{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "global_step": 351,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 5e-05,
      "loss": 0.1291,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001,
      "loss": 0.1354,
      "step": 4
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.1399,
      "step": 6
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.143,
      "step": 8
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001999832224185224,
      "loss": 0.1455,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019993289530383432,
      "loss": 0.1346,
      "step": 12
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019984903554328114,
      "loss": 0.1458,
      "step": 14
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019973167127614215,
      "loss": 0.1354,
      "step": 16
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001995808418841885,
      "loss": 0.1248,
      "step": 18
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001993965979784684,
      "loss": 0.1322,
      "step": 20
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001991790013823246,
      "loss": 0.1371,
      "step": 22
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001989281251106496,
      "loss": 0.1195,
      "step": 24
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019864405334538517,
      "loss": 0.1193,
      "step": 26
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000198326881407275,
      "loss": 0.1313,
      "step": 28
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019797671572387984,
      "loss": 0.148,
      "step": 30
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001975936737938653,
      "loss": 0.1384,
      "step": 32
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019717788414757523,
      "loss": 0.1317,
      "step": 34
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019672948630390294,
      "loss": 0.1364,
      "step": 36
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019624863072347564,
      "loss": 0.127,
      "step": 38
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019573547875816684,
      "loss": 0.1281,
      "step": 40
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001951902025969548,
      "loss": 0.1303,
      "step": 42
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001946129852081439,
      "loss": 0.1364,
      "step": 44
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019400402027796955,
      "loss": 0.1262,
      "step": 46
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019336351214560647,
      "loss": 0.1244,
      "step": 48
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001926916757346022,
      "loss": 0.1261,
      "step": 50
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001919887364807592,
      "loss": 0.1276,
      "step": 52
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019125493025648962,
      "loss": 0.1181,
      "step": 54
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019049050329166778,
      "loss": 0.1218,
      "step": 56
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001896957120910074,
      "loss": 0.1255,
      "step": 58
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00018887082334799097,
      "loss": 0.1279,
      "step": 60
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018801611385538047,
      "loss": 0.1227,
      "step": 62
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018713187041233896,
      "loss": 0.132,
      "step": 64
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018621838972819458,
      "loss": 0.1249,
      "step": 66
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018527597832287954,
      "loss": 0.1182,
      "step": 68
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018430495242407658,
      "loss": 0.1325,
      "step": 70
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018330563786110834,
      "loss": 0.1209,
      "step": 72
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001822783699556049,
      "loss": 0.1322,
      "step": 74
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018122349340898595,
      "loss": 0.1225,
      "step": 76
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018014136218679567,
      "loss": 0.1209,
      "step": 78
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00017903233939992906,
      "loss": 0.125,
      "step": 80
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00017789679718278943,
      "loss": 0.1232,
      "step": 82
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00017673511656841822,
      "loss": 0.1199,
      "step": 84
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017554768736063859,
      "loss": 0.1228,
      "step": 86
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017433490800325614,
      "loss": 0.1303,
      "step": 88
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017309718544636057,
      "loss": 0.12,
      "step": 90
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017183493500977278,
      "loss": 0.1164,
      "step": 92
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00017054858024368366,
      "loss": 0.123,
      "step": 94
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00016923855278653114,
      "loss": 0.1156,
      "step": 96
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016790529222016328,
      "loss": 0.1199,
      "step": 98
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016654924592233568,
      "loss": 0.115,
      "step": 100
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016517086891659335,
      "loss": 0.1248,
      "step": 102
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016377062371958668,
      "loss": 0.1229,
      "step": 104
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016234898018587337,
      "loss": 0.1188,
      "step": 106
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00016090641535025774,
      "loss": 0.1209,
      "step": 108
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00015944341326772112,
      "loss": 0.1197,
      "step": 110
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00015796046485099633,
      "loss": 0.1192,
      "step": 112
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001564580677058412,
      "loss": 0.1124,
      "step": 114
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015493672596406598,
      "loss": 0.1189,
      "step": 116
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015339695011437127,
      "loss": 0.1123,
      "step": 118
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015183925683105254,
      "loss": 0.1139,
      "step": 120
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00015026416880062931,
      "loss": 0.1165,
