Remove unnecessary files to save space
Browse files- checkpoint-15260/trainer_state.json +0 -3477
checkpoint-15260/trainer_state.json
DELETED
|
@@ -1,3477 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_metric": null,
|
| 3 |
-
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.38230283595550657,
|
| 5 |
-
"eval_steps": 500,
|
| 6 |
-
"global_step": 15260,
|
| 7 |
-
"is_hyper_param_search": false,
|
| 8 |
-
"is_local_process_zero": true,
|
| 9 |
-
"is_world_process_zero": true,
|
| 10 |
-
"log_history": [
|
| 11 |
-
{
|
| 12 |
-
"epoch": 0.000776630924942379,
|
| 13 |
-
"grad_norm": 23.55321502685547,
|
| 14 |
-
"learning_rate": 1.0157273918741808e-06,
|
| 15 |
-
"loss": 8.3443,
|
| 16 |
-
"step": 31
|
| 17 |
-
},
|
| 18 |
-
{
|
| 19 |
-
"epoch": 0.001553261849884758,
|
| 20 |
-
"grad_norm": 14.414477348327637,
|
| 21 |
-
"learning_rate": 2.0314547837483616e-06,
|
| 22 |
-
"loss": 7.198,
|
| 23 |
-
"step": 62
|
| 24 |
-
},
|
| 25 |
-
{
|
| 26 |
-
"epoch": 0.002329892774827137,
|
| 27 |
-
"grad_norm": 10.739773750305176,
|
| 28 |
-
"learning_rate": 3.0471821756225426e-06,
|
| 29 |
-
"loss": 5.8639,
|
| 30 |
-
"step": 93
|
| 31 |
-
},
|
| 32 |
-
{
|
| 33 |
-
"epoch": 0.003106523699769516,
|
| 34 |
-
"grad_norm": 5.378795623779297,
|
| 35 |
-
"learning_rate": 4.062909567496723e-06,
|
| 36 |
-
"loss": 4.8222,
|
| 37 |
-
"step": 124
|
| 38 |
-
},
|
| 39 |
-
{
|
| 40 |
-
"epoch": 0.003883154624711895,
|
| 41 |
-
"grad_norm": 8.51831340789795,
|
| 42 |
-
"learning_rate": 5.078636959370905e-06,
|
| 43 |
-
"loss": 4.1983,
|
| 44 |
-
"step": 155
|
| 45 |
-
},
|
| 46 |
-
{
|
| 47 |
-
"epoch": 0.004659785549654274,
|
| 48 |
-
"grad_norm": 6.32632303237915,
|
| 49 |
-
"learning_rate": 6.094364351245085e-06,
|
| 50 |
-
"loss": 3.8598,
|
| 51 |
-
"step": 186
|
| 52 |
-
},
|
| 53 |
-
{
|
| 54 |
-
"epoch": 0.005436416474596653,
|
| 55 |
-
"grad_norm": 5.590794563293457,
|
| 56 |
-
"learning_rate": 7.110091743119267e-06,
|
| 57 |
-
"loss": 3.6646,
|
| 58 |
-
"step": 217
|
| 59 |
-
},
|
| 60 |
-
{
|
| 61 |
-
"epoch": 0.006213047399539032,
|
| 62 |
-
"grad_norm": 5.9275383949279785,
|
| 63 |
-
"learning_rate": 8.125819134993446e-06,
|
| 64 |
-
"loss": 3.5212,
|
| 65 |
-
"step": 248
|
| 66 |
-
},
|
| 67 |
-
{
|
| 68 |
-
"epoch": 0.006989678324481411,
|
| 69 |
-
"grad_norm": 5.041291236877441,
|
| 70 |
-
"learning_rate": 9.141546526867629e-06,
|
| 71 |
-
"loss": 3.3936,
|
| 72 |
-
"step": 279
|
| 73 |
-
},
|
| 74 |
-
{
|
| 75 |
-
"epoch": 0.00776630924942379,
|
| 76 |
-
"grad_norm": 4.923459529876709,
|
| 77 |
-
"learning_rate": 1.015727391874181e-05,
|
| 78 |
-
"loss": 3.2713,
|
| 79 |
-
"step": 310
|
| 80 |
-
},
|
| 81 |
-
{
|
| 82 |
-
"epoch": 0.00854294017436617,
|
| 83 |
-
"grad_norm": 8.011459350585938,
|
| 84 |
-
"learning_rate": 1.117300131061599e-05,
|
| 85 |
-
"loss": 3.2,
|
| 86 |
-
"step": 341
|
| 87 |
-
},
|
| 88 |
-
{
|
| 89 |
-
"epoch": 0.009319571099308548,
|
| 90 |
-
"grad_norm": 5.261505603790283,
|
| 91 |
-
"learning_rate": 1.218872870249017e-05,
|
| 92 |
-
"loss": 3.1255,
|
| 93 |
-
"step": 372
|
| 94 |
-
},
|
| 95 |
-
{
|
| 96 |
-
"epoch": 0.010096202024250926,
|
| 97 |
-
"grad_norm": 5.004406452178955,
|
| 98 |
-
"learning_rate": 1.3204456094364351e-05,
|
| 99 |
-
"loss": 3.0726,
|
| 100 |
-
"step": 403
|
| 101 |
-
},
|
| 102 |
-
{
|
| 103 |
-
"epoch": 0.010872832949193306,
|
| 104 |
-
"grad_norm": 4.326263427734375,
|
| 105 |
-
"learning_rate": 1.4220183486238533e-05,
|
| 106 |
-
"loss": 2.9682,
|
| 107 |
-
"step": 434
|
| 108 |
-
},
|
| 109 |
-
{
|
| 110 |
-
"epoch": 0.011649463874135685,
|
| 111 |
-
"grad_norm": 4.251937389373779,
|
| 112 |
-
"learning_rate": 1.5235910878112714e-05,
|
| 113 |
-
"loss": 2.9215,
|
| 114 |
-
"step": 465
|
| 115 |
-
},
|
| 116 |
-
{
|
| 117 |
-
"epoch": 0.012426094799078065,
|
| 118 |
-
"grad_norm": 4.35053825378418,
|
| 119 |
-
"learning_rate": 1.6251638269986893e-05,
|
| 120 |
-
"loss": 2.8902,
|
| 121 |
-
"step": 496
|
| 122 |
-
},
|
| 123 |
-
{
|
| 124 |
-
"epoch": 0.013202725724020443,
|
| 125 |
-
"grad_norm": 4.316098690032959,
|
| 126 |
-
"learning_rate": 1.7267365661861077e-05,
|
| 127 |
-
"loss": 2.8521,
|
| 128 |
-
"step": 527
|
| 129 |
-
},
|
| 130 |
-
{
|
| 131 |
-
"epoch": 0.013979356648962823,
|
| 132 |
-
"grad_norm": 5.536881446838379,
|
| 133 |
-
"learning_rate": 1.8283093053735257e-05,
|
| 134 |
-
"loss": 2.8058,
|
| 135 |
-
"step": 558
|
| 136 |
-
},
|
| 137 |
-
{
|
| 138 |
-
"epoch": 0.014755987573905201,
|
| 139 |
-
"grad_norm": 3.759843111038208,
|
| 140 |
-
"learning_rate": 1.9298820445609438e-05,
|
| 141 |
-
"loss": 2.7438,
|
| 142 |
-
"step": 589
|
| 143 |
-
},
|
| 144 |
-
{
|
| 145 |
-
"epoch": 0.01553261849884758,
|
| 146 |
-
"grad_norm": 4.057703018188477,
|
| 147 |
-
"learning_rate": 2.031454783748362e-05,
|
| 148 |
-
"loss": 2.7508,
|
| 149 |
-
"step": 620
|
| 150 |
-
},
|
| 151 |
-
{
|
| 152 |
-
"epoch": 0.01630924942378996,
|
| 153 |
-
"grad_norm": 3.427708625793457,
|
| 154 |
-
"learning_rate": 2.13302752293578e-05,
|
| 155 |
-
"loss": 2.7046,
|
| 156 |
-
"step": 651
|
| 157 |
-
},
|
| 158 |
-
{
|
| 159 |
-
"epoch": 0.01708588034873234,
|
| 160 |
-
"grad_norm": 3.9012484550476074,
|
| 161 |
-
"learning_rate": 2.234600262123198e-05,
|
| 162 |
-
"loss": 2.6706,
|
| 163 |
-
"step": 682
|
| 164 |
-
},
|
| 165 |
-
{
|
| 166 |
-
"epoch": 0.017862511273674716,
|
| 167 |
-
"grad_norm": 3.388504981994629,
|
| 168 |
-
"learning_rate": 2.336173001310616e-05,
|
| 169 |
-
"loss": 2.6377,
|
| 170 |
-
"step": 713
|
| 171 |
-
},
|
| 172 |
-
{
|
| 173 |
-
"epoch": 0.018639142198617096,
|
| 174 |
-
"grad_norm": 3.2011327743530273,
|
| 175 |
-
"learning_rate": 2.437745740498034e-05,
|
| 176 |
-
"loss": 2.6214,
|
| 177 |
-
"step": 744
|
| 178 |
-
},
|
| 179 |
-
{
|
| 180 |
-
"epoch": 0.019415773123559476,
|
| 181 |
-
"grad_norm": 3.5897209644317627,
|
| 182 |
-
"learning_rate": 2.5393184796854525e-05,
|
| 183 |
-
"loss": 2.6045,
|
| 184 |
-
"step": 775
|
| 185 |
-
},
|
| 186 |
-
{
|
| 187 |
-
"epoch": 0.020192404048501852,
|
| 188 |
-
"grad_norm": 3.386697769165039,
|
| 189 |
-
"learning_rate": 2.6408912188728702e-05,
|
| 190 |
-
"loss": 2.6066,
|
| 191 |
-
"step": 806
|
| 192 |
-
},
|
| 193 |
-
{
|
| 194 |
-
"epoch": 0.020969034973444232,
|
| 195 |
-
"grad_norm": 2.9135866165161133,
|
| 196 |
-
"learning_rate": 2.7424639580602886e-05,
|
| 197 |
-
"loss": 2.5697,
|
| 198 |
-
"step": 837
|
| 199 |
-
},
|
| 200 |
-
{
|
| 201 |
-
"epoch": 0.021745665898386612,
|
| 202 |
-
"grad_norm": 9.212065696716309,
|
| 203 |
-
"learning_rate": 2.8440366972477066e-05,
|
| 204 |
-
"loss": 2.5773,
|
| 205 |
-
"step": 868
|
| 206 |
-
},
|
| 207 |
-
{
|
| 208 |
-
"epoch": 0.022522296823328992,
|
| 209 |
-
"grad_norm": 3.0339765548706055,
|
| 210 |
-
"learning_rate": 2.9456094364351244e-05,
|
| 211 |
-
"loss": 2.5453,
|
| 212 |
-
"step": 899
|
| 213 |
-
},
|
| 214 |
-
{
|
| 215 |
-
"epoch": 0.02329892774827137,
|
| 216 |
-
"grad_norm": 2.8007607460021973,
|
| 217 |
-
"learning_rate": 3.0471821756225428e-05,
|
| 218 |
-
"loss": 2.5297,
|
| 219 |
-
"step": 930
|
| 220 |
-
},
|
| 221 |
-
{
|
| 222 |
-
"epoch": 0.02407555867321375,
|
| 223 |
-
"grad_norm": 3.251768112182617,
|
| 224 |
-
"learning_rate": 3.148754914809961e-05,
|
| 225 |
-
"loss": 2.5273,
|
| 226 |
-
"step": 961
|
| 227 |
-
},
|
| 228 |
-
{
|
| 229 |
-
"epoch": 0.02485218959815613,
|
| 230 |
-
"grad_norm": 3.357011079788208,
|
| 231 |
-
"learning_rate": 3.2503276539973785e-05,
|
| 232 |
-
"loss": 2.4896,
|
| 233 |
-
"step": 992
|
| 234 |
-
},
|
| 235 |
-
{
|
| 236 |
-
"epoch": 0.025628820523098506,
|
| 237 |
-
"grad_norm": 2.6069107055664062,
|
| 238 |
-
"learning_rate": 3.351900393184797e-05,
|
| 239 |
-
"loss": 2.4718,
|
| 240 |
-
"step": 1023
|
| 241 |
-
},
|
| 242 |
-
{
|
| 243 |
-
"epoch": 0.026405451448040886,
|
| 244 |
-
"grad_norm": 4.663620948791504,
|
| 245 |
-
"learning_rate": 3.453473132372215e-05,
|
| 246 |
-
"loss": 2.4338,
|
| 247 |
-
"step": 1054
|
| 248 |
-
},
|
| 249 |
-
{
|
| 250 |
-
"epoch": 0.027182082372983266,
|
| 251 |
-
"grad_norm": 3.819638252258301,
|
| 252 |
-
"learning_rate": 3.555045871559633e-05,
|
| 253 |
-
"loss": 2.4848,
|
| 254 |
-
"step": 1085
|
| 255 |
-
},
|
| 256 |
-
{
|
| 257 |
-
"epoch": 0.027958713297925646,
|
| 258 |
-
"grad_norm": 2.6367456912994385,
|
| 259 |
-
"learning_rate": 3.6566186107470514e-05,
|
| 260 |
-
"loss": 2.4415,
|
| 261 |
-
"step": 1116
|
| 262 |
-
},
|
| 263 |
-
{
|
| 264 |
-
"epoch": 0.028735344222868022,
|
| 265 |
-
"grad_norm": 2.6118173599243164,
|
| 266 |
-
"learning_rate": 3.7581913499344695e-05,
|
| 267 |
-
"loss": 2.4341,
|
| 268 |
-
"step": 1147
|
| 269 |
-
},
|
| 270 |
-
{
|
| 271 |
-
"epoch": 0.029511975147810402,
|
| 272 |
-
"grad_norm": 9.820366859436035,
|
| 273 |
-
"learning_rate": 3.8597640891218876e-05,
|
| 274 |
-
"loss": 2.3773,
|
| 275 |
-
"step": 1178
|
| 276 |
-
},
|
| 277 |
-
{
|
| 278 |
-
"epoch": 0.030288606072752782,
|
| 279 |
-
"grad_norm": 38.890506744384766,
|
| 280 |
-
"learning_rate": 3.9613368283093056e-05,
|
| 281 |
-
"loss": 2.3966,
|
| 282 |
-
"step": 1209
|
| 283 |
-
},
|
| 284 |
-
{
|
| 285 |
-
"epoch": 0.03106523699769516,
|
| 286 |
-
"grad_norm": 2.5037872791290283,
|
| 287 |
-
"learning_rate": 4.062909567496724e-05,
|
| 288 |
-
"loss": 2.3421,
|
| 289 |
-
"step": 1240
|
| 290 |
-
},
|
| 291 |
-
{
|
| 292 |
-
"epoch": 0.03184186792263754,
|
| 293 |
-
"grad_norm": 2.426544189453125,
|
| 294 |
-
"learning_rate": 4.164482306684142e-05,
|
| 295 |
-
"loss": 2.3568,
|
| 296 |
-
"step": 1271
|
| 297 |
-
},
|
| 298 |
-
{
|
| 299 |
-
"epoch": 0.03261849884757992,
|
| 300 |
-
"grad_norm": 2.5375614166259766,
|
| 301 |
-
"learning_rate": 4.26605504587156e-05,
|
| 302 |
-
"loss": 2.3314,
|
| 303 |
-
"step": 1302
|
| 304 |
-
},
|
| 305 |
-
{
|
| 306 |
-
"epoch": 0.0333951297725223,
|
| 307 |
-
"grad_norm": 3.555330276489258,
|
| 308 |
-
"learning_rate": 4.367627785058978e-05,
|
| 309 |
-
"loss": 2.3262,
|
| 310 |
-
"step": 1333
|
| 311 |
-
},
|
| 312 |
-
{
|
| 313 |
-
"epoch": 0.03417176069746468,
|
| 314 |
-
"grad_norm": 2.2571263313293457,
|
| 315 |
-
"learning_rate": 4.469200524246396e-05,
|
| 316 |
-
"loss": 2.3167,
|
| 317 |
-
"step": 1364
|
| 318 |
-
},
|
| 319 |
-
{
|
| 320 |
-
"epoch": 0.03494839162240705,
|
| 321 |
-
"grad_norm": 2.184305429458618,
|
| 322 |
-
"learning_rate": 4.570773263433814e-05,
|
| 323 |
-
"loss": 2.2936,
|
| 324 |
-
"step": 1395
|
| 325 |
-
},
|
| 326 |
-
{
|
| 327 |
-
"epoch": 0.03572502254734943,
|
| 328 |
-
"grad_norm": 2.8295061588287354,
|
| 329 |
-
"learning_rate": 4.672346002621232e-05,
|
| 330 |
-
"loss": 2.3033,
|
| 331 |
-
"step": 1426
|
| 332 |
-
},
|
| 333 |
-
{
|
| 334 |
-
"epoch": 0.03650165347229181,
|
| 335 |
-
"grad_norm": 2.0241498947143555,
|
| 336 |
-
"learning_rate": 4.77391874180865e-05,
|
| 337 |
-
"loss": 2.2833,
|
| 338 |
-
"step": 1457
|
| 339 |
-
},
|
| 340 |
-
{
|
| 341 |
-
"epoch": 0.03727828439723419,
|
| 342 |
-
"grad_norm": 2.0029919147491455,
|
| 343 |
-
"learning_rate": 4.875491480996068e-05,
|
| 344 |
-
"loss": 2.2663,
|
| 345 |
-
"step": 1488
|
| 346 |
-
},
|
| 347 |
-
{
|
| 348 |
-
"epoch": 0.03805491532217657,
|
| 349 |
-
"grad_norm": 2.033773899078369,
|
| 350 |
-
"learning_rate": 4.977064220183487e-05,
|
| 351 |
-
"loss": 2.2597,
|
| 352 |
-
"step": 1519
|
| 353 |
-
},
|
| 354 |
-
{
|
| 355 |
-
"epoch": 0.03883154624711895,
|
| 356 |
-
"grad_norm": 2.047210216522217,
|
| 357 |
-
"learning_rate": 4.9999915451558777e-05,
|
| 358 |
-
"loss": 2.2231,
|
| 359 |
-
"step": 1550
|
| 360 |
-
},
|
| 361 |
-
{
|
| 362 |
-
"epoch": 0.03960817717206133,
|
| 363 |
-
"grad_norm": 2.032099485397339,
|
| 364 |
-
"learning_rate": 4.999955597496219e-05,
|
| 365 |
-
"loss": 2.2411,
|
| 366 |
-
"step": 1581
|
| 367 |
-
},
|
| 368 |
-
{
|
| 369 |
-
"epoch": 0.040384808097003705,
|
| 370 |
-
"grad_norm": 1.8384301662445068,
|
| 371 |
-
"learning_rate": 4.9998914381774255e-05,
|
| 372 |
-
"loss": 2.2409,
|
| 373 |
-
"step": 1612
|
| 374 |
-
},
|
| 375 |
-
{
|
| 376 |
-
"epoch": 0.041161439021946085,
|
| 377 |
-
"grad_norm": 1.721187710762024,
|
| 378 |
-
"learning_rate": 4.999799067923527e-05,
|
| 379 |
-
"loss": 2.193,
|
| 380 |
-
"step": 1643
|
| 381 |
-
},
|
| 382 |
-
{
|
| 383 |
-
"epoch": 0.041938069946888465,
|
| 384 |
-
"grad_norm": 1.8869743347167969,
|
| 385 |
-
"learning_rate": 4.999678487776908e-05,
|
| 386 |
-
"loss": 2.1917,
|
| 387 |
-
"step": 1674
|
| 388 |
-
},
|
| 389 |
-
{
|
| 390 |
-
"epoch": 0.042714700871830845,
|
| 391 |
-
"grad_norm": 1.796583652496338,
|
| 392 |
-
"learning_rate": 4.9995296990983006e-05,
|
| 393 |
-
"loss": 2.1794,
|
| 394 |
-
"step": 1705
|
| 395 |
-
},
|
| 396 |
-
{
|
| 397 |
-
"epoch": 0.043491331796773225,
|
| 398 |
-
"grad_norm": 1.6308804750442505,
|
| 399 |
-
"learning_rate": 4.999352703566763e-05,
|
| 400 |
-
"loss": 2.1854,
|
| 401 |
-
"step": 1736
|
| 402 |
-
},
|
| 403 |
-
{
|
| 404 |
-
"epoch": 0.044267962721715605,
|
| 405 |
-
"grad_norm": 1.683474063873291,
|
| 406 |
-
"learning_rate": 4.999147503179668e-05,
|
| 407 |
-
"loss": 2.1797,
|
| 408 |
-
"step": 1767
|
| 409 |
-
},
|
| 410 |
-
{
|
| 411 |
-
"epoch": 0.045044593646657985,
|
| 412 |
-
"grad_norm": 1.7442835569381714,
|
| 413 |
-
"learning_rate": 4.998914100252672e-05,
|
| 414 |
-
"loss": 2.1695,
|
| 415 |
-
"step": 1798
|
| 416 |
-
},
|
| 417 |
-
{
|
| 418 |
-
"epoch": 0.04582122457160036,
|
| 419 |
-
"grad_norm": 1.704970359802246,
|
| 420 |
-
"learning_rate": 4.998652497419696e-05,
|
| 421 |
-
"loss": 2.1365,
|
| 422 |
-
"step": 1829
|
| 423 |
-
},
|
| 424 |
-
{
|
| 425 |
-
"epoch": 0.04659785549654274,
|
| 426 |
-
"grad_norm": 1.7213023900985718,
|
| 427 |
-
"learning_rate": 4.9983626976328927e-05,
|
| 428 |
-
"loss": 2.1524,
|
| 429 |
-
"step": 1860
|
| 430 |
-
},
|
| 431 |
-
{
|
| 432 |
-
"epoch": 0.04737448642148512,
|
| 433 |
-
"grad_norm": 4.01851224899292,
|
| 434 |
-
"learning_rate": 4.998044704162613e-05,
|
| 435 |
-
"loss": 2.1171,
|
| 436 |
-
"step": 1891
|
| 437 |
-
},
|
| 438 |
-
{
|
| 439 |
-
"epoch": 0.0481511173464275,
|
| 440 |
-
"grad_norm": 1.5619858503341675,
|
| 441 |
-
"learning_rate": 4.9976985205973705e-05,
|
