Remove unnecessary files to save space
Browse files- checkpoint-15260/trainer_state.json +0 -3477
checkpoint-15260/trainer_state.json
DELETED
|
@@ -1,3477 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_metric": null,
|
| 3 |
-
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.5524281861458541,
|
| 5 |
-
"eval_steps": 500,
|
| 6 |
-
"global_step": 15260,
|
| 7 |
-
"is_hyper_param_search": false,
|
| 8 |
-
"is_local_process_zero": true,
|
| 9 |
-
"is_world_process_zero": true,
|
| 10 |
-
"log_history": [
|
| 11 |
-
{
|
| 12 |
-
"epoch": 0.0011222328814234257,
|
| 13 |
-
"grad_norm": 37.096622467041016,
|
| 14 |
-
"learning_rate": 1.0157273918741808e-06,
|
| 15 |
-
"loss": 8.8686,
|
| 16 |
-
"step": 31
|
| 17 |
-
},
|
| 18 |
-
{
|
| 19 |
-
"epoch": 0.0022444657628468514,
|
| 20 |
-
"grad_norm": 13.880346298217773,
|
| 21 |
-
"learning_rate": 2.0314547837483616e-06,
|
| 22 |
-
"loss": 7.6419,
|
| 23 |
-
"step": 62
|
| 24 |
-
},
|
| 25 |
-
{
|
| 26 |
-
"epoch": 0.0033666986442702773,
|
| 27 |
-
"grad_norm": 16.09684944152832,
|
| 28 |
-
"learning_rate": 3.0471821756225426e-06,
|
| 29 |
-
"loss": 6.4382,
|
| 30 |
-
"step": 93
|
| 31 |
-
},
|
| 32 |
-
{
|
| 33 |
-
"epoch": 0.004488931525693703,
|
| 34 |
-
"grad_norm": 19.170230865478516,
|
| 35 |
-
"learning_rate": 4.062909567496723e-06,
|
| 36 |
-
"loss": 5.3399,
|
| 37 |
-
"step": 124
|
| 38 |
-
},
|
| 39 |
-
{
|
| 40 |
-
"epoch": 0.005611164407117128,
|
| 41 |
-
"grad_norm": 24.654130935668945,
|
| 42 |
-
"learning_rate": 5.078636959370905e-06,
|
| 43 |
-
"loss": 4.7646,
|
| 44 |
-
"step": 155
|
| 45 |
-
},
|
| 46 |
-
{
|
| 47 |
-
"epoch": 0.006733397288540555,
|
| 48 |
-
"grad_norm": 24.712974548339844,
|
| 49 |
-
"learning_rate": 6.094364351245085e-06,
|
| 50 |
-
"loss": 4.4667,
|
| 51 |
-
"step": 186
|
| 52 |
-
},
|
| 53 |
-
{
|
| 54 |
-
"epoch": 0.00785563016996398,
|
| 55 |
-
"grad_norm": 17.238990783691406,
|
| 56 |
-
"learning_rate": 7.110091743119267e-06,
|
| 57 |
-
"loss": 4.2168,
|
| 58 |
-
"step": 217
|
| 59 |
-
},
|
| 60 |
-
{
|
| 61 |
-
"epoch": 0.008977863051387406,
|
| 62 |
-
"grad_norm": 20.40213394165039,
|
| 63 |
-
"learning_rate": 8.125819134993446e-06,
|
| 64 |
-
"loss": 4.0355,
|
| 65 |
-
"step": 248
|
| 66 |
-
},
|
| 67 |
-
{
|
| 68 |
-
"epoch": 0.010100095932810832,
|
| 69 |
-
"grad_norm": 15.052313804626465,
|
| 70 |
-
"learning_rate": 9.141546526867629e-06,
|
| 71 |
-
"loss": 3.8458,
|
| 72 |
-
"step": 279
|
| 73 |
-
},
|
| 74 |
-
{
|
| 75 |
-
"epoch": 0.011222328814234257,
|
| 76 |
-
"grad_norm": 18.802026748657227,
|
| 77 |
-
"learning_rate": 1.015727391874181e-05,
|
| 78 |
-
"loss": 3.6688,
|
| 79 |
-
"step": 310
|
| 80 |
-
},
|
| 81 |
-
{
|
| 82 |
-
"epoch": 0.012344561695657683,
|
| 83 |
-
"grad_norm": 16.62171745300293,
|
| 84 |
-
"learning_rate": 1.117300131061599e-05,
|
| 85 |
-
"loss": 3.52,
|
| 86 |
-
"step": 341
|
| 87 |
-
},
|
| 88 |
-
{
|
| 89 |
-
"epoch": 0.01346679457708111,
|
| 90 |
-
"grad_norm": 16.29236602783203,
|
| 91 |
-
"learning_rate": 1.218872870249017e-05,
|
| 92 |
-
"loss": 3.402,
|
| 93 |
-
"step": 372
|
| 94 |
-
},
|
| 95 |
-
{
|
| 96 |
-
"epoch": 0.014589027458504534,
|
| 97 |
-
"grad_norm": 11.65068531036377,
|
| 98 |
-
"learning_rate": 1.3204456094364351e-05,
|
| 99 |
-
"loss": 3.2829,
|
| 100 |
-
"step": 403
|
| 101 |
-
},
|
| 102 |
-
{
|
| 103 |
-
"epoch": 0.01571126033992796,
|
| 104 |
-
"grad_norm": 10.617654800415039,
|
| 105 |
-
"learning_rate": 1.4220183486238533e-05,
|
| 106 |
-
"loss": 3.2008,
|
| 107 |
-
"step": 434
|
| 108 |
-
},
|
| 109 |
-
{
|
| 110 |
-
"epoch": 0.016833493221351387,
|
| 111 |
-
"grad_norm": 10.611294746398926,
|
| 112 |
-
"learning_rate": 1.5235910878112714e-05,
|
| 113 |
-
"loss": 3.1249,
|
| 114 |
-
"step": 465
|
| 115 |
-
},
|
| 116 |
-
{
|
| 117 |
-
"epoch": 0.01795572610277481,
|
| 118 |
-
"grad_norm": 9.946114540100098,
|
| 119 |
-
"learning_rate": 1.6251638269986893e-05,
|
| 120 |
-
"loss": 3.0503,
|
| 121 |
-
"step": 496
|
| 122 |
-
},
|
| 123 |
-
{
|
| 124 |
-
"epoch": 0.019077958984198236,
|
| 125 |
-
"grad_norm": 10.92148494720459,
|
| 126 |
-
"learning_rate": 1.7267365661861077e-05,
|
| 127 |
-
"loss": 2.9903,
|
| 128 |
-
"step": 527
|
| 129 |
-
},
|
| 130 |
-
{
|
| 131 |
-
"epoch": 0.020200191865621664,
|
| 132 |
-
"grad_norm": 8.329671859741211,
|
| 133 |
-
"learning_rate": 1.8283093053735257e-05,
|
| 134 |
-
"loss": 2.9261,
|
| 135 |
-
"step": 558
|
| 136 |
-
},
|
| 137 |
-
{
|
| 138 |
-
"epoch": 0.02132242474704509,
|
| 139 |
-
"grad_norm": 7.897571086883545,
|
| 140 |
-
"learning_rate": 1.9298820445609438e-05,
|
| 141 |
-
"loss": 2.889,
|
| 142 |
-
"step": 589
|
| 143 |
-
},
|
| 144 |
-
{
|
| 145 |
-
"epoch": 0.022444657628468513,
|
| 146 |
-
"grad_norm": 7.548309326171875,
|
| 147 |
-
"learning_rate": 2.031454783748362e-05,
|
| 148 |
-
"loss": 2.7945,
|
| 149 |
-
"step": 620
|
| 150 |
-
},
|
| 151 |
-
{
|
| 152 |
-
"epoch": 0.02356689050989194,
|
| 153 |
-
"grad_norm": 8.54383659362793,
|
| 154 |
-
"learning_rate": 2.13302752293578e-05,
|
| 155 |
-
"loss": 2.7538,
|
| 156 |
-
"step": 651
|
| 157 |
-
},
|
| 158 |
-
{
|
| 159 |
-
"epoch": 0.024689123391315366,
|
| 160 |
-
"grad_norm": 7.025435924530029,
|
| 161 |
-
"learning_rate": 2.234600262123198e-05,
|
| 162 |
-
"loss": 2.7075,
|
| 163 |
-
"step": 682
|
| 164 |
-
},
|
| 165 |
-
{
|
| 166 |
-
"epoch": 0.02581135627273879,
|
| 167 |
-
"grad_norm": 7.59956169128418,
|
| 168 |
-
"learning_rate": 2.336173001310616e-05,
|
| 169 |
-
"loss": 2.6625,
|
| 170 |
-
"step": 713
|
| 171 |
-
},
|
| 172 |
-
{
|
| 173 |
-
"epoch": 0.02693358915416222,
|
| 174 |
-
"grad_norm": 6.982921123504639,
|
| 175 |
-
"learning_rate": 2.437745740498034e-05,
|
| 176 |
-
"loss": 2.6248,
|
| 177 |
-
"step": 744
|
| 178 |
-
},
|
| 179 |
-
{
|
| 180 |
-
"epoch": 0.028055822035585643,
|
| 181 |
-
"grad_norm": 6.033556938171387,
|
| 182 |
-
"learning_rate": 2.5393184796854525e-05,
|
| 183 |
-
"loss": 2.5724,
|
| 184 |
-
"step": 775
|
| 185 |
-
},
|
| 186 |
-
{
|
| 187 |
-
"epoch": 0.029178054917009068,
|
| 188 |
-
"grad_norm": 6.674008846282959,
|
| 189 |
-
"learning_rate": 2.6408912188728702e-05,
|
| 190 |
-
"loss": 2.5292,
|
| 191 |
-
"step": 806
|
| 192 |
-
},
|
| 193 |
-
{
|
| 194 |
-
"epoch": 0.030300287798432492,
|
| 195 |
-
"grad_norm": 6.499022006988525,
|
| 196 |
-
"learning_rate": 2.7424639580602886e-05,
|
| 197 |
-
"loss": 2.496,
|
| 198 |
-
"step": 837
|
| 199 |
-
},
|
| 200 |
-
{
|
| 201 |
-
"epoch": 0.03142252067985592,
|
| 202 |
-
"grad_norm": 6.163687229156494,
|
| 203 |
-
"learning_rate": 2.8440366972477066e-05,
|
| 204 |
-
"loss": 2.4541,
