{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.984984984984985,
  "global_step": 246,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "learning_rate": 0.00015384615384615385,
      "loss": 2.9074,
      "step": 2
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0003076923076923077,
      "loss": 2.7922,
      "step": 4
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0004615384615384616,
      "loss": 2.6824,
      "step": 6
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0006153846153846154,
      "loss": 2.6036,
      "step": 8
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0007692307692307693,
      "loss": 2.5524,
      "step": 10
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0009230769230769232,
      "loss": 2.5342,
      "step": 12
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0009999545513138964,
      "loss": 2.5052,
      "step": 14
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.000999591011397558,
      "loss": 2.4689,
      "step": 16
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.000998864195911451,
      "loss": 2.4487,
      "step": 18
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.000997774633356497,
      "loss": 2.4068,
      "step": 20
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0009963231160036714,
      "loss": 2.3813,
      "step": 22
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0009945106993179073,
      "loss": 2.3558,
      "step": 24
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.000992338701190618,
      "loss": 2.3425,
      "step": 26
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0009898087009813986,
      "loss": 2.3254,
      "step": 28
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.000986922538369599,
      "loss": 2.3128,
      "step": 30
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0009836823120166116,
      "loss": 2.3026,
      "step": 32
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0009800903780398356,
      "loss": 2.3005,
      "step": 34
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0009761493482994372,
      "loss": 2.2828,
      "step": 36
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0009718620884991454,
      "loss": 2.2779,
      "step": 38
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0009672317161024677,
      "loss": 2.2485,
      "step": 40
    },
    {
      "epoch": 0.98,
      "eval_accuracy": 0.5157865687819605,
      "eval_loss": 2.1457464694976807,
      "eval_runtime": 496.7153,
      "eval_samples_per_second": 1.184,
      "eval_steps_per_second": 0.296,
      "step": 41
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.000962261598065839,
      "loss": 2.9045,
      "step": 42
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.000956955348390353,
      "loss": 2.16,
      "step": 44
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.000951316825493856,
      "loss": 2.1395,
      "step": 46
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0009453501294053137,
      "loss": 2.1327,
      "step": 48
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0009390595987834929,
      "loss": 2.128,
      "step": 50
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.000932449807762122,
      "loss": 2.1251,
      "step": 52
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0009255255626238293,
      "loss": 2.1138,
      "step": 54
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0009182918983052741,
      "loss": 2.118,
      "step": 56
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.0009107540747360124,
      "loss": 2.1034,
      "step": 58
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0009029175730137609,
      "loss": 2.1016,
      "step": 60
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0008947880914188397,
      "loss": 2.1027,
      "step": 62
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0008863715412706897,
      "loss": 2.0969,
      "step": 64
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.0008776740426294817,
      "loss": 2.0926,
      "step": 66
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.0008687019198459394,
      "loss": 2.0946,
      "step": 68
