Delete checkpoint-2500/trainer_state.json with huggingface_hub
Browse files- checkpoint-2500/trainer_state.json +0 -1784
checkpoint-2500/trainer_state.json
DELETED
|
@@ -1,1784 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_global_step": null,
|
| 3 |
-
"best_metric": null,
|
| 4 |
-
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 2.0,
|
| 6 |
-
"eval_steps": 500,
|
| 7 |
-
"global_step": 2500,
|
| 8 |
-
"is_hyper_param_search": false,
|
| 9 |
-
"is_local_process_zero": true,
|
| 10 |
-
"is_world_process_zero": true,
|
| 11 |
-
"log_history": [
|
| 12 |
-
{
|
| 13 |
-
"epoch": 0.008,
|
| 14 |
-
"grad_norm": 4.96875,
|
| 15 |
-
"learning_rate": 7.964601769911505e-06,
|
| 16 |
-
"loss": 1.4112,
|
| 17 |
-
"step": 10
|
| 18 |
-
},
|
| 19 |
-
{
|
| 20 |
-
"epoch": 0.016,
|
| 21 |
-
"grad_norm": 5.3125,
|
| 22 |
-
"learning_rate": 1.6814159292035402e-05,
|
| 23 |
-
"loss": 1.4365,
|
| 24 |
-
"step": 20
|
| 25 |
-
},
|
| 26 |
-
{
|
| 27 |
-
"epoch": 0.024,
|
| 28 |
-
"grad_norm": 2.265625,
|
| 29 |
-
"learning_rate": 2.5663716814159294e-05,
|
| 30 |
-
"loss": 1.2118,
|
| 31 |
-
"step": 30
|
| 32 |
-
},
|
| 33 |
-
{
|
| 34 |
-
"epoch": 0.032,
|
| 35 |
-
"grad_norm": 2.78125,
|
| 36 |
-
"learning_rate": 3.451327433628319e-05,
|
| 37 |
-
"loss": 1.1222,
|
| 38 |
-
"step": 40
|
| 39 |
-
},
|
| 40 |
-
{
|
| 41 |
-
"epoch": 0.04,
|
| 42 |
-
"grad_norm": 1.953125,
|
| 43 |
-
"learning_rate": 4.3362831858407084e-05,
|
| 44 |
-
"loss": 1.0566,
|
| 45 |
-
"step": 50
|
| 46 |
-
},
|
| 47 |
-
{
|
| 48 |
-
"epoch": 0.048,
|
| 49 |
-
"grad_norm": 2.75,
|
| 50 |
-
"learning_rate": 5.221238938053098e-05,
|
| 51 |
-
"loss": 1.0392,
|
| 52 |
-
"step": 60
|
| 53 |
-
},
|
| 54 |
-
{
|
| 55 |
-
"epoch": 0.056,
|
| 56 |
-
"grad_norm": 2.578125,
|
| 57 |
-
"learning_rate": 6.106194690265487e-05,
|
| 58 |
-
"loss": 1.1753,
|
| 59 |
-
"step": 70
|
| 60 |
-
},
|
| 61 |
-
{
|
| 62 |
-
"epoch": 0.064,
|
| 63 |
-
"grad_norm": 1.421875,
|
| 64 |
-
"learning_rate": 6.991150442477876e-05,
|
| 65 |
-
"loss": 1.0422,
|
| 66 |
-
"step": 80
|
| 67 |
-
},
|
| 68 |
-
{
|
| 69 |
-
"epoch": 0.072,
|
| 70 |
-
"grad_norm": 3.765625,
|
| 71 |
-
"learning_rate": 7.876106194690266e-05,
|
| 72 |
-
"loss": 1.026,
|
| 73 |
-
"step": 90
|
| 74 |
-
},
|
| 75 |
-
{
|
| 76 |
-
"epoch": 0.08,
|
| 77 |
-
"grad_norm": 2.609375,
|
| 78 |
-
"learning_rate": 8.761061946902655e-05,
|
| 79 |
-
"loss": 1.0633,
|
| 80 |
-
"step": 100
|
| 81 |
-
},
|
| 82 |
-
{
|
| 83 |
-
"epoch": 0.088,
|
| 84 |
-
"grad_norm": 3.171875,
|
| 85 |
-
"learning_rate": 9.646017699115044e-05,
|
| 86 |
-
"loss": 1.1138,
|
| 87 |
-
"step": 110
|
| 88 |
-
},
|
| 89 |
-
{
|
| 90 |
-
"epoch": 0.096,
|
| 91 |
-
"grad_norm": 3.609375,
|
| 92 |
-
"learning_rate": 9.999932848660433e-05,
|
| 93 |
-
"loss": 1.1079,
|
| 94 |
-
"step": 120
|
| 95 |
-
},
|
| 96 |
-
{
|
| 97 |
-
"epoch": 0.104,
|
| 98 |
-
"grad_norm": 2.765625,
|
| 99 |
-
"learning_rate": 9.99952248589506e-05,
|
| 100 |
-
"loss": 1.0538,
|
| 101 |
-
"step": 130
|
| 102 |
-
},
|
| 103 |
-
{
|
| 104 |
-
"epoch": 0.112,
|
| 105 |
-
"grad_norm": 3.5625,
|
| 106 |
-
"learning_rate": 9.998739097245067e-05,
|
| 107 |
-
"loss": 0.9637,
|
| 108 |
-
"step": 140
|
| 109 |
-
},
|
| 110 |
-
{
|
| 111 |
-
"epoch": 0.12,
|
| 112 |
-
"grad_norm": 5.6875,
|
| 113 |
-
"learning_rate": 9.997582741160886e-05,
|
| 114 |
-
"loss": 0.8554,
|
| 115 |
-
"step": 150
|
| 116 |
-
},
|
| 117 |
-
{
|
| 118 |
-
"epoch": 0.128,
|
| 119 |
-
"grad_norm": 7.40625,
|
| 120 |
-
"learning_rate": 9.99605350392091e-05,
|
| 121 |
-
"loss": 0.6704,
|
| 122 |
-
"step": 160
|
| 123 |
-
},
|
| 124 |
-
{
|
| 125 |
-
"epoch": 0.136,
|
| 126 |
-
"grad_norm": 7.03125,
|
| 127 |
-
"learning_rate": 9.994151499625049e-05,
|
| 128 |
-
"loss": 0.8075,
|
| 129 |
-
"step": 170
|
| 130 |
-
},
|
| 131 |
-
{
|
| 132 |
-
"epoch": 0.144,
|
| 133 |
-
"grad_norm": 3.828125,
|
| 134 |
-
"learning_rate": 9.991876870186222e-05,
|
| 135 |
-
"loss": 0.7331,
|
| 136 |
-
"step": 180
|
| 137 |
-
},
|
| 138 |
-
{
|
| 139 |
-
"epoch": 0.152,
|
| 140 |
-
"grad_norm": 3.890625,
|
| 141 |
-
"learning_rate": 9.98922978531977e-05,
|
| 142 |
-
"loss": 0.7264,
|
| 143 |
-
"step": 190
|
| 144 |
-
},
|
| 145 |
-
{
|
| 146 |
-
"epoch": 0.16,
|
| 147 |
-
"grad_norm": 4.15625,
|
| 148 |
-
"learning_rate": 9.986210442530788e-05,
|
| 149 |
-
"loss": 0.5792,
|
| 150 |
-
"step": 200
|
| 151 |
-
},
|
| 152 |
-
{
|
| 153 |
-
"epoch": 0.168,
|
| 154 |
-
"grad_norm": 5.53125,
|
| 155 |
-
"learning_rate": 9.982819067099396e-05,
|
| 156 |
-
"loss": 0.6228,
|
| 157 |
-
"step": 210
|
| 158 |
-
},
|
| 159 |
-
{
|
| 160 |
-
"epoch": 0.176,
|
| 161 |
-
"grad_norm": 5.875,
|
| 162 |
-
"learning_rate": 9.979055912063925e-05,
|
| 163 |
-
"loss": 0.7417,
|
| 164 |
-
"step": 220
|
| 165 |
-
},
|
| 166 |
-
{
|
| 167 |
-
"epoch": 0.184,
|
| 168 |
-
"grad_norm": 3.71875,
|
| 169 |
-
"learning_rate": 9.974921258202036e-05,
|
| 170 |
-
"loss": 0.472,
|
| 171 |
-
"step": 230
|
| 172 |
-
},
|
| 173 |
-
{
|
| 174 |
-
"epoch": 0.192,
|
| 175 |
-
"grad_norm": 4.15625,
|
| 176 |
-
"learning_rate": 9.970415414009773e-05,
|
| 177 |
-
"loss": 0.6284,
|
| 178 |
-
"step": 240
|
| 179 |
-
},
|
| 180 |
-
{
|
| 181 |
-
"epoch": 0.2,
|
| 182 |
-
"grad_norm": 5.1875,
|
| 183 |
-
"learning_rate": 9.965538715678548e-05,
|
| 184 |
-
"loss": 0.5349,
|
| 185 |
-
"step": 250
|
| 186 |
-
},
|
| 187 |
-
{
|
| 188 |
-
"epoch": 0.208,
|
| 189 |
-
"grad_norm": 4.59375,
|
| 190 |
-
"learning_rate": 9.960291527070051e-05,
|
| 191 |
-
"loss": 0.5165,
|
| 192 |
-
"step": 260
|
| 193 |
-
},
|
| 194 |
-
{
|
| 195 |
-
"epoch": 0.216,
|
| 196 |
-
"grad_norm": 4.0625,
|
| 197 |
-
"learning_rate": 9.954674239689109e-05,
|
| 198 |
-
"loss": 0.5656,
|
| 199 |
-
"step": 270
|
| 200 |
-
},
|
| 201 |
-
{
|
| 202 |
-
"epoch": 0.224,
|
| 203 |
-
"grad_norm": 3.875,
|
| 204 |
-
"learning_rate": 9.948687272654464e-05,
|
| 205 |
-
"loss": 0.6713,
|
| 206 |
-
"step": 280
|
| 207 |
-
},
|
| 208 |
-
{
|
| 209 |
-
"epoch": 0.232,
|
| 210 |
-
"grad_norm": 5.375,
|
| 211 |
-
"learning_rate": 9.942331072667517e-05,
|
| 212 |
-
"loss": 0.4347,
|
| 213 |
-
"step": 290
|
| 214 |
-
},
|
| 215 |
-
{
|
| 216 |
-
"epoch": 0.24,
|
| 217 |
-
"grad_norm": 5.875,
|
| 218 |
-
"learning_rate": 9.935606113978981e-05,
|
| 219 |
-
"loss": 0.4404,
|
| 220 |
-
"step": 300
|
| 221 |
-
},
|
| 222 |
-
{
|
| 223 |
-
"epoch": 0.248,
|
| 224 |
-