|
| 205 |
-
"step": 868
|
| 206 |
-
},
|
| 207 |
-
{
|
| 208 |
-
"epoch": 0.032544753561279345,
|
| 209 |
-
"grad_norm": 5.20266580581665,
|
| 210 |
-
"learning_rate": 2.9456094364351244e-05,
|
| 211 |
-
"loss": 2.449,
|
| 212 |
-
"step": 899
|
| 213 |
-
},
|
| 214 |
-
{
|
| 215 |
-
"epoch": 0.03366698644270277,
|
| 216 |
-
"grad_norm": 5.6633830070495605,
|
| 217 |
-
"learning_rate": 3.0471821756225428e-05,
|
| 218 |
-
"loss": 2.4085,
|
| 219 |
-
"step": 930
|
| 220 |
-
},
|
| 221 |
-
{
|
| 222 |
-
"epoch": 0.034789219324126194,
|
| 223 |
-
"grad_norm": 6.414912700653076,
|
| 224 |
-
"learning_rate": 3.148754914809961e-05,
|
| 225 |
-
"loss": 2.3791,
|
| 226 |
-
"step": 961
|
| 227 |
-
},
|
| 228 |
-
{
|
| 229 |
-
"epoch": 0.03591145220554962,
|
| 230 |
-
"grad_norm": 4.983119964599609,
|
| 231 |
-
"learning_rate": 3.2503276539973785e-05,
|
| 232 |
-
"loss": 2.3505,
|
| 233 |
-
"step": 992
|
| 234 |
-
},
|
| 235 |
-
{
|
| 236 |
-
"epoch": 0.03703368508697305,
|
| 237 |
-
"grad_norm": 5.280698299407959,
|
| 238 |
-
"learning_rate": 3.351900393184797e-05,
|
| 239 |
-
"loss": 2.3191,
|
| 240 |
-
"step": 1023
|
| 241 |
-
},
|
| 242 |
-
{
|
| 243 |
-
"epoch": 0.03815591796839647,
|
| 244 |
-
"grad_norm": 5.565277099609375,
|
| 245 |
-
"learning_rate": 3.453473132372215e-05,
|
| 246 |
-
"loss": 2.2957,
|
| 247 |
-
"step": 1054
|
| 248 |
-
},
|
| 249 |
-
{
|
| 250 |
-
"epoch": 0.0392781508498199,
|
| 251 |
-
"grad_norm": 5.02451753616333,
|
| 252 |
-
"learning_rate": 3.555045871559633e-05,
|
| 253 |
-
"loss": 2.2618,
|
| 254 |
-
"step": 1085
|
| 255 |
-
},
|
| 256 |
-
{
|
| 257 |
-
"epoch": 0.04040038373124333,
|
| 258 |
-
"grad_norm": 4.424225807189941,
|
| 259 |
-
"learning_rate": 3.6566186107470514e-05,
|
| 260 |
-
"loss": 2.2512,
|
| 261 |
-
"step": 1116
|
| 262 |
-
},
|
| 263 |
-
{
|
| 264 |
-
"epoch": 0.04152261661266675,
|
| 265 |
-
"grad_norm": 6.270051002502441,
|
| 266 |
-
"learning_rate": 3.7581913499344695e-05,
|
| 267 |
-
"loss": 2.2354,
|
| 268 |
-
"step": 1147
|
| 269 |
-
},
|
| 270 |
-
{
|
| 271 |
-
"epoch": 0.04264484949409018,
|
| 272 |
-
"grad_norm": 14.256332397460938,
|
| 273 |
-
"learning_rate": 3.8597640891218876e-05,
|
| 274 |
-
"loss": 2.2364,
|
| 275 |
-
"step": 1178
|
| 276 |
-
},
|
| 277 |
-
{
|
| 278 |
-
"epoch": 0.043767082375513605,
|
| 279 |
-
"grad_norm": 4.837010383605957,
|
| 280 |
-
"learning_rate": 3.9613368283093056e-05,
|
| 281 |
-
"loss": 2.2346,
|
| 282 |
-
"step": 1209
|
| 283 |
-
},
|
| 284 |
-
{
|
| 285 |
-
"epoch": 0.044889315256937026,
|
| 286 |
-
"grad_norm": 3.9555633068084717,
|
| 287 |
-
"learning_rate": 4.062909567496724e-05,
|
| 288 |
-
"loss": 2.2003,
|
| 289 |
-
"step": 1240
|
| 290 |
-
},
|
| 291 |
-
{
|
| 292 |
-
"epoch": 0.046011548138360454,
|
| 293 |
-
"grad_norm": 4.136904716491699,
|
| 294 |
-
"learning_rate": 4.164482306684142e-05,
|
| 295 |
-
"loss": 2.2056,
|
| 296 |
-
"step": 1271
|
| 297 |
-
},
|
| 298 |
-
{
|
| 299 |
-
"epoch": 0.04713378101978388,
|
| 300 |
-
"grad_norm": 4.25378942489624,
|
| 301 |
-
"learning_rate": 4.26605504587156e-05,
|
| 302 |
-
"loss": 2.1395,
|
| 303 |
-
"step": 1302
|
| 304 |
-
},
|
| 305 |
-
{
|
| 306 |
-
"epoch": 0.048256013901207304,
|
| 307 |
-
"grad_norm": 3.6108360290527344,
|
| 308 |
-
"learning_rate": 4.367627785058978e-05,
|
| 309 |
-
"loss": 2.1296,
|
| 310 |
-
"step": 1333
|
| 311 |
-
},
|
| 312 |
-
{
|
| 313 |
-
"epoch": 0.04937824678263073,
|
| 314 |
-
"grad_norm": 3.66212797164917,
|
| 315 |
-
"learning_rate": 4.469200524246396e-05,
|
| 316 |
-
"loss": 2.1316,
|
| 317 |
-
"step": 1364
|
| 318 |
-
},
|
| 319 |
-
{
|
| 320 |
-
"epoch": 0.05050047966405416,
|
| 321 |
-
"grad_norm": 3.5523183345794678,
|
| 322 |
-
"learning_rate": 4.570773263433814e-05,
|
| 323 |
-
"loss": 2.1381,
|
| 324 |
-
"step": 1395
|
| 325 |
-
},
|
| 326 |
-
{
|
| 327 |
-
"epoch": 0.05162271254547758,
|
| 328 |
-
"grad_norm": 3.710803747177124,
|
| 329 |
-
"learning_rate": 4.672346002621232e-05,
|
| 330 |
-
"loss": 2.1296,
|
| 331 |
-
"step": 1426
|
| 332 |
-
},
|
| 333 |
-
{
|
| 334 |
-
"epoch": 0.05274494542690101,
|
| 335 |
-
"grad_norm": 3.346266031265259,
|
| 336 |
-
"learning_rate": 4.77391874180865e-05,
|
| 337 |
-
"loss": 2.0755,
|
| 338 |
-
"step": 1457
|
| 339 |
-
},
|
| 340 |
-
{
|
| 341 |
-
"epoch": 0.05386717830832444,
|
| 342 |
-
"grad_norm": 3.264901876449585,
|
| 343 |
-
"learning_rate": 4.875491480996068e-05,
|
| 344 |
-
"loss": 2.0902,
|
| 345 |
-
"step": 1488
|
| 346 |
-
},
|
| 347 |
-
{
|
| 348 |
-
"epoch": 0.05498941118974786,
|
| 349 |
-
"grad_norm": 3.031913995742798,
|
| 350 |
-
"learning_rate": 4.977064220183487e-05,
|
| 351 |
-
"loss": 2.1002,
|
| 352 |
-
"step": 1519
|
| 353 |
-
},
|
| 354 |
-
{
|
| 355 |
-
"epoch": 0.056111644071171286,
|
| 356 |
-
"grad_norm": 3.3827006816864014,
|
| 357 |
-
"learning_rate": 4.9999915451558777e-05,
|
| 358 |
-
"loss": 2.111,
|
| 359 |
-
"step": 1550
|
| 360 |
-
},
|
| 361 |
-
{
|
| 362 |
-
"epoch": 0.057233876952594714,
|
| 363 |
-
"grad_norm": 3.5572054386138916,
|
| 364 |
-
"learning_rate": 4.999955597496219e-05,
|
| 365 |
-
"loss": 2.0809,
|
| 366 |
-
"step": 1581
|
| 367 |
-
},
|
| 368 |
-
{
|
| 369 |
-
"epoch": 0.058356109834018136,
|
| 370 |
-
"grad_norm": 3.2875311374664307,
|
| 371 |
-
"learning_rate": 4.9998914381774255e-05,
|
| 372 |
-
"loss": 2.0562,
|
| 373 |
-
"step": 1612
|
| 374 |
-
},
|
| 375 |
-
{
|
| 376 |
-
"epoch": 0.059478342715441564,
|
| 377 |
-
"grad_norm": 2.903362274169922,
|
| 378 |
-
"learning_rate": 4.999799067923527e-05,
|
| 379 |
-
"loss": 2.0598,
|
| 380 |
-
"step": 1643
|
| 381 |
-
},
|
| 382 |
-
{
|
| 383 |
-
"epoch": 0.060600575596864985,
|
| 384 |
-
"grad_norm": 2.980804681777954,
|
| 385 |
-
"learning_rate": 4.999678487776908e-05,
|
| 386 |
-
"loss": 2.0458,
|
| 387 |
-
"step": 1674
|
| 388 |
-
},
|
| 389 |
-
{
|
| 390 |
-
"epoch": 0.06172280847828841,
|
| 391 |
-
"grad_norm": 2.880610466003418,
|
| 392 |
-
"learning_rate": 4.9995296990983006e-05,
|
| 393 |
-
"loss": 2.0433,
|
| 394 |
-
"step": 1705
|
| 395 |
-
},
|
| 396 |
-
{
|
| 397 |
-
"epoch": 0.06284504135971183,
|
| 398 |
-
"grad_norm": 2.7269234657287598,
|
| 399 |
-
"learning_rate": 4.999352703566763e-05,
|
| 400 |
-
"loss": 2.0189,
|
| 401 |
-
"step": 1736
|
| 402 |
-
},
|
| 403 |
-
{
|
| 404 |
-
"epoch": 0.06396727424113527,
|
| 405 |
-
"grad_norm": 2.808084487915039,
|
| 406 |
-
"learning_rate": 4.999147503179668e-05,
|
| 407 |
-
"loss": 2.0083,
|
| 408 |
-
"step": 1767
|
| 409 |
-
},
|
| 410 |
-
{
|
| 411 |
-
"epoch": 0.06508950712255869,
|
| 412 |
-
"grad_norm": 2.925065279006958,
|
| 413 |
-
