pythia-exp / trainer_state.json
TinyPixel's picture
Upload folder using huggingface_hub
9de6c0c
raw
history blame
56.8 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9998001465591899,
"eval_steps": 500,
"global_step": 938,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 4.705882352941177e-06,
"loss": 2.3894,
"step": 2
},
{
"epoch": 0.0,
"learning_rate": 9.411764705882354e-06,
"loss": 2.4461,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 1.411764705882353e-05,
"loss": 2.5984,
"step": 6
},
{
"epoch": 0.01,
"learning_rate": 1.8823529411764708e-05,
"loss": 2.7012,
"step": 8
},
{
"epoch": 0.01,
"learning_rate": 2.3529411764705884e-05,
"loss": 2.5558,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 2.823529411764706e-05,
"loss": 2.7513,
"step": 12
},
{
"epoch": 0.01,
"learning_rate": 3.294117647058824e-05,
"loss": 2.7527,
"step": 14
},
{
"epoch": 0.02,
"learning_rate": 3.7647058823529415e-05,
"loss": 2.6276,
"step": 16
},
{
"epoch": 0.02,
"learning_rate": 4.235294117647059e-05,
"loss": 2.6711,
"step": 18
},
{
"epoch": 0.02,
"learning_rate": 4.705882352941177e-05,
"loss": 2.6975,
"step": 20
},
{
"epoch": 0.02,
"learning_rate": 5.176470588235295e-05,
"loss": 2.5489,
"step": 22
},
{
"epoch": 0.03,
"learning_rate": 5.647058823529412e-05,
"loss": 2.5387,
"step": 24
},
{
"epoch": 0.03,
"learning_rate": 6.11764705882353e-05,
"loss": 2.5694,
"step": 26
},
{
"epoch": 0.03,
"learning_rate": 6.588235294117648e-05,
"loss": 2.6244,
"step": 28
},
{
"epoch": 0.03,
"learning_rate": 7.058823529411765e-05,
"loss": 2.5018,
"step": 30
},
{
"epoch": 0.03,
"learning_rate": 7.529411764705883e-05,
"loss": 2.4123,
"step": 32
},
{
"epoch": 0.04,
"learning_rate": 8e-05,
"loss": 2.3234,
"step": 34
},
{
"epoch": 0.04,
"learning_rate": 8.470588235294118e-05,
"loss": 2.0958,
"step": 36
},
{
"epoch": 0.04,
"learning_rate": 8.941176470588236e-05,
"loss": 2.2023,
"step": 38
},
{
"epoch": 0.04,
"learning_rate": 9.411764705882353e-05,
"loss": 2.1864,
"step": 40
},
{
"epoch": 0.04,
"learning_rate": 9.882352941176471e-05,
"loss": 2.0768,
"step": 42
},
{
"epoch": 0.05,
"learning_rate": 0.0001035294117647059,
"loss": 2.189,
"step": 44
},
{
"epoch": 0.05,
"learning_rate": 0.00010823529411764706,
"loss": 1.9094,
"step": 46
},
{
"epoch": 0.05,
"learning_rate": 0.00011294117647058824,
"loss": 2.0136,
"step": 48
},
{
"epoch": 0.05,
"learning_rate": 0.00011764705882352942,
"loss": 1.7677,
"step": 50
},
{
"epoch": 0.06,
"learning_rate": 0.0001223529411764706,
"loss": 2.3789,
"step": 52
},
{
"epoch": 0.06,
"learning_rate": 0.00012705882352941175,
"loss": 2.2419,
"step": 54
},
{
"epoch": 0.06,
"learning_rate": 0.00013176470588235296,
"loss": 2.2654,
"step": 56
},
{
"epoch": 0.06,
"learning_rate": 0.00013647058823529413,
"loss": 2.3797,
"step": 58
},
{
"epoch": 0.06,
"learning_rate": 0.0001411764705882353,
"loss": 2.319,
"step": 60
},
{
"epoch": 0.07,
"learning_rate": 0.00014588235294117646,
"loss": 2.3527,
"step": 62
},
{
"epoch": 0.07,
"learning_rate": 0.00015058823529411766,
"loss": 2.129,
"step": 64
},
{
"epoch": 0.07,
"learning_rate": 0.00015529411764705884,
"loss": 2.2285,
"step": 66
},
{
"epoch": 0.07,
"learning_rate": 0.00016,
"loss": 2.2231,
"step": 68
},
{
"epoch": 0.07,
"learning_rate": 0.0001647058823529412,
"loss": 2.0318,
"step": 70
},
{
"epoch": 0.08,
"learning_rate": 0.00016941176470588237,
"loss": 2.2135,
"step": 72
},
{
"epoch": 0.08,
"learning_rate": 0.00017411764705882354,
"loss": 2.093,
"step": 74
},
{
"epoch": 0.08,
"learning_rate": 0.00017882352941176472,
"loss": 2.0507,
"step": 76
},
{
"epoch": 0.08,
"learning_rate": 0.0001835294117647059,
"loss": 2.115,
"step": 78
},
{
"epoch": 0.09,
"learning_rate": 0.00018823529411764707,
"loss": 2.1991,
"step": 80
},
{
"epoch": 0.09,
"learning_rate": 0.00019294117647058825,
"loss": 2.1561,
"step": 82
},
{
"epoch": 0.09,
"learning_rate": 0.00019764705882352942,
"loss": 2.1816,
"step": 84
},
{
"epoch": 0.09,
"learning_rate": 0.00019999993373829138,
"loss": 1.9079,
"step": 86
},
{
"epoch": 0.09,
"learning_rate": 0.00019999940364514925,
"loss": 2.1371,
"step": 88
},
{
"epoch": 0.1,
"learning_rate": 0.00019999834346167496,
"loss": 2.0254,
"step": 90
},
{
"epoch": 0.1,
"learning_rate": 0.00019999675319348848,
"loss": 1.9081,
"step": 92
},
{
"epoch": 0.1,
"learning_rate": 0.0001999946328490197,
"loss": 1.9681,
"step": 94
},
{
"epoch": 0.1,
"learning_rate": 0.0001999919824395085,
"loss": 2.1084,
"step": 96
},
{
"epoch": 0.1,
"learning_rate": 0.00019998880197900446,
"loss": 1.8421,
"step": 98
},
{
"epoch": 0.11,
"learning_rate": 0.00019998509148436697,
"loss": 2.0253,
"step": 100
},
{
"epoch": 0.11,
"learning_rate": 0.0001999808509752652,
"loss": 2.2719,
"step": 102
},
{
"epoch": 0.11,
"learning_rate": 0.00019997608047417776,
"loss": 2.3961,
"step": 104
},
{
"epoch": 0.11,
"learning_rate": 0.0001999707800063928,
"loss": 2.2332,
"step": 106
},
{
"epoch": 0.12,
"learning_rate": 0.00019996494960000774,
"loss": 2.3148,
"step": 108
},
{
"epoch": 0.12,
"learning_rate": 0.00019995858928592916,
"loss": 2.2659,
"step": 110
},
{
"epoch": 0.12,
"learning_rate": 0.00019995169909787271,
"loss": 2.3069,
"step": 112
},
{
"epoch": 0.12,
"learning_rate": 0.0001999442790723628,
"loss": 2.1792,
"step": 114
},
{
"epoch": 0.12,