"grad_norm": 4.28125,
|
| 225 |
-
"learning_rate": 9.92851289835351e-05,
|
| 226 |
-
"loss": 0.4865,
|
| 227 |
-
"step": 310
|
| 228 |
-
},
|
| 229 |
-
{
|
| 230 |
-
"epoch": 0.256,
|
| 231 |
-
"grad_norm": 6.46875,
|
| 232 |
-
"learning_rate": 9.921051955032253e-05,
|
| 233 |
-
"loss": 0.5393,
|
| 234 |
-
"step": 320
|
| 235 |
-
},
|
| 236 |
-
{
|
| 237 |
-
"epoch": 0.264,
|
| 238 |
-
"grad_norm": 9.0625,
|
| 239 |
-
"learning_rate": 9.913223840693375e-05,
|
| 240 |
-
"loss": 0.5358,
|
| 241 |
-
"step": 330
|
| 242 |
-
},
|
| 243 |
-
{
|
| 244 |
-
"epoch": 0.272,
|
| 245 |
-
"grad_norm": 5.0625,
|
| 246 |
-
"learning_rate": 9.905029139410508e-05,
|
| 247 |
-
"loss": 0.5756,
|
| 248 |
-
"step": 340
|
| 249 |
-
},
|
| 250 |
-
{
|
| 251 |
-
"epoch": 0.28,
|
| 252 |
-
"grad_norm": 10.625,
|
| 253 |
-
"learning_rate": 9.896468462609186e-05,
|
| 254 |
-
"loss": 0.4554,
|
| 255 |
-
"step": 350
|
| 256 |
-
},
|
| 257 |
-
{
|
| 258 |
-
"epoch": 0.288,
|
| 259 |
-
"grad_norm": 3.6875,
|
| 260 |
-
"learning_rate": 9.887542449021214e-05,
|
| 261 |
-
"loss": 0.3889,
|
| 262 |
-
"step": 360
|
| 263 |
-
},
|
| 264 |
-
{
|
| 265 |
-
"epoch": 0.296,
|
| 266 |
-
"grad_norm": 6.25,
|
| 267 |
-
"learning_rate": 9.878251764637023e-05,
|
| 268 |
-
"loss": 0.4468,
|
| 269 |
-
"step": 370
|
| 270 |
-
},
|
| 271 |
-
{
|
| 272 |
-
"epoch": 0.304,
|
| 273 |
-
"grad_norm": 5.5,
|
| 274 |
-
"learning_rate": 9.868597102655968e-05,
|
| 275 |
-
"loss": 0.4612,
|
| 276 |
-
"step": 380
|
| 277 |
-
},
|
| 278 |
-
{
|
| 279 |
-
"epoch": 0.312,
|
| 280 |
-
"grad_norm": 5.4375,
|
| 281 |
-
"learning_rate": 9.858579183434605e-05,
|
| 282 |
-
"loss": 0.6069,
|
| 283 |
-
"step": 390
|
| 284 |
-
},
|
| 285 |
-
{
|
| 286 |
-
"epoch": 0.32,
|
| 287 |
-
"grad_norm": 5.84375,
|
| 288 |
-
"learning_rate": 9.848198754432959e-05,
|
| 289 |
-
"loss": 0.4464,
|
| 290 |
-
"step": 400
|
| 291 |
-
},
|
| 292 |
-
{
|
| 293 |
-
"epoch": 0.328,
|
| 294 |
-
"grad_norm": 5.125,
|
| 295 |
-
"learning_rate": 9.837456590158738e-05,
|
| 296 |
-
"loss": 0.5598,
|
| 297 |
-
"step": 410
|
| 298 |
-
},
|
| 299 |
-
{
|
| 300 |
-
"epoch": 0.336,
|
| 301 |
-
"grad_norm": 3.671875,
|
| 302 |
-
"learning_rate": 9.826353492109555e-05,
|
| 303 |
-
"loss": 0.4534,
|
| 304 |
-
"step": 420
|
| 305 |
-
},
|
| 306 |
-
{
|
| 307 |
-
"epoch": 0.344,
|
| 308 |
-
"grad_norm": 7.34375,
|
| 309 |
-
"learning_rate": 9.814890288713121e-05,
|
| 310 |
-
"loss": 0.5155,
|
| 311 |
-
"step": 430
|
| 312 |
-
},
|
| 313 |
-
{
|
| 314 |
-
"epoch": 0.352,
|
| 315 |
-
"grad_norm": 6.875,
|
| 316 |
-
"learning_rate": 9.803067835265436e-05,
|
| 317 |
-
"loss": 0.484,
|
| 318 |
-
"step": 440
|
| 319 |
-
},
|
| 320 |
-
{
|
| 321 |
-
"epoch": 0.36,
|
| 322 |
-
"grad_norm": 3.875,
|
| 323 |
-
"learning_rate": 9.790887013866973e-05,
|
| 324 |
-
"loss": 0.4077,
|
| 325 |
-
"step": 450
|
| 326 |
-
},
|
| 327 |
-
{
|
| 328 |
-
"epoch": 0.368,
|
| 329 |
-
"grad_norm": 5.4375,
|
| 330 |
-
"learning_rate": 9.778348733356868e-05,
|
| 331 |
-
"loss": 0.3779,
|
| 332 |
-
"step": 460
|
| 333 |
-
},
|
| 334 |
-
{
|
| 335 |
-
"epoch": 0.376,
|
| 336 |
-
"grad_norm": 5.34375,
|
| 337 |
-
"learning_rate": 9.765453929245096e-05,
|
| 338 |
-
"loss": 0.521,
|
| 339 |
-
"step": 470
|
| 340 |
-
},
|
| 341 |
-
{
|
| 342 |
-
"epoch": 0.384,
|
| 343 |
-
"grad_norm": 4.8125,
|
| 344 |
-
"learning_rate": 9.752203563642688e-05,
|
| 345 |
-
"loss": 0.4114,
|
| 346 |
-
"step": 480
|
| 347 |
-
},
|
| 348 |
-
{
|
| 349 |
-
"epoch": 0.392,
|
| 350 |
-
"grad_norm": 8.25,
|
| 351 |
-
"learning_rate": 9.73859862518993e-05,
|
| 352 |
-
"loss": 0.4361,
|
| 353 |
-
"step": 490
|
| 354 |
-
},
|
| 355 |
-
{
|
| 356 |
-
"epoch": 0.4,
|
| 357 |
-
"grad_norm": 7.40625,
|
| 358 |
-
"learning_rate": 9.724640128982605e-05,
|
| 359 |
-
"loss": 0.518,
|
| 360 |
-
"step": 500
|
| 361 |
-
},
|
| 362 |
-
{
|
| 363 |
-
"epoch": 0.408,
|
| 364 |
-
"grad_norm": 5.5625,
|
| 365 |
-
"learning_rate": 9.710329116496259e-05,
|
| 366 |
-
"loss": 0.4413,
|
| 367 |
-
"step": 510
|
| 368 |
-
},
|
| 369 |
-
{
|
| 370 |
-
"epoch": 0.416,
|
| 371 |
-
"grad_norm": 5.46875,
|
| 372 |
-
"learning_rate": 9.695666655508483e-05,
|
| 373 |
-
"loss": 0.4276,
|
| 374 |
-
"step": 520
|
| 375 |
-
},
|
| 376 |
-
{
|
| 377 |
-
"epoch": 0.424,
|
| 378 |
-
"grad_norm": 5.375,
|
| 379 |
-
"learning_rate": 9.680653840019259e-05,
|
| 380 |
-
"loss": 0.4476,
|
| 381 |
-
"step": 530
|
| 382 |
-
},
|
| 383 |
-
{
|
| 384 |
-
"epoch": 0.432,
|
| 385 |
-
"grad_norm": 5.875,
|
| 386 |
-
"learning_rate": 9.665291790169311e-05,
|
| 387 |
-
"loss": 0.3562,
|
| 388 |
-
"step": 540
|
| 389 |
-
},
|
| 390 |
-
{
|
| 391 |
-
"epoch": 0.44,
|
| 392 |
-
"grad_norm": 6.4375,
|
| 393 |
-
"learning_rate": 9.649581652156559e-05,
|
| 394 |
-
"loss": 0.4511,
|
| 395 |
-
"step": 550
|
| 396 |
-
},
|
| 397 |
-
{
|
| 398 |
-
"epoch": 0.448,
|
| 399 |
-
"grad_norm": 5.1875,
|
| 400 |
-
"learning_rate": 9.633524598150568e-05,
|
| 401 |
-
"loss": 0.3985,
|
| 402 |
-
"step": 560
|
| 403 |
-
},
|
| 404 |
-
{
|
| 405 |
-
"epoch": 0.456,
|
| 406 |
-
"grad_norm": 4.1875,
|
| 407 |
-
"learning_rate": 9.617121826205116e-05,
|
| 408 |
-
"loss": 0.5117,
|
| 409 |
-
"step": 570
|
| 410 |
-
},
|
| 411 |
-
{
|
| 412 |
-
"epoch": 0.464,
|
| 413 |
-
"grad_norm": 5.5,
|
| 414 |
-
"learning_rate": 9.600374560168783e-05,
|
| 415 |
-
"loss": 0.4569,
|
| 416 |
-
"step": 580
|
| 417 |
-
},
|
| 418 |
-
{
|
| 419 |
-
"epoch": 0.472,
|
| 420 |
-
"grad_norm": 4.5,
|
| 421 |
-
"learning_rate": 9.583284049593652e-05,
|
| 422 |
-
"loss": 0.449,
|
| 423 |
-
"step": 590
|
| 424 |
-
},
|
| 425 |
-
{
|
| 426 |
-
"epoch": 0.48,
|
| 427 |
-
"grad_norm": 4.25,
|
| 428 |
-
"learning_rate": 9.56585156964207e-05,
|
| 429 |
-
"loss": 0.4769,
|
| 430 |
-
"step": 600
|
| 431 |
-
},
|
| 432 |
-
{
|
| 433 |
-
"epoch": 0.488,
|
| 434 |
-
"grad_norm": 5.9375,
|
| 435 |
-
"learning_rate": 9.548078420991506e-05,
|
| 436 |
-
"loss": 0.5081,
|
| 437 |
-
"step": 610
|
| 438 |
-
},
|
| 439 |
-
{
|
| 440 |
-
"epoch": 0.496,
|
| 441 |
-
"grad_norm": 7.4375,
|
| 442 |
-
"learning_rate": 9.529965929737506e-05,
|
| 443 |
-
"loss": 0.4803,
|
| 444 |
-
"step": 620
|
| 445 |
-
},
|
| 446 |
-
{
|
| 447 |
-
"epoch": 0.504,
|
| 448 |
-
"grad_norm": 4.59375,
|
| 449 |
-
"learning_rate": 9.511515447294748e-05,
|
| 450 |
-
"loss": 0.5015,
|
| 451 |
-
"step": 630
|
| 452 |
-
},
|
| 453 |
-
{
|
| 454 |
-
"epoch": 0.512,
|
| 455 |