| 442 |
-
"loss": 2.1608,
|
| 443 |
-
"step": 1922
|
| 444 |
-
},
|
| 445 |
-
{
|
| 446 |
-
"epoch": 0.04892774827136988,
|
| 447 |
-
"grad_norm": 1.684493064880371,
|
| 448 |
-
"learning_rate": 4.997324150843799e-05,
|
| 449 |
-
"loss": 2.1278,
|
| 450 |
-
"step": 1953
|
| 451 |
-
},
|
| 452 |
-
{
|
| 453 |
-
"epoch": 0.04970437919631226,
|
| 454 |
-
"grad_norm": 1.660992980003357,
|
| 455 |
-
"learning_rate": 4.99692159912661e-05,
|
| 456 |
-
"loss": 2.1136,
|
| 457 |
-
"step": 1984
|
| 458 |
-
},
|
| 459 |
-
{
|
| 460 |
-
"epoch": 0.05048101012125464,
|
| 461 |
-
"grad_norm": 1.5491065979003906,
|
| 462 |
-
"learning_rate": 4.996490869988546e-05,
|
| 463 |
-
"loss": 2.1086,
|
| 464 |
-
"step": 2015
|
| 465 |
-
},
|
| 466 |
-
{
|
| 467 |
-
"epoch": 0.05125764104619701,
|
| 468 |
-
"grad_norm": 1.5400840044021606,
|
| 469 |
-
"learning_rate": 4.996031968290326e-05,
|
| 470 |
-
"loss": 2.1069,
|
| 471 |
-
"step": 2046
|
| 472 |
-
},
|
| 473 |
-
{
|
| 474 |
-
"epoch": 0.05203427197113939,
|
| 475 |
-
"grad_norm": 1.5687416791915894,
|
| 476 |
-
"learning_rate": 4.995544899210594e-05,
|
| 477 |
-
"loss": 2.0888,
|
| 478 |
-
"step": 2077
|
| 479 |
-
},
|
| 480 |
-
{
|
| 481 |
-
"epoch": 0.05281090289608177,
|
| 482 |
-
"grad_norm": 1.5218935012817383,
|
| 483 |
-
"learning_rate": 4.9950296682458583e-05,
|
| 484 |
-
"loss": 2.1032,
|
| 485 |
-
"step": 2108
|
| 486 |
-
},
|
| 487 |
-
{
|
| 488 |
-
"epoch": 0.05358753382102415,
|
| 489 |
-
"grad_norm": 1.763666033744812,
|
| 490 |
-
"learning_rate": 4.994486281210429e-05,
|
| 491 |
-
"loss": 2.0799,
|
| 492 |
-
"step": 2139
|
| 493 |
-
},
|
| 494 |
-
{
|
| 495 |
-
"epoch": 0.05436416474596653,
|
| 496 |
-
"grad_norm": 1.5606274604797363,
|
| 497 |
-
"learning_rate": 4.9939147442363566e-05,
|
| 498 |
-
"loss": 2.0614,
|
| 499 |
-
"step": 2170
|
| 500 |
-
},
|
| 501 |
-
{
|
| 502 |
-
"epoch": 0.05514079567090891,
|
| 503 |
-
"grad_norm": 1.4900213479995728,
|
| 504 |
-
"learning_rate": 4.9933150637733574e-05,
|
| 505 |
-
"loss": 2.0565,
|
| 506 |
-
"step": 2201
|
| 507 |
-
},
|
| 508 |
-
{
|
| 509 |
-
"epoch": 0.05591742659585129,
|
| 510 |
-
"grad_norm": 1.4454214572906494,
|
| 511 |
-
"learning_rate": 4.992687246588743e-05,
|
| 512 |
-
"loss": 2.0381,
|
| 513 |
-
"step": 2232
|
| 514 |
-
},
|
| 515 |
-
{
|
| 516 |
-
"epoch": 0.056694057520793664,
|
| 517 |
-
"grad_norm": 1.4872742891311646,
|
| 518 |
-
"learning_rate": 4.992031299767347e-05,
|
| 519 |
-
"loss": 2.0227,
|
| 520 |
-
"step": 2263
|
| 521 |
-
},
|
| 522 |
-
{
|
| 523 |
-
"epoch": 0.057470688445736044,
|
| 524 |
-
"grad_norm": 1.4538527727127075,
|
| 525 |
-
"learning_rate": 4.9913472307114386e-05,
|
| 526 |
-
"loss": 2.0395,
|
| 527 |
-
"step": 2294
|
| 528 |
-
},
|
| 529 |
-
{
|
| 530 |
-
"epoch": 0.058247319370678424,
|
| 531 |
-
"grad_norm": 1.432769536972046,
|
| 532 |
-
"learning_rate": 4.9906350471406446e-05,
|
| 533 |
-
"loss": 2.0352,
|
| 534 |
-
"step": 2325
|
| 535 |
-
},
|
| 536 |
-
{
|
| 537 |
-
"epoch": 0.059023950295620804,
|
| 538 |
-
"grad_norm": 1.4535977840423584,
|
| 539 |
-
"learning_rate": 4.989894757091861e-05,
|
| 540 |
-
"loss": 2.0341,
|
| 541 |
-
"step": 2356
|
| 542 |
-
},
|
| 543 |
-
{
|
| 544 |
-
"epoch": 0.059800581220563184,
|
| 545 |
-
"grad_norm": 1.4004398584365845,
|
| 546 |
-
"learning_rate": 4.989126368919158e-05,
|
| 547 |
-
"loss": 2.0185,
|
| 548 |
-
"step": 2387
|
| 549 |
-
},
|
| 550 |
-
{
|
| 551 |
-
"epoch": 0.060577212145505564,
|
| 552 |
-
"grad_norm": 1.433273434638977,
|
| 553 |
-
"learning_rate": 4.988329891293693e-05,
|
| 554 |
-
"loss": 2.036,
|
| 555 |
-
"step": 2418
|
| 556 |
-
},
|
| 557 |
-
{
|
| 558 |
-
"epoch": 0.06135384307044794,
|
| 559 |
-
"grad_norm": 1.3791290521621704,
|
| 560 |
-
"learning_rate": 4.987505333203608e-05,
|
| 561 |
-
"loss": 2.0421,
|
| 562 |
-
"step": 2449
|
| 563 |
-
},
|
| 564 |
-
{
|
| 565 |
-
"epoch": 0.06213047399539032,
|
| 566 |
-
"grad_norm": 2.008694648742676,
|
| 567 |
-
"learning_rate": 4.9866527039539276e-05,
|
| 568 |
-
"loss": 1.9948,
|
| 569 |
-
"step": 2480
|
| 570 |
-
},
|
| 571 |
-
{
|
| 572 |
-
"epoch": 0.0629071049203327,
|
| 573 |
-
"grad_norm": 1.3773164749145508,
|
| 574 |
-
"learning_rate": 4.9857720131664594e-05,
|
| 575 |
-
"loss": 2.0158,
|
| 576 |
-
"step": 2511
|
| 577 |
-
},
|
| 578 |
-
{
|
| 579 |
-
"epoch": 0.06368373584527508,
|
| 580 |
-
"grad_norm": 1.4489777088165283,
|
| 581 |
-
"learning_rate": 4.9848632707796773e-05,
|
| 582 |
-
"loss": 2.0216,
|
| 583 |
-
"step": 2542
|
| 584 |
-
},
|
| 585 |
-
{
|
| 586 |
-
"epoch": 0.06446036677021745,
|
| 587 |
-
"grad_norm": 2.1266908645629883,
|
| 588 |
-
"learning_rate": 4.9839264870486155e-05,
|
| 589 |
-
"loss": 1.9962,
|
| 590 |
-
"step": 2573
|
| 591 |
-
},
|
| 592 |
-
{
|
| 593 |
-
"epoch": 0.06523699769515984,
|
| 594 |
-
"grad_norm": 1.3704332113265991,
|
| 595 |
-
"learning_rate": 4.9829616725447526e-05,
|
| 596 |
-
"loss": 1.9801,
|
| 597 |
-
"step": 2604
|
| 598 |
-
},
|
| 599 |
-
{
|
| 600 |
-
"epoch": 0.06601362862010221,
|
| 601 |
-
"grad_norm": 1.3643279075622559,
|
| 602 |
-
"learning_rate": 4.981968838155888e-05,
|
| 603 |
-
"loss": 1.9902,
|
| 604 |
-
"step": 2635
|
| 605 |
-
},
|
| 606 |
-
{
|
| 607 |
-
"epoch": 0.0667902595450446,
|
| 608 |
-
"grad_norm": 1.3495409488677979,
|
| 609 |
-
"learning_rate": 4.980947995086024e-05,
|
| 610 |
-
"loss": 1.993,
|
| 611 |
-
"step": 2666
|
| 612 |
-
},
|
| 613 |
-
{
|
| 614 |
-
"epoch": 0.06756689046998697,
|
| 615 |
-
"grad_norm": 1.3918874263763428,
|
| 616 |
-
"learning_rate": 4.979899154855234e-05,
|
| 617 |
-
"loss": 1.9782,
|
| 618 |
-
"step": 2697
|
| 619 |
-
},
|
| 620 |
-
{
|
| 621 |
-
"epoch": 0.06834352139492936,
|
| 622 |
-
"grad_norm": 1.3205535411834717,
|
| 623 |
-
"learning_rate": 4.9788223292995386e-05,
|
| 624 |
-
"loss": 1.9638,
|
| 625 |
-
"step": 2728
|
| 626 |
-
},
|
| 627 |
-
{
|
| 628 |
-
"epoch": 0.06912015231987173,
|
| 629 |
-
"grad_norm": 1.3123114109039307,
|
| 630 |
-
"learning_rate": 4.977717530570768e-05,
|
| 631 |
-
"loss": 1.9826,
|
| 632 |
-
"step": 2759
|
| 633 |
-
},
|
| 634 |
-
{
|
| 635 |
-
"epoch": 0.0698967832448141,
|
| 636 |
-
"grad_norm": 1.3138995170593262,
|
| 637 |
-
"learning_rate": 4.976584771136425e-05,
|
| 638 |
-
"loss": 1.9938,
|
| 639 |
-
"step": 2790
|
| 640 |
-
},
|
| 641 |
-
{
|
| 642 |
-
"epoch": 0.07067341416975649,
|
| 643 |
-
"grad_norm": 1.2964009046554565,
|
| 644 |
-
"learning_rate": 4.975424063779547e-05,
|
| 645 |
-
"loss": 1.9924,
|
| 646 |
-
"step": 2821
|
| 647 |
-
},
|
| 648 |
-
{
|
| 649 |
-
"epoch": 0.07145004509469886,
|
| 650 |
-
"grad_norm": 1.3010739088058472,
|
| 651 |
-
"learning_rate": 4.974235421598557e-05,
|
| 652 |
-
"loss": 1.9592,
|
| 653 |
-
"step": 2852
|
| 654 |
-
},
|
| 655 |
-
{
|
| 656 |
-
"epoch": 0.07222667601964125,
|
| 657 |
-
"grad_norm": 1.2549103498458862,
|
| 658 |
-
"learning_rate": 4.973018858007122e-05,
|
| 659 |
-
"loss": 1.9394,
|
| 660 |
-
"step": 2883
|
| 661 |
-
},
|
| 662 |
-
{
|
| 663 |
-
"epoch": 0.07300330694458362,
|
| 664 |
-
"grad_norm": 1.3198585510253906,
|
| 665 |
-
"learning_rate": 4.9717743867339963e-05,
|
| 666 |
-
"loss": 1.989,
|
| 667 |
-
"step": 2914
|
| 668 |
-
},
|
| 669 |
-
{
|
| 670 |
-
"epoch": 0.07377993786952601,
|
| 671 |
-
"grad_norm": 1.3653398752212524,
|
| 672 |
-
"learning_rate": 4.9705020218228695e-05,
|
| 673 |
-
"loss": 1.9499,
|
| 674 |
-
"step": 2945
|
| 675 |
-
},
|
| 676 |
-
{
|
| 677 |
-
"epoch": 0.07455656879446838,
|
| 678 |
-
"grad_norm": 4.606905937194824,
|
| 679 |
-
"learning_rate": 4.969201777632205e-05,
|
| 680 |
-
"loss": 1.9504,
|
| 681 |
-
"step": 2976
|
| 682 |
-
},
|
| 683 |
-
{
|
| 684 |
-
"epoch": 0.07533319971941076,
|
| 685 |
-
"grad_norm": 1.2823129892349243,
|
| 686 |
-
"learning_rate": 4.9678736688350846e-05,
|
| 687 |
-
"loss": 1.9483,
|
| 688 |
-
"step": 3007
|
| 689 |
-
},
|
| 690 |
-
{
|
| 691 |
-
"epoch": 0.07610983064435314,
|
| 692 |
-
"grad_norm": 1.2803308963775635,
|
| 693 |
-
"learning_rate": 4.966517710419033e-05,
|
| 694 |
-
"loss": 1.9604,
|
| 695 |
-
"step": 3038
|
| 696 |
-
},
|
| 697 |
-
{
|
| 698 |
-
"epoch": 0.07688646156929552,
|
| 699 |
-
"grad_norm": 1.2765967845916748,
|
| 700 |
-
"learning_rate": 4.965133917685858e-05,
|
| 701 |
-
"loss": 1.941,
|
| 702 |
-
"step": 3069
|
| 703 |
-
},
|
| 704 |
-
{
|
| 705 |
-
"epoch": 0.0776630924942379,
|
| 706 |
-
"grad_norm": 2.622286796569824,
|
| 707 |
-
"learning_rate": 4.9637223062514714e-05,
|
| 708 |
-
"loss": 1.9426,
|
| 709 |
-
"step": 3100
|
| 710 |
-
},
|
| 711 |
-
{
|
| 712 |
-
"epoch": 0.07843972341918028,
|
| 713 |
-
"grad_norm": 1.231387972831726,
|
| 714 |
-
"learning_rate": 4.962282892045718e-05,
|
| 715 |
-
"loss": 1.9416,
|
| 716 |
-
"step": 3131
|
| 717 |
-
},
|
| 718 |
-
{
|
| 719 |
-
"epoch": 0.07921635434412266,
|
| 720 |
-
"grad_norm": 1.2499909400939941,
|
| 721 |
-
"learning_rate": 4.9608156913121904e-05,
|
| 722 |
-
"loss": 1.9226,
|
| 723 |
-
"step": 3162
|
| 724 |
-
},
|
| 725 |
-
{
|
| 726 |
-
"epoch": 0.07999298526906504,
|
| 727 |
-
"grad_norm": 1.296276330947876,
|
| 728 |
-
"learning_rate": 4.959320720608049e-05,
|
| 729 |
-
"loss": 1.935,
|
| 730 |
-
"step": 3193
|
| 731 |
-
},
|
| 732 |
-
{
|
| 733 |
-
"epoch": 0.08076961619400741,
|
| 734 |
-
"grad_norm": 1.2642258405685425,
|
| 735 |
-
"learning_rate": 4.9577979968038354e-05,
|
| 736 |
-
"loss": 1.9185,
|
| 737 |
-
"step": 3224
|
| 738 |
-
},
|
| 739 |
-
{
|
| 740 |
-
"epoch": 0.0815462471189498,
|
| 741 |
-
"grad_norm": 1.2396386861801147,
|
| 742 |
-
"learning_rate": 4.956247537083282e-05,
|
| 743 |
-
"loss": 1.9361,
|
| 744 |
-
"step": 3255
|
| 745 |
-
},
|
| 746 |
-
{
|
| 747 |
-
"epoch": 0.08232287804389217,
|
| 748 |
-
"grad_norm": 1.1811271905899048,
|
| 749 |
-
"learning_rate": 4.9546693589431145e-05,
|
| 750 |
-
"loss": 1.9276,
|
| 751 |
-
"step": 3286
|
| 752 |
-
},
|
| 753 |
-
{
|
| 754 |
-
"epoch": 0.08309950896883456,
|
| 755 |
-
"grad_norm": 1.2897577285766602,
|
| 756 |
-
"learning_rate": 4.9530634801928595e-05,
|
| 757 |
-
"loss": 1.9277,
|
| 758 |
-
"step": 3317
|
| 759 |
-
},
|
| 760 |
-
{
|
| 761 |
-
"epoch": 0.08387613989377693,
|
| 762 |
-
"grad_norm": 1.1453903913497925,
|
| 763 |
-
"learning_rate": 4.9514299189546395e-05,
|
| 764 |
-
"loss": 1.9109,
|
| 765 |
-
"step": 3348
|
| 766 |
-
},
|
| 767 |
-
{
|
| 768 |
-
"epoch": 0.08465277081871932,
|
| 769 |
-
"grad_norm": 1.1600992679595947,
|
| 770 |
-
"learning_rate": 4.949768693662973e-05,
|
| 771 |
-
"loss": 1.9248,
|
| 772 |
-
"step": 3379
|
| 773 |
-
},
|
| 774 |
-
{
|
| 775 |
-
"epoch": 0.08542940174366169,
|
| 776 |
-
"grad_norm": 1.234217882156372,
|
| 777 |
-
"learning_rate": 4.948079823064559e-05,
|
| 778 |
-
"loss": 1.9236,
|
| 779 |
-
"step": 3410
|
| 780 |
-
},
|
| 781 |
-
{
|
| 782 |
-
"epoch": 0.08620603266860406,
|
| 783 |
-
"grad_norm": 1.1933766603469849,
|
| 784 |
-
"learning_rate": 4.946363326218074e-05,
|
| 785 |
-
"loss": 1.9284,
|
| 786 |
-
"step": 3441
|
| 787 |
-
},
|
| 788 |
-
{
|
| 789 |
-
"epoch": 0.08698266359354645,
|
| 790 |
-
"grad_norm": 1.2087618112564087,
|
| 791 |
-
"learning_rate": 4.9446192224939525e-05,
|
| 792 |
-
"loss": 1.8971,
|
| 793 |
-
"step": 3472
|
| 794 |
-
},
|
| 795 |
-
{
|
| 796 |
-
"epoch": 0.08775929451848882,
|
| 797 |
-
"grad_norm": 1.227864146232605,
|
| 798 |
-
"learning_rate": 4.942847531574167e-05,
|
| 799 |
-
"loss": 1.9353,
|
| 800 |
-
"step": 3503
|
| 801 |
-
},
|
| 802 |
-
{
|
| 803 |
-
"epoch": 0.08853592544343121,
|
| 804 |
-
"grad_norm": 1.2828229665756226,
|
| 805 |
-
"learning_rate": 4.941048273452008e-05,
|
| 806 |
-
"loss": 1.9085,
|
| 807 |
-
"step": 3534
|
| 808 |
-
},
|
| 809 |
-
{
|
| 810 |
-
"epoch": 0.08931255636837358,
|
| 811 |
-
"grad_norm": 1.2086588144302368,
|
| 812 |
-
"learning_rate": 4.9392214684318605e-05,
|
| 813 |
-
"loss": 1.9044,
|
| 814 |
-
"step": 3565
|
| 815 |
-
},
|
| 816 |
-
{
|
| 817 |
-
"epoch": 0.09008918729331597,
|
| 818 |
-
"grad_norm": 1.1942152976989746,
|
| 819 |
-
"learning_rate": 4.93736713712897e-05,
|
| 820 |
-
"loss": 1.9182,
|
| 821 |
-
"step": 3596
|
| 822 |
-
},
|
| 823 |
-
{
|
| 824 |
-
"epoch": 0.09086581821825834,
|
| 825 |
-
"grad_norm": 1.2399394512176514,
|
| 826 |
-
"learning_rate": 4.9354853004692124e-05,
|
| 827 |
-
"loss": 1.8943,
|
| 828 |
-
"step": 3627
|
| 829 |
-
},
|
| 830 |
-
{
|
| 831 |
-
"epoch": 0.09164244914320072,
|
| 832 |
-
"grad_norm": 1.227376937866211,
|
| 833 |
-
"learning_rate": 4.93357597968886e-05,
|
| 834 |
-
"loss": 1.8881,
|
| 835 |
-
"step": 3658
|
| 836 |
-
},
|
| 837 |
-
{
|
| 838 |
-
"epoch": 0.0924190800681431,
|
| 839 |
-
"grad_norm": 1.1314102411270142,
|
| 840 |
-
"learning_rate": 4.931639196334338e-05,
|
| 841 |
-
"loss": 1.8878,
|
| 842 |
-
"step": 3689
|
| 843 |
-
},
|
| 844 |
-
{
|
| 845 |
-
"epoch": 0.09319571099308548,
|
| 846 |
-
"grad_norm": 1.192134141921997,
|
| 847 |
-
"learning_rate": 4.9296749722619826e-05,
|
| 848 |
-
"loss": 1.8857,
|
| 849 |
-
"step": 3720
|
| 850 |
-
},
|
| 851 |
-
{
|
| 852 |
-
"epoch": 0.09397234191802786,
|
| 853 |
-
"grad_norm": 1.1905503273010254,
|
| 854 |
-
"learning_rate": 4.9276833296377966e-05,
|
| 855 |
-
"loss": 1.8701,
|
| 856 |
-
"step": 3751
|
| 857 |
-
},
|
| 858 |
-
{
|
| 859 |
-
"epoch": 0.09474897284297024,
|
| 860 |
-
"grad_norm": 1.2335184812545776,
|
| 861 |
-
"learning_rate": 4.925664290937196e-05,
|
| 862 |
-
"loss": 1.8741,
|
| 863 |
-
"step": 3782
|
| 864 |
-
},
|
| 865 |
-
{
|
| 866 |
-
"epoch": 0.09552560376791262,
|
| 867 |
-
"grad_norm": 1.1403234004974365,
|
| 868 |
-
"learning_rate": 4.9236178789447576e-05,
|
| 869 |
-
"loss": 1.8658,
|
| 870 |
-
"step": 3813
|
| 871 |
-
},
|
| 872 |
-
{
|
| 873 |
-
"epoch": 0.096302234692855,
|
| 874 |
-
"grad_norm": 1.1734315156936646,
|
| 875 |
-
"learning_rate": 4.921544116753962e-05,
|
| 876 |
-
"loss": 1.8724,
|
| 877 |
-
"step": 3844
|
| 878 |
-
},
|
| 879 |
-
{
|
| 880 |
-
"epoch": 0.09707886561779737,
|
| 881 |
-
"grad_norm": 1.2637231349945068,
|
| 882 |
-
"learning_rate": 4.919443027766935e-05,
|
| 883 |
-
"loss": 1.867,
|
| 884 |
-
"step": 3875
|
| 885 |
-
},
|
| 886 |
-
{
|
| 887 |
-
"epoch": 0.09785549654273976,
|
| 888 |
