Delete checkpoint-192/trainer_state.json with huggingface_hub
Browse files- checkpoint-192/trainer_state.json +0 -1378
checkpoint-192/trainer_state.json
DELETED
|
@@ -1,1378 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_global_step": null,
|
| 3 |
-
"best_metric": null,
|
| 4 |
-
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 3.0,
|
| 6 |
-
"eval_steps": 500,
|
| 7 |
-
"global_step": 192,
|
| 8 |
-
"is_hyper_param_search": false,
|
| 9 |
-
"is_local_process_zero": true,
|
| 10 |
-
"is_world_process_zero": true,
|
| 11 |
-
"log_history": [
|
| 12 |
-
{
|
| 13 |
-
"epoch": 0.015625,
|
| 14 |
-
"grad_norm": 2.7545292377471924,
|
| 15 |
-
"learning_rate": 0.0,
|
| 16 |
-
"loss": 1.782,
|
| 17 |
-
"step": 1
|
| 18 |
-
},
|
| 19 |
-
{
|
| 20 |
-
"epoch": 0.03125,
|
| 21 |
-
"grad_norm": 2.986503839492798,
|
| 22 |
-
"learning_rate": 4e-05,
|
| 23 |
-
"loss": 1.9094,
|
| 24 |
-
"step": 2
|
| 25 |
-
},
|
| 26 |
-
{
|
| 27 |
-
"epoch": 0.046875,
|
| 28 |
-
"grad_norm": 1.059362530708313,
|
| 29 |
-
"learning_rate": 8e-05,
|
| 30 |
-
"loss": 1.555,
|
| 31 |
-
"step": 3
|
| 32 |
-
},
|
| 33 |
-
{
|
| 34 |
-
"epoch": 0.0625,
|
| 35 |
-
"grad_norm": 0.9862841367721558,
|
| 36 |
-
"learning_rate": 0.00012,
|
| 37 |
-
"loss": 1.5554,
|
| 38 |
-
"step": 4
|
| 39 |
-
},
|
| 40 |
-
{
|
| 41 |
-
"epoch": 0.078125,
|
| 42 |
-
"grad_norm": 1.2146193981170654,
|
| 43 |
-
"learning_rate": 0.00016,
|
| 44 |
-
"loss": 1.5662,
|
| 45 |
-
"step": 5
|
| 46 |
-
},
|
| 47 |
-
{
|
| 48 |
-
"epoch": 0.09375,
|
| 49 |
-
"grad_norm": 0.6501009464263916,
|
| 50 |
-
"learning_rate": 0.0002,
|
| 51 |
-
"loss": 1.4973,
|
| 52 |
-
"step": 6
|
| 53 |
-
},
|
| 54 |
-
{
|
| 55 |
-
"epoch": 0.109375,
|
| 56 |
-
"grad_norm": 0.7994824051856995,
|
| 57 |
-
"learning_rate": 0.00019998588839790777,
|
| 58 |
-
"loss": 1.5113,
|
| 59 |
-
"step": 7
|
| 60 |
-
},
|
| 61 |
-
{
|
| 62 |
-
"epoch": 0.125,
|
| 63 |
-
"grad_norm": 0.6340547204017639,
|
| 64 |
-
"learning_rate": 0.00019994355757437738,
|
| 65 |
-
"loss": 1.4214,
|
| 66 |
-
"step": 8
|
| 67 |
-
},
|
| 68 |
-
{
|
| 69 |
-
"epoch": 0.140625,
|
| 70 |
-
"grad_norm": 0.6426404118537903,
|
| 71 |
-
"learning_rate": 0.00019987301947652352,
|
| 72 |
-
"loss": 1.3852,
|
| 73 |
-
"step": 9
|
| 74 |
-
},
|
| 75 |
-
{
|
| 76 |
-
"epoch": 0.15625,
|
| 77 |
-
"grad_norm": 0.5500874519348145,
|
| 78 |
-
"learning_rate": 0.0001997742940124576,
|
| 79 |
-
"loss": 1.2877,
|
| 80 |
-
"step": 10
|
| 81 |
-
},
|
| 82 |
-
{
|
| 83 |
-
"epoch": 0.171875,
|
| 84 |
-
"grad_norm": 0.5563384294509888,
|
| 85 |
-
"learning_rate": 0.000199647409045669,
|
| 86 |
-
"loss": 1.4758,
|
| 87 |
-
"step": 11
|
| 88 |
-
},
|
| 89 |
-
{
|
| 90 |
-
"epoch": 0.1875,
|
| 91 |
-
"grad_norm": 0.6488623023033142,
|
| 92 |
-
"learning_rate": 0.0001994924003871609,
|
| 93 |
-
"loss": 1.4119,
|
| 94 |
-
"step": 12
|
| 95 |
-
},
|
| 96 |
-
{
|
| 97 |
-
"epoch": 0.203125,
|
| 98 |
-
"grad_norm": 0.5619658827781677,
|
| 99 |
-
"learning_rate": 0.0001993093117853435,
|
| 100 |
-
"loss": 1.2673,
|
| 101 |
-
"step": 13
|
| 102 |
-
},
|
| 103 |
-
{
|
| 104 |
-
"epoch": 0.21875,
|
| 105 |
-
"grad_norm": 0.5723183155059814,
|
| 106 |
-
"learning_rate": 0.00019909819491368676,
|
| 107 |
-
"loss": 1.4025,
|
| 108 |
-
"step": 14
|
| 109 |
-
},
|
| 110 |
-
{
|
| 111 |
-
"epoch": 0.234375,
|
| 112 |
-
"grad_norm": 0.5521570444107056,
|
| 113 |
-
"learning_rate": 0.0001988591093561364,
|
| 114 |
-
"loss": 1.3465,
|
| 115 |
-
"step": 15
|
| 116 |
-
},
|
| 117 |
-
{
|
| 118 |
-
"epoch": 0.25,
|
| 119 |
-
"grad_norm": 0.5407305955886841,
|
| 120 |
-
"learning_rate": 0.00019859212259029752,
|
| 121 |
-
"loss": 1.1943,
|
| 122 |
-
"step": 16
|
| 123 |
-
},
|
| 124 |
-
{
|
| 125 |
-
"epoch": 0.265625,
|
| 126 |
-
"grad_norm": 0.5799192190170288,
|
| 127 |
-
"learning_rate": 0.0001982973099683902,
|
| 128 |
-
"loss": 1.4066,
|
| 129 |
-
"step": 17
|
| 130 |
-
},
|
| 131 |
-
{
|
| 132 |
-
"epoch": 0.28125,
|
| 133 |
-
"grad_norm": 0.5761305689811707,
|
| 134 |
-
"learning_rate": 0.00019797475469598267,
|
| 135 |
-
"loss": 1.3993,
|
| 136 |
-
"step": 18
|
| 137 |
-
},
|
| 138 |
-
{
|
| 139 |
-
"epoch": 0.296875,
|
| 140 |
-
"grad_norm": 0.5504961013793945,
|
| 141 |
-
"learning_rate": 0.00019762454780850806,
|
| 142 |
-
"loss": 1.2544,
|
| 143 |
-
"step": 19
|
| 144 |
-
},
|
| 145 |
-
{
|
| 146 |
-
"epoch": 0.3125,
|
| 147 |
-
"grad_norm": 0.5236067175865173,
|
| 148 |
-
"learning_rate": 0.00019724678814557128,
|
| 149 |
-
"loss": 1.2237,
|
| 150 |
-
"step": 20
|
| 151 |
-
},
|
| 152 |
-
{
|
| 153 |
-
"epoch": 0.328125,
|
| 154 |
-
"grad_norm": 0.5526680946350098,
|
| 155 |
-
"learning_rate": 0.0001968415823230534,
|
| 156 |
-
"loss": 1.2591,
|
| 157 |
-
"step": 21
|
| 158 |
-
},
|
| 159 |
-
{
|
| 160 |
-
"epoch": 0.34375,
|
| 161 |
-
"grad_norm": 0.5238738656044006,
|
| 162 |
-
"learning_rate": 0.00019640904470302097,
|
| 163 |
-
"loss": 1.1508,
|
| 164 |
-
"step": 22
|
| 165 |
-
},
|
| 166 |
-
{
|
| 167 |
-
"epoch": 0.359375,
|
| 168 |
-
"grad_norm": 0.6222432851791382,
|
| 169 |
-
"learning_rate": 0.00019594929736144976,
|
| 170 |
-
"loss": 1.2375,
|
| 171 |
-
"step": 23
|
| 172 |
-
},
|
| 173 |
-
{
|
| 174 |
-
