{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.983219390926041,
  "eval_steps": 500,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 2.7675,
      "step": 2
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.888888888888889e-05,
      "loss": 2.6931,
      "step": 4
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00013333333333333334,
      "loss": 2.6733,
      "step": 6
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00017777777777777779,
      "loss": 2.5515,
      "step": 8
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019999417253661235,
      "loss": 2.4826,
      "step": 10
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019994755690455152,
      "loss": 2.5387,
      "step": 12
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001998543473718677,
      "loss": 2.4596,
      "step": 14
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019971458739130598,
      "loss": 2.4936,
      "step": 16
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001995283421166614,
      "loss": 2.1189,
      "step": 18
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019929569837240564,
      "loss": 1.9708,
      "step": 20
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019901676461321068,
      "loss": 2.0963,
      "step": 22
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019869167087338907,
      "loss": 2.0887,
      "step": 24
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019832056870627417,
      "loss": 2.218,
      "step": 26
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019790363111356837,
      "loss": 2.358,
      "step": 28
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00019744105246469263,
      "loss": 2.334,
      "step": 30
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00019693304840617457,
      "loss": 2.1776,
      "step": 32
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00019637985576111778,
      "loss": 2.3149,
      "step": 34
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00019578173241879872,
      "loss": 2.1172,
      "step": 36
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00019513895721444286,
      "loss": 2.183,
      "step": 38
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00019445182979923654,
      "loss": 2.2688,
      "step": 40
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00019372067050063438,
      "loss": 2.2487,
      "step": 42
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00019294582017302797,
      "loss": 2.1218,
      "step": 44
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001921276400388451,
      "loss": 2.1302,
      "step": 46
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00019126651152015403,
      "loss": 2.1458,
      "step": 48
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00019036283606085053,
      "loss": 2.1425,
      "step": 50
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00018941703493951164,
      "loss": 2.2523,
      "step": 52
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00018842954907300236,
      "loss": 2.1411,
      "step": 54
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0001874008388109276,
      "loss": 2.2491,
      "step": 56
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00018633138372102468,
      "loss": 2.1121,
      "step": 58
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00018522168236559695,
      "loss": 2.2793,
      "step": 60
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00018407225206909208,
      "loss": 2.1577,
      "step": 62
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00018288362867693414,
      "loss": 2.1961,
      "step": 64
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0001816563663057211,
      "loss": 2.1825,
      "step": 66
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.000180391037084905,
      "loss": 2.0917,
      "step": 68
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00017908823089007457,
      "loss": 2.0896,
      "step": 70
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00017774855506796496,
      "loss": 2.0877,
      "step": 72
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0001763726341533227,
      "loss": 2.1369,
      "step": 74
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0001749611095777581,
      "loss": 2.0917,
      "step": 76
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00017351463937072004,