-
"grad_norm": 1.1608805656433105,
|
| 889 |
-
"learning_rate": 4.91731463569418e-05,
|
| 890 |
-
"loss": 1.8764,
|
| 891 |
-
"step": 3906
|
| 892 |
-
},
|
| 893 |
-
{
|
| 894 |
-
"epoch": 0.09863212746768213,
|
| 895 |
-
"grad_norm": 1.1562029123306274,
|
| 896 |
-
"learning_rate": 4.915158964554312e-05,
|
| 897 |
-
"loss": 1.8612,
|
| 898 |
-
"step": 3937
|
| 899 |
-
},
|
| 900 |
-
{
|
| 901 |
-
"epoch": 0.09940875839262452,
|
| 902 |
-
"grad_norm": 1.1918668746948242,
|
| 903 |
-
"learning_rate": 4.912976038673786e-05,
|
| 904 |
-
"loss": 1.866,
|
| 905 |
-
"step": 3968
|
| 906 |
-
},
|
| 907 |
-
{
|
| 908 |
-
"epoch": 0.10018538931756689,
|
| 909 |
-
"grad_norm": 1.180206537246704,
|
| 910 |
-
"learning_rate": 4.9107658826866254e-05,
|
| 911 |
-
"loss": 1.849,
|
| 912 |
-
"step": 3999
|
| 913 |
-
},
|
| 914 |
-
{
|
| 915 |
-
"epoch": 0.10096202024250928,
|
| 916 |
-
"grad_norm": 1.0747199058532715,
|
| 917 |
-
"learning_rate": 4.908528521534139e-05,
|
| 918 |
-
"loss": 1.8547,
|
| 919 |
-
"step": 4030
|
| 920 |
-
},
|
| 921 |
-
{
|
| 922 |
-
"epoch": 0.10173865116745165,
|
| 923 |
-
"grad_norm": 1.103786826133728,
|
| 924 |
-
"learning_rate": 4.906263980464644e-05,
|
| 925 |
-
"loss": 1.864,
|
| 926 |
-
"step": 4061
|
| 927 |
-
},
|
| 928 |
-
{
|
| 929 |
-
"epoch": 0.10251528209239402,
|
| 930 |
-
"grad_norm": 1.1390912532806396,
|
| 931 |
-
"learning_rate": 4.903972285033178e-05,
|
| 932 |
-
"loss": 1.8669,
|
| 933 |
-
"step": 4092
|
| 934 |
-
},
|
| 935 |
-
{
|
| 936 |
-
"epoch": 0.10329191301733641,
|
| 937 |
-
"grad_norm": 1.1488468647003174,
|
| 938 |
-
"learning_rate": 4.901653461101213e-05,
|
| 939 |
-
"loss": 1.8445,
|
| 940 |
-
"step": 4123
|
| 941 |
-
},
|
| 942 |
-
{
|
| 943 |
-
"epoch": 0.10406854394227878,
|
| 944 |
-
"grad_norm": 1.1589927673339844,
|
| 945 |
-
"learning_rate": 4.8993075348363626e-05,
|
| 946 |
-
"loss": 1.8529,
|
| 947 |
-
"step": 4154
|
| 948 |
-
},
|
| 949 |
-
{
|
| 950 |
-
"epoch": 0.10484517486722117,
|
| 951 |
-
"grad_norm": 1.1793478727340698,
|
| 952 |
-
"learning_rate": 4.896934532712084e-05,
|
| 953 |
-
"loss": 1.8818,
|
| 954 |
-
"step": 4185
|
| 955 |
-
},
|
| 956 |
-
{
|
| 957 |
-
"epoch": 0.10562180579216354,
|
| 958 |
-
"grad_norm": 1.165292739868164,
|
| 959 |
-
"learning_rate": 4.8945344815073846e-05,
|
| 960 |
-
"loss": 1.8425,
|
| 961 |
-
"step": 4216
|
| 962 |
-
},
|
| 963 |
-
{
|
| 964 |
-
"epoch": 0.10639843671710593,
|
| 965 |
-
"grad_norm": 1.105946660041809,
|
| 966 |
-
"learning_rate": 4.892107408306516e-05,
|
| 967 |
-
"loss": 1.8327,
|
| 968 |
-
"step": 4247
|
| 969 |
-
},
|
| 970 |
-
{
|
| 971 |
-
"epoch": 0.1071750676420483,
|
| 972 |
-
"grad_norm": 1.1690527200698853,
|
| 973 |
-
"learning_rate": 4.889653340498669e-05,
|
| 974 |
-
"loss": 1.8428,
|
| 975 |
-
"step": 4278
|
| 976 |
-
},
|
| 977 |
-
{
|
| 978 |
-
"epoch": 0.10795169856699068,
|
| 979 |
-
"grad_norm": 1.1106913089752197,
|
| 980 |
-
"learning_rate": 4.8871723057776664e-05,
|
| 981 |
-
"loss": 1.839,
|
| 982 |
-
"step": 4309
|
| 983 |
-
},
|
| 984 |
-
{
|
| 985 |
-
"epoch": 0.10872832949193306,
|
| 986 |
-
"grad_norm": 1.1590090990066528,
|
| 987 |
-
"learning_rate": 4.8846643321416476e-05,
|
| 988 |
-
"loss": 1.8658,
|
| 989 |
-
"step": 4340
|
| 990 |
-
},
|
| 991 |
-
{
|
| 992 |
-
"epoch": 0.10950496041687544,
|
| 993 |
-
"grad_norm": 1.1315875053405762,
|
| 994 |
-
"learning_rate": 4.882129447892753e-05,
|
| 995 |
-
"loss": 1.8282,
|
| 996 |
-
"step": 4371
|
| 997 |
-
},
|
| 998 |
-
{
|
| 999 |
-
"epoch": 0.11028159134181782,
|
| 1000 |
-
"grad_norm": 1.6055009365081787,
|
| 1001 |
-
"learning_rate": 4.8795676816368076e-05,
|
| 1002 |
-
"loss": 1.8294,
|
| 1003 |
-
"step": 4402
|
| 1004 |
-
},
|
| 1005 |
-
{
|
| 1006 |
-
"epoch": 0.1110582222667602,
|
| 1007 |
-
"grad_norm": 1.1236201524734497,
|
| 1008 |
-
"learning_rate": 4.876979062282995e-05,
|
| 1009 |
-
"loss": 1.8325,
|
| 1010 |
-
"step": 4433
|
| 1011 |
-
},
|
| 1012 |
-
{
|
| 1013 |
-
"epoch": 0.11183485319170258,
|
| 1014 |
-
"grad_norm": 1.0830161571502686,
|
| 1015 |
-
"learning_rate": 4.8743636190435325e-05,
|
| 1016 |
-
"loss": 1.8451,
|
| 1017 |
-
"step": 4464
|
| 1018 |
-
},
|
| 1019 |
-
{
|
| 1020 |
-
"epoch": 0.11261148411664496,
|
| 1021 |
-
"grad_norm": 1.1663005352020264,
|
| 1022 |
-
"learning_rate": 4.871721381433344e-05,
|
| 1023 |
-
"loss": 1.8349,
|
| 1024 |
-
"step": 4495
|
| 1025 |
-
},
|
| 1026 |
-
{
|
| 1027 |
-
"epoch": 0.11338811504158733,
|
| 1028 |
-
"grad_norm": 1.2522406578063965,
|
| 1029 |
-
"learning_rate": 4.869052379269719e-05,
|
| 1030 |
-
"loss": 1.8162,
|
| 1031 |
-
"step": 4526
|
| 1032 |
-
},
|
| 1033 |
-
{
|
| 1034 |
-
"epoch": 0.11416474596652972,
|
| 1035 |
-
"grad_norm": 1.1271142959594727,
|
| 1036 |
-
"learning_rate": 4.866356642671985e-05,
|
| 1037 |
-
"loss": 1.8348,
|
| 1038 |
-
"step": 4557
|
| 1039 |
-
},
|
| 1040 |
-
{
|
| 1041 |
-
"epoch": 0.11494137689147209,
|
| 1042 |
-
"grad_norm": 1.053753137588501,
|
| 1043 |
-
"learning_rate": 4.8636342020611634e-05,
|
| 1044 |
-
"loss": 1.8376,
|
| 1045 |
-
"step": 4588
|
| 1046 |
-
},
|
| 1047 |
-
{
|
| 1048 |
-
"epoch": 0.11571800781641448,
|
| 1049 |
-
"grad_norm": 1.1469056606292725,
|
| 1050 |
-
"learning_rate": 4.860885088159626e-05,
|
| 1051 |
-
"loss": 1.8248,
|
| 1052 |
-
"step": 4619
|
| 1053 |
-
},
|
| 1054 |
-
{
|
| 1055 |
-
"epoch": 0.11649463874135685,
|
| 1056 |
-
"grad_norm": 1.116128921508789,
|
| 1057 |
-
"learning_rate": 4.858109331990751e-05,
|
| 1058 |
-
"loss": 1.8454,
|
| 1059 |
-
"step": 4650
|
| 1060 |
-
},
|
| 1061 |
-
{
|
| 1062 |
-
"epoch": 0.11727126966629922,
|
| 1063 |
-
"grad_norm": 1.0742651224136353,
|
| 1064 |
-
"learning_rate": 4.855306964878567e-05,
|
| 1065 |
-
"loss": 1.8231,
|
| 1066 |
-
"step": 4681
|
| 1067 |
-
},
|
| 1068 |
-
{
|
| 1069 |
-
"epoch": 0.11804790059124161,
|
| 1070 |
-
"grad_norm": 1.101657748222351,
|
| 1071 |
-
"learning_rate": 4.8524780184474084e-05,
|
| 1072 |
-
"loss": 1.8421,
|
| 1073 |
-
"step": 4712
|
| 1074 |
-
},
|
| 1075 |
-
{
|
| 1076 |
-
"epoch": 0.11882453151618398,
|
| 1077 |
-
"grad_norm": 1.0891473293304443,
|
| 1078 |
-
"learning_rate": 4.8496225246215496e-05,
|
| 1079 |
-
"loss": 1.8053,
|
| 1080 |
-
"step": 4743
|
| 1081 |
-
},
|
| 1082 |
-
{
|
| 1083 |
-
"epoch": 0.11960116244112637,
|
| 1084 |
-
"grad_norm": 1.1044034957885742,
|
| 1085 |
-
"learning_rate": 4.8467405156248505e-05,
|
| 1086 |
-
"loss": 1.8184,
|
| 1087 |
-
"step": 4774
|
| 1088 |
-
},
|
| 1089 |
-
{
|
| 1090 |
-
"epoch": 0.12037779336606874,
|
| 1091 |
-
"grad_norm": 1.0644783973693848,
|
| 1092 |
-
"learning_rate": 4.843832023980392e-05,
|
| 1093 |
-
"loss": 1.8237,
|
| 1094 |
-
"step": 4805
|
| 1095 |
-
},
|
| 1096 |
-
{
|
| 1097 |
-
"epoch": 0.12115442429101113,
|
| 1098 |
-
"grad_norm": 1.0427252054214478,
|
| 1099 |
-
"learning_rate": 4.840897082510106e-05,
|
| 1100 |
-
"loss": 1.8189,
|
| 1101 |
-
"step": 4836
|
| 1102 |
-
},
|
| 1103 |
-
{
|
| 1104 |
-
"epoch": 0.1219310552159535,
|
| 1105 |
-
"grad_norm": 1.0806516408920288,
|
| 1106 |
-
"learning_rate": 4.8379357243344084e-05,
|
| 1107 |
-
"loss": 1.7958,
|
| 1108 |
-
"step": 4867
|
| 1109 |
-
},
|
| 1110 |
-
{
|
| 1111 |
-
"epoch": 0.12270768614089587,
|
| 1112 |
-
"grad_norm": 1.092581868171692,
|
| 1113 |
-
"learning_rate": 4.8349479828718236e-05,
|
| 1114 |
-
"loss": 1.8229,
|
| 1115 |
-
"step": 4898
|
| 1116 |
-
},
|
| 1117 |
-
{
|
| 1118 |
-
"epoch": 0.12348431706583826,
|
| 1119 |
-
"grad_norm": 1.0858657360076904,
|
| 1120 |
-
"learning_rate": 4.8319338918386075e-05,
|
| 1121 |
-
"loss": 1.8165,
|
| 1122 |
-
"step": 4929
|
| 1123 |
-
},
|
| 1124 |
-
{
|
| 1125 |
-
"epoch": 0.12426094799078063,
|
| 1126 |
-
"grad_norm": 1.073818325996399,
|
| 1127 |
-
"learning_rate": 4.828893485248369e-05,
|
| 1128 |
-
"loss": 1.8352,
|
| 1129 |
-
"step": 4960
|
| 1130 |
-
},
|
| 1131 |
-
{
|
| 1132 |
-
"epoch": 0.125037578915723,
|
| 1133 |
-
"grad_norm": 1.069009780883789,
|
| 1134 |
-
"learning_rate": 4.825826797411682e-05,
|
| 1135 |
-
"loss": 1.8,
|
| 1136 |
-
"step": 4991
|
| 1137 |
-
},
|
| 1138 |
-
{
|
| 1139 |
-
"epoch": 0.1258142098406654,
|
| 1140 |
-
"grad_norm": 1.0416266918182373,
|
| 1141 |
-
"learning_rate": 4.822733862935702e-05,
|
| 1142 |
-
"loss": 1.8224,
|
| 1143 |
-
"step": 5022
|
| 1144 |
-
},
|
| 1145 |
-
{
|
| 1146 |
-
"epoch": 0.12659084076560778,
|
| 1147 |
-
"grad_norm": 1.093551516532898,
|
| 1148 |
-
"learning_rate": 4.819614716723775e-05,
|
| 1149 |
-
"loss": 1.8005,
|
| 1150 |
-
"step": 5053
|
| 1151 |
-
},
|
| 1152 |
-
{
|
| 1153 |
-
"epoch": 0.12736747169055015,
|
| 1154 |
-
"grad_norm": 1.026353359222412,
|
| 1155 |
-
"learning_rate": 4.8164693939750425e-05,
|
| 1156 |
-
"loss": 1.844,
|
| 1157 |
-
"step": 5084
|
| 1158 |
-
},
|
| 1159 |
-
{
|
| 1160 |
-
"epoch": 0.12814410261549253,
|
| 1161 |
-
"grad_norm": 1.102858304977417,
|
| 1162 |
-
"learning_rate": 4.813297930184042e-05,
|
| 1163 |
-
"loss": 1.8045,
|
| 1164 |
-
"step": 5115
|
| 1165 |
-
},
|
| 1166 |
-
{
|
| 1167 |
-
"epoch": 0.1289207335404349,
|
| 1168 |
-
"grad_norm": 1.0537272691726685,
|
| 1169 |
-
"learning_rate": 4.810100361140314e-05,
|
| 1170 |
-
"loss": 1.8054,
|
| 1171 |
-
"step": 5146
|
| 1172 |
-
},
|
| 1173 |
-
{
|
| 1174 |
-
"epoch": 0.1296973644653773,
|
| 1175 |
-
"grad_norm": 1.0389387607574463,
|
| 1176 |
-
"learning_rate": 4.8068767229279885e-05,
|
| 1177 |
-
"loss": 1.7734,
|
| 1178 |
-
"step": 5177
|
| 1179 |
-
},
|
| 1180 |
-
{
|
| 1181 |
-
"epoch": 0.13047399539031967,
|
| 1182 |
-
"grad_norm": 1.0274319648742676,
|
| 1183 |
-
"learning_rate": 4.8036270519253854e-05,
|
| 1184 |
-
"loss": 1.788,
|
| 1185 |
-
"step": 5208
|
| 1186 |
-
},
|
| 1187 |
-
{
|
| 1188 |
-
"epoch": 0.13125062631526205,
|
| 1189 |
-
"grad_norm": 1.0932128429412842,
|
| 1190 |
-
"learning_rate": 4.8003513848046e-05,
|
| 1191 |
-
"loss": 1.7813,
|
| 1192 |
-
"step": 5239
|
| 1193 |
-
},
|
| 1194 |
-
{
|
| 1195 |
-
"epoch": 0.13202725724020442,
|
| 1196 |
-
"grad_norm": 1.0294640064239502,
|
| 1197 |
-
"learning_rate": 4.79704975853109e-05,
|
| 1198 |
-
"loss": 1.81,
|
| 1199 |
-
"step": 5270
|
| 1200 |
-
},
|
| 1201 |
-
{
|
| 1202 |
-
"epoch": 0.13280388816514682,
|
| 1203 |
-
"grad_norm": 1.0617210865020752,
|
| 1204 |
-
"learning_rate": 4.793722210363262e-05,
|
| 1205 |
-
"loss": 1.8017,
|
| 1206 |
-
"step": 5301
|
| 1207 |
-
},
|
| 1208 |
-
{
|
| 1209 |
-
"epoch": 0.1335805190900892,
|
| 1210 |
-
"grad_norm": 1.0657798051834106,
|
| 1211 |
-
"learning_rate": 4.7903687778520414e-05,
|
| 1212 |
-
"loss": 1.7884,
|
| 1213 |
-
"step": 5332
|
| 1214 |
-
},
|
| 1215 |
-
{
|
| 1216 |
-
"epoch": 0.13435715001503157,
|
| 1217 |
-
"grad_norm": 0.9954230189323425,
|
| 1218 |
-
"learning_rate": 4.7869894988404593e-05,
|
| 1219 |
-
"loss": 1.7848,
|
| 1220 |
-
"step": 5363
|
| 1221 |
-
},
|
| 1222 |
-
{
|
| 1223 |
-
"epoch": 0.13513378093997394,
|
| 1224 |
-
"grad_norm": 1.117066740989685,
|
| 1225 |
-
"learning_rate": 4.783584411463221e-05,
|
| 1226 |
-
"loss": 1.7984,
|
| 1227 |
-
"step": 5394
|
| 1228 |
-
},
|
| 1229 |
-
{
|
| 1230 |
-
"epoch": 0.13591041186491631,
|
| 1231 |
-
"grad_norm": 1.0706870555877686,
|
| 1232 |
-
"learning_rate": 4.780153554146274e-05,
|
| 1233 |
-
"loss": 1.8008,
|
| 1234 |
-
"step": 5425
|
| 1235 |
-
},
|
| 1236 |
-
{
|
| 1237 |
-
"epoch": 0.13668704278985871,
|
| 1238 |
-
"grad_norm": 1.063238501548767,
|
| 1239 |
-
"learning_rate": 4.7766969656063766e-05,
|
| 1240 |
-
"loss": 1.7754,
|
| 1241 |
-
"step": 5456
|
| 1242 |
-
},
|
| 1243 |
-
{
|
| 1244 |
-
"epoch": 0.1374636737148011,
|
| 1245 |
-
"grad_norm": 1.0702152252197266,
|
| 1246 |
-
"learning_rate": 4.773214684850662e-05,
|
| 1247 |
-
"loss": 1.8037,
|
| 1248 |
-
"step": 5487
|
| 1249 |
-
},
|
| 1250 |
-
{
|
| 1251 |
-
"epoch": 0.13824030463974346,
|
| 1252 |
-
"grad_norm": 1.0318788290023804,
|
| 1253 |
-
"learning_rate": 4.769706751176193e-05,
|
| 1254 |
-
"loss": 1.8174,
|
| 1255 |
-
"step": 5518
|
| 1256 |
-
},
|
| 1257 |
-
{
|
| 1258 |
-
"epoch": 0.13901693556468583,
|
| 1259 |
-
"grad_norm": 1.0097755193710327,
|
| 1260 |
-
"learning_rate": 4.7661732041695264e-05,
|
| 1261 |
-
"loss": 1.7648,
|
| 1262 |
-
"step": 5549
|
| 1263 |
-
},
|
| 1264 |
-
{
|
| 1265 |
-
"epoch": 0.1397935664896282,
|
| 1266 |
-
"grad_norm": 1.063873291015625,
|
| 1267 |
-
"learning_rate": 4.762614083706258e-05,
|
| 1268 |
-
"loss": 1.809,
|
| 1269 |
-
"step": 5580
|
| 1270 |
-
},
|
| 1271 |
-
{
|
| 1272 |
-
"epoch": 0.1405701974145706,
|
| 1273 |
-
"grad_norm": 1.0409623384475708,
|
| 1274 |
-
"learning_rate": 4.759029429950581e-05,
|
| 1275 |
-
"loss": 1.7853,
|
| 1276 |
-
"step": 5611
|
| 1277 |
-
},
|
| 1278 |
-
{
|
| 1279 |
-
"epoch": 0.14134682833951298,
|
| 1280 |
-
"grad_norm": 1.0131454467773438,
|
| 1281 |
-
"learning_rate": 4.7554192833548235e-05,
|
| 1282 |
-
"loss": 1.7759,
|
| 1283 |
-
"step": 5642
|
| 1284 |
-
},
|
| 1285 |
-
{
|
| 1286 |
-
"epoch": 0.14212345926445535,
|
| 1287 |
-
"grad_norm": 1.1056182384490967,
|
| 1288 |
-
"learning_rate": 4.751783684659e-05,
|
| 1289 |
-
"loss": 1.7959,
|
| 1290 |
-
"step": 5673
|
| 1291 |
-
},
|
| 1292 |
-
{
|
| 1293 |
-
"epoch": 0.14290009018939773,
|
| 1294 |
-
"grad_norm": 1.0572400093078613,
|
| 1295 |
-
"learning_rate": 4.748122674890348e-05,
|
| 1296 |
-
"loss": 1.7597,
|
| 1297 |
-
"step": 5704
|
| 1298 |
-
},
|
| 1299 |
-
{
|
| 1300 |
-
"epoch": 0.14367672111434013,
|
| 1301 |
-
"grad_norm": 1.0375362634658813,
|
| 1302 |
-
"learning_rate": 4.7444362953628654e-05,
|
| 1303 |
-
"loss": 1.7719,
|
| 1304 |
-
"step": 5735
|
| 1305 |
-
},
|
| 1306 |
-
{
|
| 1307 |
-
"epoch": 0.1444533520392825,
|
| 1308 |
-
"grad_norm": 1.0238806009292603,
|
| 1309 |
-
"learning_rate": 4.7407245876768424e-05,
|
| 1310 |
-
"loss": 1.7966,
|
| 1311 |
-
"step": 5766
|
| 1312 |
-
},
|
| 1313 |
-
{
|
| 1314 |
-
"epoch": 0.14522998296422487,
|
| 1315 |
-
"grad_norm": 1.0335805416107178,
|
| 1316 |
-
"learning_rate": 4.736987593718397e-05,
|
| 1317 |
-
"loss": 1.7805,
|
| 1318 |
-
"step": 5797
|
| 1319 |
-
},
|
| 1320 |
-
{
|
| 1321 |
-
"epoch": 0.14600661388916725,
|
| 1322 |
-
"grad_norm": 1.08907151222229,
|
| 1323 |
