TienAnh's picture
Upload 4 files
12b8b67 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.998097567604294,
"eval_steps": 500,
"global_step": 1838,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 7.142857142857143e-07,
"loss": 2.422,
"step": 2
},
{
"epoch": 0.0,
"learning_rate": 1.4285714285714286e-06,
"loss": 2.4497,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 2.1428571428571427e-06,
"loss": 2.3952,
"step": 6
},
{
"epoch": 0.01,
"learning_rate": 2.8571428571428573e-06,
"loss": 2.4029,
"step": 8
},
{
"epoch": 0.01,
"learning_rate": 3.5714285714285718e-06,
"loss": 2.3259,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 4.2857142857142855e-06,
"loss": 2.3632,
"step": 12
},
{
"epoch": 0.02,
"learning_rate": 5e-06,
"loss": 2.2819,
"step": 14
},
{
"epoch": 0.02,
"learning_rate": 5.7142857142857145e-06,
"loss": 2.3343,
"step": 16
},
{
"epoch": 0.02,
"learning_rate": 6.4285714285714295e-06,
"loss": 2.3087,
"step": 18
},
{
"epoch": 0.02,
"learning_rate": 7.1428571428571436e-06,
"loss": 2.2965,
"step": 20
},
{
"epoch": 0.02,
"learning_rate": 7.857142857142858e-06,
"loss": 2.256,
"step": 22
},
{
"epoch": 0.03,
"learning_rate": 8.571428571428571e-06,
"loss": 2.2867,
"step": 24
},
{
"epoch": 0.03,
"learning_rate": 9.285714285714288e-06,
"loss": 2.2479,
"step": 26
},
{
"epoch": 0.03,
"learning_rate": 1e-05,
"loss": 2.3395,
"step": 28
},
{
"epoch": 0.03,
"learning_rate": 1.0714285714285714e-05,
"loss": 2.2321,
"step": 30
},
{
"epoch": 0.03,
"learning_rate": 1.1428571428571429e-05,
"loss": 2.2262,
"step": 32
},
{
"epoch": 0.04,
"learning_rate": 1.2142857142857142e-05,
"loss": 2.2642,
"step": 34
},
{
"epoch": 0.04,
"learning_rate": 1.2857142857142859e-05,
"loss": 2.2324,
"step": 36
},
{
"epoch": 0.04,
"learning_rate": 1.3571428571428574e-05,
"loss": 2.2856,
"step": 38
},
{
"epoch": 0.04,
"learning_rate": 1.4285714285714287e-05,
"loss": 2.2749,
"step": 40
},
{
"epoch": 0.05,
"learning_rate": 1.5000000000000002e-05,
"loss": 2.2005,
"step": 42
},
{
"epoch": 0.05,
"learning_rate": 1.5714285714285715e-05,
"loss": 2.1922,
"step": 44
},
{
"epoch": 0.05,
"learning_rate": 1.642857142857143e-05,
"loss": 2.2262,
"step": 46
},
{
"epoch": 0.05,
"learning_rate": 1.7142857142857142e-05,
"loss": 2.2273,
"step": 48
},
{
"epoch": 0.05,
"learning_rate": 1.785714285714286e-05,
"loss": 2.097,
"step": 50
},
{
"epoch": 0.06,
"learning_rate": 1.8571428571428575e-05,
"loss": 2.2123,
"step": 52
},
{
"epoch": 0.06,
"learning_rate": 1.928571428571429e-05,
"loss": 2.1893,
"step": 54
},
{
"epoch": 0.06,
"learning_rate": 2e-05,
"loss": 2.2119,
"step": 56
},
{
"epoch": 0.06,
"learning_rate": 1.999993783958694e-05,
"loss": 2.2133,
"step": 58
},
{
"epoch": 0.07,
"learning_rate": 1.9999751359120544e-05,
"loss": 2.1557,
"step": 60
},
{
"epoch": 0.07,
"learning_rate": 1.9999440560919153e-05,
"loss": 2.1473,
"step": 62
},
{
"epoch": 0.07,
"learning_rate": 1.999900544884663e-05,
"loss": 2.1789,
"step": 64
},
{
"epoch": 0.07,
"learning_rate": 1.9998446028312334e-05,
"loss": 2.2071,
"step": 66
},
{
"epoch": 0.07,
"learning_rate": 1.999776230627102e-05,
"loss": 2.1029,
"step": 68
},
{
"epoch": 0.08,
"learning_rate": 1.9996954291222778e-05,
"loss": 2.1411,
"step": 70
},
{
"epoch": 0.08,
"learning_rate": 1.999602199321292e-05,
"loss": 2.1792,
"step": 72
},
{
"epoch": 0.08,
"learning_rate": 1.9994965423831853e-05,
"loss": 2.1753,
"step": 74
},
{
"epoch": 0.08,
"learning_rate": 1.9993784596214932e-05,
"loss": 2.1749,
"step": 76
},
{
"epoch": 0.08,
"learning_rate": 1.9992479525042305e-05,
"loss": 2.1159,
"step": 78
},
{
"epoch": 0.09,
"learning_rate": 1.999105022653872e-05,
"loss": 2.125,
"step": 80
},
{
"epoch": 0.09,
"learning_rate": 1.998949671847334e-05,
"loss": 2.1453,
"step": 82
},
{
"epoch": 0.09,
"learning_rate": 1.9987819020159503e-05,
"loss": 2.1158,
"step": 84
},
{
"epoch": 0.09,
"learning_rate": 1.9986017152454497e-05,
"loss": 2.1194,
"step": 86
},
{
"epoch": 0.1,
"learning_rate": 1.998409113775928e-05,
"loss": 2.1211,
"step": 88
},
{
"epoch": 0.1,
"learning_rate": 1.9982041000018237e-05,
"loss": 2.1652,
"step": 90
},
{
"epoch": 0.1,
"learning_rate": 1.9979866764718846e-05,
"loss": 2.1269,
"step": 92
},
{
"epoch": 0.1,
"learning_rate": 1.9977568458891377e-05,
"loss": 2.0816,
"step": 94
},
{
"epoch": 0.1,
"learning_rate": 1.997514611110856e-05,
"loss": 2.0884,
"step": 96
},
{
"epoch": 0.11,
"learning_rate": 1.9972599751485225e-05,
"loss": 2.0982,
"step": 98
},
{
"epoch": 0.11,
"learning_rate": 1.996992941167792e-05,
"loss": 2.0934,
"step": 100
},
{
"epoch": 0.11,
"learning_rate": 1.996713512488454e-05,
"loss": 2.0704,
"step": 102
},
{
"epoch": 0.11,
"learning_rate": 1.9964216925843876e-05,
"loss": 2.1215,
"step": 104
},
{
"epoch": 0.12,
"learning_rate": 1.9961174850835224e-05,
"loss": 2.1173,
"step": 106
},
{
"epoch": 0.12,
"learning_rate": 1.995800893767792e-05,
"loss": 2.039,
"step": 108
},
{
"epoch": 0.12,
"learning_rate": 1.9954719225730847e-05,
"loss": 2.077,
"step": 110
},
{
"epoch": 0.12,
"learning_rate": 1.9951305755891982e-05,
"loss": 2.0687,
"step": 112
},
{
"epoch": 0.12,
"learning_rate": 1.9947768570597865e-05,
"loss": 2.0389,
"step": 114
},
{
"epoch": 0.13,
"learning_rate": 1.9944107713823068e-05,
"loss": 2.0584,
"step": 116
},
{
"epoch": 0.13,
"learning_rate": 1.9940323231079674e-05,
"loss": 2.0666,
"step": 118
},
{
"epoch": 0.13,
"learning_rate": 1.993641516941668e-05,
"loss": 2.0508,
"step": 120
},
{
"epoch": 0.13,
"learning_rate": 1.9932383577419432e-05,
"loss": 2.129,
"step": 122
},
{
"epoch": 0.13,
"learning_rate": 1.9928228505209017e-05,
"loss": 2.0056,
"step": 124
},
{
"epoch": 0.14,
"learning_rate": 1.992395000444163e-05,
"loss": 2.0473,
"step": 126
},
{
"epoch": 0.14,
"learning_rate": 1.9919548128307954e-05,
"loss": 1.9965,
"step": 128
},
{
"epoch": 0.14,
"learning_rate": 1.991502293153247e-05,
"loss": 2.0373,
"step": 130
},
{
"epoch": 0.14,
"learning_rate": 1.9910374470372805e-05,
"loss": 2.0406,
"step": 132
},
{
"epoch": 0.15,
"learning_rate": 1.990560280261901e-05,
"loss": 2.0437,
"step": 134
},
{
"epoch": 0.15,
"learning_rate": 1.9900707987592847e-05,
"loss": 2.0367,
"step": 136
},
{
"epoch": 0.15,
"learning_rate": 1.9895690086147065e-05,
"loss": 1.9801,
"step": 138
},
{
"epoch": 0.15,
"learning_rate": 1.9890549160664633e-05,
"loss": 2.0334,
"step": 140
},
{
"epoch": 0.15,
"learning_rate": 1.9885285275057954e-05,
"loss": 1.9997,
"step": 142
},
{
"epoch": 0.16,
"learning_rate": 1.9879898494768093e-05,
"loss": 2.0198,
"step": 144
},
{
"epoch": 0.16,
"learning_rate": 1.9874388886763944e-05,
"loss": 2.0302,
"step": 146
},
{
"epoch": 0.16,
"learning_rate": 1.9868756519541416e-05,
"loss": 2.0155,
"step": 148
},
{
"epoch": 0.16,
"learning_rate": 1.9863001463122557e-05,
"loss": 1.9745,
"step": 150
},
{
"epoch": 0.17,
"learning_rate": 1.9857123789054707e-05,
"loss": 2.0129,
"step": 152
},
{
"epoch": 0.17,
"learning_rate": 1.9851123570409595e-05,
"loss": 2.0115,
"step": 154
},
{
"epoch": 0.17,
"learning_rate": 1.9845000881782434e-05,
"loss": 1.9893,
"step": 156
},
{
"epoch": 0.17,
"learning_rate": 1.9838755799290993e-05,
"loss": 1.954,
"step": 158
},
{
"epoch": 0.17,
"learning_rate": 1.9832388400574658e-05,
"loss": 2.0076,
"step": 160
},
{
"epoch": 0.18,
"learning_rate": 1.9825898764793455e-05,
"loss": 1.9959,
"step": 162
},
{
"epoch": 0.18,
"learning_rate": 1.9819286972627066e-05,
"loss": 1.9442,
"step": 164
},
{
"epoch": 0.18,
"learning_rate": 1.9812553106273848e-05,
"loss": 2.0281,
"step": 166
},
{
"epoch": 0.18,
"learning_rate": 1.9805697249449774e-05,
"loss": 1.9917,
"step": 168
},
{
"epoch": 0.18,
"learning_rate": 1.979871948738743e-05,
"loss": 1.9503,
"step": 170
},
{
"epoch": 0.19,
"learning_rate": 1.9791619906834928e-05,
"loss": 2.0444,
"step": 172
},
{
"epoch": 0.19,
"learning_rate": 1.9784398596054833e-05,
"loss": 1.9531,
"step": 174
},
{
"epoch": 0.19,
"learning_rate": 1.9777055644823087e-05,
"loss": 1.9387,
"step": 176
},
{
"epoch": 0.19,
"learning_rate": 1.976959114442786e-05,
"loss": 1.9421,
"step": 178
},
{
"epoch": 0.2,
"learning_rate": 1.9762005187668442e-05,
"loss": 2.0183,
"step": 180
},
{
"epoch": 0.2,
"learning_rate": 1.9754297868854075e-05,
"loss": 1.9711,
"step": 182
},
{
"epoch": 0.2,
"learning_rate": 1.9746469283802773e-05,
"loss": 1.9696,
"step": 184
},
{
"epoch": 0.2,
"learning_rate": 1.9738519529840162e-05,
"loss": 1.9482,
"step": 186
},
{
"epoch": 0.2,
"learning_rate": 1.973044870579824e-05,
"loss": 1.9837,
"step": 188
},
{
"epoch": 0.21,
"learning_rate": 1.9722256912014153e-05,
"loss": 1.9391,
"step": 190
},
{
"epoch": 0.21,
"learning_rate": 1.971394425032896e-05,
"loss": 1.9329,
"step": 192
},
{
"epoch": 0.21,
"learning_rate": 1.970551082408636e-05,
"loss": 1.9301,
"step": 194
},
{
"epoch": 0.21,
"learning_rate": 1.9696956738131406e-05,
"loss": 1.9736,
"step": 196
},
{
"epoch": 0.22,
"learning_rate": 1.9688282098809195e-05,
"loss": 1.95,
"step": 198
},
{
"epoch": 0.22,
"learning_rate": 1.9679487013963566e-05,
"loss": 1.9916,
"step": 200
},
{
"epoch": 0.22,
"learning_rate": 1.9670571592935733e-05,
"loss": 1.9198,
"step": 202
},
{
"epoch": 0.22,
"learning_rate": 1.9661535946562954e-05,
"loss": 1.9665,
"step": 204
},
{
"epoch": 0.22,
"learning_rate": 1.9652380187177128e-05,
"loss": 1.9197,
"step": 206
},
{
"epoch": 0.23,
"learning_rate": 1.964310442860341e-05,
"loss": 1.9704,
"step": 208
},
{
"epoch": 0.23,
"learning_rate": 1.9633708786158803e-05,
"loss": 1.9304,
"step": 210
},
{
"epoch": 0.23,
"learning_rate": 1.9624193376650708e-05,
"loss": 1.958,
"step": 212
},
{
"epoch": 0.23,
"learning_rate": 1.961455831837548e-05,
"loss": 1.893,
"step": 214
},
{
"epoch": 0.23,
"learning_rate": 1.9604803731116953e-05,
"loss": 1.9692,
"step": 216
},
{
"epoch": 0.24,
"learning_rate": 1.9594929736144978e-05,
"loss": 1.9248,
"step": 218
},
{
"epoch": 0.24,
"learning_rate": 1.958493645621386e-05,
"loss": 1.9701,
"step": 220
},
{
"epoch": 0.24,
"learning_rate": 1.957482401556089e-05,
"loss": 1.932,
"step": 222
},
{
"epoch": 0.24,
"learning_rate": 1.956459253990476e-05,
"loss": 1.9386,
"step": 224
},
{
"epoch": 0.25,
"learning_rate": 1.955424215644403e-05,
"loss": 1.8804,
"step": 226
},
{
"epoch": 0.25,
"learning_rate": 1.954377299385551e-05,
"loss": 1.9025,
"step": 228
},
{
"epoch": 0.25,
"learning_rate": 1.9533185182292705e-05,
"loss": 1.8824,
"step": 230
