },
    {
      "epoch": 0.1694915254237288,
      "grad_norm": 1.489324688911438,
      "learning_rate": 0.0001,
      "loss": 3.4978,
      "step": 10
    },
    {
      "epoch": 0.1864406779661017,
      "grad_norm": 1.415766716003418,
      "learning_rate": 9.999115304121457e-05,
      "loss": 3.4619,
      "step": 11
    },
    {
      "epoch": 0.2033898305084746,
      "grad_norm": 1.4508241415023804,
      "learning_rate": 9.996461529560553e-05,
      "loss": 3.2672,
      "step": 12
    },
    {
      "epoch": 0.22033898305084745,
      "grad_norm": 1.6372668743133545,
      "learning_rate": 9.992039615430648e-05,
      "loss": 3.3624,
      "step": 13
    },
    {
      "epoch": 0.23728813559322035,
      "grad_norm": 2.086595296859741,
      "learning_rate": 9.985851126551428e-05,
      "loss": 3.8379,
      "step": 14
    },
    {
      "epoch": 0.2542372881355932,
      "grad_norm": 1.075448751449585,
      "learning_rate": 9.977898252895134e-05,
      "loss": 2.6479,
      "step": 15
    },
    {
      "epoch": 0.2711864406779661,
      "grad_norm": 2.2425975799560547,
      "learning_rate": 9.968183808811586e-05,
      "loss": 2.9848,
      "step": 16
    },
    {
      "epoch": 0.288135593220339,
      "grad_norm": 2.2366819381713867,
      "learning_rate": 9.95671123203224e-05,
      "loss": 2.818,
      "step": 17
    },
    {
      "epoch": 0.3050847457627119,
      "grad_norm": 2.1117076873779297,
      "learning_rate": 9.943484582453653e-05,
      "loss": 2.6075,
      "step": 18
    },
    {
      "epoch": 0.3220338983050847,
      "grad_norm": 2.0897672176361084,
      "learning_rate": 9.928508540700774e-05,
      "loss": 2.5123,
      "step": 19
    },
    {
      "epoch": 0.3389830508474576,
      "grad_norm": 1.8737945556640625,
      "learning_rate": 9.911788406470569e-05,
      "loss": 2.3475,
      "step": 20
    },
    {
      "epoch": 0.3559322033898305,
      "grad_norm": 1.7135223150253296,
      "learning_rate": 9.893330096656574e-05,
      "loss": 2.2067,
      "step": 21
    },
    {
      "epoch": 0.3728813559322034,
      "grad_norm": 0.705153226852417,
      "learning_rate": 9.873140143255036e-05,
      "loss": 2.1873,
      "step": 22
    },
    {
      "epoch": 0.3898305084745763,
      "grad_norm": 0.7329670190811157,
      "learning_rate": 9.85122569105338e-05,
      "loss": 2.6215,
      "step": 23
    },
    {
      "epoch": 0.4067796610169492,
      "grad_norm": 1.136795163154602,
      "learning_rate": 9.827594495101823e-05,
      "loss": 2.8488,
      "step": 24
    },
    {
      "epoch": 0.423728813559322,
      "grad_norm": 1.0769141912460327,
      "learning_rate": 9.802254917969032e-05,
      "loss": 2.8395,
      "step": 25
    },
    {
      "epoch": 0.4406779661016949,
      "grad_norm": 1.4403115510940552,
      "learning_rate": 9.775215926782788e-05,
      "loss": 2.6802,
      "step": 26
    },
    {
      "epoch": 0.4576271186440678,
      "grad_norm": 1.4279862642288208,
      "learning_rate": 9.746487090056713e-05,
      "loss": 2.7192,
      "step": 27
    },
    {
      "epoch": 0.4745762711864407,
      "grad_norm": 1.699432611465454,
      "learning_rate": 9.716078574304189e-05,
      "loss": 2.8853,
      "step": 28
    },
    {
      "epoch": 0.4915254237288136,
      "grad_norm": 1.4521034955978394,
      "learning_rate": 9.684001140440639e-05,
      "loss": 1.9164,
      "step": 29
    },
    {
      "epoch": 0.5084745762711864,
      "grad_norm": 2.434119939804077,
      "learning_rate": 9.650266139975474e-05,
      "loss": 1.3542,
      "step": 30
    },
    {
      "epoch": 0.5254237288135594,
      "grad_norm": 1.6792948246002197,
      "learning_rate": 9.614885510995047e-05,