"learning_rate": 4.998914100252672e-05,
|
| 414 |
-
"loss": 2.001,
|
| 415 |
-
"step": 1798
|
| 416 |
-
},
|
| 417 |
-
{
|
| 418 |
-
"epoch": 0.06621174000398211,
|
| 419 |
-
"grad_norm": 2.996300458908081,
|
| 420 |
-
"learning_rate": 4.998652497419696e-05,
|
| 421 |
-
"loss": 1.9877,
|
| 422 |
-
"step": 1829
|
| 423 |
-
},
|
| 424 |
-
{
|
| 425 |
-
"epoch": 0.06733397288540555,
|
| 426 |
-
"grad_norm": 2.6028084754943848,
|
| 427 |
-
"learning_rate": 4.9983626976328927e-05,
|
| 428 |
-
"loss": 1.9778,
|
| 429 |
-
"step": 1860
|
| 430 |
-
},
|
| 431 |
-
{
|
| 432 |
-
"epoch": 0.06845620576682897,
|
| 433 |
-
"grad_norm": 2.4577603340148926,
|
| 434 |
-
"learning_rate": 4.998044704162613e-05,
|
| 435 |
-
"loss": 1.9998,
|
| 436 |
-
"step": 1891
|
| 437 |
-
},
|
| 438 |
-
{
|
| 439 |
-
"epoch": 0.06957843864825239,
|
| 440 |
-
"grad_norm": 2.4269509315490723,
|
| 441 |
-
"learning_rate": 4.9976985205973705e-05,
|
| 442 |
-
"loss": 1.9813,
|
| 443 |
-
"step": 1922
|
| 444 |
-
},
|
| 445 |
-
{
|
| 446 |
-
"epoch": 0.07070067152967582,
|
| 447 |
-
"grad_norm": 2.6069250106811523,
|
| 448 |
-
"learning_rate": 4.997324150843799e-05,
|
| 449 |
-
"loss": 1.9781,
|
| 450 |
-
"step": 1953
|
| 451 |
-
},
|
| 452 |
-
{
|
| 453 |
-
"epoch": 0.07182290441109924,
|
| 454 |
-
"grad_norm": 2.5287699699401855,
|
| 455 |
-
"learning_rate": 4.99692159912661e-05,
|
| 456 |
-
"loss": 1.9684,
|
| 457 |
-
"step": 1984
|
| 458 |
-
},
|
| 459 |
-
{
|
| 460 |
-
"epoch": 0.07294513729252267,
|
| 461 |
-
"grad_norm": 2.6519899368286133,
|
| 462 |
-
"learning_rate": 4.996490869988546e-05,
|
| 463 |
-
"loss": 1.9821,
|
| 464 |
-
"step": 2015
|
| 465 |
-
},
|
| 466 |
-
{
|
| 467 |
-
"epoch": 0.0740673701739461,
|
| 468 |
-
"grad_norm": 2.525928497314453,
|
| 469 |
-
"learning_rate": 4.996031968290326e-05,
|
| 470 |
-
"loss": 1.9512,
|
| 471 |
-
"step": 2046
|
| 472 |
-
},
|
| 473 |
-
{
|
| 474 |
-
"epoch": 0.07518960305536952,
|
| 475 |
-
"grad_norm": 2.4517486095428467,
|
| 476 |
-
"learning_rate": 4.995544899210594e-05,
|
| 477 |
-
"loss": 1.9283,
|
| 478 |
-
"step": 2077
|
| 479 |
-
},
|
| 480 |
-
{
|
| 481 |
-
"epoch": 0.07631183593679294,
|
| 482 |
-
"grad_norm": 2.7807457447052,
|
| 483 |
-
"learning_rate": 4.9950296682458583e-05,
|
| 484 |
-
"loss": 1.9448,
|
| 485 |
-
"step": 2108
|
| 486 |
-
},
|
| 487 |
-
{
|
| 488 |
-
"epoch": 0.07743406881821638,
|
| 489 |
-
"grad_norm": 2.4739558696746826,
|
| 490 |
-
"learning_rate": 4.994486281210429e-05,
|
| 491 |
-
"loss": 1.946,
|
| 492 |
-
"step": 2139
|
| 493 |
-
},
|
| 494 |
-
{
|
| 495 |
-
"epoch": 0.0785563016996398,
|
| 496 |
-
"grad_norm": 2.6515214443206787,
|
| 497 |
-
"learning_rate": 4.9939147442363566e-05,
|
| 498 |
-
"loss": 1.9474,
|
| 499 |
-
"step": 2170
|
| 500 |
-
},
|
| 501 |
-
{
|
| 502 |
-
"epoch": 0.07967853458106322,
|
| 503 |
-
"grad_norm": 2.8361852169036865,
|
| 504 |
-
"learning_rate": 4.9933150637733574e-05,
|
| 505 |
-
"loss": 1.9463,
|
| 506 |
-
"step": 2201
|
| 507 |
-
},
|
| 508 |
-
{
|
| 509 |
-
"epoch": 0.08080076746248666,
|
| 510 |
-
"grad_norm": 2.332261323928833,
|
| 511 |
-
"learning_rate": 4.992687246588743e-05,
|
| 512 |
-
"loss": 1.9607,
|
| 513 |
-
"step": 2232
|
| 514 |
-
},
|
| 515 |
-
{
|
| 516 |
-
"epoch": 0.08192300034391008,
|
| 517 |
-
"grad_norm": 2.3486499786376953,
|
| 518 |
-
"learning_rate": 4.992031299767347e-05,
|
| 519 |
-
"loss": 1.9248,
|
| 520 |
-
"step": 2263
|
| 521 |
-
},
|
| 522 |
-
{
|
| 523 |
-
"epoch": 0.0830452332253335,
|
| 524 |
-
"grad_norm": 3.125208616256714,
|
| 525 |
-
"learning_rate": 4.9913472307114386e-05,
|
| 526 |
-
"loss": 1.9088,
|
| 527 |
-
"step": 2294
|
| 528 |
-
},
|
| 529 |
-
{
|
| 530 |
-
"epoch": 0.08416746610675693,
|
| 531 |
-
"grad_norm": 2.2809853553771973,
|
| 532 |
-
"learning_rate": 4.9906350471406446e-05,
|
| 533 |
-
"loss": 1.9199,
|
| 534 |
-
"step": 2325
|
| 535 |
-
},
|
| 536 |
-
{
|
| 537 |
-
"epoch": 0.08528969898818035,
|
| 538 |
-
"grad_norm": 2.567641258239746,
|
| 539 |
-
"learning_rate": 4.989894757091861e-05,
|
| 540 |
-
"loss": 1.9054,
|
| 541 |
-
"step": 2356
|
| 542 |
-
},
|
| 543 |
-
{
|
| 544 |
-
"epoch": 0.08641193186960378,
|
| 545 |
-
"grad_norm": 2.2755303382873535,
|
| 546 |
-
"learning_rate": 4.989126368919158e-05,
|
| 547 |
-
"loss": 1.903,
|
| 548 |
-
"step": 2387
|
| 549 |
-
},
|
| 550 |
-
{
|
| 551 |
-
"epoch": 0.08753416475102721,
|
| 552 |
-
"grad_norm": 2.147775888442993,
|
| 553 |
-
"learning_rate": 4.988329891293693e-05,
|
| 554 |
-
"loss": 1.8993,
|
| 555 |
-
"step": 2418
|
| 556 |
-
},
|
| 557 |
-
{
|
| 558 |
-
"epoch": 0.08865639763245063,
|
| 559 |
-
"grad_norm": 2.2279839515686035,
|
| 560 |
-
"learning_rate": 4.987505333203608e-05,
|
| 561 |
-
"loss": 1.905,
|
| 562 |
-
"step": 2449
|
| 563 |
-
},
|
| 564 |
-
{
|
| 565 |
-
"epoch": 0.08977863051387405,
|
| 566 |
-
"grad_norm": 2.317538022994995,
|
| 567 |
-
"learning_rate": 4.9866527039539276e-05,
|
| 568 |
-
"loss": 1.8776,
|
| 569 |
-
"step": 2480
|
| 570 |
-
},
|
| 571 |
-
{
|
| 572 |
-
"epoch": 0.09090086339529749,
|
| 573 |
-
"grad_norm": 2.296868324279785,
|
| 574 |
-
"learning_rate": 4.9857720131664594e-05,
|
| 575 |
-
"loss": 1.8714,
|
| 576 |
-
"step": 2511
|
| 577 |
-
},
|
| 578 |
-
{
|
| 579 |
-
"epoch": 0.09202309627672091,
|
| 580 |
-
"grad_norm": 2.282538890838623,
|
| 581 |
-
"learning_rate": 4.9848632707796773e-05,
|
| 582 |
-
"loss": 1.8765,
|
| 583 |
-
"step": 2542
|
| 584 |
-
},
|
| 585 |
-
{
|
| 586 |
-
"epoch": 0.09314532915814433,
|
| 587 |
-
"grad_norm": 2.1396827697753906,
|
| 588 |
-
"learning_rate": 4.9839264870486155e-05,
|
| 589 |
-
"loss": 1.8827,
|
| 590 |
-
"step": 2573
|
| 591 |
-
},
|
| 592 |
-
{
|
| 593 |
-
"epoch": 0.09426756203956776,
|
| 594 |
-
"grad_norm": 2.1897048950195312,
|
| 595 |
-
"learning_rate": 4.9829616725447526e-05,
|
| 596 |
-
"loss": 1.8655,
|
| 597 |
-
"step": 2604
|
| 598 |
-
},
|
| 599 |
-
{
|
| 600 |
-
"epoch": 0.09538979492099119,
|
| 601 |
-
"grad_norm": 2.1385130882263184,
|
| 602 |
-
"learning_rate": 4.981968838155888e-05,
|
| 603 |
-
"loss": 1.8768,
|
| 604 |
-
"step": 2635
|
| 605 |
-
},
|
| 606 |
-
{
|
| 607 |
-
"epoch": 0.09651202780241461,
|
| 608 |
-
"grad_norm": 2.264171600341797,
|
| 609 |
-
"learning_rate": 4.980947995086024e-05,
|
| 610 |
-
"loss": 1.8734,
|
| 611 |
-
"step": 2666
|
| 612 |
-
},
|
| 613 |
-
{
|
| 614 |
-
"epoch": 0.09763426068383804,
|
| 615 |
-
"grad_norm": 2.089871883392334,
|
| 616 |
-
"learning_rate": 4.979899154855234e-05,
|
| 617 |
-
"loss": 1.8516,
|
| 618 |
-
"step": 2697
|
| 619 |
-
},
|
| 620 |
-
{
|
| 621 |
-
"epoch": 0.09875649356526146,
