TienAnh's picture
Model save
4edd166 verified
raw
history blame
No virus
237 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 4.9984,
"eval_steps": 500,
"global_step": 3905,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 3.3898305084745764e-08,
"loss": 1.8573,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 6.779661016949153e-08,
"loss": 1.8573,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 1.0169491525423729e-07,
"loss": 1.8241,
"step": 6
},
{
"epoch": 0.01,
"learning_rate": 1.3559322033898305e-07,
"loss": 1.833,
"step": 8
},
{
"epoch": 0.01,
"learning_rate": 1.694915254237288e-07,
"loss": 1.8443,
"step": 10
},
{
"epoch": 0.02,
"learning_rate": 2.0338983050847458e-07,
"loss": 1.8591,
"step": 12
},
{
"epoch": 0.02,
"learning_rate": 2.3728813559322033e-07,
"loss": 1.8249,
"step": 14
},
{
"epoch": 0.02,
"learning_rate": 2.711864406779661e-07,
"loss": 1.8232,
"step": 16
},
{
"epoch": 0.02,
"learning_rate": 3.0508474576271186e-07,
"loss": 1.8744,
"step": 18
},
{
"epoch": 0.03,
"learning_rate": 3.389830508474576e-07,
"loss": 1.8142,
"step": 20
},
{
"epoch": 0.03,
"learning_rate": 3.7288135593220336e-07,
"loss": 1.8108,
"step": 22
},
{
"epoch": 0.03,
"learning_rate": 4.0677966101694916e-07,
"loss": 1.8525,
"step": 24
},
{
"epoch": 0.03,
"learning_rate": 4.4067796610169486e-07,
"loss": 1.8726,
"step": 26
},
{
"epoch": 0.04,
"learning_rate": 4.7457627118644066e-07,
"loss": 1.8746,
"step": 28
},
{
"epoch": 0.04,
"learning_rate": 5.084745762711864e-07,
"loss": 1.874,
"step": 30
},
{
"epoch": 0.04,
"learning_rate": 5.423728813559322e-07,
"loss": 1.8209,
"step": 32
},
{
"epoch": 0.04,
"learning_rate": 5.76271186440678e-07,
"loss": 1.8491,
"step": 34
},
{
"epoch": 0.05,
"learning_rate": 6.101694915254237e-07,
"loss": 1.8758,
"step": 36
},
{
"epoch": 0.05,
"learning_rate": 6.440677966101694e-07,
"loss": 1.8083,
"step": 38
},
{
"epoch": 0.05,
"learning_rate": 6.779661016949152e-07,
"loss": 1.8444,
"step": 40
},
{
"epoch": 0.05,
"learning_rate": 7.11864406779661e-07,
"loss": 1.8202,
"step": 42
},
{
"epoch": 0.06,
"learning_rate": 7.457627118644067e-07,
"loss": 1.8661,
"step": 44
},
{
"epoch": 0.06,
"learning_rate": 7.796610169491526e-07,
"loss": 1.8116,
"step": 46
},
{
"epoch": 0.06,
"learning_rate": 8.135593220338983e-07,
"loss": 1.8246,
"step": 48
},
{
"epoch": 0.06,
"learning_rate": 8.47457627118644e-07,
"loss": 1.7845,
"step": 50
},
{
"epoch": 0.07,
"learning_rate": 8.813559322033897e-07,
"loss": 1.8106,
"step": 52
},
{
"epoch": 0.07,
"learning_rate": 9.152542372881356e-07,
"loss": 1.7729,
"step": 54
},
{
"epoch": 0.07,
"learning_rate": 9.491525423728813e-07,
"loss": 1.8726,
"step": 56
},
{
"epoch": 0.07,
"learning_rate": 9.830508474576272e-07,
"loss": 1.8511,
"step": 58
},
{
"epoch": 0.08,
"learning_rate": 1.0169491525423727e-06,
"loss": 1.835,
"step": 60
},
{
"epoch": 0.08,
"learning_rate": 1.0508474576271187e-06,
"loss": 1.8424,
"step": 62
},
{
"epoch": 0.08,
"learning_rate": 1.0847457627118644e-06,
"loss": 1.8165,
"step": 64
},
{
"epoch": 0.08,
"learning_rate": 1.11864406779661e-06,
"loss": 1.8804,
"step": 66
},
{
"epoch": 0.09,
"learning_rate": 1.152542372881356e-06,
"loss": 1.8325,
"step": 68
},
{
"epoch": 0.09,
"learning_rate": 1.1864406779661017e-06,
"loss": 1.8372,
"step": 70
},
{
"epoch": 0.09,
"learning_rate": 1.2203389830508474e-06,
"loss": 1.7869,
"step": 72
},
{
"epoch": 0.09,
"learning_rate": 1.2542372881355932e-06,
"loss": 1.8798,
"step": 74
},
{
"epoch": 0.1,
"learning_rate": 1.2881355932203387e-06,
"loss": 1.9387,
"step": 76
},
{
"epoch": 0.1,
"learning_rate": 1.3220338983050847e-06,
"loss": 1.8491,
"step": 78
},
{
"epoch": 0.1,
"learning_rate": 1.3559322033898304e-06,
"loss": 1.8281,
"step": 80
},
{
"epoch": 0.1,
"learning_rate": 1.3898305084745762e-06,
"loss": 1.863,
"step": 82
},
{
"epoch": 0.11,
"learning_rate": 1.423728813559322e-06,
"loss": 1.8097,
"step": 84
},
{
"epoch": 0.11,
"learning_rate": 1.4576271186440677e-06,
"loss": 1.812,
"step": 86
},
{
"epoch": 0.11,
"learning_rate": 1.4915254237288134e-06,
"loss": 1.7921,
"step": 88
},
{
"epoch": 0.12,
"learning_rate": 1.5254237288135592e-06,
"loss": 1.8738,
"step": 90
},
{
"epoch": 0.12,
"learning_rate": 1.5593220338983052e-06,
"loss": 1.8431,
"step": 92
},
{
"epoch": 0.12,
"learning_rate": 1.5932203389830507e-06,
"loss": 1.8871,
"step": 94
},
{
"epoch": 0.12,
"learning_rate": 1.6271186440677967e-06,
"loss": 1.813,
"step": 96
},
{
"epoch": 0.13,
"learning_rate": 1.6610169491525424e-06,
"loss": 1.8829,
"step": 98
},
{
"epoch": 0.13,
"learning_rate": 1.694915254237288e-06,
"loss": 1.806,
"step": 100
},
{
"epoch": 0.13,
"learning_rate": 1.728813559322034e-06,
"loss": 1.8203,
"step": 102
},
{
"epoch": 0.13,
"learning_rate": 1.7627118644067794e-06,
"loss": 1.8037,
"step": 104
},
{
"epoch": 0.14,
"learning_rate": 1.7966101694915254e-06,
"loss": 1.822,
"step": 106
},
{
"epoch": 0.14,
"learning_rate": 1.8305084745762712e-06,
"loss": 1.8257,
"step": 108
},
{
"epoch": 0.14,
"learning_rate": 1.8644067796610167e-06,
"loss": 1.8411,
"step": 110
},
{
"epoch": 0.14,
"learning_rate": 1.8983050847457627e-06,
"loss": 1.7975,
"step": 112
},
{
"epoch": 0.15,
"learning_rate": 1.9322033898305084e-06,
"loss": 1.8104,
"step": 114
},
{
"epoch": 0.15,
"learning_rate": 1.9661016949152544e-06,
"loss": 1.8439,
"step": 116
},
{
"epoch": 0.15,
"learning_rate": 2e-06,
"loss": 1.8176,
"step": 118
},
{
"epoch": 0.15,
"learning_rate": 1.9999986236178518e-06,
"loss": 1.8859,
"step": 120
},
{
"epoch": 0.16,
"learning_rate": 1.9999944944751953e-06,
"loss": 1.856,
"step": 122
},
{
"epoch": 0.16,
"learning_rate": 1.999987612583398e-06,
"loss": 1.8597,
"step": 124
},
{
"epoch": 0.16,
"learning_rate": 1.9999779779614035e-06,
"loss": 1.7975,
"step": 126
},
{
"epoch": 0.16,
"learning_rate": 1.9999655906357345e-06,
"loss": 1.8519,
"step": 128
},
{
"epoch": 0.17,
"learning_rate": 1.999950450640489e-06,
"loss": 1.8934,
"step": 130
},
{
"epoch": 0.17,
"learning_rate": 1.999932558017345e-06,
"loss": 1.8283,
"step": 132
},
{
"epoch": 0.17,
"learning_rate": 1.999911912815556e-06,
"loss": 1.8677,
"step": 134
},
{
"epoch": 0.17,
"learning_rate": 1.999888515091954e-06,
"loss": 1.8343,
"step": 136
},
{
"epoch": 0.18,
"learning_rate": 1.999862364910946e-06,
"loss": 1.8371,
"step": 138
},
{
"epoch": 0.18,
"learning_rate": 1.999833462344519e-06,
"loss": 1.8763,
"step": 140
},
{
"epoch": 0.18,
"learning_rate": 1.9998018074722346e-06,
"loss": 1.8177,
"step": 142
},
{
"epoch": 0.18,
"learning_rate": 1.9997674003812307e-06,
"loss": 1.8532,
"step": 144
},
{
"epoch": 0.19,
"learning_rate": 1.999730241166222e-06,
"loss": 1.9027,
"step": 146
},
{
"epoch": 0.19,
"learning_rate": 1.999690329929499e-06,
"loss": 1.7935,
"step": 148
},
{
"epoch": 0.19,
"learning_rate": 1.999647666780928e-06,
"loss": 1.778,
"step": 150
},
{
"epoch": 0.19,
"learning_rate": 1.999602251837951e-06,
"loss": 1.8963,
"step": 152
},
{
"epoch": 0.2,
"learning_rate": 1.999554085225584e-06,
"loss": 1.873,
"step": 154
},
{
"epoch": 0.2,
"learning_rate": 1.999503167076419e-06,
"loss": 1.8708,
"step": 156
},
{
"epoch": 0.2,
"learning_rate": 1.999449497530621e-06,
"loss": 1.7885,
"step": 158
},
{
"epoch": 0.2,
"learning_rate": 1.99939307673593e-06,
"loss": 1.7956,
"step": 160
},
{
"epoch": 0.21,
"learning_rate": 1.999333904847659e-06,
"loss": 1.7897,
"step": 162
},
{
"epoch": 0.21,
"learning_rate": 1.9992719820286944e-06,
"loss": 1.8566,
"step": 164
},
{
"epoch": 0.21,
"learning_rate": 1.999207308449495e-06,
"loss": 1.802,
"step": 166
},
{
"epoch": 0.22,
"learning_rate": 1.999139884288092e-06,
"loss": 1.8811,
"step": 168
},
{
"epoch": 0.22,
"learning_rate": 1.999069709730088e-06,
"loss": 1.8066,
"step": 170
},
{
"epoch": 0.22,
"learning_rate": 1.9989967849686576e-06,
"loss": 1.8592,
"step": 172
},
{
"epoch": 0.22,
"learning_rate": 1.9989211102045447e-06,
"loss": 1.765,
"step": 174
},
{
"epoch": 0.23,
"learning_rate": 1.9988426856460646e-06,
"loss": 1.863,
"step": 176
},
{
"epoch": 0.23,
"learning_rate": 1.9987615115091016e-06,
"loss": 1.8194,
"step": 178
},
{
"epoch": 0.23,
"learning_rate": 1.9986775880171084e-06,
"loss": 1.8418,
"step": 180
},
{
"epoch": 0.23,
"learning_rate": 1.9985909154011078e-06,
"loss": 1.8577,
"step": 182
},
{
"epoch": 0.24,
"learning_rate": 1.9985014938996877e-06,
"loss": 1.8419,
"step": 184
},
{
"epoch": 0.24,
"learning_rate": 1.9984093237590053e-06,
"loss": 1.8143,
"step": 186
},
{
"epoch": 0.24,
"learning_rate": 1.998314405232783e-06,
"loss": 1.8566,
"step": 188
},
{
"epoch": 0.24,
"learning_rate": 1.998216738582309e-06,
"loss": 1.8191,
"step": 190
},
{
"epoch": 0.25,
"learning_rate": 1.998116324076437e-06,
"loss": 1.8554,
"step": 192
},
{
"epoch": 0.25,
"learning_rate": 1.998013161991584e-06,
"loss": 1.862,
"step": 194
},
{
"epoch": 0.25,
"learning_rate": 1.9979072526117314e-06,
"loss": 1.8549,
"step": 196
},
{
"epoch": 0.25,
"learning_rate": 1.997798596228422e-06,
"loss": 1.8533,
"step": 198
},
{
"epoch": 0.26,
"learning_rate": 1.997687193140762e-06,
"loss": 1.8463,
"step": 200
},
{
"epoch": 0.26,
"learning_rate": 1.9975730436554175e-06,
"loss": 1.8336,
"step": 202
},
{
"epoch": 0.26,
"learning_rate": 1.997456148086615e-06,
"loss": 1.8436,
"step": 204
},
{
"epoch": 0.26,
"learning_rate": 1.9973365067561404e-06,
"loss": 1.8437,
"step": 206
},
{
"epoch": 0.27,
"learning_rate": 1.9972141199933386e-06,
"loss": 1.7783,
"step": 208
},
{
"epoch": 0.27,
"learning_rate": 1.9970889881351113e-06,
"loss": 1.8215,
"step": 210
},
{
"epoch": 0.27,
"learning_rate": 1.9969611115259166e-06,
"loss": 1.9051,
"step": 212
},
{
"epoch": 0.27,
"learning_rate": 1.9968304905177687e-06,
"loss": 1.7652,
"step": 214
},
{
"epoch": 0.28,
"learning_rate": 1.996697125470237e-06,
"loss": 1.8549,
"step": 216
},
{
"epoch": 0.28,
"learning_rate": 1.9965610167504438e-06,
"loss": 1.794,
"step": 218
},
{
"epoch": 0.28,
"learning_rate": 1.9964221647330642e-06,
"loss": 1.7826,
"step": 220
},
{
"epoch": 0.28,
"learning_rate": 1.996280569800325e-06,
"loss": 1.8821,
"step": 222
},
{
"epoch": 0.29,
"learning_rate": 1.996136232342004e-06,
"loss": 1.8722,
"step": 224
},
{
"epoch": 0.29,
"learning_rate": 1.995989152755428e-06,
"loss": 1.8368,
"step": 226
},
{
"epoch": 0.29,
"learning_rate": 1.9958393314454725e-06,
"loss": 1.8212,
"step": 228
},
{
"epoch": 0.29,
"learning_rate": 1.9956867688245604e-06,
"loss": 1.8209,
"step": 230
},
{
"epoch": 0.3,
"learning_rate": 1.99553146531266e-06,
"loss": 1.8375,
"step": 232
},
{
"epoch": 0.3,
"learning_rate": 1.995373421337286e-06,
"loss": 1.7955,
"step": 234
},
{
"epoch": 0.3,
"learning_rate": 1.995212637333496e-06,
"loss": 1.8414,
"step": 236
},
{
"epoch": 0.3,
"learning_rate": 1.99504911374389e-06,
"loss": 1.8137,
"step": 238
},
{
"epoch": 0.31,
"learning_rate": 1.9948828510186105e-06,
"loss": 1.8558,
"step": 240
},
{
"epoch": 0.31,
"learning_rate": 1.9947138496153397e-06,
"loss": 1.8866,
"step": 242
},
{
"epoch": 0.31,
"learning_rate": 1.994542109999298e-06,
"loss": 1.8109,
"step": 244
},
{
"epoch": 0.31,
"learning_rate": 1.9943676326432443e-06,
"loss": 1.7865,
"step": 246
},
{
"epoch": 0.32,
"learning_rate": 1.9941904180274736e-06,
"loss": 1.8212,
"step": 248
},
{
"epoch": 0.32,
"learning_rate": 1.9940104666398164e-06,
"loss": 1.8137,
"step": 250
},
{
"epoch": 0.32,
"learning_rate": 1.993827778975636e-06,
"loss": 1.857,
"step": 252
},
{
"epoch": 0.33,
"learning_rate": 1.993642355537829e-06,
"loss": 1.8069,
"step": 254
},
{
"epoch": 0.33,
"learning_rate": 1.9934541968368215e-06,
"loss": 1.8627,
"step": 256
},
{
"epoch": 0.33,
"learning_rate": 1.9932633033905707e-06,
"loss": 1.8322,
"step": 258
},
{
"epoch": 0.33,
"learning_rate": 1.993069675724561e-06,
"loss": 1.8398,
"step": 260
},
{
"epoch": 0.34,
"learning_rate": 1.9928733143718042e-06,
"loss": 1.8154,
"step": 262
},
{
"epoch": 0.34,
"learning_rate": 1.9926742198728367e-06,
"loss": 1.8107,
"step": 264
},
{
"epoch": 0.34,
"learning_rate": 1.9924723927757185e-06,
"loss": 1.84,
"step": 266
},
{
"epoch": 0.34,
"learning_rate": 1.9922678336360316e-06,
"loss": 1.8141,
"step": 268
},
{
"epoch": 0.35,
"learning_rate": 1.99206054301688e-06,
"loss": 1.8476,
"step": 270
},
{
"epoch": 0.35,
"learning_rate": 1.9918505214888853e-06,
"loss": 1.8208,
"step": 272
},
{
"epoch": 0.35,
"learning_rate": 1.9916377696301877e-06,
"loss": 1.867,
"step": 274
},
{
"epoch": 0.35,
"learning_rate": 1.9914222880264423e-06,
"loss": 1.8521,
"step": 276
},
{
"epoch": 0.36,
"learning_rate": 1.9912040772708197e-06,
"loss": 1.8072,
"step": 278
},
{
"epoch": 0.36,
"learning_rate": 1.9909831379640025e-06,
"loss": 1.7919,
"step": 280
},
{
"epoch": 0.36,
"learning_rate": 1.9907594707141845e-06,
"loss": 1.8286,
"step": 282
},
{
"epoch": 0.36,
"learning_rate": 1.990533076137069e-06,
"loss": 1.8329,
"step": 284
},
{
"epoch": 0.37,
"learning_rate": 1.9903039548558666e-06,
"loss": 1.8118,
"step": 286
},
{
"epoch": 0.37,
"learning_rate": 1.990072107501295e-06,
"loss": 1.8271,
"step": 288
},
{
"epoch": 0.37,
"learning_rate": 1.989837534711574e-06,
"loss": 1.7919,
"step": 290
},
{
"epoch": 0.37,
"learning_rate": 1.989600237132429e-06,
"loss": 1.804,
"step": 292
},
{
"epoch": 0.38,
"learning_rate": 1.9893602154170826e-06,
"loss": 1.8562,
"step": 294
},
{
"epoch": 0.38,
"learning_rate": 1.989117470226259e-06,
"loss": 1.8324,
"step": 296
},
{
"epoch": 0.38,
"learning_rate": 1.9888720022281776e-06,
"loss": 1.8647,
"step": 298
},
{
"epoch": 0.38,
"learning_rate": 1.988623812098555e-06,
"loss": 1.819,
"step": 300
},
{
"epoch": 0.39,
"learning_rate": 1.9883729005205994e-06,
"loss": 1.8859,
"step": 302
},
{
"epoch": 0.39,
"learning_rate": 1.988119268185012e-06,
"loss": 1.8607,
"step": 304
},
{
"epoch": 0.39,
"learning_rate": 1.9878629157899818e-06,
"loss": 1.7748,
"step": 306
},
{
"epoch": 0.39,
"learning_rate": 1.987603844041187e-06,
"loss": 1.8544,
"step": 308
},
{
"epoch": 0.4,
"learning_rate": 1.9873420536517914e-06,
"loss": 1.8477,
"step": 310
},
{
"epoch": 0.4,
"learning_rate": 1.987077545342442e-06,
"loss": 1.8503,
"step": 312
},
{
"epoch": 0.4,
"learning_rate": 1.9868103198412677e-06,
"loss": 1.7961,
"step": 314
},
{
"epoch": 0.4,
"learning_rate": 1.9865403778838774e-06,
"loss": 1.8461,
"step": 316
},
{
"epoch": 0.41,
"learning_rate": 1.986267720213357e-06,
"loss": 1.8095,
"step": 318
},
{
"epoch": 0.41,
"learning_rate": 1.98599234758027e-06,
"loss": 1.833,
"step": 320
},
{
"epoch": 0.41,
"learning_rate": 1.985714260742652e-06,
"loss": 1.8644,
"step": 322
},
{
"epoch": 0.41,
"learning_rate": 1.9854334604660103e-06,
"loss": 1.834,
"step": 324
},
{
"epoch": 0.42,
"learning_rate": 1.985149947523322e-06,
"loss": 1.7866,
"step": 326
},
{
"epoch": 0.42,
"learning_rate": 1.984863722695031e-06,
"loss": 1.7868,
"step": 328
},
{
"epoch": 0.42,
"learning_rate": 1.9845747867690473e-06,
"loss": 1.791,
"step": 330
},
{
"epoch": 0.42,
"learning_rate": 1.984283140540743e-06,
"loss": 1.8504,
"step": 332
},
{
"epoch": 0.43,
"learning_rate": 1.983988784812952e-06,
"loss": 1.7998,
"step": 334
},
{
"epoch": 0.43,
"learning_rate": 1.9836917203959652e-06,
"loss": 1.9007,
"step": 336
},
{
"epoch": 0.43,
"learning_rate": 1.9833919481075325e-06,
"loss": 1.7926,
"step": 338
},
{
"epoch": 0.44,
"learning_rate": 1.983089468772855e-06,
"loss": 1.7594,
"step": 340
},
{
"epoch": 0.44,
"learning_rate": 1.9827842832245876e-06,
"loss": 1.8135,
"step": 342
},
{
"epoch": 0.44,
"learning_rate": 1.9824763923028337e-06,
"loss": 1.7993,
"step": 344
},
{
"epoch": 0.44,
"learning_rate": 1.982165796855145e-06,
"loss": 1.7681,
"step": 346
},
{
"epoch": 0.45,
"learning_rate": 1.981852497736517e-06,
"loss": 1.7945,
"step": 348
},
{
"epoch": 0.45,
"learning_rate": 1.981536495809389e-06,
"loss": 1.8663,
"step": 350
},
{
"epoch": 0.45,
"learning_rate": 1.9812177919436396e-06,
"loss": 1.7988,
"step": 352
},
{
"epoch": 0.45,
"learning_rate": 1.9808963870165854e-06,
"loss": 1.8523,
"step": 354
},
{
"epoch": 0.46,
"learning_rate": 1.9805722819129777e-06,
"loss": 1.7657,
"step": 356
},
{
"epoch": 0.46,
"learning_rate": 1.9802454775250027e-06,
"loss": 1.7819,
"step": 358
},
{
"epoch": 0.46,
"learning_rate": 1.979915974752275e-06,
"loss": 1.7622,
"step": 360
},
{
"epoch": 0.46,
"learning_rate": 1.979583774501838e-06,
"loss": 1.8221,
"step": 362
},
{
"epoch": 0.47,
"learning_rate": 1.9792488776881615e-06,
"loss": 1.7717,
"step": 364
},
{
"epoch": 0.47,
"learning_rate": 1.9789112852331365e-06,
"loss": 1.8507,
"step": 366
},
{
"epoch": 0.47,
"learning_rate": 1.9785709980660767e-06,
"loss": 1.8468,
"step": 368
},
{
"epoch": 0.47,
"learning_rate": 1.9782280171237107e-06,
"loss": 1.8304,
"step": 370
},
{
"epoch": 0.48,
"learning_rate": 1.977882343350186e-06,
"loss": 1.8128,
"step": 372
},
{
"epoch": 0.48,
"learning_rate": 1.97753397769706e-06,
"loss": 1.8032,
"step": 374
},
{
"epoch": 0.48,
"learning_rate": 1.977182921123301e-06,
"loss": 1.786,
"step": 376
},
{
"epoch": 0.48,
"learning_rate": 1.976829174595286e-06,
"loss": 1.8309,
"step": 378
},
{
"epoch": 0.49,
"learning_rate": 1.976472739086795e-06,
"loss": 1.7878,
"step": 380
},
{
"epoch": 0.49,
"learning_rate": 1.9761136155790114e-06,
"loss": 1.8093,
"step": 382
},
{
"epoch": 0.49,
"learning_rate": 1.975751805060517e-06,
"loss": 1.7792,
"step": 384
},
{
"epoch": 0.49,
"learning_rate": 1.9753873085272914e-06,
"loss": 1.8005,
"step": 386
},
{
"epoch": 0.5,
"learning_rate": 1.9750201269827074e-06,
"loss": 1.8366,
"step": 388
},
{
"epoch": 0.5,
"learning_rate": 1.9746502614375296e-06,
"loss": 1.8,
"step": 390
},
{
"epoch": 0.5,
"learning_rate": 1.9742777129099102e-06,
"loss": 1.8446,
"step": 392
},
{
"epoch": 0.5,
"learning_rate": 1.973902482425388e-06,
"loss": 1.8022,
"step": 394
},
{
"epoch": 0.51,
"learning_rate": 1.9735245710168836e-06,
"loss": 1.8674,
"step": 396
},
{
"epoch": 0.51,
"learning_rate": 1.973143979724698e-06,
"loss": 1.8512,
"step": 398
},
{
"epoch": 0.51,
"learning_rate": 1.97276070959651e-06,
"loss": 1.8188,
"step": 400
},
{
"epoch": 0.51,
"learning_rate": 1.972374761687371e-06,
"loss": 1.8258,
"step": 402
},
{
"epoch": 0.52,
"learning_rate": 1.971986137059705e-06,
"loss": 1.8159,
"step": 404
},
{
"epoch": 0.52,
"learning_rate": 1.9715948367833045e-06,
"loss": 1.7919,
"step": 406
},
{
"epoch": 0.52,
"learning_rate": 1.9712008619353263e-06,
"loss": 1.7774,
"step": 408
},
{
"epoch": 0.52,
"learning_rate": 1.9708042136002903e-06,
"loss": 1.8272,
"step": 410
},
{
"epoch": 0.53,
"learning_rate": 1.9704048928700762e-06,
"loss": 1.783,
"step": 412
},
{
"epoch": 0.53,
"learning_rate": 1.97000290084392e-06,
"loss": 1.857,
"step": 414
},
{
"epoch": 0.53,
"learning_rate": 1.9695982386284103e-06,
"loss": 1.9055,
"step": 416
},
{
"epoch": 0.54,
"learning_rate": 1.9691909073374874e-06,
"loss": 1.8309,
"step": 418
},
{
"epoch": 0.54,
"learning_rate": 1.9687809080924383e-06,
"loss": 1.8596,
"step": 420
},
{
"epoch": 0.54,
"learning_rate": 1.968368242021894e-06,
"loss": 1.7581,
"step": 422
},
{
"epoch": 0.54,
"learning_rate": 1.967952910261827e-06,
"loss": 1.8676,
"step": 424
},
{
"epoch": 0.55,
"learning_rate": 1.967534913955548e-06,
"loss": 1.8029,
"step": 426
},
{
"epoch": 0.55,
"learning_rate": 1.967114254253702e-06,
"loss": 1.8458,
"step": 428
},
{
"epoch": 0.55,
"learning_rate": 1.966690932314266e-06,
"loss": 1.7698,
"step": 430
},
{
"epoch": 0.55,
"learning_rate": 1.9662649493025457e-06,
"loss": 1.83,
"step": 432
},
{
"epoch": 0.56,
"learning_rate": 1.965836306391172e-06,
"loss": 1.838,
"step": 434
},
{
"epoch": 0.56,
"learning_rate": 1.9654050047600975e-06,
"loss": 1.8115,
"step": 436
},
{
"epoch": 0.56,
"learning_rate": 1.9649710455965942e-06,
"loss": 1.7583,
"step": 438
},
{
"epoch": 0.56,
"learning_rate": 1.9645344300952494e-06,
"loss": 1.8282,
"step": 440
},
{
"epoch": 0.57,
"learning_rate": 1.9640951594579626e-06,
"loss": 1.7975,
"step": 442
},
{
"epoch": 0.57,
"learning_rate": 1.963653234893942e-06,
"loss": 1.8111,
"step": 444
},
{
"epoch": 0.57,
"learning_rate": 1.963208657619702e-06,
"loss": 1.8674,
"step": 446
},
{
"epoch": 0.57,
"learning_rate": 1.9627614288590595e-06,
"loss": 1.8315,
"step": 448
},
{
"epoch": 0.58,
"learning_rate": 1.962311549843129e-06,
"loss": 1.8006,
"step": 450
},
{
"epoch": 0.58,
"learning_rate": 1.9618590218103222e-06,
"loss": 1.8305,
"step": 452
},
{
"epoch": 0.58,
"learning_rate": 1.9614038460063415e-06,
"loss": 1.8578,
"step": 454
},
{
"epoch": 0.58,
"learning_rate": 1.960946023684179e-06,
"loss": 1.7713,
"step": 456
},
{
"epoch": 0.59,
"learning_rate": 1.9604855561041116e-06,
"loss": 1.822,
"step": 458
},
{
"epoch": 0.59,
"learning_rate": 1.9600224445336976e-06,
"loss": 1.7715,
"step": 460
},
{
"epoch": 0.59,
"learning_rate": 1.9595566902477746e-06,
"loss": 1.7675,
"step": 462
},
{
"epoch": 0.59,
"learning_rate": 1.959088294528454e-06,
"loss": 1.8239,
"step": 464
},
{
"epoch": 0.6,
"learning_rate": 1.958617258665119e-06,
"loss": 1.8167,
"step": 466
},
{
"epoch": 0.6,
"learning_rate": 1.95814358395442e-06,
"loss": 1.7928,
"step": 468
},
{
"epoch": 0.6,
"learning_rate": 1.957667271700272e-06,
"loss": 1.8283,
"step": 470
},
{
"epoch": 0.6,
"learning_rate": 1.9571883232138506e-06,
"loss": 1.769,
"step": 472
},
{
"epoch": 0.61,
"learning_rate": 1.956706739813588e-06,
"loss": 1.7784,
"step": 474
},
{
"epoch": 0.61,
"learning_rate": 1.9562225228251695e-06,
"loss": 1.8252,
"step": 476
},
{
"epoch": 0.61,
"learning_rate": 1.9557356735815308e-06,
"loss": 1.8124,
"step": 478
},
{
"epoch": 0.61,
"learning_rate": 1.9552461934228525e-06,
"loss": 1.7993,
"step": 480
},
{
"epoch": 0.62,
"learning_rate": 1.9547540836965583e-06,
"loss": 1.8444,
"step": 482
},
{
"epoch": 0.62,
"learning_rate": 1.954259345757311e-06,
"loss": 1.8082,
"step": 484
},
{
"epoch": 0.62,
"learning_rate": 1.9537619809670062e-06,
"loss": 1.8021,
"step": 486
},
{
"epoch": 0.62,
"learning_rate": 1.9532619906947732e-06,
"loss": 1.8529,
"step": 488
},
{
"epoch": 0.63,
"learning_rate": 1.952759376316967e-06,
"loss": 1.8225,
"step": 490
},
{
"epoch": 0.63,