-
"learning_rate": 4.733225355658999e-05,
|
| 1324 |
-
"loss": 1.7905,
|
| 1325 |
-
"step": 5828
|
| 1326 |
-
},
|
| 1327 |
-
{
|
| 1328 |
-
"epoch": 0.14678324481410962,
|
| 1329 |
-
"grad_norm": 1.0151680707931519,
|
| 1330 |
-
"learning_rate": 4.7294379159549926e-05,
|
| 1331 |
-
"loss": 1.7766,
|
| 1332 |
-
"step": 5859
|
| 1333 |
-
},
|
| 1334 |
-
{
|
| 1335 |
-
"epoch": 0.14755987573905202,
|
| 1336 |
-
"grad_norm": 0.9963664412498474,
|
| 1337 |
-
"learning_rate": 4.725625317347119e-05,
|
| 1338 |
-
"loss": 1.7708,
|
| 1339 |
-
"step": 5890
|
| 1340 |
-
},
|
| 1341 |
-
{
|
| 1342 |
-
"epoch": 0.1483365066639944,
|
| 1343 |
-
"grad_norm": 1.0762684345245361,
|
| 1344 |
-
"learning_rate": 4.7217876028600374e-05,
|
| 1345 |
-
"loss": 1.7998,
|
| 1346 |
-
"step": 5921
|
| 1347 |
-
},
|
| 1348 |
-
{
|
| 1349 |
-
"epoch": 0.14911313758893677,
|
| 1350 |
-
"grad_norm": 1.1151126623153687,
|
| 1351 |
-
"learning_rate": 4.717924815801832e-05,
|
| 1352 |
-
"loss": 1.782,
|
| 1353 |
-
"step": 5952
|
| 1354 |
-
},
|
| 1355 |
-
{
|
| 1356 |
-
"epoch": 0.14988976851387914,
|
| 1357 |
-
"grad_norm": 0.9970519542694092,
|
| 1358 |
-
"learning_rate": 4.714036999763532e-05,
|
| 1359 |
-
"loss": 1.7779,
|
| 1360 |
-
"step": 5983
|
| 1361 |
-
},
|
| 1362 |
-
{
|
| 1363 |
-
"epoch": 0.1506663994388215,
|
| 1364 |
-
"grad_norm": 1.0146524906158447,
|
| 1365 |
-
"learning_rate": 4.7101241986186116e-05,
|
| 1366 |
-
"loss": 1.7631,
|
| 1367 |
-
"step": 6014
|
| 1368 |
-
},
|
| 1369 |
-
{
|
| 1370 |
-
"epoch": 0.15144303036376391,
|
| 1371 |
-
"grad_norm": 1.0554558038711548,
|
| 1372 |
-
"learning_rate": 4.7061864565225e-05,
|
| 1373 |
-
"loss": 1.7729,
|
| 1374 |
-
"step": 6045
|
| 1375 |
-
},
|
| 1376 |
-
{
|
| 1377 |
-
"epoch": 0.1522196612887063,
|
| 1378 |
-
"grad_norm": 1.0413624048233032,
|
| 1379 |
-
"learning_rate": 4.702223817912081e-05,
|
| 1380 |
-
"loss": 1.79,
|
| 1381 |
-
"step": 6076
|
| 1382 |
-
},
|
| 1383 |
-
{
|
| 1384 |
-
"epoch": 0.15299629221364866,
|
| 1385 |
-
"grad_norm": 1.07778000831604,
|
| 1386 |
-
"learning_rate": 4.698236327505195e-05,
|
| 1387 |
-
"loss": 1.787,
|
| 1388 |
-
"step": 6107
|
| 1389 |
-
},
|
| 1390 |
-
{
|
| 1391 |
-
"epoch": 0.15377292313859103,
|
| 1392 |
-
"grad_norm": 1.0084989070892334,
|
| 1393 |
-
"learning_rate": 4.694224030300127e-05,
|
| 1394 |
-
"loss": 1.7695,
|
| 1395 |
-
"step": 6138
|
| 1396 |
-
},
|
| 1397 |
-
{
|
| 1398 |
-
"epoch": 0.1545495540635334,
|
| 1399 |
-
"grad_norm": 1.0067577362060547,
|
| 1400 |
-
"learning_rate": 4.690186971575107e-05,
|
| 1401 |
-
"loss": 1.7611,
|
| 1402 |
-
"step": 6169
|
| 1403 |
-
},
|
| 1404 |
-
{
|
| 1405 |
-
"epoch": 0.1553261849884758,
|
| 1406 |
-
"grad_norm": 1.0149894952774048,
|
| 1407 |
-
"learning_rate": 4.6861251968877916e-05,
|
| 1408 |
-
"loss": 1.7734,
|
| 1409 |
-
"step": 6200
|
| 1410 |
-
},
|
| 1411 |
-
{
|
| 1412 |
-
"epoch": 0.15610281591341818,
|
| 1413 |
-
"grad_norm": 0.996447741985321,
|
| 1414 |
-
"learning_rate": 4.68203875207476e-05,
|
| 1415 |
-
"loss": 1.7609,
|
| 1416 |
-
"step": 6231
|
| 1417 |
-
},
|
| 1418 |
-
{
|
| 1419 |
-
"epoch": 0.15687944683836055,
|
| 1420 |
-
"grad_norm": 1.0334714651107788,
|
| 1421 |
-
"learning_rate": 4.677927683250983e-05,
|
| 1422 |
-
"loss": 1.7725,
|
| 1423 |
-
"step": 6262
|
| 1424 |
-
},
|
| 1425 |
-
{
|
| 1426 |
-
"epoch": 0.15765607776330293,
|
| 1427 |
-
"grad_norm": 0.949685275554657,
|
| 1428 |
-
"learning_rate": 4.6737920368093156e-05,
|
| 1429 |
-
"loss": 1.7597,
|
| 1430 |
-
"step": 6293
|
| 1431 |
-
},
|
| 1432 |
-
{
|
| 1433 |
-
"epoch": 0.15843270868824533,
|
| 1434 |
-
"grad_norm": 1.0946801900863647,
|
| 1435 |
-
"learning_rate": 4.669631859419965e-05,
|
| 1436 |
-
"loss": 1.755,
|
| 1437 |
-
"step": 6324
|
| 1438 |
-
},
|
| 1439 |
-
{
|
| 1440 |
-
"epoch": 0.1592093396131877,
|
| 1441 |
-
"grad_norm": 1.0390102863311768,
|
| 1442 |
-
"learning_rate": 4.6654471980299676e-05,
|
| 1443 |
-
"loss": 1.7755,
|
| 1444 |
-
"step": 6355
|
| 1445 |
-
},
|
| 1446 |
-
{
|
| 1447 |
-
"epoch": 0.15998597053813007,
|
| 1448 |
-
"grad_norm": 0.974733293056488,
|
| 1449 |
-
"learning_rate": 4.661238099862658e-05,
|
| 1450 |
-
"loss": 1.7619,
|
| 1451 |
-
"step": 6386
|
| 1452 |
-
},
|
| 1453 |
-
{
|
| 1454 |
-
"epoch": 0.16076260146307245,
|
| 1455 |
-
"grad_norm": 1.0192877054214478,
|
| 1456 |
-
"learning_rate": 4.657004612417138e-05,
|
| 1457 |
-
"loss": 1.7676,
|
| 1458 |
-
"step": 6417
|
| 1459 |
-
},
|
| 1460 |
-
{
|
| 1461 |
-
"epoch": 0.16153923238801482,
|
| 1462 |
-
"grad_norm": 1.0147426128387451,
|
| 1463 |
-
"learning_rate": 4.6527467834677374e-05,
|
| 1464 |
-
"loss": 1.7473,
|
| 1465 |
-
"step": 6448
|
| 1466 |
-
},
|
| 1467 |
-
{
|
| 1468 |
-
"epoch": 0.16231586331295722,
|
| 1469 |
-
"grad_norm": 1.0231157541275024,
|
| 1470 |
-
"learning_rate": 4.648464661063478e-05,
|
| 1471 |
-
"loss": 1.766,
|
| 1472 |
-
"step": 6479
|
| 1473 |
-
},
|
| 1474 |
-
{
|
| 1475 |
-
"epoch": 0.1630924942378996,
|
| 1476 |
-
"grad_norm": 0.9995896816253662,
|
| 1477 |
-
"learning_rate": 4.6441582935275264e-05,
|
| 1478 |
-
"loss": 1.7594,
|
| 1479 |
-
"step": 6510
|
| 1480 |
-
},
|
| 1481 |
-
{
|
| 1482 |
-
"epoch": 0.16386912516284197,
|
| 1483 |
-
"grad_norm": 0.9674972295761108,
|
| 1484 |
-
"learning_rate": 4.6398277294566586e-05,
|
| 1485 |
-
"loss": 1.7347,
|
| 1486 |
-
"step": 6541
|
| 1487 |
-
},
|
| 1488 |
-
{
|
| 1489 |
-
"epoch": 0.16464575608778434,
|
| 1490 |
-
"grad_norm": 0.9876355528831482,
|
| 1491 |
-
"learning_rate": 4.6354730177207e-05,
|
| 1492 |
-
"loss": 1.748,
|
| 1493 |
-
"step": 6572
|
| 1494 |
-
},
|
| 1495 |
-
{
|
| 1496 |
-
"epoch": 0.1654223870127267,
|
| 1497 |
-
"grad_norm": 1.0107293128967285,
|
| 1498 |
-
"learning_rate": 4.6310942074619787e-05,
|
| 1499 |
-
"loss": 1.7743,
|
| 1500 |
-
"step": 6603
|
| 1501 |
-
},
|
| 1502 |
-
{
|
| 1503 |
-
"epoch": 0.1661990179376691,
|
| 1504 |
-
"grad_norm": 0.9731600284576416,
|
| 1505 |
-
"learning_rate": 4.626691348094777e-05,
|
| 1506 |
-
"loss": 1.7515,
|
| 1507 |
-
"step": 6634
|
| 1508 |
-
},
|
| 1509 |
-
{
|
| 1510 |
-
"epoch": 0.1669756488626115,
|
| 1511 |
-
"grad_norm": 0.9843081831932068,
|
| 1512 |
-
"learning_rate": 4.622264489304762e-05,
|
| 1513 |
-
"loss": 1.7498,
|
| 1514 |
-
"step": 6665
|
| 1515 |
-
},
|
| 1516 |
-
{
|
| 1517 |
-
"epoch": 0.16775227978755386,
|
| 1518 |
-
"grad_norm": 0.9850636720657349,
|
| 1519 |
-
"learning_rate": 4.617813681048434e-05,
|
| 1520 |
-
"loss": 1.7563,
|
| 1521 |
-
"step": 6696
|
| 1522 |
-
},
|
| 1523 |
-
{
|
| 1524 |
-
"epoch": 0.16852891071249623,
|
| 1525 |
-
"grad_norm": 0.964599609375,
|
| 1526 |
-
"learning_rate": 4.61333897355256e-05,
|
| 1527 |
-
"loss": 1.7699,
|
| 1528 |
-
"step": 6727
|
| 1529 |
-
},
|
| 1530 |
-
{
|
| 1531 |
-
"epoch": 0.16930554163743863,
|
| 1532 |
-
"grad_norm": 0.9415149688720703,
|
| 1533 |
-
"learning_rate": 4.608840417313604e-05,
|
| 1534 |
-
"loss": 1.745,
|
| 1535 |
-
"step": 6758
|
| 1536 |
-
},
|
| 1537 |
-
{
|
| 1538 |
-
"epoch": 0.170082172562381,
|
| 1539 |
-
"grad_norm": 0.9608363509178162,
|
| 1540 |
-
"learning_rate": 4.6043180630971646e-05,
|
| 1541 |
-
"loss": 1.7519,
|
| 1542 |
-
"step": 6789
|
| 1543 |
-
},
|
| 1544 |
-
{
|
| 1545 |
-
"epoch": 0.17085880348732338,
|
| 1546 |
-
"grad_norm": 0.9133123159408569,
|
| 1547 |
-
"learning_rate": 4.599771961937391e-05,
|
| 1548 |
-
"loss": 1.7432,
|
| 1549 |
-
"step": 6820
|
| 1550 |
-
},
|
| 1551 |
-
{
|
| 1552 |
-
"epoch": 0.17163543441226575,
|
| 1553 |
-
"grad_norm": 0.943702220916748,
|
| 1554 |
-
"learning_rate": 4.5952021651364204e-05,
|
| 1555 |
-
"loss": 1.7231,
|
| 1556 |
-
"step": 6851
|
| 1557 |
-
},
|
| 1558 |
-
{
|
| 1559 |
-
"epoch": 0.17241206533720813,
|
| 1560 |
-
"grad_norm": 0.9676947593688965,
|
| 1561 |
-
"learning_rate": 4.590608724263786e-05,
|
| 1562 |
-
"loss": 1.7563,
|
| 1563 |
-
"step": 6882
|
| 1564 |
-
},
|
| 1565 |
-
{
|
| 1566 |
-
"epoch": 0.17318869626215053,
|
| 1567 |
-
"grad_norm": 0.964959442615509,
|
| 1568 |
-
"learning_rate": 4.585991691155845e-05,
|
| 1569 |
-
"loss": 1.7514,
|
| 1570 |
-
"step": 6913
|
| 1571 |
-
},
|
| 1572 |
-
{
|
| 1573 |
-
"epoch": 0.1739653271870929,
|
| 1574 |
-
"grad_norm": 1.0078297853469849,
|
| 1575 |
-
"learning_rate": 4.581351117915188e-05,
|
| 1576 |
-
"loss": 1.7538,
|
| 1577 |
-
"step": 6944
|
| 1578 |
-
},
|
| 1579 |
-
{
|
| 1580 |
-
"epoch": 0.17474195811203527,
|
| 1581 |
-
"grad_norm": 0.9631285071372986,
|
| 1582 |
-
"learning_rate": 4.5766870569100534e-05,
|
| 1583 |
-
"loss": 1.7363,
|
| 1584 |
-
"step": 6975
|
| 1585 |
-
},
|
| 1586 |
-
{
|
| 1587 |
-
"epoch": 0.17551858903697765,
|
| 1588 |
-
"grad_norm": 0.9542151093482971,
|
| 1589 |
-
"learning_rate": 4.571999560773736e-05,
|
| 1590 |
-
"loss": 1.753,
|
| 1591 |
-
"step": 7006
|
| 1592 |
-
},
|
| 1593 |
-
{
|
| 1594 |
-
"epoch": 0.17629521996192002,
|
| 1595 |
-
"grad_norm": 0.9770635366439819,
|
| 1596 |
-
"learning_rate": 4.5672886824039915e-05,
|
| 1597 |
-
"loss": 1.7435,
|
| 1598 |
-
"step": 7037
|
| 1599 |
-
},
|
| 1600 |
-
{
|
| 1601 |
-
"epoch": 0.17707185088686242,
|
| 1602 |
-
"grad_norm": 0.979009211063385,
|
| 1603 |
-
"learning_rate": 4.5625544749624435e-05,
|
| 1604 |
-
"loss": 1.7591,
|
| 1605 |
-
"step": 7068
|
| 1606 |
-
},
|
| 1607 |
-
{
|
| 1608 |
-
"epoch": 0.1778484818118048,
|
| 1609 |
-
"grad_norm": 0.9663967490196228,
|
| 1610 |
-
"learning_rate": 4.5577969918739794e-05,
|
| 1611 |
-
"loss": 1.7129,
|
| 1612 |
-
"step": 7099
|
| 1613 |
-
},
|
| 1614 |
-
{
|
| 1615 |
-
"epoch": 0.17862511273674717,
|
| 1616 |
-
"grad_norm": 1.0181857347488403,
|
| 1617 |
-
"learning_rate": 4.5530162868261486e-05,
|
| 1618 |
-
"loss": 1.7396,
|
| 1619 |
-
"step": 7130
|
| 1620 |
-
},
|
| 1621 |
-
{
|
| 1622 |
-
"epoch": 0.17940174366168954,
|
| 1623 |
-
"grad_norm": 1.0090553760528564,
|
| 1624 |
-
"learning_rate": 4.548212413768558e-05,
|
| 1625 |
-
"loss": 1.7488,
|
| 1626 |
-
"step": 7161
|
| 1627 |
-
},
|
| 1628 |
-
{
|
| 1629 |
-
"epoch": 0.18017837458663194,
|
| 1630 |
-
"grad_norm": 1.0095964670181274,
|
| 1631 |
-
"learning_rate": 4.543385426912261e-05,
|
| 1632 |
-
"loss": 1.7342,
|
| 1633 |
-
"step": 7192
|
| 1634 |
-
},
|
| 1635 |
-
{
|
| 1636 |
-
"epoch": 0.1809550055115743,
|
| 1637 |
-
"grad_norm": 0.994108259677887,
|
| 1638 |
-
"learning_rate": 4.53853538072915e-05,
|
| 1639 |
-
"loss": 1.7445,
|
| 1640 |
-
"step": 7223
|
| 1641 |
-
},
|
| 1642 |
-
{
|
| 1643 |
-
"epoch": 0.18173163643651669,
|
| 1644 |
-
"grad_norm": 0.9566254019737244,
|
| 1645 |
-
"learning_rate": 4.533662329951336e-05,
|
| 1646 |
-
"loss": 1.7272,
|
| 1647 |
-
"step": 7254
|
| 1648 |
-
},
|
| 1649 |
-
{
|
| 1650 |
-
"epoch": 0.18250826736145906,
|
| 1651 |
-
"grad_norm": 0.9655300974845886,
|
| 1652 |
-
"learning_rate": 4.528766329570536e-05,
|
| 1653 |
-
"loss": 1.7112,
|
| 1654 |
-
"step": 7285
|
| 1655 |
-
},
|
| 1656 |
-
{
|
| 1657 |
-
"epoch": 0.18328489828640143,
|
| 1658 |
-
"grad_norm": 0.9693655371665955,
|
| 1659 |
-
"learning_rate": 4.523847434837447e-05,
|
| 1660 |
-
"loss": 1.74,
|
| 1661 |
-
"step": 7316
|
| 1662 |
-
},
|
| 1663 |
-
{
|
| 1664 |
-
"epoch": 0.18406152921134383,
|
| 1665 |
-
"grad_norm": 0.9668208956718445,
|
| 1666 |
-
"learning_rate": 4.518905701261128e-05,
|
| 1667 |
-
"loss": 1.7239,
|
| 1668 |
-
"step": 7347
|
| 1669 |
-
},
|
| 1670 |
-
{
|
| 1671 |
-
"epoch": 0.1848381601362862,
|
| 1672 |
-
"grad_norm": 1.0193735361099243,
|
| 1673 |
-
"learning_rate": 4.5139411846083715e-05,
|
| 1674 |
-
"loss": 1.7273,
|
| 1675 |
-
"step": 7378
|
| 1676 |
-
},
|
| 1677 |
-
{
|
| 1678 |
-
"epoch": 0.18561479106122858,
|
| 1679 |
-
"grad_norm": 0.9525153636932373,
|
| 1680 |
-
"learning_rate": 4.508953940903073e-05,
|
| 1681 |
-
"loss": 1.7356,
|
| 1682 |
-
"step": 7409
|
| 1683 |
-
},
|
| 1684 |
-
{
|
| 1685 |
-
"epoch": 0.18639142198617095,
|
| 1686 |
-
"grad_norm": 0.9590099453926086,
|
| 1687 |
-
"learning_rate": 4.5039440264255994e-05,
|
| 1688 |
-
"loss": 1.7296,
|
| 1689 |
-
"step": 7440
|
| 1690 |
-
},
|
| 1691 |
-
{
|
| 1692 |
-
"epoch": 0.18716805291111333,
|
| 1693 |
-
"grad_norm": 0.9519559741020203,
|
| 1694 |
-
"learning_rate": 4.498911497712155e-05,
|
| 1695 |
-
"loss": 1.7183,
|
| 1696 |
-
"step": 7471
|
| 1697 |
-
},
|
| 1698 |
-
{
|
| 1699 |
-
"epoch": 0.18794468383605573,
|
| 1700 |
-
"grad_norm": 0.9692674279212952,
|
| 1701 |
-
"learning_rate": 4.493856411554142e-05,
|
| 1702 |
-
"loss": 1.7329,
|
| 1703 |
-
"step": 7502
|
| 1704 |
-
},
|
| 1705 |
-
{
|
| 1706 |
-
"epoch": 0.1887213147609981,
|
| 1707 |
-
"grad_norm": 0.9676815271377563,
|
| 1708 |
-
"learning_rate": 4.4887788249975206e-05,
|
| 1709 |
-
"loss": 1.7194,
|
| 1710 |
-
"step": 7533
|
| 1711 |
-
},
|
| 1712 |
-
{
|
| 1713 |
-
"epoch": 0.18949794568594047,
|
| 1714 |
-
"grad_norm": 0.9612167477607727,
|
| 1715 |
-
"learning_rate": 4.4836787953421656e-05,
|
| 1716 |
-
"loss": 1.7297,
|
| 1717 |
-
"step": 7564
|
| 1718 |
-
},
|
| 1719 |
-
{
|
| 1720 |
-
"epoch": 0.19027457661088285,
|
| 1721 |
-
"grad_norm": 0.9661709666252136,
|
| 1722 |
-
"learning_rate": 4.478556380141218e-05,
|
| 1723 |
-
"loss": 1.728,
|
| 1724 |
-
"step": 7595
|
| 1725 |
-
},
|
| 1726 |
-
{
|
| 1727 |
-
"epoch": 0.19105120753582525,
|
| 1728 |
-
"grad_norm": 0.95663982629776,
|
| 1729 |
-
"learning_rate": 4.4734116372004375e-05,
|
| 1730 |
-
"loss": 1.7387,
|
| 1731 |
-
"step": 7626
|
| 1732 |
-
},
|
| 1733 |
-
{
|
| 1734 |
-
"epoch": 0.19182783846076762,
|
| 1735 |
-
"grad_norm": 0.9469471573829651,
|
| 1736 |
-
"learning_rate": 4.4682446245775477e-05,
|
| 1737 |
-
"loss": 1.7034,
|
| 1738 |
-
"step": 7657
|
| 1739 |
-
},
|
| 1740 |
-
{
|
| 1741 |
-
"epoch": 0.19260446938571,
|
| 1742 |
-
"grad_norm": 1.03744637966156,
|
| 1743 |
-
"learning_rate": 4.463055400581586e-05,
|
| 1744 |
-
"loss": 1.7394,
|
| 1745 |
-
"step": 7688
|
| 1746 |
-
},
|
| 1747 |
-
{
|
| 1748 |
-
"epoch": 0.19338110031065237,
|
| 1749 |
-
"grad_norm": 0.932919979095459,
|
| 1750 |
-
"learning_rate": 4.4578440237722374e-05,
|
| 1751 |
-
"loss": 1.7113,
|
| 1752 |
-
"step": 7719
|
| 1753 |
-
},
|
| 1754 |
-
{
|
| 1755 |
-
"epoch": 0.19415773123559474,
|