"learning_rate": 0.0001999363292487325,
"loss": 2.2628,
"step": 116
},
{
"epoch": 0.13,
"learning_rate": 0.00019992784966912333,
"loss": 2.3282,
"step": 118
},
{
"epoch": 0.13,
"learning_rate": 0.00019991884037848497,
"loss": 2.286,
"step": 120
},
{
"epoch": 0.13,
"learning_rate": 0.00019990930142457515,
"loss": 2.2392,
"step": 122
},
{
"epoch": 0.13,
"learning_rate": 0.00019989923285795914,
"loss": 2.1468,
"step": 124
},
{
"epoch": 0.13,
"learning_rate": 0.0001998886347320098,
"loss": 2.2453,
"step": 126
},
{
"epoch": 0.14,
"learning_rate": 0.00019987750710290713,
"loss": 2.1149,
"step": 128
},
{
"epoch": 0.14,
"learning_rate": 0.00019986585002963793,
"loss": 2.1051,
"step": 130
},
{
"epoch": 0.14,
"learning_rate": 0.00019985366357399564,
"loss": 2.0007,
"step": 132
},
{
"epoch": 0.14,
"learning_rate": 0.00019984094780057978,
"loss": 1.963,
"step": 134
},
{
"epoch": 0.14,
"learning_rate": 0.00019982770277679596,
"loss": 1.9235,
"step": 136
},
{
"epoch": 0.15,
"learning_rate": 0.00019981392857285505,
"loss": 1.861,
"step": 138
},
{
"epoch": 0.15,
"learning_rate": 0.0001997996252617733,
"loss": 2.1247,
"step": 140
},
{
"epoch": 0.15,
"learning_rate": 0.00019978479291937165,
"loss": 1.7524,
"step": 142
},
{
"epoch": 0.15,
"learning_rate": 0.0001997694316242753,
"loss": 1.9346,
"step": 144
},
{
"epoch": 0.16,
"learning_rate": 0.00019975354145791355,
"loss": 1.6186,
"step": 146
},
{
"epoch": 0.16,
"learning_rate": 0.00019973712250451908,
"loss": 1.9757,
"step": 148
},
{
"epoch": 0.16,
"learning_rate": 0.00019972017485112774,
"loss": 1.9019,
"step": 150
},
{
"epoch": 0.16,
"learning_rate": 0.00019970269858757787,
"loss": 2.2553,
"step": 152
},
{
"epoch": 0.16,
"learning_rate": 0.00019968469380651015,
"loss": 2.2539,
"step": 154
},
{
"epoch": 0.17,
"learning_rate": 0.00019966616060336655,
"loss": 2.173,
"step": 156
},
{
"epoch": 0.17,
"learning_rate": 0.00019964709907639057,
"loss": 2.1496,
"step": 158
},
{
"epoch": 0.17,
"learning_rate": 0.000199627509326626,
"loss": 2.2138,
"step": 160
},
{
"epoch": 0.17,
"learning_rate": 0.00019960739145791684,
"loss": 2.2994,
"step": 162
},
{
"epoch": 0.17,
"learning_rate": 0.00019958674557690666,
"loss": 2.2498,
"step": 164
},
{
"epoch": 0.18,
"learning_rate": 0.00019956557179303788,
"loss": 2.2241,
"step": 166
},
{
"epoch": 0.18,
"learning_rate": 0.00019954387021855138,
"loss": 2.257,
"step": 168
},
{
"epoch": 0.18,
"learning_rate": 0.00019952164096848578,
"loss": 2.1482,
"step": 170
},
{
"epoch": 0.18,
"learning_rate": 0.00019949888416067688,
"loss": 2.1853,
"step": 172
},
{
"epoch": 0.19,
"learning_rate": 0.00019947559991575706,
"loss": 2.1136,
"step": 174
},
{
"epoch": 0.19,
"learning_rate": 0.00019945178835715458,
"loss": 2.1496,
"step": 176
},
{
"epoch": 0.19,
"learning_rate": 0.00019942744961109297,
"loss": 2.0761,
"step": 178
},
{
"epoch": 0.19,
"learning_rate": 0.0001994025838065903,
"loss": 2.0665,
"step": 180
},
{
"epoch": 0.19,
"learning_rate": 0.00019937719107545864,
"loss": 2.1202,
"step": 182
},
{
"epoch": 0.2,
"learning_rate": 0.00019935127155230314,
"loss": 1.9078,
"step": 184
},
{
"epoch": 0.2,
"learning_rate": 0.0001993248253745216,
"loss": 1.9247,
"step": 186
},
{
"epoch": 0.2,
"learning_rate": 0.0001992978526823034,
"loss": 1.8159,
"step": 188
},
{
"epoch": 0.2,
"learning_rate": 0.00019927035361862904,
"loss": 1.7471,
"step": 190
},
{
"epoch": 0.2,
"learning_rate": 0.0001992423283292693,
"loss": 1.8876,
"step": 192
},
{
"epoch": 0.21,
"learning_rate": 0.00019921377696278437,
"loss": 1.771,
"step": 194
},
{
"epoch": 0.21,
"learning_rate": 0.00019918469967052327,
"loss": 1.7633,
"step": 196
},
{
"epoch": 0.21,
"learning_rate": 0.00019915509660662275,
"loss": 1.7469,
"step": 198
},
{
"epoch": 0.21,
"learning_rate": 0.00019912496792800677,
"loss": 1.9769,
"step": 200
},
{
"epoch": 0.22,
"learning_rate": 0.00019909431379438544,
"loss": 2.2334,
"step": 202
},
{
"epoch": 0.22,
"learning_rate": 0.0001990631343682544,
"loss": 2.226,
"step": 204
},
{
"epoch": 0.22,
"learning_rate": 0.00019903142981489373,
"loss": 2.129,
"step": 206
},
{
"epoch": 0.22,
"learning_rate": 0.0001989992003023672,
"loss": 2.2408,
"step": 208
},
{
"epoch": 0.22,
"learning_rate": 0.00019896644600152135,
"loss": 2.142,
"step": 210
},
{
"epoch": 0.23,
"learning_rate": 0.0001989331670859846,
"loss": 2.3385,
"step": 212
},
{
"epoch": 0.23,
"learning_rate": 0.00019889936373216634,
"loss": 2.2516,
"step": 214
},
{
"epoch": 0.23,
"learning_rate": 0.0001988650361192559,
"loss": 2.2209,
"step": 216
},
{
"epoch": 0.23,
"learning_rate": 0.00019883018442922178,
"loss": 2.1603,
"step": 218
},
{
"epoch": 0.23,
"learning_rate": 0.0001987948088468105,
"loss": 2.2952,
"step": 220
},
{
"epoch": 0.24,
"learning_rate": 0.00019875890955954573,
"loss": 2.2628,
"step": 222
},
{
"epoch": 0.24,
"learning_rate": 0.00019872248675772722,
"loss": 2.2564,
"step": 224
},
{
"epoch": 0.24,
"learning_rate": 0.0001986855406344299,
"loss": 2.0969,
"step": 226
},
{
"epoch": 0.24,
"learning_rate": 0.00019864807138550273,
"loss": 2.1252,
"step": 228
},
{
"epoch": 0.25,
"learning_rate": 0.00019861007920956786,
"loss": 1.9448,
"step": 230
},
{
"epoch": 0.25,
"learning_rate": 0.0001985715643080192,
"loss": 1.9488,
"step": 232
},
{
"epoch": 0.25,