"learning_rate": 1.9522541392171662e-06,
"loss": 1.8697,
"step": 492
},
{
"epoch": 0.63,
"learning_rate": 1.95174628078617e-06,
"loss": 1.8439,
"step": 494
},
{
"epoch": 0.63,
"learning_rate": 1.951235802421992e-06,
"loss": 1.835,
"step": 496
},
{
"epoch": 0.64,
"learning_rate": 1.9507227055298592e-06,
"loss": 1.8078,
"step": 498
},
{
"epoch": 0.64,
"learning_rate": 1.9502069915222073e-06,
"loss": 1.795,
"step": 500
},
{
"epoch": 0.64,
"learning_rate": 1.9496886618186747e-06,
"loss": 1.7866,
"step": 502
},
{
"epoch": 0.65,
"learning_rate": 1.9491677178461004e-06,
"loss": 1.7851,
"step": 504
},
{
"epoch": 0.65,
"learning_rate": 1.9486441610385212e-06,
"loss": 1.8432,
"step": 506
},
{
"epoch": 0.65,
"learning_rate": 1.948117992837165e-06,
"loss": 1.7941,
"step": 508
},
{
"epoch": 0.65,
"learning_rate": 1.9475892146904494e-06,
"loss": 1.8513,
"step": 510
},
{
"epoch": 0.66,
"learning_rate": 1.947057828053976e-06,
"loss": 1.81,
"step": 512
},
{
"epoch": 0.66,
"learning_rate": 1.9465238343905264e-06,
"loss": 1.7668,
"step": 514
},
{
"epoch": 0.66,
"learning_rate": 1.9459872351700593e-06,
"loss": 1.8062,
"step": 516
},
{
"epoch": 0.66,
"learning_rate": 1.9454480318697066e-06,
"loss": 1.8499,
"step": 518
},
{
"epoch": 0.67,
"learning_rate": 1.944906225973767e-06,
"loss": 1.8235,
"step": 520
},
{
"epoch": 0.67,
"learning_rate": 1.9443618189737056e-06,
"loss": 1.7488,
"step": 522
},
{
"epoch": 0.67,
"learning_rate": 1.943814812368145e-06,
"loss": 1.8224,
"step": 524
},
{
"epoch": 0.67,
"learning_rate": 1.9432652076628666e-06,
"loss": 1.8161,
"step": 526
},
{
"epoch": 0.68,
"learning_rate": 1.9427130063708022e-06,
"loss": 1.762,
"step": 528
},
{
"epoch": 0.68,
"learning_rate": 1.942158210012032e-06,
"loss": 1.8561,
"step": 530
},
{
"epoch": 0.68,
"learning_rate": 1.9416008201137796e-06,
"loss": 1.8199,
"step": 532
},
{
"epoch": 0.68,
"learning_rate": 1.941040838210408e-06,
"loss": 1.8362,
"step": 534
},
{
"epoch": 0.69,
"learning_rate": 1.940478265843415e-06,
"loss": 1.8121,
"step": 536
},
{
"epoch": 0.69,
"learning_rate": 1.93991310456143e-06,
"loss": 1.8438,
"step": 538
},
{
"epoch": 0.69,
"learning_rate": 1.939345355920209e-06,
"loss": 1.8156,
"step": 540
},
{
"epoch": 0.69,
"learning_rate": 1.9387750214826295e-06,
"loss": 1.7878,
"step": 542
},
{
"epoch": 0.7,
"learning_rate": 1.938202102818689e-06,
"loss": 1.8869,
"step": 544
},
{
"epoch": 0.7,
"learning_rate": 1.9376266015054967e-06,
"loss": 1.8244,
"step": 546
},
{
"epoch": 0.7,
"learning_rate": 1.9370485191272715e-06,
"loss": 1.8173,
"step": 548
},
{
"epoch": 0.7,
"learning_rate": 1.9364678572753393e-06,
"loss": 1.7675,
"step": 550
},
{
"epoch": 0.71,
"learning_rate": 1.9358846175481247e-06,
"loss": 1.8346,
"step": 552
},
{
"epoch": 0.71,
"learning_rate": 1.935298801551149e-06,
"loss": 1.8084,
"step": 554
},
{
"epoch": 0.71,
"learning_rate": 1.9347104108970254e-06,
"loss": 1.8482,
"step": 556
},
{
"epoch": 0.71,
"learning_rate": 1.9341194472054552e-06,
"loss": 1.7735,
"step": 558
},
{
"epoch": 0.72,
"learning_rate": 1.933525912103222e-06,
"loss": 1.8259,
"step": 560
},
{
"epoch": 0.72,
"learning_rate": 1.932929807224188e-06,
"loss": 1.7764,
"step": 562
},
{
"epoch": 0.72,
"learning_rate": 1.9323311342092893e-06,
"loss": 1.8411,
"step": 564
},
{
"epoch": 0.72,
"learning_rate": 1.9317298947065317e-06,
"loss": 1.7686,
"step": 566
},
{
"epoch": 0.73,
"learning_rate": 1.931126090370986e-06,
"loss": 1.8071,
"step": 568
},
{
"epoch": 0.73,
"learning_rate": 1.930519722864783e-06,
"loss": 1.7838,
"step": 570
},
{
"epoch": 0.73,
"learning_rate": 1.9299107938571093e-06,
"loss": 1.8274,
"step": 572
},
{
"epoch": 0.73,
"learning_rate": 1.9292993050242033e-06,
"loss": 1.8943,
"step": 574
},
{
"epoch": 0.74,
"learning_rate": 1.92868525804935e-06,
"loss": 1.7692,
"step": 576
},
{
"epoch": 0.74,
"learning_rate": 1.9280686546228752e-06,
"loss": 1.7951,
"step": 578
},
{
"epoch": 0.74,
"learning_rate": 1.927449496442143e-06,
"loss": 1.7713,
"step": 580
},
{
"epoch": 0.74,
"learning_rate": 1.92682778521155e-06,
"loss": 1.7878,
"step": 582
},
{
"epoch": 0.75,
"learning_rate": 1.9262035226425212e-06,
"loss": 1.7805,
"step": 584
},
{
"epoch": 0.75,
"learning_rate": 1.9255767104535034e-06,
"loss": 1.8093,
"step": 586
},
{
"epoch": 0.75,
"learning_rate": 1.9249473503699637e-06,
"loss": 1.8023,
"step": 588
},
{
"epoch": 0.76,
"learning_rate": 1.9243154441243813e-06,
"loss": 1.7726,
"step": 590
},
{
"epoch": 0.76,
"learning_rate": 1.9236809934562453e-06,
"loss": 1.8557,
"step": 592
},
{
"epoch": 0.76,
"learning_rate": 1.9230440001120493e-06,
"loss": 1.8022,
"step": 594
},
{
"epoch": 0.76,
"learning_rate": 1.9224044658452855e-06,
"loss": 1.8316,
"step": 596
},
{
"epoch": 0.77,
"learning_rate": 1.921762392416441e-06,
"loss": 1.7655,
"step": 598
},
{
"epoch": 0.77,
"learning_rate": 1.921117781592993e-06,
"loss": 1.7926,
"step": 600
},
{
"epoch": 0.77,
"learning_rate": 1.9204706351494026e-06,
"loss": 1.7944,
"step": 602
},
{
"epoch": 0.77,
"learning_rate": 1.9198209548671117e-06,
"loss": 1.8268,
"step": 604
},
{
"epoch": 0.78,
"learning_rate": 1.9191687425345368e-06,
"loss": 1.8233,
"step": 606
},
{
"epoch": 0.78,
"learning_rate": 1.918513999947065e-06,
"loss": 1.8052,
"step": 608
},
{
"epoch": 0.78,
"learning_rate": 1.9178567289070482e-06,
"loss": 1.8233,
"step": 610
},
{
"epoch": 0.78,
"learning_rate": 1.9171969312237984e-06,
"loss": 1.8119,
"step": 612
},
{
"epoch": 0.79,
"learning_rate": 1.9165346087135837e-06,
"loss": 1.7953,
"step": 614
},
{
"epoch": 0.79,
"learning_rate": 1.9158697631996214e-06,
"loss": 1.7871,
"step": 616
},
{
"epoch": 0.79,
"learning_rate": 1.9152023965120743e-06,
"loss": 1.8412,
"step": 618
},
{
"epoch": 0.79,
"learning_rate": 1.9145325104880464e-06,
"loss": 1.8073,
"step": 620
},
{
"epoch": 0.8,
"learning_rate": 1.913860106971575e-06,
"loss": 1.7636,
"step": 622
},
{
"epoch": 0.8,
"learning_rate": 1.9131851878136293e-06,
"loss": 1.8171,
"step": 624
},
{
"epoch": 0.8,
"learning_rate": 1.9125077548721024e-06,
"loss": 1.7956,
"step": 626
},
{
"epoch": 0.8,
"learning_rate": 1.911827810011807e-06,
"loss": 1.8082,
"step": 628
},
{
"epoch": 0.81,
"learning_rate": 1.911145355104472e-06,
"loss": 1.8003,
"step": 630
},
{
"epoch": 0.81,
"learning_rate": 1.9104603920287344e-06,
"loss": 1.8056,
"step": 632
},
{
"epoch": 0.81,
"learning_rate": 1.909772922670136e-06,
"loss": 1.7824,
"step": 634
},
{
"epoch": 0.81,
"learning_rate": 1.909082948921118e-06,
"loss": 1.8242,
"step": 636
},
{
"epoch": 0.82,
"learning_rate": 1.9083904726810153e-06,
"loss": 1.8391,
"step": 638
},
{
"epoch": 0.82,
"learning_rate": 1.9076954958560524e-06,
"loss": 1.8208,
"step": 640
},
{
"epoch": 0.82,
"learning_rate": 1.9069980203593363e-06,
"loss": 1.7819,
"step": 642
},
{
"epoch": 0.82,
"learning_rate": 1.9062980481108527e-06,
"loss": 1.8288,
"step": 644
},
{
"epoch": 0.83,
"learning_rate": 1.9055955810374598e-06,
"loss": 1.8024,
"step": 646
},
{
"epoch": 0.83,
"learning_rate": 1.9048906210728841e-06,
"loss": 1.801,
"step": 648
},
{
"epoch": 0.83,
"learning_rate": 1.9041831701577146e-06,
"loss": 1.7938,
"step": 650
},
{
"epoch": 0.83,
"learning_rate": 1.9034732302393969e-06,
"loss": 1.7895,
"step": 652
},
{
"epoch": 0.84,
"learning_rate": 1.9027608032722277e-06,
"loss": 1.7699,
"step": 654
},
{
"epoch": 0.84,
"learning_rate": 1.9020458912173509e-06,
"loss": 1.7629,
"step": 656
},
{
"epoch": 0.84,
"learning_rate": 1.901328496042751e-06,
"loss": 1.7647,
"step": 658
},
{
"epoch": 0.84,
"learning_rate": 1.9006086197232474e-06,
"loss": 1.7773,
"step": 660
},
{
"epoch": 0.85,
"learning_rate": 1.8998862642404902e-06,
"loss": 1.8122,
"step": 662
},
{
"epoch": 0.85,
"learning_rate": 1.899161431582954e-06,
"loss": 1.8433,
"step": 664
},
{
"epoch": 0.85,
"learning_rate": 1.898434123745932e-06,
"loss": 1.8302,
"step": 666
},
{
"epoch": 0.86,
"learning_rate": 1.897704342731531e-06,
"loss": 1.7579,
"step": 668
},
{
"epoch": 0.86,
"learning_rate": 1.8969720905486666e-06,
"loss": 1.8361,
"step": 670
},
{
"epoch": 0.86,
"learning_rate": 1.8962373692130562e-06,
"loss": 1.7926,
"step": 672
},
{
"epoch": 0.86,
"learning_rate": 1.8955001807472147e-06,
"loss": 1.7964,
"step": 674
},
{
"epoch": 0.87,
"learning_rate": 1.8947605271804478e-06,
"loss": 1.8335,
"step": 676
},
{
"epoch": 0.87,
"learning_rate": 1.8940184105488478e-06,
"loss": 1.7927,
"step": 678
},
{
"epoch": 0.87,
"learning_rate": 1.8932738328952864e-06,
"loss": 1.8009,
"step": 680
},
{
"epoch": 0.87,
"learning_rate": 1.892526796269411e-06,
"loss": 1.8242,
"step": 682
},
{
"epoch": 0.88,
"learning_rate": 1.8917773027276367e-06,
"loss": 1.8067,
"step": 684
},
{
"epoch": 0.88,
"learning_rate": 1.8910253543331432e-06,
"loss": 1.8003,
"step": 686
},
{
"epoch": 0.88,
"learning_rate": 1.8902709531558667e-06,
"loss": 1.7892,
"step": 688
},
{
"epoch": 0.88,
"learning_rate": 1.8895141012724963e-06,
"loss": 1.8163,
"step": 690
},
{
"epoch": 0.89,
"learning_rate": 1.888754800766466e-06,
"loss": 1.8197,
"step": 692
},
{
"epoch": 0.89,
"learning_rate": 1.887993053727952e-06,
"loss": 1.7797,
"step": 694
},
{
"epoch": 0.89,
"learning_rate": 1.8872288622538644e-06,
"loss": 1.7675,
"step": 696
},
{
"epoch": 0.89,
"learning_rate": 1.8864622284478414e-06,
"loss": 1.7624,
"step": 698
},
{
"epoch": 0.9,
"learning_rate": 1.8856931544202456e-06,
"loss": 1.8321,
"step": 700
},
{
"epoch": 0.9,
"learning_rate": 1.8849216422881567e-06,
"loss": 1.8138,
"step": 702
},
{
"epoch": 0.9,
"learning_rate": 1.8841476941753656e-06,
"loss": 1.848,
"step": 704
},
{
"epoch": 0.9,
"learning_rate": 1.8833713122123691e-06,
"loss": 1.7775,
"step": 706
},
{
"epoch": 0.91,
"learning_rate": 1.8825924985363636e-06,
"loss": 1.7897,
"step": 708
},
{
"epoch": 0.91,
"learning_rate": 1.8818112552912396e-06,
"loss": 1.7978,
"step": 710
},
{
"epoch": 0.91,
"learning_rate": 1.8810275846275756e-06,
"loss": 1.8096,
"step": 712
},
{
"epoch": 0.91,
"learning_rate": 1.8802414887026324e-06,
"loss": 1.7734,
"step": 714
},
{
"epoch": 0.92,
"learning_rate": 1.8794529696803463e-06,
"loss": 1.8156,
"step": 716
},
{
"epoch": 0.92,
"learning_rate": 1.8786620297313252e-06,
"loss": 1.7739,
"step": 718
},
{
"epoch": 0.92,
"learning_rate": 1.8778686710328395e-06,
"loss": 1.7966,
"step": 720
},
{
"epoch": 0.92,
"learning_rate": 1.877072895768819e-06,
"loss": 1.8338,
"step": 722
},
{
"epoch": 0.93,
"learning_rate": 1.8762747061298458e-06,
"loss": 1.7717,
"step": 724
},
{
"epoch": 0.93,
"learning_rate": 1.8754741043131474e-06,
"loss": 1.8013,
"step": 726
},
{
"epoch": 0.93,
"learning_rate": 1.874671092522592e-06,
"loss": 1.7963,
"step": 728
},
{
"epoch": 0.93,
"learning_rate": 1.8738656729686819e-06,
"loss": 1.7628,
"step": 730
},
{
"epoch": 0.94,
"learning_rate": 1.873057847868547e-06,
"loss": 1.7921,
"step": 732
},
{
"epoch": 0.94,
"learning_rate": 1.8722476194459397e-06,
"loss": 1.7446,
"step": 734
},
{
"epoch": 0.94,
"learning_rate": 1.8714349899312278e-06,
"loss": 1.8283,
"step": 736
},
{
"epoch": 0.94,
"learning_rate": 1.8706199615613887e-06,
"loss": 1.7839,
"step": 738
},
{
"epoch": 0.95,
"learning_rate": 1.8698025365800034e-06,
"loss": 1.813,
"step": 740
},
{
"epoch": 0.95,
"learning_rate": 1.8689827172372502e-06,
"loss": 1.7703,
"step": 742
},
{
"epoch": 0.95,
"learning_rate": 1.8681605057898988e-06,
"loss": 1.8297,
"step": 744
},
{
"epoch": 0.95,
"learning_rate": 1.8673359045013032e-06,
"loss": 1.8051,
"step": 746
},
{
"epoch": 0.96,
"learning_rate": 1.8665089156413967e-06,
"loss": 1.7947,
"step": 748
},
{
"epoch": 0.96,
"learning_rate": 1.8656795414866844e-06,
"loss": 1.7753,
"step": 750
},
{
"epoch": 0.96,
"learning_rate": 1.8648477843202378e-06,
"loss": 1.7693,
"step": 752
},
{
"epoch": 0.97,
"learning_rate": 1.8640136464316887e-06,
"loss": 1.7754,
"step": 754
},
{
"epoch": 0.97,
"learning_rate": 1.8631771301172216e-06,
"loss": 1.7943,
"step": 756
},
{
"epoch": 0.97,
"learning_rate": 1.8623382376795695e-06,
"loss": 1.7734,
"step": 758
},
{
"epoch": 0.97,
"learning_rate": 1.861496971428005e-06,
"loss": 1.788,
"step": 760
},
{
"epoch": 0.98,
"learning_rate": 1.8606533336783356e-06,
"loss": 1.8087,
"step": 762
},
{
"epoch": 0.98,
"learning_rate": 1.8598073267528976e-06,
"loss": 1.7963,
"step": 764
},
{
"epoch": 0.98,
"learning_rate": 1.8589589529805485e-06,
"loss": 1.773,
"step": 766
},
{
"epoch": 0.98,
"learning_rate": 1.8581082146966613e-06,
"loss": 1.8287,
"step": 768
},
{
"epoch": 0.99,
"learning_rate": 1.8572551142431184e-06,
"loss": 1.7554,
"step": 770
},
{
"epoch": 0.99,
"learning_rate": 1.8563996539683035e-06,
"loss": 1.838,
"step": 772
},
{
"epoch": 0.99,
"learning_rate": 1.8555418362270974e-06,
"loss": 1.833,
"step": 774
},
{
"epoch": 0.99,
"learning_rate": 1.8546816633808704e-06,
"loss": 1.8018,
"step": 776
},
{
"epoch": 1.0,
"learning_rate": 1.8538191377974756e-06,
"loss": 1.8236,
"step": 778
},
{
"epoch": 1.0,
"learning_rate": 1.8529542618512424e-06,
"loss": 1.7984,
"step": 780
},
{
"epoch": 1.0,
"learning_rate": 1.8520870379229704e-06,
"loss": 1.7933,
"step": 782
},
{
"epoch": 1.0,
"learning_rate": 1.851217468399923e-06,
"loss": 1.6972,
"step": 784
},
{
"epoch": 1.01,
"learning_rate": 1.85034555567582e-06,
"loss": 1.7472,
"step": 786
},
{
"epoch": 1.01,
"learning_rate": 1.8494713021508313e-06,
"loss": 1.7659,
"step": 788
},
{
"epoch": 1.01,
"learning_rate": 1.848594710231571e-06,
"loss": 1.7349,
"step": 790
},
{
"epoch": 1.01,
"learning_rate": 1.8477157823310901e-06,
"loss": 1.7677,
"step": 792
},
{
"epoch": 1.02,
"learning_rate": 1.84683452086887e-06,
"loss": 1.7569,
"step": 794
},
{
"epoch": 1.02,
"learning_rate": 1.8459509282708153e-06,
"loss": 1.7986,
"step": 796
},
{
"epoch": 1.02,
"learning_rate": 1.845065006969249e-06,
"loss": 1.7613,
"step": 798
},
{
"epoch": 1.02,
"learning_rate": 1.8441767594029032e-06,
"loss": 1.8022,
"step": 800
},
{
"epoch": 1.03,
"learning_rate": 1.8432861880169138e-06,
"loss": 1.7552,
"step": 802
},
{
"epoch": 1.03,
"learning_rate": 1.8423932952628143e-06,
"loss": 1.7657,
"step": 804
},
{
"epoch": 1.03,
"learning_rate": 1.8414980835985277e-06,
"loss": 1.7605,
"step": 806
},
{
"epoch": 1.03,
"learning_rate": 1.8406005554883613e-06,
"loss": 1.7887,
"step": 808
},
{
"epoch": 1.04,
"learning_rate": 1.8397007134029976e-06,
"loss": 1.7925,
"step": 810
},
{
"epoch": 1.04,
"learning_rate": 1.8387985598194904e-06,
"loss": 1.7165,
"step": 812
},
{
"epoch": 1.04,
"learning_rate": 1.8378940972212553e-06,
"loss": 1.7897,
"step": 814
},
{
"epoch": 1.04,
"learning_rate": 1.8369873280980654e-06,
"loss": 1.7472,
"step": 816
},
{
"epoch": 1.05,
"learning_rate": 1.8360782549460418e-06,
"loss": 1.7701,
"step": 818
},
{
"epoch": 1.05,
"learning_rate": 1.835166880267649e-06,
"loss": 1.7786,
"step": 820
},
{
"epoch": 1.05,
"learning_rate": 1.8342532065716863e-06,
"loss": 1.747,
"step": 822
},
{
"epoch": 1.05,
"learning_rate": 1.8333372363732822e-06,
"loss": 1.8155,
"step": 824
},
{
"epoch": 1.06,
"learning_rate": 1.8324189721938867e-06,
"loss": 1.7557,
"step": 826
},
{
"epoch": 1.06,
"learning_rate": 1.8314984165612647e-06,
"loss": 1.7619,
"step": 828
},
{
"epoch": 1.06,
"learning_rate": 1.830575572009489e-06,
"loss": 1.8354,
"step": 830
},
{
"epoch": 1.06,
"learning_rate": 1.8296504410789328e-06,
"loss": 1.7772,
"step": 832
},
{
"epoch": 1.07,
"learning_rate": 1.828723026316264e-06,
"loss": 1.8088,
"step": 834
},
{
"epoch": 1.07,
"learning_rate": 1.8277933302744364e-06,
"loss": 1.7169,
"step": 836
},
{
"epoch": 1.07,
"learning_rate": 1.8268613555126842e-06,
"loss": 1.7681,
"step": 838
},
{
"epoch": 1.08,
"learning_rate": 1.8259271045965143e-06,
"loss": 1.8341,
"step": 840
},
{
"epoch": 1.08,
"learning_rate": 1.8249905800976991e-06,
"loss": 1.7711,
"step": 842
},
{
"epoch": 1.08,
"learning_rate": 1.8240517845942703e-06,
"loss": 1.7395,
"step": 844
},
{
"epoch": 1.08,
"learning_rate": 1.82311072067051e-06,
"loss": 1.7884,
"step": 846
},
{
"epoch": 1.09,
"learning_rate": 1.8221673909169457e-06,
"loss": 1.8014,
"step": 848
},
{
"epoch": 1.09,
"learning_rate": 1.8212217979303416e-06,
"loss": 1.7443,
"step": 850
},
{
"epoch": 1.09,
"learning_rate": 1.8202739443136932e-06,
"loss": 1.8017,
"step": 852
},
{
"epoch": 1.09,
"learning_rate": 1.819323832676217e-06,
"loss": 1.7642,
"step": 854
},
{
"epoch": 1.1,
"learning_rate": 1.8183714656333468e-06,
"loss": 1.6993,
"step": 856
},
{
"epoch": 1.1,
"learning_rate": 1.8174168458067247e-06,
"loss": 1.7745,
"step": 858
},
{
"epoch": 1.1,
"learning_rate": 1.8164599758241938e-06,
"loss": 1.7764,
"step": 860
},
{
"epoch": 1.1,
"learning_rate": 1.8155008583197922e-06,
"loss": 1.7515,
"step": 862
},
{
"epoch": 1.11,
"learning_rate": 1.8145394959337435e-06,
"loss": 1.7751,
"step": 864
},
{
"epoch": 1.11,
"learning_rate": 1.8135758913124524e-06,
"loss": 1.6793,
"step": 866
},
{
"epoch": 1.11,
"learning_rate": 1.8126100471084951e-06,
"loss": 1.7843,
"step": 868
},
{
"epoch": 1.11,
"learning_rate": 1.811641965980613e-06,
"loss": 1.7813,
"step": 870
},
{
"epoch": 1.12,
"learning_rate": 1.8106716505937052e-06,
"loss": 1.7971,
"step": 872
},
{
"epoch": 1.12,
"learning_rate": 1.8096991036188216e-06,
"loss": 1.7482,
"step": 874
},
{
"epoch": 1.12,
"learning_rate": 1.8087243277331544e-06,
"loss": 1.765,
"step": 876
},
{
"epoch": 1.12,
"learning_rate": 1.807747325620032e-06,
"loss": 1.8088,
"step": 878
},
{
"epoch": 1.13,
"learning_rate": 1.8067680999689108e-06,
"loss": 1.764,
"step": 880
},
{
"epoch": 1.13,
"learning_rate": 1.8057866534753686e-06,
"loss": 1.7689,
"step": 882
},
{
"epoch": 1.13,
"learning_rate": 1.8048029888410958e-06,
"loss": 1.7369,
"step": 884
},
{
"epoch": 1.13,
"learning_rate": 1.8038171087738895e-06,
"loss": 1.8231,
"step": 886
},
{
"epoch": 1.14,
"learning_rate": 1.8028290159876453e-06,
"loss": 1.7552,
"step": 888
},
{
"epoch": 1.14,
"learning_rate": 1.8018387132023496e-06,
"loss": 1.8052,
"step": 890
},
{
"epoch": 1.14,
"learning_rate": 1.800846203144072e-06,
"loss": 1.7474,
"step": 892
},
{
"epoch": 1.14,
"learning_rate": 1.7998514885449597e-06,
"loss": 1.7837,
"step": 894
},
{
"epoch": 1.15,
"learning_rate": 1.7988545721432273e-06,
"loss": 1.7812,
"step": 896
},
{
"epoch": 1.15,
"learning_rate": 1.7978554566831505e-06,
"loss": 1.7577,
"step": 898
},
{
"epoch": 1.15,
"learning_rate": 1.7968541449150584e-06,
"loss": 1.7825,
"step": 900
},
{
"epoch": 1.15,
"learning_rate": 1.7958506395953265e-06,
"loss": 1.8194,
"step": 902
},
{
"epoch": 1.16,
"learning_rate": 1.7948449434863687e-06,
"loss": 1.7674,
"step": 904
},
{
"epoch": 1.16,
"learning_rate": 1.793837059356629e-06,
"loss": 1.8109,
"step": 906
},
{
"epoch": 1.16,
"learning_rate": 1.792826989980575e-06,
"loss": 1.751,
"step": 908
},
{
"epoch": 1.16,
"learning_rate": 1.7918147381386894e-06,
"loss": 1.7846,
"step": 910
},
{
"epoch": 1.17,
"learning_rate": 1.7908003066174632e-06,
"loss": 1.8061,
"step": 912
},
{
"epoch": 1.17,
"learning_rate": 1.7897836982093873e-06,
"loss": 1.7639,
"step": 914
},
{
"epoch": 1.17,
"learning_rate": 1.7887649157129445e-06,
"loss": 1.7751,
"step": 916
},
{
"epoch": 1.18,
"learning_rate": 1.7877439619326038e-06,
"loss": 1.7818,
"step": 918
},
{
"epoch": 1.18,
"learning_rate": 1.7867208396788095e-06,
"loss": 1.7905,
"step": 920
},
{
"epoch": 1.18,
"learning_rate": 1.7856955517679766e-06,
"loss": 1.8213,
"step": 922
},
{
"epoch": 1.18,
"learning_rate": 1.7846681010224805e-06,
"loss": 1.785,
"step": 924
},
{
"epoch": 1.19,
"learning_rate": 1.7836384902706512e-06,
"loss": 1.7378,
"step": 926
},
{
"epoch": 1.19,
"learning_rate": 1.7826067223467644e-06,
"loss": 1.8538,
"step": 928
},
{
"epoch": 1.19,
"learning_rate": 1.781572800091034e-06,
"loss": 1.7892,
"step": 930
},
{
"epoch": 1.19,
"learning_rate": 1.7805367263496046e-06,
"loss": 1.7461,
"step": 932
},
{
"epoch": 1.2,
"learning_rate": 1.7794985039745424e-06,
"loss": 1.7368,
"step": 934
},
{
"epoch": 1.2,
"learning_rate": 1.7784581358238292e-06,
"loss": 1.7469,
"step": 936
},
{
"epoch": 1.2,
"learning_rate": 1.7774156247613533e-06,
"loss": 1.8113,
"step": 938
},
{
"epoch": 1.2,
"learning_rate": 1.7763709736569017e-06,
"loss": 1.7533,
"step": 940
},
{
"epoch": 1.21,
"learning_rate": 1.7753241853861531e-06,
"loss": 1.7669,
"step": 942
},
{
"epoch": 1.21,
"learning_rate": 1.7742752628306684e-06,
"loss": 1.7799,
"step": 944
},
{
"epoch": 1.21,
"learning_rate": 1.773224208877885e-06,
"loss": 1.8392,
"step": 946
},
{
"epoch": 1.21,
"learning_rate": 1.7721710264211057e-06,
"loss": 1.7935,
"step": 948
},
{
"epoch": 1.22,
"learning_rate": 1.771115718359494e-06,
"loss": 1.8075,
"step": 950
},
{
"epoch": 1.22,
"learning_rate": 1.7700582875980641e-06,
"loss": 1.7635,
"step": 952
},
{
"epoch": 1.22,
"learning_rate": 1.768998737047674e-06,
"loss": 1.8069,
"step": 954
},
{
"epoch": 1.22,
"learning_rate": 1.7679370696250162e-06,
"loss": 1.7255,
"step": 956
},
{
"epoch": 1.23,
"learning_rate": 1.7668732882526111e-06,
"loss": 1.7261,
"step": 958
},
{
"epoch": 1.23,
"learning_rate": 1.7658073958587982e-06,
"loss": 1.7813,
"step": 960
},
{
"epoch": 1.23,
"learning_rate": 1.7647393953777279e-06,
"loss": 1.7731,
"step": 962
},
{
"epoch": 1.23,
"learning_rate": 1.7636692897493536e-06,
"loss": 1.7978,
"step": 964
},
{
"epoch": 1.24,
"learning_rate": 1.762597081919424e-06,
"loss": 1.7776,
"step": 966
},
{
"epoch": 1.24,
"learning_rate": 1.7615227748394747e-06,
"loss": 1.779,
"step": 968
},
{
"epoch": 1.24,
"learning_rate": 1.7604463714668199e-06,
"loss": 1.7691,
"step": 970
},
{
"epoch": 1.24,
"learning_rate": 1.759367874764544e-06,
"loss": 1.7957,
"step": 972
},
{
"epoch": 1.25,
"learning_rate": 1.7582872877014944e-06,
"loss": 1.7805,
"step": 974
},
{
"epoch": 1.25,
"learning_rate": 1.7572046132522727e-06,
"loss": 1.7358,
"step": 976
},
{
"epoch": 1.25,
"learning_rate": 1.7561198543972263e-06,
"loss": 1.8211,
"step": 978
},
{
"epoch": 1.25,
"learning_rate": 1.755033014122441e-06,
"loss": 1.825,
"step": 980
},
{
"epoch": 1.26,
"learning_rate": 1.7539440954197313e-06,
"loss": 1.813,
"step": 982
},
{
"epoch": 1.26,
