{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9971671388101981,
  "global_step": 330,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.0005,
      "loss": 2.3487,
      "step": 2
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.001,
      "loss": 2.3946,
      "step": 4
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0009999071352056674,
      "loss": 2.4059,
      "step": 6
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00099962857531815,
      "loss": 2.4061,
      "step": 8
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000999164423811074,
      "loss": 2.3801,
      "step": 10
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0009985148530977765,
      "loss": 2.4389,
      "step": 12
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0009976801044672607,
      "loss": 2.4007,
      "step": 14
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0009966604879945657,
      "loss": 2.4691,
      "step": 16
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0009954563824255878,
      "loss": 2.4015,
      "step": 18
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0009940682350363913,
      "loss": 2.4415,
      "step": 20
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000992496561467063,
      "loss": 2.477,
      "step": 22
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.000990741945530174,
      "loss": 2.4429,
      "step": 24
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0009888050389939172,
      "loss": 2.4429,
      "step": 26
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0009866865613400006,
      "loss": 2.4597,
      "step": 28
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0009843872994963912,
      "loss": 2.4501,
      "step": 30
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0009819081075450014,
      "loss": 2.4307,
      "step": 32
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0009792499064044343,
      "loss": 2.4182,
      "step": 34
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0009764136834878986,
      "loss": 2.4354,
      "step": 36
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0009734004923364257,
      "loss": 2.4323,
      "step": 38
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0009702114522275216,
      "loss": 2.4592,
      "step": 40
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.000966847747759402,
      "loss": 2.4242,
      "step": 42
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0009633106284109611,
      "loss": 2.4355,
      "step": 44
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0009596014080776422,
      "loss": 2.4379,
      "step": 46
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0009557214645833791,
      "loss": 2.3786,
      "step": 48
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0009516722391687902,
      "loss": 2.4303,
      "step": 50
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0009474552359558167,
      "loss": 2.3946,
      "step": 52
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.000943072021389003,
      "loss": 2.4104,
      "step": 54
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0009385242236536259,
      "loss": 2.4266,
      "step": 56
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0009338135320708912,
      "loss": 2.5106,
      "step": 58
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0009289416964704185,
      "loss": 2.4225,
      "step": 60
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0009239105265402525,
      "loss": 2.4745,
      "step": 62
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0009187218911546363,
      "loss": 2.4572,
      "step": 64
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0009133777176798013,
      "loss": 2.4366,
      "step": 66
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0009078799912580304,
      "loss": 2.4021,
      "step": 68
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0009022307540702576,
      "loss": 2.4054,
      "step": 70
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0008964321045774807,
      "loss": 2.4628,
      "step": 72
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0008904861967412702,
      "loss": 2.5038,
      "step": 74
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0008843952392236594,
      "loss": 2.3801,
      "step": 76
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0008781614945667169,
      "loss": 2.4056,
      "step": 78
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0008717872783521047,
      "loss": 2.3334,
      "step": 80
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0008652749583409339,
      "loss": 2.3913,
      "step": 82
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0008586269535942384,
      "loss": 2.3784,
      "step": 84
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0008518457335743926,
      "loss": 2.4436,
      "step": 86
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0008449338172278058,
      "loss": 2.3735,
      "step": 88
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0008378937720492384,
      "loss": 2.374,
      "step": 90
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0008307282131280805,
      "loss": 2.4064,
      "step": 92
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.000823439802176954,
      "loss": 2.4124,
      "step": 94
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0008160312465429952,
      "loss": 2.4181,
      "step": 96
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0008085052982021848,
      "loss": 2.4253,
      "step": 98
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0008008647527371022,
      "loss": 2.4678,
      "step": 100
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0007931124482984802,
      "loss": 2.4738,
      "step": 102
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0007852512645509479,
      "loss": 2.3738,
      "step": 104
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0007772841216033533,
      "loss": 2.4081,
      "step": 106
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0007692139789240611,
      "loss": 2.3738,
      "step": 108
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0007610438342416319,
      "loss": 2.3701,
      "step": 110
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0007527767224312882,
      "loss": 2.4355,
      "step": 112
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.000744415714387582,