"epoch": 0.375,
|
| 175 |
-
"grad_norm": 0.5575475692749023,
|
| 176 |
-
"learning_rate": 0.00019546247005377065,
|
| 177 |
-
"loss": 1.2426,
|
| 178 |
-
"step": 24
|
| 179 |
-
},
|
| 180 |
-
{
|
| 181 |
-
"epoch": 0.390625,
|
| 182 |
-
"grad_norm": 0.5280503034591675,
|
| 183 |
-
"learning_rate": 0.00019494870017824876,
|
| 184 |
-
"loss": 1.2745,
|
| 185 |
-
"step": 25
|
| 186 |
-
},
|
| 187 |
-
{
|
| 188 |
-
"epoch": 0.40625,
|
| 189 |
-
"grad_norm": 0.4982561469078064,
|
| 190 |
-
"learning_rate": 0.00019440813273720504,
|
| 191 |
-
"loss": 1.2538,
|
| 192 |
-
"step": 26
|
| 193 |
-
},
|
| 194 |
-
{
|
| 195 |
-
"epoch": 0.421875,
|
| 196 |
-
"grad_norm": 0.5352105498313904,
|
| 197 |
-
"learning_rate": 0.0001938409202960922,
|
| 198 |
-
"loss": 1.28,
|
| 199 |
-
"step": 27
|
| 200 |
-
},
|
| 201 |
-
{
|
| 202 |
-
"epoch": 0.4375,
|
| 203 |
-
"grad_norm": 0.5177728533744812,
|
| 204 |
-
"learning_rate": 0.00019324722294043558,
|
| 205 |
-
"loss": 1.3372,
|
| 206 |
-
"step": 28
|
| 207 |
-
},
|
| 208 |
-
{
|
| 209 |
-
"epoch": 0.453125,
|
| 210 |
-
"grad_norm": 0.5144365429878235,
|
| 211 |
-
"learning_rate": 0.00019262720823065216,
|
| 212 |
-
"loss": 1.351,
|
| 213 |
-
"step": 29
|
| 214 |
-
},
|
| 215 |
-
{
|
| 216 |
-
"epoch": 0.46875,
|
| 217 |
-
"grad_norm": 0.4943947196006775,
|
| 218 |
-
"learning_rate": 0.00019198105115475947,
|
| 219 |
-
"loss": 1.1735,
|
| 220 |
-
"step": 30
|
| 221 |
-
},
|
| 222 |
-
{
|
| 223 |
-
"epoch": 0.484375,
|
| 224 |
-
"grad_norm": 0.5117695331573486,
|
| 225 |
-
"learning_rate": 0.00019130893407898834,
|
| 226 |
-
"loss": 1.2778,
|
| 227 |
-
"step": 31
|
| 228 |
-
},
|
| 229 |
-
{
|
| 230 |
-
"epoch": 0.5,
|
| 231 |
-
"grad_norm": 0.5207276940345764,
|
| 232 |
-
"learning_rate": 0.0001906110466963134,
|
| 233 |
-
"loss": 1.3005,
|
| 234 |
-
"step": 32
|
| 235 |
-
},
|
| 236 |
-
{
|
| 237 |
-
"epoch": 0.515625,
|
| 238 |
-
"grad_norm": 0.49616295099258423,
|
| 239 |
-
"learning_rate": 0.00018988758597291577,
|
| 240 |
-
"loss": 1.2386,
|
| 241 |
-
"step": 33
|
| 242 |
-
},
|
| 243 |
-
{
|
| 244 |
-
"epoch": 0.53125,
|
| 245 |
-
"grad_norm": 0.5076295137405396,
|
| 246 |
-
"learning_rate": 0.00018913875609259247,
|
| 247 |
-
"loss": 1.3428,
|
| 248 |
-
"step": 34
|
| 249 |
-
},
|
| 250 |
-
{
|
| 251 |
-
"epoch": 0.546875,
|
| 252 |
-
"grad_norm": 0.5187010169029236,
|
| 253 |
-
"learning_rate": 0.00018836476839912967,
|
| 254 |
-
"loss": 1.2319,
|
| 255 |
-
"step": 35
|
| 256 |
-
},
|
| 257 |
-
{
|
| 258 |
-
"epoch": 0.5625,
|
| 259 |
-
"grad_norm": 0.7806910872459412,
|
| 260 |
-
"learning_rate": 0.00018756584133665448,
|
| 261 |
-
"loss": 1.2131,
|
| 262 |
-
"step": 36
|
| 263 |
-
},
|
| 264 |
-
{
|
| 265 |
-
"epoch": 0.578125,
|
| 266 |
-
"grad_norm": 0.49942177534103394,
|
| 267 |
-
"learning_rate": 0.00018674220038798298,
|
| 268 |
-
"loss": 1.2394,
|
| 269 |
-
"step": 37
|
| 270 |
-
},
|
| 271 |
-
{
|
| 272 |
-
"epoch": 0.59375,
|
| 273 |
-
"grad_norm": 0.5420028567314148,
|
| 274 |
-
"learning_rate": 0.0001858940780109819,
|
| 275 |
-
"loss": 1.2725,
|
| 276 |
-
"step": 38
|
| 277 |
-
},
|
| 278 |
-
{
|
| 279 |
-
"epoch": 0.609375,
|
| 280 |
-
"grad_norm": 0.5082110166549683,
|
| 281 |
-
"learning_rate": 0.00018502171357296144,
|
| 282 |
-
"loss": 1.3452,
|
| 283 |
-
"step": 39
|
| 284 |
-
},
|
| 285 |
-
{
|
| 286 |
-
"epoch": 0.625,
|
| 287 |
-
"grad_norm": 0.5396978855133057,
|
| 288 |
-
"learning_rate": 0.00018412535328311814,
|
| 289 |
-
"loss": 1.2206,
|
| 290 |
-
"step": 40
|
| 291 |
-
},
|
| 292 |
-
{
|
| 293 |
-
"epoch": 0.640625,
|
| 294 |
-
"grad_norm": 0.5082774758338928,
|
| 295 |
-
"learning_rate": 0.00018320525012304685,
|
| 296 |
-
"loss": 1.2709,
|
| 297 |
-
"step": 41
|
| 298 |
-
},
|
| 299 |
-
{
|
| 300 |
-
"epoch": 0.65625,
|
| 301 |
-
"grad_norm": 0.46711206436157227,
|
| 302 |
-
"learning_rate": 0.00018226166377534114,
|
| 303 |
-
"loss": 1.3097,
|
| 304 |
-
"step": 42
|
| 305 |
-
},
|
| 306 |
-
{
|
| 307 |
-
"epoch": 0.671875,
|
| 308 |
-
"grad_norm": 0.5251287221908569,
|
| 309 |
-
"learning_rate": 0.00018129486055030257,
|
| 310 |
-
"loss": 1.4228,
|
| 311 |
-
"step": 43
|
| 312 |
-
},
|
| 313 |
-
{
|
| 314 |
-
"epoch": 0.6875,
|
| 315 |
-
"grad_norm": 0.5274046659469604,
|
| 316 |
-
"learning_rate": 0.00018030511331077945,
|
| 317 |
-
"loss": 1.2037,
|
| 318 |
-
"step": 44
|
| 319 |
-
},
|
| 320 |
-
{
|
| 321 |
-
"epoch": 0.703125,
|
| 322 |
-
"grad_norm": 0.5073964595794678,
|
| 323 |
-
"learning_rate": 0.00017929270139515604,
|
| 324 |
-
"loss": 1.1935,
|
| 325 |
-
"step": 45
|
| 326 |
-
},
|
| 327 |
-
{
|
| 328 |
-
"epoch": 0.71875,
|
| 329 |
-
"grad_norm": 0.4888913035392761,
|
| 330 |
-
"learning_rate": 0.0001782579105385145,
|
| 331 |
-
"loss": 1.2166,
|
| 332 |
-
"step": 46
|
| 333 |
-
},
|
| 334 |
-
{
|
| 335 |
-
"epoch": 0.734375,
|
| 336 |
-
"grad_norm": 0.500054121017456,
|
| 337 |
-
"learning_rate": 0.0001772010327919912,
|
| 338 |
-
"loss": 1.258,
|
| 339 |
-
"step": 47
|
| 340 |
-
},
|
| 341 |
-
{
|
| 342 |
-
"epoch": 0.75,
|
| 343 |
-
"grad_norm": 0.5388707518577576,
|
| 344 |
-
"learning_rate": 0.0001761223664403505,
|
| 345 |
-
"loss": 1.3851,
|
| 346 |
-
"step": 48
|
| 347 |
-
},
|
| 348 |
-
{