"learning_rate": 1.752853101286634e-06,
"loss": 1.7576,
"step": 984
},
{
"epoch": 1.26,
"learning_rate": 1.7517600347263993e-06,
"loss": 1.8266,
"step": 986
},
{
"epoch": 1.26,
"learning_rate": 1.7506648987479813e-06,
"loss": 1.7351,
"step": 988
},
{
"epoch": 1.27,
"learning_rate": 1.7495676963660312e-06,
"loss": 1.8129,
"step": 990
},
{
"epoch": 1.27,
"learning_rate": 1.7484684306008883e-06,
"loss": 1.7107,
"step": 992
},
{
"epoch": 1.27,
"learning_rate": 1.7473671044785729e-06,
"loss": 1.7233,
"step": 994
},
{
"epoch": 1.27,
"learning_rate": 1.7462637210307756e-06,
"loss": 1.7391,
"step": 996
},
{
"epoch": 1.28,
"learning_rate": 1.7451582832948511e-06,
"loss": 1.7801,
"step": 998
},
{
"epoch": 1.28,
"learning_rate": 1.7440507943138092e-06,
"loss": 1.7584,
"step": 1000
},
{
"epoch": 1.28,
"learning_rate": 1.7429412571363057e-06,
"loss": 1.7588,
"step": 1002
},
{
"epoch": 1.29,
"learning_rate": 1.7418296748166353e-06,
"loss": 1.7837,
"step": 1004
},
{
"epoch": 1.29,
"learning_rate": 1.7407160504147216e-06,
"loss": 1.8158,
"step": 1006
},
{
"epoch": 1.29,
"learning_rate": 1.7396003869961105e-06,
"loss": 1.7629,
"step": 1008
},
{
"epoch": 1.29,
"learning_rate": 1.73848268763196e-06,
"loss": 1.7924,
"step": 1010
},
{
"epoch": 1.3,
"learning_rate": 1.7373629553990337e-06,
"loss": 1.7924,
"step": 1012
},
{
"epoch": 1.3,
"learning_rate": 1.7362411933796902e-06,
"loss": 1.7715,
"step": 1014
},
{
"epoch": 1.3,
"learning_rate": 1.7351174046618753e-06,
"loss": 1.7834,
"step": 1016
},
{
"epoch": 1.3,
"learning_rate": 1.7339915923391156e-06,
"loss": 1.7966,
"step": 1018
},
{
"epoch": 1.31,
"learning_rate": 1.732863759510506e-06,
"loss": 1.7463,
"step": 1020
},
{
"epoch": 1.31,
"learning_rate": 1.731733909280705e-06,
"loss": 1.7759,
"step": 1022
},
{
"epoch": 1.31,
"learning_rate": 1.730602044759924e-06,
"loss": 1.7682,
"step": 1024
},
{
"epoch": 1.31,
"learning_rate": 1.7294681690639194e-06,
"loss": 1.7869,
"step": 1026
},
{
"epoch": 1.32,
"learning_rate": 1.728332285313983e-06,
"loss": 1.7948,
"step": 1028
},
{
"epoch": 1.32,
"learning_rate": 1.7271943966369357e-06,
"loss": 1.8354,
"step": 1030
},
{
"epoch": 1.32,
"learning_rate": 1.7260545061651168e-06,
"loss": 1.7485,
"step": 1032
},
{
"epoch": 1.32,
"learning_rate": 1.7249126170363757e-06,
"loss": 1.8219,
"step": 1034
},
{
"epoch": 1.33,
"learning_rate": 1.723768732394064e-06,
"loss": 1.7477,
"step": 1036
},
{
"epoch": 1.33,
"learning_rate": 1.7226228553870272e-06,
"loss": 1.8063,
"step": 1038
},
{
"epoch": 1.33,
"learning_rate": 1.7214749891695942e-06,
"loss": 1.789,
"step": 1040
},
{
"epoch": 1.33,
"learning_rate": 1.7203251369015698e-06,
"loss": 1.7607,
"step": 1042
},
{
"epoch": 1.34,
"learning_rate": 1.7191733017482266e-06,
"loss": 1.7993,
"step": 1044
},
{
"epoch": 1.34,
"learning_rate": 1.7180194868802954e-06,
"loss": 1.754,
"step": 1046
},
{
"epoch": 1.34,
"learning_rate": 1.7168636954739562e-06,
"loss": 1.7572,
"step": 1048
},
{
"epoch": 1.34,
"learning_rate": 1.7157059307108307e-06,
"loss": 1.7806,
"step": 1050
},
{
"epoch": 1.35,
"learning_rate": 1.714546195777972e-06,
"loss": 1.731,
"step": 1052
},
{
"epoch": 1.35,
"learning_rate": 1.7133844938678576e-06,
"loss": 1.7497,
"step": 1054
},
{
"epoch": 1.35,
"learning_rate": 1.7122208281783786e-06,
"loss": 1.7549,
"step": 1056
},
{
"epoch": 1.35,
"learning_rate": 1.7110552019128326e-06,
"loss": 1.7732,
"step": 1058
},
{
"epoch": 1.36,
"learning_rate": 1.7098876182799136e-06,
"loss": 1.7574,
"step": 1060
},
{
"epoch": 1.36,
"learning_rate": 1.7087180804937042e-06,
"loss": 1.7486,
"step": 1062
},
{
"epoch": 1.36,
"learning_rate": 1.7075465917736669e-06,
"loss": 1.7246,
"step": 1064
},
{
"epoch": 1.36,
"learning_rate": 1.7063731553446334e-06,
"loss": 1.7639,
"step": 1066
},
{
"epoch": 1.37,
"learning_rate": 1.7051977744367977e-06,
"loss": 1.8214,
"step": 1068
},
{
"epoch": 1.37,
"learning_rate": 1.7040204522857065e-06,
"loss": 1.7567,
"step": 1070
},
{
"epoch": 1.37,
"learning_rate": 1.7028411921322502e-06,
"loss": 1.7865,
"step": 1072
},
{
"epoch": 1.37,
"learning_rate": 1.7016599972226538e-06,
"loss": 1.7777,
"step": 1074
},
{
"epoch": 1.38,
"learning_rate": 1.7004768708084688e-06,
"loss": 1.7539,
"step": 1076
},
{
"epoch": 1.38,
"learning_rate": 1.6992918161465633e-06,
"loss": 1.7612,
"step": 1078
},
{
"epoch": 1.38,
"learning_rate": 1.6981048364991132e-06,
"loss": 1.7504,
"step": 1080
},
{
"epoch": 1.38,
"learning_rate": 1.6969159351335937e-06,
"loss": 1.7659,
"step": 1082
},
{
"epoch": 1.39,
"learning_rate": 1.6957251153227704e-06,
"loss": 1.7646,
"step": 1084
},
{
"epoch": 1.39,
"learning_rate": 1.6945323803446897e-06,
"loss": 1.7651,
"step": 1086
},
{
"epoch": 1.39,
"learning_rate": 1.6933377334826694e-06,
"loss": 1.7811,
"step": 1088
},
{
"epoch": 1.4,
"learning_rate": 1.6921411780252902e-06,
"loss": 1.7811,
"step": 1090
},
{
"epoch": 1.4,
"learning_rate": 1.6909427172663885e-06,
"loss": 1.7981,
"step": 1092
},
{
"epoch": 1.4,
"learning_rate": 1.6897423545050438e-06,
"loss": 1.7279,
"step": 1094
},
{
"epoch": 1.4,
"learning_rate": 1.6885400930455713e-06,
"loss": 1.7795,
"step": 1096
},
{
"epoch": 1.41,
"learning_rate": 1.6873359361975142e-06,
"loss": 1.7351,
"step": 1098
},
{
"epoch": 1.41,
"learning_rate": 1.686129887275632e-06,
"loss": 1.6998,
"step": 1100
},
{
"epoch": 1.41,
"learning_rate": 1.6849219495998934e-06,
"loss": 1.7847,
"step": 1102
},
{
"epoch": 1.41,
"learning_rate": 1.6837121264954656e-06,
"loss": 1.734,
"step": 1104
},
{
"epoch": 1.42,
"learning_rate": 1.6825004212927072e-06,
"loss": 1.766,
"step": 1106
},
{
"epoch": 1.42,
"learning_rate": 1.6812868373271564e-06,
"loss": 1.7493,
"step": 1108
},
{
"epoch": 1.42,
"learning_rate": 1.680071377939524e-06,
"loss": 1.7268,
"step": 1110
},
{
"epoch": 1.42,
"learning_rate": 1.6788540464756834e-06,
"loss": 1.74,
"step": 1112
},
{
"epoch": 1.43,
"learning_rate": 1.677634846286661e-06,
"loss": 1.7352,
"step": 1114
},
{
"epoch": 1.43,
"learning_rate": 1.6764137807286277e-06,
"loss": 1.7328,
"step": 1116
},
{
"epoch": 1.43,
"learning_rate": 1.675190853162889e-06,
"loss": 1.8453,
"step": 1118
},
{
"epoch": 1.43,
"learning_rate": 1.673966066955876e-06,
"loss": 1.7435,
"step": 1120
},
{
"epoch": 1.44,
"learning_rate": 1.672739425479137e-06,
"loss": 1.81,
"step": 1122
},
{
"epoch": 1.44,
"learning_rate": 1.6715109321093264e-06,
"loss": 1.7854,
"step": 1124
},
{
"epoch": 1.44,
"learning_rate": 1.6702805902281973e-06,
"loss": 1.7936,
"step": 1126
},
{
"epoch": 1.44,
"learning_rate": 1.6690484032225905e-06,
"loss": 1.797,
"step": 1128
},
{
"epoch": 1.45,
"learning_rate": 1.6678143744844266e-06,
"loss": 1.7982,
"step": 1130
},
{
"epoch": 1.45,
"learning_rate": 1.6665785074106961e-06,
"loss": 1.7911,
"step": 1132
},
{
"epoch": 1.45,
"learning_rate": 1.6653408054034493e-06,
"loss": 1.7478,
"step": 1134
},
{
"epoch": 1.45,
"learning_rate": 1.6641012718697884e-06,
"loss": 1.735,
"step": 1136
},
{
"epoch": 1.46,
"learning_rate": 1.6628599102218568e-06,
"loss": 1.7656,
"step": 1138
},
{
"epoch": 1.46,
"learning_rate": 1.6616167238768308e-06,
"loss": 1.7913,
"step": 1140
},
{
"epoch": 1.46,
"learning_rate": 1.660371716256909e-06,
"loss": 1.7329,
"step": 1142
},
{
"epoch": 1.46,
"learning_rate": 1.6591248907893043e-06,
"loss": 1.7509,
"step": 1144
},
{
"epoch": 1.47,
"learning_rate": 1.6578762509062334e-06,
"loss": 1.7303,
"step": 1146
},
{
"epoch": 1.47,
"learning_rate": 1.656625800044907e-06,
"loss": 1.74,
"step": 1148
},
{
"epoch": 1.47,
"learning_rate": 1.6553735416475227e-06,
"loss": 1.742,
"step": 1150
},
{
"epoch": 1.47,
"learning_rate": 1.6541194791612514e-06,
"loss": 1.8236,
"step": 1152
},
{
"epoch": 1.48,
"learning_rate": 1.6528636160382323e-06,
"loss": 1.7843,
"step": 1154
},
{
"epoch": 1.48,
"learning_rate": 1.6516059557355603e-06,
"loss": 1.8208,
"step": 1156
},
{
"epoch": 1.48,
"learning_rate": 1.650346501715278e-06,
"loss": 1.8232,
"step": 1158
},
{
"epoch": 1.48,
"learning_rate": 1.6490852574443651e-06,
"loss": 1.819,
"step": 1160
},
{
"epoch": 1.49,
"learning_rate": 1.6478222263947303e-06,
"loss": 1.7883,
"step": 1162
},
{
"epoch": 1.49,
"learning_rate": 1.6465574120431999e-06,
"loss": 1.7488,
"step": 1164
},
{
"epoch": 1.49,
"learning_rate": 1.64529081787151e-06,
"loss": 1.8044,
"step": 1166
},
{
"epoch": 1.5,
"learning_rate": 1.644022447366296e-06,
"loss": 1.7767,
"step": 1168
},
{
"epoch": 1.5,
"learning_rate": 1.6427523040190823e-06,
"loss": 1.7911,
"step": 1170
},
{
"epoch": 1.5,
"learning_rate": 1.6414803913262745e-06,
"loss": 1.784,
"step": 1172
},
{
"epoch": 1.5,
"learning_rate": 1.6402067127891486e-06,
"loss": 1.7605,
"step": 1174
},
{
"epoch": 1.51,
"learning_rate": 1.6389312719138415e-06,
"loss": 1.7809,
"step": 1176
},
{
"epoch": 1.51,
"learning_rate": 1.6376540722113405e-06,
"loss": 1.7418,
"step": 1178
},
{
"epoch": 1.51,
"learning_rate": 1.6363751171974762e-06,
"loss": 1.7201,
"step": 1180
},
{
"epoch": 1.51,
"learning_rate": 1.6350944103929103e-06,
"loss": 1.7579,
"step": 1182
},
{
"epoch": 1.52,
"learning_rate": 1.633811955323126e-06,
"loss": 1.7932,
"step": 1184
},
{
"epoch": 1.52,
"learning_rate": 1.6325277555184204e-06,
"loss": 1.7633,
"step": 1186
},
{
"epoch": 1.52,
"learning_rate": 1.6312418145138928e-06,
"loss": 1.7913,
"step": 1188
},
{
"epoch": 1.52,
"learning_rate": 1.629954135849436e-06,
"loss": 1.7334,
"step": 1190
},
{
"epoch": 1.53,
"learning_rate": 1.6286647230697252e-06,
"loss": 1.7396,
"step": 1192
},
{
"epoch": 1.53,
"learning_rate": 1.6273735797242103e-06,
"loss": 1.8029,
"step": 1194
},
{
"epoch": 1.53,
"learning_rate": 1.6260807093671043e-06,
"loss": 1.7739,
"step": 1196
},
{
"epoch": 1.53,
"learning_rate": 1.624786115557375e-06,
"loss": 1.7438,
"step": 1198
},
{
"epoch": 1.54,
"learning_rate": 1.6234898018587336e-06,
"loss": 1.7758,
"step": 1200
},
{
"epoch": 1.54,
"learning_rate": 1.6221917718396263e-06,
"loss": 1.7654,
"step": 1202
},
{
"epoch": 1.54,
"learning_rate": 1.6208920290732237e-06,
"loss": 1.7396,
"step": 1204
},
{
"epoch": 1.54,
"learning_rate": 1.6195905771374115e-06,
"loss": 1.7835,
"step": 1206
},
{
"epoch": 1.55,
"learning_rate": 1.6182874196147801e-06,
"loss": 1.7743,
"step": 1208
},
{
"epoch": 1.55,
"learning_rate": 1.616982560092615e-06,
"loss": 1.8123,
"step": 1210
},
{
"epoch": 1.55,
"learning_rate": 1.6156760021628868e-06,
"loss": 1.7574,
"step": 1212
},
{
"epoch": 1.55,
"learning_rate": 1.6143677494222416e-06,
"loss": 1.7278,
"step": 1214
},
{
"epoch": 1.56,
"learning_rate": 1.6130578054719903e-06,
"loss": 1.7262,
"step": 1216
},
{
"epoch": 1.56,
"learning_rate": 1.6117461739181008e-06,
"loss": 1.7763,
"step": 1218
},
{
"epoch": 1.56,
"learning_rate": 1.6104328583711851e-06,
"loss": 1.7775,
"step": 1220
},
{
"epoch": 1.56,
"learning_rate": 1.6091178624464912e-06,
"loss": 1.774,
"step": 1222
},
{
"epoch": 1.57,
"learning_rate": 1.6078011897638931e-06,
"loss": 1.7318,
"step": 1224
},
{
"epoch": 1.57,
"learning_rate": 1.6064828439478806e-06,
"loss": 1.8058,
"step": 1226
},
{
"epoch": 1.57,
"learning_rate": 1.6051628286275484e-06,
"loss": 1.7728,
"step": 1228
},
{
"epoch": 1.57,
"learning_rate": 1.6038411474365882e-06,
"loss": 1.7473,
"step": 1230
},
{
"epoch": 1.58,
"learning_rate": 1.6025178040132765e-06,
"loss": 1.7442,
"step": 1232
},
{
"epoch": 1.58,
"learning_rate": 1.6011928020004656e-06,
"loss": 1.7814,
"step": 1234
},
{
"epoch": 1.58,
"learning_rate": 1.5998661450455742e-06,
"loss": 1.7908,
"step": 1236
},
{
"epoch": 1.58,
"learning_rate": 1.5985378368005758e-06,
"loss": 1.7583,
"step": 1238
},
{
"epoch": 1.59,
"learning_rate": 1.5972078809219902e-06,
"loss": 1.7665,
"step": 1240
},
{
"epoch": 1.59,
"learning_rate": 1.5958762810708724e-06,
"loss": 1.7921,
"step": 1242
},
{
"epoch": 1.59,
"learning_rate": 1.5945430409128027e-06,
"loss": 1.7206,
"step": 1244
},
{
"epoch": 1.59,
"learning_rate": 1.593208164117877e-06,
"loss": 1.7341,
"step": 1246
},
{
"epoch": 1.6,
"learning_rate": 1.5918716543606967e-06,
"loss": 1.7533,
"step": 1248
},
{
"epoch": 1.6,
"learning_rate": 1.5905335153203582e-06,
"loss": 1.7497,
"step": 1250
},
{
"epoch": 1.6,
"learning_rate": 1.589193750680443e-06,
"loss": 1.7803,
"step": 1252
},
{
"epoch": 1.61,
"learning_rate": 1.5878523641290068e-06,
"loss": 1.7565,
"step": 1254
},
{
"epoch": 1.61,
"learning_rate": 1.5865093593585708e-06,
"loss": 1.7286,
"step": 1256
},
{
"epoch": 1.61,
"learning_rate": 1.5851647400661108e-06,
"loss": 1.8,
"step": 1258
},
{
"epoch": 1.61,
"learning_rate": 1.5838185099530473e-06,
"loss": 1.7057,
"step": 1260
},
{
"epoch": 1.62,
"learning_rate": 1.582470672725233e-06,
"loss": 1.8,
"step": 1262
},
{
"epoch": 1.62,
"learning_rate": 1.5811212320929474e-06,
"loss": 1.7741,
"step": 1264
},
{
"epoch": 1.62,
"learning_rate": 1.579770191770882e-06,
"loss": 1.784,
"step": 1266
},
{
"epoch": 1.62,
"learning_rate": 1.5784175554781328e-06,
"loss": 1.7569,
"step": 1268
},
{
"epoch": 1.63,
"learning_rate": 1.577063326938188e-06,
"loss": 1.7908,
"step": 1270
},
{
"epoch": 1.63,
"learning_rate": 1.5757075098789198e-06,
"loss": 1.7753,
"step": 1272
},
{
"epoch": 1.63,
"learning_rate": 1.5743501080325735e-06,
"loss": 1.7691,
"step": 1274
},
{
"epoch": 1.63,
"learning_rate": 1.5729911251357556e-06,
"loss": 1.7539,
"step": 1276
},
{
"epoch": 1.64,
"learning_rate": 1.5716305649294262e-06,
"loss": 1.7889,
"step": 1278
},
{
"epoch": 1.64,
"learning_rate": 1.5702684311588868e-06,
"loss": 1.7908,
"step": 1280
},
{
"epoch": 1.64,
"learning_rate": 1.5689047275737708e-06,
"loss": 1.7651,
"step": 1282
},
{
"epoch": 1.64,
"learning_rate": 1.5675394579280323e-06,
"loss": 1.7766,
"step": 1284
},
{
"epoch": 1.65,
"learning_rate": 1.5661726259799371e-06,
"loss": 1.7664,
"step": 1286
},
{
"epoch": 1.65,
"learning_rate": 1.5648042354920516e-06,
"loss": 1.804,
"step": 1288
},
{
"epoch": 1.65,
"learning_rate": 1.5634342902312318e-06,
"loss": 1.7746,
"step": 1290
},
{
"epoch": 1.65,
"learning_rate": 1.5620627939686144e-06,
"loss": 1.7667,
"step": 1292
},
{
"epoch": 1.66,
"learning_rate": 1.5606897504796058e-06,
"loss": 1.7626,
"step": 1294
},
{
"epoch": 1.66,
"learning_rate": 1.55931516354387e-06,
"loss": 1.7635,
"step": 1296
},
{
"epoch": 1.66,
"learning_rate": 1.5579390369453217e-06,
"loss": 1.7473,
"step": 1298
},
{
"epoch": 1.66,
"learning_rate": 1.5565613744721126e-06,
"loss": 1.7486,
"step": 1300
},
{
"epoch": 1.67,
"learning_rate": 1.5551821799166228e-06,
"loss": 1.7574,
"step": 1302
},
{
"epoch": 1.67,
"learning_rate": 1.5538014570754505e-06,
"loss": 1.7817,
"step": 1304
},
{
"epoch": 1.67,
"learning_rate": 1.5524192097493996e-06,
"loss": 1.756,
"step": 1306
},
{
"epoch": 1.67,
"learning_rate": 1.5510354417434713e-06,
"loss": 1.7979,
"step": 1308
},
{
"epoch": 1.68,
"learning_rate": 1.5496501568668525e-06,
"loss": 1.7505,
"step": 1310
},
{
"epoch": 1.68,
"learning_rate": 1.5482633589329063e-06,
"loss": 1.7062,
"step": 1312
},
{
"epoch": 1.68,
"learning_rate": 1.5468750517591607e-06,
"loss": 1.7463,
"step": 1314
},
{
"epoch": 1.68,
"learning_rate": 1.5454852391672977e-06,
"loss": 1.7254,
"step": 1316
},
{
"epoch": 1.69,
"learning_rate": 1.5440939249831443e-06,
"loss": 1.7854,
"step": 1318
},
{
"epoch": 1.69,
"learning_rate": 1.5427011130366598e-06,
"loss": 1.7627,
"step": 1320
},
{
"epoch": 1.69,
"learning_rate": 1.5413068071619277e-06,
"loss": 1.7754,
"step": 1322
},
{
"epoch": 1.69,
"learning_rate": 1.5399110111971436e-06,
"loss": 1.7434,
"step": 1324
},
{
"epoch": 1.7,
"learning_rate": 1.5385137289846042e-06,
"loss": 1.7646,
"step": 1326
},
{
"epoch": 1.7,
"learning_rate": 1.5371149643706986e-06,
"loss": 1.7617,
"step": 1328
},
{
"epoch": 1.7,
"learning_rate": 1.5357147212058956e-06,
"loss": 1.7316,
"step": 1330
},
{
"epoch": 1.7,
"learning_rate": 1.5343130033447351e-06,
"loss": 1.7348,
"step": 1332
},
{
"epoch": 1.71,
"learning_rate": 1.5329098146458156e-06,
"loss": 1.7613,
"step": 1334
},
{
"epoch": 1.71,
"learning_rate": 1.5315051589717852e-06,
"loss": 1.7694,
"step": 1336
},
{
"epoch": 1.71,
"learning_rate": 1.53009904018933e-06,
"loss": 1.7662,
"step": 1338
},
{
"epoch": 1.72,
"learning_rate": 1.5286914621691627e-06,
"loss": 1.7236,
"step": 1340
},
{
"epoch": 1.72,
"learning_rate": 1.5272824287860146e-06,
"loss": 1.7562,
"step": 1342
},
{
"epoch": 1.72,
"learning_rate": 1.5258719439186223e-06,
"loss": 1.7525,
"step": 1344
},
{
"epoch": 1.72,
"learning_rate": 1.5244600114497178e-06,
"loss": 1.7646,
"step": 1346
},
{
"epoch": 1.73,
"learning_rate": 1.5230466352660193e-06,
"loss": 1.7202,
"step": 1348
},
{
"epoch": 1.73,
"learning_rate": 1.5216318192582179e-06,
"loss": 1.787,
"step": 1350
},
{
"epoch": 1.73,
"learning_rate": 1.5202155673209682e-06,
"loss": 1.7842,
"step": 1352
},
{
"epoch": 1.73,
"learning_rate": 1.518797883352878e-06,
"loss": 1.7987,
"step": 1354
},
{
"epoch": 1.74,
"learning_rate": 1.5173787712564975e-06,
"loss": 1.7764,
"step": 1356
},
{
"epoch": 1.74,
"learning_rate": 1.5159582349383078e-06,
"loss": 1.7451,
"step": 1358
},
{
"epoch": 1.74,
"learning_rate": 1.5145362783087104e-06,
"loss": 1.7929,
"step": 1360
},
{
"epoch": 1.74,
"learning_rate": 1.5131129052820163e-06,
"loss": 1.7889,
"step": 1362
},
{
"epoch": 1.75,
"learning_rate": 1.5116881197764368e-06,
"loss": 1.804,
"step": 1364
},
{
"epoch": 1.75,
"learning_rate": 1.51026192571407e-06,
"loss": 1.7387,
"step": 1366
},
{
"epoch": 1.75,
"learning_rate": 1.5088343270208922e-06,
"loss": 1.7664,
"step": 1368
},
{
"epoch": 1.75,
"learning_rate": 1.5074053276267463e-06,
"loss": 1.7527,
"step": 1370
},
{
"epoch": 1.76,
"learning_rate": 1.5059749314653308e-06,
"loss": 1.7691,
"step": 1372
},
{
"epoch": 1.76,
"learning_rate": 1.5045431424741883e-06,
"loss": 1.8038,
"step": 1374
},
{
"epoch": 1.76,
"learning_rate": 1.5031099645946972e-06,
"loss": 1.8054,
"step": 1376
},
{
"epoch": 1.76,
"learning_rate": 1.5016754017720584e-06,
"loss": 1.7658,
"step": 1378
},
{
"epoch": 1.77,
"learning_rate": 1.5002394579552854e-06,
"loss": 1.7701,
"step": 1380
},
{
"epoch": 1.77,
"learning_rate": 1.4988021370971926e-06,
"loss": 1.7458,
"step": 1382
},
{
"epoch": 1.77,
"learning_rate": 1.4973634431543854e-06,
"loss": 1.7407,
"step": 1384
},
{
"epoch": 1.77,
"learning_rate": 1.4959233800872495e-06,
"loss": 1.7425,
"step": 1386
},
{
"epoch": 1.78,
"learning_rate": 1.4944819518599395e-06,
"loss": 1.7642,
"step": 1388
},
{
"epoch": 1.78,
"learning_rate": 1.4930391624403664e-06,
"loss": 1.7478,
"step": 1390
},
{
"epoch": 1.78,
"learning_rate": 1.4915950158001906e-06,
"loss": 1.7234,
"step": 1392
},
{
"epoch": 1.78,
"learning_rate": 1.4901495159148067e-06,
"loss": 1.736,
"step": 1394
},
{
"epoch": 1.79,
"learning_rate": 1.4887026667633355e-06,
"loss": 1.7748,
"step": 1396
},
{
"epoch": 1.79,
"learning_rate": 1.4872544723286115e-06,
"loss": 1.7398,
"step": 1398
},
{
"epoch": 1.79,
"learning_rate": 1.4858049365971726e-06,
"loss": 1.769,
"step": 1400
},
{
"epoch": 1.79,
"learning_rate": 1.4843540635592493e-06,
"loss": 1.7251,
"step": 1402
},
{
"epoch": 1.8,
"learning_rate": 1.4829018572087528e-06,
"loss": 1.7533,
"step": 1404
},
{
"epoch": 1.8,
"learning_rate": 1.481448321543265e-06,
"loss": 1.8421,
"step": 1406
},
{
"epoch": 1.8,
"learning_rate": 1.479993460564027e-06,
"loss": 1.744,
"step": 1408
},
{
"epoch": 1.8,
"learning_rate": 1.478537278275928e-06,
"loss": 1.7518,
"step": 1410
},
{
"epoch": 1.81,
"learning_rate": 1.4770797786874949e-06,
"loss": 1.716,
"step": 1412
},
{
"epoch": 1.81,
"learning_rate": 1.4756209658108806e-06,
"loss": 1.7626,
"step": 1414
},
{
"epoch": 1.81,
"learning_rate": 1.4741608436618524e-06,
"loss": 1.7311,
"step": 1416
},
{
"epoch": 1.82,
"learning_rate": 1.472699416259783e-06,
"loss": 1.7229,
"step": 1418
},
{
"epoch": 1.82,
"learning_rate": 1.4712366876276376e-06,
"loss": 1.7585,
"step": 1420
},
{
"epoch": 1.82,
"learning_rate": 1.4697726617919634e-06,
"loss": 1.7789,
"step": 1422
},
{
"epoch": 1.82,
"learning_rate": 1.468307342782878e-06,
"loss": 1.7205,
"step": 1424
},
{
"epoch": 1.83,
"learning_rate": 1.4668407346340599e-06,
"loss": 1.7622,
"step": 1426
},
{
"epoch": 1.83,
"learning_rate": 1.4653728413827348e-06,
"loss": 1.7567,
"step": 1428
},
{
"epoch": 1.83,
"learning_rate": 1.4639036670696675e-06,
"loss": 1.7166,
"step": 1430
},
{
"epoch": 1.83,
"learning_rate": 1.4624332157391485e-06,
"loss": 1.7641,
"step": 1432
},
{
"epoch": 1.84,
"learning_rate": 1.4609614914389835e-06,
"loss": 1.8119,
"step": 1434
},
{
"epoch": 1.84,
"learning_rate": 1.4594884982204828e-06,
"loss": 1.7252,
"step": 1436
},
{
"epoch": 1.84,
"learning_rate": 1.45801424013845e-06,
"loss": 1.7538,
"step": 1438
},
{
"epoch": 1.84,
"learning_rate": 1.4565387212511687e-06,
"loss": 1.7227,
"step": 1440
},
{
"epoch": 1.85,
"learning_rate": 1.4550619456203963e-06,
"loss": 1.7357,
"step": 1442
},
{
"epoch": 1.85,
"learning_rate": 1.4535839173113466e-06,
"loss": 1.7881,
"step": 1444
},
{
"epoch": 1.85,
"learning_rate": 1.452104640392684e-06,
"loss": 1.756,
"step": 1446
},
{
"epoch": 1.85,
"learning_rate": 1.4506241189365092e-06,
"loss": 1.7048,
"step": 1448
},
{
"epoch": 1.86,
"learning_rate": 1.4491423570183483e-06,
"loss": 1.7432,
"step": 1450
},
{
"epoch": 1.86,
"learning_rate": 1.447659358717143e-06,
"loss": 1.7477,
"step": 1452
},
{
"epoch": 1.86,
"learning_rate": 1.4461751281152382e-06,
"loss": 1.7584,
"step": 1454
},
{
"epoch": 1.86,
"learning_rate": 1.4446896692983703e-06,
"loss": 1.7921,
"step": 1456
},
{
"epoch": 1.87,
"learning_rate": 1.443202986355658e-06,
"loss": 1.7429,
"step": 1458
},
{
"epoch": 1.87,
"learning_rate": 1.4417150833795884e-06,
"loss": 1.7899,
"step": 1460
},
{
"epoch": 1.87,
"learning_rate": 1.440225964466008e-06,
"loss": 1.7643,
"step": 1462
},
{
"epoch": 1.87,
"learning_rate": 1.4387356337141103e-06,
"loss": 1.7784,
"step": 1464
},
{
"epoch": 1.88,
"learning_rate": 1.4372440952264246e-06,
"loss": 1.7917,
"step": 1466
},
{
"epoch": 1.88,
"learning_rate": 1.435751353108804e-06,
"loss": 1.7515,
"step": 1468
},
{
"epoch": 1.88,
"learning_rate": 1.4342574114704173e-06,