"learning_rate": 0.00019853252688502187,
"loss": 1.9668,
"step": 234
},
{
"epoch": 0.25,
"learning_rate": 0.00019849296714751063,
"loss": 1.8091,
"step": 236
},
{
"epoch": 0.25,
"learning_rate": 0.0001984528853051891,
"loss": 1.9742,
"step": 238
},
{
"epoch": 0.26,
"learning_rate": 0.00019841228157052853,
"loss": 1.6913,
"step": 240
},
{
"epoch": 0.26,
"learning_rate": 0.00019837115615876664,
"loss": 1.8882,
"step": 242
},
{
"epoch": 0.26,
"learning_rate": 0.00019832950928790657,
"loss": 1.5621,
"step": 244
},
{
"epoch": 0.26,
"learning_rate": 0.0001982873411787157,
"loss": 1.6418,
"step": 246
},
{
"epoch": 0.26,
"learning_rate": 0.0001982446520547244,
"loss": 1.837,
"step": 248
},
{
"epoch": 0.27,
"learning_rate": 0.00019820144214222497,
"loss": 1.8345,
"step": 250
},
{
"epoch": 0.27,
"learning_rate": 0.00019815771167027034,
"loss": 2.2542,
"step": 252
},
{
"epoch": 0.27,
"learning_rate": 0.00019811346087067287,
"loss": 2.3098,
"step": 254
},
{
"epoch": 0.27,
"learning_rate": 0.00019806868997800317,
"loss": 2.1615,
"step": 256
},
{
"epoch": 0.27,
"learning_rate": 0.0001980233992295889,
"loss": 2.314,
"step": 258
},
{
"epoch": 0.28,
"learning_rate": 0.00019797758886551324,
"loss": 2.2309,
"step": 260
},
{
"epoch": 0.28,
"learning_rate": 0.0001979312591286141,
"loss": 2.1631,
"step": 262
},
{
"epoch": 0.28,
"learning_rate": 0.00019788441026448225,
"loss": 2.0791,
"step": 264
},
{
"epoch": 0.28,
"learning_rate": 0.0001978370425214606,
"loss": 2.2653,
"step": 266
},
{
"epoch": 0.29,
"learning_rate": 0.0001977891561506424,
"loss": 2.2547,
"step": 268
},
{
"epoch": 0.29,
"learning_rate": 0.00019774075140587024,
"loss": 2.2326,
"step": 270
},
{
"epoch": 0.29,
"learning_rate": 0.00019769182854373444,
"loss": 2.0206,
"step": 272
},
{
"epoch": 0.29,
"learning_rate": 0.000197642387823572,
"loss": 2.0665,
"step": 274
},
{
"epoch": 0.29,
"learning_rate": 0.00019759242950746487,
"loss": 2.1532,
"step": 276
},
{
"epoch": 0.3,
"learning_rate": 0.0001975419538602389,
"loss": 2.0988,
"step": 278
},
{
"epoch": 0.3,
"learning_rate": 0.0001974909611494622,
"loss": 1.937,
"step": 280
},
{
"epoch": 0.3,
"learning_rate": 0.0001974394516454438,
"loss": 1.9614,
"step": 282
},
{
"epoch": 0.3,
"learning_rate": 0.00019738742562123225,
"loss": 1.8518,
"step": 284
},
{
"epoch": 0.3,
"learning_rate": 0.00019733488335261408,
"loss": 1.7994,
"step": 286
},
{
"epoch": 0.31,
"learning_rate": 0.00019728182511811245,
"loss": 1.9275,
"step": 288
},
{
"epoch": 0.31,
"learning_rate": 0.00019722825119898566,
"loss": 1.9991,
"step": 290
},
{
"epoch": 0.31,
"learning_rate": 0.0001971741618792255,
"loss": 1.6737,
"step": 292
},
{
"epoch": 0.31,
"learning_rate": 0.00019711955744555594,
"loss": 1.4669,
"step": 294
},
{
"epoch": 0.32,
"learning_rate": 0.0001970644381874316,
"loss": 1.5002,
"step": 296
},
{
"epoch": 0.32,
"learning_rate": 0.00019700880439703602,
"loss": 1.9151,
"step": 298
},
{
"epoch": 0.32,
"learning_rate": 0.00019695265636928032,
"loss": 1.7493,
"step": 300
},
{
"epoch": 0.32,
"learning_rate": 0.00019689599440180153,
"loss": 2.2535,
"step": 302
},
{
"epoch": 0.32,
"learning_rate": 0.00019683881879496107,
"loss": 2.2597,
"step": 304
},
{
"epoch": 0.33,
"learning_rate": 0.00019678112985184308,
"loss": 2.3117,
"step": 306
},
{
"epoch": 0.33,
"learning_rate": 0.00019672292787825292,
"loss": 2.1624,
"step": 308
},
{
"epoch": 0.33,
"learning_rate": 0.00019666421318271547,
"loss": 2.1857,
"step": 310
},
{
"epoch": 0.33,
"learning_rate": 0.0001966049860764735,
"loss": 2.2101,
"step": 312
},
{
"epoch": 0.33,
"learning_rate": 0.00019654524687348607,
"loss": 2.1749,
"step": 314
},
{
"epoch": 0.34,
"learning_rate": 0.00019648499589042676,
"loss": 2.1557,
"step": 316
},
{
"epoch": 0.34,
"learning_rate": 0.00019642423344668218,
"loss": 2.2259,
"step": 318
},
{
"epoch": 0.34,
"learning_rate": 0.00019636295986435003,
"loss": 2.1723,
"step": 320
},
{
"epoch": 0.34,
"learning_rate": 0.00019630117546823759,
"loss": 2.294,
"step": 322
},
{
"epoch": 0.35,
"learning_rate": 0.00019623888058585993,
"loss": 2.2241,
"step": 324
},
{
"epoch": 0.35,
"learning_rate": 0.00019617607554743818,
"loss": 2.1496,
"step": 326
},
{
"epoch": 0.35,
"learning_rate": 0.00019611276068589776,
"loss": 2.1116,
"step": 328
},
{
"epoch": 0.35,
"learning_rate": 0.00019604893633686662,
"loss": 2.1723,
"step": 330
},
{
"epoch": 0.35,
"learning_rate": 0.0001959846028386735,
"loss": 2.0301,
"step": 332
},
{
"epoch": 0.36,
"learning_rate": 0.00019591976053234608,
"loss": 1.8651,
"step": 334
},
{
"epoch": 0.36,
"learning_rate": 0.0001958544097616092,
"loss": 1.8286,
"step": 336
},
{
"epoch": 0.36,
"learning_rate": 0.00019578855087288302,
"loss": 1.9081,
"step": 338
},
{
"epoch": 0.36,
"learning_rate": 0.0001957221842152813,
"loss": 1.8546,
"step": 340
},
{
"epoch": 0.36,
"learning_rate": 0.0001956553101406093,
"loss": 1.7914,
"step": 342
},
{
"epoch": 0.37,
"learning_rate": 0.00019558792900336216,
"loss": 1.7997,
"step": 344
},
{
"epoch": 0.37,
"learning_rate": 0.00019552004116072294,
"loss": 1.3596,
"step": 346
},
{
"epoch": 0.37,
"learning_rate": 0.0001954516469725606,
"loss": 1.6549,
"step": 348
},
{
"epoch": 0.37,
"learning_rate": 0.00019538274680142834,
"loss": 1.6592,
"step": 350
},
{
"epoch": 0.38,