|
| 349 |
-
"epoch": 0.765625,
|
| 350 |
-
"grad_norm": 0.5153979063034058,
|
| 351 |
-
"learning_rate": 0.0001750222159177993,
|
| 352 |
-
"loss": 1.1528,
|
| 353 |
-
"step": 49
|
| 354 |
-
},
|
| 355 |
-
{
|
| 356 |
-
"epoch": 0.78125,
|
| 357 |
-
"grad_norm": 0.49915435910224915,
|
| 358 |
-
"learning_rate": 0.00017390089172206592,
|
| 359 |
-
"loss": 1.2669,
|
| 360 |
-
"step": 50
|
| 361 |
-
},
|
| 362 |
-
{
|
| 363 |
-
"epoch": 0.796875,
|
| 364 |
-
"grad_norm": 0.5064976215362549,
|
| 365 |
-
"learning_rate": 0.0001727587103267677,
|
| 366 |
-
"loss": 1.2352,
|
| 367 |
-
"step": 51
|
| 368 |
-
},
|
| 369 |
-
{
|
| 370 |
-
"epoch": 0.8125,
|
| 371 |
-
"grad_norm": 0.5197826623916626,
|
| 372 |
-
"learning_rate": 0.00017159599409209193,
|
| 373 |
-
"loss": 1.3366,
|
| 374 |
-
"step": 52
|
| 375 |
-
},
|
| 376 |
-
{
|
| 377 |
-
"epoch": 0.828125,
|
| 378 |
-
"grad_norm": 0.49064281582832336,
|
| 379 |
-
"learning_rate": 0.0001704130711738157,
|
| 380 |
-
"loss": 1.3363,
|
| 381 |
-
"step": 53
|
| 382 |
-
},
|
| 383 |
-
{
|
| 384 |
-
"epoch": 0.84375,
|
| 385 |
-
"grad_norm": 0.5057505965232849,
|
| 386 |
-
"learning_rate": 0.0001692102754306895,
|
| 387 |
-
"loss": 1.2715,
|
| 388 |
-
"step": 54
|
| 389 |
-
},
|
| 390 |
-
{
|
| 391 |
-
"epoch": 0.859375,
|
| 392 |
-
"grad_norm": 0.49357378482818604,
|
| 393 |
-
"learning_rate": 0.00016798794633021192,
|
| 394 |
-
"loss": 1.2188,
|
| 395 |
-
"step": 55
|
| 396 |
-
},
|
| 397 |
-
{
|
| 398 |
-
"epoch": 0.875,
|
| 399 |
-
"grad_norm": 0.5010667443275452,
|
| 400 |
-
"learning_rate": 0.0001667464288528207,
|
| 401 |
-
"loss": 1.3006,
|
| 402 |
-
"step": 56
|
| 403 |
-
},
|
| 404 |
-
{
|
| 405 |
-
"epoch": 0.890625,
|
| 406 |
-
"grad_norm": 0.5323114991188049,
|
| 407 |
-
"learning_rate": 0.00016548607339452853,
|
| 408 |
-
"loss": 1.4191,
|
| 409 |
-
"step": 57
|
| 410 |
-
},
|
| 411 |
-
{
|
| 412 |
-
"epoch": 0.90625,
|
| 413 |
-
"grad_norm": 0.547682523727417,
|
| 414 |
-
"learning_rate": 0.00016420723566802983,
|
| 415 |
-
"loss": 1.3198,
|
| 416 |
-
"step": 58
|
| 417 |
-
},
|
| 418 |
-
{
|
| 419 |
-
"epoch": 0.921875,
|
| 420 |
-
"grad_norm": 0.5031412839889526,
|
| 421 |
-
"learning_rate": 0.00016291027660230733,
|
| 422 |
-
"loss": 1.269,
|
| 423 |
-
"step": 59
|
| 424 |
-
},
|
| 425 |
-
{
|
| 426 |
-
"epoch": 0.9375,
|
| 427 |
-
"grad_norm": 0.5092846751213074,
|
| 428 |
-
"learning_rate": 0.00016159556224076637,
|
| 429 |
-
"loss": 1.1915,
|
| 430 |
-
"step": 60
|
| 431 |
-
},
|
| 432 |
-
{
|
| 433 |
-
"epoch": 0.953125,
|
| 434 |
-
"grad_norm": 0.560909628868103,
|
| 435 |
-
"learning_rate": 0.00016026346363792567,
|
| 436 |
-
"loss": 1.3038,
|
| 437 |
-
"step": 61
|
| 438 |
-
},
|
| 439 |
-
{
|
| 440 |
-
"epoch": 0.96875,
|
| 441 |
-
"grad_norm": 0.540993869304657,
|
| 442 |
-
"learning_rate": 0.00015891435675469376,
|
| 443 |
-
"loss": 1.4336,
|
| 444 |
-
"step": 62
|
| 445 |
-
},
|
| 446 |
-
{
|
| 447 |
-
"epoch": 0.984375,
|
| 448 |
-
"grad_norm": 0.4856269061565399,
|
| 449 |
-
"learning_rate": 0.000157548622352261,
|
| 450 |
-
"loss": 1.2208,
|
| 451 |
-
"step": 63
|
| 452 |
-
},
|
| 453 |
-
{
|
| 454 |
-
"epoch": 1.0,
|
| 455 |
-
"grad_norm": 0.6747854948043823,
|
| 456 |
-
"learning_rate": 0.00015616664588463647,
|
| 457 |
-
"loss": 1.3273,
|
| 458 |
-
"step": 64
|
| 459 |
-
},
|
| 460 |
-
{
|
| 461 |
-
"epoch": 1.015625,
|
| 462 |
-
"grad_norm": 0.5813027024269104,
|
| 463 |
-
"learning_rate": 0.00015476881738986037,
|
| 464 |
-
"loss": 0.896,
|
| 465 |
-
"step": 65
|
| 466 |
-
},
|
| 467 |
-
{
|
| 468 |
-
"epoch": 1.03125,
|
| 469 |
-
"grad_norm": 0.49314695596694946,
|
| 470 |
-
"learning_rate": 0.00015335553137992285,
|
| 471 |
-
"loss": 0.9917,
|
| 472 |
-
"step": 66
|
| 473 |
-
},
|
| 474 |
-
{
|
| 475 |
-
"epoch": 1.046875,
|
| 476 |
-
"grad_norm": 0.5075877904891968,
|
| 477 |
-
"learning_rate": 0.0001519271867294203,
|
| 478 |
-
"loss": 0.9436,
|
| 479 |
-
"step": 67
|
| 480 |
-
},
|
| 481 |
-
{
|
| 482 |
-
"epoch": 1.0625,
|
| 483 |
-
"grad_norm": 0.6151750087738037,
|
| 484 |
-
"learning_rate": 0.0001504841865629799,
|
| 485 |
-
"loss": 1.0398,
|
| 486 |
-
"step": 68
|
| 487 |
-
},
|
| 488 |
-
{
|
| 489 |
-
"epoch": 1.078125,
|
| 490 |
-
"grad_norm": 0.6225054860115051,
|
| 491 |
-
"learning_rate": 0.0001490269381414849,
|
| 492 |
-
"loss": 0.9602,
|
| 493 |
-
"step": 69
|
| 494 |
-
},
|
| 495 |
-
{
|
| 496 |
-
"epoch": 1.09375,
|
| 497 |
-
"grad_norm": 0.6431002616882324,
|
| 498 |
-
"learning_rate": 0.0001475558527471329,
|
| 499 |
-
"loss": 0.8976,
|
| 500 |
-
"step": 70
|
| 501 |
-
},
|
| 502 |
-
{
|
| 503 |
-
"epoch": 1.109375,
|
| 504 |
-
"grad_norm": 0.6990566253662109,
|
| 505 |
-
"learning_rate": 0.00014607134556735834,
|
| 506 |
-
"loss": 0.8879,
|
| 507 |
-
"step": 71
|
| 508 |
-
},
|
| 509 |
-
{
|
| 510 |
-
"epoch": 1.125,
|
| 511 |
-
"grad_norm": 0.9784147143363953,
|
| 512 |
-
"learning_rate": 0.00014457383557765386,
|
| 513 |
-
"loss": 0.9902,
|
| 514 |
-
"step": 72
|
| 515 |
-
},
|
| 516 |
-
{
|
| 517 |
-
"epoch": 1.140625,
|
| 518 |
-
"grad_norm": 0.6030399799346924,
|
| 519 |
-
"learning_rate": 0.00014306374542332143,
|
| 520 |
-
"loss": 0.94,
|
| 521 |
-
"step": 73
|
| 522 |
-