"loss": 1.7758,
"step": 1470
},
{
"epoch": 1.88,
"learning_rate": 1.432762274423732e-06,
"loss": 1.7614,
"step": 1472
},
{
"epoch": 1.89,
"learning_rate": 1.4312659460845092e-06,
"loss": 1.816,
"step": 1474
},
{
"epoch": 1.89,
"learning_rate": 1.4297684305717874e-06,
"loss": 1.7459,
"step": 1476
},
{
"epoch": 1.89,
"learning_rate": 1.428269732007874e-06,
"loss": 1.7816,
"step": 1478
},
{
"epoch": 1.89,
"learning_rate": 1.4267698545183335e-06,
"loss": 1.7005,
"step": 1480
},
{
"epoch": 1.9,
"learning_rate": 1.425268802231974e-06,
"loss": 1.7618,
"step": 1482
},
{
"epoch": 1.9,
"learning_rate": 1.4237665792808393e-06,
"loss": 1.7909,
"step": 1484
},
{
"epoch": 1.9,
"learning_rate": 1.4222631898001955e-06,
"loss": 1.8257,
"step": 1486
},
{
"epoch": 1.9,
"learning_rate": 1.4207586379285188e-06,
"loss": 1.7292,
"step": 1488
},
{
"epoch": 1.91,
"learning_rate": 1.419252927807486e-06,
"loss": 1.7532,
"step": 1490
},
{
"epoch": 1.91,
"learning_rate": 1.4177460635819626e-06,
"loss": 1.7359,
"step": 1492
},
{
"epoch": 1.91,
"learning_rate": 1.4162380493999899e-06,
"loss": 1.8038,
"step": 1494
},
{
"epoch": 1.91,
"learning_rate": 1.414728889412776e-06,
"loss": 1.776,
"step": 1496
},
{
"epoch": 1.92,
"learning_rate": 1.4132185877746826e-06,
"loss": 1.7683,
"step": 1498
},
{
"epoch": 1.92,
"learning_rate": 1.4117071486432144e-06,
"loss": 1.8102,
"step": 1500
},
{
"epoch": 1.92,
"learning_rate": 1.4101945761790063e-06,
"loss": 1.7829,
"step": 1502
},
{
"epoch": 1.93,
"learning_rate": 1.4086808745458143e-06,
"loss": 1.7969,
"step": 1504
},
{
"epoch": 1.93,
"learning_rate": 1.4071660479105022e-06,
"loss": 1.7397,
"step": 1506
},
{
"epoch": 1.93,
"learning_rate": 1.4056501004430306e-06,
"loss": 1.7806,
"step": 1508
},
{
"epoch": 1.93,
"learning_rate": 1.4041330363164456e-06,
"loss": 1.7545,
"step": 1510
},
{
"epoch": 1.94,
"learning_rate": 1.402614859706867e-06,
"loss": 1.796,
"step": 1512
},
{
"epoch": 1.94,
"learning_rate": 1.4010955747934774e-06,
"loss": 1.7703,
"step": 1514
},
{
"epoch": 1.94,
"learning_rate": 1.3995751857585102e-06,
"loss": 1.7464,
"step": 1516
},
{
"epoch": 1.94,
"learning_rate": 1.3980536967872377e-06,
"loss": 1.7461,
"step": 1518
},
{
"epoch": 1.95,
"learning_rate": 1.39653111206796e-06,
"loss": 1.7489,
"step": 1520
},
{
"epoch": 1.95,
"learning_rate": 1.395007435791995e-06,
"loss": 1.7645,
"step": 1522
},
{
"epoch": 1.95,
"learning_rate": 1.3934826721536642e-06,
"loss": 1.8076,
"step": 1524
},
{
"epoch": 1.95,
"learning_rate": 1.3919568253502813e-06,
"loss": 1.7259,
"step": 1526
},
{
"epoch": 1.96,
"learning_rate": 1.3904298995821441e-06,
"loss": 1.7449,
"step": 1528
},
{
"epoch": 1.96,
"learning_rate": 1.3889018990525194e-06,
"loss": 1.8062,
"step": 1530
},
{
"epoch": 1.96,
"learning_rate": 1.3873728279676316e-06,
"loss": 1.7208,
"step": 1532
},
{
"epoch": 1.96,
"learning_rate": 1.3858426905366536e-06,
"loss": 1.7659,
"step": 1534
},
{
"epoch": 1.97,
"learning_rate": 1.3843114909716931e-06,
"loss": 1.8135,
"step": 1536
},
{
"epoch": 1.97,
"learning_rate": 1.3827792334877811e-06,
"loss": 1.7369,
"step": 1538
},
{
"epoch": 1.97,
"learning_rate": 1.3812459223028623e-06,
"loss": 1.7652,
"step": 1540
},
{
"epoch": 1.97,
"learning_rate": 1.3797115616377796e-06,
"loss": 1.801,
"step": 1542
},
{
"epoch": 1.98,
"learning_rate": 1.3781761557162676e-06,
"loss": 1.7819,
"step": 1544
},
{
"epoch": 1.98,
"learning_rate": 1.376639708764936e-06,
"loss": 1.741,
"step": 1546
},
{
"epoch": 1.98,
"learning_rate": 1.3751022250132615e-06,
"loss": 1.7663,
"step": 1548
},
{
"epoch": 1.98,
"learning_rate": 1.3735637086935744e-06,
"loss": 1.7655,
"step": 1550
},
{
"epoch": 1.99,
"learning_rate": 1.3720241640410476e-06,
"loss": 1.7601,
"step": 1552
},
{
"epoch": 1.99,
"learning_rate": 1.3704835952936845e-06,
"loss": 1.797,
"step": 1554
},
{
"epoch": 1.99,
"learning_rate": 1.3689420066923076e-06,
"loss": 1.7433,
"step": 1556
},
{
"epoch": 1.99,
"learning_rate": 1.3673994024805474e-06,
"loss": 1.7393,
"step": 1558
},
{
"epoch": 2.0,
"learning_rate": 1.365855786904829e-06,
"loss": 1.794,
"step": 1560
},
{
"epoch": 2.0,
"learning_rate": 1.3643111642143631e-06,
"loss": 1.7165,
"step": 1562
},
{
"epoch": 2.0,
"learning_rate": 1.3627655386611317e-06,
"loss": 1.7437,
"step": 1564
},
{
"epoch": 2.0,
"learning_rate": 1.3612189144998767e-06,
"loss": 1.7479,
"step": 1566
},
{
"epoch": 2.01,
"learning_rate": 1.359671295988091e-06,
"loss": 1.7848,
"step": 1568
},
{
"epoch": 2.01,
"learning_rate": 1.3581226873860035e-06,
"loss": 1.7391,
"step": 1570
},
{
"epoch": 2.01,
"learning_rate": 1.3565730929565677e-06,
"loss": 1.7336,
"step": 1572
},
{
"epoch": 2.01,
"learning_rate": 1.355022516965453e-06,
"loss": 1.7284,
"step": 1574
},
{
"epoch": 2.02,
"learning_rate": 1.3534709636810287e-06,
"loss": 1.7172,
"step": 1576
},
{
"epoch": 2.02,
"learning_rate": 1.351918437374356e-06,
"loss": 1.6931,
"step": 1578
},
{
"epoch": 2.02,
"learning_rate": 1.3503649423191734e-06,
"loss": 1.6935,
"step": 1580
},
{
"epoch": 2.02,
"learning_rate": 1.3488104827918867e-06,
"loss": 1.7356,
"step": 1582
},
{
"epoch": 2.03,
"learning_rate": 1.3472550630715569e-06,
"loss": 1.7074,
"step": 1584
},
{
"epoch": 2.03,
"learning_rate": 1.3456986874398874e-06,
"loss": 1.7238,
"step": 1586
},
{
"epoch": 2.03,
"learning_rate": 1.3441413601812139e-06,
"loss": 1.7279,
"step": 1588
},
{
"epoch": 2.04,
"learning_rate": 1.342583085582491e-06,
"loss": 1.7182,
"step": 1590
},
{
"epoch": 2.04,
"learning_rate": 1.3410238679332815e-06,
"loss": 1.7343,
"step": 1592
},
{
"epoch": 2.04,
"learning_rate": 1.3394637115257443e-06,
"loss": 1.7436,
"step": 1594
},
{
"epoch": 2.04,
"learning_rate": 1.3379026206546217e-06,
"loss": 1.7674,
"step": 1596
},
{
"epoch": 2.05,
"learning_rate": 1.3363405996172295e-06,
"loss": 1.7503,
"step": 1598
},
{
"epoch": 2.05,
"learning_rate": 1.3347776527134429e-06,
"loss": 1.6799,
"step": 1600
},
{
"epoch": 2.05,
"learning_rate": 1.3332137842456866e-06,
"loss": 1.7075,
"step": 1602
},
{
"epoch": 2.05,
"learning_rate": 1.3316489985189222e-06,
"loss": 1.6781,
"step": 1604
},
{
"epoch": 2.06,
"learning_rate": 1.3300832998406354e-06,
"loss": 1.7264,
"step": 1606
},
{
"epoch": 2.06,
"learning_rate": 1.3285166925208258e-06,
"loss": 1.7209,
"step": 1608
},
{
"epoch": 2.06,
"learning_rate": 1.3269491808719942e-06,
"loss": 1.7386,
"step": 1610
},
{
"epoch": 2.06,
"learning_rate": 1.3253807692091308e-06,
"loss": 1.7068,
"step": 1612
},
{
"epoch": 2.07,
"learning_rate": 1.323811461849703e-06,
"loss": 1.7191,
"step": 1614
},
{
"epoch": 2.07,
"learning_rate": 1.3222412631136444e-06,
"loss": 1.719,
"step": 1616
},
{
"epoch": 2.07,
"learning_rate": 1.3206701773233415e-06,
"loss": 1.7426,
"step": 1618
},
{
"epoch": 2.07,
"learning_rate": 1.3190982088036236e-06,
"loss": 1.7533,
"step": 1620
},
{
"epoch": 2.08,
"learning_rate": 1.3175253618817495e-06,
"loss": 1.7106,
"step": 1622
},
{
"epoch": 2.08,
"learning_rate": 1.3159516408873957e-06,
"loss": 1.7489,
"step": 1624
},
{
"epoch": 2.08,
"learning_rate": 1.3143770501526455e-06,
"loss": 1.7464,
"step": 1626
},
{
"epoch": 2.08,
"learning_rate": 1.312801594011976e-06,
"loss": 1.74,
"step": 1628
},
{
"epoch": 2.09,
"learning_rate": 1.3112252768022465e-06,
"loss": 1.722,
"step": 1630
},
{
"epoch": 2.09,
"learning_rate": 1.3096481028626869e-06,
"loss": 1.7171,
"step": 1632
},
{
"epoch": 2.09,
"learning_rate": 1.3080700765348853e-06,
"loss": 1.7635,
"step": 1634
},
{
"epoch": 2.09,
"learning_rate": 1.3064912021627758e-06,
"loss": 1.7649,
"step": 1636
},
{
"epoch": 2.1,
"learning_rate": 1.304911484092628e-06,
"loss": 1.7239,
"step": 1638
},
{
"epoch": 2.1,
"learning_rate": 1.3033309266730331e-06,
"loss": 1.7374,
"step": 1640
},
{
"epoch": 2.1,
"learning_rate": 1.3017495342548933e-06,
"loss": 1.7415,
"step": 1642
},
{
"epoch": 2.1,
"learning_rate": 1.300167311191409e-06,
"loss": 1.7388,
"step": 1644
},
{
"epoch": 2.11,
"learning_rate": 1.2985842618380677e-06,
"loss": 1.7479,
"step": 1646
},
{
"epoch": 2.11,
"learning_rate": 1.2970003905526303e-06,
"loss": 1.6993,
"step": 1648
},
{
"epoch": 2.11,
"learning_rate": 1.2954157016951223e-06,
"loss": 1.735,
"step": 1650
},
{
"epoch": 2.11,
"learning_rate": 1.2938301996278176e-06,
"loss": 1.7448,
"step": 1652
},
{
"epoch": 2.12,
"learning_rate": 1.2922438887152302e-06,
"loss": 1.7428,
"step": 1654
},
{
"epoch": 2.12,
"learning_rate": 1.2906567733241e-06,
"loss": 1.7095,
"step": 1656
},
{
"epoch": 2.12,
"learning_rate": 1.2890688578233817e-06,
"loss": 1.7486,
"step": 1658
},
{
"epoch": 2.12,
"learning_rate": 1.2874801465842324e-06,
"loss": 1.7704,
"step": 1660
},
{
"epoch": 2.13,
"learning_rate": 1.2858906439799994e-06,
"loss": 1.7425,
"step": 1662
},
{
"epoch": 2.13,
"learning_rate": 1.2843003543862088e-06,
"loss": 1.7165,
"step": 1664
},
{
"epoch": 2.13,
"learning_rate": 1.2827092821805533e-06,
"loss": 1.6988,
"step": 1666
},
{
"epoch": 2.14,
"learning_rate": 1.2811174317428796e-06,
"loss": 1.7634,
"step": 1668
},
{
"epoch": 2.14,
"learning_rate": 1.2795248074551763e-06,
"loss": 1.7572,
"step": 1670
},
{
"epoch": 2.14,
"learning_rate": 1.2779314137015635e-06,
"loss": 1.7123,
"step": 1672
},
{
"epoch": 2.14,
"learning_rate": 1.2763372548682778e-06,
"loss": 1.7608,
"step": 1674
},
{
"epoch": 2.15,
"learning_rate": 1.2747423353436633e-06,
"loss": 1.7312,
"step": 1676
},
{
"epoch": 2.15,
"learning_rate": 1.273146659518157e-06,
"loss": 1.7067,
"step": 1678
},
{
"epoch": 2.15,
"learning_rate": 1.2715502317842788e-06,
"loss": 1.7271,
"step": 1680
},
{
"epoch": 2.15,
"learning_rate": 1.269953056536618e-06,
"loss": 1.7779,
"step": 1682
},
{
"epoch": 2.16,
"learning_rate": 1.268355138171821e-06,
"loss": 1.7377,
"step": 1684
},
{
"epoch": 2.16,
"learning_rate": 1.2667564810885807e-06,
"loss": 1.7416,
"step": 1686
},
{
"epoch": 2.16,
"learning_rate": 1.265157089687624e-06,
"loss": 1.7313,
"step": 1688
},
{
"epoch": 2.16,
"learning_rate": 1.2635569683716974e-06,
"loss": 1.7499,
"step": 1690
},
{
"epoch": 2.17,
"learning_rate": 1.2619561215455582e-06,
"loss": 1.719,
"step": 1692
},
{
"epoch": 2.17,
"learning_rate": 1.2603545536159603e-06,
"loss": 1.7399,
"step": 1694
},
{
"epoch": 2.17,
"learning_rate": 1.2587522689916426e-06,
"loss": 1.7098,
"step": 1696
},
{
"epoch": 2.17,
"learning_rate": 1.2571492720833173e-06,
"loss": 1.7184,
"step": 1698
},
{
"epoch": 2.18,
"learning_rate": 1.255545567303657e-06,
"loss": 1.7457,
"step": 1700
},
{
"epoch": 2.18,
"learning_rate": 1.2539411590672829e-06,
"loss": 1.7129,
"step": 1702
},
{
"epoch": 2.18,
"learning_rate": 1.2523360517907523e-06,
"loss": 1.7161,
"step": 1704
},
{
"epoch": 2.18,
"learning_rate": 1.250730249892548e-06,
"loss": 1.7198,
"step": 1706
},
{
"epoch": 2.19,
"learning_rate": 1.2491237577930633e-06,
"loss": 1.7029,
"step": 1708
},
{
"epoch": 2.19,
"learning_rate": 1.247516579914593e-06,
"loss": 1.7357,
"step": 1710
},
{
"epoch": 2.19,
"learning_rate": 1.2459087206813187e-06,
"loss": 1.7109,
"step": 1712
},
{
"epoch": 2.19,
"learning_rate": 1.2443001845192976e-06,
"loss": 1.7225,
"step": 1714
},
{
"epoch": 2.2,
"learning_rate": 1.2426909758564513e-06,
"loss": 1.7329,
"step": 1716
},
{
"epoch": 2.2,
"learning_rate": 1.2410810991225513e-06,
"loss": 1.6763,
"step": 1718
},
{
"epoch": 2.2,
"learning_rate": 1.239470558749209e-06,
"loss": 1.7642,
"step": 1720
},
{
"epoch": 2.2,
"learning_rate": 1.2378593591698626e-06,
"loss": 1.7988,
"step": 1722
},
{
"epoch": 2.21,
"learning_rate": 1.2362475048197645e-06,
"loss": 1.7672,
"step": 1724
},
{
"epoch": 2.21,
"learning_rate": 1.2346350001359703e-06,
"loss": 1.7281,
"step": 1726
},
{
"epoch": 2.21,
"learning_rate": 1.2330218495573246e-06,
"loss": 1.7517,
"step": 1728
},
{
"epoch": 2.21,
"learning_rate": 1.231408057524451e-06,
"loss": 1.7828,
"step": 1730
},
{
"epoch": 2.22,
"learning_rate": 1.2297936284797392e-06,
"loss": 1.7062,
"step": 1732
},
{
"epoch": 2.22,
"learning_rate": 1.228178566867331e-06,
"loss": 1.6968,
"step": 1734
},
{
"epoch": 2.22,
"learning_rate": 1.2265628771331108e-06,
"loss": 1.7087,
"step": 1736
},
{
"epoch": 2.22,
"learning_rate": 1.2249465637246915e-06,
"loss": 1.7666,
"step": 1738
},
{
"epoch": 2.23,
"learning_rate": 1.2233296310914025e-06,
"loss": 1.7184,
"step": 1740
},
{
"epoch": 2.23,
"learning_rate": 1.2217120836842794e-06,
"loss": 1.7523,
"step": 1742
},
{
"epoch": 2.23,
"learning_rate": 1.2200939259560476e-06,
"loss": 1.7136,
"step": 1744
},
{
"epoch": 2.23,
"learning_rate": 1.2184751623611147e-06,
"loss": 1.7032,
"step": 1746
},
{
"epoch": 2.24,
"learning_rate": 1.2168557973555554e-06,
"loss": 1.7385,
"step": 1748
},
{
"epoch": 2.24,
"learning_rate": 1.215235835397099e-06,
"loss": 1.7109,
"step": 1750
},
{
"epoch": 2.24,
"learning_rate": 1.21361528094512e-06,
"loss": 1.7611,
"step": 1752
},
{
"epoch": 2.25,
"learning_rate": 1.2119941384606226e-06,
"loss": 1.7091,
"step": 1754
},
{
"epoch": 2.25,
"learning_rate": 1.2103724124062293e-06,
"loss": 1.7502,
"step": 1756
},
{
"epoch": 2.25,
"learning_rate": 1.2087501072461706e-06,
"loss": 1.7393,
"step": 1758
},
{
"epoch": 2.25,
"learning_rate": 1.207127227446269e-06,
"loss": 1.77,
"step": 1760
},
{
"epoch": 2.26,
"learning_rate": 1.2055037774739316e-06,
"loss": 1.7318,
"step": 1762
},
{
"epoch": 2.26,
"learning_rate": 1.2038797617981324e-06,
"loss": 1.7433,
"step": 1764
},
{
"epoch": 2.26,
"learning_rate": 1.2022551848894043e-06,
"loss": 1.748,
"step": 1766
},
{
"epoch": 2.26,
"learning_rate": 1.2006300512198242e-06,
"loss": 1.6947,
"step": 1768
},
{
"epoch": 2.27,
"learning_rate": 1.1990043652630022e-06,
"loss": 1.712,
"step": 1770
},
{
"epoch": 2.27,
"learning_rate": 1.197378131494069e-06,
"loss": 1.6389,
"step": 1772
},
{
"epoch": 2.27,
"learning_rate": 1.1957513543896622e-06,
"loss": 1.7434,
"step": 1774
},
{
"epoch": 2.27,
"learning_rate": 1.194124038427916e-06,
"loss": 1.6982,
"step": 1776
},
{
"epoch": 2.28,
"learning_rate": 1.1924961880884478e-06,
"loss": 1.7432,
"step": 1778
},
{
"epoch": 2.28,
"learning_rate": 1.1908678078523457e-06,
"loss": 1.7796,
"step": 1780
},
{
"epoch": 2.28,
"learning_rate": 1.189238902202157e-06,
"loss": 1.7378,
"step": 1782
},
{
"epoch": 2.28,
"learning_rate": 1.1876094756218745e-06,
"loss": 1.6951,
"step": 1784
},
{
"epoch": 2.29,
"learning_rate": 1.1859795325969262e-06,
"loss": 1.7376,
"step": 1786
},
{
"epoch": 2.29,
"learning_rate": 1.1843490776141602e-06,
"loss": 1.8035,
"step": 1788
},
{
"epoch": 2.29,
"learning_rate": 1.1827181151618355e-06,
"loss": 1.7184,
"step": 1790
},
{
"epoch": 2.29,
"learning_rate": 1.181086649729607e-06,
"loss": 1.7488,
"step": 1792
},
{
"epoch": 2.3,
"learning_rate": 1.179454685808514e-06,
"loss": 1.7731,
"step": 1794
},
{
"epoch": 2.3,
"learning_rate": 1.1778222278909698e-06,
"loss": 1.7524,
"step": 1796
},
{
"epoch": 2.3,
"learning_rate": 1.1761892804707453e-06,
"loss": 1.7188,
"step": 1798
},
{
"epoch": 2.3,
"learning_rate": 1.1745558480429601e-06,
"loss": 1.6999,
"step": 1800
},
{
"epoch": 2.31,
"learning_rate": 1.1729219351040685e-06,
"loss": 1.7363,
"step": 1802
},
{
"epoch": 2.31,
"learning_rate": 1.1712875461518476e-06,
"loss": 1.736,
"step": 1804
},
{
"epoch": 2.31,
"learning_rate": 1.1696526856853856e-06,
"loss": 1.7465,
"step": 1806
},
{
"epoch": 2.31,
"learning_rate": 1.1680173582050677e-06,
"loss": 1.7033,
"step": 1808
},
{
"epoch": 2.32,
"learning_rate": 1.1663815682125646e-06,
"loss": 1.6965,
"step": 1810
},
{
"epoch": 2.32,
"learning_rate": 1.164745320210821e-06,
"loss": 1.7208,
"step": 1812
},
{
"epoch": 2.32,
"learning_rate": 1.1631086187040418e-06,
"loss": 1.6872,
"step": 1814
},
{
"epoch": 2.32,
"learning_rate": 1.1614714681976806e-06,
"loss": 1.7571,
"step": 1816
},
{
"epoch": 2.33,
"learning_rate": 1.159833873198427e-06,
"loss": 1.7109,
"step": 1818
},
{
"epoch": 2.33,
"learning_rate": 1.1581958382141938e-06,
"loss": 1.7113,
"step": 1820
},
{
"epoch": 2.33,
"learning_rate": 1.156557367754105e-06,
"loss": 1.7191,
"step": 1822
},
{
"epoch": 2.33,
"learning_rate": 1.154918466328484e-06,
"loss": 1.7137,
"step": 1824
},
{
"epoch": 2.34,
"learning_rate": 1.1532791384488404e-06,
"loss": 1.7036,
"step": 1826
},
{
"epoch": 2.34,
"learning_rate": 1.1516393886278567e-06,
"loss": 1.7364,
"step": 1828
},
{
"epoch": 2.34,
"learning_rate": 1.149999221379378e-06,
"loss": 1.7544,
"step": 1830
},
{
"epoch": 2.34,
"learning_rate": 1.1483586412183982e-06,
"loss": 1.6635,
"step": 1832
},
{
"epoch": 2.35,
"learning_rate": 1.1467176526610479e-06,
"loss": 1.8124,
"step": 1834
},
{
"epoch": 2.35,
"learning_rate": 1.1450762602245816e-06,
"loss": 1.7626,
"step": 1836
},
{
"epoch": 2.35,
"learning_rate": 1.1434344684273656e-06,
"loss": 1.7463,
"step": 1838
},
{
"epoch": 2.36,
"learning_rate": 1.1417922817888666e-06,
"loss": 1.6883,
"step": 1840
},
{
"epoch": 2.36,
"learning_rate": 1.1401497048296361e-06,
"loss": 1.7541,
"step": 1842
},
{
"epoch": 2.36,
"learning_rate": 1.138506742071302e-06,
"loss": 1.7492,
"step": 1844
},
{
"epoch": 2.36,
"learning_rate": 1.136863398036554e-06,
"loss": 1.7525,
"step": 1846
},
{
"epoch": 2.37,
"learning_rate": 1.13521967724913e-06,
"loss": 1.7138,
"step": 1848
},
{
"epoch": 2.37,
"learning_rate": 1.1335755842338065e-06,
"loss": 1.7343,
"step": 1850
},
{
"epoch": 2.37,
"learning_rate": 1.1319311235163837e-06,
"loss": 1.6761,
"step": 1852
},
{
"epoch": 2.37,
"learning_rate": 1.1302862996236743e-06,
"loss": 1.7159,
"step": 1854
},
{
"epoch": 2.38,
"learning_rate": 1.128641117083491e-06,
"loss": 1.7464,
"step": 1856
},
{
"epoch": 2.38,
"learning_rate": 1.1269955804246337e-06,
"loss": 1.7493,
"step": 1858
},
{
"epoch": 2.38,
"learning_rate": 1.1253496941768767e-06,
"loss": 1.7207,
"step": 1860
},
{
"epoch": 2.38,
"learning_rate": 1.1237034628709572e-06,
"loss": 1.6976,
"step": 1862
},
{
"epoch": 2.39,
"learning_rate": 1.1220568910385614e-06,
"loss": 1.7203,
"step": 1864
},
{
"epoch": 2.39,
"learning_rate": 1.1204099832123137e-06,
"loss": 1.6974,
"step": 1866
},
{
"epoch": 2.39,
"learning_rate": 1.1187627439257636e-06,
"loss": 1.729,
"step": 1868
},
{
"epoch": 2.39,
"learning_rate": 1.117115177713372e-06,
"loss": 1.6943,
"step": 1870
},
{
"epoch": 2.4,
"learning_rate": 1.1154672891105005e-06,
"loss": 1.7319,
"step": 1872
},
{
"epoch": 2.4,
"learning_rate": 1.113819082653399e-06,
"loss": 1.7725,
"step": 1874
},
{
"epoch": 2.4,
"learning_rate": 1.1121705628791893e-06,
"loss": 1.7467,
"step": 1876
},
{
"epoch": 2.4,
"learning_rate": 1.1105217343258596e-06,
"loss": 1.7181,
"step": 1878
},
{
"epoch": 2.41,
"learning_rate": 1.1088726015322456e-06,
"loss": 1.7646,
"step": 1880
},
{
"epoch": 2.41,
"learning_rate": 1.107223169038021e-06,
"loss": 1.7202,
"step": 1882
},
{
"epoch": 2.41,
"learning_rate": 1.1055734413836853e-06,
"loss": 1.7466,
"step": 1884
},
{
"epoch": 2.41,
"learning_rate": 1.103923423110549e-06,
"loss": 1.7037,
"step": 1886
},
{
"epoch": 2.42,
"learning_rate": 1.102273118760724e-06,
"loss": 1.7446,
"step": 1888
},
{
"epoch": 2.42,
"learning_rate": 1.1006225328771097e-06,
"loss": 1.7673,
"step": 1890
},
{
"epoch": 2.42,
"learning_rate": 1.098971670003379e-06,
"loss": 1.7546,
"step": 1892
},
{
"epoch": 2.42,
"learning_rate": 1.097320534683969e-06,
"loss": 1.7989,
"step": 1894
},
{
"epoch": 2.43,
"learning_rate": 1.0956691314640655e-06,
"loss": 1.7133,
"step": 1896
},
{
"epoch": 2.43,
"learning_rate": 1.0940174648895926e-06,
"loss": 1.7478,
"step": 1898
},
{
"epoch": 2.43,
"learning_rate": 1.0923655395071995e-06,
"loss": 1.7722,
"step": 1900
},
{
"epoch": 2.43,
"learning_rate": 1.0907133598642466e-06,
"loss": 1.7397,
"step": 1902
},
{
"epoch": 2.44,
"learning_rate": 1.0890609305087956e-06,
"loss": 1.7077,
"step": 1904
},
{
"epoch": 2.44,
"learning_rate": 1.0874082559895949e-06,
"loss": 1.7415,
"step": 1906
},
{
"epoch": 2.44,
"learning_rate": 1.0857553408560679e-06,
"loss": 1.7622,
"step": 1908
},
{
"epoch": 2.44,
"learning_rate": 1.0841021896583002e-06,
"loss": 1.7106,
"step": 1910
},
{
"epoch": 2.45,
"learning_rate": 1.0824488069470277e-06,
"loss": 1.762,
"step": 1912
},
{
"epoch": 2.45,
"learning_rate": 1.0807951972736231e-06,
"loss": 1.7022,
"step": 1914
},
{
"epoch": 2.45,
"learning_rate": 1.0791413651900843e-06,
"loss": 1.7188,
"step": 1916
},
{
"epoch": 2.46,
"learning_rate": 1.0774873152490208e-06,
"loss": 1.7748,
"step": 1918
},
{
"epoch": 2.46,
"learning_rate": 1.0758330520036422e-06,
"loss": 1.7392,
"step": 1920
},
{
"epoch": 2.46,
"learning_rate": 1.074178580007746e-06,
"loss": 1.7114,
"step": 1922
},
{
"epoch": 2.46,
"learning_rate": 1.0725239038157028e-06,
"loss": 1.7176,
"step": 1924
},
{
"epoch": 2.47,
"learning_rate": 1.0708690279824466e-06,
"loss": 1.739,
"step": 1926
},
{
"epoch": 2.47,
"learning_rate": 1.0692139570634605e-06,
"loss": 1.7366,
"step": 1928
},
{
"epoch": 2.47,
"learning_rate": 1.0675586956147646e-06,
"loss": 1.7445,
"step": 1930
},
{
"epoch": 2.47,
"learning_rate": 1.0659032481929035e-06,
"loss": 1.7299,
"step": 1932
},
{
"epoch": 2.48,
"learning_rate": 1.0642476193549337e-06,
"loss": 1.6859,
"step": 1934
},
{
"epoch": 2.48,
"learning_rate": 1.062591813658411e-06,
"loss": 1.7757,
"step": 1936
},
{
"epoch": 2.48,
"learning_rate": 1.0609358356613787e-06,
"loss": 1.767,
"step": 1938
},
{
"epoch": 2.48,
"learning_rate": 1.0592796899223535e-06,
"loss": 1.6344,
"step": 1940
},
{
"epoch": 2.49,
"learning_rate": 1.0576233810003143e-06,
"loss": 1.7609,
"step": 1942
},
{
"epoch": 2.49,
"learning_rate": 1.0559669134546895e-06,
"loss": 1.7197,
"step": 1944
},
{
"epoch": 2.49,
"learning_rate": 1.0543102918453433e-06,
"loss": 1.7323,
"step": 1946
},
{
"epoch": 2.49,
"learning_rate": 1.0526535207325648e-06,
"loss": 1.7553,
"step": 1948
},
{
"epoch": 2.5,
"learning_rate": 1.0509966046770543e-06,
"loss": 1.7385,
"step": 1950
},
{
"epoch": 2.5,
"learning_rate": 1.0493395482399112e-06,
"loss": 1.7899,
"step": 1952
},
{
"epoch": 2.5,
"learning_rate": 1.0476823559826213e-06,
"loss": 1.7538,
"step": 1954
},
{
"epoch": 2.5,
"learning_rate": 1.0460250324670446e-06,
"loss": 1.7577,