-
"grad_norm": 6.71875,
|
| 456 |
-
"learning_rate": 9.49272835029621e-05,
|
| 457 |
-
"loss": 0.5174,
|
| 458 |
-
"step": 640
|
| 459 |
-
},
|
| 460 |
-
{
|
| 461 |
-
"epoch": 0.52,
|
| 462 |
-
"grad_norm": 4.875,
|
| 463 |
-
"learning_rate": 9.47360604049046e-05,
|
| 464 |
-
"loss": 0.4957,
|
| 465 |
-
"step": 650
|
| 466 |
-
},
|
| 467 |
-
{
|
| 468 |
-
"epoch": 0.528,
|
| 469 |
-
"grad_norm": 4.71875,
|
| 470 |
-
"learning_rate": 9.454149944637064e-05,
|
| 471 |
-
"loss": 0.379,
|
| 472 |
-
"step": 660
|
| 473 |
-
},
|
| 474 |
-
{
|
| 475 |
-
"epoch": 0.536,
|
| 476 |
-
"grad_norm": 4.96875,
|
| 477 |
-
"learning_rate": 9.434361514400132e-05,
|
| 478 |
-
"loss": 0.4857,
|
| 479 |
-
"step": 670
|
| 480 |
-
},
|
| 481 |
-
{
|
| 482 |
-
"epoch": 0.544,
|
| 483 |
-
"grad_norm": 5.71875,
|
| 484 |
-
"learning_rate": 9.414242226240012e-05,
|
| 485 |
-
"loss": 0.4595,
|
| 486 |
-
"step": 680
|
| 487 |
-
},
|
| 488 |
-
{
|
| 489 |
-
"epoch": 0.552,
|
| 490 |
-
"grad_norm": 6.8125,
|
| 491 |
-
"learning_rate": 9.393793581303116e-05,
|
| 492 |
-
"loss": 0.4157,
|
| 493 |
-
"step": 690
|
| 494 |
-
},
|
| 495 |
-
{
|
| 496 |
-
"epoch": 0.56,
|
| 497 |
-
"grad_norm": 5.03125,
|
| 498 |
-
"learning_rate": 9.37301710530993e-05,
|
| 499 |
-
"loss": 0.4432,
|
| 500 |
-
"step": 700
|
| 501 |
-
},
|
| 502 |
-
{
|
| 503 |
-
"epoch": 0.568,
|
| 504 |
-
"grad_norm": 6.75,
|
| 505 |
-
"learning_rate": 9.351914348441169e-05,
|
| 506 |
-
"loss": 0.4695,
|
| 507 |
-
"step": 710
|
| 508 |
-
},
|
| 509 |
-
{
|
| 510 |
-
"epoch": 0.576,
|
| 511 |
-
"grad_norm": 2.890625,
|
| 512 |
-
"learning_rate": 9.330486885222114e-05,
|
| 513 |
-
"loss": 0.3493,
|
| 514 |
-
"step": 720
|
| 515 |
-
},
|
| 516 |
-
{
|
| 517 |
-
"epoch": 0.584,
|
| 518 |
-
"grad_norm": 3.4375,
|
| 519 |
-
"learning_rate": 9.308736314405134e-05,
|
| 520 |
-
"loss": 0.4304,
|
| 521 |
-
"step": 730
|
| 522 |
-
},
|
| 523 |
-
{
|
| 524 |
-
"epoch": 0.592,
|
| 525 |
-
"grad_norm": 3.1875,
|
| 526 |
-
"learning_rate": 9.286664258850402e-05,
|
| 527 |
-
"loss": 0.5057,
|
| 528 |
-
"step": 740
|
| 529 |
-
},
|
| 530 |
-
{
|
| 531 |
-
"epoch": 0.6,
|
| 532 |
-
"grad_norm": 4.375,
|
| 533 |
-
"learning_rate": 9.264272365404805e-05,
|
| 534 |
-
"loss": 0.4159,
|
| 535 |
-
"step": 750
|
| 536 |
-
},
|
| 537 |
-
{
|
| 538 |
-
"epoch": 0.608,
|
| 539 |
-
"grad_norm": 4.3125,
|
| 540 |
-
"learning_rate": 9.241562304779072e-05,
|
| 541 |
-
"loss": 0.3647,
|
| 542 |
-
"step": 760
|
| 543 |
-
},
|
| 544 |
-
{
|
| 545 |
-
"epoch": 0.616,
|
| 546 |
-
"grad_norm": 10.3125,
|
| 547 |
-
"learning_rate": 9.21853577142312e-05,
|
| 548 |
-
"loss": 0.4851,
|
| 549 |
-
"step": 770
|
| 550 |
-
},
|
| 551 |
-
{
|
| 552 |
-
"epoch": 0.624,
|
| 553 |
-
"grad_norm": 6.3125,
|
| 554 |
-
"learning_rate": 9.195194483399625e-05,
|
| 555 |
-
"loss": 0.5071,
|
| 556 |
-
"step": 780
|
| 557 |
-
},
|
| 558 |
-
{
|
| 559 |
-
"epoch": 0.632,
|
| 560 |
-
"grad_norm": 4.34375,
|
| 561 |
-
"learning_rate": 9.17154018225583e-05,
|
| 562 |
-
"loss": 0.3939,
|
| 563 |
-
"step": 790
|
| 564 |
-
},
|
| 565 |
-
{
|
| 566 |
-
"epoch": 0.64,
|
| 567 |
-
"grad_norm": 4.03125,
|
| 568 |
-
"learning_rate": 9.147574632893611e-05,
|
| 569 |
-
"loss": 0.3762,
|
| 570 |
-
"step": 800
|
| 571 |
-
},
|
| 572 |
-
{
|
| 573 |
-
"epoch": 0.648,
|
| 574 |
-
"grad_norm": 3.1875,
|
| 575 |
-
"learning_rate": 9.12329962343779e-05,
|
| 576 |
-
"loss": 0.4427,
|
| 577 |
-
"step": 810
|
| 578 |
-
},
|
| 579 |
-
{
|
| 580 |
-
"epoch": 0.656,
|
| 581 |
-
"grad_norm": 3.890625,
|
| 582 |
-
"learning_rate": 9.098716965102716e-05,
|
| 583 |
-
"loss": 0.357,
|
| 584 |
-
"step": 820
|
| 585 |
-
},
|
| 586 |
-
{
|
| 587 |
-
"epoch": 0.664,
|
| 588 |
-
"grad_norm": 8.25,
|
| 589 |
-
"learning_rate": 9.073828492057133e-05,
|
| 590 |
-
"loss": 0.4071,
|
| 591 |
-
"step": 830
|
| 592 |
-
},
|
| 593 |
-
{
|
| 594 |
-
"epoch": 0.672,
|
| 595 |
-
"grad_norm": 5.78125,
|
| 596 |
-
"learning_rate": 9.048636061287325e-05,
|
| 597 |
-
"loss": 0.4037,
|
| 598 |
-
"step": 840
|
| 599 |
-
},
|
| 600 |
-
{
|
| 601 |
-
"epoch": 0.68,
|
| 602 |
-
"grad_norm": 3.84375,
|
| 603 |
-
"learning_rate": 9.023141552458559e-05,
|
| 604 |
-
"loss": 0.3884,
|
| 605 |
-
"step": 850
|
| 606 |
-
},
|
| 607 |
-
{
|
| 608 |
-
"epoch": 0.688,
|
| 609 |
-
"grad_norm": 3.453125,
|
| 610 |
-
"learning_rate": 8.997346867774839e-05,
|
| 611 |
-
"loss": 0.3641,
|
| 612 |
-
"step": 860
|
| 613 |
-
},
|
| 614 |
-
{
|
| 615 |
-
"epoch": 0.696,
|
| 616 |
-
"grad_norm": 7.875,
|
| 617 |
-
"learning_rate": 8.97125393183699e-05,
|
| 618 |
-
"loss": 0.5387,
|
| 619 |
-
"step": 870
|
| 620 |
-
},
|
| 621 |
-
{
|
| 622 |
-
"epoch": 0.704,
|
| 623 |
-
"grad_norm": 4.6875,
|
| 624 |
-
"learning_rate": 8.94486469149904e-05,
|
| 625 |
-
"loss": 0.4085,
|
| 626 |
-
"step": 880
|
| 627 |
-
},
|
| 628 |
-
{
|
| 629 |
-
"epoch": 0.712,
|
| 630 |
-
"grad_norm": 6.03125,
|
| 631 |
-
"learning_rate": 8.918181115722976e-05,
|
| 632 |
-
"loss": 0.4055,
|
| 633 |
-
"step": 890
|
| 634 |
-
},
|
| 635 |
-
{
|
| 636 |
-
"epoch": 0.72,
|
| 637 |
-
"grad_norm": 7.375,
|
| 638 |
-
"learning_rate": 8.891205195431831e-05,
|
| 639 |
-
"loss": 0.42,
|
| 640 |
-
"step": 900
|
| 641 |
-
},
|
| 642 |
-
{
|
| 643 |
-
"epoch": 0.728,
|
| 644 |
-
"grad_norm": 3.21875,
|
| 645 |
-
"learning_rate": 8.863938943361128e-05,
|
| 646 |
-
"loss": 0.3372,
|
| 647 |
-
"step": 910
|
| 648 |
-
},
|
| 649 |
-
{
|
| 650 |
-
"epoch": 0.736,
|
| 651 |
-
"grad_norm": 3.65625,
|
| 652 |
-
"learning_rate": 8.836384393908721e-05,
|
| 653 |
-
"loss": 0.4544,
|
| 654 |
-
"step": 920
|
| 655 |
-
},
|
| 656 |
-
{
|
| 657 |
-
"epoch": 0.744,
|
| 658 |
-
"grad_norm": 3.703125,
|
| 659 |
-
"learning_rate": 8.808543602982993e-05,
|
| 660 |
-
"loss": 0.4979,
|
| 661 |
-
"step": 930
|
| 662 |
-
},
|
| 663 |
-
{
|
| 664 |
-
"epoch": 0.752,
|
| 665 |
-
"grad_norm": 2.90625,
|
| 666 |
-
"learning_rate": 8.780418647849458e-05,
|
| 667 |
-
"loss": 0.3366,
|
| 668 |
-
"step": 940
|
| 669 |
-
},
|
| 670 |
-
{
|
| 671 |
-
"epoch": 0.76,
|
| 672 |
-
"grad_norm": 4.53125,
|
| 673 |
-
"learning_rate": 8.752011626975781e-05,
|
| 674 |
-
"loss": 0.3778,
|
| 675 |
-
"step": 950
|
| 676 |
-
},
|
| 677 |
-
{
|
| 678 |
-
"epoch": 0.768,
|
| 679 |
-
"grad_norm": 3.4375,
|
| 680 |
-
"learning_rate": 8.723324659875201e-05,
|
| 681 |
-
"loss": 0.4498,
|
| 682 |
-
"step": 960
|
| 683 |
-
},
|
| 684 |
-
{
|