"learning_rate": 0.00019531334101256147,
"loss": 2.2759,
"step": 352
},
{
"epoch": 0.38,
"learning_rate": 0.00019524342997387557,
"loss": 2.1805,
"step": 354
},
{
"epoch": 0.38,
"learning_rate": 0.0001951730140559645,
"loss": 2.2585,
"step": 356
},
{
"epoch": 0.38,
"learning_rate": 0.00019510209363209847,
"loss": 2.2573,
"step": 358
},
{
"epoch": 0.38,
"learning_rate": 0.00019503066907822198,
"loss": 2.3154,
"step": 360
},
{
"epoch": 0.39,
"learning_rate": 0.000194958740772952,
"loss": 2.2306,
"step": 362
},
{
"epoch": 0.39,
"learning_rate": 0.00019488630909757579,
"loss": 2.3178,
"step": 364
},
{
"epoch": 0.39,
"learning_rate": 0.00019481337443604893,
"loss": 2.2691,
"step": 366
},
{
"epoch": 0.39,
"learning_rate": 0.0001947399371749933,
"loss": 2.153,
"step": 368
},
{
"epoch": 0.39,
"learning_rate": 0.00019466599770369509,
"loss": 2.0471,
"step": 370
},
{
"epoch": 0.4,
"learning_rate": 0.00019459155641410257,
"loss": 2.3142,
"step": 372
},
{
"epoch": 0.4,
"learning_rate": 0.00019451661370082426,
"loss": 2.1241,
"step": 374
},
{
"epoch": 0.4,
"learning_rate": 0.0001944411699611265,
"loss": 2.1079,
"step": 376
},
{
"epoch": 0.4,
"learning_rate": 0.0001943652255949317,
"loss": 2.063,
"step": 378
},
{
"epoch": 0.41,
"learning_rate": 0.00019428878100481606,
"loss": 2.0062,
"step": 380
},
{
"epoch": 0.41,
"learning_rate": 0.00019421183659600725,
"loss": 1.9,
"step": 382
},
{
"epoch": 0.41,
"learning_rate": 0.00019413439277638265,
"loss": 1.9723,
"step": 384
},
{
"epoch": 0.41,
"learning_rate": 0.00019405644995646696,
"loss": 1.969,
"step": 386
},
{
"epoch": 0.41,
"learning_rate": 0.00019397800854942986,
"loss": 2.0202,
"step": 388
},
{
"epoch": 0.42,
"learning_rate": 0.00019389906897108428,
"loss": 1.9028,
"step": 390
},
{
"epoch": 0.42,
"learning_rate": 0.0001938196316398837,
"loss": 1.8172,
"step": 392
},
{
"epoch": 0.42,
"learning_rate": 0.00019373969697692028,
"loss": 1.7243,
"step": 394
},
{
"epoch": 0.42,
"learning_rate": 0.00019365926540592247,
"loss": 1.4621,
"step": 396
},
{
"epoch": 0.42,
"learning_rate": 0.0001935783373532528,
"loss": 1.7987,
"step": 398
},
{
"epoch": 0.43,
"learning_rate": 0.00019349691324790555,
"loss": 1.7935,
"step": 400
},
{
"epoch": 0.43,
"learning_rate": 0.0001934149935215047,
"loss": 2.2858,
"step": 402
},
{
"epoch": 0.43,
"learning_rate": 0.00019333257860830135,
"loss": 2.3798,
"step": 404
},
{
"epoch": 0.43,
"learning_rate": 0.00019324966894517155,
"loss": 2.1534,
"step": 406
},
{
"epoch": 0.43,
"learning_rate": 0.00019316626497161408,
"loss": 2.2648,
"step": 408
},
{
"epoch": 0.44,
"learning_rate": 0.00019308236712974795,
"loss": 2.2946,
"step": 410
},
{
"epoch": 0.44,
"learning_rate": 0.0001929979758643102,
"loss": 2.319,
"step": 412
},
{
"epoch": 0.44,
"learning_rate": 0.00019291309162265338,
"loss": 2.2271,
"step": 414
},
{
"epoch": 0.44,
"learning_rate": 0.0001928277148547434,
"loss": 2.0746,
"step": 416
},
{
"epoch": 0.45,
"learning_rate": 0.00019274184601315687,
"loss": 2.1231,
"step": 418
},
{
"epoch": 0.45,
"learning_rate": 0.000192655485553079,
"loss": 2.3176,
"step": 420
},
{
"epoch": 0.45,
"learning_rate": 0.00019256863393230094,
"loss": 2.1657,
"step": 422
},
{
"epoch": 0.45,
"learning_rate": 0.00019248129161121748,
"loss": 2.2696,
"step": 424
},
{
"epoch": 0.45,
"learning_rate": 0.0001923934590528246,
"loss": 2.2132,
"step": 426
},
{
"epoch": 0.46,
"learning_rate": 0.00019230513672271698,
"loss": 2.104,
"step": 428
},
{
"epoch": 0.46,
"learning_rate": 0.0001922163250890855,
"loss": 1.9319,
"step": 430
},
{
"epoch": 0.46,
"learning_rate": 0.0001921270246227149,
"loss": 1.9152,
"step": 432
},
{
"epoch": 0.46,
"learning_rate": 0.00019203723579698108,
"loss": 1.8615,
"step": 434
},
{
"epoch": 0.46,
"learning_rate": 0.00019194695908784882,
"loss": 2.0695,
"step": 436
},
{
"epoch": 0.47,
"learning_rate": 0.0001918561949738691,
"loss": 1.8626,
"step": 438
},
{
"epoch": 0.47,
"learning_rate": 0.0001917649439361765,
"loss": 1.7538,
"step": 440
},
{
"epoch": 0.47,
"learning_rate": 0.00019167320645848695,
"loss": 2.0082,
"step": 442
},
{
"epoch": 0.47,
"learning_rate": 0.00019158098302709476,
"loss": 1.6011,
"step": 444
},
{
"epoch": 0.48,
"learning_rate": 0.00019148827413087034,
"loss": 1.5286,
"step": 446
},
{
"epoch": 0.48,
"learning_rate": 0.00019139508026125754,
"loss": 1.8795,
"step": 448
},
{
"epoch": 0.48,
"learning_rate": 0.000191301401912271,
"loss": 1.7509,
"step": 450
},
{
"epoch": 0.48,
"learning_rate": 0.00019120723958049353,
"loss": 2.3155,
"step": 452
},
{
"epoch": 0.48,
"learning_rate": 0.0001911125937650736,
"loss": 2.2125,
"step": 454
},
{
"epoch": 0.49,
"learning_rate": 0.00019101746496772242,
"loss": 2.2262,
"step": 456
},
{
"epoch": 0.49,
"learning_rate": 0.0001909218536927116,
"loss": 2.3185,
"step": 458
},
{
"epoch": 0.49,
"learning_rate": 0.0001908257604468703,
"loss": 2.2496,
"step": 460
},
{
"epoch": 0.49,
"learning_rate": 0.00019072918573958254,
"loss": 2.3569,
"step": 462
},
{
"epoch": 0.49,
"learning_rate": 0.0001906321300827846,
"loss": 2.1697,
"step": 464
},
{
"epoch": 0.5,
"learning_rate": 0.00019053459399096215,
"loss": 2.197,
"step": 466
},
{
"epoch": 0.5,
"learning_rate": 0.00019043657798114766,
"loss": 1.9929,
"step": 468
},
{
"epoch": 0.5,
"learning_rate": 0.00019033808257291768,