"step": 1956
},
{
"epoch": 2.51,
"learning_rate": 1.0443675822554014e-06,
"loss": 1.6928,
"step": 1958
},
{
"epoch": 2.51,
"learning_rate": 1.042710009910262e-06,
"loss": 1.7158,
"step": 1960
},
{
"epoch": 2.51,
"learning_rate": 1.041052319994532e-06,
"loss": 1.691,
"step": 1962
},
{
"epoch": 2.51,
"learning_rate": 1.0393945170714414e-06,
"loss": 1.7055,
"step": 1964
},
{
"epoch": 2.52,
"learning_rate": 1.0377366057045306e-06,
"loss": 1.7379,
"step": 1966
},
{
"epoch": 2.52,
"learning_rate": 1.0360785904576392e-06,
"loss": 1.6803,
"step": 1968
},
{
"epoch": 2.52,
"learning_rate": 1.0344204758948918e-06,
"loss": 1.7301,
"step": 1970
},
{
"epoch": 2.52,
"learning_rate": 1.0327622665806875e-06,
"loss": 1.7539,
"step": 1972
},
{
"epoch": 2.53,
"learning_rate": 1.0311039670796853e-06,
"loss": 1.7462,
"step": 1974
},
{
"epoch": 2.53,
"learning_rate": 1.029445581956793e-06,
"loss": 1.6892,
"step": 1976
},
{
"epoch": 2.53,
"learning_rate": 1.0277871157771545e-06,
"loss": 1.7595,
"step": 1978
},
{
"epoch": 2.53,
"learning_rate": 1.0261285731061351e-06,
"loss": 1.74,
"step": 1980
},
{
"epoch": 2.54,
"learning_rate": 1.0244699585093128e-06,
"loss": 1.7685,
"step": 1982
},
{
"epoch": 2.54,
"learning_rate": 1.0228112765524626e-06,
"loss": 1.7326,
"step": 1984
},
{
"epoch": 2.54,
"learning_rate": 1.0211525318015445e-06,
"loss": 1.7139,
"step": 1986
},
{
"epoch": 2.54,
"learning_rate": 1.0194937288226925e-06,
"loss": 1.7322,
"step": 1988
},
{
"epoch": 2.55,
"learning_rate": 1.017834872182199e-06,
"loss": 1.7564,
"step": 1990
},
{
"epoch": 2.55,
"learning_rate": 1.0161759664465066e-06,
"loss": 1.7295,
"step": 1992
},
{
"epoch": 2.55,
"learning_rate": 1.0145170161821914e-06,
"loss": 1.7107,
"step": 1994
},
{
"epoch": 2.55,
"learning_rate": 1.012858025955952e-06,
"loss": 1.7854,
"step": 1996
},
{
"epoch": 2.56,
"learning_rate": 1.011199000334598e-06,
"loss": 1.7763,
"step": 1998
},
{
"epoch": 2.56,
"learning_rate": 1.009539943885036e-06,
"loss": 1.7594,
"step": 2000
},
{
"epoch": 2.56,
"learning_rate": 1.007880861174257e-06,
"loss": 1.7608,
"step": 2002
},
{
"epoch": 2.57,
"learning_rate": 1.0062217567693246e-06,
"loss": 1.6912,
"step": 2004
},
{
"epoch": 2.57,
"learning_rate": 1.0045626352373619e-06,
"loss": 1.7566,
"step": 2006
},
{
"epoch": 2.57,
"learning_rate": 1.003733069475984e-06,
"loss": 1.7145,
"step": 2008
},
{
"epoch": 2.57,
"learning_rate": 1.0029035011455402e-06,
"loss": 1.7116,
"step": 2010
},
{
"epoch": 2.58,
"learning_rate": 1.0012443590610644e-06,
"loss": 1.7049,
"step": 2012
},
{
"epoch": 2.58,
"learning_rate": 9.99585213551161e-07,
"loss": 1.7214,
"step": 2014
},
{
"epoch": 2.58,
"learning_rate": 9.979260691830673e-07,
"loss": 1.8027,
"step": 2016
},
{
"epoch": 2.58,
"learning_rate": 9.962669305240163e-07,
"loss": 1.6745,
"step": 2018
},
{
"epoch": 2.59,
"learning_rate": 9.946078021412253e-07,
"loss": 1.7306,
"step": 2020
},
{
"epoch": 2.59,
"learning_rate": 9.929486886018843e-07,
"loss": 1.7501,
"step": 2022
},
{
"epoch": 2.59,
"learning_rate": 9.912895944731415e-07,
"loss": 1.7343,
"step": 2024
},
{
"epoch": 2.59,
"learning_rate": 9.896305243220923e-07,
"loss": 1.7327,
"step": 2026
},
{
"epoch": 2.6,
"learning_rate": 9.879714827157653e-07,
"loss": 1.7665,
"step": 2028
},
{
"epoch": 2.6,
"learning_rate": 9.863124742211109e-07,
"loss": 1.7325,
"step": 2030
},
{
"epoch": 2.6,
"learning_rate": 9.84653503404989e-07,
"loss": 1.707,
"step": 2032
},
{
"epoch": 2.6,
"learning_rate": 9.829945748341553e-07,
"loss": 1.7643,
"step": 2034
},
{
"epoch": 2.61,
"learning_rate": 9.813356930752487e-07,
"loss": 1.7248,
"step": 2036
},
{
"epoch": 2.61,
"learning_rate": 9.796768626947797e-07,
"loss": 1.73,
"step": 2038
},
{
"epoch": 2.61,
"learning_rate": 9.780180882591175e-07,
"loss": 1.7406,
"step": 2040
},
{
"epoch": 2.61,
"learning_rate": 9.763593743344771e-07,
"loss": 1.6941,
"step": 2042
},
{
"epoch": 2.62,
"learning_rate": 9.747007254869069e-07,
"loss": 1.7106,
"step": 2044
},
{
"epoch": 2.62,
"learning_rate": 9.730421462822767e-07,
"loss": 1.7051,
"step": 2046
},
{
"epoch": 2.62,
"learning_rate": 9.713836412862634e-07,
"loss": 1.7729,
"step": 2048
},
{
"epoch": 2.62,
"learning_rate": 9.697252150643407e-07,
"loss": 1.7284,
"step": 2050
},
{
"epoch": 2.63,
"learning_rate": 9.68066872181765e-07,
"loss": 1.7668,
"step": 2052
},
{
"epoch": 2.63,
"learning_rate": 9.664086172035634e-07,
"loss": 1.7332,
"step": 2054
},
{
"epoch": 2.63,
"learning_rate": 9.647504546945216e-07,
"loss": 1.7335,
"step": 2056
},
{
"epoch": 2.63,
"learning_rate": 9.630923892191689e-07,
"loss": 1.7109,
"step": 2058
},
{
"epoch": 2.64,
"learning_rate": 9.614344253417698e-07,
"loss": 1.7278,
"step": 2060
},
{
"epoch": 2.64,
"learning_rate": 9.597765676263073e-07,
"loss": 1.7762,
"step": 2062
},
{
"epoch": 2.64,
"learning_rate": 9.581188206364735e-07,
"loss": 1.7353,
"step": 2064
},
{
"epoch": 2.64,
"learning_rate": 9.564611889356554e-07,
"loss": 1.7294,
"step": 2066
},
{
"epoch": 2.65,
"learning_rate": 9.548036770869215e-07,
"loss": 1.722,
"step": 2068
},
{
"epoch": 2.65,
"learning_rate": 9.531462896530116e-07,
"loss": 1.7403,
"step": 2070
},
{
"epoch": 2.65,
"learning_rate": 9.514890311963228e-07,
"loss": 1.7656,
"step": 2072
},
{
"epoch": 2.65,
"learning_rate": 9.498319062788968e-07,
"loss": 1.7529,
"step": 2074
},
{
"epoch": 2.66,
"learning_rate": 9.481749194624086e-07,
"loss": 1.737,
"step": 2076
},
{
"epoch": 2.66,
"learning_rate": 9.465180753081513e-07,
"loss": 1.7457,
"step": 2078
},
{
"epoch": 2.66,
"learning_rate": 9.448613783770268e-07,
"loss": 1.7509,
"step": 2080
},
{
"epoch": 2.66,
"learning_rate": 9.432048332295313e-07,
"loss": 1.7186,
"step": 2082
},
{
"epoch": 2.67,
"learning_rate": 9.41548444425743e-07,
"loss": 1.7622,
"step": 2084
},
{
"epoch": 2.67,
"learning_rate": 9.398922165253104e-07,
"loss": 1.7623,
"step": 2086
},
{
"epoch": 2.67,
"learning_rate": 9.382361540874379e-07,
"loss": 1.7475,
"step": 2088
},
{
"epoch": 2.68,
"learning_rate": 9.365802616708749e-07,
"loss": 1.7038,
"step": 2090
},
{
"epoch": 2.68,
"learning_rate": 9.349245438339034e-07,
"loss": 1.7247,
"step": 2092
},
{
"epoch": 2.68,
"learning_rate": 9.332690051343244e-07,
"loss": 1.7573,
"step": 2094
},
{
"epoch": 2.68,
"learning_rate": 9.316136501294458e-07,
"loss": 1.7748,
"step": 2096
},
{
"epoch": 2.69,
"learning_rate": 9.299584833760689e-07,
"loss": 1.8123,
"step": 2098
},
{
"epoch": 2.69,
"learning_rate": 9.283035094304787e-07,
"loss": 1.7068,
"step": 2100
},
{
"epoch": 2.69,
"learning_rate": 9.266487328484276e-07,
"loss": 1.7718,
"step": 2102
},
{
"epoch": 2.69,
"learning_rate": 9.249941581851261e-07,
"loss": 1.7773,
"step": 2104
},
{
"epoch": 2.7,
"learning_rate": 9.233397899952281e-07,
"loss": 1.7494,
"step": 2106
},
{
"epoch": 2.7,
"learning_rate": 9.216856328328189e-07,
"loss": 1.7436,
"step": 2108
},
{
"epoch": 2.7,
"learning_rate": 9.200316912514036e-07,
"loss": 1.7289,
"step": 2110
},
{
"epoch": 2.7,
"learning_rate": 9.183779698038933e-07,
"loss": 1.7624,
"step": 2112
},
{
"epoch": 2.71,
"learning_rate": 9.167244730425938e-07,
"loss": 1.7458,
"step": 2114
},
{
"epoch": 2.71,
"learning_rate": 9.150712055191919e-07,
"loss": 1.7046,
"step": 2116
},
{
"epoch": 2.71,
"learning_rate": 9.134181717847427e-07,
"loss": 1.6527,
"step": 2118
},
{
"epoch": 2.71,
"learning_rate": 9.117653763896594e-07,
"loss": 1.7382,
"step": 2120
},
{
"epoch": 2.72,
"learning_rate": 9.101128238836972e-07,
"loss": 1.7238,
"step": 2122
},
{
"epoch": 2.72,
"learning_rate": 9.084605188159443e-07,
"loss": 1.7228,
"step": 2124
},
{
"epoch": 2.72,
"learning_rate": 9.068084657348074e-07,
"loss": 1.7253,
"step": 2126
},
{
"epoch": 2.72,
"learning_rate": 9.051566691879985e-07,
"loss": 1.7498,
"step": 2128
},
{
"epoch": 2.73,
"learning_rate": 9.035051337225243e-07,
"loss": 1.7508,
"step": 2130
},
{
"epoch": 2.73,
"learning_rate": 9.018538638846729e-07,
"loss": 1.7304,
"step": 2132
},
{
"epoch": 2.73,
"learning_rate": 9.002028642200006e-07,
"loss": 1.7732,
"step": 2134
},
{
"epoch": 2.73,
"learning_rate": 8.985521392733211e-07,
"loss": 1.793,
"step": 2136
},
{
"epoch": 2.74,
"learning_rate": 8.969016935886903e-07,
"loss": 1.7526,
"step": 2138
},
{
"epoch": 2.74,
"learning_rate": 8.952515317093963e-07,
"loss": 1.7177,
"step": 2140
},
{
"epoch": 2.74,
"learning_rate": 8.93601658177946e-07,
"loss": 1.7118,
"step": 2142
},
{
"epoch": 2.74,
"learning_rate": 8.919520775360523e-07,
"loss": 1.7314,
"step": 2144
},
{
"epoch": 2.75,
"learning_rate": 8.903027943246221e-07,
"loss": 1.702,
"step": 2146
},
{
"epoch": 2.75,
"learning_rate": 8.886538130837431e-07,
"loss": 1.711,
"step": 2148
},
{
"epoch": 2.75,
"learning_rate": 8.870051383526716e-07,
"loss": 1.6655,
"step": 2150
},
{
"epoch": 2.75,
"learning_rate": 8.853567746698213e-07,
"loss": 1.7369,
"step": 2152
},
{
"epoch": 2.76,
"learning_rate": 8.837087265727488e-07,
"loss": 1.729,
"step": 2154
},
{
"epoch": 2.76,
"learning_rate": 8.820609985981412e-07,
"loss": 1.7047,
"step": 2156
},
{
"epoch": 2.76,
"learning_rate": 8.804135952818059e-07,
"loss": 1.7329,
"step": 2158
},
{
"epoch": 2.76,
"learning_rate": 8.787665211586561e-07,
"loss": 1.7277,
"step": 2160
},
{
"epoch": 2.77,
"learning_rate": 8.771197807626983e-07,
"loss": 1.7089,
"step": 2162
},
{
"epoch": 2.77,
"learning_rate": 8.754733786270211e-07,
"loss": 1.7514,
"step": 2164
},
{
"epoch": 2.77,
"learning_rate": 8.73827319283781e-07,
"loss": 1.6954,
"step": 2166
},
{
"epoch": 2.78,
"learning_rate": 8.721816072641915e-07,
"loss": 1.7086,
"step": 2168
},
{
"epoch": 2.78,
"learning_rate": 8.7053624709851e-07,
"loss": 1.6756,
"step": 2170
},
{
"epoch": 2.78,
"learning_rate": 8.688912433160251e-07,
"loss": 1.728,
"step": 2172
},
{
"epoch": 2.78,
"learning_rate": 8.67246600445045e-07,
"loss": 1.7042,
"step": 2174
},
{
"epoch": 2.79,
"learning_rate": 8.65602323012883e-07,
"loss": 1.7058,
"step": 2176
},
{
"epoch": 2.79,
"learning_rate": 8.639584155458478e-07,
"loss": 1.725,
"step": 2178
},
{
"epoch": 2.79,
"learning_rate": 8.623148825692293e-07,
"loss": 1.7086,
"step": 2180
},
{
"epoch": 2.79,
"learning_rate": 8.60671728607286e-07,
"loss": 1.7114,
"step": 2182
},
{
"epoch": 2.8,
"learning_rate": 8.590289581832342e-07,
"loss": 1.7758,
"step": 2184
},
{
"epoch": 2.8,
"learning_rate": 8.57386575819233e-07,
"loss": 1.7317,
"step": 2186
},
{
"epoch": 2.8,
"learning_rate": 8.557445860363737e-07,
"loss": 1.7101,
"step": 2188
},
{
"epoch": 2.8,
"learning_rate": 8.541029933546677e-07,
"loss": 1.7195,
"step": 2190
},
{
"epoch": 2.81,
"learning_rate": 8.524618022930328e-07,
"loss": 1.7451,
"step": 2192
},
{
"epoch": 2.81,
"learning_rate": 8.508210173692811e-07,
"loss": 1.7652,
"step": 2194
},
{
"epoch": 2.81,
"learning_rate": 8.491806431001062e-07,
"loss": 1.707,
"step": 2196
},
{
"epoch": 2.81,
"learning_rate": 8.475406840010724e-07,
"loss": 1.675,
"step": 2198
},
{
"epoch": 2.82,
"learning_rate": 8.459011445866001e-07,
"loss": 1.7382,
"step": 2200
},
{
"epoch": 2.82,
"learning_rate": 8.442620293699554e-07,
"loss": 1.7058,
"step": 2202
},
{
"epoch": 2.82,
"learning_rate": 8.426233428632361e-07,
"loss": 1.7379,
"step": 2204
},
{
"epoch": 2.82,
"learning_rate": 8.409850895773594e-07,
"loss": 1.7377,
"step": 2206
},
{
"epoch": 2.83,
"learning_rate": 8.393472740220507e-07,
"loss": 1.7213,
"step": 2208
},
{
"epoch": 2.83,
"learning_rate": 8.377099007058302e-07,
"loss": 1.6698,
"step": 2210
},
{
"epoch": 2.83,
"learning_rate": 8.360729741360008e-07,
"loss": 1.6804,
"step": 2212
},
{
"epoch": 2.83,
"learning_rate": 8.344364988186359e-07,
"loss": 1.6628,
"step": 2214
},
{
"epoch": 2.84,
"learning_rate": 8.328004792585652e-07,
"loss": 1.6977,
"step": 2216
},
{
"epoch": 2.84,
"learning_rate": 8.311649199593658e-07,
"loss": 1.7028,
"step": 2218
},
{
"epoch": 2.84,
"learning_rate": 8.295298254233469e-07,
"loss": 1.7099,
"step": 2220
},
{
"epoch": 2.84,
"learning_rate": 8.27895200151538e-07,
"loss": 1.7499,
"step": 2222
},
{
"epoch": 2.85,
"learning_rate": 8.262610486436779e-07,
"loss": 1.7322,
"step": 2224
},
{
"epoch": 2.85,
"learning_rate": 8.246273753981996e-07,
"loss": 1.7313,
"step": 2226
},
{
"epoch": 2.85,
"learning_rate": 8.229941849122208e-07,
"loss": 1.7221,
"step": 2228
},
{
"epoch": 2.85,
"learning_rate": 8.213614816815305e-07,
"loss": 1.6751,
"step": 2230
},
{
"epoch": 2.86,
"learning_rate": 8.197292702005749e-07,
"loss": 1.726,
"step": 2232
},
{
"epoch": 2.86,
"learning_rate": 8.180975549624487e-07,
"loss": 1.7751,
"step": 2234
},
{
"epoch": 2.86,
"learning_rate": 8.164663404588783e-07,
"loss": 1.7474,
"step": 2236
},
{
"epoch": 2.86,
"learning_rate": 8.148356311802129e-07,
"loss": 1.7156,
"step": 2238
},
{
"epoch": 2.87,
"learning_rate": 8.132054316154114e-07,
"loss": 1.727,
"step": 2240
},
{
"epoch": 2.87,
"learning_rate": 8.115757462520281e-07,
"loss": 1.7749,
"step": 2242
},
{
"epoch": 2.87,
"learning_rate": 8.099465795762037e-07,
"loss": 1.7034,
"step": 2244
},
{
"epoch": 2.87,
"learning_rate": 8.083179360726493e-07,
"loss": 1.7613,
"step": 2246
},
{
"epoch": 2.88,
"learning_rate": 8.066898202246365e-07,
"loss": 1.7413,
"step": 2248
},
{
"epoch": 2.88,
"learning_rate": 8.050622365139847e-07,
"loss": 1.7223,
"step": 2250
},
{
"epoch": 2.88,
"learning_rate": 8.034351894210486e-07,
"loss": 1.6867,
"step": 2252
},
{
"epoch": 2.89,
"learning_rate": 8.018086834247053e-07,
"loss": 1.7452,
"step": 2254
},
{
"epoch": 2.89,
"learning_rate": 8.001827230023417e-07,
"loss": 1.7378,
"step": 2256
},
{
"epoch": 2.89,
"learning_rate": 7.985573126298443e-07,
"loss": 1.7166,
"step": 2258
},
{
"epoch": 2.89,
"learning_rate": 7.969324567815842e-07,
"loss": 1.7078,
"step": 2260
},
{
"epoch": 2.9,
"learning_rate": 7.953081599304072e-07,
"loss": 1.7301,
"step": 2262
},
{
"epoch": 2.9,
"learning_rate": 7.936844265476195e-07,
"loss": 1.7455,
"step": 2264
},
{
"epoch": 2.9,
"learning_rate": 7.920612611029759e-07,
"loss": 1.7209,
"step": 2266
},
{
"epoch": 2.9,
"learning_rate": 7.904386680646687e-07,
"loss": 1.7412,
"step": 2268
},
{
"epoch": 2.91,
"learning_rate": 7.888166518993139e-07,
"loss": 1.7011,
"step": 2270
},
{
"epoch": 2.91,
"learning_rate": 7.871952170719401e-07,
"loss": 1.7342,
"step": 2272
},
{
"epoch": 2.91,
"learning_rate": 7.855743680459749e-07,
"loss": 1.7135,
"step": 2274
},
{
"epoch": 2.91,
"learning_rate": 7.839541092832333e-07,
"loss": 1.7747,
"step": 2276
},
{
"epoch": 2.92,
"learning_rate": 7.823344452439062e-07,
"loss": 1.7266,
"step": 2278
},
{
"epoch": 2.92,
"learning_rate": 7.807153803865469e-07,
"loss": 1.7099,
"step": 2280
},
{
"epoch": 2.92,
"learning_rate": 7.790969191680594e-07,
"loss": 1.7586,
"step": 2282
},
{
"epoch": 2.92,
"learning_rate": 7.774790660436857e-07,
"loss": 1.7645,
"step": 2284
},
{
"epoch": 2.93,
"learning_rate": 7.758618254669942e-07,
"loss": 1.7443,
"step": 2286
},
{
"epoch": 2.93,
"learning_rate": 7.74245201889867e-07,
"loss": 1.7623,
"step": 2288
},
{
"epoch": 2.93,
"learning_rate": 7.72629199762488e-07,
"loss": 1.7334,
"step": 2290
},
{
"epoch": 2.93,
"learning_rate": 7.710138235333302e-07,
"loss": 1.7212,
"step": 2292
},
{
"epoch": 2.94,
"learning_rate": 7.69399077649143e-07,
"loss": 1.7441,
"step": 2294
},
{
"epoch": 2.94,
"learning_rate": 7.677849665549419e-07,
"loss": 1.6916,
"step": 2296
},
{
"epoch": 2.94,
"learning_rate": 7.661714946939937e-07,
"loss": 1.774,
"step": 2298
},
{
"epoch": 2.94,
"learning_rate": 7.645586665078067e-07,
"loss": 1.7248,
"step": 2300
},
{
"epoch": 2.95,
"learning_rate": 7.629464864361166e-07,
"loss": 1.7205,
"step": 2302
},
{
"epoch": 2.95,
"learning_rate": 7.613349589168747e-07,
"loss": 1.7359,
"step": 2304
},
{
"epoch": 2.95,
"learning_rate": 7.597240883862369e-07,
"loss": 1.7353,
"step": 2306
},
{
"epoch": 2.95,
"learning_rate": 7.581138792785498e-07,
"loss": 1.7356,
"step": 2308
},
{
"epoch": 2.96,
"learning_rate": 7.565043360263397e-07,
"loss": 1.7215,
"step": 2310
},
{
"epoch": 2.96,
"learning_rate": 7.548954630603003e-07,
"loss": 1.7212,
"step": 2312
},
{
"epoch": 2.96,
"learning_rate": 7.532872648092785e-07,
"loss": 1.7221,
"step": 2314
},
{
"epoch": 2.96,
"learning_rate": 7.516797457002657e-07,
"loss": 1.7377,
"step": 2316
},
{
"epoch": 2.97,
"learning_rate": 7.500729101583833e-07,
"loss": 1.7138,
"step": 2318
},
{
"epoch": 2.97,
"learning_rate": 7.484667626068703e-07,
"loss": 1.7118,
"step": 2320
},
{
"epoch": 2.97,
"learning_rate": 7.468613074670732e-07,
"loss": 1.7786,
"step": 2322
},
{
"epoch": 2.97,
"learning_rate": 7.452565491584306e-07,
"loss": 1.7788,
"step": 2324
},
{
"epoch": 2.98,
"learning_rate": 7.436524920984642e-07,
"loss": 1.7482,
"step": 2326
},
{
"epoch": 2.98,
"learning_rate": 7.420491407027652e-07,
"loss": 1.6754,
"step": 2328
},
{
"epoch": 2.98,
"learning_rate": 7.404464993849818e-07,
"loss": 1.7561,
"step": 2330
},
{
"epoch": 2.98,
"learning_rate": 7.388445725568085e-07,
"loss": 1.7299,
"step": 2332
},
{
"epoch": 2.99,
"learning_rate": 7.372433646279714e-07,
"loss": 1.7831,
"step": 2334
},
{
"epoch": 2.99,
"learning_rate": 7.356428800062187e-07,
"loss": 1.7369,
"step": 2336
},
{
"epoch": 2.99,
"learning_rate": 7.340431230973075e-07,
"loss": 1.7474,
"step": 2338
},
{
"epoch": 3.0,
"learning_rate": 7.324440983049914e-07,
"loss": 1.7813,
"step": 2340
},
{
"epoch": 3.0,
"learning_rate": 7.308458100310094e-07,
"loss": 1.7307,
"step": 2342
},
{
"epoch": 3.0,
"learning_rate": 7.292482626750713e-07,
"loss": 1.7165,
"step": 2344
},
{
"epoch": 3.0,
"learning_rate": 7.27651460634849e-07,
"loss": 1.7061,
"step": 2346
},
{
"epoch": 3.01,
"learning_rate": 7.260554083059621e-07,
"loss": 1.6714,
"step": 2348
},
{
"epoch": 3.01,
"learning_rate": 7.244601100819667e-07,
"loss": 1.7373,
"step": 2350
},
{
"epoch": 3.01,
"learning_rate": 7.228655703543427e-07,
"loss": 1.7059,
"step": 2352
},
{
"epoch": 3.01,
"learning_rate": 7.212717935124817e-07,
"loss": 1.7609,
"step": 2354
},
{
"epoch": 3.02,
"learning_rate": 7.19678783943676e-07,
"loss": 1.7161,
"step": 2356
},
{
"epoch": 3.02,
"learning_rate": 7.180865460331054e-07,
"loss": 1.756,
"step": 2358
},
{
"epoch": 3.02,
"learning_rate": 7.164950841638258e-07,
"loss": 1.6948,
"step": 2360
},
{
"epoch": 3.02,
"learning_rate": 7.149044027167565e-07,
"loss": 1.7037,
"step": 2362
},
{
"epoch": 3.03,
"learning_rate": 7.133145060706682e-07,
"loss": 1.6934,
"step": 2364
},
{
"epoch": 3.03,
"learning_rate": 7.117253986021723e-07,
"loss": 1.7537,
"step": 2366
},
{
"epoch": 3.03,
"learning_rate": 7.101370846857064e-07,
"loss": 1.7099,
"step": 2368
},
{
"epoch": 3.03,
"learning_rate": 7.085495686935248e-07,
"loss": 1.6593,
"step": 2370
},
{
"epoch": 3.04,
"learning_rate": 7.069628549956852e-07,
"loss": 1.6861,
"step": 2372
},
{
"epoch": 3.04,
"learning_rate": 7.053769479600354e-07,
"loss": 1.6595,
"step": 2374
},
{
"epoch": 3.04,
"learning_rate": 7.037918519522043e-07,
"loss": 1.6731,
"step": 2376
},
{
"epoch": 3.04,
"learning_rate": 7.022075713355876e-07,
"loss": 1.6906,
"step": 2378
},
{
"epoch": 3.05,
"learning_rate": 7.006241104713362e-07,
"loss": 1.6403,
"step": 2380
},
{
"epoch": 3.05,
"learning_rate": 6.990414737183452e-07,
"loss": 1.7541,
"step": 2382
},
{
"epoch": 3.05,
"learning_rate": 6.974596654332399e-07,
"loss": 1.7354,
"step": 2384
},
{
"epoch": 3.05,
"learning_rate": 6.958786899703657e-07,
"loss": 1.6888,
"step": 2386
},
{
"epoch": 3.06,
"learning_rate": 6.942985516817758e-07,
"loss": 1.6998,
"step": 2388
},
{
"epoch": 3.06,
"learning_rate": 6.92719254917218e-07,
"loss": 1.7317,
"step": 2390
},
{
"epoch": 3.06,
"learning_rate": 6.911408040241248e-07,
"loss": 1.6881,
"step": 2392
},
{
"epoch": 3.06,
"learning_rate": 6.895632033475987e-07,
"loss": 1.6602,
"step": 2394
},
{
"epoch": 3.07,
"learning_rate": 6.879864572304026e-07,
"loss": 1.6645,
"step": 2396
},
{
"epoch": 3.07,
"learning_rate": 6.864105700129473e-07,
"loss": 1.7215,
"step": 2398
},
{
"epoch": 3.07,
"learning_rate": 6.848355460332785e-07,
"loss": 1.7137,
"step": 2400
},
{
"epoch": 3.07,
"learning_rate": 6.832613896270665e-07,
"loss": 1.7086,
"step": 2402
},
{
"epoch": 3.08,
"learning_rate": 6.816881051275924e-07,
"loss": 1.7379,
"step": 2404
},
{
"epoch": 3.08,
"learning_rate": 6.801156968657375e-07,
"loss": 1.6925,
"step": 2406
},
{
"epoch": 3.08,
"learning_rate": 6.785441691699711e-07,
"loss": 1.6749,
"step": 2408
},
{
"epoch": 3.08,
"learning_rate": 6.769735263663395e-07,
"loss": 1.7344,
"step": 2410
},
{
"epoch": 3.09,
"learning_rate": 6.75403772778451e-07,
"loss": 1.7068,
"step": 2412
},
{
"epoch": 3.09,
"learning_rate": 6.738349127274674e-07,
"loss": 1.738,
"step": 2414
},
{
"epoch": 3.09,
"learning_rate": 6.72266950532091e-07,
"loss": 1.7056,
"step": 2416
},
{
"epoch": 3.1,
"learning_rate": 6.706998905085519e-07,
"loss": 1.7111,
"step": 2418
},
{
"epoch": 3.1,
"learning_rate": 6.691337369705975e-07,
"loss": 1.7408,
"step": 2420
},
{
"epoch": 3.1,
"learning_rate": 6.675684942294787e-07,
"loss": 1.679,
"step": 2422
},
{
"epoch": 3.1,
"learning_rate": 6.660041665939397e-07,
"loss": 1.7186,
"step": 2424
},
{
"epoch": 3.11,
"learning_rate": 6.644407583702066e-07,
"loss": 1.6909,
"step": 2426
},
{
"epoch": 3.11,
"learning_rate": 6.628782738619729e-07,
"loss": 1.7152,
"step": 2428
},
{
"epoch": 3.11,
"learning_rate": 6.613167173703911e-07,
"loss": 1.7748,
"step": 2430
},
{
"epoch": 3.11,
"learning_rate": 6.597560931940572e-07,
"loss": 1.6811,
"step": 2432
},
{
"epoch": 3.12,
"learning_rate": 6.58196405629002e-07,
"loss": 1.7035,
"step": 2434
},
{
"epoch": 3.12,
"learning_rate": 6.566376589686778e-07,
"loss": 1.6739,
"step": 2436
},
{
"epoch": 3.12,
"learning_rate": 6.550798575039471e-07,
"loss": 1.6997,
"step": 2438
},
{
"epoch": 3.12,
"learning_rate": 6.5352300552307e-07,
"loss": 1.7208,
"step": 2440
},
{
"epoch": 3.13,
"learning_rate": 6.519671073116924e-07,
"loss": 1.6808,
"step": 2442
},
{
"epoch": 3.13,
"learning_rate": 6.504121671528362e-07,
"loss": 1.7049,
"step": 2444
},
{
"epoch": 3.13,
"learning_rate": 6.488581893268845e-07,
"loss": 1.7546,
"step": 2446
},
{