      "loss": 1.3436,
      "step": 31
    },
    {
      "epoch": 0.5423728813559322,
      "grad_norm": 1.6474392414093018,
      "learning_rate": 9.577871773938011e-05,
      "loss": 1.1094,
      "step": 32
    },
    {
      "epoch": 0.559322033898305,
      "grad_norm": 1.6065335273742676,
      "learning_rate": 9.539238027164619e-05,
      "loss": 0.9116,
      "step": 33
    },
    {
      "epoch": 0.576271186440678,
      "grad_norm": 1.514753818511963,
      "learning_rate": 9.498997942321483e-05,
      "loss": 0.8389,
      "step": 34
    },
    {
      "epoch": 0.5932203389830508,
      "grad_norm": 1.2533358335494995,
      "learning_rate": 9.457165759503493e-05,
      "loss": 0.9727,
      "step": 35
    },
    {
      "epoch": 0.6101694915254238,
      "grad_norm": 0.8802417516708374,
      "learning_rate": 9.413756282214537e-05,
      "loss": 1.7009,
      "step": 36
    },
    {
      "epoch": 0.6271186440677966,
      "grad_norm": 1.1750346422195435,
      "learning_rate": 9.368784872128878e-05,
      "loss": 2.5651,
      "step": 37
    },
    {
      "epoch": 0.6440677966101694,
      "grad_norm": 1.331346035003662,
      "learning_rate": 9.322267443654972e-05,
      "loss": 2.5368,
      "step": 38
    },
    {
      "epoch": 0.6610169491525424,
      "grad_norm": 1.1209417581558228,
      "learning_rate": 9.274220458303727e-05,
      "loss": 2.8612,
      "step": 39
    },
    {
      "epoch": 0.6779661016949152,
      "grad_norm": 1.2335385084152222,
      "learning_rate": 9.224660918863104e-05,
      "loss": 2.6824,
      "step": 40
    },
    {
      "epoch": 0.6949152542372882,
      "grad_norm": 1.1797600984573364,
      "learning_rate": 9.173606363381219e-05,
      "loss": 2.4775,
      "step": 41
    },
    {
      "epoch": 0.711864406779661,
      "grad_norm": 1.6770628690719604,
      "learning_rate": 9.121074858959997e-05,
      "loss": 2.7293,
      "step": 42
    },
    {
      "epoch": 0.7288135593220338,
      "grad_norm": 1.0169050693511963,
      "learning_rate": 9.067084995361623e-05,
      "loss": 1.3915,
      "step": 43
    },
    {
      "epoch": 0.7457627118644068,
      "grad_norm": 1.1066895723342896,
      "learning_rate": 9.011655878430019e-05,
      "loss": 0.5636,
      "step": 44
    },
    {
      "epoch": 0.7627118644067796,
      "grad_norm": 0.9063847661018372,
      "learning_rate": 8.954807123329704e-05,
      "loss": 0.1767,
      "step": 45
    },
    {
      "epoch": 0.7796610169491526,
      "grad_norm": 0.5006846189498901,
      "learning_rate": 8.896558847604414e-05,
      "loss": 0.3629,
      "step": 46
    },
    {
      "epoch": 0.7966101694915254,
      "grad_norm": 0.42200618982315063,
      "learning_rate": 8.836931664057935e-05,
      "loss": 0.2745,
      "step": 47
    },
    {
      "epoch": 0.8135593220338984,
      "grad_norm": 0.3802186846733093,
      "learning_rate": 8.775946673459681e-05,
      "loss": 0.1882,
      "step": 48
    },
    {
      "epoch": 0.8305084745762712,
      "grad_norm": 0.3861039876937866,
      "learning_rate": 8.713625457077585e-05,
      "loss": 0.4487,
      "step": 49
    },
    {
      "epoch": 0.847457627118644,
      "grad_norm": 0.9502959847450256,
      "learning_rate": 8.649990069040961e-05,
      "loss": 2.1698,
      "step": 50
    },
    {
      "epoch": 0.847457627118644,
      "eval_loss": 1.0403923988342285,
      "eval_runtime": 1.442,
      "eval_samples_per_second": 69.349,
      "eval_steps_per_second": 17.337,
      "step": 50
    },
    {
      "epoch": 0.864406779661017,
      "grad_norm": 1.0427058935165405,
      "learning_rate": 8.585063028536016e-05,
      "loss": 2.4816,
      "step": 51
    },
    {