},
{
"epoch": 0.25,
"learning_rate": 1.9522478853384154e-05,
"loss": 1.9541,
"step": 232
},
{
"epoch": 0.25,
"learning_rate": 1.951165414023183e-05,
"loss": 1.9414,
"step": 234
},
{
"epoch": 0.26,
"learning_rate": 1.9500711177409456e-05,
"loss": 1.8997,
"step": 236
},
{
"epoch": 0.26,
"learning_rate": 1.948965010096085e-05,
"loss": 1.9041,
"step": 238
},
{
"epoch": 0.26,
"learning_rate": 1.9478471048398233e-05,
"loss": 1.8728,
"step": 240
},
{
"epoch": 0.26,
"learning_rate": 1.9467174158700507e-05,
"loss": 1.9314,
"step": 242
},
{
"epoch": 0.27,
"learning_rate": 1.9455759572311535e-05,
"loss": 1.8404,
"step": 244
},
{
"epoch": 0.27,
"learning_rate": 1.94442274311384e-05,
"loss": 1.8847,
"step": 246
},
{
"epoch": 0.27,
"learning_rate": 1.9432577878549635e-05,
"loss": 1.939,
"step": 248
},
{
"epoch": 0.27,
"learning_rate": 1.9420811059373444e-05,
"loss": 1.8801,
"step": 250
},
{
"epoch": 0.27,
"learning_rate": 1.9408927119895888e-05,
"loss": 1.9351,
"step": 252
},
{
"epoch": 0.28,
"learning_rate": 1.9396926207859085e-05,
"loss": 1.9459,
"step": 254
},
{
"epoch": 0.28,
"learning_rate": 1.938480847245937e-05,
"loss": 1.9396,
"step": 256
},
{
"epoch": 0.28,
"learning_rate": 1.9372574064345424e-05,
"loss": 1.8986,
"step": 258
},
{
"epoch": 0.28,
"learning_rate": 1.9360223135616423e-05,
"loss": 1.8859,
"step": 260
},
{
"epoch": 0.28,
"learning_rate": 1.9347755839820138e-05,
"loss": 1.9002,
"step": 262
},
{
"epoch": 0.29,
"learning_rate": 1.9335172331951014e-05,
"loss": 1.9257,
"step": 264
},
{
"epoch": 0.29,
"learning_rate": 1.932247276844826e-05,
"loss": 1.9266,
"step": 266
},
{
"epoch": 0.29,
"learning_rate": 1.93096573071939e-05,
"loss": 1.9285,
"step": 268
},
{
"epoch": 0.29,
"learning_rate": 1.929672610751081e-05,
"loss": 1.8927,
"step": 270
},
{
"epoch": 0.3,
"learning_rate": 1.9283679330160726e-05,
"loss": 1.8301,
"step": 272
},
{
"epoch": 0.3,
"learning_rate": 1.927051713734227e-05,
"loss": 1.8755,
"step": 274
},
{
"epoch": 0.3,
"learning_rate": 1.9257239692688907e-05,
"loss": 1.848,
"step": 276
},
{
"epoch": 0.3,
"learning_rate": 1.9243847161266924e-05,
"loss": 1.8943,
"step": 278
},
{
"epoch": 0.3,
"learning_rate": 1.9230339709573376e-05,
"loss": 1.9041,
"step": 280
},
{
"epoch": 0.31,
"learning_rate": 1.9216717505534025e-05,
"loss": 1.8478,
"step": 282
},
{
"epoch": 0.31,
"learning_rate": 1.920298071850123e-05,
"loss": 1.8383,
"step": 284
},
{
"epoch": 0.31,
"learning_rate": 1.9189129519251873e-05,
"loss": 1.9098,
"step": 286
},
{
"epoch": 0.31,
"learning_rate": 1.9175164079985196e-05,
"loss": 1.8996,
"step": 288
},
{
"epoch": 0.32,
"learning_rate": 1.9161084574320696e-05,
"loss": 1.9136,
"step": 290
},
{
"epoch": 0.32,
"learning_rate": 1.9146891177295956e-05,
"loss": 1.8666,
"step": 292
},
{
"epoch": 0.32,
"learning_rate": 1.9132584065364455e-05,
"loss": 1.8936,
"step": 294
},
{
"epoch": 0.32,
"learning_rate": 1.9118163416393392e-05,
"loss": 1.8678,
"step": 296
},
{
"epoch": 0.32,
"learning_rate": 1.9103629409661468e-05,
"loss": 1.8798,
"step": 298
},
{
"epoch": 0.33,
"learning_rate": 1.9088982225856653e-05,
"loss": 1.8753,
"step": 300
},
{
"epoch": 0.33,
"learning_rate": 1.9074222047073945e-05,
"loss": 1.8768,
"step": 302
},
{
"epoch": 0.33,
"learning_rate": 1.905934905681311e-05,
"loss": 1.8844,
"step": 304
},
{
"epoch": 0.33,
"learning_rate": 1.9044363439976393e-05,
"loss": 1.8549,
"step": 306
},
{
"epoch": 0.33,
"learning_rate": 1.9029265382866216e-05,
"loss": 1.8632,
"step": 308
},
{
"epoch": 0.34,
"learning_rate": 1.9014055073182872e-05,
"loss": 1.9043,
"step": 310
},
{
"epoch": 0.34,
"learning_rate": 1.8998732700022186e-05,
"loss": 1.9065,
"step": 312
},
{
"epoch": 0.34,
"learning_rate": 1.8983298453873172e-05,
"loss": 1.8886,
"step": 314
},
{
"epoch": 0.34,
"learning_rate": 1.896775252661565e-05,
"loss": 1.8515,
"step": 316
},
{
"epoch": 0.35,
"learning_rate": 1.8952095111517875e-05,
"loss": 1.8296,
"step": 318
},
{
"epoch": 0.35,
"learning_rate": 1.8936326403234125e-05,
"loss": 1.8673,
"step": 320
},
{
"epoch": 0.35,
"learning_rate": 1.8920446597802276e-05,
"loss": 1.9119,
"step": 322
},
{
"epoch": 0.35,
"learning_rate": 1.8904455892641394e-05,
"loss": 1.8574,
"step": 324
},
{
"epoch": 0.35,
"learning_rate": 1.8888354486549238e-05,
"loss": 1.8388,
"step": 326
},
{
"epoch": 0.36,
"learning_rate": 1.8872142579699818e-05,
"loss": 1.8829,
"step": 328
},
{
"epoch": 0.36,
"learning_rate": 1.88558203736409e-05,
"loss": 1.8707,
"step": 330
},
{
"epoch": 0.36,
"learning_rate": 1.8839388071291506e-05,
"loss": 1.8343,
"step": 332
},
{
"epoch": 0.36,
"learning_rate": 1.8822845876939365e-05,
"loss": 1.8576,
"step": 334
},
{
"epoch": 0.37,
"learning_rate": 1.880619399623841e-05,
"loss": 1.8613,
"step": 336
},
{
"epoch": 0.37,
"learning_rate": 1.8789432636206197e-05,
"loss": 1.7953,
"step": 338
},
{
"epoch": 0.37,
"learning_rate": 1.8772562005221338e-05,
"loss": 1.87,
"step": 340
},
{
"epoch": 0.37,
"learning_rate": 1.8755582313020912e-05,
"loss": 1.8275,
"step": 342
},
{
"epoch": 0.37,
"learning_rate": 1.873849377069785e-05,
"loss": 1.8532,
"step": 344
},
{
"epoch": 0.38,
"learning_rate": 1.872129659069833e-05,
"loss": 1.8742,
"step": 346
},
{
"epoch": 0.38,
"learning_rate": 1.870399098681911e-05,
"loss": 1.8423,
"step": 348
},
{
"epoch": 0.38,
"learning_rate": 1.8686577174204887e-05,
"loss": 1.8021,
"step": 350
},
{
"epoch": 0.38,
"learning_rate": 1.8669055369345617e-05,
"loss": 1.8343,
"step": 352
},
{
"epoch": 0.38,
"learning_rate": 1.865142579007383e-05,
"loss": 1.8753,
"step": 354
},
{
"epoch": 0.39,
"learning_rate": 1.863368865556191e-05,
"loss": 1.8335,
"step": 356
},
{
"epoch": 0.39,
"learning_rate": 1.8615844186319377e-05,
"loss": 1.8022,
"step": 358
},
{
"epoch": 0.39,
"learning_rate": 1.8597892604190148e-05,
"loss": 1.8993,
"step": 360
},
{
"epoch": 0.39,
"learning_rate": 1.8579834132349773e-05,
"loss": 1.8056,
"step": 362
},
{
"epoch": 0.4,
"learning_rate": 1.8561668995302668e-05,
"loss": 1.8487,
"step": 364
},
{
"epoch": 0.4,
"learning_rate": 1.8543397418879315e-05,
"loss": 1.8424,
"step": 366
},
{
"epoch": 0.4,
"learning_rate": 1.8525019630233463e-05,
"loss": 1.8354,
"step": 368
},
{
"epoch": 0.4,
"learning_rate": 1.8506535857839304e-05,
"loss": 1.8145,
"step": 370
},
{
"epoch": 0.4,
"learning_rate": 1.8487946331488613e-05,
"loss": 1.7753,
"step": 372
},
{
"epoch": 0.41,
"learning_rate": 1.8469251282287925e-05,
"loss": 1.8,
"step": 374
},
{
"epoch": 0.41,
"learning_rate": 1.845045094265563e-05,
"loss": 1.787,
"step": 376
},
{
"epoch": 0.41,
"learning_rate": 1.843154554631911e-05,
"loss": 1.809,
"step": 378
},
{
"epoch": 0.41,
"learning_rate": 1.8412535328311813e-05,
"loss": 1.8421,
"step": 380
},
{
"epoch": 0.42,
"learning_rate": 1.8393420524970337e-05,
"loss": 1.8344,
"step": 382
},
{
"epoch": 0.42,
"learning_rate": 1.8374201373931497e-05,
"loss": 1.7844,
"step": 384
},
{
"epoch": 0.42,
"learning_rate": 1.8354878114129368e-05,
"loss": 1.8122,
"step": 386
},
{
"epoch": 0.42,
"learning_rate": 1.8335450985792307e-05,
"loss": 1.8689,
"step": 388
},
{
"epoch": 0.42,
"learning_rate": 1.8315920230439985e-05,
"loss": 1.802,
"step": 390
},
{
"epoch": 0.43,
"learning_rate": 1.8296286090880362e-05,
"loss": 1.8247,
"step": 392
},
{
"epoch": 0.43,
"learning_rate": 1.8276548811206684e-05,
"loss": 1.8199,
"step": 394
},
{
"epoch": 0.43,
"learning_rate": 1.8256708636794446e-05,
"loss": 1.8626,
"step": 396
},
{
"epoch": 0.43,
"learning_rate": 1.8236765814298328e-05,
"loss": 1.8371,
"step": 398
},
{
"epoch": 0.43,
"learning_rate": 1.8216720591649152e-05,
"loss": 1.7781,
"step": 400
},
{
"epoch": 0.44,
"learning_rate": 1.8196573218050784e-05,
"loss": 1.8401,
"step": 402
},
{
"epoch": 0.44,
"learning_rate": 1.8176323943977034e-05,
"loss": 1.8454,
"step": 404
},
{
"epoch": 0.44,
"learning_rate": 1.8155973021168546e-05,
"loss": 1.8241,
"step": 406
},
{
"epoch": 0.44,
"learning_rate": 1.8135520702629677e-05,
"loss": 1.8396,
"step": 408
},
{
"epoch": 0.45,
"learning_rate": 1.8114967242625342e-05,
"loss": 1.7954,
"step": 410
},
{
"epoch": 0.45,
"learning_rate": 1.8094312896677853e-05,
"loss": 1.8167,
"step": 412
},
{
"epoch": 0.45,
"learning_rate": 1.8073557921563747e-05,
"loss": 1.7939,
"step": 414
},
{
"epoch": 0.45,
"learning_rate": 1.8052702575310588e-05,
"loss": 1.7459,
"step": 416
},
{
"epoch": 0.45,
"learning_rate": 1.803174711719376e-05,
"loss": 1.7744,
"step": 418
},
{
"epoch": 0.46,
"learning_rate": 1.8010691807733253e-05,
"loss": 1.7739,
"step": 420
},
{
"epoch": 0.46,
"learning_rate": 1.7989536908690413e-05,
"loss": 1.8295,
"step": 422
},
{
"epoch": 0.46,
"learning_rate": 1.796828268306469e-05,
"loss": 1.8341,
"step": 424
},
{
"epoch": 0.46,
"learning_rate": 1.7946929395090382e-05,
"loss": 1.7919,
"step": 426
},
{
"epoch": 0.47,
"learning_rate": 1.792547731023332e-05,
"loss": 1.8405,
"step": 428
},
{
"epoch": 0.47,
"learning_rate": 1.7903926695187595e-05,
"loss": 1.7965,
"step": 430
},
{
"epoch": 0.47,
"learning_rate": 1.7882277817872236e-05,
"loss": 1.8004,
"step": 432
},
{
"epoch": 0.47,
"learning_rate": 1.7860530947427878e-05,
"loss": 1.7944,
"step": 434
},
{
"epoch": 0.47,
"learning_rate": 1.78386863542134e-05,
"loss": 1.8024,
"step": 436
},
{
"epoch": 0.48,
"learning_rate": 1.7816744309802604e-05,
"loss": 1.7964,
"step": 438
},
{
"epoch": 0.48,
"learning_rate": 1.779470508698079e-05,
"loss": 1.8238,
"step": 440
},
{
"epoch": 0.48,
"learning_rate": 1.77725689597414e-05,
"loss": 1.8253,
"step": 442
},
{
"epoch": 0.48,
"learning_rate": 1.7750336203282588e-05,
"loss": 1.7792,
"step": 444
},
{
"epoch": 0.48,
"learning_rate": 1.772800709400383e-05,
"loss": 1.767,
"step": 446
},
{
"epoch": 0.49,
"learning_rate": 1.7705581909502457e-05,
"loss": 1.8158,
"step": 448
},
{
"epoch": 0.49,
"learning_rate": 1.768306092857021e-05,
"loss": 1.8087,
"step": 450
},
{
"epoch": 0.49,
"learning_rate": 1.766044443118978e-05,
"loss": 1.7894,
"step": 452
},
{
"epoch": 0.49,
"learning_rate": 1.763773269853134e-05,
"loss": 1.7663,
"step": 454
},
{
"epoch": 0.5,
"learning_rate": 1.7614926012949027e-05,
"loss": 1.793,
"step": 456
},
{
"epoch": 0.5,
"learning_rate": 1.7592024657977432e-05,
"loss": 1.8305,
"step": 458
},
{
"epoch": 0.5,
"learning_rate": 1.75690289183281e-05,
"loss": 1.8158,
"step": 460
},
{
"epoch": 0.5,
"learning_rate": 1.7545939079885962e-05,
"loss": 1.7655,