      "loss": 2.4036,
      "step": 114
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0007359639158836828,
      "loss": 2.3746,
      "step": 116
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0007274244664177097,
      "loss": 2.4855,
      "step": 118
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0007188005380465365,
      "loss": 2.379,
      "step": 120
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.000710095334207501,
      "loss": 2.4178,
      "step": 122
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0007013120885284599,
      "loss": 2.4561,
      "step": 124
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0006924540636266272,
      "loss": 2.4024,
      "step": 126
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.000683524549896646,
      "loss": 2.4172,
      "step": 128
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0006745268642883404,
      "loss": 2.3858,
      "step": 130
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0006654643490746042,
      "loss": 2.3547,
      "step": 132
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0006563403706098833,
      "loss": 2.4372,
      "step": 134
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0006471583180797121,
      "loss": 2.3785,
      "step": 136
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0006379216022417695,
      "loss": 2.3815,
      "step": 138
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0006286336541589224,
      "loss": 2.4209,
      "step": 140
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0006192979239247243,
      "loss": 2.3962,
      "step": 142
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0006099178793818478,
      "loss": 2.3626,
      "step": 144
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0006004970048339225,
      "loss": 2.3991,
      "step": 146
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0005910387997512573,
      "loss": 2.4396,
      "step": 148
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0005815467774709313,
      "loss": 2.3816,
      "step": 150
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0005720244638917323,
      "loss": 2.3866,
      "step": 152
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0005624753961644281,
      "loss": 2.4035,
      "step": 154
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0005529031213778615,
      "loss": 2.4063,
      "step": 156
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0005433111952413496,
      "loss": 2.3944,
      "step": 158
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0005337031807638841,
      "loss": 2.4192,
      "step": 160
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0005240826469306187,
      "loss": 2.3603,
      "step": 162
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0005144531673771364,
      "loss": 2.4041,
      "step": 164
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0005048183190619903,
      "loss": 2.8813,
      "step": 166
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0004951816809380097,
      "loss": 2.2786,
      "step": 168
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0004855468326228638,
      "loss": 2.2886,
      "step": 170
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00047591735306938137,
      "loss": 2.1822,
      "step": 172
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00046629681923611606,
      "loss": 2.2589,
      "step": 174
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0004566888047586507,
      "loss": 2.2625,
      "step": 176
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00044709687862213866,
      "loss": 2.2715,
      "step": 178
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.000437524603835572,
      "loss": 2.1988,
      "step": 180
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.000427975536108268,
      "loss": 2.3257,
      "step": 182
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00041845322252906863,
      "loss": 2.3026,
      "step": 184
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00040896120024874283,
      "loss": 2.2306,
      "step": 186
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0003995029951660776,
      "loss": 2.2269,
      "step": 188
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00039008212061815206,
      "loss": 2.3079,
      "step": 190
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00038070207607527587,
      "loss": 2.218,
      "step": 192
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00037136634584107787,
      "loss": 2.2667,
      "step": 194
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0003620783977582305,
      "loss": 2.2754,
      "step": 196
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0003528416819202881,
      "loss": 2.2835,
      "step": 198
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00034365962939011697,
      "loss": 2.2843,
      "step": 200
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00033453565092539584,
      "loss": 2.2387,
      "step": 202
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0003254731357116597,
      "loss": 2.254,
      "step": 204
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.000316475450103354,
      "loss": 2.2686,
      "step": 206
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00030754593637337277,
      "loss": 2.2422,
      "step": 208
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0002986879114715403,
      "loss": 2.3003,
      "step": 210
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0002899046657924992,
      "loss": 2.2619,
      "step": 212
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00028119946195346375,
      "loss": 2.3022,
      "step": 214
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00027257553358229033,
      "loss": 2.2523,
      "step": 216
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0002640360841163174,
      "loss": 2.3098,
      "step": 218
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0002555842856124182,
      "loss": 2.235,
      "step": 220
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00024722327756871186,
      "loss": 2.2448,
      "step": 222
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0002389561657583681,
      "loss": 2.2411,
      "step": 224
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00023078602107593898,
      "loss": 2.2485,
      "step": 226
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0002227158783966467,