| 685 |
-
"epoch": 0.776,
|
| 686 |
-
"grad_norm": 4.90625,
|
| 687 |
-
"learning_rate": 8.694359886948384e-05,
|
| 688 |
-
"loss": 0.4232,
|
| 689 |
-
"step": 970
|
| 690 |
-
},
|
| 691 |
-
{
|
| 692 |
-
"epoch": 0.784,
|
| 693 |
-
"grad_norm": 4.15625,
|
| 694 |
-
"learning_rate": 8.665119469323737e-05,
|
| 695 |
-
"loss": 0.3602,
|
| 696 |
-
"step": 980
|
| 697 |
-
},
|
| 698 |
-
{
|
| 699 |
-
"epoch": 0.792,
|
| 700 |
-
"grad_norm": 5.375,
|
| 701 |
-
"learning_rate": 8.635605588696148e-05,
|
| 702 |
-
"loss": 0.4095,
|
| 703 |
-
"step": 990
|
| 704 |
-
},
|
| 705 |
-
{
|
| 706 |
-
"epoch": 0.8,
|
| 707 |
-
"grad_norm": 3.5625,
|
| 708 |
-
"learning_rate": 8.605820447164206e-05,
|
| 709 |
-
"loss": 0.405,
|
| 710 |
-
"step": 1000
|
| 711 |
-
},
|
| 712 |
-
{
|
| 713 |
-
"epoch": 0.808,
|
| 714 |
-
"grad_norm": 4.40625,
|
| 715 |
-
"learning_rate": 8.575766267065905e-05,
|
| 716 |
-
"loss": 0.3137,
|
| 717 |
-
"step": 1010
|
| 718 |
-
},
|
| 719 |
-
{
|
| 720 |
-
"epoch": 0.816,
|
| 721 |
-
"grad_norm": 5.65625,
|
| 722 |
-
"learning_rate": 8.54544529081283e-05,
|
| 723 |
-
"loss": 0.3701,
|
| 724 |
-
"step": 1020
|
| 725 |
-
},
|
| 726 |
-
{
|
| 727 |
-
"epoch": 0.824,
|
| 728 |
-
"grad_norm": 5.0,
|
| 729 |
-
"learning_rate": 8.514859780722833e-05,
|
| 730 |
-
"loss": 0.3759,
|
| 731 |
-
"step": 1030
|
| 732 |
-
},
|
| 733 |
-
{
|
| 734 |
-
"epoch": 0.832,
|
| 735 |
-
"grad_norm": 4.9375,
|
| 736 |
-
"learning_rate": 8.484012018851246e-05,
|
| 737 |
-
"loss": 0.3032,
|
| 738 |
-
"step": 1040
|
| 739 |
-
},
|
| 740 |
-
{
|
| 741 |
-
"epoch": 0.84,
|
| 742 |
-
"grad_norm": 4.375,
|
| 743 |
-
"learning_rate": 8.452904306820618e-05,
|
| 744 |
-
"loss": 0.4171,
|
| 745 |
-
"step": 1050
|
| 746 |
-
},
|
| 747 |
-
{
|
| 748 |
-
"epoch": 0.848,
|
| 749 |
-
"grad_norm": 4.53125,
|
| 750 |
-
"learning_rate": 8.421538965648966e-05,
|
| 751 |
-
"loss": 0.374,
|
| 752 |
-
"step": 1060
|
| 753 |
-
},
|
| 754 |
-
{
|
| 755 |
-
"epoch": 0.856,
|
| 756 |
-
"grad_norm": 4.3125,
|
| 757 |
-
"learning_rate": 8.389918335576623e-05,
|
| 758 |
-
"loss": 0.3358,
|
| 759 |
-
"step": 1070
|
| 760 |
-
},
|
| 761 |
-
{
|
| 762 |
-
"epoch": 0.864,
|
| 763 |
-
"grad_norm": 4.21875,
|
| 764 |
-
"learning_rate": 8.358044775891605e-05,
|
| 765 |
-
"loss": 0.3586,
|
| 766 |
-
"step": 1080
|
| 767 |
-
},
|
| 768 |
-
{
|
| 769 |
-
"epoch": 0.872,
|
| 770 |
-
"grad_norm": 4.15625,
|
| 771 |
-
"learning_rate": 8.325920664753595e-05,
|
| 772 |
-
"loss": 0.4036,
|
| 773 |
-
"step": 1090
|
| 774 |
-
},
|
| 775 |
-
{
|
| 776 |
-
"epoch": 0.88,
|
| 777 |
-
"grad_norm": 4.625,
|
| 778 |
-
"learning_rate": 8.293548399016491e-05,
|
| 779 |
-
"loss": 0.3673,
|
| 780 |
-
"step": 1100
|
| 781 |
-
},
|
| 782 |
-
{
|
| 783 |
-
"epoch": 0.888,
|
| 784 |
-
"grad_norm": 2.625,
|
| 785 |
-
"learning_rate": 8.260930394049583e-05,
|
| 786 |
-
"loss": 0.3388,
|
| 787 |
-
"step": 1110
|
| 788 |
-
},
|
| 789 |
-
{
|
| 790 |
-
"epoch": 0.896,
|
| 791 |
-
"grad_norm": 4.78125,
|
| 792 |
-
"learning_rate": 8.228069083557328e-05,
|
| 793 |
-
"loss": 0.427,
|
| 794 |
-
"step": 1120
|
| 795 |
-
},
|
| 796 |
-
{
|
| 797 |
-
"epoch": 0.904,
|
| 798 |
-
"grad_norm": 4.21875,
|
| 799 |
-
"learning_rate": 8.194966919397767e-05,
|
| 800 |
-
"loss": 0.3926,
|
| 801 |
-
"step": 1130
|
| 802 |
-
},
|
| 803 |
-
{
|
| 804 |
-
"epoch": 0.912,
|
| 805 |
-
"grad_norm": 5.84375,
|
| 806 |
-
"learning_rate": 8.161626371399591e-05,
|
| 807 |
-
"loss": 0.3654,
|
| 808 |
-
"step": 1140
|
| 809 |
-
},
|
| 810 |
-
{
|
| 811 |
-
"epoch": 0.92,
|
| 812 |
-
"grad_norm": 3.71875,
|
| 813 |
-
"learning_rate": 8.128049927177854e-05,
|
| 814 |
-
"loss": 0.4047,
|
| 815 |
-
"step": 1150
|
| 816 |
-
},
|
| 817 |
-
{
|
| 818 |
-
"epoch": 0.928,
|
| 819 |
-
"grad_norm": 5.0,
|
| 820 |
-
"learning_rate": 8.094240091948375e-05,
|
| 821 |
-
"loss": 0.4114,
|
| 822 |
-
"step": 1160
|
| 823 |
-
},
|
| 824 |
-
{
|
| 825 |
-
"epoch": 0.936,
|
| 826 |
-
"grad_norm": 6.625,
|
| 827 |
-
"learning_rate": 8.06019938834081e-05,
|
| 828 |
-
"loss": 0.4485,
|
| 829 |
-
"step": 1170
|
| 830 |
-
},
|
| 831 |
-
{
|
| 832 |
-
"epoch": 0.944,
|
| 833 |
-
"grad_norm": 4.4375,
|
| 834 |
-
"learning_rate": 8.025930356210439e-05,
|
| 835 |
-
"loss": 0.3833,
|
| 836 |
-
"step": 1180
|
| 837 |
-
},
|
| 838 |
-
{
|
| 839 |
-
"epoch": 0.952,
|
| 840 |
-
"grad_norm": 3.171875,
|
| 841 |
-
"learning_rate": 7.991435552448657e-05,
|
| 842 |
-
"loss": 0.3742,
|
| 843 |
-
"step": 1190
|
| 844 |
-
},
|
| 845 |
-
{
|
| 846 |
-
"epoch": 0.96,
|
| 847 |
-
"grad_norm": 4.65625,
|
| 848 |
-
"learning_rate": 7.956717550792199e-05,
|
| 849 |
-
"loss": 0.3284,
|
| 850 |
-
"step": 1200
|
| 851 |
-
},
|
| 852 |
-
{
|
| 853 |
-
"epoch": 0.968,
|
| 854 |
-
"grad_norm": 4.4375,
|
| 855 |
-
"learning_rate": 7.921778941631113e-05,
|
| 856 |
-
"loss": 0.3862,
|
| 857 |
-
"step": 1210
|
| 858 |
-
},
|
| 859 |
-
{
|
| 860 |
-
"epoch": 0.976,
|
| 861 |
-
"grad_norm": 8.9375,
|
| 862 |
-
"learning_rate": 7.886622331815477e-05,
|
| 863 |
-
"loss": 0.4144,
|
| 864 |
-
"step": 1220
|
| 865 |
-
},
|
| 866 |
-
{
|
| 867 |
-
"epoch": 0.984,
|
| 868 |
-
"grad_norm": 3.875,
|
| 869 |
-
"learning_rate": 7.851250344460902e-05,
|
| 870 |
-
"loss": 0.3654,
|
| 871 |
-
"step": 1230
|
| 872 |
-
},
|
| 873 |
-
{
|
| 874 |
-
"epoch": 0.992,
|
| 875 |
-
"grad_norm": 2.59375,
|
| 876 |
-
"learning_rate": 7.815665618752812e-05,
|
| 877 |
-
"loss": 0.3808,
|
| 878 |
-
"step": 1240
|
| 879 |
-
},
|
| 880 |
-
{
|
| 881 |
-
"epoch": 1.0,
|
| 882 |
-
"grad_norm": 5.0625,
|
| 883 |
-
"learning_rate": 7.77987080974953e-05,
|
| 884 |
-
"loss": 0.3482,
|
| 885 |
-
"step": 1250
|
| 886 |
-
},
|
| 887 |
-
{
|
| 888 |
-
"epoch": 1.008,
|
| 889 |
-
"grad_norm": 3.28125,
|
| 890 |
-
"learning_rate": 7.743868588184176e-05,
|
| 891 |
-
"loss": 0.3312,
|
| 892 |
-
"step": 1260
|
| 893 |
-
},
|
| 894 |
-
{
|
| 895 |
-
"epoch": 1.016,
|
| 896 |
-
"grad_norm": 4.375,
|
| 897 |
-
"learning_rate": 7.707661640265401e-05,
|
| 898 |
-
"loss": 0.37,
|
| 899 |
-
"step": 1270
|
| 900 |
-
},
|
| 901 |
-
{
|
| 902 |
-
"epoch": 1.024,
|
| 903 |
-
"grad_norm": 4.40625,
|
| 904 |
-
"learning_rate": 7.67125266747696e-05,
|
| 905 |
-
"loss": 0.3253,
|
| 906 |
-
"step": 1280
|
| 907 |
-
},
|
| 908 |
-
{
|
| 909 |
-
"epoch": 1.032,
|
| 910 |
-
"grad_norm": 4.0625,
|
| 911 |
-
"learning_rate": 7.634644386376149e-05,
|
| 912 |
-
"loss": 0.4361,
|