"loss": 2.1488,
"step": 470
},
{
"epoch": 0.5,
"learning_rate": 0.0001902391082883899,
"loss": 2.2224,
"step": 472
},
{
"epoch": 0.51,
"learning_rate": 0.00019013965565222062,
"loss": 2.0495,
"step": 474
},
{
"epoch": 0.51,
"learning_rate": 0.00019003972519160178,
"loss": 2.0964,
"step": 476
},
{
"epoch": 0.51,
"learning_rate": 0.0001899393174362582,
"loss": 1.8708,
"step": 478
},
{
"epoch": 0.51,
"learning_rate": 0.00018983843291844492,
"loss": 1.9741,
"step": 480
},
{
"epoch": 0.51,
"learning_rate": 0.00018973707217294415,
"loss": 1.9908,
"step": 482
},
{
"epoch": 0.52,
"learning_rate": 0.00018963523573706264,
"loss": 1.7973,
"step": 484
},
{
"epoch": 0.52,
"learning_rate": 0.0001895329241506287,
"loss": 1.9293,
"step": 486
},
{
"epoch": 0.52,
"learning_rate": 0.00018943013795598944,
"loss": 1.94,
"step": 488
},
{
"epoch": 0.52,
"learning_rate": 0.00018932687769800767,
"loss": 1.9435,
"step": 490
},
{
"epoch": 0.52,
"learning_rate": 0.00018922314392405944,
"loss": 1.7907,
"step": 492
},
{
"epoch": 0.53,
"learning_rate": 0.00018911893718403063,
"loss": 1.6344,
"step": 494
},
{
"epoch": 0.53,
"learning_rate": 0.00018901425803031447,
"loss": 1.3563,
"step": 496
},
{
"epoch": 0.53,
"learning_rate": 0.00018890910701780826,
"loss": 1.7,
"step": 498
},
{
"epoch": 0.53,
"learning_rate": 0.00018880348470391077,
"loss": 1.7682,
"step": 500
},
{
"epoch": 0.54,
"learning_rate": 0.00018869739164851889,
"loss": 2.2041,
"step": 502
},
{
"epoch": 0.54,
"learning_rate": 0.00018859082841402513,
"loss": 2.237,
"step": 504
},
{
"epoch": 0.54,
"learning_rate": 0.0001884837955653142,
"loss": 2.1694,
"step": 506
},
{
"epoch": 0.54,
"learning_rate": 0.00018837629366976025,
"loss": 2.2373,
"step": 508
},
{
"epoch": 0.54,
"learning_rate": 0.0001882683232972239,
"loss": 2.2511,
"step": 510
},
{
"epoch": 0.55,
"learning_rate": 0.000188159885020049,
"loss": 2.2474,
"step": 512
},
{
"epoch": 0.55,
"learning_rate": 0.00018805097941305984,
"loss": 2.1938,
"step": 514
},
{
"epoch": 0.55,
"learning_rate": 0.00018794160705355796,
"loss": 2.0874,
"step": 516
},
{
"epoch": 0.55,
"learning_rate": 0.00018783176852131908,
"loss": 2.2795,
"step": 518
},
{
"epoch": 0.55,
"learning_rate": 0.00018772146439859015,
"loss": 2.179,
"step": 520
},
{
"epoch": 0.56,
"learning_rate": 0.00018761069527008613,
"loss": 2.0959,
"step": 522
},
{
"epoch": 0.56,
"learning_rate": 0.00018749946172298698,
"loss": 2.3345,
"step": 524
},
{
"epoch": 0.56,
"learning_rate": 0.00018738776434693447,
"loss": 2.0522,
"step": 526
},
{
"epoch": 0.56,
"learning_rate": 0.00018727560373402917,
"loss": 2.1055,
"step": 528
},
{
"epoch": 0.56,
"learning_rate": 0.00018716298047882714,
"loss": 2.0651,
"step": 530
},
{
"epoch": 0.57,
"learning_rate": 0.00018704989517833695,
"loss": 2.0961,
"step": 532
},
{
"epoch": 0.57,
"learning_rate": 0.0001869363484320164,
"loss": 1.9879,
"step": 534
},
{
"epoch": 0.57,
"learning_rate": 0.00018682234084176945,
"loss": 2.0118,
"step": 536
},
{
"epoch": 0.57,
"learning_rate": 0.0001867078730119429,
"loss": 1.9059,
"step": 538
},
{
"epoch": 0.58,
"learning_rate": 0.00018659294554932324,
"loss": 1.8227,
"step": 540
},
{
"epoch": 0.58,
"learning_rate": 0.00018647755906313348,
"loss": 1.8794,
"step": 542
},
{
"epoch": 0.58,
"learning_rate": 0.0001863617141650299,
"loss": 1.6243,
"step": 544
},
{
"epoch": 0.58,
"learning_rate": 0.00018624541146909873,
"loss": 1.6429,
"step": 546
},
{
"epoch": 0.58,
"learning_rate": 0.00018612865159185304,
"loss": 2.03,
"step": 548
},
{
"epoch": 0.59,
"learning_rate": 0.0001860114351522293,
"loss": 1.7897,
"step": 550
},
{
"epoch": 0.59,
"learning_rate": 0.00018589376277158425,
"loss": 2.2226,
"step": 552
},
{
"epoch": 0.59,
"learning_rate": 0.00018577563507369153,
"loss": 2.2998,
"step": 554
},
{
"epoch": 0.59,
"learning_rate": 0.00018565705268473837,
"loss": 2.1385,
"step": 556
},
{
"epoch": 0.59,
"learning_rate": 0.0001855380162333223,
"loss": 2.1793,
"step": 558
},
{
"epoch": 0.6,
"learning_rate": 0.0001854185263504478,
"loss": 2.2456,
"step": 560
},
{
"epoch": 0.6,
"learning_rate": 0.00018529858366952298,
"loss": 2.162,
"step": 562
},
{
"epoch": 0.6,
"learning_rate": 0.00018517818882635617,
"loss": 2.1046,
"step": 564
},
{
"epoch": 0.6,
"learning_rate": 0.0001850573424591526,
"loss": 2.1761,
"step": 566
},
{
"epoch": 0.61,
"learning_rate": 0.00018493604520851097,
"loss": 2.2593,
"step": 568
},
{
"epoch": 0.61,
"learning_rate": 0.00018481429771742018,
"loss": 2.2067,
"step": 570
},
{
"epoch": 0.61,
"learning_rate": 0.00018469210063125572,
"loss": 2.1257,
"step": 572
},
{
"epoch": 0.61,
"learning_rate": 0.00018456945459777643,
"loss": 2.2823,
"step": 574
},
{
"epoch": 0.61,
"learning_rate": 0.0001844463602671209,
"loss": 2.2942,
"step": 576
},
{
"epoch": 0.62,
"learning_rate": 0.0001843228182918042,
"loss": 2.1126,
"step": 578
},
{
"epoch": 0.62,
"learning_rate": 0.0001841988293267143,
"loss": 2.2014,
"step": 580
},
{
"epoch": 0.62,
"learning_rate": 0.00018407439402910858,
"loss": 2.0244,
"step": 582
},
{
"epoch": 0.62,
"learning_rate": 0.00018394951305861055,
"loss": 1.9842,
"step": 584
},
{
"epoch": 0.62,
"learning_rate": 0.00018382418707720604,
"loss": 1.8637,
"step": 586
},
{
"epoch": 0.63,
"learning_rate": 0.00018369841674923998,