| 1756 |
-
"grad_norm": 0.9527629017829895,
|
| 1757 |
-
"learning_rate": 4.452610552959183e-05,
|
| 1758 |
-
"loss": 1.7228,
|
| 1759 |
-
"step": 7750
|
| 1760 |
-
},
|
| 1761 |
-
{
|
| 1762 |
-
"epoch": 0.19493436216053714,
|
| 1763 |
-
"grad_norm": 0.9649306535720825,
|
| 1764 |
-
"learning_rate": 4.447355047201428e-05,
|
| 1765 |
-
"loss": 1.7434,
|
| 1766 |
-
"step": 7781
|
| 1767 |
-
},
|
| 1768 |
-
{
|
| 1769 |
-
"epoch": 0.1957109930854795,
|
| 1770 |
-
"grad_norm": 0.9027903079986572,
|
| 1771 |
-
"learning_rate": 4.4420775658066414e-05,
|
| 1772 |
-
"loss": 1.7022,
|
| 1773 |
-
"step": 7812
|
| 1774 |
-
},
|
| 1775 |
-
{
|
| 1776 |
-
"epoch": 0.19648762401042189,
|
| 1777 |
-
"grad_norm": 0.9486429691314697,
|
| 1778 |
-
"learning_rate": 4.436778168330484e-05,
|
| 1779 |
-
"loss": 1.7277,
|
| 1780 |
-
"step": 7843
|
| 1781 |
-
},
|
| 1782 |
-
{
|
| 1783 |
-
"epoch": 0.19726425493536426,
|
| 1784 |
-
"grad_norm": 0.9951580762863159,
|
| 1785 |
-
"learning_rate": 4.4314569145759353e-05,
|
| 1786 |
-
"loss": 1.7354,
|
| 1787 |
-
"step": 7874
|
| 1788 |
-
},
|
| 1789 |
-
{
|
| 1790 |
-
"epoch": 0.19804088586030663,
|
| 1791 |
-
"grad_norm": 0.984990656375885,
|
| 1792 |
-
"learning_rate": 4.42611386459262e-05,
|
| 1793 |
-
"loss": 1.7247,
|
| 1794 |
-
"step": 7905
|
| 1795 |
-
},
|
| 1796 |
-
{
|
| 1797 |
-
"epoch": 0.19881751678524903,
|
| 1798 |
-
"grad_norm": 1.0146019458770752,
|
| 1799 |
-
"learning_rate": 4.420749078676133e-05,
|
| 1800 |
-
"loss": 1.7048,
|
| 1801 |
-
"step": 7936
|
| 1802 |
-
},
|
| 1803 |
-
{
|
| 1804 |
-
"epoch": 0.1995941477101914,
|
| 1805 |
-
"grad_norm": 0.9386274814605713,
|
| 1806 |
-
"learning_rate": 4.4153626173673516e-05,
|
| 1807 |
-
"loss": 1.7035,
|
| 1808 |
-
"step": 7967
|
| 1809 |
-
},
|
| 1810 |
-
{
|
| 1811 |
-
"epoch": 0.20037077863513378,
|
| 1812 |
-
"grad_norm": 0.9656661152839661,
|
| 1813 |
-
"learning_rate": 4.409954541451762e-05,
|
| 1814 |
-
"loss": 1.7138,
|
| 1815 |
-
"step": 7998
|
| 1816 |
-
},
|
| 1817 |
-
{
|
| 1818 |
-
"epoch": 0.20114740956007615,
|
| 1819 |
-
"grad_norm": 0.9721409678459167,
|
| 1820 |
-
"learning_rate": 4.404524911958764e-05,
|
| 1821 |
-
"loss": 1.7174,
|
| 1822 |
-
"step": 8029
|
| 1823 |
-
},
|
| 1824 |
-
{
|
| 1825 |
-
"epoch": 0.20192404048501855,
|
| 1826 |
-
"grad_norm": 0.9685981869697571,
|
| 1827 |
-
"learning_rate": 4.399073790160989e-05,
|
| 1828 |
-
"loss": 1.7162,
|
| 1829 |
-
"step": 8060
|
| 1830 |
-
},
|
| 1831 |
-
{
|
| 1832 |
-
"epoch": 0.20270067140996093,
|
| 1833 |
-
"grad_norm": 0.9472204446792603,
|
| 1834 |
-
"learning_rate": 4.393601237573607e-05,
|
| 1835 |
-
"loss": 1.7068,
|
| 1836 |
-
"step": 8091
|
| 1837 |
-
},
|
| 1838 |
-
{
|
| 1839 |
-
"epoch": 0.2034773023349033,
|
| 1840 |
-
"grad_norm": 0.9472411870956421,
|
| 1841 |
-
"learning_rate": 4.388107315953628e-05,
|
| 1842 |
-
"loss": 1.7244,
|
| 1843 |
-
"step": 8122
|
| 1844 |
-
},
|
| 1845 |
-
{
|
| 1846 |
-
"epoch": 0.20425393325984567,
|
| 1847 |
-
"grad_norm": 0.9380378723144531,
|
| 1848 |
-
"learning_rate": 4.382592087299212e-05,
|
| 1849 |
-
"loss": 1.7169,
|
| 1850 |
-
"step": 8153
|
| 1851 |
-
},
|
| 1852 |
-
{
|
| 1853 |
-
"epoch": 0.20503056418478804,
|
| 1854 |
-
"grad_norm": 0.9613087177276611,
|
| 1855 |
-
"learning_rate": 4.377055613848964e-05,
|
| 1856 |
-
"loss": 1.7108,
|
| 1857 |
-
"step": 8184
|
| 1858 |
-
},
|
| 1859 |
-
{
|
| 1860 |
-
"epoch": 0.20580719510973045,
|
| 1861 |
-
"grad_norm": 0.9507735967636108,
|
| 1862 |
-
"learning_rate": 4.3714979580812355e-05,
|
| 1863 |
-
"loss": 1.7147,
|
| 1864 |
-
"step": 8215
|
| 1865 |
-
},
|
| 1866 |
-
{
|
| 1867 |
-
"epoch": 0.20658382603467282,
|
| 1868 |
-
"grad_norm": 0.9669816493988037,
|
| 1869 |
-
"learning_rate": 4.365919182713416e-05,
|
| 1870 |
-
"loss": 1.7058,
|
| 1871 |
-
"step": 8246
|
| 1872 |
-
},
|
| 1873 |
-
{
|
| 1874 |
-
"epoch": 0.2073604569596152,
|
| 1875 |
-
"grad_norm": 0.8880124688148499,
|
| 1876 |
-
"learning_rate": 4.360319350701226e-05,
|
| 1877 |
-
"loss": 1.7049,
|
| 1878 |
-
"step": 8277
|
| 1879 |
-
},
|
| 1880 |
-
{
|
| 1881 |
-
"epoch": 0.20813708788455756,
|
| 1882 |
-
"grad_norm": 4.802671909332275,
|
| 1883 |
-
"learning_rate": 4.3546985252380115e-05,
|
| 1884 |
-
"loss": 1.7349,
|
| 1885 |
-
"step": 8308
|
| 1886 |
-
},
|
| 1887 |
-
{
|
| 1888 |
-
"epoch": 0.20891371880949994,
|
| 1889 |
-
"grad_norm": 0.9394221901893616,
|
| 1890 |
-
"learning_rate": 4.349056769754021e-05,
|
| 1891 |
-
"loss": 1.6932,
|
| 1892 |
-
"step": 8339
|
| 1893 |
-
},
|
| 1894 |
-
{
|
| 1895 |
-
"epoch": 0.20969034973444234,
|
| 1896 |
-
"grad_norm": 0.9521833062171936,
|
| 1897 |
-
"learning_rate": 4.3433941479156994e-05,
|
| 1898 |
-
"loss": 1.695,
|
| 1899 |
-
"step": 8370
|
| 1900 |
-
},
|
| 1901 |
-
{
|
| 1902 |
-
"epoch": 0.2104669806593847,
|
| 1903 |
-
"grad_norm": 0.9627339839935303,
|
| 1904 |
-
"learning_rate": 4.3377107236249647e-05,
|
| 1905 |
-
"loss": 1.7329,
|
| 1906 |
-
"step": 8401
|
| 1907 |
-
},
|
| 1908 |
-
{
|
| 1909 |
-
"epoch": 0.21124361158432708,
|
| 1910 |
-
"grad_norm": 0.9096025228500366,
|
| 1911 |
-
"learning_rate": 4.332006561018488e-05,
|
| 1912 |
-
"loss": 1.6885,
|
| 1913 |
-
"step": 8432
|
| 1914 |
-
},
|
| 1915 |
-
{
|
| 1916 |
-
"epoch": 0.21202024250926946,
|
| 1917 |
-
"grad_norm": 0.9301928877830505,
|
| 1918 |
-
"learning_rate": 4.3262817244669683e-05,
|
| 1919 |
-
"loss": 1.7112,
|
| 1920 |
-
"step": 8463
|
| 1921 |
-
},
|
| 1922 |
-
{
|
| 1923 |
-
"epoch": 0.21279687343421186,
|
| 1924 |
-
"grad_norm": 1.0362213850021362,
|
| 1925 |
-
"learning_rate": 4.3205362785744083e-05,
|
| 1926 |
-
"loss": 1.7061,
|
| 1927 |
-
"step": 8494
|
| 1928 |
-
},
|
| 1929 |
-
{
|
| 1930 |
-
"epoch": 0.21357350435915423,
|
| 1931 |
-
"grad_norm": 1.986802339553833,
|
| 1932 |
-
"learning_rate": 4.314770288177384e-05,
|
| 1933 |
-
"loss": 1.7095,
|
| 1934 |
-
"step": 8525
|
| 1935 |
-
},
|
| 1936 |
-
{
|
| 1937 |
-
"epoch": 0.2143501352840966,
|
| 1938 |
-
"grad_norm": 0.9070325493812561,
|
| 1939 |
-
"learning_rate": 4.308983818344313e-05,
|
| 1940 |
-
"loss": 1.7087,
|
| 1941 |
-
"step": 8556
|
| 1942 |
-
},
|
| 1943 |
-
{
|
| 1944 |
-
"epoch": 0.21512676620903898,
|
| 1945 |
-
"grad_norm": 0.985433042049408,
|
| 1946 |
-
"learning_rate": 4.3031769343747206e-05,
|
| 1947 |
-
"loss": 1.7176,
|
| 1948 |
-
"step": 8587
|
| 1949 |
-
},
|
| 1950 |
-
{
|
| 1951 |
-
"epoch": 0.21590339713398135,
|
| 1952 |
-
"grad_norm": 0.9339021444320679,
|
| 1953 |
-
"learning_rate": 4.297349701798505e-05,
|
| 1954 |
-
"loss": 1.6823,
|
| 1955 |
-
"step": 8618
|
| 1956 |
-
},
|
| 1957 |
-
{
|
| 1958 |
-
"epoch": 0.21668002805892375,
|
| 1959 |
-
"grad_norm": 0.9413474798202515,
|
| 1960 |
-
"learning_rate": 4.2915021863751916e-05,
|
| 1961 |
-
"loss": 1.7205,
|
| 1962 |
-
"step": 8649
|
| 1963 |
-
},
|
| 1964 |
-
{
|
| 1965 |
-
"epoch": 0.21745665898386612,
|
| 1966 |
-
"grad_norm": 1.023187279701233,
|
| 1967 |
-
"learning_rate": 4.285634454093198e-05,
|
| 1968 |
-
"loss": 1.6943,
|
| 1969 |
-
"step": 8680
|
| 1970 |
-
},
|
| 1971 |
-
{
|
| 1972 |
-
"epoch": 0.2182332899088085,
|
| 1973 |
-
"grad_norm": 0.9431496262550354,
|
| 1974 |
-
"learning_rate": 4.279746571169086e-05,
|
| 1975 |
-
"loss": 1.7012,
|
| 1976 |
-
"step": 8711
|
| 1977 |
-
},
|
| 1978 |
-
{
|
| 1979 |
-
"epoch": 0.21900992083375087,
|
| 1980 |
-
"grad_norm": 0.9386807680130005,
|
| 1981 |
-
"learning_rate": 4.2738386040468136e-05,
|
| 1982 |
-
"loss": 1.7069,
|
| 1983 |
-
"step": 8742
|
| 1984 |
-
},
|
| 1985 |
-
{
|
| 1986 |
-
"epoch": 0.21978655175869324,
|
| 1987 |
-
"grad_norm": 0.9307882785797119,
|
| 1988 |
-
"learning_rate": 4.2679106193969866e-05,
|
| 1989 |
-
"loss": 1.6914,
|
| 1990 |
-
"step": 8773
|
| 1991 |
-
},
|
| 1992 |
-
{
|
| 1993 |
-
"epoch": 0.22056318268363564,
|
| 1994 |
-
"grad_norm": 1.0440980195999146,
|
| 1995 |
-
"learning_rate": 4.261962684116106e-05,
|
| 1996 |
-
"loss": 1.6892,
|
| 1997 |
-
"step": 8804
|
| 1998 |
-
},
|
| 1999 |
-
{
|
| 2000 |
-
"epoch": 0.22133981360857802,
|
| 2001 |
-
"grad_norm": 0.9271411895751953,
|
| 2002 |
-
"learning_rate": 4.2559948653258145e-05,
|
| 2003 |
-
"loss": 1.7117,
|
| 2004 |
-
"step": 8835
|
| 2005 |
-
},
|
| 2006 |
-
{
|
| 2007 |
-
"epoch": 0.2221164445335204,
|
| 2008 |
-
"grad_norm": 0.9182149767875671,
|
| 2009 |
-
"learning_rate": 4.250007230372134e-05,
|
| 2010 |
-
"loss": 1.7092,
|
| 2011 |
-
"step": 8866
|
| 2012 |
-
},
|
| 2013 |
-
{
|
| 2014 |
-
"epoch": 0.22289307545846276,
|
| 2015 |
-
"grad_norm": 0.9707378149032593,
|
| 2016 |
-
"learning_rate": 4.2439998468247126e-05,
|
| 2017 |
-
"loss": 1.7055,
|
| 2018 |
-
"step": 8897
|
| 2019 |
-
},
|
| 2020 |
-
{
|
| 2021 |
-
"epoch": 0.22366970638340516,
|
| 2022 |
-
"grad_norm": 0.9413692951202393,
|
| 2023 |
-
"learning_rate": 4.2379727824760566e-05,
|
| 2024 |
-
"loss": 1.6968,
|
| 2025 |
-
"step": 8928
|
| 2026 |
-
},
|
| 2027 |
-
{
|
| 2028 |
-
"epoch": 0.22444633730834754,
|
| 2029 |
-
"grad_norm": 1.1943906545639038,
|
| 2030 |
-
"learning_rate": 4.231926105340768e-05,
|
| 2031 |
-
"loss": 1.7174,
|
| 2032 |
-
"step": 8959
|
| 2033 |
-
},
|
| 2034 |
-
{
|
| 2035 |
-
"epoch": 0.2252229682332899,
|
| 2036 |
-
"grad_norm": 0.9508203268051147,
|
| 2037 |
-
"learning_rate": 4.225859883654776e-05,
|
| 2038 |
-
"loss": 1.6941,
|
| 2039 |
-
"step": 8990
|
| 2040 |
-
},
|
| 2041 |
-
{
|
| 2042 |
-
"epoch": 0.22599959915823228,
|
| 2043 |
-
"grad_norm": 0.9774237275123596,
|
| 2044 |
-
"learning_rate": 4.219774185874569e-05,
|
| 2045 |
-
"loss": 1.6996,
|
| 2046 |
-
"step": 9021
|
| 2047 |
-
},
|
| 2048 |
-
{
|
| 2049 |
-
"epoch": 0.22677623008317466,
|
| 2050 |
-
"grad_norm": 0.9906953573226929,
|
| 2051 |
-
"learning_rate": 4.213669080676418e-05,
|
| 2052 |
-
"loss": 1.7186,
|
| 2053 |
-
"step": 9052
|
| 2054 |
-
},
|
| 2055 |
-
{
|
| 2056 |
-
"epoch": 0.22755286100811706,
|
| 2057 |
-
"grad_norm": 0.966076135635376,
|
| 2058 |
-
"learning_rate": 4.2075446369556056e-05,
|
| 2059 |
-
"loss": 1.6828,
|
| 2060 |
-
"step": 9083
|
| 2061 |
-
},
|
| 2062 |
-
{
|
| 2063 |
-
"epoch": 0.22832949193305943,
|
| 2064 |
-
"grad_norm": 0.9266401529312134,
|
| 2065 |
-
"learning_rate": 4.201400923825648e-05,
|
| 2066 |
-
"loss": 1.6969,
|
| 2067 |
-
"step": 9114
|
| 2068 |
-
},
|
| 2069 |
-
{
|
| 2070 |
-
"epoch": 0.2291061228580018,
|
| 2071 |
-
"grad_norm": 0.8797683119773865,
|
| 2072 |
-
"learning_rate": 4.195238010617511e-05,
|
| 2073 |
-
"loss": 1.6835,
|
| 2074 |
-
"step": 9145
|
| 2075 |
-
},
|
| 2076 |
-
{
|
| 2077 |
-
"epoch": 0.22988275378294418,
|
| 2078 |
-
"grad_norm": 0.92194664478302,
|
| 2079 |
-
"learning_rate": 4.1890559668788344e-05,
|
| 2080 |
-
"loss": 1.7028,
|
| 2081 |
-
"step": 9176
|
| 2082 |
-
},
|
| 2083 |
-
{
|
| 2084 |
-
"epoch": 0.23065938470788655,
|
| 2085 |
-
"grad_norm": 0.9278755187988281,
|
| 2086 |
-
"learning_rate": 4.1828548623731405e-05,
|
| 2087 |
-
"loss": 1.6853,
|
| 2088 |
-
"step": 9207
|
| 2089 |
-
},
|
| 2090 |
-
{
|
| 2091 |
-
"epoch": 0.23143601563282895,
|
| 2092 |
-
"grad_norm": 0.9345482587814331,
|
| 2093 |
-
"learning_rate": 4.1766347670790506e-05,
|
| 2094 |
-
"loss": 1.6879,
|
| 2095 |
-
"step": 9238
|
| 2096 |
-
},
|
| 2097 |
-
{
|
| 2098 |
-
"epoch": 0.23221264655777132,
|
| 2099 |
-
"grad_norm": 0.9217596054077148,
|
| 2100 |
-
"learning_rate": 4.170395751189495e-05,
|
| 2101 |
-
"loss": 1.679,
|
| 2102 |
-
"step": 9269
|
| 2103 |
-
},
|
| 2104 |
-
{
|
| 2105 |
-
"epoch": 0.2329892774827137,
|
| 2106 |
-
"grad_norm": 0.9330849647521973,
|
| 2107 |
-
"learning_rate": 4.164137885110921e-05,
|
| 2108 |
-
"loss": 1.6891,
|
| 2109 |
-
"step": 9300
|
| 2110 |
-
},
|
| 2111 |
-
{
|
| 2112 |
-
"epoch": 0.23376590840765607,
|
| 2113 |
-
"grad_norm": 0.923973023891449,
|
| 2114 |
-
"learning_rate": 4.157861239462495e-05,
|
| 2115 |
-
"loss": 1.6929,
|
| 2116 |
-
"step": 9331
|
| 2117 |
-
},
|
| 2118 |
-
{
|
| 2119 |
-
"epoch": 0.23454253933259844,
|
| 2120 |
-
"grad_norm": 0.9245807528495789,
|
| 2121 |
-
"learning_rate": 4.1515658850753114e-05,
|
| 2122 |
-
"loss": 1.7162,
|
| 2123 |
-
"step": 9362
|
| 2124 |
-
},
|
| 2125 |
-
{
|
| 2126 |
-
"epoch": 0.23531917025754084,
|
| 2127 |
-
"grad_norm": 0.9212767481803894,
|
| 2128 |
-
"learning_rate": 4.145251892991588e-05,
|
| 2129 |
-
"loss": 1.7169,
|
| 2130 |
-
"step": 9393
|
| 2131 |
-
},
|
| 2132 |
-
{
|
| 2133 |
-
"epoch": 0.23609580118248322,
|
| 2134 |
-
"grad_norm": 0.9439975023269653,
|
| 2135 |
-
"learning_rate": 4.138919334463868e-05,
|
| 2136 |
-
"loss": 1.6869,
|
| 2137 |
-
"step": 9424
|
| 2138 |
-
},
|
| 2139 |
-
{
|
| 2140 |
-
"epoch": 0.2368724321074256,
|
| 2141 |
-
"grad_norm": 0.9876207709312439,
|
| 2142 |
-
"learning_rate": 4.1325682809542124e-05,
|
| 2143 |
-
"loss": 1.6989,
|
| 2144 |
-
"step": 9455
|
| 2145 |
-
},
|
| 2146 |
-
{
|
| 2147 |
-
"epoch": 0.23764906303236796,
|
| 2148 |
-
"grad_norm": 0.8833792805671692,
|
| 2149 |
-
"learning_rate": 4.126198804133398e-05,
|
| 2150 |
-
"loss": 1.6917,
|
| 2151 |
-
"step": 9486
|
| 2152 |
-
},
|
| 2153 |
-
{
|
| 2154 |
-
"epoch": 0.23842569395731036,
|
| 2155 |
-
"grad_norm": 0.9133450388908386,
|
| 2156 |
-
"learning_rate": 4.1198109758801055e-05,
|
| 2157 |
-
"loss": 1.7038,
|
| 2158 |
-
"step": 9517
|
| 2159 |
-
},
|
| 2160 |
-
{
|
| 2161 |
-
"epoch": 0.23920232488225274,
|
| 2162 |
-
"grad_norm": 0.8729329705238342,
|
| 2163 |
-
"learning_rate": 4.113404868280107e-05,
|
| 2164 |
-
"loss": 1.672,
|
| 2165 |
-
"step": 9548
|
| 2166 |
-
},
|
| 2167 |
-
{
|
| 2168 |
-
"epoch": 0.2399789558071951,
|
| 2169 |
-
"grad_norm": 0.892375111579895,
|
| 2170 |
-
"learning_rate": 4.106980553625457e-05,
|
| 2171 |
-
"loss": 1.6829,
|
| 2172 |
-
"step": 9579
|
| 2173 |
-
},
|
| 2174 |
-
{
|
| 2175 |
-
"epoch": 0.24075558673213748,
|
| 2176 |
-
"grad_norm": 0.8939517140388489,
|
| 2177 |
-
"learning_rate": 4.100538104413674e-05,
|
| 2178 |
-
"loss": 1.6965,
|
| 2179 |
-
"step": 9610
|
| 2180 |
-
},
|
| 2181 |
-
{
|
| 2182 |
-
"epoch": 0.24153221765707986,
|
| 2183 |
-
"grad_norm": 0.8656035661697388,
|
| 2184 |
-
"learning_rate": 4.09407759334692e-05,
|
| 2185 |
-
"loss": 1.7063,
|
| 2186 |
-
"step": 9641