| 913 |
-
"step": 1290
|
| 914 |
-
},
|
| 915 |
-
{
|
| 916 |
-
"epoch": 1.04,
|
| 917 |
-
"grad_norm": 3.953125,
|
| 918 |
-
"learning_rate": 7.597839528391114e-05,
|
| 919 |
-
"loss": 0.3981,
|
| 920 |
-
"step": 1300
|
| 921 |
-
},
|
| 922 |
-
{
|
| 923 |
-
"epoch": 1.048,
|
| 924 |
-
"grad_norm": 7.6875,
|
| 925 |
-
"learning_rate": 7.560840839617056e-05,
|
| 926 |
-
"loss": 0.3634,
|
| 927 |
-
"step": 1310
|
| 928 |
-
},
|
| 929 |
-
{
|
| 930 |
-
"epoch": 1.056,
|
| 931 |
-
"grad_norm": 4.03125,
|
| 932 |
-
"learning_rate": 7.523651080611341e-05,
|
| 933 |
-
"loss": 0.3653,
|
| 934 |
-
"step": 1320
|
| 935 |
-
},
|
| 936 |
-
{
|
| 937 |
-
"epoch": 1.064,
|
| 938 |
-
"grad_norm": 3.09375,
|
| 939 |
-
"learning_rate": 7.48627302618752e-05,
|
| 940 |
-
"loss": 0.3433,
|
| 941 |
-
"step": 1330
|
| 942 |
-
},
|
| 943 |
-
{
|
| 944 |
-
"epoch": 1.072,
|
| 945 |
-
"grad_norm": 4.21875,
|
| 946 |
-
"learning_rate": 7.448709465208299e-05,
|
| 947 |
-
"loss": 0.3587,
|
| 948 |
-
"step": 1340
|
| 949 |
-
},
|
| 950 |
-
{
|
| 951 |
-
"epoch": 1.08,
|
| 952 |
-
"grad_norm": 5.375,
|
| 953 |
-
"learning_rate": 7.410963200377458e-05,
|
| 954 |
-
"loss": 0.346,
|
| 955 |
-
"step": 1350
|
| 956 |
-
},
|
| 957 |
-
{
|
| 958 |
-
"epoch": 1.088,
|
| 959 |
-
"grad_norm": 4.0625,
|
| 960 |
-
"learning_rate": 7.373037048030731e-05,
|
| 961 |
-
"loss": 0.4562,
|
| 962 |
-
"step": 1360
|
| 963 |
-
},
|
| 964 |
-
{
|
| 965 |
-
"epoch": 1.096,
|
| 966 |
-
"grad_norm": 3.75,
|
| 967 |
-
"learning_rate": 7.334933837925675e-05,
|
| 968 |
-
"loss": 0.4333,
|
| 969 |
-
"step": 1370
|
| 970 |
-
},
|
| 971 |
-
{
|
| 972 |
-
"epoch": 1.104,
|
| 973 |
-
"grad_norm": 3.46875,
|
| 974 |
-
"learning_rate": 7.296656413030531e-05,
|
| 975 |
-
"loss": 0.306,
|
| 976 |
-
"step": 1380
|
| 977 |
-
},
|
| 978 |
-
{
|
| 979 |
-
"epoch": 1.112,
|
| 980 |
-
"grad_norm": 5.25,
|
| 981 |
-
"learning_rate": 7.25820762931211e-05,
|
| 982 |
-
"loss": 0.4095,
|
| 983 |
-
"step": 1390
|
| 984 |
-
},
|
| 985 |
-
{
|
| 986 |
-
"epoch": 1.12,
|
| 987 |
-
"grad_norm": 3.578125,
|
| 988 |
-
"learning_rate": 7.219590355522697e-05,
|
| 989 |
-
"loss": 0.369,
|
| 990 |
-
"step": 1400
|
| 991 |
-
},
|
| 992 |
-
{
|
| 993 |
-
"epoch": 1.1280000000000001,
|
| 994 |
-
"grad_norm": 4.96875,
|
| 995 |
-
"learning_rate": 7.180807472986009e-05,
|
| 996 |
-
"loss": 0.3763,
|
| 997 |
-
"step": 1410
|
| 998 |
-
},
|
| 999 |
-
{
|
| 1000 |
-
"epoch": 1.1360000000000001,
|
| 1001 |
-
"grad_norm": 5.25,
|
| 1002 |
-
"learning_rate": 7.141861875382215e-05,
|
| 1003 |
-
"loss": 0.4269,
|
| 1004 |
-
"step": 1420
|
| 1005 |
-
},
|
| 1006 |
-
{
|
| 1007 |
-
"epoch": 1.144,
|
| 1008 |
-
"grad_norm": 3.53125,
|
| 1009 |
-
"learning_rate": 7.102756468532027e-05,
|
| 1010 |
-
"loss": 0.4017,
|
| 1011 |
-
"step": 1430
|
| 1012 |
-
},
|
| 1013 |
-
{
|
| 1014 |
-
"epoch": 1.152,
|
| 1015 |
-
"grad_norm": 4.6875,
|
| 1016 |
-
"learning_rate": 7.063494170179898e-05,
|
| 1017 |
-
"loss": 0.3601,
|
| 1018 |
-
"step": 1440
|
| 1019 |
-
},
|
| 1020 |
-
{
|
| 1021 |
-
"epoch": 1.16,
|
| 1022 |
-
"grad_norm": 3.8125,
|
| 1023 |
-
"learning_rate": 7.024077909776309e-05,
|
| 1024 |
-
"loss": 0.3678,
|
| 1025 |
-
"step": 1450
|
| 1026 |
-
},
|
| 1027 |
-
{
|
| 1028 |
-
"epoch": 1.168,
|
| 1029 |
-
"grad_norm": 5.25,
|
| 1030 |
-
"learning_rate": 6.984510628259212e-05,
|
| 1031 |
-
"loss": 0.3732,
|
| 1032 |
-
"step": 1460
|
| 1033 |
-
},
|
| 1034 |
-
{
|
| 1035 |
-
"epoch": 1.176,
|
| 1036 |
-
"grad_norm": 2.140625,
|
| 1037 |
-
"learning_rate": 6.94479527783459e-05,
|
| 1038 |
-
"loss": 0.3332,
|
| 1039 |
-
"step": 1470
|
| 1040 |
-
},
|
| 1041 |
-
{
|
| 1042 |
-
"epoch": 1.184,
|
| 1043 |
-
"grad_norm": 4.5,
|
| 1044 |
-
"learning_rate": 6.904934821756184e-05,
|
| 1045 |
-
"loss": 0.3887,
|
| 1046 |
-
"step": 1480
|
| 1047 |
-
},
|
| 1048 |
-
{
|
| 1049 |
-
"epoch": 1.192,
|
| 1050 |
-
"grad_norm": 2.296875,
|
| 1051 |
-
"learning_rate": 6.864932234104409e-05,
|
| 1052 |
-
"loss": 0.3196,
|
| 1053 |
-
"step": 1490
|
| 1054 |
-
},
|
| 1055 |
-
{
|
| 1056 |
-
"epoch": 1.2,
|
| 1057 |
-
"grad_norm": 4.15625,
|
| 1058 |
-
"learning_rate": 6.824790499564435e-05,
|
| 1059 |
-
"loss": 0.3256,
|
| 1060 |
-
"step": 1500
|
| 1061 |
-
},
|
| 1062 |
-
{
|
| 1063 |
-
"epoch": 1.208,
|
| 1064 |
-
"grad_norm": 3.6875,
|
| 1065 |
-
"learning_rate": 6.784512613203511e-05,
|
| 1066 |
-
"loss": 0.3074,
|
| 1067 |
-
"step": 1510
|
| 1068 |
-
},
|
| 1069 |
-
{
|
| 1070 |
-
"epoch": 1.216,
|
| 1071 |
-
"grad_norm": 3.0,
|
| 1072 |
-
"learning_rate": 6.744101580247481e-05,
|
| 1073 |
-
"loss": 0.35,
|
| 1074 |
-
"step": 1520
|
| 1075 |
-
},
|
| 1076 |
-
{
|
| 1077 |
-
"epoch": 1.224,
|
| 1078 |
-
"grad_norm": 3.828125,
|
| 1079 |
-
"learning_rate": 6.703560415856565e-05,
|
| 1080 |
-
"loss": 0.3731,
|
| 1081 |
-
"step": 1530
|
| 1082 |
-
},
|
| 1083 |
-
{
|
| 1084 |
-
"epoch": 1.232,
|
| 1085 |
-
"grad_norm": 5.625,
|
| 1086 |
-
"learning_rate": 6.662892144900388e-05,
|
| 1087 |
-
"loss": 0.3769,
|
| 1088 |
-
"step": 1540
|
| 1089 |
-
},
|
| 1090 |
-
{
|
| 1091 |
-
"epoch": 1.24,
|
| 1092 |
-
"grad_norm": 8.1875,
|
| 1093 |
-
"learning_rate": 6.62209980173229e-05,
|
| 1094 |
-
"loss": 0.4385,
|
| 1095 |
-
"step": 1550
|
| 1096 |
-
},
|
| 1097 |
-
{
|
| 1098 |
-
"epoch": 1.248,
|
| 1099 |
-
"grad_norm": 5.9375,
|
| 1100 |
-
"learning_rate": 6.581186429962922e-05,
|
| 1101 |
-
"loss": 0.3563,
|
| 1102 |
-
"step": 1560
|
| 1103 |
-
},
|
| 1104 |
-
{
|
| 1105 |
-
"epoch": 1.256,
|
| 1106 |
-
"grad_norm": 3.53125,
|
| 1107 |
-
"learning_rate": 6.54015508223316e-05,
|
| 1108 |
-
"loss": 0.3225,
|
| 1109 |
-
"step": 1570
|
| 1110 |
-
},
|
| 1111 |
-
{
|
| 1112 |
-
"epoch": 1.264,
|
| 1113 |
-
"grad_norm": 4.125,
|
| 1114 |
-
"learning_rate": 6.499008819986339e-05,
|
| 1115 |
-
"loss": 0.3246,
|
| 1116 |
-
"step": 1580
|
| 1117 |
-
},
|
| 1118 |
-
{
|
| 1119 |
-
"epoch": 1.272,
|
| 1120 |
-
"grad_norm": 4.34375,
|
| 1121 |
-
"learning_rate": 6.457750713239828e-05,
|
| 1122 |
-
"loss": 0.304,
|
| 1123 |
-
"step": 1590
|
| 1124 |
-
},
|
| 1125 |
-
{
|
| 1126 |
-
"epoch": 1.28,
|
| 1127 |
-
"grad_norm": 4.75,
|
| 1128 |
-
"learning_rate": 6.41638384035597e-05,
|
| 1129 |
-
"loss": 0.383,
|
| 1130 |
-
"step": 1600
|
| 1131 |
-
},
|
| 1132 |
-
{
|
| 1133 |
-
"epoch": 1.288,
|
| 1134 |
-
"grad_norm": 4.46875,
|
| 1135 |
-
"learning_rate": 6.374911287812406e-05,
|
| 1136 |
-