"loss": 1.8229,
"step": 588
},
{
"epoch": 0.63,
"learning_rate": 0.00018357220274141262,
"loss": 1.8023,
"step": 590
},
{
"epoch": 0.63,
"learning_rate": 0.00018344554572277628,
"loss": 1.6493,
"step": 592
},
{
"epoch": 0.63,
"learning_rate": 0.00018331844636473152,
"loss": 1.4272,
"step": 594
},
{
"epoch": 0.64,
"learning_rate": 0.00018319090534102381,
"loss": 1.5226,
"step": 596
},
{
"epoch": 0.64,
"learning_rate": 0.0001830629233277398,
"loss": 1.5868,
"step": 598
},
{
"epoch": 0.64,
"learning_rate": 0.00018293450100330375,
"loss": 1.6859,
"step": 600
},
{
"epoch": 0.64,
"learning_rate": 0.00018280563904847415,
"loss": 2.2781,
"step": 602
},
{
"epoch": 0.64,
"learning_rate": 0.0001826763381463398,
"loss": 2.2743,
"step": 604
},
{
"epoch": 0.65,
"learning_rate": 0.0001825465989823164,
"loss": 2.2974,
"step": 606
},
{
"epoch": 0.65,
"learning_rate": 0.00018241642224414272,
"loss": 2.089,
"step": 608
},
{
"epoch": 0.65,
"learning_rate": 0.00018228580862187727,
"loss": 2.3559,
"step": 610
},
{
"epoch": 0.65,
"learning_rate": 0.00018215475880789433,
"loss": 2.2152,
"step": 612
},
{
"epoch": 0.65,
"learning_rate": 0.00018202327349688043,
"loss": 2.1726,
"step": 614
},
{
"epoch": 0.66,
"learning_rate": 0.00018189135338583066,
"loss": 2.2242,
"step": 616
},
{
"epoch": 0.66,
"learning_rate": 0.00018175899917404492,
"loss": 2.2506,
"step": 618
},
{
"epoch": 0.66,
"learning_rate": 0.00018162621156312433,
"loss": 2.1324,
"step": 620
},
{
"epoch": 0.66,
"learning_rate": 0.00018149299125696735,
"loss": 2.006,
"step": 622
},
{
"epoch": 0.67,
"learning_rate": 0.00018135933896176612,
"loss": 2.2178,
"step": 624
},
{
"epoch": 0.67,
"learning_rate": 0.00018122525538600282,
"loss": 2.0817,
"step": 626
},
{
"epoch": 0.67,
"learning_rate": 0.00018109074124044572,
"loss": 2.0006,
"step": 628
},
{
"epoch": 0.67,
"learning_rate": 0.00018095579723814557,
"loss": 1.9424,
"step": 630
},
{
"epoch": 0.67,
"learning_rate": 0.00018082042409443174,
"loss": 1.9661,
"step": 632
},
{
"epoch": 0.68,
"learning_rate": 0.00018068462252690843,
"loss": 1.8678,
"step": 634
},
{
"epoch": 0.68,
"learning_rate": 0.00018054839325545096,
"loss": 1.8343,
"step": 636
},
{
"epoch": 0.68,
"learning_rate": 0.0001804117370022018,
"loss": 1.8003,
"step": 638
},
{
"epoch": 0.68,
"learning_rate": 0.0001802746544915669,
"loss": 1.7928,
"step": 640
},
{
"epoch": 0.68,
"learning_rate": 0.00018013714645021166,
"loss": 1.8922,
"step": 642
},
{
"epoch": 0.69,
"learning_rate": 0.00017999921360705733,
"loss": 1.6961,
"step": 644
},
{
"epoch": 0.69,
"learning_rate": 0.0001798608566932769,
"loss": 1.3043,
"step": 646
},
{
"epoch": 0.69,
"learning_rate": 0.00017972207644229138,
"loss": 1.8295,
"step": 648
},
{
"epoch": 0.69,
"learning_rate": 0.0001795828735897658,
"loss": 1.7105,
"step": 650
},
{
"epoch": 0.69,
"learning_rate": 0.00017944324887360553,
"loss": 2.1881,
"step": 652
},
{
"epoch": 0.7,
"learning_rate": 0.000179303203033952,
"loss": 2.2434,
"step": 654
},
{
"epoch": 0.7,
"learning_rate": 0.0001791627368131792,
"loss": 2.3566,
"step": 656
},
{
"epoch": 0.7,
"learning_rate": 0.00017902185095588927,
"loss": 2.3222,
"step": 658
},
{
"epoch": 0.7,
"learning_rate": 0.00017888054620890915,
"loss": 2.181,
"step": 660
},
{
"epoch": 0.71,
"learning_rate": 0.00017873882332128597,
"loss": 2.3261,
"step": 662
},
{
"epoch": 0.71,
"learning_rate": 0.00017859668304428365,
"loss": 2.2798,
"step": 664
},
{
"epoch": 0.71,
"learning_rate": 0.00017845412613137844,
"loss": 2.0487,
"step": 666
},
{
"epoch": 0.71,
"learning_rate": 0.00017831115333825535,
"loss": 2.1863,
"step": 668
},
{
"epoch": 0.71,
"learning_rate": 0.00017816776542280377,
"loss": 2.1308,
"step": 670
},
{
"epoch": 0.72,
"learning_rate": 0.0001780239631451138,
"loss": 2.3122,
"step": 672
},
{
"epoch": 0.72,
"learning_rate": 0.0001778797472674719,
"loss": 2.2757,
"step": 674
},
{
"epoch": 0.72,
"learning_rate": 0.00017773511855435708,
"loss": 2.0241,
"step": 676
},
{
"epoch": 0.72,
"learning_rate": 0.00017759007777243672,
"loss": 1.9896,
"step": 678
},
{
"epoch": 0.72,
"learning_rate": 0.00017744462569056256,
"loss": 1.9607,
"step": 680
},
{
"epoch": 0.73,
"learning_rate": 0.00017729876307976663,
"loss": 1.9798,
"step": 682
},
{
"epoch": 0.73,
"learning_rate": 0.00017715249071325717,
"loss": 1.9075,
"step": 684
},
{
"epoch": 0.73,
"learning_rate": 0.00017700580936641443,
"loss": 2.0141,
"step": 686
},
{
"epoch": 0.73,
"learning_rate": 0.00017685871981678672,
"loss": 1.9238,
"step": 688
},
{
"epoch": 0.74,
"learning_rate": 0.00017671122284408614,
"loss": 1.9244,
"step": 690
},
{
"epoch": 0.74,
"learning_rate": 0.00017656331923018457,
"loss": 1.6621,
"step": 692
},
{
"epoch": 0.74,
"learning_rate": 0.00017641500975910945,
"loss": 1.7402,
"step": 694
},
{
"epoch": 0.74,
"learning_rate": 0.0001762662952170396,
"loss": 1.3913,
"step": 696
},
{
"epoch": 0.74,
"learning_rate": 0.0001761171763923012,
"loss": 1.5825,
"step": 698
},
{
"epoch": 0.75,
"learning_rate": 0.0001759676540753634,
"loss": 1.6809,
"step": 700
},
{
"epoch": 0.75,
"learning_rate": 0.00017581772905883423,
"loss": 2.3459,
"step": 702
},
{
"epoch": 0.75,
"learning_rate": 0.00017566740213745648,
"loss": 2.1963,
"step": 704
},
{
"epoch": 0.75,
"learning_rate": 0.00017551667410810337,