|
| 622 |
-
"grad_norm": 2.092179298400879,
|
| 623 |
-
"learning_rate": 4.9788223292995386e-05,
|
| 624 |
-
"loss": 1.8729,
|
| 625 |
-
"step": 2728
|
| 626 |
-
},
|
| 627 |
-
{
|
| 628 |
-
"epoch": 0.09987872644668488,
|
| 629 |
-
"grad_norm": 2.3216769695281982,
|
| 630 |
-
"learning_rate": 4.977717530570768e-05,
|
| 631 |
-
"loss": 1.8673,
|
| 632 |
-
"step": 2759
|
| 633 |
-
},
|
| 634 |
-
{
|
| 635 |
-
"epoch": 0.10100095932810832,
|
| 636 |
-
"grad_norm": 2.104457139968872,
|
| 637 |
-
"learning_rate": 4.976584771136425e-05,
|
| 638 |
-
"loss": 1.8734,
|
| 639 |
-
"step": 2790
|
| 640 |
-
},
|
| 641 |
-
{
|
| 642 |
-
"epoch": 0.10212319220953174,
|
| 643 |
-
"grad_norm": 2.236363649368286,
|
| 644 |
-
"learning_rate": 4.975424063779547e-05,
|
| 645 |
-
"loss": 1.8316,
|
| 646 |
-
"step": 2821
|
| 647 |
-
},
|
| 648 |
-
{
|
| 649 |
-
"epoch": 0.10324542509095516,
|
| 650 |
-
"grad_norm": 2.264967203140259,
|
| 651 |
-
"learning_rate": 4.974235421598557e-05,
|
| 652 |
-
"loss": 1.8614,
|
| 653 |
-
"step": 2852
|
| 654 |
-
},
|
| 655 |
-
{
|
| 656 |
-
"epoch": 0.1043676579723786,
|
| 657 |
-
"grad_norm": 2.1815454959869385,
|
| 658 |
-
"learning_rate": 4.973018858007122e-05,
|
| 659 |
-
"loss": 1.8365,
|
| 660 |
-
"step": 2883
|
| 661 |
-
},
|
| 662 |
-
{
|
| 663 |
-
"epoch": 0.10548989085380202,
|
| 664 |
-
"grad_norm": 2.049677848815918,
|
| 665 |
-
"learning_rate": 4.9717743867339963e-05,
|
| 666 |
-
"loss": 1.8454,
|
| 667 |
-
"step": 2914
|
| 668 |
-
},
|
| 669 |
-
{
|
| 670 |
-
"epoch": 0.10661212373522544,
|
| 671 |
-
"grad_norm": 1.9844895601272583,
|
| 672 |
-
"learning_rate": 4.9705020218228695e-05,
|
| 673 |
-
"loss": 1.8419,
|
| 674 |
-
"step": 2945
|
| 675 |
-
},
|
| 676 |
-
{
|
| 677 |
-
"epoch": 0.10773435661664887,
|
| 678 |
-
"grad_norm": 2.052708387374878,
|
| 679 |
-
"learning_rate": 4.969201777632205e-05,
|
| 680 |
-
"loss": 1.8509,
|
| 681 |
-
"step": 2976
|
| 682 |
-
},
|
| 683 |
-
{
|
| 684 |
-
"epoch": 0.1088565894980723,
|
| 685 |
-
"grad_norm": 2.014535665512085,
|
| 686 |
-
"learning_rate": 4.9678736688350846e-05,
|
| 687 |
-
"loss": 1.8129,
|
| 688 |
-
"step": 3007
|
| 689 |
-
},
|
| 690 |
-
{
|
| 691 |
-
"epoch": 0.10997882237949572,
|
| 692 |
-
"grad_norm": 1.9768311977386475,
|
| 693 |
-
"learning_rate": 4.966517710419033e-05,
|
| 694 |
-
"loss": 1.8375,
|
| 695 |
-
"step": 3038
|
| 696 |
-
},
|
| 697 |
-
{
|
| 698 |
-
"epoch": 0.11110105526091915,
|
| 699 |
-
"grad_norm": 2.046293258666992,
|
| 700 |
-
"learning_rate": 4.965133917685858e-05,
|
| 701 |
-
"loss": 1.8132,
|
| 702 |
-
"step": 3069
|
| 703 |
-
},
|
| 704 |
-
{
|
| 705 |
-
"epoch": 0.11222328814234257,
|
| 706 |
-
"grad_norm": 2.104555368423462,
|
| 707 |
-
"learning_rate": 4.9637223062514714e-05,
|
| 708 |
-
"loss": 1.8147,
|
| 709 |
-
"step": 3100
|
| 710 |
-
},
|
| 711 |
-
{
|
| 712 |
-
"epoch": 0.113345521023766,
|
| 713 |
-
"grad_norm": 2.04533052444458,
|
| 714 |
-
"learning_rate": 4.962282892045718e-05,
|
| 715 |
-
"loss": 1.8591,
|
| 716 |
-
"step": 3131
|
| 717 |
-
},
|
| 718 |
-
{
|
| 719 |
-
"epoch": 0.11446775390518943,
|
| 720 |
-
"grad_norm": 1.967282772064209,
|
| 721 |
-
"learning_rate": 4.9608156913121904e-05,
|
| 722 |
-
"loss": 1.7966,
|
| 723 |
-
"step": 3162
|
| 724 |
-
},
|
| 725 |
-
{
|
| 726 |
-
"epoch": 0.11558998678661285,
|
| 727 |
-
"grad_norm": 2.092106342315674,
|
| 728 |
-
"learning_rate": 4.959320720608049e-05,
|
| 729 |
-
"loss": 1.8301,
|
| 730 |
-
"step": 3193
|
| 731 |
-
},
|
| 732 |
-
{
|
| 733 |
-
"epoch": 0.11671221966803627,
|
| 734 |
-
"grad_norm": 2.0512046813964844,
|
| 735 |
-
"learning_rate": 4.9577979968038354e-05,
|
| 736 |
-
"loss": 1.8211,
|
| 737 |
-
"step": 3224
|
| 738 |
-
},
|
| 739 |
-
{
|
| 740 |
-
"epoch": 0.11783445254945969,
|
| 741 |
-
"grad_norm": 1.9260915517807007,
|
| 742 |
-
"learning_rate": 4.956247537083282e-05,
|
| 743 |
-
"loss": 1.7989,
|
| 744 |
-
"step": 3255
|
| 745 |
-
},
|
| 746 |
-
{
|
| 747 |
-
"epoch": 0.11895668543088313,
|
| 748 |
-
"grad_norm": 2.0938026905059814,
|
| 749 |
-
"learning_rate": 4.9546693589431145e-05,
|
| 750 |
-
"loss": 1.8336,
|
| 751 |
-
"step": 3286
|
| 752 |
-
},
|
| 753 |
-
{
|
| 754 |
-
"epoch": 0.12007891831230655,
|
| 755 |
-
"grad_norm": 1.9972988367080688,
|
| 756 |
-
"learning_rate": 4.9530634801928595e-05,
|
| 757 |
-
"loss": 1.8147,
|
| 758 |
-
"step": 3317
|
| 759 |
-
},
|
| 760 |
-
{
|
| 761 |
-
"epoch": 0.12120115119372997,
|
| 762 |
-
"grad_norm": 1.9120224714279175,
|
| 763 |
-
"learning_rate": 4.9514299189546395e-05,
|
| 764 |
-
"loss": 1.8028,
|
| 765 |
-
"step": 3348
|
| 766 |
-
},
|
| 767 |
-
{
|
| 768 |
-
"epoch": 0.1223233840751534,
|
| 769 |
-
"grad_norm": 1.959033727645874,
|
| 770 |
-
"learning_rate": 4.949768693662973e-05,
|
| 771 |
-
"loss": 1.8281,
|
| 772 |
-
"step": 3379
|
| 773 |
-
},
|
| 774 |
-
{
|
| 775 |
-
"epoch": 0.12344561695657683,
|
| 776 |
-
"grad_norm": 1.9182357788085938,
|
| 777 |
-
"learning_rate": 4.948079823064559e-05,
|
| 778 |
-
"loss": 1.8165,
|
| 779 |
-
"step": 3410
|
| 780 |
-
},
|
| 781 |
-
{
|
| 782 |
-
"epoch": 0.12456784983800025,
|
| 783 |
-
"grad_norm": 1.9079999923706055,
|
| 784 |
-
"learning_rate": 4.946363326218074e-05,
|
| 785 |
-
"loss": 1.7916,
|
| 786 |
-
"step": 3441
|
| 787 |
-
},
|
| 788 |
-
{
|
| 789 |
-
"epoch": 0.12569008271942367,
|
| 790 |
-
"grad_norm": 1.916276216506958,
|
| 791 |
-
"learning_rate": 4.9446192224939525e-05,
|
| 792 |
-
"loss": 1.8086,
|
| 793 |
-
"step": 3472
|
| 794 |
-
},
|
| 795 |
-
{
|
| 796 |
-
"epoch": 0.1268123156008471,
|
| 797 |
-
"grad_norm": 1.903389811515808,
|
| 798 |
-
"learning_rate": 4.942847531574167e-05,
|
| 799 |
-
"loss": 1.8116,
|
| 800 |
-
"step": 3503
|
| 801 |
-
},
|
| 802 |
-
{
|
| 803 |
-
"epoch": 0.12793454848227054,
|
| 804 |
-
"grad_norm": 2.064885139465332,
|
| 805 |
-
"learning_rate": 4.941048273452008e-05,
|
| 806 |
-
"loss": 1.8144,
|
| 807 |
-
"step": 3534
|
| 808 |
-
},
|
| 809 |
-
{
|
| 810 |
-
"epoch": 0.12905678136369395,
|
| 811 |
-
"grad_norm": 2.1314241886138916,
|
| 812 |
-
"learning_rate": 4.9392214684318605e-05,
|
| 813 |
-
"loss": 1.7943,
|
| 814 |
-
"step": 3565
|
| 815 |
-
},
|
| 816 |
-
{
|
| 817 |
-
"epoch": 0.13017901424511738,
|
| 818 |
-
"grad_norm": 2.0061681270599365,
|
| 819 |
-
"learning_rate": 4.93736713712897e-05,
|
| 820 |
-
"loss": 1.794,
|
| 821 |
-
"step": 3596
|
| 822 |
-
},
|
| 823 |
-
{
|
| 824 |
-
"epoch": 0.13130124712654082,
|
| 825 |
-
"grad_norm": 1.9408286809921265,
|
| 826 |
-
"learning_rate": 4.9354853004692124e-05,
|
| 827 |
-
"loss": 1.7882,
|
| 828 |
-
"step": 3627
|