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.0008594616969626134,
      "loss": 2.0968,
      "step": 70
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.0008499600929699501,
      "loss": 2.0932,
      "step": 72
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.0008402040169206053,
      "loss": 2.0813,
      "step": 74
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.0008302005629055549,
      "loss": 2.0815,
      "step": 76
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.0008199570048956552,
      "loss": 2.0809,
      "step": 78
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.0008094807914524047,
      "loss": 2.0704,
      "step": 80
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.0007987795403117528,
      "loss": 2.0757,
      "step": 82
    },
    {
      "epoch": 1.98,
      "eval_accuracy": 0.530352903624793,
      "eval_loss": 2.058377742767334,
      "eval_runtime": 493.7321,
      "eval_samples_per_second": 1.191,
      "eval_steps_per_second": 0.298,
      "step": 82
    },
    {
      "epoch": 2.05,
      "learning_rate": 0.0007878610328448947,
      "loss": 2.615,
      "step": 84
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.0007767332084000785,
      "loss": 1.9638,
      "step": 86
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.0007654041585295399,
      "loss": 1.979,
      "step": 88
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.0007538821211057647,
      "loss": 1.9628,
      "step": 90
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.0007421754743313514,
      "loss": 1.9717,
      "step": 92
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.0007302927306468364,
      "loss": 1.9625,
      "step": 94
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.0007182425305409072,
      "loss": 1.9683,
      "step": 96
    },
    {
      "epoch": 2.38,
      "learning_rate": 0.0007060336362675068,
      "loss": 1.9556,
      "step": 98
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.0006936749254743951,
      "loss": 1.9565,
      "step": 100
    },
    {
      "epoch": 2.48,
      "learning_rate": 0.000681175384747805,
      "loss": 1.9601,
      "step": 102
    },
    {
      "epoch": 2.53,
      "learning_rate": 0.0006685441030778817,
      "loss": 1.9612,
      "step": 104
    },
    {
      "epoch": 2.58,
      "learning_rate": 0.0006557902652496611,
      "loss": 1.9539,
      "step": 106
    },
    {
      "epoch": 2.62,
      "learning_rate": 0.0006429231451643907,
      "loss": 1.9563,
      "step": 108
    },
    {
      "epoch": 2.67,
      "learning_rate": 0.0006299520990960496,
      "loss": 1.9597,
      "step": 110
    },
    {
      "epoch": 2.72,
      "learning_rate": 0.000616886558887973,
      "loss": 1.9625,
      "step": 112
    },
    {
      "epoch": 2.77,
      "learning_rate": 0.0006037360250945242,
      "loss": 1.965,
      "step": 114
    },
    {
      "epoch": 2.82,
      "learning_rate": 0.0005905100600728067,
      "loss": 1.9588,
      "step": 116
    },
    {
      "epoch": 2.86,
      "learning_rate": 0.0005772182810294344,
      "loss": 1.965,
      "step": 118
    },
    {
      "epoch": 2.91,
      "learning_rate": 0.0005638703530274187,
      "loss": 1.9595,
      "step": 120
    },
    {
      "epoch": 2.96,
      "learning_rate": 0.0005504759819582581,
      "loss": 1.966,
      "step": 122
    },
    {
      "epoch": 2.98,
      "eval_accuracy": 0.5375845352803879,
      "eval_loss": 2.0210342407226562,
      "eval_runtime": 475.4248,
      "eval_samples_per_second": 1.237,
      "eval_steps_per_second": 0.309,
      "step": 123
    },
    {
      "epoch": 3.02,
      "learning_rate": 0.000537044907484338,
      "loss": 2.5101,
      "step": 124
    },
    {
      "epoch": 3.07,
      "learning_rate": 0.0005235868959567755,
      "loss": 1.8782,
      "step": 126
    },
    {
      "epoch": 3.12,
      "learning_rate": 0.0005101117333138558,
      "loss": 1.8556,
      "step": 128
    },
    {
      "epoch": 3.17,
      "learning_rate": 0.0004966292179652285,
      "loss": 1.8622,
      "step": 130
    },
    {
      "epoch": 3.22,
      "learning_rate": 0.00048314915366703335,
      "loss": 1.8668,