      "epoch": 0.8813559322033898,
      "grad_norm": 0.9536698460578918,
      "learning_rate": 8.518867311836808e-05,
      "loss": 2.379,
      "step": 52
    },
    {
      "epoch": 0.8983050847457628,
      "grad_norm": 1.1528958082199097,
      "learning_rate": 8.451426344174433e-05,
      "loss": 2.5705,
      "step": 53
    },
    {
      "epoch": 0.9152542372881356,
      "grad_norm": 1.075803518295288,
      "learning_rate": 8.382763991447344e-05,
      "loss": 2.3945,
      "step": 54
    },
    {
      "epoch": 0.9322033898305084,
      "grad_norm": 1.1288622617721558,
      "learning_rate": 8.312904551775731e-05,
      "loss": 2.536,
      "step": 55
    },
    {
      "epoch": 0.9491525423728814,
      "grad_norm": 1.494862675666809,
      "learning_rate": 8.241872746902935e-05,
      "loss": 2.5827,
      "step": 56
    },
    {
      "epoch": 0.9661016949152542,
      "grad_norm": 0.41931426525115967,
      "learning_rate": 8.169693713446959e-05,
      "loss": 0.7727,
      "step": 57
    },
    {
      "epoch": 0.9830508474576272,
      "grad_norm": 0.464871883392334,
      "learning_rate": 8.096392994005177e-05,
      "loss": 1.2605,
      "step": 58
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.0274232625961304,
      "learning_rate": 8.021996528115335e-05,
      "loss": 2.5275,
      "step": 59
    },
    {
      "epoch": 1.0169491525423728,
      "grad_norm": 0.5695710182189941,
      "learning_rate": 7.946530643076138e-05,
      "loss": 1.3716,
      "step": 60
    },
    {
      "epoch": 1.0338983050847457,
      "grad_norm": 0.29576823115348816,
      "learning_rate": 7.870022044630569e-05,
      "loss": 0.3392,
      "step": 61
    },
    {
      "epoch": 1.0508474576271187,
      "grad_norm": 0.29110977053642273,
      "learning_rate": 7.792497807515317e-05,
      "loss": 0.3041,
      "step": 62
    },
    {
      "epoch": 1.0677966101694916,
      "grad_norm": 0.27382704615592957,
      "learning_rate": 7.713985365879606e-05,
      "loss": 0.4193,
      "step": 63
    },
    {
      "epoch": 1.0847457627118644,
      "grad_norm": 0.19342516362667084,
      "learning_rate": 7.63451250357685e-05,
      "loss": 0.1109,
      "step": 64
    },
    {
      "epoch": 1.1016949152542372,
      "grad_norm": 0.1454094499349594,
      "learning_rate": 7.55410734433254e-05,
      "loss": 0.0198,
      "step": 65
    },
    {
      "epoch": 1.11864406779661,
      "grad_norm": 0.23074690997600555,
      "learning_rate": 7.472798341791877e-05,
      "loss": 0.1309,
      "step": 66
    },
    {
      "epoch": 1.1355932203389831,
      "grad_norm": 0.47609075903892517,
      "learning_rate": 7.390614269450634e-05,
      "loss": 1.3382,
      "step": 67
    },
    {
      "epoch": 1.152542372881356,
      "grad_norm": 0.7256209254264832,
      "learning_rate": 7.307584210472844e-05,
      "loss": 2.2253,
      "step": 68
    },
    {
      "epoch": 1.1694915254237288,
      "grad_norm": 0.7721383571624756,
      "learning_rate": 7.223737547398898e-05,
      "loss": 2.1726,
      "step": 69
    },
    {
      "epoch": 1.1864406779661016,
      "grad_norm": 0.8785566091537476,
      "learning_rate": 7.139103951747695e-05,
      "loss": 2.4489,
      "step": 70
    },
    {
      "epoch": 1.2033898305084745,
      "grad_norm": 0.797492265701294,
      "learning_rate": 7.053713373516538e-05,
      "loss": 2.2085,
      "step": 71
    },
    {
      "epoch": 1.2203389830508475,
      "grad_norm": 0.8545417785644531,
      "learning_rate": 6.967596030582478e-05,
      "loss": 2.4864,
      "step": 72
    },
    {
      "epoch": 1.2372881355932204,
      "grad_norm": 1.2952442169189453,
      "learning_rate": 6.880782398008862e-05,
      "loss": 2.3607,