| 829 |
-
},
|
| 830 |
-
{
|
| 831 |
-
"epoch": 0.13242348000796422,
|
| 832 |
-
"grad_norm": 1.8884766101837158,
|
| 833 |
-
"learning_rate": 4.93357597968886e-05,
|
| 834 |
-
"loss": 1.7846,
|
| 835 |
-
"step": 3658
|
| 836 |
-
},
|
| 837 |
-
{
|
| 838 |
-
"epoch": 0.13354571288938766,
|
| 839 |
-
"grad_norm": 1.9393378496170044,
|
| 840 |
-
"learning_rate": 4.931639196334338e-05,
|
| 841 |
-
"loss": 1.7923,
|
| 842 |
-
"step": 3689
|
| 843 |
-
},
|
| 844 |
-
{
|
| 845 |
-
"epoch": 0.1346679457708111,
|
| 846 |
-
"grad_norm": 1.8815410137176514,
|
| 847 |
-
"learning_rate": 4.9296749722619826e-05,
|
| 848 |
-
"loss": 1.7939,
|
| 849 |
-
"step": 3720
|
| 850 |
-
},
|
| 851 |
-
{
|
| 852 |
-
"epoch": 0.1357901786522345,
|
| 853 |
-
"grad_norm": 1.8603038787841797,
|
| 854 |
-
"learning_rate": 4.9276833296377966e-05,
|
| 855 |
-
"loss": 1.7589,
|
| 856 |
-
"step": 3751
|
| 857 |
-
},
|
| 858 |
-
{
|
| 859 |
-
"epoch": 0.13691241153365794,
|
| 860 |
-
"grad_norm": 1.775247573852539,
|
| 861 |
-
"learning_rate": 4.925664290937196e-05,
|
| 862 |
-
"loss": 1.7897,
|
| 863 |
-
"step": 3782
|
| 864 |
-
},
|
| 865 |
-
{
|
| 866 |
-
"epoch": 0.13803464441508137,
|
| 867 |
-
"grad_norm": 1.8576780557632446,
|
| 868 |
-
"learning_rate": 4.9236178789447576e-05,
|
| 869 |
-
"loss": 1.7908,
|
| 870 |
-
"step": 3813
|
| 871 |
-
},
|
| 872 |
-
{
|
| 873 |
-
"epoch": 0.13915687729650478,
|
| 874 |
-
"grad_norm": 1.800264596939087,
|
| 875 |
-
"learning_rate": 4.921544116753962e-05,
|
| 876 |
-
"loss": 1.7736,
|
| 877 |
-
"step": 3844
|
| 878 |
-
},
|
| 879 |
-
{
|
| 880 |
-
"epoch": 0.1402791101779282,
|
| 881 |
-
"grad_norm": 1.9730401039123535,
|
| 882 |
-
"learning_rate": 4.919443027766935e-05,
|
| 883 |
-
"loss": 1.7639,
|
| 884 |
-
"step": 3875
|
| 885 |
-
},
|
| 886 |
-
{
|
| 887 |
-
"epoch": 0.14140134305935165,
|
| 888 |
-
"grad_norm": 1.8654968738555908,
|
| 889 |
-
"learning_rate": 4.91731463569418e-05,
|
| 890 |
-
"loss": 1.7477,
|
| 891 |
-
"step": 3906
|
| 892 |
-
},
|
| 893 |
-
{
|
| 894 |
-
"epoch": 0.14252357594077505,
|
| 895 |
-
"grad_norm": 1.8131386041641235,
|
| 896 |
-
"learning_rate": 4.915158964554312e-05,
|
| 897 |
-
"loss": 1.7887,
|
| 898 |
-
"step": 3937
|
| 899 |
-
},
|
| 900 |
-
{
|
| 901 |
-
"epoch": 0.1436458088221985,
|
| 902 |
-
"grad_norm": 1.8576264381408691,
|
| 903 |
-
"learning_rate": 4.912976038673786e-05,
|
| 904 |
-
"loss": 1.7779,
|
| 905 |
-
"step": 3968
|
| 906 |
-
},
|
| 907 |
-
{
|
| 908 |
-
"epoch": 0.14476804170362192,
|
| 909 |
-
"grad_norm": 1.8940199613571167,
|
| 910 |
-
"learning_rate": 4.9107658826866254e-05,
|
| 911 |
-
"loss": 1.7653,
|
| 912 |
-
"step": 3999
|
| 913 |
-
},
|
| 914 |
-
{
|
| 915 |
-
"epoch": 0.14589027458504533,
|
| 916 |
-
"grad_norm": 1.7727802991867065,
|
| 917 |
-
"learning_rate": 4.908528521534139e-05,
|
| 918 |
-
"loss": 1.7809,
|
| 919 |
-
"step": 4030
|
| 920 |
-
},
|
| 921 |
-
{
|
| 922 |
-
"epoch": 0.14701250746646877,
|
| 923 |
-
"grad_norm": 1.7416553497314453,
|
| 924 |
-
"learning_rate": 4.906263980464644e-05,
|
| 925 |
-
"loss": 1.7605,
|
| 926 |
-
"step": 4061
|
| 927 |
-
},
|
| 928 |
-
{
|
| 929 |
-
"epoch": 0.1481347403478922,
|
| 930 |
-
"grad_norm": 1.82987642288208,
|
| 931 |
-
"learning_rate": 4.903972285033178e-05,
|
| 932 |
-
"loss": 1.7554,
|
| 933 |
-
"step": 4092
|
| 934 |
-
},
|
| 935 |
-
{
|
| 936 |
-
"epoch": 0.1492569732293156,
|
| 937 |
-
"grad_norm": 1.916339635848999,
|
| 938 |
-
"learning_rate": 4.901653461101213e-05,
|
| 939 |
-
"loss": 1.7872,
|
| 940 |
-
"step": 4123
|
| 941 |
-
},
|
| 942 |
-
{
|
| 943 |
-
"epoch": 0.15037920611073904,
|
| 944 |
-
"grad_norm": 1.8903008699417114,
|
| 945 |
-
"learning_rate": 4.8993075348363626e-05,
|
| 946 |
-
"loss": 1.782,
|
| 947 |
-
"step": 4154
|
| 948 |
-
},
|
| 949 |
-
{
|
| 950 |
-
"epoch": 0.15150143899216248,
|
| 951 |
-
"grad_norm": 1.9334847927093506,
|
| 952 |
-
"learning_rate": 4.896934532712084e-05,
|
| 953 |
-
"loss": 1.7565,
|
| 954 |
-
"step": 4185
|
| 955 |
-
},
|
| 956 |
-
{
|
| 957 |
-
"epoch": 0.1526236718735859,
|
| 958 |
-
"grad_norm": 1.7778478860855103,
|
| 959 |
-
"learning_rate": 4.8945344815073846e-05,
|
| 960 |
-
"loss": 1.7613,
|
| 961 |
-
"step": 4216
|
| 962 |
-
},
|
| 963 |
-
{
|
| 964 |
-
"epoch": 0.15374590475500932,
|
| 965 |
-
"grad_norm": 1.7348295450210571,
|
| 966 |
-
"learning_rate": 4.892107408306516e-05,
|
| 967 |
-
"loss": 1.7512,
|
| 968 |
-
"step": 4247
|
| 969 |
-
},
|
| 970 |
-
{
|
| 971 |
-
"epoch": 0.15486813763643276,
|
| 972 |
-
"grad_norm": 1.7189710140228271,
|
| 973 |
-
"learning_rate": 4.889653340498669e-05,
|
| 974 |
-
"loss": 1.741,
|
| 975 |
-
"step": 4278
|
| 976 |
-
},
|
| 977 |
-
{
|
| 978 |
-
"epoch": 0.15599037051785616,
|
| 979 |
-
"grad_norm": 1.8557075262069702,
|
| 980 |
-
"learning_rate": 4.8871723057776664e-05,
|
| 981 |
-
"loss": 1.7471,
|
| 982 |
-
"step": 4309
|
| 983 |
-
},
|
| 984 |
-
{
|
| 985 |
-
"epoch": 0.1571126033992796,
|
| 986 |
-
"grad_norm": 1.7188880443572998,
|
| 987 |
-
"learning_rate": 4.8846643321416476e-05,
|
| 988 |
-
"loss": 1.7492,
|
| 989 |
-
"step": 4340
|
| 990 |
-
},
|
| 991 |
-
{
|
| 992 |
-
"epoch": 0.15823483628070303,
|
| 993 |
-
"grad_norm": 1.6712063550949097,
|
| 994 |
-
"learning_rate": 4.882129447892753e-05,
|
| 995 |
-
"loss": 1.7434,
|
| 996 |
-
"step": 4371
|
| 997 |
-
},
|
| 998 |
-
{
|
| 999 |
-
"epoch": 0.15935706916212644,
|
| 1000 |
-
"grad_norm": 1.7652437686920166,
|
| 1001 |
-
"learning_rate": 4.8795676816368076e-05,
|
| 1002 |
-
"loss": 1.7422,
|
| 1003 |
-
"step": 4402
|
| 1004 |
-
},
|
| 1005 |
-
{
|
| 1006 |
-
"epoch": 0.16047930204354988,
|
| 1007 |
-
"grad_norm": 1.7910144329071045,
|
| 1008 |
-
"learning_rate": 4.876979062282995e-05,
|
| 1009 |
-
"loss": 1.7635,
|
| 1010 |
-
"step": 4433
|
| 1011 |
-
},
|
| 1012 |
-
{
|
| 1013 |
-
"epoch": 0.1616015349249733,
|
| 1014 |
-
"grad_norm": 1.9248684644699097,
|
| 1015 |
-
"learning_rate": 4.8743636190435325e-05,
|
| 1016 |
-
"loss": 1.7401,
|
| 1017 |
-
"step": 4464
|
| 1018 |
-
},
|
| 1019 |
-
{
|
| 1020 |
-
"epoch": 0.16272376780639672,
|
| 1021 |
-
"grad_norm": 1.828202486038208,
|
| 1022 |
-
"learning_rate": 4.871721381433344e-05,
|
| 1023 |
-
"loss": 1.7419,
|
| 1024 |
-
"step": 4495
|
| 1025 |
-
},
|
| 1026 |
-
{
|
| 1027 |
-
"epoch": 0.16384600068782015,
|
| 1028 |
-
"grad_norm": 1.7170790433883667,
|
| 1029 |
-
"learning_rate": 4.869052379269719e-05,
|
| 1030 |
-
"loss": 1.7562,
|
| 1031 |
-
"step": 4526
|
| 1032 |
-
},
|
| 1033 |
-
{
|
| 1034 |
-
"epoch": 0.1649682335692436,
|
| 1035 |
-
"grad_norm": 1.753203272819519,
|
| 1036 |