      "step": 132
    },
    {
      "epoch": 3.26,
      "learning_rate": 0.0004696813423931381,
      "loss": 1.873,
      "step": 134
    },
    {
      "epoch": 3.31,
      "learning_rate": 0.000456235577207674,
      "loss": 1.8694,
      "step": 136
    },
    {
      "epoch": 3.36,
      "learning_rate": 0.00044282163514404915,
      "loss": 1.8742,
      "step": 138
    },
    {
      "epoch": 3.41,
      "learning_rate": 0.00042944927009561784,
      "loss": 1.8694,
      "step": 140
    },
    {
      "epoch": 3.46,
      "learning_rate": 0.00041612820572317757,
      "loss": 1.8569,
      "step": 142
    },
    {
      "epoch": 3.5,
      "learning_rate": 0.0004028681283844471,
      "loss": 1.8619,
      "step": 144
    },
    {
      "epoch": 3.55,
      "learning_rate": 0.0003896786800906733,
      "loss": 1.8734,
      "step": 146
    },
    {
      "epoch": 3.6,
      "learning_rate": 0.00037656945149547956,
      "loss": 1.8677,
      "step": 148
    },
    {
      "epoch": 3.65,
      "learning_rate": 0.00036354997492106257,
      "loss": 1.872,
      "step": 150
    },
    {
      "epoch": 3.7,
      "learning_rate": 0.00035062971742680246,
      "loss": 1.847,
      "step": 152
    },
    {
      "epoch": 3.74,
      "learning_rate": 0.00033781807392532895,
      "loss": 1.8733,
      "step": 154
    },
    {
      "epoch": 3.79,
      "learning_rate": 0.00032512436035104966,
      "loss": 1.8657,
      "step": 156
    },
    {
      "epoch": 3.84,
      "learning_rate": 0.00031255780688610506,
      "loss": 1.8581,
      "step": 158
    },
    {
      "epoch": 3.89,
      "learning_rate": 0.00030012755124868095,
      "loss": 1.8672,
      "step": 160
    },
    {
      "epoch": 3.94,
      "learning_rate": 0.00028784263204855175,
      "loss": 1.8585,
      "step": 162
    },
    {
      "epoch": 3.98,
      "learning_rate": 0.00027571198221469395,
      "loss": 1.8602,
      "step": 164
    },
    {
      "epoch": 3.98,
      "eval_accuracy": 0.5422011424315571,
      "eval_loss": 2.0011844635009766,
      "eval_runtime": 493.1263,
      "eval_samples_per_second": 1.192,
      "eval_steps_per_second": 0.298,
      "step": 164
    },
    {
      "epoch": 4.05,
      "learning_rate": 0.0002637444224997421,
      "loss": 2.4006,
      "step": 166
    },
    {
      "epoch": 4.1,
      "learning_rate": 0.00025194865506601504,
      "loss": 1.8118,
      "step": 168
    },
    {
      "epoch": 4.14,
      "learning_rate": 0.00024033325715777377,
      "loss": 1.7888,
      "step": 170
    },
    {
      "epoch": 4.19,
      "learning_rate": 0.00022890667486431295,
      "loss": 1.798,
      "step": 172
    },
    {
      "epoch": 4.24,
      "learning_rate": 0.00021767721697842242,
      "loss": 1.8052,
      "step": 174
    },
    {
      "epoch": 4.29,
      "learning_rate": 0.00020665304895468113,
      "loss": 1.8054,
      "step": 176
    },
    {
      "epoch": 4.34,
      "learning_rate": 0.0001958421869719807,
      "loss": 1.7966,
      "step": 178
    },
    {
      "epoch": 4.38,
      "learning_rate": 0.00018525249210459344,
      "loss": 1.8049,
      "step": 180
    },
    {
      "epoch": 4.43,
      "learning_rate": 0.00017489166460602496,
      "loss": 1.7955,
      "step": 182
    },
    {
      "epoch": 4.48,
      "learning_rate": 0.0001647672383098045,
      "loss": 1.8062,
      "step": 184
    },
    {
      "epoch": 4.53,
      "learning_rate": 0.00015488657515129006,
      "loss": 1.8132,
      "step": 186
    },
    {
      "epoch": 4.58,
      "learning_rate": 0.0001452568598144668,
      "loss": 1.8027,
      "step": 188
    },
    {
      "epoch": 4.62,
      "learning_rate": 0.00013588509450763282,
      "loss": 1.8066,
      "step": 190
    },
    {
      "epoch": 4.67,
      "learning_rate": 0.0001267780938717722,
      "loss": 1.7989,
      "step": 192
    },
    {
      "epoch": 4.72,
      "learning_rate": 0.00011794248002531643,
      "loss": 1.7966,
      "step": 194
    },
    {
      "epoch": 4.77,
      "learning_rate": 0.00010938467774889881,
      "loss": 1.8074,
      "step": 196
    },
    {
      "epoch": 4.82,
      "learning_rate": 0.00010111090981359961,