      "step": 73
    },
    {
      "epoch": 1.2542372881355932,
      "grad_norm": 0.4277438223361969,
      "learning_rate": 6.793303197260864e-05,
      "loss": 1.2012,
      "step": 74
    },
    {
      "epoch": 1.271186440677966,
      "grad_norm": 0.23187437653541565,
      "learning_rate": 6.70518938533383e-05,
      "loss": 0.1912,
      "step": 75
    },
    {
      "epoch": 1.288135593220339,
      "grad_norm": 0.13725751638412476,
      "learning_rate": 6.616472143798261e-05,
      "loss": 0.1406,
      "step": 76
    },
    {
      "epoch": 1.305084745762712,
      "grad_norm": 0.23800960183143616,
      "learning_rate": 6.527182867765332e-05,
      "loss": 0.0717,
      "step": 77
    },
    {
      "epoch": 1.3220338983050848,
      "grad_norm": 0.16830310225486755,
      "learning_rate": 6.437353154776849e-05,
      "loss": 0.1892,
      "step": 78
    },
    {
      "epoch": 1.3389830508474576,
      "grad_norm": 0.05917459353804588,
      "learning_rate": 6.347014793623547e-05,
      "loss": 0.0077,
      "step": 79
    },
    {
      "epoch": 1.3559322033898304,
      "grad_norm": 0.17031961679458618,
      "learning_rate": 6.256199753095745e-05,
      "loss": 0.2442,
      "step": 80
    },
    {
      "epoch": 1.3728813559322033,
      "grad_norm": 0.603077232837677,
      "learning_rate": 6.164940170670266e-05,
      "loss": 1.8995,
      "step": 81
    },
    {
      "epoch": 1.3898305084745763,
      "grad_norm": 0.6798323392868042,
      "learning_rate": 6.0732683411376935e-05,
      "loss": 2.2423,
      "step": 82
    },
    {
      "epoch": 1.4067796610169492,
      "grad_norm": 0.8995802998542786,
      "learning_rate": 5.98121670517393e-05,
      "loss": 2.1578,
      "step": 83
    },
    {
      "epoch": 1.423728813559322,
      "grad_norm": 0.7790073752403259,
      "learning_rate": 5.8888178378601565e-05,
      "loss": 2.3126,
      "step": 84
    },
    {
      "epoch": 1.4406779661016949,
      "grad_norm": 0.9033922553062439,
      "learning_rate": 5.796104437155213e-05,
      "loss": 2.207,
      "step": 85
    },
    {
      "epoch": 1.457627118644068,
      "grad_norm": 0.8630293607711792,
      "learning_rate": 5.7031093123244925e-05,
      "loss": 2.1339,
      "step": 86
    },
    {
      "epoch": 1.4745762711864407,
      "grad_norm": 1.140993595123291,
      "learning_rate": 5.6098653723294604e-05,
      "loss": 2.2742,
      "step": 87
    },
    {
      "epoch": 1.4915254237288136,
      "grad_norm": 0.5041856169700623,
      "learning_rate": 5.516405614181883e-05,
      "loss": 1.2441,
      "step": 88
    },
    {
      "epoch": 1.5084745762711864,
      "grad_norm": 0.0990825667977333,
      "learning_rate": 5.4227631112668955e-05,
      "loss": 0.0708,
      "step": 89
    },
    {
      "epoch": 1.5254237288135593,
      "grad_norm": 0.1579853743314743,
      "learning_rate": 5.3289710016390535e-05,
      "loss": 0.2237,
      "step": 90
    },
    {
      "epoch": 1.542372881355932,
      "grad_norm": 0.1326770782470703,
      "learning_rate": 5.2350624762954884e-05,
      "loss": 0.1283,
      "step": 91
    },
    {
      "epoch": 1.559322033898305,
      "grad_norm": 0.13696810603141785,
      "learning_rate": 5.14107076743033e-05,
      "loss": 0.1354,
      "step": 92
    },
    {
      "epoch": 1.576271186440678,
      "grad_norm": 0.039330050349235535,
      "learning_rate": 5.047029136674563e-05,
      "loss": 0.0049,
      "step": 93
    },
    {
      "epoch": 1.5932203389830508,
      "grad_norm": 0.17127054929733276,
      "learning_rate": 4.95297086332544e-05,
      "loss": 0.2072,
      "step": 94
    },
    {
      "epoch": 1.6101694915254239,
      "grad_norm": 0.502240777015686,