      "loss": 2.2261,
      "step": 228
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00021474873544905204,
      "loss": 2.2427,
      "step": 230
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00020688755170151997,
      "loss": 2.2961,
      "step": 232
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00019913524726289784,
      "loss": 2.2272,
      "step": 234
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00019149470179781532,
      "loss": 2.2368,
      "step": 236
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00018396875345700497,
      "loss": 2.2846,
      "step": 238
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.000176560197823046,
      "loss": 2.1709,
      "step": 240
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0001692717868719195,
      "loss": 2.2659,
      "step": 242
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0001621062279507617,
      "loss": 2.2655,
      "step": 244
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0001550661827721941,
      "loss": 2.2284,
      "step": 246
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00014815426642560752,
      "loss": 2.2444,
      "step": 248
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.0001413730464057616,
      "loss": 2.3102,
      "step": 250
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.00013472504165906613,
      "loss": 2.2287,
      "step": 252
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.00012821272164789544,
      "loss": 2.2713,
      "step": 254
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.00012183850543328313,
      "loss": 2.2127,
      "step": 256
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.00011560476077634069,
      "loss": 2.1682,
      "step": 258
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00010951380325872979,
      "loss": 2.2393,
      "step": 260
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.00010356789542251938,
      "loss": 2.2259,
      "step": 262
    },
    {
      "epoch": 1.6,
      "learning_rate": 9.776924592974257e-05,
      "loss": 2.2157,
      "step": 264
    },
    {
      "epoch": 1.61,
      "learning_rate": 9.212000874196952e-05,
      "loss": 2.2393,
      "step": 266
    },
    {
      "epoch": 1.62,
      "learning_rate": 8.662228232019875e-05,
      "loss": 2.2613,
      "step": 268
    },
    {
      "epoch": 1.63,
      "learning_rate": 8.127810884536401e-05,
      "loss": 2.1981,
      "step": 270
    },
    {
      "epoch": 1.65,
      "learning_rate": 7.60894734597476e-05,
      "loss": 2.2457,
      "step": 272
    },
    {
      "epoch": 1.66,
      "learning_rate": 7.105830352958143e-05,
      "loss": 2.2571,
      "step": 274
    },
    {
      "epoch": 1.67,
      "learning_rate": 6.618646792910893e-05,
      "loss": 2.1771,
      "step": 276
    },
    {
      "epoch": 1.68,
      "learning_rate": 6.147577634637414e-05,
      "loss": 2.2243,
      "step": 278
    },
    {
      "epoch": 1.69,
      "learning_rate": 5.692797861099719e-05,
      "loss": 2.2427,
      "step": 280
    },
    {
      "epoch": 1.71,
      "learning_rate": 5.25447640441834e-05,
      "loss": 2.2266,
      "step": 282
    },
    {
      "epoch": 1.72,
      "learning_rate": 4.832776083120982e-05,
      "loss": 2.3057,
      "step": 284
    },
    {
      "epoch": 1.73,
      "learning_rate": 4.4278535416620916e-05,
      "loss": 2.2225,
      "step": 286
    },
    {
      "epoch": 1.74,
      "learning_rate": 4.039859192235778e-05,
      "loss": 2.2665,
      "step": 288
    },
    {
      "epoch": 1.76,
      "learning_rate": 3.668937158903901e-05,
      "loss": 2.2807,
      "step": 290
    },
    {
      "epoch": 1.77,
      "learning_rate": 3.315225224059809e-05,
      "loss": 2.2165,
      "step": 292
    },
    {
      "epoch": 1.78,
      "learning_rate": 2.9788547772478415e-05,
      "loss": 2.2651,
      "step": 294
    },
    {
      "epoch": 1.79,
      "learning_rate": 2.6599507663574384e-05,
      "loss": 2.2437,
      "step": 296
    },
    {
      "epoch": 1.8,
      "learning_rate": 2.3586316512101414e-05,
      "loss": 2.3066,
      "step": 298
    },
    {
      "epoch": 1.82,
      "learning_rate": 2.0750093595565732e-05,
      "loss": 2.1727,
      "step": 300
    },
    {
      "epoch": 1.83,
      "learning_rate": 1.8091892454998595e-05,
      "loss": 2.2409,
      "step": 302
    },
    {
      "epoch": 1.84,
      "learning_rate": 1.561270050360897e-05,
      "loss": 2.2908,
      "step": 304
    },
    {
      "epoch": 1.85,
      "learning_rate": 1.33134386599994e-05,
      "loss": 2.2925,
      "step": 306
    },
    {
      "epoch": 1.86,
      "learning_rate": 1.1194961006082971e-05,
      "loss": 2.2449,
      "step": 308
    },
    {
      "epoch": 1.88,
      "learning_rate": 9.258054469825972e-06,
      "loss": 2.235,
      "step": 310
    },
    {
      "epoch": 1.89,
      "learning_rate": 7.503438532937168e-06,
      "loss": 2.2216,
      "step": 312
    },
    {
      "epoch": 1.9,
      "learning_rate": 5.931764963608866e-06,
      "loss": 2.2884,
      "step": 314
    },
    {
      "epoch": 1.91,
      "learning_rate": 4.5436175744121845e-06,
      "loss": 2.2124,
      "step": 316
    },
    {
      "epoch": 1.92,
      "learning_rate": 3.3395120054343087e-06,
      "loss": 2.2418,
      "step": 318
    },
    {
      "epoch": 1.94,
      "learning_rate": 2.319895532739369e-06,
      "loss": 2.2855,
      "step": 320
    },
    {
      "epoch": 1.95,
      "learning_rate": 1.4851469022234e-06,
      "loss": 2.2974,
      "step": 322
    },
    {
      "epoch": 1.96,
      "learning_rate": 8.35576188926046e-07,
      "loss": 2.2552,
      "step": 324
    },
    {
      "epoch": 1.97,
      "learning_rate": 3.71424681850141e-07,
      "loss": 2.2209,
      "step": 326
    },
    {
      "epoch": 1.99,
      "learning_rate": 9.286479433257e-08,
      "loss": 2.1935,
      "step": 328
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0,
      "loss": 2.2702,
      "step": 330
    },
    {
      "epoch": 2.0,
      "step": 330,
      "total_flos": 4.634629374287544e+17,
      "train_loss": 2.336302039117524,
      "train_runtime": 79791.9217,
      "train_samples_per_second": 0.265,
      "train_steps_per_second": 0.004
    }
  ],
  "max_steps": 330,
  "num_train_epochs": 2,
  "total_flos": 4.634629374287544e+17,
  "trial_name": null,
  "trial_params": null
}