-
"learning_rate": 4.866356642671985e-05,
|
| 1037 |
-
"loss": 1.7569,
|
| 1038 |
-
"step": 4557
|
| 1039 |
-
},
|
| 1040 |
-
{
|
| 1041 |
-
"epoch": 0.166090466450667,
|
| 1042 |
-
"grad_norm": 1.7906442880630493,
|
| 1043 |
-
"learning_rate": 4.8636342020611634e-05,
|
| 1044 |
-
"loss": 1.7376,
|
| 1045 |
-
"step": 4588
|
| 1046 |
-
},
|
| 1047 |
-
{
|
| 1048 |
-
"epoch": 0.16721269933209043,
|
| 1049 |
-
"grad_norm": 1.7113378047943115,
|
| 1050 |
-
"learning_rate": 4.860885088159626e-05,
|
| 1051 |
-
"loss": 1.7386,
|
| 1052 |
-
"step": 4619
|
| 1053 |
-
},
|
| 1054 |
-
{
|
| 1055 |
-
"epoch": 0.16833493221351387,
|
| 1056 |
-
"grad_norm": 1.7997937202453613,
|
| 1057 |
-
"learning_rate": 4.858109331990751e-05,
|
| 1058 |
-
"loss": 1.7531,
|
| 1059 |
-
"step": 4650
|
| 1060 |
-
},
|
| 1061 |
-
{
|
| 1062 |
-
"epoch": 0.16945716509493727,
|
| 1063 |
-
"grad_norm": 1.76421320438385,
|
| 1064 |
-
"learning_rate": 4.855306964878567e-05,
|
| 1065 |
-
"loss": 1.7402,
|
| 1066 |
-
"step": 4681
|
| 1067 |
-
},
|
| 1068 |
-
{
|
| 1069 |
-
"epoch": 0.1705793979763607,
|
| 1070 |
-
"grad_norm": 1.7803616523742676,
|
| 1071 |
-
"learning_rate": 4.8524780184474084e-05,
|
| 1072 |
-
"loss": 1.7345,
|
| 1073 |
-
"step": 4712
|
| 1074 |
-
},
|
| 1075 |
-
{
|
| 1076 |
-
"epoch": 0.17170163085778414,
|
| 1077 |
-
"grad_norm": 1.7763142585754395,
|
| 1078 |
-
"learning_rate": 4.8496225246215496e-05,
|
| 1079 |
-
"loss": 1.7469,
|
| 1080 |
-
"step": 4743
|
| 1081 |
-
},
|
| 1082 |
-
{
|
| 1083 |
-
"epoch": 0.17282386373920755,
|
| 1084 |
-
"grad_norm": 1.728219747543335,
|
| 1085 |
-
"learning_rate": 4.8467405156248505e-05,
|
| 1086 |
-
"loss": 1.7182,
|
| 1087 |
-
"step": 4774
|
| 1088 |
-
},
|
| 1089 |
-
{
|
| 1090 |
-
"epoch": 0.17394609662063099,
|
| 1091 |
-
"grad_norm": 1.7837860584259033,
|
| 1092 |
-
"learning_rate": 4.843832023980392e-05,
|
| 1093 |
-
"loss": 1.739,
|
| 1094 |
-
"step": 4805
|
| 1095 |
-
},
|
| 1096 |
-
{
|
| 1097 |
-
"epoch": 0.17506832950205442,
|
| 1098 |
-
"grad_norm": 1.7005128860473633,
|
| 1099 |
-
"learning_rate": 4.840897082510106e-05,
|
| 1100 |
-
"loss": 1.7377,
|
| 1101 |
-
"step": 4836
|
| 1102 |
-
},
|
| 1103 |
-
{
|
| 1104 |
-
"epoch": 0.17619056238347783,
|
| 1105 |
-
"grad_norm": 1.6570392847061157,
|
| 1106 |
-
"learning_rate": 4.8379357243344084e-05,
|
| 1107 |
-
"loss": 1.712,
|
| 1108 |
-
"step": 4867
|
| 1109 |
-
},
|
| 1110 |
-
{
|
| 1111 |
-
"epoch": 0.17731279526490126,
|
| 1112 |
-
"grad_norm": 1.6575350761413574,
|
| 1113 |
-
"learning_rate": 4.8349479828718236e-05,
|
| 1114 |
-
"loss": 1.7147,
|
| 1115 |
-
"step": 4898
|
| 1116 |
-
},
|
| 1117 |
-
{
|
| 1118 |
-
"epoch": 0.1784350281463247,
|
| 1119 |
-
"grad_norm": 1.8768808841705322,
|
| 1120 |
-
"learning_rate": 4.8319338918386075e-05,
|
| 1121 |
-
"loss": 1.7312,
|
| 1122 |
-
"step": 4929
|
| 1123 |
-
},
|
| 1124 |
-
{
|
| 1125 |
-
"epoch": 0.1795572610277481,
|
| 1126 |
-
"grad_norm": 1.7145389318466187,
|
| 1127 |
-
"learning_rate": 4.828893485248369e-05,
|
| 1128 |
-
"loss": 1.7221,
|
| 1129 |
-
"step": 4960
|
| 1130 |
-
},
|
| 1131 |
-
{
|
| 1132 |
-
"epoch": 0.18067949390917154,
|
| 1133 |
-
"grad_norm": 1.834173560142517,
|
| 1134 |
-
"learning_rate": 4.825826797411682e-05,
|
| 1135 |
-
"loss": 1.7322,
|
| 1136 |
-
"step": 4991
|
| 1137 |
-
},
|
| 1138 |
-
{
|
| 1139 |
-
"epoch": 0.18180172679059498,
|
| 1140 |
-
"grad_norm": 1.7125933170318604,
|
| 1141 |
-
"learning_rate": 4.822733862935702e-05,
|
| 1142 |
-
"loss": 1.7156,
|
| 1143 |
-
"step": 5022
|
| 1144 |
-
},
|
| 1145 |
-
{
|
| 1146 |
-
"epoch": 0.18292395967201838,
|
| 1147 |
-
"grad_norm": 1.7470024824142456,
|
| 1148 |
-
"learning_rate": 4.819614716723775e-05,
|
| 1149 |
-
"loss": 1.7176,
|
| 1150 |
-
"step": 5053
|
| 1151 |
-
},
|
| 1152 |
-
{
|
| 1153 |
-
"epoch": 0.18404619255344182,
|
| 1154 |
-
"grad_norm": 1.7042289972305298,
|
| 1155 |
-
"learning_rate": 4.8164693939750425e-05,
|
| 1156 |
-
"loss": 1.7192,
|
| 1157 |
-
"step": 5084
|
| 1158 |
-
},
|
| 1159 |
-
{
|
| 1160 |
-
"epoch": 0.18516842543486525,
|
| 1161 |
-
"grad_norm": 1.6803418397903442,
|
| 1162 |
-
"learning_rate": 4.813297930184042e-05,
|
| 1163 |
-
"loss": 1.7197,
|
| 1164 |
-
"step": 5115
|
| 1165 |
-
},
|
| 1166 |
-
{
|
| 1167 |
-
"epoch": 0.18629065831628866,
|
| 1168 |
-
"grad_norm": 1.7296956777572632,
|
| 1169 |
-
"learning_rate": 4.810100361140314e-05,
|
| 1170 |
-
"loss": 1.72,
|
| 1171 |
-
"step": 5146
|
| 1172 |
-
},
|
| 1173 |
-
{
|
| 1174 |
-
"epoch": 0.1874128911977121,
|
| 1175 |
-
"grad_norm": 1.6245464086532593,
|
| 1176 |
-
"learning_rate": 4.8068767229279885e-05,
|
| 1177 |
-
"loss": 1.7081,
|
| 1178 |
-
"step": 5177
|
| 1179 |
-
},
|
| 1180 |
-
{
|
| 1181 |
-
"epoch": 0.18853512407913553,
|
| 1182 |
-
"grad_norm": 1.7138885259628296,
|
| 1183 |
-
"learning_rate": 4.8036270519253854e-05,
|
| 1184 |
-
"loss": 1.7068,
|
| 1185 |
-
"step": 5208
|
| 1186 |
-
},
|
| 1187 |
-
{
|
| 1188 |
-
"epoch": 0.18965735696055894,
|
| 1189 |
-
"grad_norm": 1.704185128211975,
|
| 1190 |
-
"learning_rate": 4.8003513848046e-05,
|
| 1191 |
-
"loss": 1.7219,
|
| 1192 |
-
"step": 5239
|
| 1193 |
-
},
|
| 1194 |
-
{
|
| 1195 |
-
"epoch": 0.19077958984198237,
|
| 1196 |
-
"grad_norm": 1.712551236152649,
|
| 1197 |
-
"learning_rate": 4.79704975853109e-05,
|
| 1198 |
-
"loss": 1.7118,
|
| 1199 |
-
"step": 5270
|
| 1200 |
-
},
|
| 1201 |
-
{
|
| 1202 |
-
"epoch": 0.1919018227234058,
|
| 1203 |
-
"grad_norm": 1.7193052768707275,
|
| 1204 |
-
"learning_rate": 4.793722210363262e-05,
|
| 1205 |
-
"loss": 1.7195,
|
| 1206 |
-
"step": 5301
|
| 1207 |
-
},
|
| 1208 |
-
{
|
| 1209 |
-
"epoch": 0.19302405560482921,
|
| 1210 |
-
"grad_norm": 1.5574607849121094,
|
| 1211 |
-
"learning_rate": 4.7903687778520414e-05,
|
| 1212 |
-
"loss": 1.7286,
|
| 1213 |
-
"step": 5332
|
| 1214 |
-
},
|
| 1215 |
-
{
|
| 1216 |
-
"epoch": 0.19414628848625265,
|
| 1217 |
-
"grad_norm": 1.7480719089508057,
|
| 1218 |
-
"learning_rate": 4.7869894988404593e-05,
|
| 1219 |
-
"loss": 1.6957,
|
| 1220 |
-
"step": 5363
|
| 1221 |
-
},
|
| 1222 |
-
{
|
| 1223 |
-
"epoch": 0.19526852136767608,
|
| 1224 |
-
"grad_norm": 1.7487633228302002,
|
| 1225 |
-
"learning_rate": 4.783584411463221e-05,
|
| 1226 |
-
"loss": 1.7203,
|
| 1227 |
-
"step": 5394
|
| 1228 |
-
},
|
| 1229 |
-
{
|
| 1230 |
-
"epoch": 0.1963907542490995,
|
| 1231 |
-
"grad_norm": 1.6720587015151978,
|
| 1232 |
-
"learning_rate": 4.780153554146274e-05,
|
| 1233 |
-
"loss": 1.7009,
|
| 1234 |
-
"step": 5425
|
| 1235 |
-
},
|
| 1236 |
-
{
|
| 1237 |
-
"epoch": 0.19751298713052293,
|
| 1238 |