|
| 2187 |
-
},
|
| 2188 |
-
{
|
| 2189 |
-
"epoch": 0.24230884858202226,
|
| 2190 |
-
"grad_norm": 0.8904181122779846,
|
| 2191 |
-
"learning_rate": 4.087599093331186e-05,
|
| 2192 |
-
"loss": 1.6719,
|
| 2193 |
-
"step": 9672
|
| 2194 |
-
},
|
| 2195 |
-
{
|
| 2196 |
-
"epoch": 0.24308547950696463,
|
| 2197 |
-
"grad_norm": 0.9176281690597534,
|
| 2198 |
-
"learning_rate": 4.081102677475462e-05,
|
| 2199 |
-
"loss": 1.6648,
|
| 2200 |
-
"step": 9703
|
| 2201 |
-
},
|
| 2202 |
-
{
|
| 2203 |
-
"epoch": 0.243862110431907,
|
| 2204 |
-
"grad_norm": 0.9038643836975098,
|
| 2205 |
-
"learning_rate": 4.0745884190909194e-05,
|
| 2206 |
-
"loss": 1.6756,
|
| 2207 |
-
"step": 9734
|
| 2208 |
-
},
|
| 2209 |
-
{
|
| 2210 |
-
"epoch": 0.24463874135684938,
|
| 2211 |
-
"grad_norm": 0.9255871772766113,
|
| 2212 |
-
"learning_rate": 4.0680563916900796e-05,
|
| 2213 |
-
"loss": 1.6752,
|
| 2214 |
-
"step": 9765
|
| 2215 |
-
},
|
| 2216 |
-
{
|
| 2217 |
-
"epoch": 0.24541537228179175,
|
| 2218 |
-
"grad_norm": 0.9124768972396851,
|
| 2219 |
-
"learning_rate": 4.0615066689859815e-05,
|
| 2220 |
-
"loss": 1.6982,
|
| 2221 |
-
"step": 9796
|
| 2222 |
-
},
|
| 2223 |
-
{
|
| 2224 |
-
"epoch": 0.24619200320673415,
|
| 2225 |
-
"grad_norm": 0.9149096608161926,
|
| 2226 |
-
"learning_rate": 4.0549393248913584e-05,
|
| 2227 |
-
"loss": 1.6692,
|
| 2228 |
-
"step": 9827
|
| 2229 |
-
},
|
| 2230 |
-
{
|
| 2231 |
-
"epoch": 0.24696863413167652,
|
| 2232 |
-
"grad_norm": 0.9468510150909424,
|
| 2233 |
-
"learning_rate": 4.048354433517794e-05,
|
| 2234 |
-
"loss": 1.6775,
|
| 2235 |
-
"step": 9858
|
| 2236 |
-
},
|
| 2237 |
-
{
|
| 2238 |
-
"epoch": 0.2477452650566189,
|
| 2239 |
-
"grad_norm": 1.2210197448730469,
|
| 2240 |
-
"learning_rate": 4.0417520691748916e-05,
|
| 2241 |
-
"loss": 1.692,
|
| 2242 |
-
"step": 9889
|
| 2243 |
-
},
|
| 2244 |
-
{
|
| 2245 |
-
"epoch": 0.24852189598156127,
|
| 2246 |
-
"grad_norm": 0.9717695116996765,
|
| 2247 |
-
"learning_rate": 4.035132306369438e-05,
|
| 2248 |
-
"loss": 1.6583,
|
| 2249 |
-
"step": 9920
|
| 2250 |
-
},
|
| 2251 |
-
{
|
| 2252 |
-
"epoch": 0.24929852690650367,
|
| 2253 |
-
"grad_norm": 0.9524528980255127,
|
| 2254 |
-
"learning_rate": 4.028495219804555e-05,
|
| 2255 |
-
"loss": 1.6606,
|
| 2256 |
-
"step": 9951
|
| 2257 |
-
},
|
| 2258 |
-
{
|
| 2259 |
-
"epoch": 0.250075157831446,
|
| 2260 |
-
"grad_norm": 0.937414824962616,
|
| 2261 |
-
"learning_rate": 4.021840884378864e-05,
|
| 2262 |
-
"loss": 1.7063,
|
| 2263 |
-
"step": 9982
|
| 2264 |
-
},
|
| 2265 |
-
{
|
| 2266 |
-
"epoch": 0.2508517887563884,
|
| 2267 |
-
"grad_norm": 0.9392083883285522,
|
| 2268 |
-
"learning_rate": 4.015169375185633e-05,
|
| 2269 |
-
"loss": 1.6813,
|
| 2270 |
-
"step": 10013
|
| 2271 |
-
},
|
| 2272 |
-
{
|
| 2273 |
-
"epoch": 0.2516284196813308,
|
| 2274 |
-
"grad_norm": 0.9055363535881042,
|
| 2275 |
-
"learning_rate": 4.0084807675119396e-05,
|
| 2276 |
-
"loss": 1.6622,
|
| 2277 |
-
"step": 10044
|
| 2278 |
-
},
|
| 2279 |
-
{
|
| 2280 |
-
"epoch": 0.25240505060627316,
|
| 2281 |
-
"grad_norm": 0.8967134356498718,
|
| 2282 |
-
"learning_rate": 4.0017751368378106e-05,
|
| 2283 |
-
"loss": 1.7052,
|
| 2284 |
-
"step": 10075
|
| 2285 |
-
},
|
| 2286 |
-
{
|
| 2287 |
-
"epoch": 0.25318168153121556,
|
| 2288 |
-
"grad_norm": 0.9304991364479065,
|
| 2289 |
-
"learning_rate": 3.995052558835377e-05,
|
| 2290 |
-
"loss": 1.6779,
|
| 2291 |
-
"step": 10106
|
| 2292 |
-
},
|
| 2293 |
-
{
|
| 2294 |
-
"epoch": 0.2539583124561579,
|
| 2295 |
-
"grad_norm": 0.9946010708808899,
|
| 2296 |
-
"learning_rate": 3.988313109368017e-05,
|
| 2297 |
-
"loss": 1.6727,
|
| 2298 |
-
"step": 10137
|
| 2299 |
-
},
|
| 2300 |
-
{
|
| 2301 |
-
"epoch": 0.2547349433811003,
|
| 2302 |
-
"grad_norm": 0.936072051525116,
|
| 2303 |
-
"learning_rate": 3.981556864489504e-05,
|
| 2304 |
-
"loss": 1.6861,
|
| 2305 |
-
"step": 10168
|
| 2306 |
-
},
|
| 2307 |
-
{
|
| 2308 |
-
"epoch": 0.2555115743060427,
|
| 2309 |
-
"grad_norm": 0.9157513380050659,
|
| 2310 |
-
"learning_rate": 3.974783900443142e-05,
|
| 2311 |
-
"loss": 1.6871,
|
| 2312 |
-
"step": 10199
|
| 2313 |
-
},
|
| 2314 |
-
{
|
| 2315 |
-
"epoch": 0.25628820523098506,
|
| 2316 |
-
"grad_norm": 0.8980918526649475,
|
| 2317 |
-
"learning_rate": 3.9679942936609095e-05,
|
| 2318 |
-
"loss": 1.674,
|
| 2319 |
-
"step": 10230
|
| 2320 |
-
},
|
| 2321 |
-
{
|
| 2322 |
-
"epoch": 0.25706483615592746,
|
| 2323 |
-
"grad_norm": 0.9256001114845276,
|
| 2324 |
-
"learning_rate": 3.961188120762596e-05,
|
| 2325 |
-
"loss": 1.6858,
|
| 2326 |
-
"step": 10261
|
| 2327 |
-
},
|
| 2328 |
-
{
|
| 2329 |
-
"epoch": 0.2578414670808698,
|
| 2330 |
-
"grad_norm": 0.8827298879623413,
|
| 2331 |
-
"learning_rate": 3.954365458554938e-05,
|
| 2332 |
-
"loss": 1.6734,
|
| 2333 |
-
"step": 10292
|
| 2334 |
-
},
|
| 2335 |
-
{
|
| 2336 |
-
"epoch": 0.2586180980058122,
|
| 2337 |
-
"grad_norm": 0.9297879338264465,
|
| 2338 |
-
"learning_rate": 3.947526384030751e-05,
|
| 2339 |
-
"loss": 1.6648,
|
| 2340 |
-
"step": 10323
|
| 2341 |
-
},
|
| 2342 |
-
{
|
| 2343 |
-
"epoch": 0.2593947289307546,
|
| 2344 |
-
"grad_norm": 0.91744065284729,
|
| 2345 |
-
"learning_rate": 3.9406709743680624e-05,
|
| 2346 |
-
"loss": 1.6713,
|
| 2347 |
-
"step": 10354
|
| 2348 |
-
},
|
| 2349 |
-
{
|
| 2350 |
-
"epoch": 0.26017135985569695,
|
| 2351 |
-
"grad_norm": 0.949213445186615,
|
| 2352 |
-
"learning_rate": 3.9337993069292366e-05,
|
| 2353 |
-
"loss": 1.6633,
|
| 2354 |
-
"step": 10385
|
| 2355 |
-
},
|
| 2356 |
-
{
|
| 2357 |
-
"epoch": 0.26094799078063935,
|
| 2358 |
-
"grad_norm": 0.9231769442558289,
|
| 2359 |
-
"learning_rate": 3.926911459260109e-05,
|
| 2360 |
-
"loss": 1.6815,
|
| 2361 |
-
"step": 10416
|
| 2362 |
-
},
|
| 2363 |
-
{
|
| 2364 |
-
"epoch": 0.2617246217055817,
|
| 2365 |
-
"grad_norm": 0.9055944681167603,
|
| 2366 |
-
"learning_rate": 3.920007509089102e-05,
|
| 2367 |
-
"loss": 1.6621,
|
| 2368 |
-
"step": 10447
|
| 2369 |
-
},
|
| 2370 |
-
{
|
| 2371 |
-
"epoch": 0.2625012526305241,
|
| 2372 |
-
"grad_norm": 1.7065776586532593,
|
| 2373 |
-
"learning_rate": 3.913087534326357e-05,
|
| 2374 |
-
"loss": 1.6832,
|
| 2375 |
-
"step": 10478
|
| 2376 |
-
},
|
| 2377 |
-
{
|
| 2378 |
-
"epoch": 0.2632778835554665,
|
| 2379 |
-
"grad_norm": 0.9098711013793945,
|
| 2380 |
-
"learning_rate": 3.9061516130628475e-05,
|
| 2381 |
-
"loss": 1.7106,
|
| 2382 |
-
"step": 10509
|
| 2383 |
-
},
|
| 2384 |
-
{
|
| 2385 |
-
"epoch": 0.26405451448040884,
|
| 2386 |
-
"grad_norm": 0.9403277635574341,
|
| 2387 |
-
"learning_rate": 3.8991998235695025e-05,
|
| 2388 |
-
"loss": 1.708,
|
| 2389 |
-
"step": 10540
|
| 2390 |
-
},
|
| 2391 |
-
{
|
| 2392 |
-
"epoch": 0.26483114540535124,
|
| 2393 |
-
"grad_norm": 0.9076827168464661,
|
| 2394 |
-
"learning_rate": 3.8922322442963224e-05,
|
| 2395 |
-
"loss": 1.6571,
|
| 2396 |
-
"step": 10571
|
| 2397 |
-
},
|
| 2398 |
-
{
|
| 2399 |
-
"epoch": 0.26560777633029364,
|
| 2400 |
-
"grad_norm": 0.9140092730522156,
|
| 2401 |
-
"learning_rate": 3.885248953871491e-05,
|
| 2402 |
-
"loss": 1.6626,
|
| 2403 |
-
"step": 10602
|
| 2404 |
-
},
|
| 2405 |
-
{
|
| 2406 |
-
"epoch": 0.266384407255236,
|
| 2407 |
-
"grad_norm": 0.9277907013893127,
|
| 2408 |
-
"learning_rate": 3.8782500311004915e-05,
|
| 2409 |
-
"loss": 1.6625,
|
| 2410 |
-
"step": 10633
|
| 2411 |
-
},
|
| 2412 |
-
{
|
| 2413 |
-
"epoch": 0.2671610381801784,
|
| 2414 |
-
"grad_norm": 0.9199085831642151,
|
| 2415 |
-
"learning_rate": 3.871235554965218e-05,
|
| 2416 |
-
"loss": 1.663,
|
| 2417 |
-
"step": 10664
|
| 2418 |
-
},
|
| 2419 |
-
{
|
| 2420 |
-
"epoch": 0.26793766910512073,
|
| 2421 |
-
"grad_norm": 0.9358407855033875,
|
| 2422 |
-
"learning_rate": 3.864205604623078e-05,
|
| 2423 |
-
"loss": 1.6743,
|
| 2424 |
-
"step": 10695
|
| 2425 |
-
},
|
| 2426 |
-
{
|
| 2427 |
-
"epoch": 0.26871430003006314,
|
| 2428 |
-
"grad_norm": 0.8855702877044678,
|
| 2429 |
-
"learning_rate": 3.857160259406107e-05,
|
| 2430 |
-
"loss": 1.6619,
|
| 2431 |
-
"step": 10726
|
| 2432 |
-
},
|
| 2433 |
-
{
|
| 2434 |
-
"epoch": 0.26949093095500554,
|
| 2435 |
-
"grad_norm": 0.9157874584197998,
|
| 2436 |
-
"learning_rate": 3.8500995988200674e-05,
|
| 2437 |
-
"loss": 1.6772,
|
| 2438 |
-
"step": 10757
|
| 2439 |
-
},
|
| 2440 |
-
{
|
| 2441 |
-
"epoch": 0.2702675618799479,
|
| 2442 |
-
"grad_norm": 0.9023963809013367,
|
| 2443 |
-
"learning_rate": 3.843023702543556e-05,
|
| 2444 |
-
"loss": 1.6559,
|
| 2445 |
-
"step": 10788
|
| 2446 |
-
},
|
| 2447 |
-
{
|
| 2448 |
-
"epoch": 0.2710441928048903,
|
| 2449 |
-
"grad_norm": 0.9174203872680664,
|
| 2450 |
-
"learning_rate": 3.8359326504270984e-05,
|
| 2451 |
-
"loss": 1.6393,
|
| 2452 |
-
"step": 10819
|
| 2453 |
-
},
|
| 2454 |
-
{
|
| 2455 |
-
"epoch": 0.27182082372983263,
|
| 2456 |
-
"grad_norm": 0.9019688963890076,
|
| 2457 |
-
"learning_rate": 3.828826522492255e-05,
|
| 2458 |
-
"loss": 1.6763,
|
| 2459 |
-
"step": 10850
|
| 2460 |
-
},
|
| 2461 |
-
{
|
| 2462 |
-
"epoch": 0.27259745465477503,
|
| 2463 |
-
"grad_norm": 0.8955567479133606,
|
| 2464 |
-
"learning_rate": 3.821705398930713e-05,
|
| 2465 |
-
"loss": 1.6679,
|
| 2466 |
-
"step": 10881
|
| 2467 |
-
},
|
| 2468 |
-
{
|
| 2469 |
-
"epoch": 0.27337408557971743,
|
| 2470 |
-
"grad_norm": 0.9326659440994263,
|
| 2471 |
-
"learning_rate": 3.814569360103385e-05,
|
| 2472 |
-
"loss": 1.6765,
|
| 2473 |
-
"step": 10912
|
| 2474 |
-
},
|
| 2475 |
-
{
|
| 2476 |
-
"epoch": 0.2741507165046598,
|
| 2477 |
-
"grad_norm": 0.8885530233383179,
|
| 2478 |
-
"learning_rate": 3.807418486539499e-05,
|
| 2479 |
-
"loss": 1.674,
|
| 2480 |
-
"step": 10943
|
| 2481 |
-
},
|
| 2482 |
-
{
|
| 2483 |
-
"epoch": 0.2749273474296022,
|
| 2484 |
-
"grad_norm": 0.909267783164978,
|
| 2485 |
-
"learning_rate": 3.80025285893569e-05,
|
| 2486 |
-
"loss": 1.6602,
|
| 2487 |
-
"step": 10974
|
| 2488 |
-
},
|
| 2489 |
-
{
|
| 2490 |
-
"epoch": 0.2757039783545445,
|
| 2491 |
-
"grad_norm": 0.9005350470542908,
|
| 2492 |
-
"learning_rate": 3.793072558155093e-05,
|
| 2493 |
-
"loss": 1.6628,
|
| 2494 |
-
"step": 11005
|
| 2495 |
-
},
|
| 2496 |
-
{
|
| 2497 |
-
"epoch": 0.2764806092794869,
|
| 2498 |
-
"grad_norm": 0.919683575630188,
|
| 2499 |
-
"learning_rate": 3.785877665226426e-05,
|
| 2500 |
-
"loss": 1.6647,
|
| 2501 |
-
"step": 11036
|
| 2502 |
-
},
|
| 2503 |
-
{
|
| 2504 |
-
"epoch": 0.2772572402044293,
|
| 2505 |
-
"grad_norm": 0.8954905867576599,
|
| 2506 |
-
"learning_rate": 3.778668261343079e-05,
|
| 2507 |
-
"loss": 1.6763,
|
| 2508 |
-
"step": 11067
|
| 2509 |
-
},
|
| 2510 |
-
{
|
| 2511 |
-
"epoch": 0.27803387112937167,
|
| 2512 |
-
"grad_norm": 0.9120632410049438,
|
| 2513 |
-
"learning_rate": 3.771444427862192e-05,
|
| 2514 |
-
"loss": 1.6552,
|
| 2515 |
-
"step": 11098
|
| 2516 |
-
},
|
| 2517 |
-
{
|
| 2518 |
-
"epoch": 0.27881050205431407,
|
| 2519 |
-
"grad_norm": 0.9041403532028198,
|
| 2520 |
-
"learning_rate": 3.7642062463037465e-05,
|
| 2521 |
-
"loss": 1.6604,
|
| 2522 |
-
"step": 11129
|
| 2523 |
-
},
|
| 2524 |
-
{
|
| 2525 |
-
"epoch": 0.2795871329792564,
|
| 2526 |
-
"grad_norm": 0.9149596095085144,
|
| 2527 |
-
"learning_rate": 3.7569537983496373e-05,
|
| 2528 |
-
"loss": 1.6666,
|
| 2529 |
-
"step": 11160
|
| 2530 |
-
},
|
| 2531 |
-
{
|
| 2532 |
-
"epoch": 0.2803637639041988,
|
| 2533 |
-
"grad_norm": 0.9379541277885437,
|
| 2534 |
-
"learning_rate": 3.749687165842753e-05,
|
| 2535 |
-
"loss": 1.654,
|
| 2536 |
-
"step": 11191
|
| 2537 |
-
},
|
| 2538 |
-
{
|
| 2539 |
-
"epoch": 0.2811403948291412,
|
| 2540 |
-
"grad_norm": 0.8942285180091858,
|
| 2541 |
-
"learning_rate": 3.7424064307860536e-05,
|
| 2542 |
-
"loss": 1.6558,
|
| 2543 |
-
"step": 11222
|
| 2544 |
-
},
|
| 2545 |
-
{
|
| 2546 |
-
"epoch": 0.28191702575408356,
|
| 2547 |
-
"grad_norm": 0.9407718181610107,
|
| 2548 |
-
"learning_rate": 3.735111675341645e-05,
|
| 2549 |
-
"loss": 1.6574,
|
| 2550 |
-
"step": 11253
|
| 2551 |
-
},
|
| 2552 |
-
{
|
| 2553 |
-
"epoch": 0.28269365667902596,
|
| 2554 |
-
"grad_norm": 0.9167685508728027,
|
| 2555 |
-
"learning_rate": 3.7278029818298524e-05,
|
| 2556 |
-
"loss": 1.6767,
|
| 2557 |
-
"step": 11284
|
| 2558 |
-
},
|
| 2559 |
-
{
|
| 2560 |
-
"epoch": 0.2834702876039683,
|
| 2561 |
-
"grad_norm": 0.8957439661026001,
|
| 2562 |
-
"learning_rate": 3.720480432728287e-05,
|
| 2563 |
-
"loss": 1.6846,
|
| 2564 |
-
"step": 11315
|
| 2565 |
-
},
|
| 2566 |
-
{
|
| 2567 |
-
"epoch": 0.2842469185289107,
|
| 2568 |
-
"grad_norm": 0.9044497609138489,
|
| 2569 |
-
"learning_rate": 3.71314411067092e-05,
|
| 2570 |
-
"loss": 1.6323,
|
| 2571 |
-
"step": 11346
|
| 2572 |
-
},
|
| 2573 |
-
{
|
| 2574 |
-
"epoch": 0.2850235494538531,
|
| 2575 |
-
"grad_norm": 0.9024799466133118,
|
| 2576 |
-
"learning_rate": 3.70579409844715e-05,
|
| 2577 |
-
"loss": 1.682,
|
| 2578 |
-
"step": 11377
|
| 2579 |
-
},
|
| 2580 |
-
{
|
| 2581 |
-
"epoch": 0.28580018037879545,
|
| 2582 |
-
"grad_norm": 0.9126555323600769,
|
| 2583 |
-
"learning_rate": 3.698430479000865e-05,
|
| 2584 |
-
"loss": 1.6802,
|
| 2585 |
-
"step": 11408
|
| 2586 |
-
},
|
| 2587 |
-
{
|
| 2588 |
-
"epoch": 0.28657681130373786,
|
| 2589 |
-
"grad_norm": 0.924310564994812,
|
| 2590 |
-
"learning_rate": 3.691053335429509e-05,
|
| 2591 |
-
"loss": 1.6568,
|
| 2592 |
-
"step": 11439
|
| 2593 |
-
},
|
| 2594 |
-
{
|
| 2595 |
-
"epoch": 0.28735344222868026,
|
| 2596 |
-
"grad_norm": 0.8566572666168213,
|
| 2597 |
-
"learning_rate": 3.683662750983147e-05,
|
| 2598 |
-
"loss": 1.6682,
|
| 2599 |
-
"step": 11470
|
| 2600 |
-
},
|
| 2601 |
-
{
|
| 2602 |
-
"epoch": 0.2881300731536226,
|
| 2603 |
-
"grad_norm": 0.8287222981452942,
|
| 2604 |
-
"learning_rate": 3.676258809063518e-05,
|
| 2605 |
-
"loss": 1.6484,
|
| 2606 |
-
"step": 11501
|
| 2607 |
-
},
|
| 2608 |
-
{
|
| 2609 |
-
"epoch": 0.288906704078565,
|
| 2610 |
-
"grad_norm": 1.0163201093673706,
|
| 2611 |
-
"learning_rate": 3.6688415932231004e-05,
|
| 2612 |
-
"loss": 1.635,
|
| 2613 |
-
"step": 11532
|
| 2614 |
-
},
|
| 2615 |
-
{
|
| 2616 |
-
"epoch": 0.28968333500350735,
|
| 2617 |
-
"grad_norm": 0.8813551068305969,