"loss": 0.331,
|
| 1137 |
-
"step": 1610
|
| 1138 |
-
},
|
| 1139 |
-
{
|
| 1140 |
-
"epoch": 1.296,
|
| 1141 |
-
"grad_norm": 3.984375,
|
| 1142 |
-
"learning_rate": 6.333336149971776e-05,
|
| 1143 |
-
"loss": 0.3022,
|
| 1144 |
-
"step": 1620
|
| 1145 |
-
},
|
| 1146 |
-
{
|
| 1147 |
-
"epoch": 1.304,
|
| 1148 |
-
"grad_norm": 5.53125,
|
| 1149 |
-
"learning_rate": 6.291661528850844e-05,
|
| 1150 |
-
"loss": 0.3257,
|
| 1151 |
-
"step": 1630
|
| 1152 |
-
},
|
| 1153 |
-
{
|
| 1154 |
-
"epoch": 1.312,
|
| 1155 |
-
"grad_norm": 4.03125,
|
| 1156 |
-
"learning_rate": 6.249890533889054e-05,
|
| 1157 |
-
"loss": 0.3071,
|
| 1158 |
-
"step": 1640
|
| 1159 |
-
},
|
| 1160 |
-
{
|
| 1161 |
-
"epoch": 1.32,
|
| 1162 |
-
"grad_norm": 4.25,
|
| 1163 |
-
"learning_rate": 6.208026281716521e-05,
|
| 1164 |
-
"loss": 0.3833,
|
| 1165 |
-
"step": 1650
|
| 1166 |
-
},
|
| 1167 |
-
{
|
| 1168 |
-
"epoch": 1.328,
|
| 1169 |
-
"grad_norm": 3.109375,
|
| 1170 |
-
"learning_rate": 6.166071895921496e-05,
|
| 1171 |
-
"loss": 0.3378,
|
| 1172 |
-
"step": 1660
|
| 1173 |
-
},
|
| 1174 |
-
{
|
| 1175 |
-
"epoch": 1.336,
|
| 1176 |
-
"grad_norm": 3.5,
|
| 1177 |
-
"learning_rate": 6.124030506817309e-05,
|
| 1178 |
-
"loss": 0.31,
|
| 1179 |
-
"step": 1670
|
| 1180 |
-
},
|
| 1181 |
-
{
|
| 1182 |
-
"epoch": 1.3439999999999999,
|
| 1183 |
-
"grad_norm": 2.65625,
|
| 1184 |
-
"learning_rate": 6.0819052512088057e-05,
|
| 1185 |
-
"loss": 0.3139,
|
| 1186 |
-
"step": 1680
|
| 1187 |
-
},
|
| 1188 |
-
{
|
| 1189 |
-
"epoch": 1.3519999999999999,
|
| 1190 |
-
"grad_norm": 4.90625,
|
| 1191 |
-
"learning_rate": 6.039699272158305e-05,
|
| 1192 |
-
"loss": 0.4388,
|
| 1193 |
-
"step": 1690
|
| 1194 |
-
},
|
| 1195 |
-
{
|
| 1196 |
-
"epoch": 1.3599999999999999,
|
| 1197 |
-
"grad_norm": 5.59375,
|
| 1198 |
-
"learning_rate": 5.997415718751086e-05,
|
| 1199 |
-
"loss": 0.3989,
|
| 1200 |
-
"step": 1700
|
| 1201 |
-
},
|
| 1202 |
-
{
|
| 1203 |
-
"epoch": 1.3679999999999999,
|
| 1204 |
-
"grad_norm": 5.5,
|
| 1205 |
-
"learning_rate": 5.955057745860435e-05,
|
| 1206 |
-
"loss": 0.3977,
|
| 1207 |
-
"step": 1710
|
| 1208 |
-
},
|
| 1209 |
-
{
|
| 1210 |
-
"epoch": 1.376,
|
| 1211 |
-
"grad_norm": 6.25,
|
| 1212 |
-
"learning_rate": 5.9126285139122406e-05,
|
| 1213 |
-
"loss": 0.3527,
|
| 1214 |
-
"step": 1720
|
| 1215 |
-
},
|
| 1216 |
-
{
|
| 1217 |
-
"epoch": 1.384,
|
| 1218 |
-
"grad_norm": 3.28125,
|
| 1219 |
-
"learning_rate": 5.8701311886491947e-05,
|
| 1220 |
-
"loss": 0.4044,
|
| 1221 |
-
"step": 1730
|
| 1222 |
-
},
|
| 1223 |
-
{
|
| 1224 |
-
"epoch": 1.392,
|
| 1225 |
-
"grad_norm": 5.5625,
|
| 1226 |
-
"learning_rate": 5.827568940894593e-05,
|
| 1227 |
-
"loss": 0.374,
|
| 1228 |
-
"step": 1740
|
| 1229 |
-
},
|
| 1230 |
-
{
|
| 1231 |
-
"epoch": 1.4,
|
| 1232 |
-
"grad_norm": 3.625,
|
| 1233 |
-
"learning_rate": 5.7849449463157435e-05,
|
| 1234 |
-
"loss": 0.3479,
|
| 1235 |
-
"step": 1750
|
| 1236 |
-
},
|
| 1237 |
-
{
|
| 1238 |
-
"epoch": 1.408,
|
| 1239 |
-
"grad_norm": 4.84375,
|
| 1240 |
-
"learning_rate": 5.742262385187028e-05,
|
| 1241 |
-
"loss": 0.3666,
|
| 1242 |
-
"step": 1760
|
| 1243 |
-
},
|
| 1244 |
-
{
|
| 1245 |
-
"epoch": 1.416,
|
| 1246 |
-
"grad_norm": 5.4375,
|
| 1247 |
-
"learning_rate": 5.699524442152613e-05,
|
| 1248 |
-
"loss": 0.3707,
|
| 1249 |
-
"step": 1770
|
| 1250 |
-
},
|
| 1251 |
-
{
|
| 1252 |
-
"epoch": 1.424,
|
| 1253 |
-
"grad_norm": 4.4375,
|
| 1254 |
-
"learning_rate": 5.656734305988839e-05,
|
| 1255 |
-
"loss": 0.3847,
|
| 1256 |
-
"step": 1780
|
| 1257 |
-
},
|
| 1258 |
-
{
|
| 1259 |
-
"epoch": 1.432,
|
| 1260 |
-
"grad_norm": 3.96875,
|
| 1261 |
-
"learning_rate": 5.613895169366292e-05,
|
| 1262 |
-
"loss": 0.3515,
|
| 1263 |
-
"step": 1790
|
| 1264 |
-
},
|
| 1265 |
-
{
|
| 1266 |
-
"epoch": 1.44,
|
| 1267 |
-
"grad_norm": 3.734375,
|
| 1268 |
-
"learning_rate": 5.571010228611597e-05,
|
| 1269 |
-
"loss": 0.3763,
|
| 1270 |
-
"step": 1800
|
| 1271 |
-
},
|
| 1272 |
-
{
|
| 1273 |
-
"epoch": 1.448,
|
| 1274 |
-
"grad_norm": 5.71875,
|
| 1275 |
-
"learning_rate": 5.528082683468934e-05,
|
| 1276 |
-
"loss": 0.3548,
|
| 1277 |
-
"step": 1810
|
| 1278 |
-
},
|
| 1279 |
-
{
|
| 1280 |
-
"epoch": 1.456,
|
| 1281 |
-
"grad_norm": 5.03125,
|
| 1282 |
-
"learning_rate": 5.485115736861288e-05,
|
| 1283 |
-
"loss": 0.3903,
|
| 1284 |
-
"step": 1820
|
| 1285 |
-
},
|
| 1286 |
-
{
|
| 1287 |
-
"epoch": 1.464,
|
| 1288 |
-
"grad_norm": 4.375,
|
| 1289 |
-
"learning_rate": 5.442112594651484e-05,
|
| 1290 |
-
"loss": 0.257,
|
| 1291 |
-
"step": 1830
|
| 1292 |
-
},
|
| 1293 |
-
{
|
| 1294 |
-
"epoch": 1.472,
|
| 1295 |
-
"grad_norm": 5.46875,
|
| 1296 |
-
"learning_rate": 5.399076465402979e-05,
|
| 1297 |
-
"loss": 0.3424,
|
| 1298 |
-
"step": 1840
|
| 1299 |
-
},
|
| 1300 |
-
{
|
| 1301 |
-
"epoch": 1.48,
|
| 1302 |
-
"grad_norm": 3.40625,
|
| 1303 |
-
"learning_rate": 5.356010560140475e-05,
|
| 1304 |
-
"loss": 0.3317,
|
| 1305 |
-
"step": 1850
|
| 1306 |
-
},
|
| 1307 |
-
{
|
| 1308 |
-
"epoch": 1.488,
|
| 1309 |
-
"grad_norm": 5.0,
|
| 1310 |
-
"learning_rate": 5.312918092110325e-05,
|
| 1311 |
-
"loss": 0.2753,
|
| 1312 |
-
"step": 1860
|
| 1313 |
-
},
|
| 1314 |
-
{
|
| 1315 |
-
"epoch": 1.496,
|
| 1316 |
-
"grad_norm": 3.84375,
|
| 1317 |
-
"learning_rate": 5.269802276540795e-05,
|
| 1318 |
-
"loss": 0.3318,
|
| 1319 |
-
"step": 1870
|
| 1320 |
-
},
|
| 1321 |
-
{
|
| 1322 |
-
"epoch": 1.504,
|
| 1323 |
-
"grad_norm": 5.71875,
|
| 1324 |
-
"learning_rate": 5.226666330402164e-05,
|
| 1325 |
-
"loss": 0.3836,
|
| 1326 |
-
"step": 1880
|
| 1327 |
-
},
|
| 1328 |
-
{
|
| 1329 |
-
"epoch": 1.512,
|
| 1330 |
-
"grad_norm": 3.671875,
|
| 1331 |
-
"learning_rate": 5.1835134721666956e-05,
|
| 1332 |
-
"loss": 0.3498,
|
| 1333 |
-
"step": 1890
|
| 1334 |
-
},
|
| 1335 |
-
{
|
| 1336 |
-
"epoch": 1.52,
|
| 1337 |
-
"grad_norm": 2.90625,
|
| 1338 |
-
"learning_rate": 5.1403469215685094e-05,
|
| 1339 |
-
"loss": 0.4228,
|
| 1340 |
-
"step": 1900
|
| 1341 |
-
},
|
| 1342 |
-
{
|
| 1343 |
-
"epoch": 1.528,
|
| 1344 |
-
"grad_norm": 4.4375,
|
| 1345 |
-
"learning_rate": 5.097169899363342e-05,
|
| 1346 |
-
"loss": 0.3703,
|
| 1347 |
-
"step": 1910
|
| 1348 |
-
},
|
| 1349 |
-
{
|
| 1350 |
-
"epoch": 1.536,
|
| 1351 |
-
"grad_norm": 3.90625,
|
| 1352 |
-
"learning_rate": 5.053985627088238e-05,
|
| 1353 |
-
"loss": 0.3816,
|
| 1354 |
-
"step": 1920
|