      "learning_rate": 4.858929232569671e-05,
      "loss": 1.5421,
      "step": 95
    },
    {
      "epoch": 1.6271186440677967,
      "grad_norm": 0.7475689053535461,
      "learning_rate": 4.7649375237045135e-05,
      "loss": 2.2061,
      "step": 96
    },
    {
      "epoch": 1.6440677966101696,
      "grad_norm": 0.7506973743438721,
      "learning_rate": 4.671028998360947e-05,
      "loss": 2.0706,
      "step": 97
    },
    {
      "epoch": 1.6610169491525424,
      "grad_norm": 0.8322485685348511,
      "learning_rate": 4.577236888733105e-05,
      "loss": 2.3213,
      "step": 98
    },
    {
      "epoch": 1.6779661016949152,
      "grad_norm": 0.8912888765335083,
      "learning_rate": 4.483594385818118e-05,
      "loss": 2.2682,
      "step": 99
    },
    {
      "epoch": 1.694915254237288,
      "grad_norm": 0.9926512241363525,
      "learning_rate": 4.39013462767054e-05,
      "loss": 2.2907,
      "step": 100
    },
    {
      "epoch": 1.694915254237288,
      "eval_loss": 0.9476182460784912,
      "eval_runtime": 1.4397,
      "eval_samples_per_second": 69.46,
      "eval_steps_per_second": 17.365,
      "step": 100
    },
    {
      "epoch": 1.711864406779661,
      "grad_norm": 1.0757006406784058,
      "learning_rate": 4.29689068767551e-05,
      "loss": 2.3057,
      "step": 101
    },
    {
      "epoch": 1.7288135593220337,
      "grad_norm": 0.5664078593254089,
      "learning_rate": 4.203895562844789e-05,
      "loss": 1.469,
      "step": 102
    },
    {
      "epoch": 1.7457627118644068,
      "grad_norm": 0.09226689487695694,
      "learning_rate": 4.1111821621398446e-05,
      "loss": 0.0674,
      "step": 103
    },
    {
      "epoch": 1.7627118644067796,
      "grad_norm": 0.07321758568286896,
      "learning_rate": 4.0187832948260705e-05,
      "loss": 0.0404,
      "step": 104
    },
    {
      "epoch": 1.7796610169491527,
      "grad_norm": 0.24070608615875244,
      "learning_rate": 3.926731658862307e-05,
      "loss": 0.2084,
      "step": 105
    },
    {
      "epoch": 1.7966101694915255,
      "grad_norm": 0.027658900246024132,
      "learning_rate": 3.835059829329735e-05,
      "loss": 0.0039,
      "step": 106
    },
    {
      "epoch": 1.8135593220338984,
      "grad_norm": 0.07214166969060898,
      "learning_rate": 3.7438002469042565e-05,
      "loss": 0.0415,
      "step": 107
    },
    {
      "epoch": 1.8305084745762712,
      "grad_norm": 0.22489815950393677,
      "learning_rate": 3.6529852063764545e-05,
      "loss": 0.3323,
      "step": 108
    },
    {
      "epoch": 1.847457627118644,
      "grad_norm": 0.525007963180542,
      "learning_rate": 3.562646845223153e-05,
      "loss": 1.4499,
      "step": 109
    },
    {
      "epoch": 1.8644067796610169,
      "grad_norm": 0.7562161684036255,
      "learning_rate": 3.4728171322346694e-05,
      "loss": 2.1267,
      "step": 110
    },
    {
      "epoch": 1.8813559322033897,
      "grad_norm": 0.7749287486076355,
      "learning_rate": 3.38352785620174e-05,
      "loss": 2.1855,
      "step": 111
    },
    {
      "epoch": 1.8983050847457628,
      "grad_norm": 0.8717202544212341,
      "learning_rate": 3.29481061466617e-05,
      "loss": 2.2716,
      "step": 112
    },
    {
      "epoch": 1.9152542372881356,
      "grad_norm": 0.990043580532074,
      "learning_rate": 3.2066968027391374e-05,
      "loss": 2.1828,
      "step": 113
    },
    {
      "epoch": 1.9322033898305084,
      "grad_norm": 0.9501929879188538,
      "learning_rate": 3.119217601991139e-05,
      "loss": 1.9919,
      "step": 114
    },
    {
      "epoch": 1.9491525423728815,
      "grad_norm": 1.3463528156280518,
      "learning_rate": 3.0324039694175233e-05,