"epoch": 3.13,
"learning_rate": 6.473051781115726e-07,
"loss": 1.6928,
"step": 2448
},
{
"epoch": 3.14,
"learning_rate": 6.45753137781974e-07,
"loss": 1.7064,
"step": 2450
},
{
"epoch": 3.14,
"learning_rate": 6.442020726104898e-07,
"loss": 1.7164,
"step": 2452
},
{
"epoch": 3.14,
"learning_rate": 6.426519868668369e-07,
"loss": 1.6695,
"step": 2454
},
{
"epoch": 3.14,
"learning_rate": 6.411028848180359e-07,
"loss": 1.6921,
"step": 2456
},
{
"epoch": 3.15,
"learning_rate": 6.395547707283999e-07,
"loss": 1.6897,
"step": 2458
},
{
"epoch": 3.15,
"learning_rate": 6.380076488595222e-07,
"loss": 1.6925,
"step": 2460
},
{
"epoch": 3.15,
"learning_rate": 6.364615234702639e-07,
"loss": 1.6795,
"step": 2462
},
{
"epoch": 3.15,
"learning_rate": 6.349163988167446e-07,
"loss": 1.7223,
"step": 2464
},
{
"epoch": 3.16,
"learning_rate": 6.333722791523275e-07,
"loss": 1.7437,
"step": 2466
},
{
"epoch": 3.16,
"learning_rate": 6.318291687276107e-07,
"loss": 1.7554,
"step": 2468
},
{
"epoch": 3.16,
"learning_rate": 6.302870717904136e-07,
"loss": 1.7251,
"step": 2470
},
{
"epoch": 3.16,
"learning_rate": 6.28745992585765e-07,
"loss": 1.7159,
"step": 2472
},
{
"epoch": 3.17,
"learning_rate": 6.272059353558929e-07,
"loss": 1.6963,
"step": 2474
},
{
"epoch": 3.17,
"learning_rate": 6.256669043402122e-07,
"loss": 1.6631,
"step": 2476
},
{
"epoch": 3.17,
"learning_rate": 6.241289037753119e-07,
"loss": 1.697,
"step": 2478
},
{
"epoch": 3.17,
"learning_rate": 6.225919378949461e-07,
"loss": 1.7226,
"step": 2480
},
{
"epoch": 3.18,
"learning_rate": 6.210560109300185e-07,
"loss": 1.7485,
"step": 2482
},
{
"epoch": 3.18,
"learning_rate": 6.195211271085743e-07,
"loss": 1.7733,
"step": 2484
},
{
"epoch": 3.18,
"learning_rate": 6.179872906557872e-07,
"loss": 1.6833,
"step": 2486
},
{
"epoch": 3.18,
"learning_rate": 6.164545057939472e-07,
"loss": 1.6895,
"step": 2488
},
{
"epoch": 3.19,
"learning_rate": 6.149227767424501e-07,
"loss": 1.7024,
"step": 2490
},
{
"epoch": 3.19,
"learning_rate": 6.133921077177844e-07,
"loss": 1.7455,
"step": 2492
},
{
"epoch": 3.19,
"learning_rate": 6.118625029335212e-07,
"loss": 1.747,
"step": 2494
},
{
"epoch": 3.19,
"learning_rate": 6.103339666003023e-07,
"loss": 1.7028,
"step": 2496
},
{
"epoch": 3.2,
"learning_rate": 6.088065029258273e-07,
"loss": 1.6859,
"step": 2498
},
{
"epoch": 3.2,
"learning_rate": 6.072801161148448e-07,
"loss": 1.7432,
"step": 2500
},
{
"epoch": 3.2,
"learning_rate": 6.057548103691368e-07,
"loss": 1.6872,
"step": 2502
},
{
"epoch": 3.21,
"learning_rate": 6.042305898875111e-07,
"loss": 1.6957,
"step": 2504
},
{
"epoch": 3.21,
"learning_rate": 6.027074588657872e-07,
"loss": 1.6616,
"step": 2506
},
{
"epoch": 3.21,
"learning_rate": 6.01185421496786e-07,
"loss": 1.7558,
"step": 2508
},
{
"epoch": 3.21,
"learning_rate": 5.996644819703176e-07,
"loss": 1.688,
"step": 2510
},
{
"epoch": 3.22,
"learning_rate": 5.981446444731694e-07,
"loss": 1.7313,
"step": 2512
},
{
"epoch": 3.22,
"learning_rate": 5.966259131890967e-07,
"loss": 1.668,
"step": 2514
},
{
"epoch": 3.22,
"learning_rate": 5.951082922988082e-07,
"loss": 1.7323,
"step": 2516
},
{
"epoch": 3.22,
"learning_rate": 5.935917859799567e-07,
"loss": 1.7431,
"step": 2518
},
{
"epoch": 3.23,
"learning_rate": 5.92076398407127e-07,
"loss": 1.7354,
"step": 2520
},
{
"epoch": 3.23,
"learning_rate": 5.905621337518229e-07,
"loss": 1.7386,
"step": 2522
},
{
"epoch": 3.23,
"learning_rate": 5.890489961824591e-07,
"loss": 1.6786,
"step": 2524
},
{
"epoch": 3.23,
"learning_rate": 5.87536989864346e-07,
"loss": 1.7089,
"step": 2526
},
{
"epoch": 3.24,
"learning_rate": 5.860261189596809e-07,
"loss": 1.6985,
"step": 2528
},
{
"epoch": 3.24,
"learning_rate": 5.845163876275358e-07,
"loss": 1.7073,
"step": 2530
},
{
"epoch": 3.24,
"learning_rate": 5.830078000238441e-07,
"loss": 1.7425,
"step": 2532
},
{
"epoch": 3.24,
"learning_rate": 5.815003603013926e-07,
"loss": 1.6829,
"step": 2534
},
{
"epoch": 3.25,
"learning_rate": 5.799940726098072e-07,
"loss": 1.7058,
"step": 2536
},
{
"epoch": 3.25,
"learning_rate": 5.784889410955436e-07,
"loss": 1.6897,
"step": 2538
},
{
"epoch": 3.25,
"learning_rate": 5.769849699018736e-07,
"loss": 1.7014,
"step": 2540
},
{
"epoch": 3.25,
"learning_rate": 5.754821631688751e-07,
"loss": 1.7284,
"step": 2542
},
{
"epoch": 3.26,
"learning_rate": 5.73980525033421e-07,
"loss": 1.7094,
"step": 2544
},
{
"epoch": 3.26,
"learning_rate": 5.724800596291672e-07,
"loss": 1.6953,
"step": 2546
},
{
"epoch": 3.26,
"learning_rate": 5.709807710865418e-07,
"loss": 1.7556,
"step": 2548
},
{
"epoch": 3.26,
"learning_rate": 5.694826635327323e-07,
"loss": 1.6957,
"step": 2550
},
{
"epoch": 3.27,
"learning_rate": 5.679857410916755e-07,
"loss": 1.7493,
"step": 2552
},
{
"epoch": 3.27,
"learning_rate": 5.664900078840461e-07,
"loss": 1.7389,
"step": 2554
},
{
"epoch": 3.27,
"learning_rate": 5.649954680272453e-07,
"loss": 1.7328,
"step": 2556
},
{
"epoch": 3.27,
"learning_rate": 5.635021256353893e-07,
"loss": 1.7164,
"step": 2558
},
{
"epoch": 3.28,
"learning_rate": 5.620099848192974e-07,
"loss": 1.6921,
"step": 2560
},
{
"epoch": 3.28,
"learning_rate": 5.605190496864814e-07,
"loss": 1.7499,
"step": 2562
},
{
"epoch": 3.28,
"learning_rate": 5.590293243411342e-07,
"loss": 1.731,
"step": 2564
},
{
"epoch": 3.28,
"learning_rate": 5.575408128841189e-07,
"loss": 1.7464,
"step": 2566
},
{
"epoch": 3.29,
"learning_rate": 5.560535194129571e-07,
"loss": 1.7261,
"step": 2568
},
{
"epoch": 3.29,
"learning_rate": 5.545674480218161e-07,
"loss": 1.6968,
"step": 2570
},
{
"epoch": 3.29,
"learning_rate": 5.530826028015014e-07,
"loss": 1.6866,
"step": 2572
},
{
"epoch": 3.29,
"learning_rate": 5.515989878394407e-07,
"loss": 1.7046,
"step": 2574
},
{
"epoch": 3.3,
"learning_rate": 5.501166072196768e-07,
"loss": 1.6637,
"step": 2576
},
{
"epoch": 3.3,
"learning_rate": 5.486354650228547e-07,
"loss": 1.6955,
"step": 2578
},
{
"epoch": 3.3,
"learning_rate": 5.471555653262088e-07,
"loss": 1.6866,
"step": 2580
},
{
"epoch": 3.3,
"learning_rate": 5.456769122035551e-07,
"loss": 1.6743,
"step": 2582
},
{
"epoch": 3.31,
"learning_rate": 5.44199509725276e-07,
"loss": 1.6932,
"step": 2584
},
{
"epoch": 3.31,
"learning_rate": 5.427233619583131e-07,
"loss": 1.6746,
"step": 2586
},
{
"epoch": 3.31,
"learning_rate": 5.412484729661535e-07,
"loss": 1.7464,
"step": 2588
},
{
"epoch": 3.32,
"learning_rate": 5.397748468088181e-07,
"loss": 1.67,
"step": 2590
},
{
"epoch": 3.32,
"learning_rate": 5.383024875428533e-07,
"loss": 1.6785,
"step": 2592
},
{
"epoch": 3.32,
"learning_rate": 5.36831399221316e-07,
"loss": 1.6624,
"step": 2594
},
{
"epoch": 3.32,
"learning_rate": 5.353615858937666e-07,
"loss": 1.7712,
"step": 2596
},
{
"epoch": 3.33,
"learning_rate": 5.338930516062545e-07,
"loss": 1.6507,
"step": 2598
},
{
"epoch": 3.33,
"learning_rate": 5.32425800401308e-07,
"loss": 1.7277,
"step": 2600
},
{
"epoch": 3.33,
"learning_rate": 5.309598363179243e-07,
"loss": 1.6706,
"step": 2602
},
{
"epoch": 3.33,
"learning_rate": 5.294951633915572e-07,
"loss": 1.7087,
"step": 2604
},
{
"epoch": 3.34,
"learning_rate": 5.280317856541055e-07,
"loss": 1.7032,
"step": 2606
},
{
"epoch": 3.34,
"learning_rate": 5.265697071339035e-07,
"loss": 1.6969,
"step": 2608
},
{
"epoch": 3.34,
"learning_rate": 5.251089318557083e-07,
"loss": 1.7435,
"step": 2610
},
{
"epoch": 3.34,
"learning_rate": 5.236494638406904e-07,
"loss": 1.7183,
"step": 2612
},
{
"epoch": 3.35,
"learning_rate": 5.221913071064214e-07,
"loss": 1.7128,
"step": 2614
},
{
"epoch": 3.35,
"learning_rate": 5.207344656668626e-07,
"loss": 1.6868,
"step": 2616
},
{
"epoch": 3.35,
"learning_rate": 5.192789435323557e-07,
"loss": 1.6988,
"step": 2618
},
{
"epoch": 3.35,
"learning_rate": 5.178247447096092e-07,
"loss": 1.7053,
"step": 2620
},
{
"epoch": 3.36,
"learning_rate": 5.163718732016902e-07,
"loss": 1.7295,
"step": 2622
},
{
"epoch": 3.36,
"learning_rate": 5.149203330080114e-07,
"loss": 1.733,
"step": 2624
},
{
"epoch": 3.36,
"learning_rate": 5.134701281243215e-07,
"loss": 1.6811,
"step": 2626
},
{
"epoch": 3.36,
"learning_rate": 5.120212625426921e-07,
"loss": 1.7752,
"step": 2628
},
{
"epoch": 3.37,
"learning_rate": 5.105737402515082e-07,
"loss": 1.6915,
"step": 2630
},
{
"epoch": 3.37,
"learning_rate": 5.091275652354581e-07,
"loss": 1.6874,
"step": 2632
},
{
"epoch": 3.37,
"learning_rate": 5.076827414755205e-07,
"loss": 1.6911,
"step": 2634
},
{
"epoch": 3.37,
"learning_rate": 5.062392729489553e-07,
"loss": 1.7123,
"step": 2636
},
{
"epoch": 3.38,
"learning_rate": 5.047971636292905e-07,
"loss": 1.7383,
"step": 2638
},
{
"epoch": 3.38,
"learning_rate": 5.03356417486313e-07,
"loss": 1.717,
"step": 2640
},
{
"epoch": 3.38,
"learning_rate": 5.019170384860573e-07,
"loss": 1.7162,
"step": 2642
},
{
"epoch": 3.38,
"learning_rate": 5.004790305907951e-07,
"loss": 1.7199,
"step": 2644
},
{
"epoch": 3.39,
"learning_rate": 4.990423977590232e-07,
"loss": 1.6808,
"step": 2646
},
{
"epoch": 3.39,
"learning_rate": 4.97607143945453e-07,
"loss": 1.7264,
"step": 2648
},
{
"epoch": 3.39,
"learning_rate": 4.961732731009993e-07,
"loss": 1.7366,
"step": 2650
},
{
"epoch": 3.39,
"learning_rate": 4.947407891727712e-07,
"loss": 1.6979,
"step": 2652
},
{
"epoch": 3.4,
"learning_rate": 4.933096961040592e-07,
"loss": 1.7305,
"step": 2654
},
{
"epoch": 3.4,
"learning_rate": 4.918799978343252e-07,
"loss": 1.7191,
"step": 2656
},
{
"epoch": 3.4,
"learning_rate": 4.904516982991919e-07,
"loss": 1.7545,
"step": 2658
},
{
"epoch": 3.4,
"learning_rate": 4.89024801430431e-07,
"loss": 1.6748,
"step": 2660
},
{
"epoch": 3.41,
"learning_rate": 4.875993111559528e-07,
"loss": 1.7371,
"step": 2662
},
{
"epoch": 3.41,
"learning_rate": 4.861752313997963e-07,
"loss": 1.6671,
"step": 2664
},
{
"epoch": 3.41,
"learning_rate": 4.847525660821177e-07,
"loss": 1.7024,
"step": 2666
},
{
"epoch": 3.42,
"learning_rate": 4.833313191191794e-07,
"loss": 1.6872,
"step": 2668
},
{
"epoch": 3.42,
"learning_rate": 4.819114944233391e-07,
"loss": 1.735,
"step": 2670
},
{
"epoch": 3.42,
"learning_rate": 4.804930959030391e-07,
"loss": 1.7085,
"step": 2672
},
{
"epoch": 3.42,
"learning_rate": 4.790761274627965e-07,
"loss": 1.7181,
"step": 2674
},
{
"epoch": 3.43,
"learning_rate": 4.776605930031918e-07,
"loss": 1.7066,
"step": 2676
},
{
"epoch": 3.43,
"learning_rate": 4.7624649642085715e-07,
"loss": 1.7145,
"step": 2678
},
{
"epoch": 3.43,
"learning_rate": 4.7483384160846763e-07,
"loss": 1.7003,
"step": 2680
},
{
"epoch": 3.43,
"learning_rate": 4.7342263245472845e-07,
"loss": 1.7498,
"step": 2682
},
{
"epoch": 3.44,
"learning_rate": 4.720128728443661e-07,
"loss": 1.7287,
"step": 2684
},
{
"epoch": 3.44,
"learning_rate": 4.7060456665811674e-07,
"loss": 1.7017,
"step": 2686
},
{
"epoch": 3.44,
"learning_rate": 4.691977177727148e-07,
"loss": 1.7323,
"step": 2688
},
{
"epoch": 3.44,
"learning_rate": 4.677923300608839e-07,
"loss": 1.6809,
"step": 2690
},
{
"epoch": 3.45,
"learning_rate": 4.6638840739132554e-07,
"loss": 1.7143,
"step": 2692
},
{
"epoch": 3.45,
"learning_rate": 4.649859536287073e-07,
"loss": 1.6958,
"step": 2694
},
{
"epoch": 3.45,
"learning_rate": 4.635849726336545e-07,
"loss": 1.6667,
"step": 2696
},
{
"epoch": 3.45,
"learning_rate": 4.6218546826273677e-07,
"loss": 1.7238,
"step": 2698
},
{
"epoch": 3.46,
"learning_rate": 4.6078744436846016e-07,
"loss": 1.7126,
"step": 2700
},
{
"epoch": 3.46,
"learning_rate": 4.5939090479925545e-07,
"loss": 1.6543,
"step": 2702
},
{
"epoch": 3.46,
"learning_rate": 4.5799585339946613e-07,
"loss": 1.6866,
"step": 2704
},
{
"epoch": 3.46,
"learning_rate": 4.5660229400934045e-07,
"loss": 1.6672,
"step": 2706
},
{
"epoch": 3.47,
"learning_rate": 4.552102304650185e-07,
"loss": 1.6894,
"step": 2708
},
{
"epoch": 3.47,
"learning_rate": 4.538196665985231e-07,
"loss": 1.6483,
"step": 2710
},
{
"epoch": 3.47,
"learning_rate": 4.5243060623774956e-07,
"loss": 1.7246,
"step": 2712
},
{
"epoch": 3.47,
"learning_rate": 4.5104305320645264e-07,
"loss": 1.7318,
"step": 2714
},
{
"epoch": 3.48,
"learning_rate": 4.4965701132423963e-07,
"loss": 1.7616,
"step": 2716
},
{
"epoch": 3.48,
"learning_rate": 4.482724844065563e-07,
"loss": 1.7369,
"step": 2718
},
{
"epoch": 3.48,
"learning_rate": 4.4688947626467943e-07,
"loss": 1.7157,
"step": 2720
},
{
"epoch": 3.48,
"learning_rate": 4.455079907057044e-07,
"loss": 1.674,
"step": 2722
},
{
"epoch": 3.49,
"learning_rate": 4.4412803153253575e-07,
"loss": 1.739,
"step": 2724
},
{
"epoch": 3.49,
"learning_rate": 4.427496025438754e-07,
"loss": 1.6664,
"step": 2726
},
{
"epoch": 3.49,
"learning_rate": 4.4137270753421295e-07,
"loss": 1.7188,
"step": 2728
},
{
"epoch": 3.49,
"learning_rate": 4.3999735029381645e-07,
"loss": 1.74,
"step": 2730
},
{
"epoch": 3.5,
"learning_rate": 4.3862353460872e-07,
"loss": 1.7153,
"step": 2732
},
{
"epoch": 3.5,
"learning_rate": 4.372512642607149e-07,
"loss": 1.7448,
"step": 2734
},
{
"epoch": 3.5,
"learning_rate": 4.358805430273376e-07,
"loss": 1.7009,
"step": 2736
},
{
"epoch": 3.5,
"learning_rate": 4.3451137468185993e-07,
"loss": 1.7433,
"step": 2738
},
{
"epoch": 3.51,
"learning_rate": 4.3314376299328024e-07,
"loss": 1.7182,
"step": 2740
},
{
"epoch": 3.51,
"learning_rate": 4.317777117263113e-07,
"loss": 1.6875,
"step": 2742
},
{
"epoch": 3.51,
"learning_rate": 4.304132246413702e-07,
"loss": 1.7303,
"step": 2744
},
{
"epoch": 3.51,
"learning_rate": 4.2905030549456823e-07,
"loss": 1.6692,
"step": 2746
},
{
"epoch": 3.52,
"learning_rate": 4.2768895803770013e-07,
"loss": 1.6905,
"step": 2748
},
{
"epoch": 3.52,
"learning_rate": 4.2632918601823486e-07,
"loss": 1.7407,
"step": 2750
},
{
"epoch": 3.52,
"learning_rate": 4.249709931793044e-07,
"loss": 1.7284,
"step": 2752
},
{
"epoch": 3.53,
"learning_rate": 4.2361438325969346e-07,
"loss": 1.6921,
"step": 2754
},
{
"epoch": 3.53,
"learning_rate": 4.2225935999382966e-07,
"loss": 1.7132,
"step": 2756
},
{
"epoch": 3.53,
"learning_rate": 4.2090592711177253e-07,
"loss": 1.696,
"step": 2758
},
{
"epoch": 3.53,
"learning_rate": 4.1955408833920316e-07,
"loss": 1.6883,
"step": 2760
},
{
"epoch": 3.54,
"learning_rate": 4.1820384739741553e-07,
"loss": 1.7034,
"step": 2762
},
{
"epoch": 3.54,
"learning_rate": 4.168552080033048e-07,
"loss": 1.7624,
"step": 2764
},
{
"epoch": 3.54,
"learning_rate": 4.1550817386935754e-07,
"loss": 1.6977,
"step": 2766
},
{
"epoch": 3.54,
"learning_rate": 4.1416274870364087e-07,
"loss": 1.7197,
"step": 2768
},
{
"epoch": 3.55,
"learning_rate": 4.1281893620979303e-07,
"loss": 1.6789,
"step": 2770
},
{
"epoch": 3.55,
"learning_rate": 4.1147674008701306e-07,
"loss": 1.7043,
"step": 2772
},
{
"epoch": 3.55,
"learning_rate": 4.101361640300508e-07,
"loss": 1.7427,
"step": 2774
},
{
"epoch": 3.55,
"learning_rate": 4.087972117291965e-07,
"loss": 1.718,
"step": 2776
},
{
"epoch": 3.56,
"learning_rate": 4.074598868702698e-07,
"loss": 1.6922,
"step": 2778
},
{
"epoch": 3.56,
"learning_rate": 4.061241931346104e-07,
"loss": 1.6605,
"step": 2780
},
{
"epoch": 3.56,
"learning_rate": 4.047901341990688e-07,
"loss": 1.7437,
"step": 2782
},
{
"epoch": 3.56,
"learning_rate": 4.034577137359949e-07,
"loss": 1.7406,
"step": 2784
},
{
"epoch": 3.57,
"learning_rate": 4.0212693541322827e-07,
"loss": 1.6832,
"step": 2786
},
{
"epoch": 3.57,
"learning_rate": 4.007978028940875e-07,
"loss": 1.6964,
"step": 2788
},
{
"epoch": 3.57,
"learning_rate": 3.994703198373617e-07,
"loss": 1.6936,
"step": 2790
},
{
"epoch": 3.57,
"learning_rate": 3.9814448989729823e-07,
"loss": 1.706,
"step": 2792
},
{
"epoch": 3.58,
"learning_rate": 3.9682031672359463e-07,
"loss": 1.7341,
"step": 2794
},
{
"epoch": 3.58,
"learning_rate": 3.95497803961388e-07,
"loss": 1.7375,
"step": 2796
},
{
"epoch": 3.58,
"learning_rate": 3.941769552512435e-07,
"loss": 1.6859,
"step": 2798
},
{
"epoch": 3.58,
"learning_rate": 3.92857774229147e-07,
"loss": 1.7387,
"step": 2800
},
{
"epoch": 3.59,
"learning_rate": 3.9154026452649236e-07,
"loss": 1.6935,
"step": 2802
},
{
"epoch": 3.59,
"learning_rate": 3.9022442977007363e-07,
"loss": 1.6894,
"step": 2804
},
{
"epoch": 3.59,
"learning_rate": 3.889102735820734e-07,
"loss": 1.6711,
"step": 2806
},
{
"epoch": 3.59,
"learning_rate": 3.87597799580054e-07,
"loss": 1.6919,
"step": 2808
},
{
"epoch": 3.6,
"learning_rate": 3.862870113769475e-07,
"loss": 1.7753,
"step": 2810
},
{
"epoch": 3.6,
"learning_rate": 3.8497791258104405e-07,
"loss": 1.6993,
"step": 2812
},
{
"epoch": 3.6,
"learning_rate": 3.836705067959849e-07,
"loss": 1.7343,
"step": 2814
},
{
"epoch": 3.6,
"learning_rate": 3.8236479762074923e-07,
"loss": 1.7445,
"step": 2816
},
{
"epoch": 3.61,
"learning_rate": 3.8106078864964706e-07,
"loss": 1.6669,
"step": 2818
},
{
"epoch": 3.61,
"learning_rate": 3.7975848347230765e-07,
"loss": 1.7274,
"step": 2820
},
{
"epoch": 3.61,
"learning_rate": 3.7845788567367063e-07,
"loss": 1.7243,
"step": 2822
},
{
"epoch": 3.61,
"learning_rate": 3.771589988339747e-07,
"loss": 1.7371,
"step": 2824
},
{
"epoch": 3.62,
"learning_rate": 3.7586182652874897e-07,
"loss": 1.7094,
"step": 2826
},
{
"epoch": 3.62,
"learning_rate": 3.745663723288033e-07,
"loss": 1.6703,
"step": 2828
},
{
"epoch": 3.62,
"learning_rate": 3.7327263980021786e-07,
"loss": 1.7065,
"step": 2830
},
{
"epoch": 3.62,
"learning_rate": 3.719806325043336e-07,
"loss": 1.6635,
"step": 2832
},
{
"epoch": 3.63,
"learning_rate": 3.7069035399774187e-07,
"loss": 1.7406,
"step": 2834
},
{
"epoch": 3.63,
"learning_rate": 3.694018078322747e-07,
"loss": 1.7344,
"step": 2836
},
{
"epoch": 3.63,
"learning_rate": 3.6811499755499653e-07,
"loss": 1.6857,
"step": 2838
},
{
"epoch": 3.64,
"learning_rate": 3.6682992670819266e-07,
"loss": 1.6962,
"step": 2840
},
{
"epoch": 3.64,
"learning_rate": 3.655465988293602e-07,
"loss": 1.6847,
"step": 2842
},
{
"epoch": 3.64,
"learning_rate": 3.642650174511992e-07,
"loss": 1.6805,
"step": 2844
},
{
"epoch": 3.64,
"learning_rate": 3.6298518610159944e-07,
"loss": 1.7231,
"step": 2846
},
{
"epoch": 3.65,
"learning_rate": 3.617071083036359e-07,
"loss": 1.7102,
"step": 2848
},
{
"epoch": 3.65,
"learning_rate": 3.6043078757555534e-07,
"loss": 1.6789,
"step": 2850
},
{
"epoch": 3.65,
"learning_rate": 3.591562274307681e-07,
"loss": 1.7094,
"step": 2852
},
{
"epoch": 3.65,
"learning_rate": 3.578834313778379e-07,
"loss": 1.6921,
"step": 2854
},
{
"epoch": 3.66,
"learning_rate": 3.5661240292047223e-07,
"loss": 1.6901,
"step": 2856
},
{
"epoch": 3.66,
"learning_rate": 3.553431455575123e-07,
"loss": 1.7158,
"step": 2858
},
{
"epoch": 3.66,
"learning_rate": 3.540756627829248e-07,
"loss": 1.7571,
"step": 2860
},
{
"epoch": 3.66,
"learning_rate": 3.5280995808579115e-07,
"loss": 1.6981,
"step": 2862
},
{
"epoch": 3.67,
"learning_rate": 3.5154603495029845e-07,
"loss": 1.6826,
"step": 2864
},
{
"epoch": 3.67,
"learning_rate": 3.502838968557287e-07,
"loss": 1.6713,
"step": 2866
},
{
"epoch": 3.67,
"learning_rate": 3.490235472764502e-07,
"loss": 1.6996,
"step": 2868
},
{
"epoch": 3.67,
"learning_rate": 3.4776498968190883e-07,
"loss": 1.7092,
"step": 2870
},
{
"epoch": 3.68,
"learning_rate": 3.465082275366169e-07,
"loss": 1.6855,
"step": 2872
},
{
"epoch": 3.68,
"learning_rate": 3.452532643001447e-07,
"loss": 1.7074,
"step": 2874
},
{
"epoch": 3.68,
"learning_rate": 3.440001034271094e-07,
"loss": 1.7411,
"step": 2876
},
{
"epoch": 3.68,
"learning_rate": 3.427487483671684e-07,
"loss": 1.6927,
"step": 2878
},
{
"epoch": 3.69,
"learning_rate": 3.4149920256500655e-07,
"loss": 1.7094,
"step": 2880
},
{
"epoch": 3.69,
"learning_rate": 3.4025146946032903e-07,
"loss": 1.6977,
"step": 2882
},
{
"epoch": 3.69,
"learning_rate": 3.3900555248785157e-07,
"loss": 1.6928,
"step": 2884
},
{
"epoch": 3.69,
"learning_rate": 3.377614550772891e-07,
"loss": 1.6579,
"step": 2886
},
{
"epoch": 3.7,
"learning_rate": 3.365191806533494e-07,
"loss": 1.6968,
"step": 2888
},
{
"epoch": 3.7,
"learning_rate": 3.352787326357204e-07,
"loss": 1.7145,
"step": 2890
},
{
"epoch": 3.7,
"learning_rate": 3.340401144390632e-07,
"loss": 1.6662,
"step": 2892
},
{
"epoch": 3.7,
"learning_rate": 3.328033294730025e-07,
"loss": 1.6866,
"step": 2894
},
{
"epoch": 3.71,
"learning_rate": 3.315683811421148e-07,
"loss": 1.7212,
"step": 2896
},
{
"epoch": 3.71,
"learning_rate": 3.303352728459227e-07,
"loss": 1.6816,
"step": 2898
},
{
"epoch": 3.71,
"learning_rate": 3.291040079788818e-07,
"loss": 1.7127,
"step": 2900
},
{
"epoch": 3.71,
"learning_rate": 3.2787458993037454e-07,
"loss": 1.685,
"step": 2902
},
{
"epoch": 3.72,
"learning_rate": 3.266470220846993e-07,
"loss": 1.6845,
"step": 2904
},
{
"epoch": 3.72,
"learning_rate": 3.2542130782106026e-07,
"loss": 1.6905,
"step": 2906
},
{
"epoch": 3.72,
"learning_rate": 3.241974505135605e-07,
"loss": 1.7071,
"step": 2908
},
{
"epoch": 3.72,
"learning_rate": 3.2297545353119085e-07,
"loss": 1.7594,
"step": 2910
},
{
"epoch": 3.73,
"learning_rate": 3.217553202378201e-07,
"loss": 1.6994,
"step": 2912
},
{
"epoch": 3.73,
"learning_rate": 3.2053705399218876e-07,
"loss": 1.7848,
"step": 2914
},
{
"epoch": 3.73,
"learning_rate": 3.1932065814789575e-07,
"loss": 1.6733,
"step": 2916
},
{
"epoch": 3.74,
"learning_rate": 3.1810613605339245e-07,
"loss": 1.6999,
"step": 2918
},
{
"epoch": 3.74,
"learning_rate": 3.168934910519722e-07,
"loss": 1.7632,
"step": 2920
},
{
"epoch": 3.74,
"learning_rate": 3.156827264817602e-07,
"loss": 1.7137,
"step": 2922
},
{
"epoch": 3.74,
"learning_rate": 3.1447384567570667e-07,
"loss": 1.666,
"step": 2924
},
{
"epoch": 3.75,
"learning_rate": 3.132668519615749e-07,
"loss": 1.6483,
"step": 2926
},
{
"epoch": 3.75,
"learning_rate": 3.1206174866193427e-07,
"loss": 1.6765,
"step": 2928
},
{
"epoch": 3.75,
"learning_rate": 3.108585390941506e-07,
"loss": 1.7457,
"step": 2930
},
{
"epoch": 3.75,
"learning_rate": 3.0965722657037587e-07,
"loss": 1.7451,
"step": 2932
},
{
"epoch": 3.76,
"learning_rate": 3.0845781439753994e-07,
"loss": 1.7325,
"step": 2934
},
{
"epoch": 3.76,
"learning_rate": 3.0726030587734207e-07,
"loss": 1.7204,