| 1355 |
-
},
|
| 1356 |
-
{
|
| 1357 |
-
"epoch": 1.544,
|
| 1358 |
-
"grad_norm": 2.71875,
|
| 1359 |
-
"learning_rate": 5.010797326821189e-05,
|
| 1360 |
-
"loss": 0.3842,
|
| 1361 |
-
"step": 1930
|
| 1362 |
-
},
|
| 1363 |
-
{
|
| 1364 |
-
"epoch": 1.552,
|
| 1365 |
-
"grad_norm": 3.875,
|
| 1366 |
-
"learning_rate": 4.9676082209407254e-05,
|
| 1367 |
-
"loss": 0.3848,
|
| 1368 |
-
"step": 1940
|
| 1369 |
-
},
|
| 1370 |
-
{
|
| 1371 |
-
"epoch": 1.56,
|
| 1372 |
-
"grad_norm": 3.484375,
|
| 1373 |
-
"learning_rate": 4.924421531885481e-05,
|
| 1374 |
-
"loss": 0.3416,
|
| 1375 |
-
"step": 1950
|
| 1376 |
-
},
|
| 1377 |
-
{
|
| 1378 |
-
"epoch": 1.568,
|
| 1379 |
-
"grad_norm": 4.1875,
|
| 1380 |
-
"learning_rate": 4.881240481913773e-05,
|
| 1381 |
-
"loss": 0.3407,
|
| 1382 |
-
"step": 1960
|
| 1383 |
-
},
|
| 1384 |
-
{
|
| 1385 |
-
"epoch": 1.576,
|
| 1386 |
-
"grad_norm": 3.921875,
|
| 1387 |
-
"learning_rate": 4.838068292863164e-05,
|
| 1388 |
-
"loss": 0.3319,
|
| 1389 |
-
"step": 1970
|
| 1390 |
-
},
|
| 1391 |
-
{
|
| 1392 |
-
"epoch": 1.584,
|
| 1393 |
-
"grad_norm": 4.4375,
|
| 1394 |
-
"learning_rate": 4.7949081859100896e-05,
|
| 1395 |
-
"loss": 0.3979,
|
| 1396 |
-
"step": 1980
|
| 1397 |
-
},
|
| 1398 |
-
{
|
| 1399 |
-
"epoch": 1.592,
|
| 1400 |
-
"grad_norm": 4.84375,
|
| 1401 |
-
"learning_rate": 4.7517633813295114e-05,
|
| 1402 |
-
"loss": 0.4184,
|
| 1403 |
-
"step": 1990
|
| 1404 |
-
},
|
| 1405 |
-
{
|
| 1406 |
-
"epoch": 1.6,
|
| 1407 |
-
"grad_norm": 3.890625,
|
| 1408 |
-
"learning_rate": 4.708637098254644e-05,
|
| 1409 |
-
"loss": 0.3959,
|
| 1410 |
-
"step": 2000
|
| 1411 |
-
},
|
| 1412 |
-
{
|
| 1413 |
-
"epoch": 1.608,
|
| 1414 |
-
"grad_norm": 4.8125,
|
| 1415 |
-
"learning_rate": 4.6655325544367715e-05,
|
| 1416 |
-
"loss": 0.313,
|
| 1417 |
-
"step": 2010
|
| 1418 |
-
},
|
| 1419 |
-
{
|
| 1420 |
-
"epoch": 1.616,
|
| 1421 |
-
"grad_norm": 4.21875,
|
| 1422 |
-
"learning_rate": 4.6224529660051593e-05,
|
| 1423 |
-
"loss": 0.3012,
|
| 1424 |
-
"step": 2020
|
| 1425 |
-
},
|
| 1426 |
-
{
|
| 1427 |
-
"epoch": 1.624,
|
| 1428 |
-
"grad_norm": 3.734375,
|
| 1429 |
-
"learning_rate": 4.579401547227096e-05,
|
| 1430 |
-
"loss": 0.2532,
|
| 1431 |
-
"step": 2030
|
| 1432 |
-
},
|
| 1433 |
-
{
|
| 1434 |
-
"epoch": 1.6320000000000001,
|
| 1435 |
-
"grad_norm": 2.953125,
|
| 1436 |
-
"learning_rate": 4.53638151026807e-05,
|
| 1437 |
-
"loss": 0.2714,
|
| 1438 |
-
"step": 2040
|
| 1439 |
-
},
|
| 1440 |
-
{
|
| 1441 |
-
"epoch": 1.6400000000000001,
|
| 1442 |
-
"grad_norm": 4.1875,
|
| 1443 |
-
"learning_rate": 4.493396064952093e-05,
|
| 1444 |
-
"loss": 0.3468,
|
| 1445 |
-
"step": 2050
|
| 1446 |
-
},
|
| 1447 |
-
{
|
| 1448 |
-
"epoch": 1.6480000000000001,
|
| 1449 |
-
"grad_norm": 5.125,
|
| 1450 |
-
"learning_rate": 4.450448418522221e-05,
|
| 1451 |
-
"loss": 0.4547,
|
| 1452 |
-
"step": 2060
|
| 1453 |
-
},
|
| 1454 |
-
{
|
| 1455 |
-
"epoch": 1.6560000000000001,
|
| 1456 |
-
"grad_norm": 3.5,
|
| 1457 |
-
"learning_rate": 4.4075417754012475e-05,
|
| 1458 |
-
"loss": 0.2839,
|
| 1459 |
-
"step": 2070
|
| 1460 |
-
},
|
| 1461 |
-
{
|
| 1462 |
-
"epoch": 1.6640000000000001,
|
| 1463 |
-
"grad_norm": 5.84375,
|
| 1464 |
-
"learning_rate": 4.364679336952609e-05,
|
| 1465 |
-
"loss": 0.3426,
|
| 1466 |
-
"step": 2080
|
| 1467 |
-
},
|
| 1468 |
-
{
|
| 1469 |
-
"epoch": 1.6720000000000002,
|
| 1470 |
-
"grad_norm": 4.84375,
|
| 1471 |
-
"learning_rate": 4.321864301241535e-05,
|
| 1472 |
-
"loss": 0.3325,
|
| 1473 |
-
"step": 2090
|
| 1474 |
-
},
|
| 1475 |
-
{
|
| 1476 |
-
"epoch": 1.6800000000000002,
|
| 1477 |
-
"grad_norm": 4.46875,
|
| 1478 |
-
"learning_rate": 4.279099862796427e-05,
|
| 1479 |
-
"loss": 0.314,
|
| 1480 |
-
"step": 2100
|
| 1481 |
-
},
|
| 1482 |
-
{
|
| 1483 |
-
"epoch": 1.688,
|
| 1484 |
-
"grad_norm": 2.8125,
|
| 1485 |
-
"learning_rate": 4.23638921237051e-05,
|
| 1486 |
-
"loss": 0.4189,
|
| 1487 |
-
"step": 2110
|
| 1488 |
-
},
|
| 1489 |
-
{
|
| 1490 |
-
"epoch": 1.696,
|
| 1491 |
-
"grad_norm": 3.59375,
|
| 1492 |
-
"learning_rate": 4.1937355367037516e-05,
|
| 1493 |
-
"loss": 0.3436,
|
| 1494 |
-
"step": 2120
|
| 1495 |
-
},
|
| 1496 |
-
{
|
| 1497 |
-
"epoch": 1.704,
|
| 1498 |
-
"grad_norm": 6.21875,
|
| 1499 |
-
"learning_rate": 4.151142018285112e-05,
|
| 1500 |
-
"loss": 0.3681,
|
| 1501 |
-
"step": 2130
|
| 1502 |
-
},
|
| 1503 |
-
{
|
| 1504 |
-
"epoch": 1.712,
|
| 1505 |
-
"grad_norm": 4.0625,
|
| 1506 |
-
"learning_rate": 4.1086118351150785e-05,
|
| 1507 |
-
"loss": 0.3716,
|
| 1508 |
-
"step": 2140
|
| 1509 |
-
},
|
| 1510 |
-
{
|
| 1511 |
-
"epoch": 1.72,
|
| 1512 |
-
"grad_norm": 2.703125,
|
| 1513 |
-
"learning_rate": 4.066148160468543e-05,
|
| 1514 |
-
"loss": 0.2761,
|
| 1515 |
-
"step": 2150
|
| 1516 |
-
},
|
| 1517 |
-
{
|
| 1518 |
-
"epoch": 1.728,
|
| 1519 |
-
"grad_norm": 3.765625,
|
| 1520 |
-
"learning_rate": 4.023754162658051e-05,
|
| 1521 |
-
"loss": 0.2904,
|
| 1522 |
-
"step": 2160
|
| 1523 |
-
},
|
| 1524 |
-
{
|
| 1525 |
-
"epoch": 1.736,
|
| 1526 |
-
"grad_norm": 5.4375,
|
| 1527 |
-
"learning_rate": 3.981433004797395e-05,
|
| 1528 |
-
"loss": 0.3563,
|
| 1529 |
-
"step": 2170
|
| 1530 |
-
},
|
| 1531 |
-
{
|
| 1532 |
-
"epoch": 1.744,
|
| 1533 |
-
"grad_norm": 4.125,
|
| 1534 |
-
"learning_rate": 3.939187844565616e-05,
|
| 1535 |
-
"loss": 0.3248,
|
| 1536 |
-
"step": 2180
|
| 1537 |
-
},
|
| 1538 |
-
{
|
| 1539 |
-
"epoch": 1.752,
|
| 1540 |
-
"grad_norm": 5.71875,
|
| 1541 |
-
"learning_rate": 3.897021833971386e-05,
|
| 1542 |
-
"loss": 0.3246,
|
| 1543 |
-
"step": 2190
|
| 1544 |
-
},
|
| 1545 |
-
{
|
| 1546 |
-
"epoch": 1.76,
|
| 1547 |
-
"grad_norm": 4.21875,
|
| 1548 |
-
"learning_rate": 3.8549381191178516e-05,
|
| 1549 |
-
"loss": 0.4073,
|
| 1550 |
-
"step": 2200
|
| 1551 |
-
},
|
| 1552 |
-
{
|
| 1553 |
-
"epoch": 1.768,
|
| 1554 |
-
"grad_norm": 4.4375,
|
| 1555 |
-
"learning_rate": 3.8129398399678814e-05,
|
| 1556 |
-
"loss": 0.4147,
|
| 1557 |
-
"step": 2210
|
| 1558 |
-
},
|
| 1559 |
-
{
|
| 1560 |
-
"epoch": 1.776,
|
| 1561 |
-
"grad_norm": 4.4375,
|
| 1562 |
-
"learning_rate": 3.771030130109785e-05,
|
| 1563 |
-
"loss": 0.2378,
|
| 1564 |
-
"step": 2220
|
| 1565 |
-
},
|
| 1566 |
-
{
|
| 1567 |
-
"epoch": 1.784,
|
| 1568 |
-
"grad_norm": 3.65625,
|
| 1569 |
-
"learning_rate": 3.729212116523518e-05,
|
| 1570 |
-
"loss": 0.3305,
|
| 1571 |
-
"step": 2230