      "loss": 2.3176,
      "step": 115
    },
    {
      "epoch": 1.9661016949152543,
      "grad_norm": 0.2480294406414032,
      "learning_rate": 2.946286626483463e-05,
      "loss": 0.4455,
      "step": 116
    },
    {
      "epoch": 1.9830508474576272,
      "grad_norm": 0.5426979660987854,
      "learning_rate": 2.8608960482523056e-05,
      "loss": 1.2601,
      "step": 117
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.9084144234657288,
      "learning_rate": 2.7762624526011038e-05,
      "loss": 2.1384,
      "step": 118
    },
    {
      "epoch": 2.016949152542373,
      "grad_norm": 0.38337242603302,
      "learning_rate": 2.6924157895271563e-05,
      "loss": 0.9181,
      "step": 119
    },
    {
      "epoch": 2.0338983050847457,
      "grad_norm": 0.09438680857419968,
      "learning_rate": 2.6093857305493664e-05,
      "loss": 0.064,
      "step": 120
    },
    {
      "epoch": 2.0508474576271185,
      "grad_norm": 0.025368427857756615,
      "learning_rate": 2.5272016582081236e-05,
      "loss": 0.0037,
      "step": 121
    },
    {
      "epoch": 2.0677966101694913,
      "grad_norm": 0.22418174147605896,
      "learning_rate": 2.4458926556674615e-05,
      "loss": 0.3752,
      "step": 122
    },
    {
      "epoch": 2.084745762711864,
      "grad_norm": 0.029728621244430542,
      "learning_rate": 2.3654874964231518e-05,
      "loss": 0.0035,
      "step": 123
    },
    {
      "epoch": 2.1016949152542375,
      "grad_norm": 0.07155339419841766,
      "learning_rate": 2.2860146341203937e-05,
      "loss": 0.0405,
      "step": 124
    },
    {
      "epoch": 2.1186440677966103,
      "grad_norm": 0.08262301981449127,
      "learning_rate": 2.207502192484685e-05,
      "loss": 0.0428,
      "step": 125
    },
    {
      "epoch": 2.135593220338983,
      "grad_norm": 0.5090848803520203,
      "learning_rate": 2.1299779553694323e-05,
      "loss": 1.3961,
      "step": 126
    },
    {
      "epoch": 2.152542372881356,
      "grad_norm": 0.6652891635894775,
      "learning_rate": 2.053469356923865e-05,
      "loss": 2.0337,
      "step": 127
    },
    {
      "epoch": 2.169491525423729,
      "grad_norm": 0.7932724356651306,
      "learning_rate": 1.978003471884665e-05,
      "loss": 2.2015,
      "step": 128
    },
    {
      "epoch": 2.1864406779661016,
      "grad_norm": 0.828244686126709,
      "learning_rate": 1.9036070059948252e-05,
      "loss": 2.0406,
      "step": 129
    },
    {
      "epoch": 2.2033898305084745,
      "grad_norm": 0.8815770149230957,
      "learning_rate": 1.8303062865530406e-05,
      "loss": 2.0167,
      "step": 130
    },
    {
      "epoch": 2.2203389830508473,
      "grad_norm": 0.9002049565315247,
      "learning_rate": 1.7581272530970667e-05,
      "loss": 2.0821,
      "step": 131
    },
    {
      "epoch": 2.23728813559322,
      "grad_norm": 1.0344882011413574,
      "learning_rate": 1.6870954482242707e-05,
      "loss": 2.0685,
      "step": 132
    },
    {
      "epoch": 2.2542372881355934,
      "grad_norm": 0.44666269421577454,
      "learning_rate": 1.6172360085526565e-05,
      "loss": 1.1569,
      "step": 133
    },
    {
      "epoch": 2.2711864406779663,
      "grad_norm": 0.09210528433322906,
      "learning_rate": 1.5485736558255697e-05,
      "loss": 0.0479,
      "step": 134
    },
    {
      "epoch": 2.288135593220339,
      "grad_norm": 0.038695137947797775,
      "learning_rate": 1.4811326881631937e-05,
      "loss": 0.0034,
      "step": 135
    },
    {
      "epoch": 2.305084745762712,
      "grad_norm": 0.1461106240749359,
      "learning_rate": 1.4149369714639853e-05,
      "loss": 0.1391,
      "step": 136
    },
    {