"step": 462
},
{
"epoch": 0.5,
"learning_rate": 1.75227554297058e-05,
"loss": 1.7749,
"step": 464
},
{
"epoch": 0.51,
"learning_rate": 1.7499478256008658e-05,
"loss": 1.7694,
"step": 466
},
{
"epoch": 0.51,
"learning_rate": 1.7476107848178298e-05,
"loss": 1.775,
"step": 468
},
{
"epoch": 0.51,
"learning_rate": 1.745264449675755e-05,
"loss": 1.7868,
"step": 470
},
{
"epoch": 0.51,
"learning_rate": 1.7429088493444738e-05,
"loss": 1.7893,
"step": 472
},
{
"epoch": 0.52,
"learning_rate": 1.740544013109005e-05,
"loss": 1.7614,
"step": 474
},
{
"epoch": 0.52,
"learning_rate": 1.7381699703691866e-05,
"loss": 1.7538,
"step": 476
},
{
"epoch": 0.52,
"learning_rate": 1.7357867506393154e-05,
"loss": 1.7761,
"step": 478
},
{
"epoch": 0.52,
"learning_rate": 1.7333943835477752e-05,
"loss": 1.7411,
"step": 480
},
{
"epoch": 0.52,
"learning_rate": 1.730992898836672e-05,
"loss": 1.7823,
"step": 482
},
{
"epoch": 0.53,
"learning_rate": 1.7285823263614613e-05,
"loss": 1.8391,
"step": 484
},
{
"epoch": 0.53,
"learning_rate": 1.7261626960905795e-05,
"loss": 1.8099,
"step": 486
},
{
"epoch": 0.53,
"learning_rate": 1.72373403810507e-05,
"loss": 1.7953,
"step": 488
},
{
"epoch": 0.53,
"learning_rate": 1.7212963825982103e-05,
"loss": 1.7979,
"step": 490
},
{
"epoch": 0.53,
"learning_rate": 1.7188497598751343e-05,
"loss": 1.8395,
"step": 492
},
{
"epoch": 0.54,
"learning_rate": 1.7163942003524574e-05,
"loss": 1.7335,
"step": 494
},
{
"epoch": 0.54,
"learning_rate": 1.7139297345578992e-05,
"loss": 1.7415,
"step": 496
},
{
"epoch": 0.54,
"learning_rate": 1.7114563931299016e-05,
"loss": 1.7761,
"step": 498
},
{
"epoch": 0.54,
"learning_rate": 1.70897420681725e-05,
"loss": 1.8035,
"step": 500
},
{
"epoch": 0.55,
"learning_rate": 1.7064832064786894e-05,
"loss": 1.7779,
"step": 502
},
{
"epoch": 0.55,
"learning_rate": 1.703983423082542e-05,
"loss": 1.7921,
"step": 504
},
{
"epoch": 0.55,
"learning_rate": 1.7014748877063212e-05,
"loss": 1.7611,
"step": 506
},
{
"epoch": 0.55,
"learning_rate": 1.6989576315363467e-05,
"loss": 1.763,
"step": 508
},
{
"epoch": 0.55,
"learning_rate": 1.6964316858673538e-05,
"loss": 1.8226,
"step": 510
},
{
"epoch": 0.56,
"learning_rate": 1.693897082102109e-05,
"loss": 1.7751,
"step": 512
},
{
"epoch": 0.56,
"learning_rate": 1.6913538517510155e-05,
"loss": 1.7234,
"step": 514
},
{
"epoch": 0.56,
"learning_rate": 1.6888020264317227e-05,
"loss": 1.7529,
"step": 516
},
{
"epoch": 0.56,
"learning_rate": 1.686241637868734e-05,
"loss": 1.7853,
"step": 518
},
{
"epoch": 0.57,
"learning_rate": 1.683672717893011e-05,
"loss": 1.7837,
"step": 520
},
{
"epoch": 0.57,
"learning_rate": 1.6810952984415804e-05,
"loss": 1.7382,
"step": 522
},
{
"epoch": 0.57,
"learning_rate": 1.6785094115571323e-05,
"loss": 1.7846,
"step": 524
},
{
"epoch": 0.57,
"learning_rate": 1.6759150893876272e-05,
"loss": 1.7314,
"step": 526
},
{
"epoch": 0.57,
"learning_rate": 1.6733123641858915e-05,
"loss": 1.7938,
"step": 528
},
{
"epoch": 0.58,
"learning_rate": 1.670701268309221e-05,
"loss": 1.8066,
"step": 530
},
{
"epoch": 0.58,
"learning_rate": 1.6680818342189748e-05,
"loss": 1.7837,
"step": 532
},
{
"epoch": 0.58,
"learning_rate": 1.665454094480174e-05,
"loss": 1.7621,
"step": 534
},
{
"epoch": 0.58,
"learning_rate": 1.6628180817610963e-05,
"loss": 1.6982,
"step": 536
},
{
"epoch": 0.58,
"learning_rate": 1.6601738288328692e-05,
"loss": 1.7988,
"step": 538
},
{
"epoch": 0.59,
"learning_rate": 1.657521368569064e-05,
"loss": 1.7403,
"step": 540
},
{
"epoch": 0.59,
"learning_rate": 1.6548607339452853e-05,
"loss": 1.7521,
"step": 542
},
{
"epoch": 0.59,
"learning_rate": 1.652191958038763e-05,
"loss": 1.7478,
"step": 544
},
{
"epoch": 0.59,
"learning_rate": 1.649515074027939e-05,
"loss": 1.806,
"step": 546
},
{
"epoch": 0.6,
"learning_rate": 1.6468301151920576e-05,
"loss": 1.7771,
"step": 548
},
{
"epoch": 0.6,
"learning_rate": 1.6441371149107478e-05,
"loss": 1.7893,
"step": 550
},
{
"epoch": 0.6,
"learning_rate": 1.6414361066636123e-05,
"loss": 1.7405,
"step": 552
},
{
"epoch": 0.6,
"learning_rate": 1.6387271240298082e-05,
"loss": 1.7464,
"step": 554
},
{
"epoch": 0.6,
"learning_rate": 1.6360102006876317e-05,
"loss": 1.741,
"step": 556
},
{
"epoch": 0.61,
"learning_rate": 1.633285370414098e-05,
"loss": 1.7354,
"step": 558
},
{
"epoch": 0.61,
"learning_rate": 1.6305526670845225e-05,
"loss": 1.7579,
"step": 560
},
{
"epoch": 0.61,
"learning_rate": 1.627812124672099e-05,
"loss": 1.7034,
"step": 562
},
{
"epoch": 0.61,
"learning_rate": 1.6250637772474764e-05,
"loss": 1.7857,
"step": 564
},
{
"epoch": 0.62,
"learning_rate": 1.6223076589783368e-05,
"loss": 1.8225,
"step": 566
},
{
"epoch": 0.62,
"learning_rate": 1.619543804128971e-05,
"loss": 1.7726,
"step": 568
},
{
"epoch": 0.62,
"learning_rate": 1.6167722470598506e-05,
"loss": 1.7834,
"step": 570
},
{
"epoch": 0.62,
"learning_rate": 1.613993022227202e-05,
"loss": 1.7551,
"step": 572
},
{
"epoch": 0.62,
"learning_rate": 1.611206164182578e-05,
"loss": 1.7747,
"step": 574
},
{
"epoch": 0.63,
"learning_rate": 1.608411707572428e-05,
"loss": 1.731,
"step": 576
},
{
"epoch": 0.63,
"learning_rate": 1.6056096871376667e-05,
"loss": 1.7758,
"step": 578
},
{
"epoch": 0.63,
"learning_rate": 1.6028001377132447e-05,
"loss": 1.7286,
"step": 580
},
{
"epoch": 0.63,
"learning_rate": 1.5999830942277124e-05,
"loss": 1.8262,
"step": 582
},
{
"epoch": 0.63,
"learning_rate": 1.5971585917027864e-05,
"loss": 1.6955,
"step": 584
},
{
"epoch": 0.64,
"learning_rate": 1.5943266652529162e-05,
"loss": 1.7457,
"step": 586
},
{
"epoch": 0.64,
"learning_rate": 1.5914873500848446e-05,
"loss": 1.7036,
"step": 588
},
{
"epoch": 0.64,
"learning_rate": 1.5886406814971728e-05,
"loss": 1.741,
"step": 590
},
{
"epoch": 0.64,
"learning_rate": 1.5857866948799202e-05,
"loss": 1.713,
"step": 592
},
{
"epoch": 0.65,
"learning_rate": 1.582925425714084e-05,
"loss": 1.7516,
"step": 594
},
{
"epoch": 0.65,
"learning_rate": 1.5800569095711983e-05,
"loss": 1.7651,
"step": 596
},
{
"epoch": 0.65,
"learning_rate": 1.5771811821128932e-05,
"loss": 1.7862,
"step": 598
},
{
"epoch": 0.65,
"learning_rate": 1.57429827909045e-05,
"loss": 1.7699,
"step": 600
},
{
"epoch": 0.65,
"learning_rate": 1.5714082363443576e-05,
"loss": 1.7597,
"step": 602
},
{
"epoch": 0.66,
"learning_rate": 1.5685110898038653e-05,
"loss": 1.7237,
"step": 604
},
{
"epoch": 0.66,
"learning_rate": 1.5656068754865388e-05,
"loss": 1.7492,
"step": 606
},
{
"epoch": 0.66,
"learning_rate": 1.5626956294978103e-05,
"loss": 1.7847,
"step": 608
},
{
"epoch": 0.66,
"learning_rate": 1.5597773880305307e-05,
"loss": 1.7614,
"step": 610
},
{
"epoch": 0.67,
"learning_rate": 1.5568521873645183e-05,
"loss": 1.7552,
"step": 612
},
{
"epoch": 0.67,
"learning_rate": 1.5539200638661106e-05,
"loss": 1.7548,
"step": 614
},
{
"epoch": 0.67,
"learning_rate": 1.550981053987708e-05,
"loss": 1.7262,
"step": 616
},
{
"epoch": 0.67,
"learning_rate": 1.5480351942673248e-05,
"loss": 1.7185,
"step": 618
},
{
"epoch": 0.67,
"learning_rate": 1.5450825213281317e-05,
"loss": 1.7144,
"step": 620
},
{
"epoch": 0.68,
"learning_rate": 1.5421230718780036e-05,
"loss": 1.7541,
"step": 622
},
{
"epoch": 0.68,
"learning_rate": 1.53915688270906e-05,
"loss": 1.7444,
"step": 624
},
{
"epoch": 0.68,
"learning_rate": 1.5361839906972095e-05,
"loss": 1.7496,
"step": 626
},
{
"epoch": 0.68,
"learning_rate": 1.5332044328016916e-05,
"loss": 1.736,
"step": 628
},
{
"epoch": 0.68,
"learning_rate": 1.5302182460646158e-05,
"loss": 1.767,
"step": 630
},
{
"epoch": 0.69,
"learning_rate": 1.5272254676105026e-05,
"loss": 1.7799,
"step": 632
},
{
"epoch": 0.69,
"learning_rate": 1.524226134645821e-05,
"loss": 1.7511,
"step": 634
},
{
"epoch": 0.69,
"learning_rate": 1.5212202844585258e-05,
"loss": 1.7502,
"step": 636
},
{
"epoch": 0.69,
"learning_rate": 1.5182079544175957e-05,
"loss": 1.7569,
"step": 638
},
{
"epoch": 0.7,
"learning_rate": 1.5151891819725657e-05,
"loss": 1.7103,
"step": 640
},
{
"epoch": 0.7,
"learning_rate": 1.5121640046530651e-05,
"loss": 1.7018,
"step": 642
},
{
"epoch": 0.7,
"learning_rate": 1.5091324600683472e-05,
"loss": 1.7335,
"step": 644
},
{
"epoch": 0.7,
"learning_rate": 1.5060945859068252e-05,
"loss": 1.8015,
"step": 646
},
{
"epoch": 0.7,
"learning_rate": 1.5030504199356022e-05,
"loss": 1.7309,
"step": 648
},
{
"epoch": 0.71,
"learning_rate": 1.5000000000000002e-05,
"loss": 1.6938,
"step": 650
},
{
"epoch": 0.71,
"learning_rate": 1.4969433640230922e-05,
"loss": 1.7381,
"step": 652
},
{
"epoch": 0.71,
"learning_rate": 1.4938805500052294e-05,
"loss": 1.7376,
"step": 654
},
{
"epoch": 0.71,
"learning_rate": 1.4908115960235683e-05,
"loss": 1.7744,
"step": 656
},
{
"epoch": 0.72,
"learning_rate": 1.4877365402315986e-05,
"loss": 1.7562,
"step": 658
},
{
"epoch": 0.72,
"learning_rate": 1.4846554208586676e-05,
"loss": 1.7368,
"step": 660
},
{
"epoch": 0.72,
"learning_rate": 1.4815682762095065e-05,
"loss": 1.7065,
"step": 662
},
{
"epoch": 0.72,
"learning_rate": 1.4784751446637522e-05,
"loss": 1.7647,
"step": 664
},
{
"epoch": 0.72,
"learning_rate": 1.4753760646754714e-05,
"loss": 1.7098,
"step": 666
},
{
"epoch": 0.73,
"learning_rate": 1.472271074772683e-05,
"loss": 1.6901,
"step": 668
},
{
"epoch": 0.73,
"learning_rate": 1.4691602135568776e-05,
"loss": 1.7465,
"step": 670
},
{
"epoch": 0.73,
"learning_rate": 1.4660435197025391e-05,
"loss": 1.7038,
"step": 672
},
{
"epoch": 0.73,
"learning_rate": 1.4629210319566626e-05,
"loss": 1.7026,
"step": 674
},
{
"epoch": 0.73,
"learning_rate": 1.4597927891382742e-05,
"loss": 1.7556,
"step": 676
},
{
"epoch": 0.74,
"learning_rate": 1.456658830137947e-05,
"loss": 1.7338,
"step": 678
},
{
"epoch": 0.74,
"learning_rate": 1.4535191939173179e-05,
"loss": 1.698,
"step": 680
},
{
"epoch": 0.74,
"learning_rate": 1.4503739195086038e-05,
"loss": 1.7293,
"step": 682
},
{
"epoch": 0.74,
"learning_rate": 1.4472230460141159e-05,
"loss": 1.6856,
"step": 684
},
{
"epoch": 0.75,
"learning_rate": 1.4440666126057743e-05,
"loss": 1.7491,
"step": 686
},
{
"epoch": 0.75,
"learning_rate": 1.4409046585246193e-05,
"loss": 1.7427,
"step": 688
},
{
"epoch": 0.75,
"learning_rate": 1.4377372230803257e-05,
"loss": 1.7147,
"step": 690
},
{
"epoch": 0.75,
"learning_rate": 1.4345643456507126e-05,
"loss": 1.697,
"step": 692
},
{
"epoch": 0.75,
"learning_rate": 1.4313860656812537e-05,