      "step": 122
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00014867221454645696,
      "loss": 0.1265,
      "step": 124
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014706392825137964,
      "loss": 0.1179,
      "step": 126
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001454398495784844,
      "loss": 0.1279,
      "step": 128
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014380052349001647,
      "loss": 0.106,
      "step": 130
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014214650006451622,
      "loss": 0.118,
      "step": 132
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014047833431223938,
      "loss": 0.1276,
      "step": 134
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00013879658598892254,
      "loss": 0.1255,
      "step": 136
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.000137101819407956,
      "loss": 0.1191,
      "step": 138
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013539460325102777,
      "loss": 0.111,
      "step": 140
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013367551037730128,
      "loss": 0.1251,
      "step": 142
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00013194511763119172,
      "loss": 0.1193,
      "step": 144
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001302040056488047,
      "loss": 0.11,
      "step": 146
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00012845275866310324,
      "loss": 0.1033,
      "step": 148
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012669196430786713,
      "loss": 0.1149,
      "step": 150
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012492221342051154,
      "loss": 0.1231,
      "step": 152
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00012314409984383066,
      "loss": 0.1244,
      "step": 154
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00012135822022673263,
      "loss": 0.1125,
      "step": 156
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00011956517382403321,
      "loss": 0.1102,
      "step": 158
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001177655622953746,
      "loss": 0.1175,
      "step": 160
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011595998950333793,
      "loss": 0.116,
      "step": 162
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011414906131081575,
      "loss": 0.1144,
      "step": 164
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011233338537771407,
      "loss": 0.1229,
      "step": 166
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011051357095705101,
      "loss": 0.1117,
      "step": 168
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001086902286905209,
      "loss": 0.1144,
      "step": 170
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010686397040359253,
      "loss": 0.109,
      "step": 172
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010503540890020997,
      "loss": 0.1151,
      "step": 174
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010320515775716555,
      "loss": 0.1197,
      "step": 176
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010137383111821266,
      "loss": 0.1073,
      "step": 178
    },
    {
      "epoch": 0.51,
      "learning_rate": 9.954204348798938e-05,
      "loss": 0.1114,
      "step": 180
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.771040952581998e-05,
      "loss": 0.1158,
      "step": 182
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.587954383946517e-05,
      "loss": 0.1103,
      "step": 184
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.405006077888954e-05,
      "loss": 0.1083,
      "step": 186
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.22225742301153e-05,
      "loss": 0.1137,
      "step": 188
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.039769740923183e-05,
      "loss": 0.1123,
      "step": 190
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.857604265663017e-05,
      "loss": 0.1191,
      "step": 192
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.675822123153103e-05,
      "loss": 0.1119,
      "step": 194
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.494484310687581e-05,
      "loss": 0.1196,
      "step": 196
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.313651676464923e-05,
      "loss": 0.1135,
      "step": 198
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.133384899170225e-05,
      "loss": 0.1092,
      "step": 200
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.953744467614354e-05,
      "loss": 0.112,
      "step": 202
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.774790660436858e-05,
      "loss": 0.1099,
      "step": 204
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.596583525879344e-05,
      "loss": 0.1064,
      "step": 206
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.419182861636218e-05,
      "loss": 0.1165,
      "step": 208
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.242648194789446e-05,
      "loss": 0.1215,
      "step": 210
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.067038761834164e-05,
      "loss": 0.1025,
      "step": 212
    },
    {
      "epoch": 0.61,
      "learning_rate": 6.89241348880176e-05,
      "loss": 0.1109,
      "step": 214
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.718830971487165e-05,
      "loss": 0.1157,
      "step": 216
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.546349455786926e-05,
      "loss": 0.1108,
      "step": 218
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.3750268181547e-05,
      "loss": 0.1043,
      "step": 220
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.204920546180728e-05,
      "loss": 0.108,
      "step": 222
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.036087719301763e-05,
      "loss": 0.1125,
      "step": 224
    },
    {
      "epoch": 0.64,
      "learning_rate": 5.868584989647994e-05,
      "loss": 0.1096,
      "step": 226
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.702468563033306e-05,
      "loss": 0.1114,
      "step": 228
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.5377941800953416e-05,
      "loss": 0.0981,
      "step": 230
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.37461709759165e-05,
      "loss": 0.1147,
      "step": 232
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.2129920698581606e-05,
      "loss": 0.1085,
      "step": 234
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.0529733304363145e-05,
      "loss": 0.1133,
      "step": 236
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.894614573874877e-05,
      "loss": 0.1036,
      "step": 238
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.7379689377126735e-05,
      "loss": 0.1106,