      "epoch": 2.3220338983050848,
      "grad_norm": 0.16508442163467407,
      "learning_rate": 1.3500099309590397e-05,
      "loss": 0.1813,
      "step": 137
    },
    {
      "epoch": 2.3389830508474576,
      "grad_norm": 0.12389306724071503,
      "learning_rate": 1.2863745429224144e-05,
      "loss": 0.097,
      "step": 138
    },
    {
      "epoch": 2.3559322033898304,
      "grad_norm": 0.2678169012069702,
      "learning_rate": 1.2240533265403198e-05,
      "loss": 0.4644,
      "step": 139
    },
    {
      "epoch": 2.3728813559322033,
      "grad_norm": 0.6074098348617554,
      "learning_rate": 1.1630683359420652e-05,
      "loss": 2.0744,
      "step": 140
    },
    {
      "epoch": 2.389830508474576,
      "grad_norm": 0.7297008633613586,
      "learning_rate": 1.103441152395588e-05,
      "loss": 2.0194,
      "step": 141
    },
    {
      "epoch": 2.406779661016949,
      "grad_norm": 0.7776730060577393,
      "learning_rate": 1.0451928766702979e-05,
      "loss": 2.083,
      "step": 142
    },
    {
      "epoch": 2.423728813559322,
      "grad_norm": 0.8881759643554688,
      "learning_rate": 9.883441215699823e-06,
      "loss": 2.5883,
      "step": 143
    },
    {
      "epoch": 2.440677966101695,
      "grad_norm": 0.8794331550598145,
      "learning_rate": 9.329150046383772e-06,
      "loss": 2.0489,
      "step": 144
    },
    {
      "epoch": 2.457627118644068,
      "grad_norm": 0.8844050765037537,
      "learning_rate": 8.789251410400023e-06,
      "loss": 2.1398,
      "step": 145
    },
    {
      "epoch": 2.4745762711864407,
      "grad_norm": 1.1741251945495605,
      "learning_rate": 8.263936366187824e-06,
      "loss": 2.1663,
      "step": 146
    },
    {
      "epoch": 2.4915254237288136,
      "grad_norm": 0.4704148471355438,
      "learning_rate": 7.753390811368971e-06,
      "loss": 1.4645,
      "step": 147
    },
    {
      "epoch": 2.5084745762711864,
      "grad_norm": 0.20011013746261597,
      "learning_rate": 7.257795416962753e-06,
      "loss": 0.308,
      "step": 148
    },
    {
      "epoch": 2.5254237288135593,
      "grad_norm": 0.19620303809642792,
      "learning_rate": 6.777325563450282e-06,
      "loss": 0.1889,
      "step": 149
    },
    {
      "epoch": 2.542372881355932,
      "grad_norm": 0.022152384743094444,
      "learning_rate": 6.312151278711237e-06,
      "loss": 0.0033,
      "step": 150
    },
    {
      "epoch": 2.542372881355932,
      "eval_loss": 0.9148275852203369,
      "eval_runtime": 1.4467,
      "eval_samples_per_second": 69.125,
      "eval_steps_per_second": 17.281,
      "step": 150
    },
    {
      "epoch": 2.559322033898305,
      "grad_norm": 0.11883600056171417,
      "learning_rate": 5.86243717785463e-06,
      "loss": 0.0865,
      "step": 151
    },
    {
      "epoch": 2.576271186440678,
      "grad_norm": 0.029807042330503464,
      "learning_rate": 5.428342404965076e-06,
      "loss": 0.0033,
      "step": 152
    },
    {
      "epoch": 2.593220338983051,
      "grad_norm": 0.15622468292713165,
      "learning_rate": 5.010020576785174e-06,
      "loss": 0.1535,
      "step": 153
    },
    {
      "epoch": 2.610169491525424,
      "grad_norm": 0.4695366322994232,
      "learning_rate": 4.607619728353818e-06,
      "loss": 1.2671,
      "step": 154
    },
    {
      "epoch": 2.6271186440677967,
      "grad_norm": 0.7809627652168274,
      "learning_rate": 4.221282260619891e-06,
      "loss": 1.7782,
      "step": 155
    },
    {
      "epoch": 2.6440677966101696,
      "grad_norm": 0.7714522480964661,
      "learning_rate": 3.851144890049535e-06,
      "loss": 2.0438,
      "step": 156
    },
    {
      "epoch": 2.6610169491525424,
      "grad_norm": 0.9179351329803467,