|
| 2618 |
-
"learning_rate": 3.661411187164166e-05,
|
| 2619 |
-
"loss": 1.6654,
|
| 2620 |
-
"step": 11563
|
| 2621 |
-
},
|
| 2622 |
-
{
|
| 2623 |
-
"epoch": 0.29045996592844975,
|
| 2624 |
-
"grad_norm": 0.8688541650772095,
|
| 2625 |
-
"learning_rate": 3.65396767473784e-05,
|
| 2626 |
-
"loss": 1.6787,
|
| 2627 |
-
"step": 11594
|
| 2628 |
-
},
|
| 2629 |
-
{
|
| 2630 |
-
"epoch": 0.29123659685339215,
|
| 2631 |
-
"grad_norm": 0.8820333480834961,
|
| 2632 |
-
"learning_rate": 3.6465111399431465e-05,
|
| 2633 |
-
"loss": 1.6418,
|
| 2634 |
-
"step": 11625
|
| 2635 |
-
},
|
| 2636 |
-
{
|
| 2637 |
-
"epoch": 0.2920132277783345,
|
| 2638 |
-
"grad_norm": 0.9284527897834778,
|
| 2639 |
-
"learning_rate": 3.6390416669260674e-05,
|
| 2640 |
-
"loss": 1.6727,
|
| 2641 |
-
"step": 11656
|
| 2642 |
-
},
|
| 2643 |
-
{
|
| 2644 |
-
"epoch": 0.2927898587032769,
|
| 2645 |
-
"grad_norm": 0.8665077090263367,
|
| 2646 |
-
"learning_rate": 3.63155933997859e-05,
|
| 2647 |
-
"loss": 1.6377,
|
| 2648 |
-
"step": 11687
|
| 2649 |
-
},
|
| 2650 |
-
{
|
| 2651 |
-
"epoch": 0.29356648962821924,
|
| 2652 |
-
"grad_norm": 0.9927760362625122,
|
| 2653 |
-
"learning_rate": 3.624064243537758e-05,
|
| 2654 |
-
"loss": 1.6628,
|
| 2655 |
-
"step": 11718
|
| 2656 |
-
},
|
| 2657 |
-
{
|
| 2658 |
-
"epoch": 0.29434312055316164,
|
| 2659 |
-
"grad_norm": 0.9006340503692627,
|
| 2660 |
-
"learning_rate": 3.616556462184716e-05,
|
| 2661 |
-
"loss": 1.6589,
|
| 2662 |
-
"step": 11749
|
| 2663 |
-
},
|
| 2664 |
-
{
|
| 2665 |
-
"epoch": 0.29511975147810404,
|
| 2666 |
-
"grad_norm": 0.9278168082237244,
|
| 2667 |
-
"learning_rate": 3.609036080643755e-05,
|
| 2668 |
-
"loss": 1.6519,
|
| 2669 |
-
"step": 11780
|
| 2670 |
-
},
|
| 2671 |
-
{
|
| 2672 |
-
"epoch": 0.2958963824030464,
|
| 2673 |
-
"grad_norm": 0.9146036505699158,
|
| 2674 |
-
"learning_rate": 3.60150318378136e-05,
|
| 2675 |
-
"loss": 1.6541,
|
| 2676 |
-
"step": 11811
|
| 2677 |
-
},
|
| 2678 |
-
{
|
| 2679 |
-
"epoch": 0.2966730133279888,
|
| 2680 |
-
"grad_norm": 0.8698804378509521,
|
| 2681 |
-
"learning_rate": 3.5939578566052465e-05,
|
| 2682 |
-
"loss": 1.6722,
|
| 2683 |
-
"step": 11842
|
| 2684 |
-
},
|
| 2685 |
-
{
|
| 2686 |
-
"epoch": 0.29744964425293113,
|
| 2687 |
-
"grad_norm": 0.9304215312004089,
|
| 2688 |
-
"learning_rate": 3.586400184263408e-05,
|
| 2689 |
-
"loss": 1.6392,
|
| 2690 |
-
"step": 11873
|
| 2691 |
-
},
|
| 2692 |
-
{
|
| 2693 |
-
"epoch": 0.29822627517787353,
|
| 2694 |
-
"grad_norm": 0.8917405605316162,
|
| 2695 |
-
"learning_rate": 3.578830252043148e-05,
|
| 2696 |
-
"loss": 1.6373,
|
| 2697 |
-
"step": 11904
|
| 2698 |
-
},
|
| 2699 |
-
{
|
| 2700 |
-
"epoch": 0.29900290610281594,
|
| 2701 |
-
"grad_norm": 0.9075546860694885,
|
| 2702 |
-
"learning_rate": 3.571248145370125e-05,
|
| 2703 |
-
"loss": 1.6401,
|
| 2704 |
-
"step": 11935
|
| 2705 |
-
},
|
| 2706 |
-
{
|
| 2707 |
-
"epoch": 0.2997795370277583,
|
| 2708 |
-
"grad_norm": 0.9235963225364685,
|
| 2709 |
-
"learning_rate": 3.5636539498073794e-05,
|
| 2710 |
-
"loss": 1.667,
|
| 2711 |
-
"step": 11966
|
| 2712 |
-
},
|
| 2713 |
-
{
|
| 2714 |
-
"epoch": 0.3005561679527007,
|
| 2715 |
-
"grad_norm": 0.9514668583869934,
|
| 2716 |
-
"learning_rate": 3.556047751054378e-05,
|
| 2717 |
-
"loss": 1.6654,
|
| 2718 |
-
"step": 11997
|
| 2719 |
-
},
|
| 2720 |
-
{
|
| 2721 |
-
"epoch": 0.301332798877643,
|
| 2722 |
-
"grad_norm": 0.8843172192573547,
|
| 2723 |
-
"learning_rate": 3.548429634946039e-05,
|
| 2724 |
-
"loss": 1.6609,
|
| 2725 |
-
"step": 12028
|
| 2726 |
-
},
|
| 2727 |
-
{
|
| 2728 |
-
"epoch": 0.3021094298025854,
|
| 2729 |
-
"grad_norm": 0.9325070977210999,
|
| 2730 |
-
"learning_rate": 3.540799687451768e-05,
|
| 2731 |
-
"loss": 1.6392,
|
| 2732 |
-
"step": 12059
|
| 2733 |
-
},
|
| 2734 |
-
{
|
| 2735 |
-
"epoch": 0.30288606072752783,
|
| 2736 |
-
"grad_norm": 0.8855581879615784,
|
| 2737 |
-
"learning_rate": 3.533157994674485e-05,
|
| 2738 |
-
"loss": 1.6607,
|
| 2739 |
-
"step": 12090
|
| 2740 |
-
},
|
| 2741 |
-
{
|
| 2742 |
-
"epoch": 0.3036626916524702,
|
| 2743 |
-
"grad_norm": 0.9044367671012878,
|
| 2744 |
-
"learning_rate": 3.5255046428496546e-05,
|
| 2745 |
-
"loss": 1.6417,
|
| 2746 |
-
"step": 12121
|
| 2747 |
-
},
|
| 2748 |
-
{
|
| 2749 |
-
"epoch": 0.3044393225774126,
|
| 2750 |
-
"grad_norm": 0.9446975588798523,
|
| 2751 |
-
"learning_rate": 3.517839718344311e-05,
|
| 2752 |
-
"loss": 1.6279,
|
| 2753 |
-
"step": 12152
|
| 2754 |
-
},
|
| 2755 |
-
{
|
| 2756 |
-
"epoch": 0.3052159535023549,
|
| 2757 |
-
"grad_norm": 0.8764945864677429,
|
| 2758 |
-
"learning_rate": 3.510163307656086e-05,
|
| 2759 |
-
"loss": 1.6297,
|
| 2760 |
-
"step": 12183
|
| 2761 |
-
},
|
| 2762 |
-
{
|
| 2763 |
-
"epoch": 0.3059925844272973,
|
| 2764 |
-
"grad_norm": 0.8633154034614563,
|
| 2765 |
-
"learning_rate": 3.5024754974122324e-05,
|
| 2766 |
-
"loss": 1.648,
|
| 2767 |
-
"step": 12214
|
| 2768 |
-
},
|
| 2769 |
-
{
|
| 2770 |
-
"epoch": 0.3067692153522397,
|
| 2771 |
-
"grad_norm": 0.8891461491584778,
|
| 2772 |
-
"learning_rate": 3.494776374368643e-05,
|
| 2773 |
-
"loss": 1.6492,
|
| 2774 |
-
"step": 12245
|
| 2775 |
-
},
|
| 2776 |
-
{
|
| 2777 |
-
"epoch": 0.30754584627718207,
|
| 2778 |
-
"grad_norm": 0.8888112306594849,
|
| 2779 |
-
"learning_rate": 3.4870660254088724e-05,
|
| 2780 |
-
"loss": 1.6507,
|
| 2781 |
-
"step": 12276
|
| 2782 |
-
},
|
| 2783 |
-
{
|
| 2784 |
-
"epoch": 0.30832247720212447,
|
| 2785 |
-
"grad_norm": 0.8980075120925903,
|
| 2786 |
-
"learning_rate": 3.479344537543164e-05,
|
| 2787 |
-
"loss": 1.6571,
|
| 2788 |
-
"step": 12307
|
| 2789 |
-
},
|
| 2790 |
-
{
|
| 2791 |
-
"epoch": 0.3090991081270668,
|
| 2792 |
-
"grad_norm": 0.86537104845047,
|
| 2793 |
-
"learning_rate": 3.4716119979074565e-05,
|
| 2794 |
-
"loss": 1.6331,
|
| 2795 |
-
"step": 12338
|
| 2796 |
-
},
|
| 2797 |
-
{
|
| 2798 |
-
"epoch": 0.3098757390520092,
|
| 2799 |
-
"grad_norm": 0.9001527428627014,
|
| 2800 |
-
"learning_rate": 3.463868493762412e-05,
|
| 2801 |
-
"loss": 1.6453,
|
| 2802 |
-
"step": 12369
|
| 2803 |
-
},
|
| 2804 |
-
{
|
| 2805 |
-
"epoch": 0.3106523699769516,
|
| 2806 |
-
"grad_norm": 0.8868582248687744,
|
| 2807 |
-
"learning_rate": 3.456114112492418e-05,
|
| 2808 |
-
"loss": 1.6623,
|
| 2809 |
-
"step": 12400
|
| 2810 |
-
},
|
| 2811 |
-
{
|
| 2812 |
-
"epoch": 0.31142900090189396,
|
| 2813 |
-
"grad_norm": 0.899174690246582,
|
| 2814 |
-
"learning_rate": 3.4483489416046164e-05,
|
| 2815 |
-
"loss": 1.6451,
|
| 2816 |
-
"step": 12431
|
| 2817 |
-
},
|
| 2818 |
-
{
|
| 2819 |
-
"epoch": 0.31220563182683636,
|
| 2820 |
-
"grad_norm": 0.9003099203109741,
|
| 2821 |
-
"learning_rate": 3.440573068727905e-05,
|
| 2822 |
-
"loss": 1.6544,
|
| 2823 |
-
"step": 12462
|
| 2824 |
-
},
|
| 2825 |
-
{
|
| 2826 |
-
"epoch": 0.31298226275177876,
|
| 2827 |
-
"grad_norm": 0.8912012577056885,
|
| 2828 |
-
"learning_rate": 3.4327865816119495e-05,
|
| 2829 |
-
"loss": 1.6579,
|
| 2830 |
-
"step": 12493
|
| 2831 |
-
},
|
| 2832 |
-
{
|
| 2833 |
-
"epoch": 0.3137588936767211,
|
| 2834 |
-
"grad_norm": 0.8915206789970398,
|
| 2835 |
-
"learning_rate": 3.4249895681262025e-05,
|
| 2836 |
-
"loss": 1.65,
|
| 2837 |
-
"step": 12524
|
| 2838 |
-
},
|
| 2839 |
-
{
|
| 2840 |
-
"epoch": 0.3145355246016635,
|
| 2841 |
-
"grad_norm": 0.9975365400314331,
|
| 2842 |
-
"learning_rate": 3.417182116258899e-05,
|
| 2843 |
-
"loss": 1.6506,
|
| 2844 |
-
"step": 12555
|
| 2845 |
-
},
|
| 2846 |
-
{
|
| 2847 |
-
"epoch": 0.31531215552660585,
|
| 2848 |
-
"grad_norm": 0.8904858827590942,
|
| 2849 |
-
"learning_rate": 3.409364314116074e-05,
|
| 2850 |
-
"loss": 1.6402,
|
| 2851 |
-
"step": 12586
|
| 2852 |
-
},
|
| 2853 |
-
{
|
| 2854 |
-
"epoch": 0.31608878645154825,
|
| 2855 |
-
"grad_norm": 0.8596284985542297,
|
| 2856 |
-
"learning_rate": 3.401536249920559e-05,
|
| 2857 |
-
"loss": 1.6473,
|
| 2858 |
-
"step": 12617
|
| 2859 |
-
},
|
| 2860 |
-
{
|
| 2861 |
-
"epoch": 0.31686541737649065,
|
| 2862 |
-
"grad_norm": 0.8970181345939636,
|
| 2863 |
-
"learning_rate": 3.393698012010998e-05,
|
| 2864 |
-
"loss": 1.6347,
|
| 2865 |
-
"step": 12648
|
| 2866 |
-
},
|
| 2867 |
-
{
|
| 2868 |
-
"epoch": 0.317642048301433,
|
| 2869 |
-
"grad_norm": 0.890839695930481,
|
| 2870 |
-
"learning_rate": 3.385849688840839e-05,
|
| 2871 |
-
"loss": 1.6323,
|
| 2872 |
-
"step": 12679
|
| 2873 |
-
},
|
| 2874 |
-
{
|
| 2875 |
-
"epoch": 0.3184186792263754,
|
| 2876 |
-
"grad_norm": 0.914010226726532,
|
| 2877 |
-
"learning_rate": 3.3779913689773414e-05,
|
| 2878 |
-
"loss": 1.6396,
|
| 2879 |
-
"step": 12710
|
| 2880 |
-
},
|
| 2881 |
-
{
|
| 2882 |
-
"epoch": 0.31919531015131775,
|
| 2883 |
-
"grad_norm": 0.8762277960777283,
|
| 2884 |
-
"learning_rate": 3.370123141100578e-05,
|
| 2885 |
-
"loss": 1.6057,
|
| 2886 |
-
"step": 12741
|
| 2887 |
-
},
|
| 2888 |
-
{
|
| 2889 |
-
"epoch": 0.31997194107626015,
|
| 2890 |
-
"grad_norm": 0.9001442193984985,
|
| 2891 |
-
"learning_rate": 3.3622450940024305e-05,
|
| 2892 |
-
"loss": 1.647,
|
| 2893 |
-
"step": 12772
|
| 2894 |
-
},
|
| 2895 |
-
{
|
| 2896 |
-
"epoch": 0.32074857200120255,
|
| 2897 |
-
"grad_norm": 0.8792625069618225,
|
| 2898 |
-
"learning_rate": 3.35435731658559e-05,
|
| 2899 |
-
"loss": 1.6441,
|
| 2900 |
-
"step": 12803
|
| 2901 |
-
},
|
| 2902 |
-
{
|
| 2903 |
-
"epoch": 0.3215252029261449,
|
| 2904 |
-
"grad_norm": 0.889738142490387,
|
| 2905 |
-
"learning_rate": 3.346459897862552e-05,
|
| 2906 |
-
"loss": 1.6433,
|
| 2907 |
-
"step": 12834
|
| 2908 |
-
},
|
| 2909 |
-
{
|
| 2910 |
-
"epoch": 0.3223018338510873,
|
| 2911 |
-
"grad_norm": 0.9831507205963135,
|
| 2912 |
-
"learning_rate": 3.338552926954613e-05,
|
| 2913 |
-
"loss": 1.6635,
|
| 2914 |
-
"step": 12865
|
| 2915 |
-
},
|
| 2916 |
-
{
|
| 2917 |
-
"epoch": 0.32307846477602964,
|
| 2918 |
-
"grad_norm": 0.8929276466369629,
|
| 2919 |
-
"learning_rate": 3.330636493090868e-05,
|
| 2920 |
-
"loss": 1.6439,
|
| 2921 |
-
"step": 12896
|
| 2922 |
-
},
|
| 2923 |
-
{
|
| 2924 |
-
"epoch": 0.32385509570097204,
|
| 2925 |
-
"grad_norm": 0.8983376026153564,
|
| 2926 |
-
"learning_rate": 3.322710685607193e-05,
|
| 2927 |
-
"loss": 1.641,
|
| 2928 |
-
"step": 12927
|
| 2929 |
-
},
|
| 2930 |
-
{
|
| 2931 |
-
"epoch": 0.32463172662591444,
|
| 2932 |
-
"grad_norm": 0.8629191517829895,
|
| 2933 |
-
"learning_rate": 3.314775593945251e-05,
|
| 2934 |
-
"loss": 1.6336,
|
| 2935 |
-
"step": 12958
|
| 2936 |
-
},
|
| 2937 |
-
{
|
| 2938 |
-
"epoch": 0.3254083575508568,
|
| 2939 |
-
"grad_norm": 0.9323459267616272,
|
| 2940 |
-
"learning_rate": 3.3068313076514714e-05,
|
| 2941 |
-
"loss": 1.6304,
|
| 2942 |
-
"step": 12989
|
| 2943 |
-
},
|
| 2944 |
-
{
|
| 2945 |
-
"epoch": 0.3261849884757992,
|
| 2946 |
-
"grad_norm": 0.8520583510398865,
|
| 2947 |
-
"learning_rate": 3.298877916376047e-05,
|
| 2948 |
-
"loss": 1.6277,
|
| 2949 |
-
"step": 13020
|
| 2950 |
-
},
|
| 2951 |
-
{
|
| 2952 |
-
"epoch": 0.32696161940074153,
|
| 2953 |
-
"grad_norm": 0.8893365263938904,
|
| 2954 |
-
"learning_rate": 3.290915509871915e-05,
|
| 2955 |
-
"loss": 1.6508,
|
| 2956 |
-
"step": 13051
|
| 2957 |
-
},
|
| 2958 |
-
{
|
| 2959 |
-
"epoch": 0.32773825032568393,
|
| 2960 |
-
"grad_norm": 0.8612290024757385,
|
| 2961 |
-
"learning_rate": 3.282944177993753e-05,
|
| 2962 |
-
"loss": 1.6319,
|
| 2963 |
-
"step": 13082
|
| 2964 |
-
},
|
| 2965 |
-
{
|
| 2966 |
-
"epoch": 0.32851488125062633,
|
| 2967 |
-
"grad_norm": 0.9378547072410583,
|
| 2968 |
-
"learning_rate": 3.274964010696957e-05,
|
| 2969 |
-
"loss": 1.637,
|
| 2970 |
-
"step": 13113
|
| 2971 |
-
},
|
| 2972 |
-
{
|
| 2973 |
-
"epoch": 0.3292915121755687,
|
| 2974 |
-
"grad_norm": 0.8851338028907776,
|
| 2975 |
-
"learning_rate": 3.266975098036629e-05,
|
| 2976 |
-
"loss": 1.6326,
|
| 2977 |
-
"step": 13144
|
| 2978 |
-
},
|
| 2979 |
-
{
|
| 2980 |
-
"epoch": 0.3300681431005111,
|
| 2981 |
-
"grad_norm": 0.9052163362503052,
|
| 2982 |
-
"learning_rate": 3.258977530166562e-05,
|
| 2983 |
-
"loss": 1.6507,
|
| 2984 |
-
"step": 13175
|
| 2985 |
-
},
|
| 2986 |
-
{
|
| 2987 |
-
"epoch": 0.3308447740254534,
|
| 2988 |
-
"grad_norm": 0.9593476057052612,
|
| 2989 |
-
"learning_rate": 3.250971397338227e-05,
|
| 2990 |
-
"loss": 1.6497,
|
| 2991 |
-
"step": 13206
|
| 2992 |
-
},
|
| 2993 |
-
{
|
| 2994 |
-
"epoch": 0.3316214049503958,
|
| 2995 |
-
"grad_norm": 0.8861746788024902,
|
| 2996 |
-
"learning_rate": 3.2429567898997404e-05,
|
| 2997 |
-
"loss": 1.6487,
|
| 2998 |
-
"step": 13237
|
| 2999 |
-
},
|
| 3000 |
-
{
|
| 3001 |
-
"epoch": 0.3323980358753382,
|
| 3002 |
-
"grad_norm": 0.8835756778717041,
|
| 3003 |
-
"learning_rate": 3.234933798294859e-05,
|
| 3004 |
-
"loss": 1.6328,
|
| 3005 |
-
"step": 13268
|
| 3006 |
-
},
|
| 3007 |
-
{
|
| 3008 |
-
"epoch": 0.33317466680028057,
|
| 3009 |
-
"grad_norm": 0.9133350849151611,
|
| 3010 |
-
"learning_rate": 3.2269025130619535e-05,
|
| 3011 |
-
"loss": 1.6326,
|
| 3012 |
-
"step": 13299
|
| 3013 |
-
},
|
| 3014 |
-
{
|
| 3015 |
-
"epoch": 0.333951297725223,
|
| 3016 |
-
"grad_norm": 0.8866952657699585,
|
| 3017 |
-
"learning_rate": 3.218863024832985e-05,
|
| 3018 |
-
"loss": 1.6418,
|
| 3019 |
-
"step": 13330
|
| 3020 |
-
},
|
| 3021 |
-
{
|
| 3022 |
-
"epoch": 0.3347279286501654,
|
| 3023 |
-
"grad_norm": 0.8961243033409119,
|
| 3024 |
-
"learning_rate": 3.2108154243324864e-05,
|
| 3025 |
-
"loss": 1.6436,
|
| 3026 |
-
"step": 13361
|
| 3027 |
-
},
|
| 3028 |
-
{
|
| 3029 |
-
"epoch": 0.3355045595751077,
|
| 3030 |
-
"grad_norm": 0.871108889579773,
|
| 3031 |
-
"learning_rate": 3.2027598023765345e-05,
|
| 3032 |
-
"loss": 1.6205,
|
| 3033 |
-
"step": 13392
|
| 3034 |
-
},
|
| 3035 |
-
{
|
| 3036 |
-
"epoch": 0.3362811905000501,
|
| 3037 |
-
"grad_norm": 0.8666812777519226,
|
| 3038 |
-
"learning_rate": 3.194696249871729e-05,
|
| 3039 |
-
"loss": 1.6478,
|
| 3040 |
-
"step": 13423
|
| 3041 |
-
},
|
| 3042 |
-
{
|
| 3043 |
-
"epoch": 0.33705782142499247,
|
| 3044 |
-
"grad_norm": 0.8760045766830444,
|
| 3045 |
-
"learning_rate": 3.186624857814164e-05,
|
| 3046 |
-
"loss": 1.63,
|
| 3047 |
-
"step": 13454
|
| 3048 |