      "loss": 2.3862,
      "step": 78
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.000172033897852734,
      "loss": 2.1755,
      "step": 80
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0001705195753210446,
      "loss": 2.1165,
      "step": 82
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00016897237772781044,
      "loss": 2.1959,
      "step": 84
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00016739302635100108,
      "loss": 2.1884,
      "step": 86
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00016578225745814907,
      "loss": 2.2531,
      "step": 88
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.000164140821963114,
      "loss": 2.2549,
      "step": 90
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00016246948507601914,
      "loss": 2.0919,
      "step": 92
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0001607690259465229,
      "loss": 2.0073,
      "step": 94
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00015904023730059228,
      "loss": 2.1638,
      "step": 96
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.000157283925070947,
      "loss": 2.0956,
      "step": 98
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.000155500908021347,
      "loss": 1.9043,
      "step": 100
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0001536920173648984,
      "loss": 2.0836,
      "step": 102
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0001518580963765555,
      "loss": 2.1632,
      "step": 104
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00015000000000000001,
      "loss": 2.0727,
      "step": 106
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00014811859444908052,
      "loss": 2.2505,
      "step": 108
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0001462147568039977,
      "loss": 2.1901,
      "step": 110
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00014428937460242417,
      "loss": 2.1774,
      "step": 112
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00014234334542574906,
      "loss": 2.1062,
      "step": 114
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00014037757648064018,
      "loss": 2.0187,
      "step": 116
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00013839298417611963,
      "loss": 2.0678,
      "step": 118
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00013639049369634876,
      "loss": 2.0362,
      "step": 120
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00013437103856932264,
      "loss": 2.0308,
      "step": 122
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00013233556023167485,
      "loss": 1.9568,
      "step": 124
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00013028500758979506,
      "loss": 2.1364,
      "step": 126
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00012822033657746478,
      "loss": 2.2107,
      "step": 128
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00012614250971021657,
      "loss": 2.0798,
      "step": 130
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00012405249563662537,
      "loss": 2.2118,
      "step": 132
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00012195126868674051,
      "loss": 2.1874,
      "step": 134
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.000119839808417869,
      "loss": 2.1919,
      "step": 136
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0001177190991579223,
      "loss": 2.0894,
      "step": 138
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00011559012954653865,
      "loss": 2.1773,
      "step": 140
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00011345389207419588,
      "loss": 2.2115,
      "step": 142
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00011131138261952845,
      "loss": 1.9207,
      "step": 144
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.0001091635999850655,
      "loss": 1.9258,
      "step": 146
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00010701154543160541,
      "loss": 1.9662,
      "step": 148
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00010485622221144484,
      "loss": 2.0598,
      "step": 150
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00010269863510067872,
      "loss": 1.933,
      "step": 152
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.00010053978993079045,
      "loss": 2.2902,
      "step": 154
    },
    {
      "epoch": 1.55,