      "loss": 1.8073,
      "step": 198
    },
    {
      "epoch": 4.86,
      "learning_rate": 9.312719245608486e-05,
      "loss": 1.8022,
      "step": 200
    },
    {
      "epoch": 4.91,
      "learning_rate": 8.54393310039246e-05,
      "loss": 1.8014,
      "step": 202
    },
    {
      "epoch": 4.96,
      "learning_rate": 7.805291565427064e-05,
      "loss": 1.8089,
      "step": 204
    },
    {
      "epoch": 4.98,
      "eval_accuracy": 0.5435859583325021,
      "eval_loss": 1.9977257251739502,
      "eval_runtime": 497.2866,
      "eval_samples_per_second": 1.182,
      "eval_steps_per_second": 0.296,
      "step": 205
    },
    {
      "epoch": 5.02,
      "learning_rate": 7.097331740896996e-05,
      "loss": 2.3557,
      "step": 206
    },
    {
      "epoch": 5.07,
      "learning_rate": 6.420568416906064e-05,
      "loss": 1.7835,
      "step": 208
    },
    {
      "epoch": 5.12,
      "learning_rate": 5.775493699149753e-05,
      "loss": 1.7641,
      "step": 210
    },
    {
      "epoch": 5.17,
      "learning_rate": 5.16257665108254e-05,
      "loss": 1.7754,
      "step": 212
    },
    {
      "epoch": 5.22,
      "learning_rate": 4.582262952840355e-05,
      "loss": 1.7765,
      "step": 214
    },
    {
      "epoch": 5.26,
      "learning_rate": 4.034974577166023e-05,
      "loss": 1.7732,
      "step": 216
    },
    {
      "epoch": 5.31,
      "learning_rate": 3.521109482573515e-05,
      "loss": 1.7663,
      "step": 218
    },
    {
      "epoch": 5.36,
      "learning_rate": 3.0410413239740975e-05,
      "loss": 1.7779,
      "step": 220
    },
    {
      "epoch": 5.41,
      "learning_rate": 2.5951191809746145e-05,
      "loss": 1.7739,
      "step": 222
    },
    {
      "epoch": 5.46,
      "learning_rate": 2.1836673040456943e-05,
      "loss": 1.7602,
      "step": 224
    },
    {
      "epoch": 5.5,
      "learning_rate": 1.8069848787443555e-05,
      "loss": 1.7773,
      "step": 226
    },
    {
      "epoch": 5.55,
      "learning_rate": 1.4653458081624272e-05,
      "loss": 1.7841,
      "step": 228
    },
    {
      "epoch": 5.6,
      "learning_rate": 1.1589985137590519e-05,
      "loss": 1.7746,
      "step": 230
    },
    {
      "epoch": 5.65,
      "learning_rate": 8.881657547219868e-06,
      "loss": 1.7801,
      "step": 232
    },
    {
      "epoch": 5.7,
      "learning_rate": 6.530444659892443e-06,
      "loss": 1.7639,
      "step": 234
    },
    {
      "epoch": 5.74,
      "learning_rate": 4.538056150485858e-06,
      "loss": 1.7771,
      "step": 236
    },
    {
      "epoch": 5.79,
      "learning_rate": 2.905940776192384e-06,
      "loss": 1.7724,
      "step": 238
    },
    {
      "epoch": 5.84,
      "learning_rate": 1.6352853230609532e-06,
      "loss": 1.7876,
      "step": 240
    },
    {
      "epoch": 5.89,
      "learning_rate": 7.270137430306356e-07,
      "loss": 1.7718,
      "step": 242
    },
    {
      "epoch": 5.94,
      "learning_rate": 1.817864820827242e-07,
      "loss": 1.779,
      "step": 244
    },
    {
      "epoch": 5.98,
      "learning_rate": 0.0,
      "loss": 1.7698,
      "step": 246
    },
    {
      "epoch": 5.98,
      "eval_accuracy": 0.544073054441718,
      "eval_loss": 1.9982993602752686,
      "eval_runtime": 495.216,
      "eval_samples_per_second": 1.187,
      "eval_steps_per_second": 0.297,
      "step": 246
    },
    {
      "before_init_mem_cpu": 699817984,
      "before_init_mem_gpu": 0,
      "epoch": 5.98,
      "init_mem_cpu_alloc_delta": -283938816,
      "init_mem_cpu_peaked_delta": 332918784,
      "init_mem_gpu_alloc_delta": 334744576,
      "init_mem_gpu_peaked_delta": 0,
      "step": 246,
      "total_flos": 8328311331618816.0,
      "train_loss": 2.0183091745143984,
      "train_mem_cpu_alloc_delta": 1155149824,
      "train_mem_cpu_peaked_delta": 308719616,
      "train_mem_gpu_alloc_delta": 988995584,
      "train_mem_gpu_peaked_delta": 4500811776,
      "train_runtime": 35067.5673,
      "train_samples_per_second": 0.911,
      "train_steps_per_second": 0.007
    }
  ],
  "max_steps": 246,
  "num_train_epochs": 6,
  "total_flos": 8328311331618816.0,
  "trial_name": null,
  "trial_params": null
}