-
"grad_norm": 1.6622951030731201,
|
| 1239 |
-
"learning_rate": 4.7766969656063766e-05,
|
| 1240 |
-
"loss": 1.7049,
|
| 1241 |
-
"step": 5456
|
| 1242 |
-
},
|
| 1243 |
-
{
|
| 1244 |
-
"epoch": 0.19863522001194636,
|
| 1245 |
-
"grad_norm": 1.656158208847046,
|
| 1246 |
-
"learning_rate": 4.773214684850662e-05,
|
| 1247 |
-
"loss": 1.7104,
|
| 1248 |
-
"step": 5487
|
| 1249 |
-
},
|
| 1250 |
-
{
|
| 1251 |
-
"epoch": 0.19975745289336977,
|
| 1252 |
-
"grad_norm": 1.6559454202651978,
|
| 1253 |
-
"learning_rate": 4.769706751176193e-05,
|
| 1254 |
-
"loss": 1.7089,
|
| 1255 |
-
"step": 5518
|
| 1256 |
-
},
|
| 1257 |
-
{
|
| 1258 |
-
"epoch": 0.2008796857747932,
|
| 1259 |
-
"grad_norm": 1.7262494564056396,
|
| 1260 |
-
"learning_rate": 4.7661732041695264e-05,
|
| 1261 |
-
"loss": 1.7143,
|
| 1262 |
-
"step": 5549
|
| 1263 |
-
},
|
| 1264 |
-
{
|
| 1265 |
-
"epoch": 0.20200191865621664,
|
| 1266 |
-
"grad_norm": 1.6877381801605225,
|
| 1267 |
-
"learning_rate": 4.762614083706258e-05,
|
| 1268 |
-
"loss": 1.7134,
|
| 1269 |
-
"step": 5580
|
| 1270 |
-
},
|
| 1271 |
-
{
|
| 1272 |
-
"epoch": 0.20312415153764005,
|
| 1273 |
-
"grad_norm": 1.5669549703598022,
|
| 1274 |
-
"learning_rate": 4.759029429950581e-05,
|
| 1275 |
-
"loss": 1.7213,
|
| 1276 |
-
"step": 5611
|
| 1277 |
-
},
|
| 1278 |
-
{
|
| 1279 |
-
"epoch": 0.20424638441906348,
|
| 1280 |
-
"grad_norm": 1.7044217586517334,
|
| 1281 |
-
"learning_rate": 4.7554192833548235e-05,
|
| 1282 |
-
"loss": 1.7185,
|
| 1283 |
-
"step": 5642
|
| 1284 |
-
},
|
| 1285 |
-
{
|
| 1286 |
-
"epoch": 0.20536861730048692,
|
| 1287 |
-
"grad_norm": 1.6999757289886475,
|
| 1288 |
-
"learning_rate": 4.751783684659e-05,
|
| 1289 |
-
"loss": 1.7163,
|
| 1290 |
-
"step": 5673
|
| 1291 |
-
},
|
| 1292 |
-
{
|
| 1293 |
-
"epoch": 0.20649085018191032,
|
| 1294 |
-
"grad_norm": 1.6043522357940674,
|
| 1295 |
-
"learning_rate": 4.748122674890348e-05,
|
| 1296 |
-
"loss": 1.7031,
|
| 1297 |
-
"step": 5704
|
| 1298 |
-
},
|
| 1299 |
-
{
|
| 1300 |
-
"epoch": 0.20761308306333376,
|
| 1301 |
-
"grad_norm": 1.7062305212020874,
|
| 1302 |
-
"learning_rate": 4.7444362953628654e-05,
|
| 1303 |
-
"loss": 1.7035,
|
| 1304 |
-
"step": 5735
|
| 1305 |
-
},
|
| 1306 |
-
{
|
| 1307 |
-
"epoch": 0.2087353159447572,
|
| 1308 |
-
"grad_norm": 1.6612005233764648,
|
| 1309 |
-
"learning_rate": 4.7407245876768424e-05,
|
| 1310 |
-
"loss": 1.6981,
|
| 1311 |
-
"step": 5766
|
| 1312 |
-
},
|
| 1313 |
-
{
|
| 1314 |
-
"epoch": 0.2098575488261806,
|
| 1315 |
-
"grad_norm": 1.7277076244354248,
|
| 1316 |
-
"learning_rate": 4.736987593718397e-05,
|
| 1317 |
-
"loss": 1.7161,
|
| 1318 |
-
"step": 5797
|
| 1319 |
-
},
|
| 1320 |
-
{
|
| 1321 |
-
"epoch": 0.21097978170760404,
|
| 1322 |
-
"grad_norm": 1.705458402633667,
|
| 1323 |
-
"learning_rate": 4.733225355658999e-05,
|
| 1324 |
-
"loss": 1.6854,
|
| 1325 |
-
"step": 5828
|
| 1326 |
-
},
|
| 1327 |
-
{
|
| 1328 |
-
"epoch": 0.21210201458902747,
|
| 1329 |
-
"grad_norm": 1.629443883895874,
|
| 1330 |
-
"learning_rate": 4.7294379159549926e-05,
|
| 1331 |
-
"loss": 1.7025,
|
| 1332 |
-
"step": 5859
|
| 1333 |
-
},
|
| 1334 |
-
{
|
| 1335 |
-
"epoch": 0.21322424747045088,
|
| 1336 |
-
"grad_norm": 1.613192081451416,
|
| 1337 |
-
"learning_rate": 4.725625317347119e-05,
|
| 1338 |
-
"loss": 1.6992,
|
| 1339 |
-
"step": 5890
|
| 1340 |
-
},
|
| 1341 |
-
{
|
| 1342 |
-
"epoch": 0.2143464803518743,
|
| 1343 |
-
"grad_norm": 1.6801332235336304,
|
| 1344 |
-
"learning_rate": 4.7217876028600374e-05,
|
| 1345 |
-
"loss": 1.6798,
|
| 1346 |
-
"step": 5921
|
| 1347 |
-
},
|
| 1348 |
-
{
|
| 1349 |
-
"epoch": 0.21546871323329775,
|
| 1350 |
-
"grad_norm": 1.6418830156326294,
|
| 1351 |
-
"learning_rate": 4.717924815801832e-05,
|
| 1352 |
-
"loss": 1.6918,
|
| 1353 |
-
"step": 5952
|
| 1354 |
-
},
|
| 1355 |
-
{
|
| 1356 |
-
"epoch": 0.21659094611472116,
|
| 1357 |
-
"grad_norm": 1.6128371953964233,
|
| 1358 |
-
"learning_rate": 4.714036999763532e-05,
|
| 1359 |
-
"loss": 1.706,
|
| 1360 |
-
"step": 5983
|
| 1361 |
-
},
|
| 1362 |
-
{
|
| 1363 |
-
"epoch": 0.2177131789961446,
|
| 1364 |
-
"grad_norm": 1.71291983127594,
|
| 1365 |
-
"learning_rate": 4.7101241986186116e-05,
|
| 1366 |
-
"loss": 1.6861,
|
| 1367 |
-
"step": 6014
|
| 1368 |
-
},
|
| 1369 |
-
{
|
| 1370 |
-
"epoch": 0.21883541187756803,
|
| 1371 |
-
"grad_norm": 1.5903745889663696,
|
| 1372 |
-
"learning_rate": 4.7061864565225e-05,
|
| 1373 |
-
"loss": 1.6886,
|
| 1374 |
-
"step": 6045
|
| 1375 |
-
},
|
| 1376 |
-
{
|
| 1377 |
-
"epoch": 0.21995764475899143,
|
| 1378 |
-
"grad_norm": 1.71088445186615,
|
| 1379 |
-
"learning_rate": 4.702223817912081e-05,
|
| 1380 |
-
"loss": 1.7003,
|
| 1381 |
-
"step": 6076
|
| 1382 |
-
},
|
| 1383 |
-
{
|
| 1384 |
-
"epoch": 0.22107987764041487,
|
| 1385 |
-
"grad_norm": 1.541530966758728,
|
| 1386 |
-
"learning_rate": 4.698236327505195e-05,
|
| 1387 |
-
"loss": 1.6956,
|
| 1388 |
-
"step": 6107
|
| 1389 |
-
},
|
| 1390 |
-
{
|
| 1391 |
-
"epoch": 0.2222021105218383,
|
| 1392 |
-
"grad_norm": 1.539455533027649,
|
| 1393 |
-
"learning_rate": 4.694224030300127e-05,
|
| 1394 |
-
"loss": 1.6833,
|
| 1395 |
-
"step": 6138
|
| 1396 |
-
},
|
| 1397 |
-
{
|
| 1398 |
-
"epoch": 0.2233243434032617,
|
| 1399 |
-
"grad_norm": 1.688120722770691,
|
| 1400 |
-
"learning_rate": 4.690186971575107e-05,
|
| 1401 |
-
"loss": 1.6973,
|
| 1402 |
-
"step": 6169
|
| 1403 |
-
},
|
| 1404 |
-
{
|
| 1405 |
-
"epoch": 0.22444657628468515,
|
| 1406 |
-
"grad_norm": 1.6934964656829834,
|
| 1407 |
-
"learning_rate": 4.6861251968877916e-05,
|
| 1408 |
-
"loss": 1.6979,
|
| 1409 |
-
"step": 6200
|
| 1410 |
-
},
|
| 1411 |
-
{
|
| 1412 |
-
"epoch": 0.22556880916610858,
|
| 1413 |
-
"grad_norm": 1.6558688879013062,
|
| 1414 |
-
"learning_rate": 4.68203875207476e-05,
|
| 1415 |
-
"loss": 1.6925,
|
| 1416 |
-
"step": 6231
|
| 1417 |
-
},
|
| 1418 |
-
{
|
| 1419 |
-
"epoch": 0.226691042047532,
|
| 1420 |
-
"grad_norm": 1.6245280504226685,
|
| 1421 |
-
"learning_rate": 4.677927683250983e-05,
|
| 1422 |
-
"loss": 1.6688,
|
| 1423 |
-
"step": 6262
|
| 1424 |
-
},
|
| 1425 |
-
{
|
| 1426 |
-
"epoch": 0.22781327492895542,
|
| 1427 |
-
"grad_norm": 1.5808422565460205,
|
| 1428 |
-
"learning_rate": 4.6737920368093156e-05,
|
| 1429 |
-
"loss": 1.688,
|
| 1430 |
-
"step": 6293
|
| 1431 |
-
},
|
| 1432 |
-
{
|
| 1433 |
-
"epoch": 0.22893550781037886,
|
| 1434 |
-
"grad_norm": 1.5224875211715698,
|
| 1435 |
-
"learning_rate": 4.669631859419965e-05,
|
| 1436 |
-
"loss": 1.6864,
|
| 1437 |
-
"step": 6324
|
| 1438 |
-
},
|
| 1439 |
-
{
|
| 1440 |
-