},
|
| 523 |
-
{
|
| 524 |
-
"epoch": 1.15625,
|
| 525 |
-
"grad_norm": 0.5666849613189697,
|
| 526 |
-
"learning_rate": 0.00014154150130018866,
|
| 527 |
-
"loss": 0.8381,
|
| 528 |
-
"step": 74
|
| 529 |
-
},
|
| 530 |
-
{
|
| 531 |
-
"epoch": 1.171875,
|
| 532 |
-
"grad_norm": 0.626495361328125,
|
| 533 |
-
"learning_rate": 0.00014000753283432266,
|
| 534 |
-
"loss": 0.868,
|
| 535 |
-
"step": 75
|
| 536 |
-
},
|
| 537 |
-
{
|
| 538 |
-
"epoch": 1.1875,
|
| 539 |
-
"grad_norm": 0.5842832922935486,
|
| 540 |
-
"learning_rate": 0.00013846227296077568,
|
| 541 |
-
"loss": 0.8837,
|
| 542 |
-
"step": 76
|
| 543 |
-
},
|
| 544 |
-
{
|
| 545 |
-
"epoch": 1.203125,
|
| 546 |
-
"grad_norm": 0.5995466113090515,
|
| 547 |
-
"learning_rate": 0.000136906157801397,
|
| 548 |
-
"loss": 0.979,
|
| 549 |
-
"step": 77
|
| 550 |
-
},
|
| 551 |
-
{
|
| 552 |
-
"epoch": 1.21875,
|
| 553 |
-
"grad_norm": 0.6081043481826782,
|
| 554 |
-
"learning_rate": 0.0001353396265417454,
|
| 555 |
-
"loss": 0.882,
|
| 556 |
-
"step": 78
|
| 557 |
-
},
|
| 558 |
-
{
|
| 559 |
-
"epoch": 1.234375,
|
| 560 |
-
"grad_norm": 0.5832274556159973,
|
| 561 |
-
"learning_rate": 0.00013376312130713687,
|
| 562 |
-
"loss": 0.9649,
|
| 563 |
-
"step": 79
|
| 564 |
-
},
|
| 565 |
-
{
|
| 566 |
-
"epoch": 1.25,
|
| 567 |
-
"grad_norm": 0.6251536011695862,
|
| 568 |
-
"learning_rate": 0.0001321770870378628,
|
| 569 |
-
"loss": 0.917,
|
| 570 |
-
"step": 80
|
| 571 |
-
},
|
| 572 |
-
{
|
| 573 |
-
"epoch": 1.265625,
|
| 574 |
-
"grad_norm": 0.6604623794555664,
|
| 575 |
-
"learning_rate": 0.00013058197136361343,
|
| 576 |
-
"loss": 0.9478,
|
| 577 |
-
"step": 81
|
| 578 |
-
},
|
| 579 |
-
{
|
| 580 |
-
"epoch": 1.28125,
|
| 581 |
-
"grad_norm": 0.6800036430358887,
|
| 582 |
-
"learning_rate": 0.00012897822447714247,
|
| 583 |
-
"loss": 0.8825,
|
| 584 |
-
"step": 82
|
| 585 |
-
},
|
| 586 |
-
{
|
| 587 |
-
"epoch": 1.296875,
|
| 588 |
-
"grad_norm": 0.709237813949585,
|
| 589 |
-
"learning_rate": 0.0001273662990072083,
|
| 590 |
-
"loss": 0.9113,
|
| 591 |
-
"step": 83
|
| 592 |
-
},
|
| 593 |
-
{
|
| 594 |
-
"epoch": 1.3125,
|
| 595 |
-
"grad_norm": 0.6891036629676819,
|
| 596 |
-
"learning_rate": 0.00012574664989082758,
|
| 597 |
-
"loss": 0.9004,
|
| 598 |
-
"step": 84
|
| 599 |
-
},
|
| 600 |
-
{
|
| 601 |
-
"epoch": 1.328125,
|
| 602 |
-
"grad_norm": 0.5835941433906555,
|
| 603 |
-
"learning_rate": 0.0001241197342448775,
|
| 604 |
-
"loss": 0.9267,
|
| 605 |
-
"step": 85
|
| 606 |
-
},
|
| 607 |
-
{
|
| 608 |
-
"epoch": 1.34375,
|
| 609 |
-
"grad_norm": 0.5817910432815552,
|
| 610 |
-
"learning_rate": 0.0001224860112370828,
|
| 611 |
-
"loss": 0.8757,
|
| 612 |
-
"step": 86
|
| 613 |
-
},
|
| 614 |
-
{
|
| 615 |
-
"epoch": 1.359375,
|
| 616 |
-
"grad_norm": 0.6036533117294312,
|
| 617 |
-
"learning_rate": 0.00012084594195642367,
|
| 618 |
-
"loss": 0.8987,
|
| 619 |
-
"step": 87
|
| 620 |
-
},
|
| 621 |
-
{
|
| 622 |
-
"epoch": 1.375,
|
| 623 |
-
"grad_norm": 0.623345136642456,
|
| 624 |
-
"learning_rate": 0.00011919998928300203,
|
| 625 |
-
"loss": 0.9115,
|
| 626 |
-
"step": 88
|
| 627 |
-
},
|
| 628 |
-
{
|
| 629 |
-
"epoch": 1.390625,
|
| 630 |
-
"grad_norm": 0.6265957951545715,
|
| 631 |
-
"learning_rate": 0.00011754861775740162,
|
| 632 |
-
"loss": 0.874,
|
| 633 |
-
"step": 89
|
| 634 |
-
},
|
| 635 |
-
{
|
| 636 |
-
"epoch": 1.40625,
|
| 637 |
-
"grad_norm": 0.6529715061187744,
|
| 638 |
-
"learning_rate": 0.00011589229344957999,
|
| 639 |
-
"loss": 0.8702,
|
| 640 |
-
"step": 90
|
| 641 |
-
},
|
| 642 |
-
{
|
| 643 |
-
"epoch": 1.421875,
|
| 644 |
-
"grad_norm": 0.6559955477714539,
|
| 645 |
-
"learning_rate": 0.00011423148382732853,
|
| 646 |
-
"loss": 0.9008,
|
| 647 |
-
"step": 91
|
| 648 |
-
},
|
| 649 |
-
{
|
| 650 |
-
"epoch": 1.4375,
|
| 651 |
-
"grad_norm": 0.6313908100128174,
|
| 652 |
-
"learning_rate": 0.00011256665762433798,
|
| 653 |
-
"loss": 0.942,
|
| 654 |
-
"step": 92
|
| 655 |
-
},
|
| 656 |
-
{
|
| 657 |
-
"epoch": 1.453125,
|
| 658 |
-
"grad_norm": 0.6203813552856445,
|
| 659 |
-
"learning_rate": 0.00011089828470790693,
|
| 660 |
-
"loss": 0.9118,
|
| 661 |
-
"step": 93
|
| 662 |
-
},
|
| 663 |
-
{
|
| 664 |
-
"epoch": 1.46875,
|
| 665 |
-
"grad_norm": 0.7021353244781494,
|
| 666 |
-
"learning_rate": 0.00010922683594633021,
|
| 667 |
-
"loss": 0.7378,
|
| 668 |
-
"step": 94
|
| 669 |
-
},
|
| 670 |
-
{
|
| 671 |
-
"epoch": 1.484375,
|
| 672 |
-
"grad_norm": 0.6011958122253418,
|
| 673 |
-
"learning_rate": 0.00010755278307600458,
|
| 674 |
-
"loss": 0.8333,
|
| 675 |
-
"step": 95
|
| 676 |
-
},
|
| 677 |
-
{
|
| 678 |
-
"epoch": 1.5,
|
| 679 |
-
"grad_norm": 0.7509216070175171,
|
| 680 |
-
"learning_rate": 0.0001058765985682898,
|
| 681 |
-
"loss": 0.9437,
|
| 682 |
-
"step": 96
|
| 683 |
-
},
|
| 684 |
-
{
|
| 685 |
-
"epoch": 1.515625,
|
| 686 |
-
"grad_norm": 0.638576865196228,
|
| 687 |
-
"learning_rate": 0.00010419875549616196,
|
| 688 |
-
"loss": 0.9436,
|
| 689 |
-
"step": 97
|
| 690 |
-
},
|
| 691 |
-
{
|
| 692 |
-
"epoch": 1.53125,
|
| 693 |
-
"grad_norm": 0.6763246059417725,
|
| 694 |
-
"learning_rate": 0.00010251972740069724,
|
| 695 |
-
"loss": 0.9515,
|
| 696 |
-
"step": 98
|