"loss": 1.7302,
"step": 694
},
{
"epoch": 0.76,
"learning_rate": 1.4282024226845885e-05,
"loss": 1.7183,
"step": 696
},
{
"epoch": 0.76,
"learning_rate": 1.4250134562400301e-05,
"loss": 1.7126,
"step": 698
},
{
"epoch": 0.76,
"learning_rate": 1.4218192059930724e-05,
"loss": 1.7619,
"step": 700
},
{
"epoch": 0.76,
"learning_rate": 1.4186197116548987e-05,
"loss": 1.6905,
"step": 702
},
{
"epoch": 0.77,
"learning_rate": 1.4154150130018867e-05,
"loss": 1.6881,
"step": 704
},
{
"epoch": 0.77,
"learning_rate": 1.4122051498751144e-05,
"loss": 1.6719,
"step": 706
},
{
"epoch": 0.77,
"learning_rate": 1.4089901621798663e-05,
"loss": 1.738,
"step": 708
},
{
"epoch": 0.77,
"learning_rate": 1.405770089885134e-05,
"loss": 1.7501,
"step": 710
},
{
"epoch": 0.77,
"learning_rate": 1.402544973023123e-05,
"loss": 1.744,
"step": 712
},
{
"epoch": 0.78,
"learning_rate": 1.3993148516887522e-05,
"loss": 1.7005,
"step": 714
},
{
"epoch": 0.78,
"learning_rate": 1.396079766039157e-05,
"loss": 1.6991,
"step": 716
},
{
"epoch": 0.78,
"learning_rate": 1.3928397562931895e-05,
"loss": 1.7411,
"step": 718
},
{
"epoch": 0.78,
"learning_rate": 1.3895948627309184e-05,
"loss": 1.7382,
"step": 720
},
{
"epoch": 0.78,
"learning_rate": 1.3863451256931286e-05,
"loss": 1.6855,
"step": 722
},
{
"epoch": 0.79,
"learning_rate": 1.3830905855808197e-05,
"loss": 1.7052,
"step": 724
},
{
"epoch": 0.79,
"learning_rate": 1.3798312828547028e-05,
"loss": 1.6984,
"step": 726
},
{
"epoch": 0.79,
"learning_rate": 1.3765672580346986e-05,
"loss": 1.6992,
"step": 728
},
{
"epoch": 0.79,
"learning_rate": 1.3732985516994341e-05,
"loss": 1.7465,
"step": 730
},
{
"epoch": 0.8,
"learning_rate": 1.3700252044857356e-05,
"loss": 1.6975,
"step": 732
},
{
"epoch": 0.8,
"learning_rate": 1.3667472570881264e-05,
"loss": 1.7907,
"step": 734
},
{
"epoch": 0.8,
"learning_rate": 1.3634647502583196e-05,
"loss": 1.7531,
"step": 736
},
{
"epoch": 0.8,
"learning_rate": 1.3601777248047105e-05,
"loss": 1.6898,
"step": 738
},
{
"epoch": 0.8,
"learning_rate": 1.356886221591872e-05,
"loss": 1.6602,
"step": 740
},
{
"epoch": 0.81,
"learning_rate": 1.3535902815400435e-05,
"loss": 1.6931,
"step": 742
},
{
"epoch": 0.81,
"learning_rate": 1.350289945624624e-05,
"loss": 1.74,
"step": 744
},
{
"epoch": 0.81,
"learning_rate": 1.3469852548756626e-05,
"loss": 1.7237,
"step": 746
},
{
"epoch": 0.81,
"learning_rate": 1.3436762503773473e-05,
"loss": 1.6722,
"step": 748
},
{
"epoch": 0.82,
"learning_rate": 1.3403629732674954e-05,
"loss": 1.7103,
"step": 750
},
{
"epoch": 0.82,
"learning_rate": 1.3370454647370418e-05,
"loss": 1.7433,
"step": 752
},
{
"epoch": 0.82,
"learning_rate": 1.3337237660295269e-05,
"loss": 1.6665,
"step": 754
},
{
"epoch": 0.82,
"learning_rate": 1.3303979184405826e-05,
"loss": 1.7245,
"step": 756
},
{
"epoch": 0.82,
"learning_rate": 1.3270679633174219e-05,
"loss": 1.7018,
"step": 758
},
{
"epoch": 0.83,
"learning_rate": 1.3237339420583213e-05,
"loss": 1.7226,
"step": 760
},
{
"epoch": 0.83,
"learning_rate": 1.3203958961121087e-05,
"loss": 1.6809,
"step": 762
},
{
"epoch": 0.83,
"learning_rate": 1.3170538669776469e-05,
"loss": 1.7042,
"step": 764
},
{
"epoch": 0.83,
"learning_rate": 1.3137078962033186e-05,
"loss": 1.7106,
"step": 766
},
{
"epoch": 0.83,
"learning_rate": 1.3103580253865086e-05,
"loss": 1.7325,
"step": 768
},
{
"epoch": 0.84,
"learning_rate": 1.3070042961730878e-05,
"loss": 1.7218,
"step": 770
},
{
"epoch": 0.84,
"learning_rate": 1.3036467502568945e-05,
"loss": 1.6903,
"step": 772
},
{
"epoch": 0.84,
"learning_rate": 1.3002854293792175e-05,
"loss": 1.7216,
"step": 774
},
{
"epoch": 0.84,
"learning_rate": 1.296920375328275e-05,
"loss": 1.735,
"step": 776
},
{
"epoch": 0.85,
"learning_rate": 1.2935516299386972e-05,
"loss": 1.6757,
"step": 778
},
{
"epoch": 0.85,
"learning_rate": 1.2901792350910053e-05,
"loss": 1.7137,
"step": 780
},
{
"epoch": 0.85,
"learning_rate": 1.2868032327110904e-05,
"loss": 1.7286,
"step": 782
},
{
"epoch": 0.85,
"learning_rate": 1.283423664769693e-05,
"loss": 1.7215,
"step": 784
},
{
"epoch": 0.85,
"learning_rate": 1.280040573281881e-05,
"loss": 1.7133,
"step": 786
},
{
"epoch": 0.86,
"learning_rate": 1.2766540003065272e-05,
"loss": 1.7211,
"step": 788
},
{
"epoch": 0.86,
"learning_rate": 1.2732639879457867e-05,
"loss": 1.7219,
"step": 790
},
{
"epoch": 0.86,
"learning_rate": 1.2698705783445733e-05,
"loss": 1.7033,
"step": 792
},
{
"epoch": 0.86,
"learning_rate": 1.266473813690035e-05,
"loss": 1.7126,
"step": 794
},
{
"epoch": 0.87,
"learning_rate": 1.2630737362110314e-05,
"loss": 1.7169,
"step": 796
},
{
"epoch": 0.87,
"learning_rate": 1.259670388177606e-05,
"loss": 1.6949,
"step": 798
},
{
"epoch": 0.87,
"learning_rate": 1.2562638119004627e-05,
"loss": 1.6698,
"step": 800
},
{
"epoch": 0.87,
"learning_rate": 1.2528540497304398e-05,
"loss": 1.6932,
"step": 802
},
{
"epoch": 0.87,
"learning_rate": 1.2494411440579814e-05,
"loss": 1.6716,
"step": 804
},
{
"epoch": 0.88,
"learning_rate": 1.2460251373126136e-05,
"loss": 1.6726,
"step": 806
},
{
"epoch": 0.88,
"learning_rate": 1.2426060719624139e-05,
"loss": 1.6908,
"step": 808
},
{
"epoch": 0.88,
"learning_rate": 1.2391839905134853e-05,
"loss": 1.7084,
"step": 810
},
{
"epoch": 0.88,
"learning_rate": 1.2357589355094275e-05,
"loss": 1.7016,
"step": 812
},
{
"epoch": 0.88,
"learning_rate": 1.2323309495308066e-05,
"loss": 1.7306,
"step": 814
},
{
"epoch": 0.89,
"learning_rate": 1.228900075194628e-05,
"loss": 1.6963,
"step": 816
},
{
"epoch": 0.89,
"learning_rate": 1.2254663551538047e-05,
"loss": 1.7015,
"step": 818
},
{
"epoch": 0.89,
"learning_rate": 1.2220298320966278e-05,
"loss": 1.6627,
"step": 820
},
{
"epoch": 0.89,
"learning_rate": 1.2185905487462359e-05,
"loss": 1.7094,
"step": 822
},
{
"epoch": 0.9,
"learning_rate": 1.215148547860084e-05,
"loss": 1.7147,
"step": 824
},
{
"epoch": 0.9,
"learning_rate": 1.211703872229411e-05,
"loss": 1.7279,
"step": 826
},
{
"epoch": 0.9,
"learning_rate": 1.2082565646787092e-05,
"loss": 1.6936,
"step": 828
},
{
"epoch": 0.9,
"learning_rate": 1.2048066680651908e-05,
"loss": 1.7198,
"step": 830
},
{
"epoch": 0.9,
"learning_rate": 1.2013542252782556e-05,
"loss": 1.6956,
"step": 832
},
{
"epoch": 0.91,
"learning_rate": 1.1978992792389574e-05,
"loss": 1.7093,
"step": 834
},
{
"epoch": 0.91,
"learning_rate": 1.194441872899471e-05,
"loss": 1.6571,
"step": 836
},
{
"epoch": 0.91,
"learning_rate": 1.1909820492425574e-05,
"loss": 1.6882,
"step": 838
},
{
"epoch": 0.91,
"learning_rate": 1.1875198512810301e-05,
"loss": 1.698,
"step": 840
},
{
"epoch": 0.92,
"learning_rate": 1.1840553220572204e-05,
"loss": 1.6806,
"step": 842
},
{
"epoch": 0.92,
"learning_rate": 1.180588504642442e-05,
"loss": 1.725,
"step": 844
},
{
"epoch": 0.92,
"learning_rate": 1.1771194421364546e-05,
"loss": 1.726,
"step": 846
},
{
"epoch": 0.92,
"learning_rate": 1.1736481776669307e-05,
"loss": 1.7191,
"step": 848
},
{
"epoch": 0.92,
"learning_rate": 1.1701747543889161e-05,
"loss": 1.6475,
"step": 850
},
{
"epoch": 0.93,
"learning_rate": 1.166699215484297e-05,
"loss": 1.6848,
"step": 852
},
{
"epoch": 0.93,
"learning_rate": 1.1632216041612595e-05,
"loss": 1.67,
"step": 854
},
{
"epoch": 0.93,
"learning_rate": 1.159741963653755e-05,
"loss": 1.6746,
"step": 856
},
{
"epoch": 0.93,
"learning_rate": 1.1562603372209616e-05,
"loss": 1.6875,
"step": 858
},
{
"epoch": 0.93,
"learning_rate": 1.1527767681467472e-05,
"loss": 1.6981,
"step": 860
},
{
"epoch": 0.94,
"learning_rate": 1.1492912997391296e-05,
"loss": 1.679,
"step": 862
},
{
"epoch": 0.94,
"learning_rate": 1.1458039753297408e-05,
"loss": 1.6867,
"step": 864
},
{
"epoch": 0.94,
"learning_rate": 1.1423148382732854e-05,
"loss": 1.6921,
"step": 866
},
{
"epoch": 0.94,
"learning_rate": 1.1388239319470035e-05,
"loss": 1.7129,
"step": 868
},
{
"epoch": 0.95,
"learning_rate": 1.1353312997501313e-05,
"loss": 1.6651,
"step": 870
},
{
"epoch": 0.95,
"learning_rate": 1.1318369851033604e-05,
"loss": 1.7309,
"step": 872
},
{
"epoch": 0.95,
"learning_rate": 1.1283410314482994e-05,
"loss": 1.6894,
"step": 874
},
{
"epoch": 0.95,
"learning_rate": 1.1248434822469334e-05,
"loss": 1.6943,
"step": 876
},
{
"epoch": 0.95,
"learning_rate": 1.121344380981082e-05,
"loss": 1.7303,
"step": 878
},
{
"epoch": 0.96,
"learning_rate": 1.117843771151862e-05,
"loss": 1.7122,
"step": 880
},
{
"epoch": 0.96,
"learning_rate": 1.1143416962791437e-05,
"loss": 1.6939,
"step": 882
},
{
"epoch": 0.96,
"learning_rate": 1.1108381999010111e-05,
"loss": 1.6969,
"step": 884
},
{
"epoch": 0.96,
"learning_rate": 1.1073333255732208e-05,
"loss": 1.7352,
"step": 886
},
{
"epoch": 0.97,
"learning_rate": 1.1038271168686603e-05,
"loss": 1.6713,
"step": 888
},
{
"epoch": 0.97,
"learning_rate": 1.1003196173768051e-05,
"loss": 1.7177,
"step": 890
},
{
"epoch": 0.97,
"learning_rate": 1.0968108707031792e-05,
"loss": 1.6492,
"step": 892
},
{
"epoch": 0.97,
"learning_rate": 1.093300920468811e-05,
"loss": 1.6801,
"step": 894
},
{
"epoch": 0.97,
"learning_rate": 1.0897898103096917e-05,
"loss": 1.6938,
"step": 896
},
{
"epoch": 0.98,
"learning_rate": 1.0862775838762332e-05,
"loss": 1.7084,
"step": 898
},
{
"epoch": 0.98,
"learning_rate": 1.082764284832724e-05,
"loss": 1.6669,
"step": 900
},
{
"epoch": 0.98,
"learning_rate": 1.0792499568567885e-05,
"loss": 1.6981,
"step": 902
},
{
"epoch": 0.98,
"learning_rate": 1.0757346436388427e-05,
"loss": 1.683,
"step": 904
},
{
"epoch": 0.98,
"learning_rate": 1.0722183888815503e-05,
"loss": 1.7075,
"step": 906
},
{
"epoch": 0.99,
"learning_rate": 1.068701236299281e-05,
"loss": 1.6859,
"step": 908
},
{
"epoch": 0.99,
"learning_rate": 1.0651832296175671e-05,
"loss": 1.7037,
"step": 910
},
{
"epoch": 0.99,
"learning_rate": 1.0616644125725573e-05,
"loss": 1.7035,
"step": 912
},
{
"epoch": 0.99,
"learning_rate": 1.0581448289104759e-05,
"loss": 1.6886,
"step": 914
},
{
"epoch": 1.0,
"learning_rate": 1.0546245223870783e-05,
"loss": 1.6434,
"step": 916
},
{
"epoch": 1.0,
"learning_rate": 1.0511035367671057e-05,
"loss": 1.6806,
"step": 918
},
{
"epoch": 1.0,
"learning_rate": 1.0475819158237426e-05,
"loss": 1.7277,
"step": 920
},
{
"epoch": 1.0,
"learning_rate": 1.0440597033380706e-05,
"loss": 1.6252,
"step": 922
},
{
"epoch": 1.0,
"learning_rate": 1.040536943098527e-05,
"loss": 1.649,
"step": 924
},
{
"epoch": 1.01,