      "learning_rate": 9.838069311974986e-05,
      "loss": 2.1651,
      "step": 156
    },
    {
      "epoch": 1.57,
      "learning_rate": 9.622235120283769e-05,
      "loss": 2.0562,
      "step": 158
    },
    {
      "epoch": 1.59,
      "learning_rate": 9.406577036341548e-05,
      "loss": 2.1876,
      "step": 160
    },
    {
      "epoch": 1.61,
      "learning_rate": 9.19119559638596e-05,
      "loss": 2.1455,
      "step": 162
    },
    {
      "epoch": 1.63,
      "learning_rate": 8.976191207687775e-05,
      "loss": 2.0586,
      "step": 164
    },
    {
      "epoch": 1.65,
      "learning_rate": 8.7616641017427e-05,
      "loss": 2.0516,
      "step": 166
    },
    {
      "epoch": 1.67,
      "learning_rate": 8.5477142875451e-05,
      "loss": 2.1687,
      "step": 168
    },
    {
      "epoch": 1.69,
      "learning_rate": 8.334441504965455e-05,
      "loss": 1.8243,
      "step": 170
    },
    {
      "epoch": 1.71,
      "learning_rate": 8.1219451782533e-05,
      "loss": 2.011,
      "step": 172
    },
    {
      "epoch": 1.73,
      "learning_rate": 7.91032436968725e-05,
      "loss": 2.0671,
      "step": 174
    },
    {
      "epoch": 1.75,
      "learning_rate": 7.699677733393826e-05,
      "loss": 2.1099,
      "step": 176
    },
    {
      "epoch": 1.77,
      "learning_rate": 7.490103469356513e-05,
      "loss": 2.2192,
      "step": 178
    },
    {
      "epoch": 1.79,
      "learning_rate": 7.281699277636572e-05,
      "loss": 2.1303,
      "step": 180
    },
    {
      "epoch": 1.81,
      "learning_rate": 7.07456231282686e-05,
      "loss": 2.2478,
      "step": 182
    },
    {
      "epoch": 1.83,
      "learning_rate": 6.868789138759976e-05,
      "loss": 2.2372,
      "step": 184
    },
    {
      "epoch": 1.85,
      "learning_rate": 6.664475683491796e-05,
      "loss": 2.0905,
      "step": 186
    },
    {
      "epoch": 1.87,
      "learning_rate": 6.461717194581393e-05,
      "loss": 2.1761,
      "step": 188
    },
    {
      "epoch": 1.89,
      "learning_rate": 6.260608194688206e-05,
      "loss": 2.2156,
      "step": 190
    },
    {
      "epoch": 1.91,
      "learning_rate": 6.061242437507131e-05,
      "loss": 2.0831,
      "step": 192
    },
    {
      "epoch": 1.93,
      "learning_rate": 5.863712864062089e-05,
      "loss": 1.9666,
      "step": 194
    },
    {
      "epoch": 1.95,
      "learning_rate": 5.668111559378471e-05,
      "loss": 2.0193,
      "step": 196
    },
    {
      "epoch": 1.97,
      "learning_rate": 5.474529709554612e-05,
      "loss": 2.0009,
      "step": 198
    },
    {
      "epoch": 1.99,
      "learning_rate": 5.283057559252341e-05,
      "loss": 1.8429,
      "step": 200
    },
    {
      "epoch": 2.01,
      "learning_rate": 5.0937843696263966e-05,
      "loss": 1.825,
      "step": 202
    },
    {
      "epoch": 2.03,
      "learning_rate": 4.9067983767123736e-05,
      "loss": 2.1982,
      "step": 204
    },
    {
      "epoch": 2.05,
      "learning_rate": 4.722186750292511e-05,
      "loss": 2.2024,
      "step": 206
    },
    {
      "epoch": 2.07,
      "learning_rate": 4.540035553258619e-05,
      "loss": 2.0208,
      "step": 208
    },
    {
      "epoch": 2.09,
      "learning_rate": 4.360429701490934e-05,
      "loss": 2.0707,
      "step": 210
    },
    {
      "epoch": 2.11,
      "learning_rate": 4.183452924271776e-05,
      "loss": 2.0485,
      "step": 212
    },
    {
      "epoch": 2.13,
      "learning_rate": 4.009187725252309e-05,
      "loss": 2.1584,
      "step": 214
    },
    {
      "epoch": 2.15,
      "learning_rate": 3.8377153439907266e-05,
      "loss": 2.1151,
      "step": 216
    },
    {
      "epoch": 2.17,
      "learning_rate": 3.669115718079702e-05,
      "loss": 1.9831,
      "step": 218
    },
    {
      "epoch": 2.19,
      "learning_rate": 3.503467445880789e-05,
      "loss": 1.9593,
      "step": 220
    },
    {
      "epoch": 2.21,
      "learning_rate": 3.340847749883191e-05,
      "loss": 1.9555,
      "step": 222
    },
    {
      "epoch": 2.23,
      "learning_rate": 3.1813324407038825e-05,
      "loss": 1.9759,
      "step": 224
    },
    {
      "epoch": 2.25,
      "learning_rate": 3.0249958817459722e-05,
      "loss": 1.9367,
      "step": 226
    },
    {
      "epoch": 2.27,
      "learning_rate": 2.8719109545317103e-05,
      "loss": 2.0455,
      "step": 228
    },
    {
      "epoch": 2.29,