| 697 |
-
},
|
| 698 |
-
{
|
| 699 |
-
"epoch": 1.546875,
|
| 700 |
-
"grad_norm": 0.6507485508918762,
|
| 701 |
-
"learning_rate": 0.00010083998815742335,
|
| 702 |
-
"loss": 0.9399,
|
| 703 |
-
"step": 99
|
| 704 |
-
},
|
| 705 |
-
{
|
| 706 |
-
"epoch": 1.5625,
|
| 707 |
-
"grad_norm": 0.615294337272644,
|
| 708 |
-
"learning_rate": 9.916001184257668e-05,
|
| 709 |
-
"loss": 0.9096,
|
| 710 |
-
"step": 100
|
| 711 |
-
},
|
| 712 |
-
{
|
| 713 |
-
"epoch": 1.578125,
|
| 714 |
-
"grad_norm": 0.580854594707489,
|
| 715 |
-
"learning_rate": 9.748027259930276e-05,
|
| 716 |
-
"loss": 1.0188,
|
| 717 |
-
"step": 101
|
| 718 |
-
},
|
| 719 |
-
{
|
| 720 |
-
"epoch": 1.59375,
|
| 721 |
-
"grad_norm": 0.5845345258712769,
|
| 722 |
-
"learning_rate": 9.580124450383803e-05,
|
| 723 |
-
"loss": 0.8994,
|
| 724 |
-
"step": 102
|
| 725 |
-
},
|
| 726 |
-
{
|
| 727 |
-
"epoch": 1.609375,
|
| 728 |
-
"grad_norm": 0.6133562922477722,
|
| 729 |
-
"learning_rate": 9.412340143171024e-05,
|
| 730 |
-
"loss": 0.8916,
|
| 731 |
-
"step": 103
|
| 732 |
-
},
|
| 733 |
-
{
|
| 734 |
-
"epoch": 1.625,
|
| 735 |
-
"grad_norm": 0.6874757409095764,
|
| 736 |
-
"learning_rate": 9.244721692399545e-05,
|
| 737 |
-
"loss": 0.9934,
|
| 738 |
-
"step": 104
|
| 739 |
-
},
|
| 740 |
-
{
|
| 741 |
-
"epoch": 1.640625,
|
| 742 |
-
"grad_norm": 0.5951738357543945,
|
| 743 |
-
"learning_rate": 9.077316405366981e-05,
|
| 744 |
-
"loss": 0.8346,
|
| 745 |
-
"step": 105
|
| 746 |
-
},
|
| 747 |
-
{
|
| 748 |
-
"epoch": 1.65625,
|
| 749 |
-
"grad_norm": 0.6542007923126221,
|
| 750 |
-
"learning_rate": 8.910171529209305e-05,
|
| 751 |
-
"loss": 0.883,
|
| 752 |
-
"step": 106
|
| 753 |
-
},
|
| 754 |
-
{
|
| 755 |
-
"epoch": 1.671875,
|
| 756 |
-
"grad_norm": 0.6282486915588379,
|
| 757 |
-
"learning_rate": 8.743334237566202e-05,
|
| 758 |
-
"loss": 0.8681,
|
| 759 |
-
"step": 107
|
| 760 |
-
},
|
| 761 |
-
{
|
| 762 |
-
"epoch": 1.6875,
|
| 763 |
-
"grad_norm": 0.6178871989250183,
|
| 764 |
-
"learning_rate": 8.57685161726715e-05,
|
| 765 |
-
"loss": 0.8562,
|
| 766 |
-
"step": 108
|
| 767 |
-
},
|
| 768 |
-
{
|
| 769 |
-
"epoch": 1.703125,
|
| 770 |
-
"grad_norm": 0.6271396279335022,
|
| 771 |
-
"learning_rate": 8.410770655042003e-05,
|
| 772 |
-
"loss": 0.8078,
|
| 773 |
-
"step": 109
|
| 774 |
-
},
|
| 775 |
-
{
|
| 776 |
-
"epoch": 1.71875,
|
| 777 |
-
"grad_norm": 0.6065046191215515,
|
| 778 |
-
"learning_rate": 8.245138224259841e-05,
|
| 779 |
-
"loss": 0.8439,
|
| 780 |
-
"step": 110
|
| 781 |
-
},
|
| 782 |
-
{
|
| 783 |
-
"epoch": 1.734375,
|
| 784 |
-
"grad_norm": 0.6628541350364685,
|
| 785 |
-
"learning_rate": 8.0800010716998e-05,
|
| 786 |
-
"loss": 0.93,
|
| 787 |
-
"step": 111
|
| 788 |
-
},
|
| 789 |
-
{
|
| 790 |
-
"epoch": 1.75,
|
| 791 |
-
"grad_norm": 0.6493437886238098,
|
| 792 |
-
"learning_rate": 7.915405804357633e-05,
|
| 793 |
-
"loss": 0.8781,
|
| 794 |
-
"step": 112
|
| 795 |
-
},
|
| 796 |
-
{
|
| 797 |
-
"epoch": 1.765625,
|
| 798 |
-
"grad_norm": 0.6871931552886963,
|
| 799 |
-
"learning_rate": 7.751398876291725e-05,
|
| 800 |
-
"loss": 0.8897,
|
| 801 |
-
"step": 113
|
| 802 |
-
},
|
| 803 |
-
{
|
| 804 |
-
"epoch": 1.78125,
|
| 805 |
-
"grad_norm": 0.6025776863098145,
|
| 806 |
-
"learning_rate": 7.588026575512251e-05,
|
| 807 |
-
"loss": 0.8177,
|
| 808 |
-
"step": 114
|
| 809 |
-
},
|
| 810 |
-
{
|
| 811 |
-
"epoch": 1.796875,
|
| 812 |
-
"grad_norm": 0.6263808608055115,
|
| 813 |
-
"learning_rate": 7.425335010917244e-05,
|
| 814 |
-
"loss": 0.8712,
|
| 815 |
-
"step": 115
|
| 816 |
-
},
|
| 817 |
-
{
|
| 818 |
-
"epoch": 1.8125,
|
| 819 |
-
"grad_norm": 0.6137387752532959,
|
| 820 |
-
"learning_rate": 7.263370099279172e-05,
|
| 821 |
-
"loss": 0.8607,
|
| 822 |
-
"step": 116
|
| 823 |
-
},
|
| 824 |
-
{
|
| 825 |
-
"epoch": 1.828125,
|
| 826 |
-
"grad_norm": 0.6260087490081787,
|
| 827 |
-
"learning_rate": 7.102177552285753e-05,
|
| 828 |
-
"loss": 0.9137,
|
| 829 |
-
"step": 117
|
| 830 |
-
},
|
| 831 |
-
{
|
| 832 |
-
"epoch": 1.84375,
|
| 833 |
-
"grad_norm": 0.6399638056755066,
|
| 834 |
-
"learning_rate": 6.941802863638659e-05,
|
| 835 |
-
"loss": 0.9687,
|
| 836 |
-
"step": 118
|
| 837 |
-
},
|
| 838 |
-
{
|
| 839 |
-
"epoch": 1.859375,
|
| 840 |
-
"grad_norm": 0.6690117120742798,
|
| 841 |
-
"learning_rate": 6.782291296213722e-05,
|
| 842 |
-
"loss": 0.9625,
|
| 843 |
-
"step": 119
|
| 844 |
-
},
|
| 845 |
-
{
|
| 846 |
-
"epoch": 1.875,
|
| 847 |
-
"grad_norm": 0.6296346783638,
|
| 848 |
-
"learning_rate": 6.623687869286313e-05,
|
| 849 |
-
"loss": 0.8872,
|
| 850 |
-
"step": 120
|
| 851 |
-
},
|
| 852 |
-
{
|
| 853 |
-
"epoch": 1.890625,
|
| 854 |
-
"grad_norm": 0.5934789776802063,
|
| 855 |
-
"learning_rate": 6.466037345825462e-05,
|
| 856 |
-
"loss": 0.7974,
|
| 857 |
-
"step": 121
|
| 858 |
-
},
|
| 859 |
-
{
|
| 860 |
-
"epoch": 1.90625,
|
| 861 |
-
"grad_norm": 0.6167766451835632,
|
| 862 |
-
"learning_rate": 6.309384219860301e-05,
|
| 863 |
-
"loss": 0.8482,
|
| 864 |
-
"step": 122
|
| 865 |
-
},
|
| 866 |
-
{
|
| 867 |
-
"epoch": 1.921875,
|
| 868 |
-
"grad_norm": 0.6420045495033264,
|
| 869 |
-
"learning_rate": 6.153772703922433e-05,
|
| 870 |
-
"loss": 0.9149,
|