"loss": 2.1334,
"step": 706
},
{
"epoch": 0.75,
"learning_rate": 0.00017536554576977442,
"loss": 2.3778,
"step": 708
},
{
"epoch": 0.76,
"learning_rate": 0.00017521401792359108,
"loss": 2.183,
"step": 710
},
{
"epoch": 0.76,
"learning_rate": 0.0001750620913727926,
"loss": 2.1674,
"step": 712
},
{
"epoch": 0.76,
"learning_rate": 0.00017490976692273176,
"loss": 2.3534,
"step": 714
},
{
"epoch": 0.76,
"learning_rate": 0.00017475704538087055,
"loss": 2.1677,
"step": 716
},
{
"epoch": 0.77,
"learning_rate": 0.00017460392755677592,
"loss": 2.1642,
"step": 718
},
{
"epoch": 0.77,
"learning_rate": 0.0001744504142621155,
"loss": 2.1983,
"step": 720
},
{
"epoch": 0.77,
"learning_rate": 0.0001742965063106533,
"loss": 2.1661,
"step": 722
},
{
"epoch": 0.77,
"learning_rate": 0.0001741422045182453,
"loss": 2.2135,
"step": 724
},
{
"epoch": 0.77,
"learning_rate": 0.00017398750970283532,
"loss": 2.1288,
"step": 726
},
{
"epoch": 0.78,
"learning_rate": 0.00017383242268445047,
"loss": 1.9906,
"step": 728
},
{
"epoch": 0.78,
"learning_rate": 0.00017367694428519696,
"loss": 1.9031,
"step": 730
},
{
"epoch": 0.78,
"learning_rate": 0.00017352107532925569,
"loss": 1.831,
"step": 732
},
{
"epoch": 0.78,
"learning_rate": 0.00017336481664287777,
"loss": 1.9116,
"step": 734
},
{
"epoch": 0.78,
"learning_rate": 0.00017320816905438044,
"loss": 1.8241,
"step": 736
},
{
"epoch": 0.79,
"learning_rate": 0.0001730511333941423,
"loss": 1.8745,
"step": 738
},
{
"epoch": 0.79,
"learning_rate": 0.00017289371049459922,
"loss": 1.8306,
"step": 740
},
{
"epoch": 0.79,
"learning_rate": 0.00017273590119023968,
"loss": 1.6032,
"step": 742
},
{
"epoch": 0.79,
"learning_rate": 0.00017257770631760058,
"loss": 1.3571,
"step": 744
},
{
"epoch": 0.8,
"learning_rate": 0.00017241912671526265,
"loss": 1.6282,
"step": 746
},
{
"epoch": 0.8,
"learning_rate": 0.00017226016322384604,
"loss": 1.5942,
"step": 748
},
{
"epoch": 0.8,
"learning_rate": 0.00017210081668600586,
"loss": 1.6988,
"step": 750
},
{
"epoch": 0.8,
"learning_rate": 0.00017194108794642775,
"loss": 2.334,
"step": 752
},
{
"epoch": 0.8,
"learning_rate": 0.00017178097785182337,
"loss": 2.2731,
"step": 754
},
{
"epoch": 0.81,
"learning_rate": 0.0001716204872509259,
"loss": 2.1642,
"step": 756
},
{
"epoch": 0.81,
"learning_rate": 0.00017145961699448559,
"loss": 2.4107,
"step": 758
},
{
"epoch": 0.81,
"learning_rate": 0.00017129836793526517,
"loss": 2.2767,
"step": 760
},
{
"epoch": 0.81,
"learning_rate": 0.00017113674092803543,
"loss": 2.3137,
"step": 762
},
{
"epoch": 0.81,
"learning_rate": 0.00017097473682957067,
"loss": 2.3095,
"step": 764
},
{
"epoch": 0.82,
"learning_rate": 0.00017081235649864395,
"loss": 2.1327,
"step": 766
},
{
"epoch": 0.82,
"learning_rate": 0.00017064960079602297,
"loss": 2.2666,
"step": 768
},
{
"epoch": 0.82,
"learning_rate": 0.00017048647058446505,
"loss": 2.2871,
"step": 770
},
{
"epoch": 0.82,
"learning_rate": 0.00017032296672871283,
"loss": 2.2055,
"step": 772
},
{
"epoch": 0.82,
"learning_rate": 0.00017015909009548966,
"loss": 2.1066,
"step": 774
},
{
"epoch": 0.83,
"learning_rate": 0.00016999484155349483,
"loss": 2.1887,
"step": 776
},
{
"epoch": 0.83,
"learning_rate": 0.00016983022197339923,
"loss": 2.1014,
"step": 778
},
{
"epoch": 0.83,
"learning_rate": 0.00016966523222784058,
"loss": 2.1138,
"step": 780
},
{
"epoch": 0.83,
"learning_rate": 0.00016949987319141868,
"loss": 1.8663,
"step": 782
},
{
"epoch": 0.84,
"learning_rate": 0.0001693341457406911,
"loss": 1.7421,
"step": 784
},
{
"epoch": 0.84,
"learning_rate": 0.00016916805075416823,
"loss": 1.8293,
"step": 786
},
{
"epoch": 0.84,
"learning_rate": 0.0001690015891123088,
"loss": 1.8993,
"step": 788
},
{
"epoch": 0.84,
"learning_rate": 0.00016883476169751518,
"loss": 1.8486,
"step": 790
},
{
"epoch": 0.84,
"learning_rate": 0.0001686675693941286,
"loss": 1.7033,
"step": 792
},
{
"epoch": 0.85,
"learning_rate": 0.00016850001308842458,
"loss": 1.5906,
"step": 794
},
{
"epoch": 0.85,
"learning_rate": 0.00016833209366860826,
"loss": 1.4477,
"step": 796
},
{
"epoch": 0.85,
"learning_rate": 0.00016816381202480946,
"loss": 1.8339,
"step": 798
},
{
"epoch": 0.85,
"learning_rate": 0.00016799516904907828,
"loss": 1.6691,
"step": 800
},
{
"epoch": 0.85,
"learning_rate": 0.00016782616563538016,
"loss": 2.4258,
"step": 802
},
{
"epoch": 0.86,
"learning_rate": 0.0001676568026795912,
"loss": 2.3445,
"step": 804
},
{
"epoch": 0.86,
"learning_rate": 0.00016748708107949337,
"loss": 2.137,
"step": 806
},
{
"epoch": 0.86,
"learning_rate": 0.00016731700173476988,
"loss": 2.2656,
"step": 808
},
{
"epoch": 0.86,
"learning_rate": 0.00016714656554700022,
"loss": 2.2945,
"step": 810
},
{
"epoch": 0.87,
"learning_rate": 0.0001669757734196556,
"loss": 2.0641,
"step": 812
},
{
"epoch": 0.87,
"learning_rate": 0.0001668046262580939,
"loss": 2.0698,
"step": 814
},
{
"epoch": 0.87,
"learning_rate": 0.00016663312496955517,
"loss": 2.1787,
"step": 816
},
{
"epoch": 0.87,
"learning_rate": 0.00016646127046315653,
"loss": 2.0295,
"step": 818
},
{
"epoch": 0.87,
"learning_rate": 0.0001662890636498875,
"loss": 2.2736,
"step": 820
},
{
"epoch": 0.88,
"learning_rate": 0.00016611650544260526,
"loss": 2.1205,
"step": 822
},
{
"epoch": 0.88,
"learning_rate": 0.00016594359675602962,