"learning_rate": 1.0370136789003582e-05,
"loss": 1.6915,
"step": 926
},
{
"epoch": 1.01,
"learning_rate": 1.0334899545450753e-05,
"loss": 1.6248,
"step": 928
},
{
"epoch": 1.01,
"learning_rate": 1.029965813839911e-05,
"loss": 1.7067,
"step": 930
},
{
"epoch": 1.01,
"learning_rate": 1.0264413005972736e-05,
"loss": 1.6492,
"step": 932
},
{
"epoch": 1.02,
"learning_rate": 1.0229164586342024e-05,
"loss": 1.6859,
"step": 934
},
{
"epoch": 1.02,
"learning_rate": 1.0193913317718245e-05,
"loss": 1.658,
"step": 936
},
{
"epoch": 1.02,
"learning_rate": 1.015865963834808e-05,
"loss": 1.6379,
"step": 938
},
{
"epoch": 1.02,
"learning_rate": 1.0123403986508184e-05,
"loss": 1.6257,
"step": 940
},
{
"epoch": 1.02,
"learning_rate": 1.0088146800499734e-05,
"loss": 1.661,
"step": 942
},
{
"epoch": 1.03,
"learning_rate": 1.0052888518642978e-05,
"loss": 1.6839,
"step": 944
},
{
"epoch": 1.03,
"learning_rate": 1.0017629579271789e-05,
"loss": 1.6268,
"step": 946
},
{
"epoch": 1.03,
"learning_rate": 9.982370420728213e-06,
"loss": 1.6114,
"step": 948
},
{
"epoch": 1.03,
"learning_rate": 9.947111481357023e-06,
"loss": 1.6545,
"step": 950
},
{
"epoch": 1.03,
"learning_rate": 9.911853199500268e-06,
"loss": 1.6429,
"step": 952
},
{
"epoch": 1.04,
"learning_rate": 9.876596013491817e-06,
"loss": 1.635,
"step": 954
},
{
"epoch": 1.04,
"learning_rate": 9.841340361651921e-06,
"loss": 1.6508,
"step": 956
},
{
"epoch": 1.04,
"learning_rate": 9.806086682281759e-06,
"loss": 1.6623,
"step": 958
},
{
"epoch": 1.04,
"learning_rate": 9.770835413657978e-06,
"loss": 1.6282,
"step": 960
},
{
"epoch": 1.05,
"learning_rate": 9.735586994027267e-06,
"loss": 1.6316,
"step": 962
},
{
"epoch": 1.05,
"learning_rate": 9.700341861600894e-06,
"loss": 1.6269,
"step": 964
},
{
"epoch": 1.05,
"learning_rate": 9.665100454549249e-06,
"loss": 1.626,
"step": 966
},
{
"epoch": 1.05,
"learning_rate": 9.62986321099642e-06,
"loss": 1.6456,
"step": 968
},
{
"epoch": 1.05,
"learning_rate": 9.594630569014733e-06,
"loss": 1.6367,
"step": 970
},
{
"epoch": 1.06,
"learning_rate": 9.559402966619296e-06,
"loss": 1.6145,
"step": 972
},
{
"epoch": 1.06,
"learning_rate": 9.524180841762577e-06,
"loss": 1.6695,
"step": 974
},
{
"epoch": 1.06,
"learning_rate": 9.488964632328945e-06,
"loss": 1.656,
"step": 976
},
{
"epoch": 1.06,
"learning_rate": 9.453754776129219e-06,
"loss": 1.6895,
"step": 978
},
{
"epoch": 1.07,
"learning_rate": 9.418551710895243e-06,
"loss": 1.6528,
"step": 980
},
{
"epoch": 1.07,
"learning_rate": 9.383355874274434e-06,
"loss": 1.6276,
"step": 982
},
{
"epoch": 1.07,
"learning_rate": 9.348167703824334e-06,
"loss": 1.6301,
"step": 984
},
{
"epoch": 1.07,
"learning_rate": 9.312987637007191e-06,
"loss": 1.6541,
"step": 986
},
{
"epoch": 1.07,
"learning_rate": 9.277816111184504e-06,
"loss": 1.6725,
"step": 988
},
{
"epoch": 1.08,
"learning_rate": 9.24265356361158e-06,
"loss": 1.6714,
"step": 990
},
{
"epoch": 1.08,
"learning_rate": 9.207500431432115e-06,
"loss": 1.6509,
"step": 992
},
{
"epoch": 1.08,
"learning_rate": 9.17235715167276e-06,
"loss": 1.5701,
"step": 994
},
{
"epoch": 1.08,
"learning_rate": 9.137224161237672e-06,
"loss": 1.6494,
"step": 996
},
{
"epoch": 1.08,
"learning_rate": 9.102101896903084e-06,
"loss": 1.591,
"step": 998
},
{
"epoch": 1.09,
"learning_rate": 9.066990795311891e-06,
"loss": 1.6227,
"step": 1000
},
{
"epoch": 1.09,
"learning_rate": 9.03189129296821e-06,
"loss": 1.6277,
"step": 1002
},
{
"epoch": 1.09,
"learning_rate": 8.99680382623195e-06,
"loss": 1.6702,
"step": 1004
},
{
"epoch": 1.09,
"learning_rate": 8.9617288313134e-06,
"loss": 1.6227,
"step": 1006
},
{
"epoch": 1.1,
"learning_rate": 8.926666744267794e-06,
"loss": 1.6527,
"step": 1008
},
{
"epoch": 1.1,
"learning_rate": 8.89161800098989e-06,
"loss": 1.6507,
"step": 1010
},
{
"epoch": 1.1,
"learning_rate": 8.856583037208566e-06,
"loss": 1.6088,
"step": 1012
},
{
"epoch": 1.1,
"learning_rate": 8.821562288481383e-06,
"loss": 1.5843,
"step": 1014
},
{
"epoch": 1.1,
"learning_rate": 8.786556190189183e-06,
"loss": 1.6324,
"step": 1016
},
{
"epoch": 1.11,
"learning_rate": 8.751565177530669e-06,
"loss": 1.5882,
"step": 1018
},
{
"epoch": 1.11,
"learning_rate": 8.716589685517007e-06,
"loss": 1.6663,
"step": 1020
},
{
"epoch": 1.11,
"learning_rate": 8.681630148966397e-06,
"loss": 1.609,
"step": 1022
},
{
"epoch": 1.11,
"learning_rate": 8.646687002498692e-06,
"loss": 1.6324,
"step": 1024
},
{
"epoch": 1.12,
"learning_rate": 8.61176068052997e-06,
"loss": 1.6329,
"step": 1026
},
{
"epoch": 1.12,
"learning_rate": 8.576851617267151e-06,
"loss": 1.6288,
"step": 1028
},
{
"epoch": 1.12,
"learning_rate": 8.541960246702597e-06,
"loss": 1.6064,
"step": 1030
},
{
"epoch": 1.12,
"learning_rate": 8.507087002608707e-06,
"loss": 1.6498,
"step": 1032
},
{
"epoch": 1.12,
"learning_rate": 8.472232318532531e-06,
"loss": 1.6407,
"step": 1034
},
{
"epoch": 1.13,
"learning_rate": 8.437396627790384e-06,
"loss": 1.6374,
"step": 1036
},
{
"epoch": 1.13,
"learning_rate": 8.402580363462451e-06,
"loss": 1.618,
"step": 1038
},
{
"epoch": 1.13,
"learning_rate": 8.367783958387407e-06,
"loss": 1.6261,
"step": 1040
},
{
"epoch": 1.13,
"learning_rate": 8.333007845157032e-06,
"loss": 1.6398,
"step": 1042
},
{
"epoch": 1.13,
"learning_rate": 8.298252456110839e-06,
"loss": 1.628,
"step": 1044
},
{
"epoch": 1.14,
"learning_rate": 8.263518223330698e-06,
"loss": 1.6068,
"step": 1046
},
{
"epoch": 1.14,
"learning_rate": 8.228805578635457e-06,
"loss": 1.6232,
"step": 1048
},
{
"epoch": 1.14,
"learning_rate": 8.194114953575584e-06,
"loss": 1.6444,
"step": 1050
},
{
"epoch": 1.14,
"learning_rate": 8.159446779427798e-06,
"loss": 1.6266,
"step": 1052
},
{
"epoch": 1.15,
"learning_rate": 8.1248014871897e-06,
"loss": 1.6385,
"step": 1054
},
{
"epoch": 1.15,
"learning_rate": 8.090179507574428e-06,
"loss": 1.6566,
"step": 1056
},
{
"epoch": 1.15,
"learning_rate": 8.055581271005292e-06,
"loss": 1.6199,
"step": 1058
},
{
"epoch": 1.15,
"learning_rate": 8.021007207610427e-06,
"loss": 1.6047,
"step": 1060
},
{
"epoch": 1.15,
"learning_rate": 7.986457747217448e-06,
"loss": 1.5977,
"step": 1062
},
{
"epoch": 1.16,
"learning_rate": 7.951933319348095e-06,
"loss": 1.6626,
"step": 1064
},
{
"epoch": 1.16,
"learning_rate": 7.917434353212911e-06,
"loss": 1.6085,
"step": 1066
},
{
"epoch": 1.16,
"learning_rate": 7.882961277705897e-06,
"loss": 1.6528,
"step": 1068
},
{
"epoch": 1.16,
"learning_rate": 7.848514521399167e-06,
"loss": 1.6223,
"step": 1070
},
{
"epoch": 1.17,
"learning_rate": 7.814094512537645e-06,
"loss": 1.5814,
"step": 1072
},
{
"epoch": 1.17,
"learning_rate": 7.779701679033729e-06,
"loss": 1.6478,
"step": 1074
},
{
"epoch": 1.17,
"learning_rate": 7.745336448461958e-06,
"loss": 1.6188,
"step": 1076
},
{
"epoch": 1.17,
"learning_rate": 7.710999248053722e-06,
"loss": 1.6254,
"step": 1078
},
{
"epoch": 1.17,
"learning_rate": 7.676690504691935e-06,
"loss": 1.694,
"step": 1080
},
{
"epoch": 1.18,
"learning_rate": 7.642410644905726e-06,
"loss": 1.6248,
"step": 1082
},
{
"epoch": 1.18,
"learning_rate": 7.608160094865148e-06,
"loss": 1.6333,
"step": 1084
},
{
"epoch": 1.18,
"learning_rate": 7.573939280375864e-06,
"loss": 1.5986,
"step": 1086
},
{
"epoch": 1.18,
"learning_rate": 7.539748626873866e-06,
"loss": 1.6283,
"step": 1088
},
{
"epoch": 1.18,
"learning_rate": 7.505588559420188e-06,
"loss": 1.6012,
"step": 1090
},
{
"epoch": 1.19,
"learning_rate": 7.471459502695606e-06,
"loss": 1.5643,
"step": 1092
},
{
"epoch": 1.19,
"learning_rate": 7.4373618809953755e-06,
"loss": 1.6646,
"step": 1094
},
{
"epoch": 1.19,
"learning_rate": 7.403296118223944e-06,
"loss": 1.6241,
"step": 1096
},
{
"epoch": 1.19,
"learning_rate": 7.369262637889689e-06,
"loss": 1.6218,
"step": 1098
},
{
"epoch": 1.2,
"learning_rate": 7.335261863099652e-06,
"loss": 1.6436,
"step": 1100
},
{
"epoch": 1.2,
"learning_rate": 7.301294216554271e-06,
"loss": 1.6144,
"step": 1102
},
{
"epoch": 1.2,
"learning_rate": 7.267360120542135e-06,
"loss": 1.6411,
"step": 1104
},
{
"epoch": 1.2,
"learning_rate": 7.233459996934731e-06,
"loss": 1.6185,
"step": 1106
},
{
"epoch": 1.2,
"learning_rate": 7.199594267181193e-06,
"loss": 1.6463,
"step": 1108
},
{
"epoch": 1.21,
"learning_rate": 7.165763352303072e-06,
"loss": 1.6129,
"step": 1110
},
{
"epoch": 1.21,
"learning_rate": 7.131967672889101e-06,
"loss": 1.6221,
"step": 1112
},
{
"epoch": 1.21,
"learning_rate": 7.09820764908995e-06,
"loss": 1.6203,
"step": 1114
},
{
"epoch": 1.21,
"learning_rate": 7.0644837006130295e-06,
"loss": 1.6553,
"step": 1116
},
{
"epoch": 1.22,
"learning_rate": 7.0307962467172555e-06,
"loss": 1.6053,
"step": 1118
},
{
"epoch": 1.22,
"learning_rate": 6.99714570620783e-06,
"loss": 1.6477,
"step": 1120
},
{
"epoch": 1.22,
"learning_rate": 6.963532497431056e-06,
"loss": 1.6295,
"step": 1122
},
{
"epoch": 1.22,
"learning_rate": 6.929957038269123e-06,
"loss": 1.5975,
"step": 1124
},
{
"epoch": 1.22,
"learning_rate": 6.896419746134915e-06,
"loss": 1.6256,
"step": 1126
},
{
"epoch": 1.23,
"learning_rate": 6.862921037966815e-06,
"loss": 1.6324,
"step": 1128
},
{
"epoch": 1.23,
"learning_rate": 6.8294613302235325e-06,
"loss": 1.6103,
"step": 1130
},
{
"epoch": 1.23,
"learning_rate": 6.796041038878918e-06,
"loss": 1.5883,
"step": 1132
},
{
"epoch": 1.23,
"learning_rate": 6.762660579416791e-06,
"loss": 1.6604,
"step": 1134
},
{
"epoch": 1.23,
"learning_rate": 6.729320366825785e-06,
"loss": 1.6339,
"step": 1136
},
{
"epoch": 1.24,
"learning_rate": 6.696020815594176e-06,
"loss": 1.5994,
"step": 1138
},
{
"epoch": 1.24,
"learning_rate": 6.6627623397047355e-06,
"loss": 1.6027,
"step": 1140
},
{
"epoch": 1.24,
"learning_rate": 6.629545352629583e-06,
"loss": 1.6474,
"step": 1142
},
{
"epoch": 1.24,
"learning_rate": 6.59637026732505e-06,
"loss": 1.6322,
"step": 1144
},
{
"epoch": 1.25,
"learning_rate": 6.563237496226531e-06,
"loss": 1.6382,
"step": 1146
},
{
"epoch": 1.25,
"learning_rate": 6.530147451243377e-06,
"loss": 1.6061,
"step": 1148
},
{
"epoch": 1.25,
"learning_rate": 6.497100543753763e-06,
"loss": 1.6787,
"step": 1150
},
{
"epoch": 1.25,
"learning_rate": 6.4640971845995685e-06,
"loss": 1.6073,
"step": 1152
},
{
"epoch": 1.25,
"learning_rate": 6.431137784081283e-06,
"loss": 1.6591,
"step": 1154
},
{
"epoch": 1.26,
"learning_rate": 6.3982227519528986e-06,
"loss": 1.6769,
"step": 1156
},
{
"epoch": 1.26,