| 871 |
-
"step": 123
|
| 872 |
-
},
|
| 873 |
-
{
|
| 874 |
-
"epoch": 1.9375,
|
| 875 |
-
"grad_norm": 0.6557563543319702,
|
| 876 |
-
"learning_rate": 5.999246716567737e-05,
|
| 877 |
-
"loss": 0.9324,
|
| 878 |
-
"step": 124
|
| 879 |
-
},
|
| 880 |
-
{
|
| 881 |
-
"epoch": 1.953125,
|
| 882 |
-
"grad_norm": 0.6023949980735779,
|
| 883 |
-
"learning_rate": 5.845849869981137e-05,
|
| 884 |
-
"loss": 0.8399,
|
| 885 |
-
"step": 125
|
| 886 |
-
},
|
| 887 |
-
{
|
| 888 |
-
"epoch": 1.96875,
|
| 889 |
-
"grad_norm": 0.6570467352867126,
|
| 890 |
-
"learning_rate": 5.693625457667862e-05,
|
| 891 |
-
"loss": 0.9289,
|
| 892 |
-
"step": 126
|
| 893 |
-
},
|
| 894 |
-
{
|
| 895 |
-
"epoch": 1.984375,
|
| 896 |
-
"grad_norm": 0.6379124522209167,
|
| 897 |
-
"learning_rate": 5.542616442234618e-05,
|
| 898 |
-
"loss": 0.9081,
|
| 899 |
-
"step": 127
|
| 900 |
-
},
|
| 901 |
-
{
|
| 902 |
-
"epoch": 2.0,
|
| 903 |
-
"grad_norm": 0.7978578209877014,
|
| 904 |
-
"learning_rate": 5.392865443264163e-05,
|
| 905 |
-
"loss": 0.9279,
|
| 906 |
-
"step": 128
|
| 907 |
-
},
|
| 908 |
-
{
|
| 909 |
-
"epoch": 2.015625,
|
| 910 |
-
"grad_norm": 0.7730198502540588,
|
| 911 |
-
"learning_rate": 5.244414725286717e-05,
|
| 912 |
-
"loss": 0.6409,
|
| 913 |
-
"step": 129
|
| 914 |
-
},
|
| 915 |
-
{
|
| 916 |
-
"epoch": 2.03125,
|
| 917 |
-
"grad_norm": 0.7514629364013672,
|
| 918 |
-
"learning_rate": 5.0973061858515145e-05,
|
| 919 |
-
"loss": 0.6736,
|
| 920 |
-
"step": 130
|
| 921 |
-
},
|
| 922 |
-
{
|
| 923 |
-
"epoch": 2.046875,
|
| 924 |
-
"grad_norm": 0.6814653873443604,
|
| 925 |
-
"learning_rate": 4.9515813437020144e-05,
|
| 926 |
-
"loss": 0.6016,
|
| 927 |
-
"step": 131
|
| 928 |
-
},
|
| 929 |
-
{
|
| 930 |
-
"epoch": 2.0625,
|
| 931 |
-
"grad_norm": 0.8626322150230408,
|
| 932 |
-
"learning_rate": 4.807281327057972e-05,
|
| 933 |
-
"loss": 0.5432,
|
| 934 |
-
"step": 132
|
| 935 |
-
},
|
| 936 |
-
{
|
| 937 |
-
"epoch": 2.078125,
|
| 938 |
-
"grad_norm": 1.3772077560424805,
|
| 939 |
-
"learning_rate": 4.6644468620077174e-05,
|
| 940 |
-
"loss": 0.6443,
|
| 941 |
-
"step": 133
|
| 942 |
-
},
|
| 943 |
-
{
|
| 944 |
-
"epoch": 2.09375,
|
| 945 |
-
"grad_norm": 1.0154165029525757,
|
| 946 |
-
"learning_rate": 4.523118261013969e-05,
|
| 947 |
-
"loss": 0.5985,
|
| 948 |
-
"step": 134
|
| 949 |
-
},
|
| 950 |
-
{
|
| 951 |
-
"epoch": 2.109375,
|
| 952 |
-
"grad_norm": 0.7242003679275513,
|
| 953 |
-
"learning_rate": 4.383335411536357e-05,
|
| 954 |
-
"loss": 0.5446,
|
| 955 |
-
"step": 135
|
| 956 |
-
},
|
| 957 |
-
{
|
| 958 |
-
"epoch": 2.125,
|
| 959 |
-
"grad_norm": 0.7211042046546936,
|
| 960 |
-
"learning_rate": 4.2451377647738985e-05,
|
| 961 |
-
"loss": 0.5153,
|
| 962 |
-
"step": 136
|
| 963 |
-
},
|
| 964 |
-
{
|
| 965 |
-
"epoch": 2.140625,
|
| 966 |
-
"grad_norm": 0.7623264193534851,
|
| 967 |
-
"learning_rate": 4.108564324530626e-05,
|
| 968 |
-
"loss": 0.5706,
|
| 969 |
-
"step": 137
|
| 970 |
-
},
|
| 971 |
-
{
|
| 972 |
-
"epoch": 2.15625,
|
| 973 |
-
"grad_norm": 0.7787522077560425,
|
| 974 |
-
"learning_rate": 3.973653636207437e-05,
|
| 975 |
-
"loss": 0.666,
|
| 976 |
-
"step": 138
|
| 977 |
-
},
|
| 978 |
-
{
|
| 979 |
-
"epoch": 2.171875,
|
| 980 |
-
"grad_norm": 0.6728441119194031,
|
| 981 |
-
"learning_rate": 3.840443775923365e-05,
|
| 982 |
-
"loss": 0.5425,
|
| 983 |
-
"step": 139
|
| 984 |
-
},
|
| 985 |
-
{
|
| 986 |
-
"epoch": 2.1875,
|
| 987 |
-
"grad_norm": 0.7324855327606201,
|
| 988 |
-
"learning_rate": 3.70897233976927e-05,
|
| 989 |
-
"loss": 0.5939,
|
| 990 |
-
"step": 140
|
| 991 |
-
},
|
| 992 |
-
{
|
| 993 |
-
"epoch": 2.203125,
|
| 994 |
-
"grad_norm": 0.7769740223884583,
|
| 995 |
-
"learning_rate": 3.5792764331970185e-05,
|
| 996 |
-
"loss": 0.6202,
|
| 997 |
-
"step": 141
|
| 998 |
-
},
|
| 999 |
-
{
|
| 1000 |
-
"epoch": 2.21875,
|
| 1001 |
-
"grad_norm": 0.767734169960022,
|
| 1002 |
-
"learning_rate": 3.45139266054715e-05,
|
| 1003 |
-
"loss": 0.5615,
|
| 1004 |
-
"step": 142
|
| 1005 |
-
},
|
| 1006 |
-
{
|
| 1007 |
-
"epoch": 2.234375,
|
| 1008 |
-
"grad_norm": 0.751020073890686,
|
| 1009 |
-
"learning_rate": 3.325357114717933e-05,
|
| 1010 |
-
"loss": 0.575,
|
| 1011 |
-
"step": 143
|
| 1012 |
-
},
|
| 1013 |
-
{
|
| 1014 |
-
"epoch": 2.25,
|
| 1015 |
-
"grad_norm": 0.8365825414657593,
|
| 1016 |
-
"learning_rate": 3.2012053669788135e-05,
|
| 1017 |
-
"loss": 0.601,
|
| 1018 |
-
"step": 144
|
| 1019 |
-
},
|
| 1020 |
-
{
|
| 1021 |
-
"epoch": 2.265625,
|
| 1022 |
-
"grad_norm": 0.8232370615005493,
|
| 1023 |
-
"learning_rate": 3.078972456931053e-05,
|
| 1024 |
-
"loss": 0.5701,
|
| 1025 |
-
"step": 145
|
| 1026 |
-
},
|
| 1027 |
-
{
|
| 1028 |
-
"epoch": 2.28125,
|
| 1029 |
-
"grad_norm": 0.8521618843078613,
|
| 1030 |
-
"learning_rate": 2.9586928826184325e-05,
|
| 1031 |
-
"loss": 0.5909,
|
| 1032 |
-
"step": 146
|
| 1033 |
-
},
|
| 1034 |
-
{
|
| 1035 |
-
"epoch": 2.296875,
|
| 1036 |
-
"grad_norm": 0.7347127795219421,
|
| 1037 |
-
"learning_rate": 2.8404005907908082e-05,
|
| 1038 |
-
"loss": 0.5318,
|
| 1039 |
-
"step": 147
|
| 1040 |
-
},
|
| 1041 |
-
{
|
| 1042 |
-
"epoch": 2.3125,
|
| 1043 |
-
"grad_norm": 0.7891002893447876,
|
| 1044 |
-