      "step": 240
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.583088984648172e-05,
      "loss": 0.1185,
      "step": 242
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.430026684902017e-05,
      "loss": 0.1127,
      "step": 244
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.278833398778306e-05,
      "loss": 0.1187,
      "step": 246
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.129559859430573e-05,
      "loss": 0.12,
      "step": 248
    },
    {
      "epoch": 0.71,
      "learning_rate": 3.982256155838199e-05,
      "loss": 0.1159,
      "step": 250
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.836971715998967e-05,
      "loss": 0.1278,
      "step": 252
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.693755290343409e-05,
      "loss": 0.1188,
      "step": 254
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.5526549353765296e-05,
      "loss": 0.1091,
      "step": 256
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.413717997552376e-05,
      "loss": 0.1014,
      "step": 258
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.276991097386831e-05,
      "loss": 0.1147,
      "step": 260
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.142520113814059e-05,
      "loss": 0.1144,
      "step": 262
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.010350168791719e-05,
      "loss": 0.1161,
      "step": 264
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.8805256121602398e-05,
      "loss": 0.1145,
      "step": 266
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.7530900067611577e-05,
      "loss": 0.1151,
      "step": 268
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.62808611381953e-05,
      "loss": 0.1149,
      "step": 270
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.5055558785953303e-05,
      "loss": 0.114,
      "step": 272
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.3855404163086558e-05,
      "loss": 0.1187,
      "step": 274
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.268079998343453e-05,
      "loss": 0.1108,
      "step": 276
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.1532140387343735e-05,
      "loss": 0.1112,
      "step": 278
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.0409810809413486e-05,
      "loss": 0.1132,
      "step": 280
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.9314187849162524e-05,
      "loss": 0.1098,
      "step": 282
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.8245639144660532e-05,
      "loss": 0.1073,
      "step": 284
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.720452324916656e-05,
      "loss": 0.1079,
      "step": 286
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.619118951081594e-05,
      "loss": 0.1068,
      "step": 288
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.5205977955395812e-05,
      "loss": 0.1162,
      "step": 290
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.424921917224905e-05,
      "loss": 0.111,
      "step": 292
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.3321234203344435e-05,
      "loss": 0.1145,
      "step": 294
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.2422334435550509e-05,
      "loss": 0.1137,
      "step": 296
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1552821496149135e-05,
      "loss": 0.1009,
      "step": 298
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.0712987151624054e-05,
      "loss": 0.1055,
      "step": 300
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.903113209758096e-06,
      "loss": 0.1054,
      "step": 302
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.123471425072206e-06,
      "loss": 0.1042,
      "step": 304
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.374323407637742e-06,
      "loss": 0.1032,
      "step": 306
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.655920535292682e-06,
      "loss": 0.104,
      "step": 308
    },
    {
      "epoch": 0.88,
      "learning_rate": 6.968503869291521e-06,
      "loss": 0.1064,
      "step": 310
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.312304073416719e-06,
      "loss": 0.1081,
      "step": 312
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.687541336579128e-06,
      "loss": 0.1151,
      "step": 314
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.094425298933136e-06,
      "loss": 0.1184,
      "step": 316
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.5331549815317174e-06,
      "loss": 0.1061,
      "step": 318
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.003918719544464e-06,
      "loss": 0.1104,
      "step": 320
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.5068940990615197e-06,
      "loss": 0.1022,
      "step": 322
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.0422478975042246e-06,
      "loss": 0.1042,
      "step": 324
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.6101360276626798e-06,
      "loss": 0.1126,
      "step": 326
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.2107034853789288e-06,
      "loss": 0.1084,
      "step": 328
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.8440843008934561e-06,
      "loss": 0.1047,
      "step": 330
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.5104014938710497e-06,
      "loss": 0.0979,
      "step": 332
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.209767032121345e-06,
      "loss": 0.1147,
      "step": 334
    },
    {
      "epoch": 0.96,
      "learning_rate": 9.422817940278772e-07,
      "loss": 0.1116,
      "step": 336
    },
    {
      "epoch": 0.96,
      "learning_rate": 7.080355346981815e-07,
      "loss": 0.1036,
      "step": 338
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.071068558462732e-07,
      "loss": 0.115,
      "step": 340
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.3956317941779005e-07,
      "loss": 0.108,
      "step": 342
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.054607249663665e-07,
      "loss": 0.1063,
      "step": 344
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.0484449078912439e-07,
      "loss": 0.1028,
      "step": 346
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.774823882738421e-08,
      "loss": 0.1009,
      "step": 348
    },
    {
      "epoch": 1.0,
      "learning_rate": 4.194483337860433e-09,
      "loss": 0.1114,
      "step": 350
    },
    {
      "epoch": 1.0,
      "step": 351,
      "total_flos": 2.4611000956852634e+17,
      "train_loss": 0.11711755568994756,
      "train_runtime": 56238.1049,
      "train_samples_per_second": 3.195,
      "train_steps_per_second": 0.006
    }
  ],
  "max_steps": 351,
  "num_train_epochs": 1,
  "total_flos": 2.4611000956852634e+17,
  "trial_name": null,
  "trial_params": null
}