-
},
|
| 3049 |
-
{
|
| 3050 |
-
"epoch": 0.33783445234993487,
|
| 3051 |
-
"grad_norm": 0.9416362047195435,
|
| 3052 |
-
"learning_rate": 3.178545717288401e-05,
|
| 3053 |
-
"loss": 1.6268,
|
| 3054 |
-
"step": 13485
|
| 3055 |
-
},
|
| 3056 |
-
{
|
| 3057 |
-
"epoch": 0.33861108327487727,
|
| 3058 |
-
"grad_norm": 0.8591843843460083,
|
| 3059 |
-
"learning_rate": 3.170458919466444e-05,
|
| 3060 |
-
"loss": 1.6206,
|
| 3061 |
-
"step": 13516
|
| 3062 |
-
},
|
| 3063 |
-
{
|
| 3064 |
-
"epoch": 0.3393877141998196,
|
| 3065 |
-
"grad_norm": 0.9452426433563232,
|
| 3066 |
-
"learning_rate": 3.1623645556067063e-05,
|
| 3067 |
-
"loss": 1.6351,
|
| 3068 |
-
"step": 13547
|
| 3069 |
-
},
|
| 3070 |
-
{
|
| 3071 |
-
"epoch": 0.340164345124762,
|
| 3072 |
-
"grad_norm": 0.8680084943771362,
|
| 3073 |
-
"learning_rate": 3.154262717052985e-05,
|
| 3074 |
-
"loss": 1.6389,
|
| 3075 |
-
"step": 13578
|
| 3076 |
-
},
|
| 3077 |
-
{
|
| 3078 |
-
"epoch": 0.34094097604970436,
|
| 3079 |
-
"grad_norm": 0.8631142973899841,
|
| 3080 |
-
"learning_rate": 3.146153495233426e-05,
|
| 3081 |
-
"loss": 1.6198,
|
| 3082 |
-
"step": 13609
|
| 3083 |
-
},
|
| 3084 |
-
{
|
| 3085 |
-
"epoch": 0.34171760697464676,
|
| 3086 |
-
"grad_norm": 0.905168354511261,
|
| 3087 |
-
"learning_rate": 3.1380369816594944e-05,
|
| 3088 |
-
"loss": 1.6395,
|
| 3089 |
-
"step": 13640
|
| 3090 |
-
},
|
| 3091 |
-
{
|
| 3092 |
-
"epoch": 0.34249423789958916,
|
| 3093 |
-
"grad_norm": 0.8644616007804871,
|
| 3094 |
-
"learning_rate": 3.129913267924946e-05,
|
| 3095 |
-
"loss": 1.6282,
|
| 3096 |
-
"step": 13671
|
| 3097 |
-
},
|
| 3098 |
-
{
|
| 3099 |
-
"epoch": 0.3432708688245315,
|
| 3100 |
-
"grad_norm": 0.8989911675453186,
|
| 3101 |
-
"learning_rate": 3.121782445704782e-05,
|
| 3102 |
-
"loss": 1.6378,
|
| 3103 |
-
"step": 13702
|
| 3104 |
-
},
|
| 3105 |
-
{
|
| 3106 |
-
"epoch": 0.3440474997494739,
|
| 3107 |
-
"grad_norm": 0.908371090888977,
|
| 3108 |
-
"learning_rate": 3.11364460675423e-05,
|
| 3109 |
-
"loss": 1.6152,
|
| 3110 |
-
"step": 13733
|
| 3111 |
-
},
|
| 3112 |
-
{
|
| 3113 |
-
"epoch": 0.34482413067441625,
|
| 3114 |
-
"grad_norm": 0.876471221446991,
|
| 3115 |
-
"learning_rate": 3.1054998429076934e-05,
|
| 3116 |
-
"loss": 1.6533,
|
| 3117 |
-
"step": 13764
|
| 3118 |
-
},
|
| 3119 |
-
{
|
| 3120 |
-
"epoch": 0.34560076159935865,
|
| 3121 |
-
"grad_norm": 0.879152238368988,
|
| 3122 |
-
"learning_rate": 3.097348246077728e-05,
|
| 3123 |
-
"loss": 1.6196,
|
| 3124 |
-
"step": 13795
|
| 3125 |
-
},
|
| 3126 |
-
{
|
| 3127 |
-
"epoch": 0.34637739252430105,
|
| 3128 |
-
"grad_norm": 0.8737320303916931,
|
| 3129 |
-
"learning_rate": 3.0891899082539924e-05,
|
| 3130 |
-
"loss": 1.6122,
|
| 3131 |
-
"step": 13826
|
| 3132 |
-
},
|
| 3133 |
-
{
|
| 3134 |
-
"epoch": 0.3471540234492434,
|
| 3135 |
-
"grad_norm": 0.894914448261261,
|
| 3136 |
-
"learning_rate": 3.0810249215022233e-05,
|
| 3137 |
-
"loss": 1.6231,
|
| 3138 |
-
"step": 13857
|
| 3139 |
-
},
|
| 3140 |
-
{
|
| 3141 |
-
"epoch": 0.3479306543741858,
|
| 3142 |
-
"grad_norm": 0.8699216842651367,
|
| 3143 |
-
"learning_rate": 3.0728533779631865e-05,
|
| 3144 |
-
"loss": 1.6374,
|
| 3145 |
-
"step": 13888
|
| 3146 |
-
},
|
| 3147 |
-
{
|
| 3148 |
-
"epoch": 0.34870728529912814,
|
| 3149 |
-
"grad_norm": 0.8811262249946594,
|
| 3150 |
-
"learning_rate": 3.064675369851637e-05,
|
| 3151 |
-
"loss": 1.635,
|
| 3152 |
-
"step": 13919
|
| 3153 |
-
},
|
| 3154 |
-
{
|
| 3155 |
-
"epoch": 0.34948391622407055,
|
| 3156 |
-
"grad_norm": 0.9017398953437805,
|
| 3157 |
-
"learning_rate": 3.056490989455289e-05,
|
| 3158 |
-
"loss": 1.6377,
|
| 3159 |
-
"step": 13950
|
| 3160 |
-
},
|
| 3161 |
-
{
|
| 3162 |
-
"epoch": 0.35026054714901295,
|
| 3163 |
-
"grad_norm": 0.8944412469863892,
|
| 3164 |
-
"learning_rate": 3.0483003291337596e-05,
|
| 3165 |
-
"loss": 1.6401,
|
| 3166 |
-
"step": 13981
|
| 3167 |
-
},
|
| 3168 |
-
{
|
| 3169 |
-
"epoch": 0.3510371780739553,
|
| 3170 |
-
"grad_norm": 0.9429489970207214,
|
| 3171 |
-
"learning_rate": 3.040103481317539e-05,
|
| 3172 |
-
"loss": 1.6313,
|
| 3173 |
-
"step": 14012
|
| 3174 |
-
},
|
| 3175 |
-
{
|
| 3176 |
-
"epoch": 0.3518138089988977,
|
| 3177 |
-
"grad_norm": 0.8750442862510681,
|
| 3178 |
-
"learning_rate": 3.03190053850694e-05,
|
| 3179 |
-
"loss": 1.6305,
|
| 3180 |
-
"step": 14043
|
| 3181 |
-
},
|
| 3182 |
-
{
|
| 3183 |
-
"epoch": 0.35259043992384004,
|
| 3184 |
-
"grad_norm": 0.8219168782234192,
|
| 3185 |
-
"learning_rate": 3.0236915932710573e-05,
|
| 3186 |
-
"loss": 1.6289,
|
| 3187 |
-
"step": 14074
|
| 3188 |
-
},
|
| 3189 |
-
{
|
| 3190 |
-
"epoch": 0.35336707084878244,
|
| 3191 |
-
"grad_norm": 0.9778533577919006,
|
| 3192 |
-
"learning_rate": 3.0154767382467232e-05,
|
| 3193 |
-
"loss": 1.6221,
|
| 3194 |
-
"step": 14105
|
| 3195 |
-
},
|
| 3196 |
-
{
|
| 3197 |
-
"epoch": 0.35414370177372484,
|
| 3198 |
-
"grad_norm": 0.8655532598495483,
|
| 3199 |
-
"learning_rate": 3.0072560661374582e-05,
|
| 3200 |
-
"loss": 1.6352,
|
| 3201 |
-
"step": 14136
|
| 3202 |
-
},
|
| 3203 |
-
{
|
| 3204 |
-
"epoch": 0.3549203326986672,
|
| 3205 |
-
"grad_norm": 0.8914876580238342,
|
| 3206 |
-
"learning_rate": 2.999029669712431e-05,
|
| 3207 |
-
"loss": 1.6283,
|
| 3208 |
-
"step": 14167
|
| 3209 |
-
},
|
| 3210 |
-
{
|
| 3211 |
-
"epoch": 0.3556969636236096,
|
| 3212 |
-
"grad_norm": 0.9823268055915833,
|
| 3213 |
-
"learning_rate": 2.990797641805408e-05,
|
| 3214 |
-
"loss": 1.6037,
|
| 3215 |
-
"step": 14198
|
| 3216 |
-
},
|
| 3217 |
-
{
|
| 3218 |
-
"epoch": 0.356473594548552,
|
| 3219 |
-
"grad_norm": 0.8770225048065186,
|
| 3220 |
-
"learning_rate": 2.982560075313704e-05,
|
| 3221 |
-
"loss": 1.6199,
|
| 3222 |
-
"step": 14229
|
| 3223 |
-
},
|
| 3224 |
-
{
|
| 3225 |
-
"epoch": 0.35725022547349433,
|
| 3226 |
-
"grad_norm": 0.8294642567634583,
|
| 3227 |
-
"learning_rate": 2.9743170631971368e-05,
|
| 3228 |
-
"loss": 1.587,
|
| 3229 |
-
"step": 14260
|
| 3230 |
-
},
|
| 3231 |
-
{
|
| 3232 |
-
"epoch": 0.35802685639843673,
|
| 3233 |
-
"grad_norm": 0.8678600192070007,
|
| 3234 |
-
"learning_rate": 2.9660686984769792e-05,
|
| 3235 |
-
"loss": 1.6006,
|
| 3236 |
-
"step": 14291
|
| 3237 |
-
},
|
| 3238 |
-
{
|
| 3239 |
-
"epoch": 0.3588034873233791,
|
| 3240 |
-
"grad_norm": 0.8829056620597839,
|
| 3241 |
-
"learning_rate": 2.9578150742349047e-05,
|
| 3242 |
-
"loss": 1.6354,
|
| 3243 |
-
"step": 14322
|
| 3244 |
-
},
|
| 3245 |
-
{
|
| 3246 |
-
"epoch": 0.3595801182483215,
|
| 3247 |
-
"grad_norm": 0.8785590529441833,
|
| 3248 |
-
"learning_rate": 2.949556283611942e-05,
|
| 3249 |
-
"loss": 1.6293,
|
| 3250 |
-
"step": 14353
|
| 3251 |
-
},
|
| 3252 |
-
{
|
| 3253 |
-
"epoch": 0.3603567491732639,
|
| 3254 |
-
"grad_norm": 0.8895497918128967,
|
| 3255 |
-
"learning_rate": 2.9412924198074206e-05,
|
| 3256 |
-
"loss": 1.6121,
|
| 3257 |
-
"step": 14384
|
| 3258 |
-
},
|
| 3259 |
-
{
|
| 3260 |
-
"epoch": 0.3611333800982062,
|
| 3261 |
-
"grad_norm": 0.8808982372283936,
|
| 3262 |
-
"learning_rate": 2.9330235760779208e-05,
|
| 3263 |
-
"loss": 1.6251,
|
| 3264 |
-
"step": 14415
|
| 3265 |
-
},
|
| 3266 |
-
{
|
| 3267 |
-
"epoch": 0.3619100110231486,
|
| 3268 |
-
"grad_norm": 0.8854517936706543,
|
| 3269 |
-
"learning_rate": 2.9247498457362188e-05,
|
| 3270 |
-
"loss": 1.617,
|
| 3271 |
-
"step": 14446
|
| 3272 |
-
},
|
| 3273 |
-
{
|
| 3274 |
-
"epoch": 0.36268664194809097,
|
| 3275 |
-
"grad_norm": 0.9169306755065918,
|
| 3276 |
-
"learning_rate": 2.9164713221502373e-05,
|
| 3277 |
-
"loss": 1.632,
|
| 3278 |
-
"step": 14477
|
| 3279 |
-
},
|
| 3280 |
-
{
|
| 3281 |
-
"epoch": 0.36346327287303337,
|
| 3282 |
-
"grad_norm": 0.9230756163597107,
|
| 3283 |
-
"learning_rate": 2.9081880987419912e-05,
|
| 3284 |
-
"loss": 1.6227,
|
| 3285 |
-
"step": 14508
|
| 3286 |
-
},
|
| 3287 |
-
{
|
| 3288 |
-
"epoch": 0.3642399037979758,
|
| 3289 |
-
"grad_norm": 0.8728978037834167,
|
| 3290 |
-
"learning_rate": 2.8999002689865296e-05,
|
| 3291 |
-
"loss": 1.6175,
|
| 3292 |
-
"step": 14539
|
| 3293 |
-
},
|
| 3294 |
-
{
|
| 3295 |
-
"epoch": 0.3650165347229181,
|
| 3296 |
-
"grad_norm": 0.9083303213119507,
|
| 3297 |
-
"learning_rate": 2.8916079264108852e-05,
|
| 3298 |
-
"loss": 1.6147,
|
| 3299 |
-
"step": 14570
|
| 3300 |
-
},
|
| 3301 |
-
{
|
| 3302 |
-
"epoch": 0.3657931656478605,
|
| 3303 |
-
"grad_norm": 0.8577157855033875,
|
| 3304 |
-
"learning_rate": 2.883311164593017e-05,
|
| 3305 |
-
"loss": 1.6357,
|
| 3306 |
-
"step": 14601
|
| 3307 |
-
},
|
| 3308 |
-
{
|
| 3309 |
-
"epoch": 0.36656979657280286,
|
| 3310 |
-
"grad_norm": 0.9495333433151245,
|
| 3311 |
-
"learning_rate": 2.875010077160754e-05,
|
| 3312 |
-
"loss": 1.6192,
|
| 3313 |
-
"step": 14632
|
| 3314 |
-
},
|
| 3315 |
-
{
|
| 3316 |
-
"epoch": 0.36734642749774526,
|
| 3317 |
-
"grad_norm": 0.9099650979042053,
|
| 3318 |
-
"learning_rate": 2.866704757790741e-05,
|
| 3319 |
-
"loss": 1.6417,
|
| 3320 |
-
"step": 14663
|
| 3321 |
-
},
|
| 3322 |
-
{
|
| 3323 |
-
"epoch": 0.36812305842268767,
|
| 3324 |
-
"grad_norm": 0.8684884905815125,
|
| 3325 |
-
"learning_rate": 2.858395300207376e-05,
|
| 3326 |
-
"loss": 1.6171,
|
| 3327 |
-
"step": 14694
|
| 3328 |
-
},
|
| 3329 |
-
{
|
| 3330 |
-
"epoch": 0.36889968934763,
|
| 3331 |
-
"grad_norm": 0.8524884581565857,
|
| 3332 |
-
"learning_rate": 2.8500817981817607e-05,
|
| 3333 |
-
"loss": 1.6153,
|
| 3334 |
-
"step": 14725
|
| 3335 |
-
},
|
| 3336 |
-
{
|
| 3337 |
-
"epoch": 0.3696763202725724,
|
| 3338 |
-
"grad_norm": 0.9122047424316406,
|
| 3339 |
-
"learning_rate": 2.8417643455306336e-05,
|
| 3340 |
-
"loss": 1.6223,
|
| 3341 |
-
"step": 14756
|
| 3342 |
-
},
|
| 3343 |
-
{
|
| 3344 |
-
"epoch": 0.37045295119751476,
|
| 3345 |
-
"grad_norm": 0.875884473323822,
|
| 3346 |
-
"learning_rate": 2.8334430361153185e-05,
|
| 3347 |
-
"loss": 1.6364,
|
| 3348 |
-
"step": 14787
|
| 3349 |
-
},
|
| 3350 |
-
{
|
| 3351 |
-
"epoch": 0.37122958212245716,
|
| 3352 |
-
"grad_norm": 0.8689435720443726,
|
| 3353 |
-
"learning_rate": 2.8251179638406612e-05,
|
| 3354 |
-
"loss": 1.639,
|
| 3355 |
-
"step": 14818
|
| 3356 |
-
},
|
| 3357 |
-
{
|
| 3358 |
-
"epoch": 0.37200621304739956,
|
| 3359 |
-
"grad_norm": 0.8948261141777039,
|
| 3360 |
-
"learning_rate": 2.8167892226539704e-05,
|
| 3361 |
-
"loss": 1.6091,
|
| 3362 |
-
"step": 14849
|
| 3363 |
-
},
|
| 3364 |
-
{
|
| 3365 |
-
"epoch": 0.3727828439723419,
|
| 3366 |
-
"grad_norm": 0.8971095085144043,
|
| 3367 |
-
"learning_rate": 2.8084569065439588e-05,
|
| 3368 |
-
"loss": 1.6527,
|
| 3369 |
-
"step": 14880
|
| 3370 |
-
},
|
| 3371 |
-
{
|
| 3372 |
-
"epoch": 0.3735594748972843,
|
| 3373 |
-
"grad_norm": 0.9517078995704651,
|
| 3374 |
-
"learning_rate": 2.8001211095396807e-05,
|
| 3375 |
-
"loss": 1.6201,
|
| 3376 |
-
"step": 14911
|
| 3377 |
-
},
|
| 3378 |
-
{
|
| 3379 |
-
"epoch": 0.37433610582222665,
|
| 3380 |
-
"grad_norm": 0.8965676426887512,
|
| 3381 |
-
"learning_rate": 2.791781925709473e-05,
|
| 3382 |
-
"loss": 1.6104,
|
| 3383 |
-
"step": 14942
|
| 3384 |
-
},
|
| 3385 |
-
{
|
| 3386 |
-
"epoch": 0.37511273674716905,
|
| 3387 |
-
"grad_norm": 0.9771518707275391,
|
| 3388 |
-
"learning_rate": 2.7834394491598908e-05,
|
| 3389 |
-
"loss": 1.6329,
|
| 3390 |
-
"step": 14973
|
| 3391 |
-
},
|
| 3392 |
-
{
|
| 3393 |
-
"epoch": 0.37588936767211145,
|
| 3394 |
-
"grad_norm": 0.8746607899665833,
|
| 3395 |
-
"learning_rate": 2.7750937740346485e-05,
|
| 3396 |
-
"loss": 1.6135,
|
| 3397 |
-
"step": 15004
|
| 3398 |
-
},
|
| 3399 |
-
{
|
| 3400 |
-
"epoch": 0.3766659985970538,
|
| 3401 |
-
"grad_norm": 0.860730767250061,
|
| 3402 |
-
"learning_rate": 2.7667449945135564e-05,
|
| 3403 |
-
"loss": 1.6163,
|
| 3404 |
-
"step": 15035
|
| 3405 |
-
},
|
| 3406 |
-
{
|
| 3407 |
-
"epoch": 0.3774426295219962,
|
| 3408 |
-
"grad_norm": 0.8879541158676147,
|
| 3409 |
-
"learning_rate": 2.7583932048114557e-05,
|
| 3410 |
-
"loss": 1.6036,
|
| 3411 |
-
"step": 15066
|
| 3412 |
-
},
|
| 3413 |
-
{
|
| 3414 |
-
"epoch": 0.37821926044693854,
|
| 3415 |
-
"grad_norm": 0.936347246170044,
|
| 3416 |
-
"learning_rate": 2.7500384991771587e-05,
|
| 3417 |
-
"loss": 1.5914,
|
| 3418 |
-
"step": 15097
|
| 3419 |
-
},
|
| 3420 |
-
{
|
| 3421 |
-
"epoch": 0.37899589137188094,
|
| 3422 |
-
"grad_norm": 0.8772497773170471,
|
| 3423 |
-
"learning_rate": 2.7416809718923825e-05,
|
| 3424 |
-
"loss": 1.5994,
|
| 3425 |
-
"step": 15128
|
| 3426 |
-
},
|
| 3427 |
-
{
|
| 3428 |
-
"epoch": 0.37977252229682334,
|
| 3429 |
-
"grad_norm": 0.8785439729690552,
|
| 3430 |
-
"learning_rate": 2.7333207172706864e-05,
|
| 3431 |
-
"loss": 1.6057,
|
| 3432 |
-
"step": 15159
|
| 3433 |
-
},
|
| 3434 |
-
{
|
| 3435 |
-
"epoch": 0.3805491532217657,
|
| 3436 |
-
"grad_norm": 1.1660430431365967,
|
| 3437 |
-
"learning_rate": 2.7249578296564088e-05,
|
| 3438 |
-
"loss": 1.6257,
|
| 3439 |
-
"step": 15190
|
| 3440 |
-
},
|
| 3441 |
-
{
|
| 3442 |
-
"epoch": 0.3813257841467081,
|
| 3443 |
-
"grad_norm": 0.8710660934448242,
|
| 3444 |
-
"learning_rate": 2.7165924034235973e-05,
|
| 3445 |
-
"loss": 1.6223,
|
| 3446 |
-
"step": 15221
|
| 3447 |
-
},
|
| 3448 |
-
{
|
| 3449 |
-
"epoch": 0.3821024150716505,
|
| 3450 |
-
"grad_norm": 0.9040597081184387,
|
| 3451 |
-
"learning_rate": 2.708224532974953e-05,
|
| 3452 |
-
"loss": 1.6054,
|
| 3453 |
-
"step": 15252
|
| 3454 |
-
}
|
| 3455 |
-
],
|
| 3456 |
-
"logging_steps": 31,
|
| 3457 |
-
"max_steps": 30517,
|
| 3458 |
-
"num_input_tokens_seen": 0,
|
| 3459 |
-
"num_train_epochs": 1,
|
| 3460 |
-
"save_steps": 3052,
|
| 3461 |
-
"stateful_callbacks": {
|
| 3462 |
-
"TrainerControl": {
|
| 3463 |
-
"args": {
|
| 3464 |
-
"should_epoch_stop": false,
|
| 3465 |
-
"should_evaluate": false,
|
| 3466 |
-
"should_log": false,
|
| 3467 |
-
"should_save": true,
|
| 3468 |
-
"should_training_stop": false
|
| 3469 |
-
},
|
| 3470 |
-
"attributes": {}
|
| 3471 |
-
}
|
| 3472 |
-
},
|
| 3473 |
-
"total_flos": 1.065842709765292e+19,
|
| 3474 |
-
"train_batch_size": 16,
|
| 3475 |
-
"trial_name": null,
|
| 3476 |
-
"trial_params": null
|
| 3477 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|