"learning_rate": 2.724128967323234e-05,
|
| 1045 |
-
"loss": 0.6265,
|
| 1046 |
-
"step": 148
|
| 1047 |
-
},
|
| 1048 |
-
{
|
| 1049 |
-
"epoch": 2.328125,
|
| 1050 |
-
"grad_norm": 0.7826504111289978,
|
| 1051 |
-
"learning_rate": 2.6099108277934103e-05,
|
| 1052 |
-
"loss": 0.5961,
|
| 1053 |
-
"step": 149
|
| 1054 |
-
},
|
| 1055 |
-
{
|
| 1056 |
-
"epoch": 2.34375,
|
| 1057 |
-
"grad_norm": 0.7414980530738831,
|
| 1058 |
-
"learning_rate": 2.497778408220073e-05,
|
| 1059 |
-
"loss": 0.582,
|
| 1060 |
-
"step": 150
|
| 1061 |
-
},
|
| 1062 |
-
{
|
| 1063 |
-
"epoch": 2.359375,
|
| 1064 |
-
"grad_norm": 0.8048492074012756,
|
| 1065 |
-
"learning_rate": 2.3877633559649505e-05,
|
| 1066 |
-
"loss": 0.5838,
|
| 1067 |
-
"step": 151
|
| 1068 |
-
},
|
| 1069 |
-
{
|
| 1070 |
-
"epoch": 2.375,
|
| 1071 |
-
"grad_norm": 0.7372992634773254,
|
| 1072 |
-
"learning_rate": 2.2798967208008804e-05,
|
| 1073 |
-
"loss": 0.5877,
|
| 1074 |
-
"step": 152
|
| 1075 |
-
},
|
| 1076 |
-
{
|
| 1077 |
-
"epoch": 2.390625,
|
| 1078 |
-
"grad_norm": 0.7260457873344421,
|
| 1079 |
-
"learning_rate": 2.1742089461485504e-05,
|
| 1080 |
-
"loss": 0.5532,
|
| 1081 |
-
"step": 153
|
| 1082 |
-
},
|
| 1083 |
-
{
|
| 1084 |
-
"epoch": 2.40625,
|
| 1085 |
-
"grad_norm": 0.7830657362937927,
|
| 1086 |
-
"learning_rate": 2.070729860484396e-05,
|
| 1087 |
-
"loss": 0.5761,
|
| 1088 |
-
"step": 154
|
| 1089 |
-
},
|
| 1090 |
-
{
|
| 1091 |
-
"epoch": 2.421875,
|
| 1092 |
-
"grad_norm": 0.7378799915313721,
|
| 1093 |
-
"learning_rate": 1.9694886689220594e-05,
|
| 1094 |
-
"loss": 0.5386,
|
| 1095 |
-
"step": 155
|
| 1096 |
-
},
|
| 1097 |
-
{
|
| 1098 |
-
"epoch": 2.4375,
|
| 1099 |
-
"grad_norm": 0.7603411078453064,
|
| 1100 |
-
"learning_rate": 1.870513944969743e-05,
|
| 1101 |
-
"loss": 0.5384,
|
| 1102 |
-
"step": 156
|
| 1103 |
-
},
|
| 1104 |
-
{
|
| 1105 |
-
"epoch": 2.453125,
|
| 1106 |
-
"grad_norm": 0.7275040745735168,
|
| 1107 |
-
"learning_rate": 1.7738336224658882e-05,
|
| 1108 |
-
"loss": 0.5791,
|
| 1109 |
-
"step": 157
|
| 1110 |
-
},
|
| 1111 |
-
{
|
| 1112 |
-
"epoch": 2.46875,
|
| 1113 |
-
"grad_norm": 0.7369095683097839,
|
| 1114 |
-
"learning_rate": 1.6794749876953188e-05,
|
| 1115 |
-
"loss": 0.5816,
|
| 1116 |
-
"step": 158
|
| 1117 |
-
},
|
| 1118 |
-
{
|
| 1119 |
-
"epoch": 2.484375,
|
| 1120 |
-
"grad_norm": 0.741500735282898,
|
| 1121 |
-
"learning_rate": 1.587464671688187e-05,
|
| 1122 |
-
"loss": 0.5534,
|
| 1123 |
-
"step": 159
|
| 1124 |
-
},
|
| 1125 |
-
{
|
| 1126 |
-
"epoch": 2.5,
|
| 1127 |
-
"grad_norm": 0.6802282929420471,
|
| 1128 |
-
"learning_rate": 1.4978286427038601e-05,
|
| 1129 |
-
"loss": 0.5091,
|
| 1130 |
-
"step": 160
|
| 1131 |
-
},
|
| 1132 |
-
{
|
| 1133 |
-
"epoch": 2.515625,
|
| 1134 |
-
"grad_norm": 0.7638409733772278,
|
| 1135 |
-
"learning_rate": 1.4105921989018111e-05,
|
| 1136 |
-
"loss": 0.6298,
|
| 1137 |
-
"step": 161
|
| 1138 |
-
},
|
| 1139 |
-
{
|
| 1140 |
-
"epoch": 2.53125,
|
| 1141 |
-
"grad_norm": 0.7683125138282776,
|
| 1142 |
-
"learning_rate": 1.325779961201703e-05,
|
| 1143 |
-
"loss": 0.551,
|
| 1144 |
-
"step": 162
|
| 1145 |
-
},
|
| 1146 |
-
{
|
| 1147 |
-
"epoch": 2.546875,
|
| 1148 |
-
"grad_norm": 0.7749364376068115,
|
| 1149 |
-
"learning_rate": 1.2434158663345552e-05,
|
| 1150 |
-
"loss": 0.5891,
|
| 1151 |
-
"step": 163
|
| 1152 |
-
},
|
| 1153 |
-
{
|
| 1154 |
-
"epoch": 2.5625,
|
| 1155 |
-
"grad_norm": 0.6828547716140747,
|
| 1156 |
-
"learning_rate": 1.1635231600870333e-05,
|
| 1157 |
-
"loss": 0.5396,
|
| 1158 |
-
"step": 164
|
| 1159 |
-
},
|
| 1160 |
-
{
|
| 1161 |
-
"epoch": 2.578125,
|
| 1162 |
-
"grad_norm": 0.7164223194122314,
|
| 1163 |
-
"learning_rate": 1.086124390740757e-05,
|
| 1164 |
-
"loss": 0.5755,
|
| 1165 |
-
"step": 165
|
| 1166 |
-
},
|
| 1167 |
-
{
|
| 1168 |
-
"epoch": 2.59375,
|
| 1169 |
-
"grad_norm": 0.7504003643989563,
|
| 1170 |
-
"learning_rate": 1.0112414027084261e-05,
|
| 1171 |
-
"loss": 0.6454,
|
| 1172 |
-
"step": 166
|
| 1173 |
-
},
|
| 1174 |
-
{
|
| 1175 |
-
"epoch": 2.609375,
|
| 1176 |
-
"grad_norm": 0.7125520706176758,
|
| 1177 |
-
"learning_rate": 9.388953303686588e-06,
|
| 1178 |
-
"loss": 0.5439,
|
| 1179 |
-
"step": 167
|
| 1180 |
-
},
|
| 1181 |
-
{
|
| 1182 |
-
"epoch": 2.625,
|
| 1183 |
-
"grad_norm": 0.7042016386985779,
|
| 1184 |
-
"learning_rate": 8.691065921011687e-06,
|
| 1185 |
-
"loss": 0.5675,
|
| 1186 |
-
"step": 168
|
| 1187 |
-
},
|
| 1188 |
-
{
|
| 1189 |
-
"epoch": 2.640625,
|
| 1190 |
-
"grad_norm": 0.7672927975654602,
|
| 1191 |
-
"learning_rate": 8.018948845240538e-06,
|
| 1192 |
-
"loss": 0.5189,
|
| 1193 |
-
"step": 169
|
| 1194 |
-
},
|
| 1195 |
-
{
|
| 1196 |
-
"epoch": 2.65625,
|
| 1197 |
-
"grad_norm": 0.701722264289856,
|
| 1198 |
-
"learning_rate": 7.372791769347842e-06,
|
| 1199 |
-
"loss": 0.5917,
|
| 1200 |
-
"step": 170
|
| 1201 |
-
},
|
| 1202 |
-
{
|
| 1203 |
-
"epoch": 2.671875,
|
| 1204 |
-
"grad_norm": 0.7036768198013306,
|
| 1205 |
-
"learning_rate": 6.75277705956443e-06,
|
| 1206 |
-
"loss": 0.5691,
|
| 1207 |
-
"step": 171
|
| 1208 |
-
},
|
| 1209 |
-
{
|
| 1210 |
-
"epoch": 2.6875,
|
| 1211 |
-
"grad_norm": 0.7126287817955017,
|
| 1212 |
-