      "learning_rate": 2.722149024726307e-05,
      "loss": 2.0912,
      "step": 230
    },
    {
      "epoch": 2.31,
      "learning_rate": 2.5757799088684654e-05,
      "loss": 2.0974,
      "step": 232
    },
    {
      "epoch": 2.33,
      "learning_rate": 2.432871841823047e-05,
      "loss": 2.1669,
      "step": 234
    },
    {
      "epoch": 2.35,
      "learning_rate": 2.2934914449711087e-05,
      "loss": 2.0861,
      "step": 236
    },
    {
      "epoch": 2.37,
      "learning_rate": 2.157703695152109e-05,
      "loss": 2.2297,
      "step": 238
    },
    {
      "epoch": 2.39,
      "learning_rate": 2.025571894372794e-05,
      "loss": 2.078,
      "step": 240
    },
    {
      "epoch": 2.41,
      "learning_rate": 1.897157640296825e-05,
      "loss": 2.0759,
      "step": 242
    },
    {
      "epoch": 2.43,
      "learning_rate": 1.772520797528988e-05,
      "loss": 1.957,
      "step": 244
    },
    {
      "epoch": 2.45,
      "learning_rate": 1.65171946970729e-05,
      "loss": 2.0201,
      "step": 246
    },
    {
      "epoch": 2.47,
      "learning_rate": 1.534809972415998e-05,
      "loss": 1.972,
      "step": 248
    },
    {
      "epoch": 2.49,
      "learning_rate": 1.4218468069322578e-05,
      "loss": 1.9812,
      "step": 250
    },
    {
      "epoch": 2.51,
      "learning_rate": 1.3128826348184887e-05,
      "loss": 1.7967,
      "step": 252
    },
    {
      "epoch": 2.53,
      "learning_rate": 1.2079682533724379e-05,
      "loss": 2.1202,
      "step": 254
    },
    {
      "epoch": 2.55,
      "learning_rate": 1.1071525719463095e-05,
      "loss": 2.2584,
      "step": 256
    },
    {
      "epoch": 2.57,
      "learning_rate": 1.010482589146048e-05,
      "loss": 2.1405,
      "step": 258
    },
    {
      "epoch": 2.59,
      "learning_rate": 9.180033709213454e-06,
      "loss": 2.1317,
      "step": 260
    },
    {
      "epoch": 2.61,
      "learning_rate": 8.297580295566575e-06,
      "loss": 2.0388,
      "step": 262
    },
    {
      "epoch": 2.63,
      "learning_rate": 7.457877035729588e-06,
      "loss": 2.0719,
      "step": 264
    },
    {
      "epoch": 2.65,
      "learning_rate": 6.661315385496425e-06,
      "loss": 2.1417,
      "step": 266
    },
    {
      "epoch": 2.67,
      "learning_rate": 5.908266688755049e-06,
      "loss": 2.0137,
      "step": 268
    },
    {
      "epoch": 2.68,
      "learning_rate": 5.199082004372957e-06,
      "loss": 2.0492,
      "step": 270
    },
    {
      "epoch": 2.7,
      "learning_rate": 4.534091942539475e-06,
      "loss": 1.9081,
      "step": 272
    },
    {
      "epoch": 2.72,
      "learning_rate": 3.913606510640644e-06,
      "loss": 2.0606,
      "step": 274
    },
    {
      "epoch": 2.74,
      "learning_rate": 3.3379149687388867e-06,
      "loss": 1.8957,
      "step": 276
    },
    {
      "epoch": 2.76,
      "learning_rate": 2.8072856947248037e-06,
      "loss": 2.1141,
      "step": 278
    },
    {
      "epoch": 2.78,
      "learning_rate": 2.3219660592038285e-06,
      "loss": 2.002,
      "step": 280
    },
    {
      "epoch": 2.8,
      "learning_rate": 1.882182310176095e-06,
      "loss": 2.0662,
      "step": 282
    },
    {
      "epoch": 2.82,
      "learning_rate": 1.488139467563354e-06,
      "loss": 1.9553,
      "step": 284
    },
    {
      "epoch": 2.84,
      "learning_rate": 1.1400212276321376e-06,
      "loss": 2.2417,
      "step": 286
    },
    {
      "epoch": 2.86,
      "learning_rate": 8.379898773574924e-07,
      "loss": 2.2588,
      "step": 288
    },
    {
      "epoch": 2.88,
      "learning_rate": 5.821862187675775e-07,
      "loss": 2.0636,
      "step": 290
    },
    {
      "epoch": 2.9,
      "learning_rate": 3.727295033040035e-07,
      "loss": 2.1176,
      "step": 292
    },
    {
      "epoch": 2.92,
      "learning_rate": 2.0971737622883515e-07,
      "loss": 1.9134,
      "step": 294
    },
    {
      "epoch": 2.94,
      "learning_rate": 9.32258311039269e-08,
      "loss": 1.8922,
      "step": 296
    },
    {
      "epoch": 2.96,
      "learning_rate": 2.3309174364027907e-08,
      "loss": 1.9239,
      "step": 298
    },
    {
      "epoch": 2.98,
      "learning_rate": 0.0,
      "loss": 1.9386,
      "step": 300
    }
  ],
  "logging_steps": 2,
  "max_steps": 300,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 2.587049079238656e+16,
  "trial_name": null,
  "trial_params": null
}