"step": 2936
},
{
"epoch": 3.76,
"learning_rate": 3.060647043062412e-07,
"loss": 1.7569,
"step": 2938
},
{
"epoch": 3.76,
"learning_rate": 3.048710129754464e-07,
"loss": 1.7254,
"step": 2940
},
{
"epoch": 3.77,
"learning_rate": 3.0367923517090897e-07,
"loss": 1.6894,
"step": 2942
},
{
"epoch": 3.77,
"learning_rate": 3.02489374173312e-07,
"loss": 1.6881,
"step": 2944
},
{
"epoch": 3.77,
"learning_rate": 3.01301433258062e-07,
"loss": 1.7329,
"step": 2946
},
{
"epoch": 3.77,
"learning_rate": 3.0011541569528065e-07,
"loss": 1.6985,
"step": 2948
},
{
"epoch": 3.78,
"learning_rate": 2.9893132474979465e-07,
"loss": 1.6939,
"step": 2950
},
{
"epoch": 3.78,
"learning_rate": 2.977491636811278e-07,
"loss": 1.7388,
"step": 2952
},
{
"epoch": 3.78,
"learning_rate": 2.965689357434904e-07,
"loss": 1.6622,
"step": 2954
},
{
"epoch": 3.78,
"learning_rate": 2.9539064418577154e-07,
"loss": 1.7515,
"step": 2956
},
{
"epoch": 3.79,
"learning_rate": 2.942142922515305e-07,
"loss": 1.6769,
"step": 2958
},
{
"epoch": 3.79,
"learning_rate": 2.930398831789868e-07,
"loss": 1.7089,
"step": 2960
},
{
"epoch": 3.79,
"learning_rate": 2.918674202010121e-07,
"loss": 1.6385,
"step": 2962
},
{
"epoch": 3.79,
"learning_rate": 2.9069690654512036e-07,
"loss": 1.7065,
"step": 2964
},
{
"epoch": 3.8,
"learning_rate": 2.895283454334594e-07,
"loss": 1.7135,
"step": 2966
},
{
"epoch": 3.8,
"learning_rate": 2.88361740082803e-07,
"loss": 1.7676,
"step": 2968
},
{
"epoch": 3.8,
"learning_rate": 2.871970937045406e-07,
"loss": 1.7283,
"step": 2970
},
{
"epoch": 3.8,
"learning_rate": 2.860344095046695e-07,
"loss": 1.7918,
"step": 2972
},
{
"epoch": 3.81,
"learning_rate": 2.8487369068378463e-07,
"loss": 1.6793,
"step": 2974
},
{
"epoch": 3.81,
"learning_rate": 2.83714940437072e-07,
"loss": 1.7446,
"step": 2976
},
{
"epoch": 3.81,
"learning_rate": 2.8255816195429713e-07,
"loss": 1.6963,
"step": 2978
},
{
"epoch": 3.81,
"learning_rate": 2.8140335841979903e-07,
"loss": 1.637,
"step": 2980
},
{
"epoch": 3.82,
"learning_rate": 2.802505330124798e-07,
"loss": 1.7529,
"step": 2982
},
{
"epoch": 3.82,
"learning_rate": 2.7909968890579563e-07,
"loss": 1.6938,
"step": 2984
},
{
"epoch": 3.82,
"learning_rate": 2.779508292677495e-07,
"loss": 1.7465,
"step": 2986
},
{
"epoch": 3.82,
"learning_rate": 2.768039572608807e-07,
"loss": 1.7312,
"step": 2988
},
{
"epoch": 3.83,
"learning_rate": 2.756590760422578e-07,
"loss": 1.7191,
"step": 2990
},
{
"epoch": 3.83,
"learning_rate": 2.7451618876346927e-07,
"loss": 1.7555,
"step": 2992
},
{
"epoch": 3.83,
"learning_rate": 2.733752985706137e-07,
"loss": 1.7363,
"step": 2994
},
{
"epoch": 3.83,
"learning_rate": 2.7223640860429374e-07,
"loss": 1.7193,
"step": 2996
},
{
"epoch": 3.84,
"learning_rate": 2.7109952199960417e-07,
"loss": 1.6694,
"step": 2998
},
{
"epoch": 3.84,
"learning_rate": 2.6996464188612634e-07,
"loss": 1.6661,
"step": 3000
},
{
"epoch": 3.84,
"learning_rate": 2.6883177138791777e-07,
"loss": 1.714,
"step": 3002
},
{
"epoch": 3.85,
"learning_rate": 2.6770091362350357e-07,
"loss": 1.7145,
"step": 3004
},
{
"epoch": 3.85,
"learning_rate": 2.665720717058688e-07,
"loss": 1.7151,
"step": 3006
},
{
"epoch": 3.85,
"learning_rate": 2.654452487424494e-07,
"loss": 1.7233,
"step": 3008
},
{
"epoch": 3.85,
"learning_rate": 2.643204478351231e-07,
"loss": 1.7022,
"step": 3010
},
{
"epoch": 3.86,
"learning_rate": 2.6375880662031e-07,
"loss": 1.7129,
"step": 3012
},
{
"epoch": 3.86,
"learning_rate": 2.626370446009661e-07,
"loss": 1.7054,
"step": 3014
},
{
"epoch": 3.86,
"learning_rate": 2.6207692456842246e-07,
"loss": 1.7009,
"step": 3016
},
{
"epoch": 3.86,
"learning_rate": 2.6095820838493866e-07,
"loss": 1.6808,
"step": 3018
},
{
"epoch": 3.87,
"learning_rate": 2.598415266093128e-07,
"loss": 1.7333,
"step": 3020
},
{
"epoch": 3.87,
"learning_rate": 2.587268823155061e-07,
"loss": 1.7043,
"step": 3022
},
{
"epoch": 3.87,
"learning_rate": 2.576142785718721e-07,
"loss": 1.6746,
"step": 3024
},
{
"epoch": 3.87,
"learning_rate": 2.5650371844114613e-07,
"loss": 1.7619,
"step": 3026
},
{
"epoch": 3.88,
"learning_rate": 2.553952049804388e-07,
"loss": 1.6781,
"step": 3028
},
{
"epoch": 3.88,
"learning_rate": 2.542887412412265e-07,
"loss": 1.6487,
"step": 3030
},
{
"epoch": 3.88,
"learning_rate": 2.531843302693426e-07,
"loss": 1.7854,
"step": 3032
},
{
"epoch": 3.88,
"learning_rate": 2.5208197510497076e-07,
"loss": 1.7068,
"step": 3034
},
{
"epoch": 3.89,
"learning_rate": 2.5098167878263445e-07,
"loss": 1.7307,
"step": 3036
},
{
"epoch": 3.89,
"learning_rate": 2.4988344433119037e-07,
"loss": 1.7006,
"step": 3038
},
{
"epoch": 3.89,
"learning_rate": 2.4878727477381886e-07,
"loss": 1.7459,
"step": 3040
},
{
"epoch": 3.89,
"learning_rate": 2.4769317312801705e-07,
"loss": 1.7071,
"step": 3042
},
{
"epoch": 3.9,
"learning_rate": 2.466011424055883e-07,
"loss": 1.7222,
"step": 3044
},
{
"epoch": 3.9,
"learning_rate": 2.455111856126355e-07,
"loss": 1.7639,
"step": 3046
},
{
"epoch": 3.9,
"learning_rate": 2.4442330574955315e-07,
"loss": 1.7381,
"step": 3048
},
{
"epoch": 3.9,
"learning_rate": 2.433375058110182e-07,
"loss": 1.7169,
"step": 3050
},
{
"epoch": 3.91,
"learning_rate": 2.422537887859821e-07,
"loss": 1.7337,
"step": 3052
},
{
"epoch": 3.91,
"learning_rate": 2.411721576576622e-07,
"loss": 1.765,
"step": 3054
},
{
"epoch": 3.91,
"learning_rate": 2.400926154035335e-07,
"loss": 1.7118,
"step": 3056
},
{
"epoch": 3.91,
"learning_rate": 2.3901516499532217e-07,
"loss": 1.7446,
"step": 3058
},
{
"epoch": 3.92,
"learning_rate": 2.379398093989947e-07,
"loss": 1.7302,
"step": 3060
},
{
"epoch": 3.92,
"learning_rate": 2.368665515747522e-07,
"loss": 1.6904,
"step": 3062
},
{
"epoch": 3.92,
"learning_rate": 2.3579539447702003e-07,
"loss": 1.7352,
"step": 3064
},
{
"epoch": 3.92,
"learning_rate": 2.34726341054441e-07,
"loss": 1.712,
"step": 3066
},
{
"epoch": 3.93,
"learning_rate": 2.336593942498676e-07,
"loss": 1.7018,
"step": 3068
},
{
"epoch": 3.93,
"learning_rate": 2.3259455700035258e-07,
"loss": 1.6936,
"step": 3070
},
{
"epoch": 3.93,
"learning_rate": 2.3153183223714245e-07,
"loss": 1.7495,
"step": 3072
},
{
"epoch": 3.93,
"learning_rate": 2.3047122288566745e-07,
"loss": 1.732,
"step": 3074
},
{
"epoch": 3.94,
"learning_rate": 2.2941273186553556e-07,
"loss": 1.6828,
"step": 3076
},
{
"epoch": 3.94,
"learning_rate": 2.2835636209052244e-07,
"loss": 1.7184,
"step": 3078
},
{
"epoch": 3.94,
"learning_rate": 2.2730211646856569e-07,
"loss": 1.7153,
"step": 3080
},
{
"epoch": 3.94,
"learning_rate": 2.2624999790175492e-07,
"loss": 1.7347,
"step": 3082
},
{
"epoch": 3.95,
"learning_rate": 2.252000092863242e-07,
"loss": 1.6867,
"step": 3084
},
{
"epoch": 3.95,
"learning_rate": 2.2415215351264526e-07,
"loss": 1.7274,
"step": 3086
},
{
"epoch": 3.95,
"learning_rate": 2.2310643346521752e-07,
"loss": 1.7072,
"step": 3088
},
{
"epoch": 3.96,
"learning_rate": 2.2206285202266196e-07,
"loss": 1.7311,
"step": 3090
},
{
"epoch": 3.96,
"learning_rate": 2.2102141205771274e-07,
"loss": 1.7562,
"step": 3092
},
{
"epoch": 3.96,
"learning_rate": 2.1998211643720788e-07,
"loss": 1.6817,
"step": 3094
},
{
"epoch": 3.96,
"learning_rate": 2.1894496802208363e-07,
"loss": 1.7242,
"step": 3096
},
{
"epoch": 3.97,
"learning_rate": 2.1790996966736542e-07,
"loss": 1.73,
"step": 3098
},
{
"epoch": 3.97,
"learning_rate": 2.168771242221592e-07,
"loss": 1.7511,
"step": 3100
},
{
"epoch": 3.97,
"learning_rate": 2.1584643452964568e-07,
"loss": 1.7194,
"step": 3102
},
{
"epoch": 3.97,
"learning_rate": 2.1481790342706983e-07,
"loss": 1.6974,
"step": 3104
},
{
"epoch": 3.98,
"learning_rate": 2.137915337457359e-07,
"loss": 1.7217,
"step": 3106
},
{
"epoch": 3.98,
"learning_rate": 2.1276732831099774e-07,
"loss": 1.6785,
"step": 3108
},
{
"epoch": 3.98,
"learning_rate": 2.1174528994225127e-07,
"loss": 1.7027,
"step": 3110
},
{
"epoch": 3.98,
"learning_rate": 2.1072542145292738e-07,
"loss": 1.7174,
"step": 3112
},
{
"epoch": 3.99,
"learning_rate": 2.0970772565048345e-07,
"loss": 1.6776,
"step": 3114
},
{
"epoch": 3.99,
"learning_rate": 2.086922053363961e-07,
"loss": 1.6972,
"step": 3116
},
{
"epoch": 3.99,
"learning_rate": 2.0767886330615391e-07,
"loss": 1.739,
"step": 3118
},
{
"epoch": 3.99,
"learning_rate": 2.0666770234924803e-07,
"loss": 1.6911,
"step": 3120
},
{
"epoch": 4.0,
"learning_rate": 2.0565872524916672e-07,
"loss": 1.7745,
"step": 3122
},
{
"epoch": 4.0,
"learning_rate": 2.0465193478338572e-07,
"loss": 1.7669,
"step": 3124
},
{
"epoch": 4.0,
"learning_rate": 2.0364733372336197e-07,
"loss": 1.7336,
"step": 3126
},
{
"epoch": 4.0,
"learning_rate": 2.0264492483452544e-07,
"loss": 1.6707,
"step": 3128
},
{
"epoch": 4.01,
"learning_rate": 2.0164471087627187e-07,
"loss": 1.6787,
"step": 3130
},
{
"epoch": 4.01,
"learning_rate": 2.0064669460195427e-07,
"loss": 1.7261,
"step": 3132
},
{
"epoch": 4.01,
"learning_rate": 1.9965087875887588e-07,
"loss": 1.7131,
"step": 3134
},
{
"epoch": 4.01,
"learning_rate": 1.9865726608828327e-07,
"loss": 1.7338,
"step": 3136
},
{
"epoch": 4.02,
"learning_rate": 1.9766585932535796e-07,
"loss": 1.7418,
"step": 3138
},
{
"epoch": 4.02,
"learning_rate": 1.9667666119920933e-07,
"loss": 1.6556,
"step": 3140
},
{
"epoch": 4.02,
"learning_rate": 1.9568967443286643e-07,
"loss": 1.735,
"step": 3142
},
{
"epoch": 4.02,
"learning_rate": 1.947049017432708e-07,
"loss": 1.7191,
"step": 3144
},
{
"epoch": 4.03,
"learning_rate": 1.9372234584127e-07,
"loss": 1.6939,
"step": 3146
},
{
"epoch": 4.03,
"learning_rate": 1.927420094316088e-07,
"loss": 1.6494,
"step": 3148
},
{
"epoch": 4.03,
"learning_rate": 1.9176389521292236e-07,
"loss": 1.7454,
"step": 3150
},
{
"epoch": 4.03,
"learning_rate": 1.907880058777286e-07,
"loss": 1.6877,
"step": 3152
},
{
"epoch": 4.04,
"learning_rate": 1.8981434411242026e-07,
"loss": 1.744,
"step": 3154
},
{
"epoch": 4.04,
"learning_rate": 1.8884291259725915e-07,
"loss": 1.6577,
"step": 3156
},
{
"epoch": 4.04,
"learning_rate": 1.878737140063672e-07,
"loss": 1.7261,
"step": 3158
},
{
"epoch": 4.04,
"learning_rate": 1.869067510077197e-07,
"loss": 1.7241,
"step": 3160
},
{
"epoch": 4.05,
"learning_rate": 1.8594202626313804e-07,
"loss": 1.7092,
"step": 3162
},
{
"epoch": 4.05,
"learning_rate": 1.8497954242828195e-07,
"loss": 1.7007,
"step": 3164
},
{
"epoch": 4.05,
"learning_rate": 1.8401930215264228e-07,
"loss": 1.6673,
"step": 3166
},
{
"epoch": 4.06,
"learning_rate": 1.8306130807953436e-07,
"loss": 1.6156,
"step": 3168
},
{
"epoch": 4.06,
"learning_rate": 1.8210556284609002e-07,
"loss": 1.6996,
"step": 3170
},
{
"epoch": 4.06,
"learning_rate": 1.811520690832511e-07,
"loss": 1.7123,
"step": 3172
},
{
"epoch": 4.06,
"learning_rate": 1.8020082941576064e-07,
"loss": 1.7114,
"step": 3174
},
{
"epoch": 4.07,
"learning_rate": 1.7925184646215718e-07,
"loss": 1.7183,
"step": 3176
},
{
"epoch": 4.07,
"learning_rate": 1.783051228347674e-07,
"loss": 1.7159,
"step": 3178
},
{
"epoch": 4.07,
"learning_rate": 1.7736066113969806e-07,
"loss": 1.6925,
"step": 3180
},
{
"epoch": 4.07,
"learning_rate": 1.7641846397683013e-07,
"loss": 1.7117,
"step": 3182
},
{
"epoch": 4.08,
"learning_rate": 1.7547853393980982e-07,
"loss": 1.7223,
"step": 3184
},
{
"epoch": 4.08,
"learning_rate": 1.7454087361604298e-07,
"loss": 1.6937,
"step": 3186
},
{
"epoch": 4.08,
"learning_rate": 1.7360548558668743e-07,
"loss": 1.6818,
"step": 3188
},
{
"epoch": 4.08,
"learning_rate": 1.7267237242664623e-07,
"loss": 1.6717,
"step": 3190
},
{
"epoch": 4.09,
"learning_rate": 1.7174153670456003e-07,
"loss": 1.7032,
"step": 3192
},
{
"epoch": 4.09,
"learning_rate": 1.7081298098279972e-07,
"loss": 1.6447,
"step": 3194
},
{
"epoch": 4.09,
"learning_rate": 1.6988670781746084e-07,
"loss": 1.7154,
"step": 3196
},
{
"epoch": 4.09,
"learning_rate": 1.6896271975835462e-07,
"loss": 1.699,
"step": 3198
},
{
"epoch": 4.1,
"learning_rate": 1.6804101934900283e-07,
"loss": 1.686,
"step": 3200
},
{
"epoch": 4.1,
"learning_rate": 1.6712160912662898e-07,
"loss": 1.7066,
"step": 3202
},
{
"epoch": 4.1,
"learning_rate": 1.6620449162215312e-07,
"loss": 1.6741,
"step": 3204
},
{
"epoch": 4.1,
"learning_rate": 1.652896693601835e-07,
"loss": 1.6564,
"step": 3206
},
{
"epoch": 4.11,
"learning_rate": 1.643771448590099e-07,
"loss": 1.6937,
"step": 3208
},
{
"epoch": 4.11,
"learning_rate": 1.6346692063059765e-07,
"loss": 1.7722,
"step": 3210
},
{
"epoch": 4.11,
"learning_rate": 1.6255899918057902e-07,
"loss": 1.7238,
"step": 3212
},
{
"epoch": 4.11,
"learning_rate": 1.6165338300824794e-07,
"loss": 1.7136,
"step": 3214
},
{
"epoch": 4.12,
"learning_rate": 1.6075007460655265e-07,
"loss": 1.6716,
"step": 3216
},
{
"epoch": 4.12,
"learning_rate": 1.5984907646208768e-07,
"loss": 1.7446,
"step": 3218
},
{
"epoch": 4.12,
"learning_rate": 1.58950391055089e-07,
"loss": 1.6996,
"step": 3220
},
{
"epoch": 4.12,
"learning_rate": 1.5805402085942532e-07,
"loss": 1.7073,
"step": 3222
},
{
"epoch": 4.13,
"learning_rate": 1.571599683425926e-07,
"loss": 1.7165,
"step": 3224
},
{
"epoch": 4.13,
"learning_rate": 1.5626823596570693e-07,
"loss": 1.6742,
"step": 3226
},
{
"epoch": 4.13,
"learning_rate": 1.5537882618349752e-07,
"loss": 1.6698,
"step": 3228
},
{
"epoch": 4.13,
"learning_rate": 1.5449174144429945e-07,
"loss": 1.7382,
"step": 3230
},
{
"epoch": 4.14,
"learning_rate": 1.536069841900479e-07,
"loss": 1.6836,
"step": 3232
},
{
"epoch": 4.14,
"learning_rate": 1.5272455685627118e-07,
"loss": 1.7285,
"step": 3234
},
{
"epoch": 4.14,
"learning_rate": 1.5184446187208365e-07,
"loss": 1.7055,
"step": 3236
},
{
"epoch": 4.14,
"learning_rate": 1.509667016601799e-07,
"loss": 1.7006,
"step": 3238
},
{
"epoch": 4.15,
"learning_rate": 1.5009127863682636e-07,
"loss": 1.7094,
"step": 3240
},
{
"epoch": 4.15,
"learning_rate": 1.492181952118562e-07,
"loss": 1.7013,
"step": 3242
},
{
"epoch": 4.15,
"learning_rate": 1.4834745378866242e-07,
"loss": 1.7054,
"step": 3244
},
{
"epoch": 4.15,
"learning_rate": 1.4747905676419105e-07,
"loss": 1.6952,
"step": 3246
},
{
"epoch": 4.16,
"learning_rate": 1.466130065289346e-07,
"loss": 1.6888,
"step": 3248
},
{
"epoch": 4.16,
"learning_rate": 1.4574930546692489e-07,
"loss": 1.7329,
"step": 3250
},
{
"epoch": 4.16,
"learning_rate": 1.4488795595572733e-07,
"loss": 1.7524,
"step": 3252
},
{
"epoch": 4.17,
"learning_rate": 1.440289603664343e-07,
"loss": 1.6873,
"step": 3254
},
{
"epoch": 4.17,
"learning_rate": 1.4317232106365805e-07,
"loss": 1.6874,
"step": 3256
},
{
"epoch": 4.17,
"learning_rate": 1.4231804040552476e-07,
"loss": 1.6717,
"step": 3258
},
{
"epoch": 4.17,
"learning_rate": 1.4146612074366792e-07,
"loss": 1.7065,
"step": 3260
},
{
"epoch": 4.18,
"learning_rate": 1.4061656442322134e-07,
"loss": 1.6688,
"step": 3262
},
{
"epoch": 4.18,
"learning_rate": 1.3976937378281317e-07,
"loss": 1.6604,
"step": 3264
},
{
"epoch": 4.18,
"learning_rate": 1.389245511545597e-07,
"loss": 1.7284,
"step": 3266
},
{
"epoch": 4.18,
"learning_rate": 1.3808209886405854e-07,
"loss": 1.7139,
"step": 3268
},
{
"epoch": 4.19,
"learning_rate": 1.3724201923038247e-07,
"loss": 1.7482,
"step": 3270
},
{
"epoch": 4.19,
"learning_rate": 1.364043145660725e-07,
"loss": 1.6513,
"step": 3272
},
{
"epoch": 4.19,
"learning_rate": 1.3556898717713195e-07,
"loss": 1.7275,
"step": 3274
},
{
"epoch": 4.19,
"learning_rate": 1.3473603936302035e-07,
"loss": 1.652,
"step": 3276
},
{
"epoch": 4.2,
"learning_rate": 1.3390547341664672e-07,
"loss": 1.6625,
"step": 3278
},
{
"epoch": 4.2,
"learning_rate": 1.3307729162436365e-07,
"loss": 1.6643,
"step": 3280
},
{
"epoch": 4.2,
"learning_rate": 1.3225149626596023e-07,
"loss": 1.6935,
"step": 3282
},
{
"epoch": 4.2,
"learning_rate": 1.31428089614656e-07,
"loss": 1.6755,
"step": 3284
},
{
"epoch": 4.21,
"learning_rate": 1.306070739370958e-07,
"loss": 1.7038,
"step": 3286
},
{
"epoch": 4.21,
"learning_rate": 1.2978845149334216e-07,
"loss": 1.6859,
"step": 3288
},
{
"epoch": 4.21,
"learning_rate": 1.2897222453687007e-07,
"loss": 1.6954,
"step": 3290
},
{
"epoch": 4.21,
"learning_rate": 1.281583953145594e-07,
"loss": 1.709,
"step": 3292
},
{
"epoch": 4.22,
"learning_rate": 1.273469660666906e-07,
"loss": 1.7255,
"step": 3294
},
{
"epoch": 4.22,
"learning_rate": 1.2653793902693687e-07,
"loss": 1.711,
"step": 3296
},
{
"epoch": 4.22,
"learning_rate": 1.2573131642235901e-07,
"loss": 1.6828,
"step": 3298
},
{
"epoch": 4.22,
"learning_rate": 1.2492710047339915e-07,
"loss": 1.6988,
"step": 3300
},
{
"epoch": 4.23,
"learning_rate": 1.241252933938739e-07,
"loss": 1.6929,
"step": 3302
},
{
"epoch": 4.23,
"learning_rate": 1.2332589739096944e-07,
"loss": 1.708,
"step": 3304
},
{
"epoch": 4.23,
"learning_rate": 1.225289146652343e-07,
"loss": 1.665,
"step": 3306
},
{
"epoch": 4.23,
"learning_rate": 1.217343474105742e-07,
"loss": 1.6689,
"step": 3308
},
{
"epoch": 4.24,
"learning_rate": 1.2094219781424565e-07,
"loss": 1.704,
"step": 3310
},
{
"epoch": 4.24,
"learning_rate": 1.2015246805684952e-07,
"loss": 1.7255,
"step": 3312
},
{
"epoch": 4.24,
"learning_rate": 1.193651603123258e-07,
"loss": 1.7532,
"step": 3314
},
{
"epoch": 4.24,
"learning_rate": 1.1858027674794735e-07,
"loss": 1.6486,
"step": 3316
},
{
"epoch": 4.25,
"learning_rate": 1.1779781952431312e-07,
"loss": 1.6976,
"step": 3318
},
{
"epoch": 4.25,
"learning_rate": 1.1701779079534402e-07,
"loss": 1.6852,
"step": 3320
},
{
"epoch": 4.25,
"learning_rate": 1.1624019270827478e-07,
"loss": 1.698,
"step": 3322
},
{
"epoch": 4.25,
"learning_rate": 1.1546502740364983e-07,
"loss": 1.7164,
"step": 3324
},
{
"epoch": 4.26,
"learning_rate": 1.146922970153168e-07,
"loss": 1.7238,
"step": 3326
},
{
"epoch": 4.26,
"learning_rate": 1.1392200367042004e-07,
"loss": 1.6902,
"step": 3328
},
{
"epoch": 4.26,
"learning_rate": 1.131541494893955e-07,
"loss": 1.6727,
"step": 3330
},
{
"epoch": 4.26,
"learning_rate": 1.1238873658596482e-07,
"loss": 1.6673,
"step": 3332
},
{
"epoch": 4.27,
"learning_rate": 1.1162576706712934e-07,
"loss": 1.7185,
"step": 3334
},
{
"epoch": 4.27,
"learning_rate": 1.1086524303316447e-07,
"loss": 1.6936,
"step": 3336
},
{
"epoch": 4.27,
"learning_rate": 1.1010716657761354e-07,
"loss": 1.698,
"step": 3338
},
{
"epoch": 4.28,
"learning_rate": 1.0935153978728218e-07,
"loss": 1.6868,
"step": 3340
},
{
"epoch": 4.28,
"learning_rate": 1.0859836474223283e-07,
"loss": 1.6824,
"step": 3342
},
{
"epoch": 4.28,
"learning_rate": 1.0784764351577902e-07,
"loss": 1.6788,
"step": 3344
},
{
"epoch": 4.28,
"learning_rate": 1.0709937817447934e-07,
"loss": 1.6996,
"step": 3346
},
{
"epoch": 4.29,
"learning_rate": 1.0635357077813201e-07,
"loss": 1.7371,
"step": 3348
},
{
"epoch": 4.29,
"learning_rate": 1.0561022337976888e-07,
"loss": 1.7239,
"step": 3350
},
{
"epoch": 4.29,
"learning_rate": 1.048693380256499e-07,
"loss": 1.7078,
"step": 3352
},
{
"epoch": 4.29,
"learning_rate": 1.0413091675525809e-07,
"loss": 1.6648,
"step": 3354
},
{
"epoch": 4.3,
"learning_rate": 1.0339496160129302e-07,
"loss": 1.6738,
"step": 3356
},
{
"epoch": 4.3,
"learning_rate": 1.0266147458966612e-07,
"loss": 1.6922,
"step": 3358
},
{
"epoch": 4.3,
"learning_rate": 1.0193045773949394e-07,
"loss": 1.7022,
"step": 3360
},
{
"epoch": 4.3,
"learning_rate": 1.0120191306309334e-07,
"loss": 1.7019,
"step": 3362
},
{
"epoch": 4.31,
"learning_rate": 1.004758425659764e-07,
"loss": 1.7304,
"step": 3364
},
{
"epoch": 4.31,
"learning_rate": 9.975224824684392e-08,
"loss": 1.7477,
"step": 3366
},
{
"epoch": 4.31,
"learning_rate": 9.903113209758096e-08,
"loss": 1.6761,
"step": 3368
},
{
"epoch": 4.31,
"learning_rate": 9.831249610324977e-08,
"loss": 1.6862,
"step": 3370
},
{
"epoch": 4.32,
"learning_rate": 9.75963422420859e-08,
"loss": 1.7484,
"step": 3372
},
{
"epoch": 4.32,
"learning_rate": 9.688267248549231e-08,
"loss": 1.6503,
"step": 3374
},
{
"epoch": 4.32,
"learning_rate": 9.61714887980336e-08,
"loss": 1.6984,
"step": 3376
},
{
"epoch": 4.32,
"learning_rate": 9.546279313743089e-08,
"loss": 1.7249,
"step": 3378
},
{
"epoch": 4.33,
"learning_rate": 9.475658745455617e-08,
"loss": 1.6661,
"step": 3380
},
{
"epoch": 4.33,
"learning_rate": 9.40528736934273e-08,
"loss": 1.7115,
"step": 3382
},
{
"epoch": 4.33,
"learning_rate": 9.335165379120224e-08,
"loss": 1.6741,
"step": 3384
},
{
"epoch": 4.33,
"learning_rate": 9.265292967817428e-08,
"loss": 1.779,
"step": 3386
},
{
"epoch": 4.34,
"learning_rate": 9.195670327776627e-08,
"loss": 1.6652,
"step": 3388
},
{
"epoch": 4.34,
"learning_rate": 9.126297650652514e-08,
"loss": 1.7105,
"step": 3390
},
{
"epoch": 4.34,
"learning_rate": 9.057175127411754e-08,
"loss": 1.6798,
"step": 3392
},
{
"epoch": 4.34,
"learning_rate": 8.988302948332316e-08,
"loss": 1.6792,
"step": 3394
},
{
"epoch": 4.35,
"learning_rate": 8.919681303003102e-08,
"loss": 1.6992,
"step": 3396
},
{
"epoch": 4.35,
"learning_rate": 8.85131038032334e-08,
"loss": 1.6795,
"step": 3398
},
{
"epoch": 4.35,
"learning_rate": 8.783190368502025e-08,
"loss": 1.6653,
"step": 3400
},
{
"epoch": 4.35,
"learning_rate": 8.715321455057534e-08,
"loss": 1.7712,
"step": 3402
},
{
"epoch": 4.36,
"learning_rate": 8.647703826816966e-08,
"loss": 1.7148,
"step": 3404
},
{
"epoch": 4.36,
"learning_rate": 8.580337669915705e-08,
"loss": 1.6741,
"step": 3406
},
{
"epoch": 4.36,
"learning_rate": 8.513223169796946e-08,
"loss": 1.7244,
"step": 3408
},
{
"epoch": 4.36,
"learning_rate": 8.446360511211037e-08,
"loss": 1.6875,
"step": 3410
},
{
"epoch": 4.37,
"learning_rate": 8.379749878215148e-08,
"loss": 1.6941,
"step": 3412
},
{
"epoch": 4.37,
"learning_rate": 8.313391454172647e-08,
"loss": 1.6502,
"step": 3414
},
{
"epoch": 4.37,
"learning_rate": 8.247285421752625e-08,
"loss": 1.7092,
"step": 3416
},
{
"epoch": 4.38,
"learning_rate": 8.18143196292942e-08,
"loss": 1.7503,
"step": 3418
},
{
"epoch": 4.38,
"learning_rate": 8.115831258982064e-08,
"loss": 1.6918,
"step": 3420
},
{
"epoch": 4.38,
"learning_rate": 8.050483490493854e-08,
"loss": 1.6786,
"step": 3422
},
{
"epoch": 4.38,
"learning_rate": 7.985388837351792e-08,