"learning_rate": 6.3653524974168105e-06,
"loss": 1.6325,
"step": 1158
},
{
"epoch": 1.26,
"learning_rate": 6.33252742911874e-06,
"loss": 1.651,
"step": 1160
},
{
"epoch": 1.26,
"learning_rate": 6.299747955142648e-06,
"loss": 1.6184,
"step": 1162
},
{
"epoch": 1.27,
"learning_rate": 6.267014483005664e-06,
"loss": 1.5922,
"step": 1164
},
{
"epoch": 1.27,
"learning_rate": 6.234327419653013e-06,
"loss": 1.5832,
"step": 1166
},
{
"epoch": 1.27,
"learning_rate": 6.2016871714529725e-06,
"loss": 1.6537,
"step": 1168
},
{
"epoch": 1.27,
"learning_rate": 6.169094144191805e-06,
"loss": 1.6424,
"step": 1170
},
{
"epoch": 1.27,
"learning_rate": 6.136548743068713e-06,
"loss": 1.5831,
"step": 1172
},
{
"epoch": 1.28,
"learning_rate": 6.1040513726908154e-06,
"loss": 1.6628,
"step": 1174
},
{
"epoch": 1.28,
"learning_rate": 6.071602437068108e-06,
"loss": 1.6093,
"step": 1176
},
{
"epoch": 1.28,
"learning_rate": 6.039202339608432e-06,
"loss": 1.6575,
"step": 1178
},
{
"epoch": 1.28,
"learning_rate": 6.00685148311248e-06,
"loss": 1.6236,
"step": 1180
},
{
"epoch": 1.28,
"learning_rate": 5.974550269768775e-06,
"loss": 1.6254,
"step": 1182
},
{
"epoch": 1.29,
"learning_rate": 5.9422991011486635e-06,
"loss": 1.6757,
"step": 1184
},
{
"epoch": 1.29,
"learning_rate": 5.910098378201341e-06,
"loss": 1.6367,
"step": 1186
},
{
"epoch": 1.29,
"learning_rate": 5.877948501248858e-06,
"loss": 1.6179,
"step": 1188
},
{
"epoch": 1.29,
"learning_rate": 5.845849869981137e-06,
"loss": 1.6268,
"step": 1190
},
{
"epoch": 1.3,
"learning_rate": 5.813802883451014e-06,
"loss": 1.6498,
"step": 1192
},
{
"epoch": 1.3,
"learning_rate": 5.781807940069277e-06,
"loss": 1.6222,
"step": 1194
},
{
"epoch": 1.3,
"learning_rate": 5.749865437599703e-06,
"loss": 1.6241,
"step": 1196
},
{
"epoch": 1.3,
"learning_rate": 5.717975773154116e-06,
"loss": 1.6186,
"step": 1198
},
{
"epoch": 1.3,
"learning_rate": 5.686139343187468e-06,
"loss": 1.6451,
"step": 1200
},
{
"epoch": 1.31,
"learning_rate": 5.654356543492883e-06,
"loss": 1.6549,
"step": 1202
},
{
"epoch": 1.31,
"learning_rate": 5.622627769196746e-06,
"loss": 1.5829,
"step": 1204
},
{
"epoch": 1.31,
"learning_rate": 5.59095341475381e-06,
"loss": 1.5941,
"step": 1206
},
{
"epoch": 1.31,
"learning_rate": 5.559333873942259e-06,
"loss": 1.6329,
"step": 1208
},
{
"epoch": 1.32,
"learning_rate": 5.527769539858839e-06,
"loss": 1.638,
"step": 1210
},
{
"epoch": 1.32,
"learning_rate": 5.4962608049139646e-06,
"loss": 1.6026,
"step": 1212
},
{
"epoch": 1.32,
"learning_rate": 5.464808060826825e-06,
"loss": 1.6985,
"step": 1214
},
{
"epoch": 1.32,
"learning_rate": 5.43341169862053e-06,
"loss": 1.62,
"step": 1216
},
{
"epoch": 1.32,
"learning_rate": 5.402072108617258e-06,
"loss": 1.6195,
"step": 1218
},
{
"epoch": 1.33,
"learning_rate": 5.370789680433376e-06,
"loss": 1.5992,
"step": 1220
},
{
"epoch": 1.33,
"learning_rate": 5.339564802974615e-06,
"loss": 1.5754,
"step": 1222
},
{
"epoch": 1.33,
"learning_rate": 5.308397864431226e-06,
"loss": 1.6545,
"step": 1224
},
{
"epoch": 1.33,
"learning_rate": 5.277289252273175e-06,
"loss": 1.6625,
"step": 1226
},
{
"epoch": 1.33,
"learning_rate": 5.24623935324529e-06,
"loss": 1.6156,
"step": 1228
},
{
"epoch": 1.34,
"learning_rate": 5.215248553362482e-06,
"loss": 1.6134,
"step": 1230
},
{
"epoch": 1.34,
"learning_rate": 5.184317237904939e-06,
"loss": 1.5809,
"step": 1232
},
{
"epoch": 1.34,
"learning_rate": 5.153445791413327e-06,
"loss": 1.6192,
"step": 1234
},
{
"epoch": 1.34,
"learning_rate": 5.122634597684016e-06,
"loss": 1.667,
"step": 1236
},
{
"epoch": 1.35,
"learning_rate": 5.091884039764321e-06,
"loss": 1.6199,
"step": 1238
},
{
"epoch": 1.35,
"learning_rate": 5.061194499947712e-06,
"loss": 1.5865,
"step": 1240
},
{
"epoch": 1.35,
"learning_rate": 5.03056635976908e-06,
"loss": 1.6202,
"step": 1242
},
{
"epoch": 1.35,
"learning_rate": 5.000000000000003e-06,
"loss": 1.596,
"step": 1244
},
{
"epoch": 1.35,
"learning_rate": 4.969495800643985e-06,
"loss": 1.6162,
"step": 1246
},
{
"epoch": 1.36,
"learning_rate": 4.939054140931751e-06,
"loss": 1.6511,
"step": 1248
},
{
"epoch": 1.36,
"learning_rate": 4.908675399316534e-06,
"loss": 1.5728,
"step": 1250
},
{
"epoch": 1.36,
"learning_rate": 4.878359953469354e-06,
"loss": 1.6091,
"step": 1252
},
{
"epoch": 1.36,
"learning_rate": 4.848108180274345e-06,
"loss": 1.601,
"step": 1254
},
{
"epoch": 1.37,
"learning_rate": 4.817920455824045e-06,
"loss": 1.5653,
"step": 1256
},
{
"epoch": 1.37,
"learning_rate": 4.787797155414742e-06,
"loss": 1.5522,
"step": 1258
},
{
"epoch": 1.37,
"learning_rate": 4.757738653541795e-06,
"loss": 1.6041,
"step": 1260
},
{
"epoch": 1.37,
"learning_rate": 4.727745323894976e-06,
"loss": 1.5904,
"step": 1262
},
{
"epoch": 1.37,
"learning_rate": 4.697817539353845e-06,
"loss": 1.6125,
"step": 1264
},
{
"epoch": 1.38,
"learning_rate": 4.66795567198309e-06,
"loss": 1.5485,
"step": 1266
},
{
"epoch": 1.38,
"learning_rate": 4.638160093027908e-06,
"loss": 1.6128,
"step": 1268
},
{
"epoch": 1.38,
"learning_rate": 4.608431172909405e-06,
"loss": 1.6421,
"step": 1270
},
{
"epoch": 1.38,
"learning_rate": 4.578769281219969e-06,
"loss": 1.6406,
"step": 1272
},
{
"epoch": 1.38,
"learning_rate": 4.549174786718684e-06,
"loss": 1.617,
"step": 1274
},
{
"epoch": 1.39,
"learning_rate": 4.519648057326757e-06,
"loss": 1.632,
"step": 1276
},
{
"epoch": 1.39,
"learning_rate": 4.490189460122926e-06,
"loss": 1.6389,
"step": 1278
},
{
"epoch": 1.39,
"learning_rate": 4.460799361338898e-06,
"loss": 1.6284,
"step": 1280
},
{
"epoch": 1.39,
"learning_rate": 4.431478126354818e-06,
"loss": 1.6267,
"step": 1282
},
{
"epoch": 1.4,
"learning_rate": 4.4022261196946995e-06,
"loss": 1.6062,
"step": 1284
},
{
"epoch": 1.4,
"learning_rate": 4.373043705021899e-06,
"loss": 1.6064,
"step": 1286
},
{
"epoch": 1.4,
"learning_rate": 4.343931245134616e-06,
"loss": 1.5933,
"step": 1288
},
{
"epoch": 1.4,
"learning_rate": 4.314889101961353e-06,
"loss": 1.5707,
"step": 1290
},
{
"epoch": 1.4,
"learning_rate": 4.2859176365564294e-06,
"loss": 1.5996,
"step": 1292
},
{
"epoch": 1.41,
"learning_rate": 4.257017209095503e-06,
"loss": 1.6112,
"step": 1294
},
{
"epoch": 1.41,
"learning_rate": 4.228188178871069e-06,
"loss": 1.6038,
"step": 1296
},
{
"epoch": 1.41,
"learning_rate": 4.19943090428802e-06,
"loss": 1.6185,
"step": 1298
},
{
"epoch": 1.41,
"learning_rate": 4.1707457428591615e-06,
"loss": 1.6087,
"step": 1300
},
{
"epoch": 1.42,
"learning_rate": 4.142133051200799e-06,
"loss": 1.6118,
"step": 1302
},
{
"epoch": 1.42,
"learning_rate": 4.113593185028273e-06,
"loss": 1.6334,
"step": 1304
},
{
"epoch": 1.42,
"learning_rate": 4.085126499151555e-06,
"loss": 1.5767,
"step": 1306
},
{
"epoch": 1.42,
"learning_rate": 4.056733347470842e-06,
"loss": 1.657,
"step": 1308
},
{
"epoch": 1.42,
"learning_rate": 4.028414082972141e-06,
"loss": 1.6121,
"step": 1310
},
{
"epoch": 1.43,
"learning_rate": 4.000169057722879e-06,
"loss": 1.6357,
"step": 1312
},
{
"epoch": 1.43,
"learning_rate": 3.9719986228675546e-06,
"loss": 1.5881,
"step": 1314
},
{
"epoch": 1.43,
"learning_rate": 3.943903128623336e-06,
"loss": 1.6296,
"step": 1316
},
{
"epoch": 1.43,
"learning_rate": 3.915882924275725e-06,
"loss": 1.6005,
"step": 1318
},
{
"epoch": 1.43,
"learning_rate": 3.887938358174224e-06,
"loss": 1.5584,
"step": 1320
},
{
"epoch": 1.44,
"learning_rate": 3.860069777727983e-06,
"loss": 1.5739,
"step": 1322
},
{
"epoch": 1.44,
"learning_rate": 3.832277529401494e-06,
"loss": 1.5829,
"step": 1324
},
{
"epoch": 1.44,
"learning_rate": 3.804561958710292e-06,
"loss": 1.6117,
"step": 1326
},
{
"epoch": 1.44,
"learning_rate": 3.7769234102166365e-06,
"loss": 1.6283,
"step": 1328
},
{
"epoch": 1.45,
"learning_rate": 3.7493622275252417e-06,
"loss": 1.6123,
"step": 1330
},
{
"epoch": 1.45,
"learning_rate": 3.7218787532790167e-06,
"loss": 1.613,
"step": 1332
},
{
"epoch": 1.45,
"learning_rate": 3.6944733291547784e-06,
"loss": 1.5981,
"step": 1334
},
{
"epoch": 1.45,
"learning_rate": 3.667146295859021e-06,
"loss": 1.5747,
"step": 1336
},
{
"epoch": 1.45,
"learning_rate": 3.6398979931236866e-06,
"loss": 1.5758,
"step": 1338
},
{
"epoch": 1.46,
"learning_rate": 3.612728759701919e-06,
"loss": 1.6561,
"step": 1340
},
{
"epoch": 1.46,
"learning_rate": 3.5856389333638795e-06,
"loss": 1.6034,
"step": 1342
},
{
"epoch": 1.46,
"learning_rate": 3.5586288508925203e-06,
"loss": 1.5936,
"step": 1344
},
{
"epoch": 1.46,
"learning_rate": 3.5316988480794255e-06,
"loss": 1.6436,
"step": 1346
},
{
"epoch": 1.47,
"learning_rate": 3.5048492597206107e-06,
"loss": 1.5742,
"step": 1348
},
{
"epoch": 1.47,
"learning_rate": 3.478080419612372e-06,
"loss": 1.6403,
"step": 1350
},
{
"epoch": 1.47,
"learning_rate": 3.4513926605471504e-06,
"loss": 1.5285,
"step": 1352
},
{
"epoch": 1.47,
"learning_rate": 3.424786314309365e-06,
"loss": 1.6122,
"step": 1354
},
{
"epoch": 1.47,
"learning_rate": 3.398261711671309e-06,
"loss": 1.6457,
"step": 1356
},
{
"epoch": 1.48,
"learning_rate": 3.37181918238904e-06,
"loss": 1.6318,
"step": 1358
},
{
"epoch": 1.48,
"learning_rate": 3.3454590551982623e-06,
"loss": 1.6204,
"step": 1360
},
{
"epoch": 1.48,
"learning_rate": 3.3191816578102533e-06,
"loss": 1.5928,
"step": 1362
},
{
"epoch": 1.48,
"learning_rate": 3.292987316907792e-06,
"loss": 1.5786,
"step": 1364
},
{
"epoch": 1.48,
"learning_rate": 3.2668763581410877e-06,
"loss": 1.6392,
"step": 1366
},
{
"epoch": 1.49,
"learning_rate": 3.2408491061237325e-06,
"loss": 1.6181,
"step": 1368
},
{
"epoch": 1.49,
"learning_rate": 3.2149058844286796e-06,
"loss": 1.6025,
"step": 1370
},
{
"epoch": 1.49,
"learning_rate": 3.1890470155842023e-06,
"loss": 1.6043,
"step": 1372
},
{
"epoch": 1.49,
"learning_rate": 3.1632728210698902e-06,
"loss": 1.6213,
"step": 1374
},
{
"epoch": 1.5,
"learning_rate": 3.1375836213126653e-06,
"loss": 1.6274,
"step": 1376
},
{
"epoch": 1.5,
"learning_rate": 3.1119797356827796e-06,
"loss": 1.6218,
"step": 1378
},
{
"epoch": 1.5,
"learning_rate": 3.0864614824898487e-06,
"loss": 1.6166,
"step": 1380
},
{
"epoch": 1.5,
"learning_rate": 3.0610291789789094e-06,
"loss": 1.6601,
"step": 1382
},
{
"epoch": 1.5,
"learning_rate": 3.035683141326462e-06,
"loss": 1.6031,
"step": 1384
},
{
"epoch": 1.51,
"learning_rate": 3.0104236846365376e-06,
"loss": 1.5814,
"step": 1386
},
{
"epoch": 1.51,