|
| 1572 |
-
},
|
| 1573 |
-
{
|
| 1574 |
-
"epoch": 1.792,
|
| 1575 |
-
"grad_norm": 3.09375,
|
| 1576 |
-
"learning_rate": 3.6874889193473646e-05,
|
| 1577 |
-
"loss": 0.3865,
|
| 1578 |
-
"step": 2240
|
| 1579 |
-
},
|
| 1580 |
-
{
|
| 1581 |
-
"epoch": 1.8,
|
| 1582 |
-
"grad_norm": 4.5,
|
| 1583 |
-
"learning_rate": 3.64586365164514e-05,
|
| 1584 |
-
"loss": 0.3443,
|
| 1585 |
-
"step": 2250
|
| 1586 |
-
},
|
| 1587 |
-
{
|
| 1588 |
-
"epoch": 1.808,
|
| 1589 |
-
"grad_norm": 2.71875,
|
| 1590 |
-
"learning_rate": 3.604339419173912e-05,
|
| 1591 |
-
"loss": 0.2762,
|
| 1592 |
-
"step": 2260
|
| 1593 |
-
},
|
| 1594 |
-
{
|
| 1595 |
-
"epoch": 1.8159999999999998,
|
| 1596 |
-
"grad_norm": 5.15625,
|
| 1597 |
-
"learning_rate": 3.5629193201522794e-05,
|
| 1598 |
-
"loss": 0.3787,
|
| 1599 |
-
"step": 2270
|
| 1600 |
-
},
|
| 1601 |
-
{
|
| 1602 |
-
"epoch": 1.8239999999999998,
|
| 1603 |
-
"grad_norm": 5.53125,
|
| 1604 |
-
"learning_rate": 3.521606445029208e-05,
|
| 1605 |
-
"loss": 0.4157,
|
| 1606 |
-
"step": 2280
|
| 1607 |
-
},
|
| 1608 |
-
{
|
| 1609 |
-
"epoch": 1.8319999999999999,
|
| 1610 |
-
"grad_norm": 5.34375,
|
| 1611 |
-
"learning_rate": 3.480403876253432e-05,
|
| 1612 |
-
"loss": 0.3345,
|
| 1613 |
-
"step": 2290
|
| 1614 |
-
},
|
| 1615 |
-
{
|
| 1616 |
-
"epoch": 1.8399999999999999,
|
| 1617 |
-
"grad_norm": 3.3125,
|
| 1618 |
-
"learning_rate": 3.4393146880434845e-05,
|
| 1619 |
-
"loss": 0.3111,
|
| 1620 |
-
"step": 2300
|
| 1621 |
-
},
|
| 1622 |
-
{
|
| 1623 |
-
"epoch": 1.8479999999999999,
|
| 1624 |
-
"grad_norm": 4.03125,
|
| 1625 |
-
"learning_rate": 3.398341946158311e-05,
|
| 1626 |
-
"loss": 0.3763,
|
| 1627 |
-
"step": 2310
|
| 1628 |
-
},
|
| 1629 |
-
{
|
| 1630 |
-
"epoch": 1.8559999999999999,
|
| 1631 |
-
"grad_norm": 3.703125,
|
| 1632 |
-
"learning_rate": 3.357488707668529e-05,
|
| 1633 |
-
"loss": 0.3246,
|
| 1634 |
-
"step": 2320
|
| 1635 |
-
},
|
| 1636 |
-
{
|
| 1637 |
-
"epoch": 1.8639999999999999,
|
| 1638 |
-
"grad_norm": 4.65625,
|
| 1639 |
-
"learning_rate": 3.316758020728327e-05,
|
| 1640 |
-
"loss": 0.3852,
|
| 1641 |
-
"step": 2330
|
| 1642 |
-
},
|
| 1643 |
-
{
|
| 1644 |
-
"epoch": 1.8719999999999999,
|
| 1645 |
-
"grad_norm": 3.859375,
|
| 1646 |
-
"learning_rate": 3.276152924348046e-05,
|
| 1647 |
-
"loss": 0.3295,
|
| 1648 |
-
"step": 2340
|
| 1649 |
-
},
|
| 1650 |
-
{
|
| 1651 |
-
"epoch": 1.88,
|
| 1652 |
-
"grad_norm": 5.15625,
|
| 1653 |
-
"learning_rate": 3.2356764481674254e-05,
|
| 1654 |
-
"loss": 0.3567,
|
| 1655 |
-
"step": 2350
|
| 1656 |
-
},
|
| 1657 |
-
{
|
| 1658 |
-
"epoch": 1.888,
|
| 1659 |
-
"grad_norm": 3.421875,
|
| 1660 |
-
"learning_rate": 3.1953316122295554e-05,
|
| 1661 |
-
"loss": 0.3091,
|
| 1662 |
-
"step": 2360
|
| 1663 |
-
},
|
| 1664 |
-
{
|
| 1665 |
-
"epoch": 1.896,
|
| 1666 |
-
"grad_norm": 3.265625,
|
| 1667 |
-
"learning_rate": 3.1551214267555416e-05,
|
| 1668 |
-
"loss": 0.3847,
|
| 1669 |
-
"step": 2370
|
| 1670 |
-
},
|
| 1671 |
-
{
|
| 1672 |
-
"epoch": 1.904,
|
| 1673 |
-
"grad_norm": 6.09375,
|
| 1674 |
-
"learning_rate": 3.1150488919199124e-05,
|
| 1675 |
-
"loss": 0.3958,
|
| 1676 |
-
"step": 2380
|
| 1677 |
-
},
|
| 1678 |
-
{
|
| 1679 |
-
"epoch": 1.912,
|
| 1680 |
-
"grad_norm": 4.03125,
|
| 1681 |
-
"learning_rate": 3.075116997626764e-05,
|
| 1682 |
-
"loss": 0.384,
|
| 1683 |
-
"step": 2390
|
| 1684 |
-
},
|
| 1685 |
-
{
|
| 1686 |
-
"epoch": 1.92,
|
| 1687 |
-
"grad_norm": 4.0625,
|
| 1688 |
-
"learning_rate": 3.0353287232866736e-05,
|
| 1689 |
-
"loss": 0.3349,
|
| 1690 |
-
"step": 2400
|
| 1691 |
-
},
|
| 1692 |
-
{
|
| 1693 |
-
"epoch": 1.928,
|
| 1694 |
-
"grad_norm": 4.375,
|
| 1695 |
-
"learning_rate": 2.995687037594408e-05,
|
| 1696 |
-
"loss": 0.3801,
|
| 1697 |
-
"step": 2410
|
| 1698 |
-
},
|
| 1699 |
-
{
|
| 1700 |
-
"epoch": 1.936,
|
| 1701 |
-
"grad_norm": 5.09375,
|
| 1702 |
-
"learning_rate": 2.9561948983074174e-05,
|
| 1703 |
-
"loss": 0.3281,
|
| 1704 |
-
"step": 2420
|
| 1705 |
-
},
|
| 1706 |
-
{
|
| 1707 |
-
"epoch": 1.944,
|
| 1708 |
-
"grad_norm": 6.8125,
|
| 1709 |
-
"learning_rate": 2.916855252025149e-05,
|
| 1710 |
-
"loss": 0.3549,
|
| 1711 |
-
"step": 2430
|
| 1712 |
-
},
|
| 1713 |
-
{
|
| 1714 |
-
"epoch": 1.952,
|
| 1715 |
-
"grad_norm": 4.125,
|
| 1716 |
-
"learning_rate": 2.877671033969193e-05,
|
| 1717 |
-
"loss": 0.4092,
|
| 1718 |
-
"step": 2440
|
| 1719 |
-
},
|
| 1720 |
-
{
|
| 1721 |
-
"epoch": 1.96,
|
| 1722 |
-
"grad_norm": 4.21875,
|
| 1723 |
-
"learning_rate": 2.8386451677642878e-05,
|
| 1724 |
-
"loss": 0.3866,
|
| 1725 |
-
"step": 2450
|
| 1726 |
-
},
|
| 1727 |
-
{
|
| 1728 |
-
"epoch": 1.968,
|
| 1729 |
-
"grad_norm": 3.078125,
|
| 1730 |
-
"learning_rate": 2.7997805652201714e-05,
|
| 1731 |
-
"loss": 0.3484,
|
| 1732 |
-
"step": 2460
|
| 1733 |
-
},
|
| 1734 |
-
{
|
| 1735 |
-
"epoch": 1.976,
|
| 1736 |
-
"grad_norm": 4.09375,
|
| 1737 |
-
"learning_rate": 2.7610801261143283e-05,
|
| 1738 |
-
"loss": 0.3496,
|
| 1739 |
-
"step": 2470
|
| 1740 |
-
},
|
| 1741 |
-
{
|
| 1742 |
-
"epoch": 1.984,
|
| 1743 |
-
"grad_norm": 4.6875,
|
| 1744 |
-
"learning_rate": 2.7225467379756314e-05,
|
| 1745 |
-
"loss": 0.3691,
|
| 1746 |
-
"step": 2480
|
| 1747 |
-
},
|
| 1748 |
-
{
|
| 1749 |
-
"epoch": 1.992,
|
| 1750 |
-
"grad_norm": 5.5,
|
| 1751 |
-
"learning_rate": 2.6841832758689002e-05,
|
| 1752 |
-
"loss": 0.3698,
|
| 1753 |
-
"step": 2490
|
| 1754 |
-
},
|
| 1755 |
-
{
|
| 1756 |
-
"epoch": 2.0,
|
| 1757 |
-
"grad_norm": 3.875,
|
| 1758 |
-
"learning_rate": 2.645992602180377e-05,
|
| 1759 |
-
"loss": 0.3577,
|
| 1760 |
-
"step": 2500
|
| 1761 |
-
}
|
| 1762 |
-
],
|
| 1763 |
-
"logging_steps": 10,
|
| 1764 |
-
"max_steps": 3750,
|
| 1765 |
-
"num_input_tokens_seen": 0,
|
| 1766 |
-
"num_train_epochs": 3,
|
| 1767 |
-
"save_steps": 500,
|
| 1768 |
-
"stateful_callbacks": {
|
| 1769 |
-
"TrainerControl": {
|
| 1770 |
-
"args": {
|
| 1771 |
-
"should_epoch_stop": false,
|
| 1772 |
-
"should_evaluate": false,
|
| 1773 |
-
"should_log": false,
|
| 1774 |
-
"should_save": true,
|
| 1775 |
-
"should_training_stop": false
|
| 1776 |
-
},
|
| 1777 |
-
"attributes": {}
|
| 1778 |
-
}
|
| 1779 |
-
},
|
| 1780 |
-
"total_flos": 4.257447323738318e+17,
|
| 1781 |
-
"train_batch_size": 4,
|
| 1782 |
-
"trial_name": null,
|
| 1783 |
-
"trial_params": null
|
| 1784 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|