"loss": 1.667,
"step": 3424
},
{
"epoch": 4.39,
"learning_rate": 7.920547478746087e-08,
"loss": 1.6706,
"step": 3426
},
{
"epoch": 4.39,
"learning_rate": 7.855959593169759e-08,
"loss": 1.7382,
"step": 3428
},
{
"epoch": 4.39,
"learning_rate": 7.791625358417997e-08,
"loss": 1.6842,
"step": 3430
},
{
"epoch": 4.39,
"learning_rate": 7.727544951587795e-08,
"loss": 1.67,
"step": 3432
},
{
"epoch": 4.4,
"learning_rate": 7.663718549077435e-08,
"loss": 1.7736,
"step": 3434
},
{
"epoch": 4.4,
"learning_rate": 7.60014632658591e-08,
"loss": 1.6972,
"step": 3436
},
{
"epoch": 4.4,
"learning_rate": 7.53682845911262e-08,
"loss": 1.7332,
"step": 3438
},
{
"epoch": 4.4,
"learning_rate": 7.473765120956676e-08,
"loss": 1.6818,
"step": 3440
},
{
"epoch": 4.41,
"learning_rate": 7.410956485716613e-08,
"loss": 1.6999,
"step": 3442
},
{
"epoch": 4.41,
"learning_rate": 7.348402726289804e-08,
"loss": 1.678,
"step": 3444
},
{
"epoch": 4.41,
"learning_rate": 7.286104014872008e-08,
"loss": 1.6956,
"step": 3446
},
{
"epoch": 4.41,
"learning_rate": 7.224060522956876e-08,
"loss": 1.6851,
"step": 3448
},
{
"epoch": 4.42,
"learning_rate": 7.162272421335513e-08,
"loss": 1.6943,
"step": 3450
},
{
"epoch": 4.42,
"learning_rate": 7.100739880096007e-08,
"loss": 1.7076,
"step": 3452
},
{
"epoch": 4.42,
"learning_rate": 7.039463068622942e-08,
"loss": 1.7234,
"step": 3454
},
{
"epoch": 4.42,
"learning_rate": 6.978442155596964e-08,
"loss": 1.7327,
"step": 3456
},
{
"epoch": 4.43,
"learning_rate": 6.91767730899423e-08,
"loss": 1.6904,
"step": 3458
},
{
"epoch": 4.43,
"learning_rate": 6.857168696086036e-08,
"loss": 1.7062,
"step": 3460
},
{
"epoch": 4.43,
"learning_rate": 6.796916483438331e-08,
"loss": 1.7382,
"step": 3462
},
{
"epoch": 4.43,
"learning_rate": 6.736920836911275e-08,
"loss": 1.6858,
"step": 3464
},
{
"epoch": 4.44,
"learning_rate": 6.677181921658758e-08,
"loss": 1.6949,
"step": 3466
},
{
"epoch": 4.44,
"learning_rate": 6.617699902127905e-08,
"loss": 1.7112,
"step": 3468
},
{
"epoch": 4.44,
"learning_rate": 6.558474942058678e-08,
"loss": 1.6983,
"step": 3470
},
{
"epoch": 4.44,
"learning_rate": 6.499507204483457e-08,
"loss": 1.7315,
"step": 3472
},
{
"epoch": 4.45,
"learning_rate": 6.440796851726516e-08,
"loss": 1.7329,
"step": 3474
},
{
"epoch": 4.45,
"learning_rate": 6.382344045403643e-08,
"loss": 1.7181,
"step": 3476
},
{
"epoch": 4.45,
"learning_rate": 6.324148946421604e-08,
"loss": 1.6792,
"step": 3478
},
{
"epoch": 4.45,
"learning_rate": 6.26621171497782e-08,
"loss": 1.7048,
"step": 3480
},
{
"epoch": 4.46,
"learning_rate": 6.208532510559795e-08,
"loss": 1.7114,
"step": 3482
},
{
"epoch": 4.46,
"learning_rate": 6.151111491944805e-08,
"loss": 1.7136,
"step": 3484
},
{
"epoch": 4.46,
"learning_rate": 6.09394881719939e-08,
"loss": 1.7417,
"step": 3486
},
{
"epoch": 4.46,
"learning_rate": 6.037044643678901e-08,
"loss": 1.738,
"step": 3488
},
{
"epoch": 4.47,
"learning_rate": 5.980399128027136e-08,
"loss": 1.6914,
"step": 3490
},
{
"epoch": 4.47,
"learning_rate": 5.924012426175829e-08,
"loss": 1.7019,
"step": 3492
},
{
"epoch": 4.47,
"learning_rate": 5.867884693344272e-08,
"loss": 1.7239,
"step": 3494
},
{
"epoch": 4.47,
"learning_rate": 5.812016084038929e-08,
"loss": 1.6987,
"step": 3496
},
{
"epoch": 4.48,
"learning_rate": 5.7564067520528557e-08,
"loss": 1.6852,
"step": 3498
},
{
"epoch": 4.48,
"learning_rate": 5.70105685046548e-08,
"loss": 1.7321,
"step": 3500
},
{
"epoch": 4.48,
"learning_rate": 5.645966531641999e-08,
"loss": 1.7221,
"step": 3502
},
{
"epoch": 4.49,
"learning_rate": 5.5911359472330945e-08,
"loss": 1.7158,
"step": 3504
},
{
"epoch": 4.49,
"learning_rate": 5.536565248174463e-08,
"loss": 1.674,
"step": 3506
},
{
"epoch": 4.49,
"learning_rate": 5.48225458468633e-08,
"loss": 1.6944,
"step": 3508
},
{
"epoch": 4.49,
"learning_rate": 5.428204106273182e-08,
"loss": 1.6997,
"step": 3510
},
{
"epoch": 4.5,
"learning_rate": 5.374413961723257e-08,
"loss": 1.7045,
"step": 3512
},
{
"epoch": 4.5,
"learning_rate": 5.320884299108097e-08,
"loss": 1.7023,
"step": 3514
},
{
"epoch": 4.5,
"learning_rate": 5.26761526578231e-08,
"loss": 1.7252,
"step": 3516
},
{
"epoch": 4.5,
"learning_rate": 5.214607008382921e-08,
"loss": 1.7038,
"step": 3518
},
{
"epoch": 4.51,
"learning_rate": 5.161859672829216e-08,
"loss": 1.7423,
"step": 3520
},
{
"epoch": 4.51,
"learning_rate": 5.1093734043221704e-08,
"loss": 1.7427,
"step": 3522
},
{
"epoch": 4.51,
"learning_rate": 5.057148347344098e-08,
"loss": 1.7575,
"step": 3524
},
{
"epoch": 4.51,
"learning_rate": 5.005184645658278e-08,
"loss": 1.7064,
"step": 3526
},
{
"epoch": 4.52,
"learning_rate": 4.953482442308521e-08,
"loss": 1.6722,
"step": 3528
},
{
"epoch": 4.52,
"learning_rate": 4.902041879618823e-08,
"loss": 1.7063,
"step": 3530
},
{
"epoch": 4.52,
"learning_rate": 4.850863099192926e-08,
"loss": 1.6983,
"step": 3532
},
{
"epoch": 4.52,
"learning_rate": 4.799946241913944e-08,
"loss": 1.6463,
"step": 3534
},
{
"epoch": 4.53,
"learning_rate": 4.7492914479439924e-08,
"loss": 1.713,
"step": 3536
},
{
"epoch": 4.53,
"learning_rate": 4.6988988567237544e-08,
"loss": 1.69,
"step": 3538
},
{
"epoch": 4.53,
"learning_rate": 4.6487686069721755e-08,
"loss": 1.7067,
"step": 3540
},
{
"epoch": 4.53,
"learning_rate": 4.598900836686026e-08,
"loss": 1.7104,
"step": 3542
},
{
"epoch": 4.54,
"learning_rate": 4.54929568313952e-08,
"loss": 1.7053,
"step": 3544
},
{
"epoch": 4.54,
"learning_rate": 4.499953282883939e-08,
"loss": 1.7076,
"step": 3546
},
{
"epoch": 4.54,
"learning_rate": 4.4508737717472876e-08,
"loss": 1.6861,
"step": 3548
},
{
"epoch": 4.54,
"learning_rate": 4.4020572848338824e-08,
"loss": 1.7148,
"step": 3550
},
{
"epoch": 4.55,
"learning_rate": 4.353503956524018e-08,
"loss": 1.6923,
"step": 3552
},
{
"epoch": 4.55,
"learning_rate": 4.3052139204735826e-08,
"loss": 1.7028,
"step": 3554
},
{
"epoch": 4.55,
"learning_rate": 4.25718730961363e-08,
"loss": 1.6719,
"step": 3556
},
{
"epoch": 4.55,
"learning_rate": 4.209424256150107e-08,
"loss": 1.6857,
"step": 3558
},
{
"epoch": 4.56,
"learning_rate": 4.16192489156344e-08,
"loss": 1.6904,
"step": 3560
},
{
"epoch": 4.56,
"learning_rate": 4.114689346608191e-08,
"loss": 1.6615,
"step": 3562
},
{
"epoch": 4.56,
"learning_rate": 4.067717751312682e-08,
"loss": 1.6939,
"step": 3564
},
{
"epoch": 4.56,
"learning_rate": 4.021010234978672e-08,
"loss": 1.7125,
"step": 3566
},
{
"epoch": 4.57,
"learning_rate": 3.974566926180878e-08,
"loss": 1.7017,
"step": 3568
},
{
"epoch": 4.57,
"learning_rate": 3.928387952766832e-08,
"loss": 1.6904,
"step": 3570
},
{
"epoch": 4.57,
"learning_rate": 3.8824734418563375e-08,
"loss": 1.6979,
"step": 3572
},
{
"epoch": 4.57,
"learning_rate": 3.836823519841248e-08,
"loss": 1.7146,
"step": 3574
},
{
"epoch": 4.58,
"learning_rate": 3.7914383123850316e-08,
"loss": 1.7263,
"step": 3576
},
{
"epoch": 4.58,
"learning_rate": 3.74631794442245e-08,
"loss": 1.7132,
"step": 3578
},
{
"epoch": 4.58,
"learning_rate": 3.70146254015925e-08,
"loss": 1.6744,
"step": 3580
},
{
"epoch": 4.58,
"learning_rate": 3.656872223071783e-08,
"loss": 1.6925,
"step": 3582
},
{
"epoch": 4.59,
"learning_rate": 3.6125471159066946e-08,
"loss": 1.7036,
"step": 3584
},
{
"epoch": 4.59,
"learning_rate": 3.568487340680548e-08,
"loss": 1.7099,
"step": 3586
},
{
"epoch": 4.59,
"learning_rate": 3.524693018679525e-08,
"loss": 1.6665,
"step": 3588
},
{
"epoch": 4.6,
"learning_rate": 3.4811642704590586e-08,
"loss": 1.628,
"step": 3590
},
{
"epoch": 4.6,
"learning_rate": 3.437901215843542e-08,
"loss": 1.6846,
"step": 3592
},
{
"epoch": 4.6,
"learning_rate": 3.3949039739259775e-08,
"loss": 1.6854,
"step": 3594
},
{
"epoch": 4.6,
"learning_rate": 3.352172663067621e-08,
"loss": 1.7065,
"step": 3596
},
{
"epoch": 4.61,
"learning_rate": 3.3097074008976986e-08,
"loss": 1.7015,
"step": 3598
},
{
"epoch": 4.61,
"learning_rate": 3.267508304313082e-08,
"loss": 1.686,
"step": 3600
},
{
"epoch": 4.61,
"learning_rate": 3.225575489477928e-08,
"loss": 1.6785,
"step": 3602
},
{
"epoch": 4.61,
"learning_rate": 3.1839090718233985e-08,
"loss": 1.668,
"step": 3604
},
{
"epoch": 4.62,
"learning_rate": 3.142509166047314e-08,
"loss": 1.6977,
"step": 3606
},
{
"epoch": 4.62,
"learning_rate": 3.101375886113855e-08,
"loss": 1.7192,
"step": 3608
},
{
"epoch": 4.62,
"learning_rate": 3.0605093452532595e-08,
"loss": 1.7001,
"step": 3610
},
{
"epoch": 4.62,
"learning_rate": 3.019909655961461e-08,
"loss": 1.6923,
"step": 3612
},
{
"epoch": 4.63,
"learning_rate": 2.979576929999861e-08,
"loss": 1.7555,
"step": 3614
},
{
"epoch": 4.63,
"learning_rate": 2.939511278394913e-08,
"loss": 1.7102,
"step": 3616
},
{
"epoch": 4.63,
"learning_rate": 2.8997128114379378e-08,
"loss": 1.6927,
"step": 3618
},
{
"epoch": 4.63,
"learning_rate": 2.8601816386847442e-08,
"loss": 1.6885,
"step": 3620
},
{
"epoch": 4.64,
"learning_rate": 2.820917868955308e-08,
"loss": 1.7188,
"step": 3622
},
{
"epoch": 4.64,
"learning_rate": 2.7819216103335374e-08,
"loss": 1.6713,
"step": 3624
},
{
"epoch": 4.64,
"learning_rate": 2.743192970166952e-08,
"loss": 1.6892,
"step": 3626
},
{
"epoch": 4.64,
"learning_rate": 2.704732055066361e-08,
"loss": 1.7135,
"step": 3628
},
{
"epoch": 4.65,
"learning_rate": 2.6665389709055964e-08,
"loss": 1.7128,
"step": 3630
},
{
"epoch": 4.65,
"learning_rate": 2.628613822821224e-08,
"loss": 1.6952,
"step": 3632
},
{
"epoch": 4.65,
"learning_rate": 2.5909567152122448e-08,
"loss": 1.6808,
"step": 3634
},
{
"epoch": 4.65,
"learning_rate": 2.5535677517397824e-08,
"loss": 1.6949,
"step": 3636
},
{
"epoch": 4.66,
"learning_rate": 2.516447035326841e-08,
"loss": 1.7426,
"step": 3638
},
{
"epoch": 4.66,
"learning_rate": 2.4795946681580137e-08,
"loss": 1.704,
"step": 3640
},
{
"epoch": 4.66,
"learning_rate": 2.4430107516791754e-08,
"loss": 1.7054,
"step": 3642
},
{
"epoch": 4.66,
"learning_rate": 2.4066953865972463e-08,
"loss": 1.7219,
"step": 3644
},
{
"epoch": 4.67,
"learning_rate": 2.370648672879827e-08,
"loss": 1.6743,
"step": 3646
},
{
"epoch": 4.67,
"learning_rate": 2.3348707097550434e-08,
"loss": 1.6867,
"step": 3648
},
{
"epoch": 4.67,
"learning_rate": 2.2993615957112023e-08,
"loss": 1.7278,
"step": 3650
},
{
"epoch": 4.67,
"learning_rate": 2.264121428496535e-08,
"loss": 1.6713,
"step": 3652
},
{
"epoch": 4.68,
"learning_rate": 2.2291503051188877e-08,
"loss": 1.6944,
"step": 3654
},
{
"epoch": 4.68,
"learning_rate": 2.1944483218455213e-08,
"loss": 1.6786,
"step": 3656
},
{
"epoch": 4.68,
"learning_rate": 2.1600155742028448e-08,
"loss": 1.7177,
"step": 3658
},
{
"epoch": 4.68,
"learning_rate": 2.12585215697606e-08,
"loss": 1.7252,
"step": 3660
},
{
"epoch": 4.69,
"learning_rate": 2.091958164209029e-08,
"loss": 1.7591,
"step": 3662
},
{
"epoch": 4.69,
"learning_rate": 2.0583336892039283e-08,
"loss": 1.666,
"step": 3664
},
{
"epoch": 4.69,
"learning_rate": 2.0249788245210064e-08,
"loss": 1.7237,
"step": 3666
},
{
"epoch": 4.7,
"learning_rate": 1.9918936619783167e-08,
"loss": 1.6982,
"step": 3668
},
{
"epoch": 4.7,
"learning_rate": 1.9590782926515505e-08,
"loss": 1.724,
"step": 3670
},
{
"epoch": 4.7,
"learning_rate": 1.9265328068736597e-08,
"loss": 1.6932,
"step": 3672
},
{
"epoch": 4.7,
"learning_rate": 1.8942572942347135e-08,
"loss": 1.6912,
"step": 3674
},
{
"epoch": 4.71,
"learning_rate": 1.8622518435815858e-08,
"loss": 1.7129,
"step": 3676
},
{
"epoch": 4.71,
"learning_rate": 1.830516543017735e-08,
"loss": 1.6872,
"step": 3678
},
{
"epoch": 4.71,
"learning_rate": 1.7990514799029578e-08,
"loss": 1.7456,
"step": 3680
},
{
"epoch": 4.71,
"learning_rate": 1.7678567408531574e-08,
"loss": 1.6937,
"step": 3682
},
{
"epoch": 4.72,
"learning_rate": 1.7369324117401217e-08,
"loss": 1.7171,
"step": 3684
},
{
"epoch": 4.72,
"learning_rate": 1.7062785776912115e-08,
"loss": 1.6868,
"step": 3686
},
{
"epoch": 4.72,
"learning_rate": 1.675895323089205e-08,
"loss": 1.7159,
"step": 3688
},
{
"epoch": 4.72,
"learning_rate": 1.645782731572065e-08,
"loss": 1.6812,
"step": 3690
},
{
"epoch": 4.73,
"learning_rate": 1.6159408860326405e-08,
"loss": 1.693,
"step": 3692
},
{
"epoch": 4.73,
"learning_rate": 1.586369868618509e-08,
"loss": 1.6664,
"step": 3694
},
{
"epoch": 4.73,
"learning_rate": 1.5570697607316995e-08,
"loss": 1.696,
"step": 3696
},
{
"epoch": 4.73,
"learning_rate": 1.5280406430285166e-08,
"loss": 1.7046,
"step": 3698
},
{
"epoch": 4.74,
"learning_rate": 1.4992825954192602e-08,
"loss": 1.6879,
"step": 3700
},
{
"epoch": 4.74,
"learning_rate": 1.4707956970680723e-08,
"loss": 1.6829,
"step": 3702
},
{
"epoch": 4.74,
"learning_rate": 1.4425800263926813e-08,
"loss": 1.7013,
"step": 3704
},
{
"epoch": 4.74,
"learning_rate": 1.4146356610641453e-08,
"loss": 1.6975,
"step": 3706
},
{
"epoch": 4.75,
"learning_rate": 1.3869626780067423e-08,
"loss": 1.6609,
"step": 3708
},
{
"epoch": 4.75,
"learning_rate": 1.3595611533976482e-08,
"loss": 1.6908,
"step": 3710
},
{
"epoch": 4.75,
"learning_rate": 1.3324311626668249e-08,
"loss": 1.7112,
"step": 3712
},
{
"epoch": 4.75,
"learning_rate": 1.3055727804967331e-08,
"loss": 1.7025,
"step": 3714
},
{
"epoch": 4.76,
"learning_rate": 1.2789860808221753e-08,
"loss": 1.7091,
"step": 3716
},
{
"epoch": 4.76,
"learning_rate": 1.2526711368300524e-08,
"loss": 1.7049,
"step": 3718
},
{
"epoch": 4.76,
"learning_rate": 1.2266280209592195e-08,
"loss": 1.6926,
"step": 3720
},
{
"epoch": 4.76,
"learning_rate": 1.2008568049002298e-08,
"loss": 1.6827,
"step": 3722
},
{
"epoch": 4.77,
"learning_rate": 1.1753575595951582e-08,
"loss": 1.6602,
"step": 3724
},
{
"epoch": 4.77,
"learning_rate": 1.150130355237422e-08,
"loss": 1.665,
"step": 3726
},
{
"epoch": 4.77,
"learning_rate": 1.1251752612715714e-08,
"loss": 1.6997,
"step": 3728
},
{
"epoch": 4.77,
"learning_rate": 1.1004923463931116e-08,
"loss": 1.752,
"step": 3730
},
{
"epoch": 4.78,
"learning_rate": 1.0760816785482685e-08,
"loss": 1.7279,
"step": 3732
},
{
"epoch": 4.78,
"learning_rate": 1.0519433249338682e-08,
"loss": 1.7024,
"step": 3734
},
{
"epoch": 4.78,
"learning_rate": 1.028077351997092e-08,
"loss": 1.6959,
"step": 3736
},
{
"epoch": 4.78,
"learning_rate": 1.0044838254353538e-08,
"loss": 1.7141,
"step": 3738
},
{
"epoch": 4.79,
"learning_rate": 9.81162810196079e-09,
"loss": 1.689,
"step": 3740
},
{
"epoch": 4.79,
"learning_rate": 9.581143704765149e-09,
"loss": 1.6795,
"step": 3742
},
{
"epoch": 4.79,
"learning_rate": 9.353385697235761e-09,
"loss": 1.7652,
"step": 3744
},
{
"epoch": 4.79,
"learning_rate": 9.128354706336883e-09,
"loss": 1.7653,
"step": 3746
},
{
"epoch": 4.8,
"learning_rate": 8.906051351525668e-09,
"loss": 1.6847,
"step": 3748
},
{
"epoch": 4.8,
"learning_rate": 8.68647624475094e-09,
"loss": 1.7386,
"step": 3750
},
{
"epoch": 4.8,
"learning_rate": 8.4696299904512e-09,
"loss": 1.7136,
"step": 3752
},
{
"epoch": 4.81,
"learning_rate": 8.255513185552953e-09,
"loss": 1.73,
"step": 3754
},
{
"epoch": 4.81,
"learning_rate": 8.044126419469388e-09,
"loss": 1.6712,
"step": 3756
},
{
"epoch": 4.81,
"learning_rate": 7.835470274098477e-09,
"loss": 1.7472,
"step": 3758
},
{
"epoch": 4.81,
"learning_rate": 7.629545323821429e-09,
"loss": 1.7428,
"step": 3760
},
{
"epoch": 4.82,
"learning_rate": 7.426352135501135e-09,
"loss": 1.7166,
"step": 3762
},
{
"epoch": 4.82,
"learning_rate": 7.225891268480388e-09,
"loss": 1.7199,
"step": 3764
},
{
"epoch": 4.82,
"learning_rate": 7.028163274580779e-09,
"loss": 1.7266,
"step": 3766
},
{
"epoch": 4.82,
"learning_rate": 6.833168698100911e-09,
"loss": 1.7122,
"step": 3768
},
{
"epoch": 4.83,
"learning_rate": 6.640908075814744e-09,
"loss": 1.6738,
"step": 3770
},
{
"epoch": 4.83,
"learning_rate": 6.451381936970701e-09,
"loss": 1.6955,
"step": 3772
},
{
"epoch": 4.83,
"learning_rate": 6.264590803289449e-09,
"loss": 1.6699,
"step": 3774
},
{
"epoch": 4.83,
"learning_rate": 6.080535188962898e-09,
"loss": 1.7218,
"step": 3776
},
{
"epoch": 4.84,
"learning_rate": 5.899215600652763e-09,
"loss": 1.6764,
"step": 3778
},
{
"epoch": 4.84,
"learning_rate": 5.7206325374891115e-09,
"loss": 1.6539,
"step": 3780
},
{
"epoch": 4.84,
"learning_rate": 5.544786491069264e-09,
"loss": 1.708,
"step": 3782
},
{
"epoch": 4.84,
"learning_rate": 5.371677945455788e-09,
"loss": 1.67,
"step": 3784
},
{
"epoch": 4.85,
"learning_rate": 5.201307377175501e-09,
"loss": 1.6916,
"step": 3786
},
{
"epoch": 4.85,
"learning_rate": 5.0336752552186945e-09,
"loss": 1.6578,
"step": 3788
},
{
"epoch": 4.85,
"learning_rate": 4.868782041037023e-09,
"loss": 1.6793,
"step": 3790
},
{
"epoch": 4.85,
"learning_rate": 4.706628188542727e-09,
"loss": 1.6685,
"step": 3792
},
{
"epoch": 4.86,
"learning_rate": 4.547214144106859e-09,
"loss": 1.746,
"step": 3794
},
{
"epoch": 4.86,
"learning_rate": 4.390540346558946e-09,
"loss": 1.769,
"step": 3796
},
{
"epoch": 4.86,
"learning_rate": 4.236607227184996e-09,
"loss": 1.6973,
"step": 3798
},
{
"epoch": 4.86,
"learning_rate": 4.085415209726495e-09,
"loss": 1.658,
"step": 3800
},
{
"epoch": 4.87,
"learning_rate": 3.936964710379631e-09,
"loss": 1.6755,
"step": 3802
},
{
"epoch": 4.87,
"learning_rate": 3.791256137793409e-09,
"loss": 1.6588,
"step": 3804
},
{
"epoch": 4.87,
"learning_rate": 3.6482898930693117e-09,
"loss": 1.7605,
"step": 3806
},
{
"epoch": 4.87,
"learning_rate": 3.5080663697597545e-09,
"loss": 1.7025,
"step": 3808
},
{
"epoch": 4.88,
"learning_rate": 3.370585953866856e-09,
"loss": 1.7139,
"step": 3810
},
{
"epoch": 4.88,
"learning_rate": 3.235849023842108e-09,
"loss": 1.7405,
"step": 3812
},
{
"epoch": 4.88,
"learning_rate": 3.1038559505841554e-09,
"loss": 1.6946,
"step": 3814
},
{
"epoch": 4.88,
"learning_rate": 2.97460709743913e-09,
"loss": 1.698,
"step": 3816
},
{
"epoch": 4.89,
"learning_rate": 2.848102820198428e-09,
"loss": 1.7037,
"step": 3818
},
{
"epoch": 4.89,
"learning_rate": 2.7243434670986e-09,
"loss": 1.7676,
"step": 3820
},
{
"epoch": 4.89,
"learning_rate": 2.6033293788201295e-09,
"loss": 1.671,
"step": 3822
},
{
"epoch": 4.89,
"learning_rate": 2.4850608884859904e-09,
"loss": 1.6957,
"step": 3824
},
{
"epoch": 4.9,
"learning_rate": 2.369538321661646e-09,
"loss": 1.7241,
"step": 3826
},
{
"epoch": 4.9,
"learning_rate": 2.2567619963534956e-09,
"loss": 1.6994,
"step": 3828
},
{
"epoch": 4.9,
"learning_rate": 2.1467322230080965e-09,
"loss": 1.7383,
"step": 3830
},
{
"epoch": 4.9,
"learning_rate": 2.039449304511498e-09,
"loss": 1.6878,
"step": 3832
},
{
"epoch": 4.91,
"learning_rate": 1.934913536188354e-09,
"loss": 1.6796,
"step": 3834
},
{
"epoch": 4.91,
"learning_rate": 1.8331252058008119e-09,
"loss": 1.6307,
"step": 3836
},
{
"epoch": 4.91,
"learning_rate": 1.7340845935484016e-09,
"loss": 1.6987,
"step": 3838
},
{
"epoch": 4.92,
"learning_rate": 1.6377919720664823e-09,
"loss": 1.7338,
"step": 3840
},
{
"epoch": 4.92,
"learning_rate": 1.544247606426019e-09,
"loss": 1.6588,
"step": 3842
},
{
"epoch": 4.92,
"learning_rate": 1.453451754132362e-09,
"loss": 1.7235,
"step": 3844
},
{
"epoch": 4.92,
"learning_rate": 1.3654046651252472e-09,
"loss": 1.6511,
"step": 3846
},
{
"epoch": 4.93,
"learning_rate": 1.2801065817776847e-09,
"loss": 1.7,
"step": 3848
},
{
"epoch": 4.93,
"learning_rate": 1.197557738894961e-09,
"loss": 1.6737,
"step": 3850
},
{
"epoch": 4.93,
"learning_rate": 1.1177583637147492e-09,
"loss": 1.7184,
"step": 3852
},
{
"epoch": 4.93,
"learning_rate": 1.040708675905888e-09,
"loss": 1.6842,
"step": 3854
},
{
"epoch": 4.94,
"learning_rate": 9.664088875679376e-10,
"loss": 1.6451,
"step": 3856
},
{
"epoch": 4.94,
"learning_rate": 8.948592032307356e-10,
"loss": 1.7192,
"step": 3858
},
{
"epoch": 4.94,
"learning_rate": 8.260598198537305e-10,
"loss": 1.7032,
"step": 3860
},
{
"epoch": 4.94,
"learning_rate": 7.600109268253163e-10,
"loss": 1.7337,
"step": 3862
},
{
"epoch": 4.95,
"learning_rate": 6.967127059626098e-10,
"loss": 1.6974,
"step": 3864
},
{
"epoch": 4.95,
"learning_rate": 6.361653315107851e-10,
"loss": 1.7529,
"step": 3866
},
{
"epoch": 4.95,
"learning_rate": 5.783689701422955e-10,
"loss": 1.7133,
"step": 3868
},
{
"epoch": 4.95,
"learning_rate": 5.233237809569857e-10,
"loss": 1.6991,
"step": 3870
},
{
"epoch": 4.96,
"learning_rate": 4.710299154814246e-10,
"loss": 1.6562,
"step": 3872
},
{
"epoch": 4.96,
"learning_rate": 4.214875176680177e-10,
"loss": 1.683,
"step": 3874
},
{
"epoch": 4.96,
"learning_rate": 3.7469672389545125e-10,
"loss": 1.685,
"step": 3876
},
{
"epoch": 4.96,
"learning_rate": 3.306576629679148e-10,
"loss": 1.7251,
"step": 3878
},
{
"epoch": 4.97,
"learning_rate": 2.8937045611432397e-10,
"loss": 1.652,
"step": 3880
},
{
"epoch": 4.97,
"learning_rate": 2.508352169886541e-10,
"loss": 1.6988,
"step": 3882
},
{
"epoch": 4.97,
"learning_rate": 2.1505205166949535e-10,
"loss": 1.6873,
"step": 3884
},
{
"epoch": 4.97,
"learning_rate": 1.820210586592763e-10,
"loss": 1.7379,
"step": 3886
},
{
"epoch": 4.98,
"learning_rate": 1.517423288847075e-10,
"loss": 1.6629,
"step": 3888
},
{
"epoch": 4.98,
"learning_rate": 1.2421594569578252e-10,
"loss": 1.7126,
"step": 3890
},
{
"epoch": 4.98,
"learning_rate": 9.944198486644406e-11,
"loss": 1.6859,
"step": 3892
},
{
"epoch": 4.98,
"learning_rate": 7.742051459325161e-11,
"loss": 1.6987,
"step": 3894
},
{
"epoch": 4.99,
"learning_rate": 5.815159549638071e-11,
"loss": 1.6974,
"step": 3896
},
{
"epoch": 4.99,
"learning_rate": 4.163528061840171e-11,
"loss": 1.6635,
"step": 3898
},
{
"epoch": 4.99,
"learning_rate": 2.7871615425056892e-11,
"loss": 1.6411,
"step": 3900
},
{
"epoch": 4.99,
"learning_rate": 1.686063780426128e-11,
"loss": 1.7425,
"step": 3902
},
{
"epoch": 5.0,
"learning_rate": 8.6023780668798e-12,
"loss": 1.6688,
"step": 3904
},
{
"epoch": 5.0,
"step": 3905,
"total_flos": 2.2591395969210778e+17,
"train_loss": 1.745837493162607,
"train_runtime": 41077.3358,
"train_samples_per_second": 6.086,
"train_steps_per_second": 0.095
}
],
"logging_steps": 2,
"max_steps": 3905,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 3000,
"total_flos": 2.2591395969210778e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}