"learning_rate": 6.159079703907822e-06,
|
| 1213 |
-
"loss": 0.5656,
|
| 1214 |
-
"step": 172
|
| 1215 |
-
},
|
| 1216 |
-
{
|
| 1217 |
-
"epoch": 2.703125,
|
| 1218 |
-
"grad_norm": 0.7400851249694824,
|
| 1219 |
-
"learning_rate": 5.59186726279497e-06,
|
| 1220 |
-
"loss": 0.573,
|
| 1221 |
-
"step": 173
|
| 1222 |
-
},
|
| 1223 |
-
{
|
| 1224 |
-
"epoch": 2.71875,
|
| 1225 |
-
"grad_norm": 0.7629361152648926,
|
| 1226 |
-
"learning_rate": 5.051299821751254e-06,
|
| 1227 |
-
"loss": 0.5996,
|
| 1228 |
-
"step": 174
|
| 1229 |
-
},
|
| 1230 |
-
{
|
| 1231 |
-
"epoch": 2.734375,
|
| 1232 |
-
"grad_norm": 0.7034224271774292,
|
| 1233 |
-
"learning_rate": 4.537529946229368e-06,
|
| 1234 |
-
"loss": 0.5706,
|
| 1235 |
-
"step": 175
|
| 1236 |
-
},
|
| 1237 |
-
{
|
| 1238 |
-
"epoch": 2.75,
|
| 1239 |
-
"grad_norm": 0.7580721974372864,
|
| 1240 |
-
"learning_rate": 4.050702638550275e-06,
|
| 1241 |
-
"loss": 0.5697,
|
| 1242 |
-
"step": 176
|
| 1243 |
-
},
|
| 1244 |
-
{
|
| 1245 |
-
"epoch": 2.765625,
|
| 1246 |
-
"grad_norm": 0.7541771531105042,
|
| 1247 |
-
"learning_rate": 3.590955296979037e-06,
|
| 1248 |
-
"loss": 0.5489,
|
| 1249 |
-
"step": 177
|
| 1250 |
-
},
|
| 1251 |
-
{
|
| 1252 |
-
"epoch": 2.78125,
|
| 1253 |
-
"grad_norm": 0.7310436964035034,
|
| 1254 |
-
"learning_rate": 3.1584176769466346e-06,
|
| 1255 |
-
"loss": 0.5879,
|
| 1256 |
-
"step": 178
|
| 1257 |
-
},
|
| 1258 |
-
{
|
| 1259 |
-
"epoch": 2.796875,
|
| 1260 |
-
"grad_norm": 0.7326951622962952,
|
| 1261 |
-
"learning_rate": 2.7532118544287276e-06,
|
| 1262 |
-
"loss": 0.5475,
|
| 1263 |
-
"step": 179
|
| 1264 |
-
},
|
| 1265 |
-
{
|
| 1266 |
-
"epoch": 2.8125,
|
| 1267 |
-
"grad_norm": 0.7719696164131165,
|
| 1268 |
-
"learning_rate": 2.3754521914919668e-06,
|
| 1269 |
-
"loss": 0.6063,
|
| 1270 |
-
"step": 180
|
| 1271 |
-
},
|
| 1272 |
-
{
|
| 1273 |
-
"epoch": 2.828125,
|
| 1274 |
-
"grad_norm": 0.8477444648742676,
|
| 1275 |
-
"learning_rate": 2.0252453040173647e-06,
|
| 1276 |
-
"loss": 0.5877,
|
| 1277 |
-
"step": 181
|
| 1278 |
-
},
|
| 1279 |
-
{
|
| 1280 |
-
"epoch": 2.84375,
|
| 1281 |
-
"grad_norm": 0.7376056909561157,
|
| 1282 |
-
"learning_rate": 1.7026900316098215e-06,
|
| 1283 |
-
"loss": 0.5247,
|
| 1284 |
-
"step": 182
|
| 1285 |
-
},
|
| 1286 |
-
{
|
| 1287 |
-
"epoch": 2.859375,
|
| 1288 |
-
"grad_norm": 0.734314501285553,
|
| 1289 |
-
"learning_rate": 1.407877409702496e-06,
|
| 1290 |
-
"loss": 0.5798,
|
| 1291 |
-
"step": 183
|
| 1292 |
-
},
|
| 1293 |
-
{
|
| 1294 |
-
"epoch": 2.875,
|
| 1295 |
-
"grad_norm": 0.7004963755607605,
|
| 1296 |
-
"learning_rate": 1.1408906438636236e-06,
|
| 1297 |
-
"loss": 0.4904,
|
| 1298 |
-
"step": 184
|
| 1299 |
-
},
|
| 1300 |
-
{
|
| 1301 |
-
"epoch": 2.890625,
|
| 1302 |
-
"grad_norm": 0.7169924378395081,
|
| 1303 |
-
"learning_rate": 9.018050863132565e-07,
|
| 1304 |
-
"loss": 0.5529,
|
| 1305 |
-
"step": 185
|
| 1306 |
-
},
|
| 1307 |
-
{
|
| 1308 |
-
"epoch": 2.90625,
|
| 1309 |
-
"grad_norm": 0.7529072165489197,
|
| 1310 |
-
"learning_rate": 6.906882146565096e-07,
|
| 1311 |
-
"loss": 0.5226,
|
| 1312 |
-
"step": 186
|
| 1313 |
-
},
|
| 1314 |
-
{
|
| 1315 |
-
"epoch": 2.921875,
|
| 1316 |
-
"grad_norm": 0.762661337852478,
|
| 1317 |
-
"learning_rate": 5.075996128391158e-07,
|
| 1318 |
-
"loss": 0.6149,
|
| 1319 |
-
"step": 187
|
| 1320 |
-
},
|
| 1321 |
-
{
|
| 1322 |
-
"epoch": 2.9375,
|
| 1323 |
-
"grad_norm": 0.7445721626281738,
|
| 1324 |
-
"learning_rate": 3.525909543310002e-07,
|
| 1325 |
-
"loss": 0.6561,
|
| 1326 |
-
"step": 188
|
| 1327 |
-
},
|
| 1328 |
-
{
|
| 1329 |
-
"epoch": 2.953125,
|
| 1330 |
-
"grad_norm": 0.7027716040611267,
|
| 1331 |
-
"learning_rate": 2.2570598754237947e-07,
|
| 1332 |
-
"loss": 0.54,
|
| 1333 |
-
"step": 189
|
| 1334 |
-
},
|
| 1335 |
-
{
|
| 1336 |
-
"epoch": 2.96875,
|
| 1337 |
-
"grad_norm": 0.7662133574485779,
|
| 1338 |
-
"learning_rate": 1.2698052347649426e-07,
|
| 1339 |
-
"loss": 0.5341,
|
| 1340 |
-
"step": 190
|
| 1341 |
-
},
|
| 1342 |
-
{
|
| 1343 |
-
"epoch": 2.984375,
|
| 1344 |
-
"grad_norm": 0.7629265785217285,
|
| 1345 |
-
"learning_rate": 5.644242562264923e-08,
|
| 1346 |
-
"loss": 0.5647,
|
| 1347 |
-
"step": 191
|
| 1348 |
-
},
|
| 1349 |
-
{
|
| 1350 |
-
"epoch": 3.0,
|
| 1351 |
-
"grad_norm": 0.8505879044532776,
|
| 1352 |
-
"learning_rate": 1.4111602092226062e-08,
|
| 1353 |
-
"loss": 0.5023,
|
| 1354 |
-
"step": 192
|
| 1355 |
-
}
|
| 1356 |
-
],
|
| 1357 |
-
"logging_steps": 1,
|
| 1358 |
-
"max_steps": 192,
|
| 1359 |
-
"num_input_tokens_seen": 0,
|
| 1360 |
-
"num_train_epochs": 3,
|
| 1361 |
-
"save_steps": 500,
|
| 1362 |
-
"stateful_callbacks": {
|
| 1363 |
-
"TrainerControl": {
|
| 1364 |
-
"args": {
|
| 1365 |
-
"should_epoch_stop": false,
|
| 1366 |
-
"should_evaluate": false,
|
| 1367 |
-
"should_log": false,
|
| 1368 |
-
"should_save": true,
|
| 1369 |
-
"should_training_stop": true
|
| 1370 |
-
},
|
| 1371 |
-
"attributes": {}
|
| 1372 |
-
}
|
| 1373 |
-
},
|
| 1374 |
-
"total_flos": 4.417588075387945e+17,
|
| 1375 |
-
"train_batch_size": 8,
|
| 1376 |
-
"trial_name": null,
|
| 1377 |
-
"trial_params": null
|
| 1378 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|