      "learning_rate": 3.4973386002452535e-06,
      "loss": 2.2235,
      "step": 157
    },
    {
      "epoch": 2.6779661016949152,
      "grad_norm": 0.8256776332855225,
      "learning_rate": 3.159988595593616e-06,
      "loss": 1.9886,
      "step": 158
    },
    {
      "epoch": 2.694915254237288,
      "grad_norm": 0.9762132167816162,
      "learning_rate": 2.839214256958106e-06,
      "loss": 2.0266,
      "step": 159
    },
    {
      "epoch": 2.711864406779661,
      "grad_norm": 1.1027181148529053,
      "learning_rate": 2.53512909943287e-06,
      "loss": 2.1582,
      "step": 160
    },
    {
      "epoch": 2.7288135593220337,
      "grad_norm": 0.5595541000366211,
      "learning_rate": 2.2478407321721296e-06,
      "loss": 1.4767,
      "step": 161
    },
    {
      "epoch": 2.7457627118644066,
      "grad_norm": 0.19766104221343994,
      "learning_rate": 1.977450820309684e-06,
      "loss": 0.2643,
      "step": 162
    },
    {
      "epoch": 2.7627118644067794,
      "grad_norm": 0.2085597813129425,
      "learning_rate": 1.7240550489817653e-06,
      "loss": 0.2502,
      "step": 163
    },
    {
      "epoch": 2.7796610169491527,
      "grad_norm": 0.2631925940513611,
      "learning_rate": 1.4877430894662036e-06,
      "loss": 0.4407,
      "step": 164
    },
    {
      "epoch": 2.7966101694915255,
      "grad_norm": 0.1086735650897026,
      "learning_rate": 1.268598567449647e-06,
      "loss": 0.0985,
      "step": 165
    },
    {
      "epoch": 2.8135593220338984,
      "grad_norm": 0.1114293783903122,
      "learning_rate": 1.0666990334342707e-06,
      "loss": 0.0853,
      "step": 166
    },
    {
      "epoch": 2.830508474576271,
      "grad_norm": 0.20077882707118988,
      "learning_rate": 8.821159352943143e-07,
      "loss": 0.3038,
      "step": 167
    },
    {
      "epoch": 2.847457627118644,
      "grad_norm": 0.5867683291435242,
      "learning_rate": 7.149145929922607e-07,
      "loss": 1.7456,
      "step": 168
    },
    {
      "epoch": 2.864406779661017,
      "grad_norm": 0.8998249173164368,
      "learning_rate": 5.651541754634726e-07,
      "loss": 2.1784,
      "step": 169
    },
    {
      "epoch": 2.8813559322033897,
      "grad_norm": 0.7912001609802246,
      "learning_rate": 4.3288767967760715e-07,
      "loss": 1.8512,
      "step": 170
    },
    {
      "epoch": 2.898305084745763,
      "grad_norm": 0.7731630206108093,
      "learning_rate": 3.1816191188415166e-07,
      "loss": 2.1491,
      "step": 171
    },
    {
      "epoch": 2.915254237288136,
      "grad_norm": 0.860531210899353,
      "learning_rate": 2.2101747104866788e-07,
      "loss": 1.8962,
      "step": 172
    },
    {
      "epoch": 2.9322033898305087,
      "grad_norm": 0.9022953510284424,
      "learning_rate": 1.4148873448573408e-07,
      "loss": 2.2015,
      "step": 173
    },
    {
      "epoch": 2.9491525423728815,
      "grad_norm": 1.231516718864441,
      "learning_rate": 7.960384569353219e-08,
      "loss": 2.2436,
      "step": 174
    },
    {
      "epoch": 2.9661016949152543,
      "grad_norm": 0.2086687535047531,
      "learning_rate": 3.538470439448105e-08,
      "loss": 0.2974,
      "step": 175
    },
    {
      "epoch": 2.983050847457627,
      "grad_norm": 0.2978679835796356,
      "learning_rate": 8.846958785418968e-09,
      "loss": 0.6034,
      "step": 176
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.9400612711906433,
      "learning_rate": 0.0,
      "loss": 2.0483,
      "step": 177
    }
  ],
  "logging_steps": 1,
  "max_steps": 177,
  "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": 4366480939941888.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}