"learning_rate": 2.9852511229367862e-06,
"loss": 1.5826,
"step": 1388
},
{
"epoch": 1.51,
"learning_rate": 2.96016576917458e-06,
"loss": 1.5896,
"step": 1390
},
{
"epoch": 1.51,
"learning_rate": 2.935167935213107e-06,
"loss": 1.651,
"step": 1392
},
{
"epoch": 1.52,
"learning_rate": 2.9102579318274994e-06,
"loss": 1.5741,
"step": 1394
},
{
"epoch": 1.52,
"learning_rate": 2.885436068700984e-06,
"loss": 1.6375,
"step": 1396
},
{
"epoch": 1.52,
"learning_rate": 2.8607026544210115e-06,
"loss": 1.589,
"step": 1398
},
{
"epoch": 1.52,
"learning_rate": 2.8360579964754277e-06,
"loss": 1.6302,
"step": 1400
},
{
"epoch": 1.52,
"learning_rate": 2.8115024012486624e-06,
"loss": 1.6499,
"step": 1402
},
{
"epoch": 1.53,
"learning_rate": 2.7870361740179007e-06,
"loss": 1.614,
"step": 1404
},
{
"epoch": 1.53,
"learning_rate": 2.7626596189492983e-06,
"loss": 1.5965,
"step": 1406
},
{
"epoch": 1.53,
"learning_rate": 2.7383730390942075e-06,
"loss": 1.595,
"step": 1408
},
{
"epoch": 1.53,
"learning_rate": 2.714176736385392e-06,
"loss": 1.6051,
"step": 1410
},
{
"epoch": 1.53,
"learning_rate": 2.690071011633284e-06,
"loss": 1.5999,
"step": 1412
},
{
"epoch": 1.54,
"learning_rate": 2.666056164522249e-06,
"loss": 1.5581,
"step": 1414
},
{
"epoch": 1.54,
"learning_rate": 2.6421324936068492e-06,
"loss": 1.567,
"step": 1416
},
{
"epoch": 1.54,
"learning_rate": 2.618300296308135e-06,
"loss": 1.6331,
"step": 1418
},
{
"epoch": 1.54,
"learning_rate": 2.594559868909956e-06,
"loss": 1.624,
"step": 1420
},
{
"epoch": 1.55,
"learning_rate": 2.5709115065552647e-06,
"loss": 1.5888,
"step": 1422
},
{
"epoch": 1.55,
"learning_rate": 2.5473555032424534e-06,
"loss": 1.6057,
"step": 1424
},
{
"epoch": 1.55,
"learning_rate": 2.5238921518217042e-06,
"loss": 1.6054,
"step": 1426
},
{
"epoch": 1.55,
"learning_rate": 2.500521743991342e-06,
"loss": 1.6118,
"step": 1428
},
{
"epoch": 1.55,
"learning_rate": 2.477244570294206e-06,
"loss": 1.583,
"step": 1430
},
{
"epoch": 1.56,
"learning_rate": 2.4540609201140386e-06,
"loss": 1.679,
"step": 1432
},
{
"epoch": 1.56,
"learning_rate": 2.4309710816719014e-06,
"loss": 1.6098,
"step": 1434
},
{
"epoch": 1.56,
"learning_rate": 2.4079753420225694e-06,
"loss": 1.5828,
"step": 1436
},
{
"epoch": 1.56,
"learning_rate": 2.3850739870509745e-06,
"loss": 1.6061,
"step": 1438
},
{
"epoch": 1.57,
"learning_rate": 2.362267301468659e-06,
"loss": 1.6345,
"step": 1440
},
{
"epoch": 1.57,
"learning_rate": 2.339555568810221e-06,
"loss": 1.5623,
"step": 1442
},
{
"epoch": 1.57,
"learning_rate": 2.3169390714297936e-06,
"loss": 1.5693,
"step": 1444
},
{
"epoch": 1.57,
"learning_rate": 2.2944180904975457e-06,
"loss": 1.6289,
"step": 1446
},
{
"epoch": 1.57,
"learning_rate": 2.27199290599617e-06,
"loss": 1.6167,
"step": 1448
},
{
"epoch": 1.58,
"learning_rate": 2.2496637967174104e-06,
"loss": 1.6036,
"step": 1450
},
{
"epoch": 1.58,
"learning_rate": 2.2274310402586042e-06,
"loss": 1.598,
"step": 1452
},
{
"epoch": 1.58,
"learning_rate": 2.2052949130192136e-06,
"loss": 1.6045,
"step": 1454
},
{
"epoch": 1.58,
"learning_rate": 2.1832556901973967e-06,
"loss": 1.6274,
"step": 1456
},
{
"epoch": 1.58,
"learning_rate": 2.161313645786599e-06,
"loss": 1.6466,
"step": 1458
},
{
"epoch": 1.59,
"learning_rate": 2.1394690525721275e-06,
"loss": 1.5997,
"step": 1460
},
{
"epoch": 1.59,
"learning_rate": 2.117722182127765e-06,
"loss": 1.6361,
"step": 1462
},
{
"epoch": 1.59,
"learning_rate": 2.0960733048124082e-06,
"loss": 1.5858,
"step": 1464
},
{
"epoch": 1.59,
"learning_rate": 2.0745226897666858e-06,
"loss": 1.6085,
"step": 1466
},
{
"epoch": 1.6,
"learning_rate": 2.0530706049096206e-06,
"loss": 1.6317,
"step": 1468
},
{
"epoch": 1.6,
"learning_rate": 2.0317173169353066e-06,
"loss": 1.6084,
"step": 1470
},
{
"epoch": 1.6,
"learning_rate": 2.010463091309587e-06,
"loss": 1.5833,
"step": 1472
},
{
"epoch": 1.6,
"learning_rate": 1.989308192266748e-06,
"loss": 1.6618,
"step": 1474
},
{
"epoch": 1.6,
"learning_rate": 1.9682528828062397e-06,
"loss": 1.5823,
"step": 1476
},
{
"epoch": 1.61,
"learning_rate": 1.947297424689414e-06,
"loss": 1.65,
"step": 1478
},
{
"epoch": 1.61,
"learning_rate": 1.926442078436255e-06,
"loss": 1.6057,
"step": 1480
},
{
"epoch": 1.61,
"learning_rate": 1.9056871033221458e-06,
"loss": 1.5702,
"step": 1482
},
{
"epoch": 1.61,
"learning_rate": 1.8850327573746584e-06,
"loss": 1.6414,
"step": 1484
},
{
"epoch": 1.62,
"learning_rate": 1.8644792973703252e-06,
"loss": 1.6103,
"step": 1486
},
{
"epoch": 1.62,
"learning_rate": 1.844026978831457e-06,
"loss": 1.5989,
"step": 1488
},
{
"epoch": 1.62,
"learning_rate": 1.8236760560229715e-06,
"loss": 1.5267,
"step": 1490
},
{
"epoch": 1.62,
"learning_rate": 1.803426781949219e-06,
"loss": 1.5732,
"step": 1492
},
{
"epoch": 1.62,
"learning_rate": 1.7832794083508476e-06,
"loss": 1.6437,
"step": 1494
},
{
"epoch": 1.63,
"learning_rate": 1.7632341857016733e-06,
"loss": 1.6356,
"step": 1496
},
{
"epoch": 1.63,
"learning_rate": 1.7432913632055582e-06,
"loss": 1.645,
"step": 1498
},
{
"epoch": 1.63,
"learning_rate": 1.7234511887933159e-06,
"loss": 1.6653,
"step": 1500
},
{
"epoch": 1.63,
"learning_rate": 1.7037139091196396e-06,
"loss": 1.6185,
"step": 1502
},
{
"epoch": 1.64,
"learning_rate": 1.6840797695600187e-06,
"loss": 1.6301,
"step": 1504
},
{
"epoch": 1.64,
"learning_rate": 1.6645490142076948e-06,
"loss": 1.5717,
"step": 1506
},
{
"epoch": 1.64,
"learning_rate": 1.6451218858706374e-06,
"loss": 1.5834,
"step": 1508
},
{
"epoch": 1.64,
"learning_rate": 1.6257986260685077e-06,
"loss": 1.5836,
"step": 1510
},
{
"epoch": 1.64,
"learning_rate": 1.6065794750296648e-06,
"loss": 1.5904,
"step": 1512
},
{
"epoch": 1.65,
"learning_rate": 1.587464671688187e-06,
"loss": 1.6012,
"step": 1514
},
{
"epoch": 1.65,
"learning_rate": 1.56845445368089e-06,
"loss": 1.6069,
"step": 1516
},
{
"epoch": 1.65,
"learning_rate": 1.5495490573443705e-06,
"loss": 1.5809,
"step": 1518
},
{
"epoch": 1.65,
"learning_rate": 1.5307487177120773e-06,
"loss": 1.5976,
"step": 1520
},
{
"epoch": 1.65,
"learning_rate": 1.5120536685113895e-06,
"loss": 1.5876,
"step": 1522
},
{
"epoch": 1.66,
"learning_rate": 1.493464142160701e-06,
"loss": 1.6259,
"step": 1524
},
{
"epoch": 1.66,
"learning_rate": 1.4749803697665366e-06,
"loss": 1.5831,
"step": 1526
},
{
"epoch": 1.66,
"learning_rate": 1.4566025811206875e-06,
"loss": 1.6355,
"step": 1528
},
{
"epoch": 1.66,
"learning_rate": 1.4383310046973365e-06,
"loss": 1.6095,
"step": 1530
},
{
"epoch": 1.67,
"learning_rate": 1.4201658676502294e-06,
"loss": 1.6515,
"step": 1532
},
{
"epoch": 1.67,
"learning_rate": 1.4021073958098553e-06,
"loss": 1.5863,
"step": 1534
},
{
"epoch": 1.67,
"learning_rate": 1.3841558136806254e-06,
"loss": 1.6162,
"step": 1536
},
{
"epoch": 1.67,
"learning_rate": 1.3663113444380905e-06,
"loss": 1.6111,
"step": 1538
},
{
"epoch": 1.67,
"learning_rate": 1.34857420992617e-06,
"loss": 1.5941,
"step": 1540
},
{
"epoch": 1.68,
"learning_rate": 1.3309446306543827e-06,
"loss": 1.5376,
"step": 1542
},
{
"epoch": 1.68,
"learning_rate": 1.3134228257951142e-06,
"loss": 1.5601,
"step": 1544
},
{
"epoch": 1.68,
"learning_rate": 1.2960090131808923e-06,
"loss": 1.6233,
"step": 1546
},
{
"epoch": 1.68,
"learning_rate": 1.2787034093016726e-06,
"loss": 1.5793,
"step": 1548
},
{
"epoch": 1.69,
"learning_rate": 1.2615062293021508e-06,
"loss": 1.6271,
"step": 1550
},
{
"epoch": 1.69,
"learning_rate": 1.2444176869790925e-06,
"loss": 1.611,
"step": 1552
},
{
"epoch": 1.69,
"learning_rate": 1.2274379947786662e-06,
"loss": 1.6106,
"step": 1554
},
{
"epoch": 1.69,
"learning_rate": 1.2105673637938054e-06,
"loss": 1.5766,
"step": 1556
},
{
"epoch": 1.69,
"learning_rate": 1.1938060037615906e-06,
"loss": 1.6424,
"step": 1558
},
{
"epoch": 1.7,
"learning_rate": 1.1771541230606364e-06,
"loss": 1.6204,
"step": 1560
},
{
"epoch": 1.7,
"learning_rate": 1.1606119287084982e-06,
"loss": 1.568,
"step": 1562
},
{
"epoch": 1.7,
"learning_rate": 1.1441796263590988e-06,
"loss": 1.5711,
"step": 1564
},
{
"epoch": 1.7,
"learning_rate": 1.1278574203001846e-06,
"loss": 1.6569,
"step": 1566
},
{
"epoch": 1.7,
"learning_rate": 1.1116455134507665e-06,
"loss": 1.62,
"step": 1568
},
{
"epoch": 1.71,
"learning_rate": 1.095544107358607e-06,
"loss": 1.6469,
"step": 1570
},
{
"epoch": 1.71,
"learning_rate": 1.0795534021977229e-06,
"loss": 1.5438,
"step": 1572
},
{
"epoch": 1.71,
"learning_rate": 1.0636735967658785e-06,
"loss": 1.6138,
"step": 1574
},
{
"epoch": 1.71,
"learning_rate": 1.0479048884821253e-06,
"loss": 1.5924,
"step": 1576
},
{
"epoch": 1.72,
"learning_rate": 1.03224747338435e-06,
"loss": 1.5761,
"step": 1578
},
{
"epoch": 1.72,
"learning_rate": 1.0167015461268303e-06,
"loss": 1.5651,
"step": 1580
},
{
"epoch": 1.72,
"learning_rate": 1.001267299977815e-06,
"loss": 1.6368,
"step": 1582
},
{
"epoch": 1.72,
"learning_rate": 9.859449268171328e-07,
"loss": 1.6616,
"step": 1584
},
{
"epoch": 1.72,
"learning_rate": 9.707346171337895e-07,
"loss": 1.656,
"step": 1586
},
{
"epoch": 1.73,
"learning_rate": 9.556365600236107e-07,
"loss": 1.5951,
"step": 1588
},
{
"epoch": 1.73,
"learning_rate": 9.406509431868893e-07,
"loss": 1.6588,
"step": 1590
},
{
"epoch": 1.73,
"learning_rate": 9.257779529260558e-07,
"loss": 1.6394,
"step": 1592
},
{
"epoch": 1.73,
"learning_rate": 9.110177741433501e-07,
"loss": 1.5994,
"step": 1594
},
{
"epoch": 1.74,
"learning_rate": 8.963705903385344e-07,
"loss": 1.5851,
"step": 1596
},
{
"epoch": 1.74,
"learning_rate": 8.818365836066101e-07,
"loss": 1.5949,
"step": 1598
},
{
"epoch": 1.74,
"learning_rate": 8.67415934635546e-07,
"loss": 1.6209,
"step": 1600
},
{
"epoch": 1.74,
"learning_rate": 8.53108822704044e-07,
"loss": 1.5985,
"step": 1602
},
{
"epoch": 1.74,
"learning_rate": 8.389154256793042e-07,
"loss": 1.6188,
"step": 1604
},
{
"epoch": 1.75,
"learning_rate": 8.248359200148059e-07,
"loss": 1.5641,
"step": 1606
},
{
"epoch": 1.75,
"learning_rate": 8.108704807481282e-07,
"loss": 1.6266,
"step": 1608
},
{
"epoch": 1.75,
"learning_rate": 7.970192814987676e-07,
"loss": 1.5811,
"step": 1610
},
{
"epoch": 1.75,
"learning_rate": 7.832824944659768e-07,
"loss": 1.6541,
"step": 1612
},
{
"epoch": 1.75,
"learning_rate": 7.696602904266237e-07,
"loss": 1.5432,
"step": 1614
},
{
"epoch": 1.76,
"learning_rate": 7.561528387330797e-07,
"loss": 1.5934,
"step": 1616
},
{
"epoch": 1.76,