"loss": 2.1249,
"step": 824
},
{
"epoch": 0.88,
"learning_rate": 0.00016577033850673824,
"loss": 1.9355,
"step": 826
},
{
"epoch": 0.88,
"learning_rate": 0.00016559673161316188,
"loss": 1.8423,
"step": 828
},
{
"epoch": 0.88,
"learning_rate": 0.00016542277699557934,
"loss": 2.0979,
"step": 830
},
{
"epoch": 0.89,
"learning_rate": 0.00016524847557611278,
"loss": 1.7747,
"step": 832
},
{
"epoch": 0.89,
"learning_rate": 0.00016507382827872264,
"loss": 1.7137,
"step": 834
},
{
"epoch": 0.89,
"learning_rate": 0.0001648988360292029,
"loss": 1.9926,
"step": 836
},
{
"epoch": 0.89,
"learning_rate": 0.0001647234997551761,
"loss": 2.033,
"step": 838
},
{
"epoch": 0.9,
"learning_rate": 0.00016454782038608835,
"loss": 1.7298,
"step": 840
},
{
"epoch": 0.9,
"learning_rate": 0.00016437179885320466,
"loss": 1.8326,
"step": 842
},
{
"epoch": 0.9,
"learning_rate": 0.00016419543608960367,
"loss": 1.5744,
"step": 844
},
{
"epoch": 0.9,
"learning_rate": 0.00016401873303017287,
"loss": 1.471,
"step": 846
},
{
"epoch": 0.9,
"learning_rate": 0.00016384169061160376,
"loss": 1.7169,
"step": 848
},
{
"epoch": 0.91,
"learning_rate": 0.00016366430977238667,
"loss": 1.5636,
"step": 850
},
{
"epoch": 0.91,
"learning_rate": 0.00016348659145280585,
"loss": 2.3071,
"step": 852
},
{
"epoch": 0.91,
"learning_rate": 0.00016330853659493456,
"loss": 2.1993,
"step": 854
},
{
"epoch": 0.91,
"learning_rate": 0.00016313014614263003,
"loss": 2.1583,
"step": 856
},
{
"epoch": 0.91,
"learning_rate": 0.0001629514210415284,
"loss": 2.1996,
"step": 858
},
{
"epoch": 0.92,
"learning_rate": 0.00016277236223903986,
"loss": 2.309,
"step": 860
},
{
"epoch": 0.92,
"learning_rate": 0.00016259297068434343,
"loss": 2.2155,
"step": 862
},
{
"epoch": 0.92,
"learning_rate": 0.0001624132473283821,
"loss": 2.2474,
"step": 864
},
{
"epoch": 0.92,
"learning_rate": 0.00016223319312385766,
"loss": 2.2034,
"step": 866
},
{
"epoch": 0.93,
"learning_rate": 0.00016205280902522576,
"loss": 2.2016,
"step": 868
},
{
"epoch": 0.93,
"learning_rate": 0.00016187209598869074,
"loss": 2.133,
"step": 870
},
{
"epoch": 0.93,
"learning_rate": 0.00016169105497220064,
"loss": 2.1746,
"step": 872
},
{
"epoch": 0.93,
"learning_rate": 0.00016150968693544215,
"loss": 2.0806,
"step": 874
},
{
"epoch": 0.93,
"learning_rate": 0.00016132799283983542,
"loss": 2.2318,
"step": 876
},
{
"epoch": 0.94,
"learning_rate": 0.000161145973648529,
"loss": 2.0729,
"step": 878
},
{
"epoch": 0.94,
"learning_rate": 0.0001609636303263948,
"loss": 1.8199,
"step": 880
},
{
"epoch": 0.94,
"learning_rate": 0.00016078096384002292,
"loss": 2.0973,
"step": 882
},
{
"epoch": 0.94,
"learning_rate": 0.00016059797515771652,
"loss": 1.7302,
"step": 884
},
{
"epoch": 0.94,
"learning_rate": 0.00016041466524948663,
"loss": 1.9608,
"step": 886
},
{
"epoch": 0.95,
"learning_rate": 0.00016023103508704725,
"loss": 1.8483,
"step": 888
},
{
"epoch": 0.95,
"learning_rate": 0.00016004708564380985,
"loss": 1.9501,
"step": 890
},
{
"epoch": 0.95,
"learning_rate": 0.0001598628178948785,
"loss": 1.6526,
"step": 892
},
{
"epoch": 0.95,
"learning_rate": 0.0001596782328170445,
"loss": 1.4811,
"step": 894
},
{
"epoch": 0.96,
"learning_rate": 0.00015949333138878138,
"loss": 1.4048,
"step": 896
},
{
"epoch": 0.96,
"learning_rate": 0.00015930811459023957,
"loss": 1.5489,
"step": 898
},
{
"epoch": 0.96,
"learning_rate": 0.00015912258340324126,
"loss": 1.7197,
"step": 900
},
{
"epoch": 0.96,
"learning_rate": 0.00015893673881127524,
"loss": 2.1217,
"step": 902
},
{
"epoch": 0.96,
"learning_rate": 0.00015875058179949151,
"loss": 2.2086,
"step": 904
},
{
"epoch": 0.97,
"learning_rate": 0.00015856411335469638,
"loss": 2.094,
"step": 906
},
{
"epoch": 0.97,
"learning_rate": 0.00015837733446534688,
"loss": 2.3415,
"step": 908
},
{
"epoch": 0.97,
"learning_rate": 0.00015819024612154575,
"loss": 2.2378,
"step": 910
},
{
"epoch": 0.97,
"learning_rate": 0.00015800284931503618,
"loss": 2.1351,
"step": 912
},
{
"epoch": 0.97,
"learning_rate": 0.0001578151450391964,
"loss": 2.1795,
"step": 914
},
{
"epoch": 0.98,
"learning_rate": 0.00015762713428903454,
"loss": 2.0282,
"step": 916
},
{
"epoch": 0.98,
"learning_rate": 0.00015743881806118342,
"loss": 2.2858,
"step": 918
},
{
"epoch": 0.98,
"learning_rate": 0.00015725019735389503,
"loss": 2.0929,
"step": 920
},
{
"epoch": 0.98,
"learning_rate": 0.00015706127316703557,
"loss": 1.9913,
"step": 922
},
{
"epoch": 0.98,
"learning_rate": 0.0001568720465020798,
"loss": 2.0128,
"step": 924
},
{
"epoch": 0.99,
"learning_rate": 0.00015668251836210595,
"loss": 1.8792,
"step": 926
},
{
"epoch": 0.99,
"learning_rate": 0.0001564926897517904,
"loss": 1.6978,
"step": 928
},
{
"epoch": 0.99,
"learning_rate": 0.0001563025616774022,
"loss": 2.0335,
"step": 930
},
{
"epoch": 0.99,
"learning_rate": 0.0001561121351467979,
"loss": 1.845,
"step": 932
},
{
"epoch": 1.0,
"learning_rate": 0.00015592141116941628,
"loss": 1.3927,
"step": 934
},
{
"epoch": 1.0,
"learning_rate": 0.00015573039075627256,
"loss": 1.6165,
"step": 936
},
{
"epoch": 1.0,
"learning_rate": 0.00015553907491995365,
"loss": 1.6737,
"step": 938
}
],
"logging_steps": 2,
"max_steps": 2814,
"num_train_epochs": 3,
"save_steps": 500,
"total_flos": 1.51669593729024e+16,
"trial_name": null,
"trial_params": null
}