"learning_rate": 7.427603073110967e-07,
"loss": 1.6044,
"step": 1618
},
{
"epoch": 1.76,
"learning_rate": 7.294828626577321e-07,
"loss": 1.5923,
"step": 1620
},
{
"epoch": 1.76,
"learning_rate": 7.163206698392744e-07,
"loss": 1.5758,
"step": 1622
},
{
"epoch": 1.77,
"learning_rate": 7.032738924891936e-07,
"loss": 1.6244,
"step": 1624
},
{
"epoch": 1.77,
"learning_rate": 6.903426928061019e-07,
"loss": 1.6335,
"step": 1626
},
{
"epoch": 1.77,
"learning_rate": 6.775272315517423e-07,
"loss": 1.5721,
"step": 1628
},
{
"epoch": 1.77,
"learning_rate": 6.648276680489896e-07,
"loss": 1.5646,
"step": 1630
},
{
"epoch": 1.77,
"learning_rate": 6.522441601798646e-07,
"loss": 1.5941,
"step": 1632
},
{
"epoch": 1.78,
"learning_rate": 6.397768643835755e-07,
"loss": 1.6154,
"step": 1634
},
{
"epoch": 1.78,
"learning_rate": 6.274259356545775e-07,
"loss": 1.6103,
"step": 1636
},
{
"epoch": 1.78,
"learning_rate": 6.151915275406339e-07,
"loss": 1.6158,
"step": 1638
},
{
"epoch": 1.78,
"learning_rate": 6.030737921409169e-07,
"loss": 1.649,
"step": 1640
},
{
"epoch": 1.79,
"learning_rate": 5.910728801041166e-07,
"loss": 1.5911,
"step": 1642
},
{
"epoch": 1.79,
"learning_rate": 5.791889406265583e-07,
"loss": 1.6096,
"step": 1644
},
{
"epoch": 1.79,
"learning_rate": 5.674221214503639e-07,
"loss": 1.5872,
"step": 1646
},
{
"epoch": 1.79,
"learning_rate": 5.557725688616001e-07,
"loss": 1.5873,
"step": 1648
},
{
"epoch": 1.79,
"learning_rate": 5.442404276884683e-07,
"loss": 1.5804,
"step": 1650
},
{
"epoch": 1.8,
"learning_rate": 5.328258412994958e-07,
"loss": 1.6198,
"step": 1652
},
{
"epoch": 1.8,
"learning_rate": 5.215289516017685e-07,
"loss": 1.6101,
"step": 1654
},
{
"epoch": 1.8,
"learning_rate": 5.103498990391509e-07,
"loss": 1.625,
"step": 1656
},
{
"epoch": 1.8,
"learning_rate": 4.992888225905467e-07,
"loss": 1.5625,
"step": 1658
},
{
"epoch": 1.8,
"learning_rate": 4.883458597681722e-07,
"loss": 1.587,
"step": 1660
},
{
"epoch": 1.81,
"learning_rate": 4.775211466158469e-07,
"loss": 1.6131,
"step": 1662
},
{
"epoch": 1.81,
"learning_rate": 4.6681481770729844e-07,
"loss": 1.6255,
"step": 1664
},
{
"epoch": 1.81,
"learning_rate": 4.562270061444907e-07,
"loss": 1.6489,
"step": 1666
},
{
"epoch": 1.81,
"learning_rate": 4.4575784355597284e-07,
"loss": 1.5978,
"step": 1668
},
{
"epoch": 1.82,
"learning_rate": 4.354074600952407e-07,
"loss": 1.6011,
"step": 1670
},
{
"epoch": 1.82,
"learning_rate": 4.2517598443911235e-07,
"loss": 1.632,
"step": 1672
},
{
"epoch": 1.82,
"learning_rate": 4.1506354378614277e-07,
"loss": 1.6592,
"step": 1674
},
{
"epoch": 1.82,
"learning_rate": 4.0507026385502747e-07,
"loss": 1.5987,
"step": 1676
},
{
"epoch": 1.82,
"learning_rate": 3.9519626888304684e-07,
"loss": 1.62,
"step": 1678
},
{
"epoch": 1.83,
"learning_rate": 3.8544168162452544e-07,
"loss": 1.5558,
"step": 1680
},
{
"epoch": 1.83,
"learning_rate": 3.7580662334929517e-07,
"loss": 1.5665,
"step": 1682
},
{
"epoch": 1.83,
"learning_rate": 3.662912138411967e-07,
"loss": 1.5468,
"step": 1684
},
{
"epoch": 1.83,
"learning_rate": 3.5689557139658824e-07,
"loss": 1.6209,
"step": 1686
},
{
"epoch": 1.84,
"learning_rate": 3.476198128228736e-07,
"loss": 1.629,
"step": 1688
},
{
"epoch": 1.84,
"learning_rate": 3.3846405343704757e-07,
"loss": 1.6102,
"step": 1690
},
{
"epoch": 1.84,
"learning_rate": 3.2942840706426725e-07,
"loss": 1.6254,
"step": 1692
},
{
"epoch": 1.84,
"learning_rate": 3.2051298603643754e-07,
"loss": 1.61,
"step": 1694
},
{
"epoch": 1.84,
"learning_rate": 3.117179011908067e-07,
"loss": 1.6095,
"step": 1696
},
{
"epoch": 1.85,
"learning_rate": 3.0304326186859525e-07,
"loss": 1.5745,
"step": 1698
},
{
"epoch": 1.85,
"learning_rate": 2.9448917591363923e-07,
"loss": 1.6298,
"step": 1700
},
{
"epoch": 1.85,
"learning_rate": 2.8605574967103924e-07,
"loss": 1.6412,
"step": 1702
},
{
"epoch": 1.85,
"learning_rate": 2.777430879858478e-07,
"loss": 1.5913,
"step": 1704
},
{
"epoch": 1.85,
"learning_rate": 2.6955129420176193e-07,
"loss": 1.5864,
"step": 1706
},
{
"epoch": 1.86,
"learning_rate": 2.6148047015983834e-07,
"loss": 1.6392,
"step": 1708
},
{
"epoch": 1.86,
"learning_rate": 2.535307161972278e-07,
"loss": 1.5669,
"step": 1710
},
{
"epoch": 1.86,
"learning_rate": 2.4570213114592957e-07,
"loss": 1.5771,
"step": 1712
},
{
"epoch": 1.86,
"learning_rate": 2.3799481233156008e-07,
"loss": 1.6162,
"step": 1714
},
{
"epoch": 1.87,
"learning_rate": 2.3040885557214065e-07,
"loss": 1.6131,
"step": 1716
},
{
"epoch": 1.87,
"learning_rate": 2.2294435517691504e-07,
"loss": 1.6432,
"step": 1718
},
{
"epoch": 1.87,
"learning_rate": 2.1560140394516815e-07,
"loss": 1.6298,
"step": 1720
},
{
"epoch": 1.87,
"learning_rate": 2.083800931650759e-07,
"loss": 1.6646,
"step": 1722
},
{
"epoch": 1.87,
"learning_rate": 2.0128051261257165e-07,
"loss": 1.5325,
"step": 1724
},
{
"epoch": 1.88,
"learning_rate": 1.9430275055022597e-07,
"loss": 1.5823,
"step": 1726
},
{
"epoch": 1.88,
"learning_rate": 1.874468937261531e-07,
"loss": 1.6312,
"step": 1728
},
{
"epoch": 1.88,
"learning_rate": 1.8071302737293294e-07,
"loss": 1.6128,
"step": 1730
},
{
"epoch": 1.88,
"learning_rate": 1.7410123520654743e-07,
"loss": 1.6452,
"step": 1732
},
{
"epoch": 1.89,
"learning_rate": 1.6761159942534356e-07,
"loss": 1.5895,
"step": 1734
},
{
"epoch": 1.89,
"learning_rate": 1.612442007090076e-07,
"loss": 1.6007,
"step": 1736
},
{
"epoch": 1.89,
"learning_rate": 1.5499911821756918e-07,
"loss": 1.5869,
"step": 1738
},
{
"epoch": 1.89,
"learning_rate": 1.4887642959040881e-07,
"loss": 1.6045,
"step": 1740
},
{
"epoch": 1.89,
"learning_rate": 1.4287621094529524e-07,
"loss": 1.6119,
"step": 1742
},
{
"epoch": 1.9,
"learning_rate": 1.3699853687744514e-07,
"loss": 1.5636,
"step": 1744
},
{
"epoch": 1.9,
"learning_rate": 1.3124348045858716e-07,
"loss": 1.5762,
"step": 1746
},
{
"epoch": 1.9,
"learning_rate": 1.2561111323605714e-07,
"loss": 1.5763,
"step": 1748
},
{
"epoch": 1.9,
"learning_rate": 1.201015052319099e-07,
"loss": 1.5797,
"step": 1750
},
{
"epoch": 1.9,
"learning_rate": 1.1471472494204994e-07,
"loss": 1.58,
"step": 1752
},
{
"epoch": 1.91,
"learning_rate": 1.0945083933537104e-07,
"loss": 1.6223,
"step": 1754
},
{
"epoch": 1.91,
"learning_rate": 1.0430991385293576e-07,
"loss": 1.6336,
"step": 1756
},
{
"epoch": 1.91,
"learning_rate": 9.929201240715503e-08,
"loss": 1.6027,
"step": 1758
},
{
"epoch": 1.91,
"learning_rate": 9.439719738099318e-08,
"loss": 1.5486,
"step": 1760
},
{
"epoch": 1.92,
"learning_rate": 8.962552962719528e-08,
"loss": 1.6065,
"step": 1762
},
{
"epoch": 1.92,
"learning_rate": 8.497706846752885e-08,
"loss": 1.5629,
"step": 1764
},
{
"epoch": 1.92,
"learning_rate": 8.04518716920466e-08,
"loss": 1.5595,
"step": 1766
},
{
"epoch": 1.92,
"learning_rate": 7.604999555837045e-08,
"loss": 1.5957,
"step": 1768
},
{
"epoch": 1.92,
"learning_rate": 7.177149479098644e-08,
"loss": 1.5925,
"step": 1770
},
{
"epoch": 1.93,
"learning_rate": 6.761642258056977e-08,
"loss": 1.5969,
"step": 1772
},
{
"epoch": 1.93,
"learning_rate": 6.358483058332199e-08,
"loss": 1.5818,
"step": 1774
},
{
"epoch": 1.93,
"learning_rate": 5.967676892032814e-08,
"loss": 1.6095,
"step": 1776
},
{
"epoch": 1.93,
"learning_rate": 5.5892286176932875e-08,
"loss": 1.7004,
"step": 1778
},
{
"epoch": 1.94,
"learning_rate": 5.223142940213865e-08,
"loss": 1.5483,
"step": 1780
},
{
"epoch": 1.94,
"learning_rate": 4.869424410801848e-08,
"loss": 1.5991,
"step": 1782
},
{
"epoch": 1.94,
"learning_rate": 4.528077426915412e-08,
"loss": 1.605,
"step": 1784
},
{
"epoch": 1.94,
"learning_rate": 4.1991062322082057e-08,
"loss": 1.6146,
"step": 1786
},
{
"epoch": 1.94,
"learning_rate": 3.88251491647762e-08,
"loss": 1.6491,
"step": 1788
},
{
"epoch": 1.95,
"learning_rate": 3.578307415612714e-08,
"loss": 1.6435,
"step": 1790
},
{
"epoch": 1.95,
"learning_rate": 3.2864875115464765e-08,
"loss": 1.5878,
"step": 1792
},
{
"epoch": 1.95,
"learning_rate": 3.0070588322079765e-08,
"loss": 1.5822,
"step": 1794
},
{
"epoch": 1.95,
"learning_rate": 2.7400248514776184e-08,
"loss": 1.6123,
"step": 1796
},
{
"epoch": 1.95,
"learning_rate": 2.4853888891439582e-08,
"loss": 1.5567,
"step": 1798
},
{
"epoch": 1.96,
"learning_rate": 2.2431541108624e-08,
"loss": 1.6457,
"step": 1800
},
{
"epoch": 1.96,
"learning_rate": 2.013323528115674e-08,
"loss": 1.6099,
"step": 1802
},
{
"epoch": 1.96,
"learning_rate": 1.7958999981764203e-08,
"loss": 1.598,
"step": 1804
},
{
"epoch": 1.96,
"learning_rate": 1.590886224071997e-08,
"loss": 1.5856,
"step": 1806
},
{
"epoch": 1.97,
"learning_rate": 1.3982847545507271e-08,
"loss": 1.5992,
"step": 1808
},
{
"epoch": 1.97,
"learning_rate": 1.2180979840498153e-08,
"loss": 1.5829,
"step": 1810
},
{
"epoch": 1.97,
"learning_rate": 1.0503281526662579e-08,
"loss": 1.5946,
"step": 1812
},
{
"epoch": 1.97,
"learning_rate": 8.949773461282008e-09,
"loss": 1.6109,
"step": 1814
},
{
"epoch": 1.97,
"learning_rate": 7.520474957699586e-09,
"loss": 1.6202,
"step": 1816
},
{
"epoch": 1.98,
"learning_rate": 6.2154037850703505e-09,
"loss": 1.63,
"step": 1818
},
{
"epoch": 1.98,
"learning_rate": 5.034576168149175e-09,
"loss": 1.5909,
"step": 1820
},
{
"epoch": 1.98,
"learning_rate": 3.978006787079824e-09,
"loss": 1.5918,
"step": 1822
},
{
"epoch": 1.98,
"learning_rate": 3.0457087772228777e-09,
"loss": 1.5599,
"step": 1824
},
{
"epoch": 1.99,
"learning_rate": 2.237693728981416e-09,
"loss": 1.6168,
"step": 1826
},
{
"epoch": 1.99,
"learning_rate": 1.553971687667799e-09,
"loss": 1.5127,
"step": 1828
},
{
"epoch": 1.99,
"learning_rate": 9.945511533693275e-10,
"loss": 1.5519,
"step": 1830
},
{
"epoch": 1.99,
"learning_rate": 5.594390808494332e-10,
"loss": 1.6029,
"step": 1832
},
{
"epoch": 1.99,
"learning_rate": 2.4864087945664085e-10,
"loss": 1.6068,
"step": 1834
},
{
"epoch": 2.0,
"learning_rate": 6.216041306017495e-11,
"loss": 1.6181,
"step": 1836
},
{
"epoch": 2.0,
"learning_rate": 0.0,
"loss": 1.6149,
"step": 1838
},
{
"epoch": 2.0,
"step": 1838,
"total_flos": 2.6076119341989888e+17,
"train_loss": 1.732028792680153,
"train_runtime": 22667.7018,
"train_samples_per_second": 5.194,
"train_steps_per_second": 0.081
}
],
"logging_steps": 2,
"max_steps": 1838,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 1000,
"total_flos": 2.6076119341989888e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}