"epoch": 0.23005774069180226,
|
| 1441 |
-
"grad_norm": 1.5904366970062256,
|
| 1442 |
-
"learning_rate": 4.6654471980299676e-05,
|
| 1443 |
-
"loss": 1.6893,
|
| 1444 |
-
"step": 6355
|
| 1445 |
-
},
|
| 1446 |
-
{
|
| 1447 |
-
"epoch": 0.2311799735732257,
|
| 1448 |
-
"grad_norm": 1.6145131587982178,
|
| 1449 |
-
"learning_rate": 4.661238099862658e-05,
|
| 1450 |
-
"loss": 1.6818,
|
| 1451 |
-
"step": 6386
|
| 1452 |
-
},
|
| 1453 |
-
{
|
| 1454 |
-
"epoch": 0.23230220645464913,
|
| 1455 |
-
"grad_norm": 1.6297610998153687,
|
| 1456 |
-
"learning_rate": 4.657004612417138e-05,
|
| 1457 |
-
"loss": 1.687,
|
| 1458 |
-
"step": 6417
|
| 1459 |
-
},
|
| 1460 |
-
{
|
| 1461 |
-
"epoch": 0.23342443933607254,
|
| 1462 |
-
"grad_norm": 1.6199692487716675,
|
| 1463 |
-
"learning_rate": 4.6527467834677374e-05,
|
| 1464 |
-
"loss": 1.6945,
|
| 1465 |
-
"step": 6448
|
| 1466 |
-
},
|
| 1467 |
-
{
|
| 1468 |
-
"epoch": 0.23454667221749598,
|
| 1469 |
-
"grad_norm": 1.5439369678497314,
|
| 1470 |
-
"learning_rate": 4.648464661063478e-05,
|
| 1471 |
-
"loss": 1.6926,
|
| 1472 |
-
"step": 6479
|
| 1473 |
-
},
|
| 1474 |
-
{
|
| 1475 |
-
"epoch": 0.23566890509891938,
|
| 1476 |
-
"grad_norm": 1.6095410585403442,
|
| 1477 |
-
"learning_rate": 4.6441582935275264e-05,
|
| 1478 |
-
"loss": 1.689,
|
| 1479 |
-
"step": 6510
|
| 1480 |
-
},
|
| 1481 |
-
{
|
| 1482 |
-
"epoch": 0.23679113798034282,
|
| 1483 |
-
"grad_norm": 1.4971855878829956,
|
| 1484 |
-
"learning_rate": 4.6398277294566586e-05,
|
| 1485 |
-
"loss": 1.6622,
|
| 1486 |
-
"step": 6541
|
| 1487 |
-
},
|
| 1488 |
-
{
|
| 1489 |
-
"epoch": 0.23791337086176625,
|
| 1490 |
-
"grad_norm": 1.53174889087677,
|
| 1491 |
-
"learning_rate": 4.6354730177207e-05,
|
| 1492 |
-
"loss": 1.6785,
|
| 1493 |
-
"step": 6572
|
| 1494 |
-
},
|
| 1495 |
-
{
|
| 1496 |
-
"epoch": 0.23903560374318966,
|
| 1497 |
-
"grad_norm": 1.4567692279815674,
|
| 1498 |
-
"learning_rate": 4.6310942074619787e-05,
|
| 1499 |
-
"loss": 1.6776,
|
| 1500 |
-
"step": 6603
|
| 1501 |
-
},
|
| 1502 |
-
{
|
| 1503 |
-
"epoch": 0.2401578366246131,
|
| 1504 |
-
"grad_norm": 1.6813284158706665,
|
| 1505 |
-
"learning_rate": 4.626691348094777e-05,
|
| 1506 |
-
"loss": 1.6692,
|
| 1507 |
-
"step": 6634
|
| 1508 |
-
},
|
| 1509 |
-
{
|
| 1510 |
-
"epoch": 0.24128006950603653,
|
| 1511 |
-
"grad_norm": 1.5593857765197754,
|
| 1512 |
-
"learning_rate": 4.622264489304762e-05,
|
| 1513 |
-
"loss": 1.6811,
|
| 1514 |
-
"step": 6665
|
| 1515 |
-
},
|
| 1516 |
-
{
|
| 1517 |
-
"epoch": 0.24240230238745994,
|
| 1518 |
-
"grad_norm": 1.5681389570236206,
|
| 1519 |
-
"learning_rate": 4.617813681048434e-05,
|
| 1520 |
-
"loss": 1.689,
|
| 1521 |
-
"step": 6696
|
| 1522 |
-
},
|
| 1523 |
-
{
|
| 1524 |
-
"epoch": 0.24352453526888337,
|
| 1525 |
-
"grad_norm": 1.6402842998504639,
|
| 1526 |
-
"learning_rate": 4.61333897355256e-05,
|
| 1527 |
-
"loss": 1.6621,
|
| 1528 |
-
"step": 6727
|
| 1529 |
-
},
|
| 1530 |
-
{
|
| 1531 |
-
"epoch": 0.2446467681503068,
|
| 1532 |
-
"grad_norm": 1.642669677734375,
|
| 1533 |
-
"learning_rate": 4.608840417313604e-05,
|
| 1534 |
-
"loss": 1.6562,
|
| 1535 |
-
"step": 6758
|
| 1536 |
-
},
|
| 1537 |
-
{
|
| 1538 |
-
"epoch": 0.24576900103173022,
|
| 1539 |
-
"grad_norm": 1.6442660093307495,
|
| 1540 |
-
"learning_rate": 4.6043180630971646e-05,
|
| 1541 |
-
"loss": 1.6721,
|
| 1542 |
-
"step": 6789
|
| 1543 |
-
},
|
| 1544 |
-
{
|
| 1545 |
-
"epoch": 0.24689123391315365,
|
| 1546 |
-
"grad_norm": 1.5577408075332642,
|
| 1547 |
-
"learning_rate": 4.599771961937391e-05,
|
| 1548 |
-
"loss": 1.6837,
|
| 1549 |
-
"step": 6820
|
| 1550 |
-
},
|
| 1551 |
-
{
|
| 1552 |
-
"epoch": 0.2480134667945771,
|
| 1553 |
-
"grad_norm": 1.8555899858474731,
|
| 1554 |
-
"learning_rate": 4.5952021651364204e-05,
|
| 1555 |
-
"loss": 1.6739,
|
| 1556 |
-
"step": 6851
|
| 1557 |
-
},
|
| 1558 |
-
{
|
| 1559 |
-
"epoch": 0.2491356996760005,
|
| 1560 |
-
"grad_norm": 1.667812466621399,
|
| 1561 |
-
"learning_rate": 4.590608724263786e-05,
|
| 1562 |
-
"loss": 1.6704,
|
| 1563 |
-
"step": 6882
|
| 1564 |
-
},
|
| 1565 |
-
{
|
| 1566 |
-
"epoch": 0.25025793255742396,
|
| 1567 |
-
"grad_norm": 1.6642868518829346,
|
| 1568 |
-
"learning_rate": 4.585991691155845e-05,
|
| 1569 |
-
"loss": 1.6784,
|
| 1570 |
-
"step": 6913
|
| 1571 |
-
},
|
| 1572 |
-
{
|
| 1573 |
-
"epoch": 0.25138016543884734,
|
| 1574 |
-
"grad_norm": 1.6429824829101562,
|
| 1575 |
-
"learning_rate": 4.581351117915188e-05,
|
| 1576 |
-
"loss": 1.6729,
|
| 1577 |
-
"step": 6944
|
| 1578 |
-
},
|
| 1579 |
-
{
|
| 1580 |
-
"epoch": 0.25250239832027077,
|
| 1581 |
-
"grad_norm": 1.6268694400787354,
|
| 1582 |
-
"learning_rate": 4.5766870569100534e-05,
|
| 1583 |
-
"loss": 1.6657,
|
| 1584 |
-
"step": 6975
|
| 1585 |
-
},
|
| 1586 |
-
{
|
| 1587 |
-
"epoch": 0.2536246312016942,
|
| 1588 |
-
"grad_norm": 1.496177315711975,
|
| 1589 |
-
"learning_rate": 4.571999560773736e-05,
|
| 1590 |
-
"loss": 1.6611,
|
| 1591 |
-
"step": 7006
|
| 1592 |
-
},
|
| 1593 |
-
{
|
| 1594 |
-
"epoch": 0.25474686408311764,
|
| 1595 |
-
"grad_norm": 1.7032805681228638,
|
| 1596 |
-
"learning_rate": 4.5672886824039915e-05,
|
| 1597 |
-
"loss": 1.6816,
|
| 1598 |
-
"step": 7037
|
| 1599 |
-
},
|
| 1600 |
-
{
|
| 1601 |
-
"epoch": 0.2558690969645411,
|
| 1602 |
-
"grad_norm": 1.791925072669983,
|
| 1603 |
-
"learning_rate": 4.5625544749624435e-05,
|
| 1604 |
-
"loss": 1.6689,
|
| 1605 |
-
"step": 7068
|
| 1606 |
-
},
|
| 1607 |
-
{
|
| 1608 |
-
"epoch": 0.2569913298459645,
|
| 1609 |
-
"grad_norm": 1.5614711046218872,
|
| 1610 |
-
"learning_rate": 4.5577969918739794e-05,
|
| 1611 |
-
"loss": 1.6647,
|
| 1612 |
-
"step": 7099
|
| 1613 |
-
},
|
| 1614 |
-
{
|
| 1615 |
-
"epoch": 0.2581135627273879,
|
| 1616 |
-
"grad_norm": 1.517112135887146,
|
| 1617 |
-
"learning_rate": 4.5530162868261486e-05,
|
| 1618 |
-
"loss": 1.6614,
|
| 1619 |
-
"step": 7130
|
| 1620 |
-
},
|
| 1621 |
-
{
|
| 1622 |
-
"epoch": 0.2592357956088113,
|
| 1623 |
-
"grad_norm": 1.5636824369430542,
|
| 1624 |
-
"learning_rate": 4.548212413768558e-05,
|
| 1625 |
-
"loss": 1.6599,
|
| 1626 |
-
"step": 7161
|
| 1627 |
-
},
|
| 1628 |
-
{
|
| 1629 |
-
"epoch": 0.26035802849023476,
|
| 1630 |
-
"grad_norm": 1.5803399085998535,
|
| 1631 |
-
"learning_rate": 4.543385426912261e-05,
|
| 1632 |
-
"loss": 1.6558,
|
| 1633 |
-
"step": 7192
|
| 1634 |
-
},
|
| 1635 |
-
{
|
| 1636 |
-
"epoch": 0.2614802613716582,
|
| 1637 |
-
"grad_norm": 1.6228526830673218,
|
| 1638 |
-
"learning_rate": 4.53853538072915e-05,
|
| 1639 |
-
"loss": 1.6778,
|
| 1640 |
-
"step": 7223
|
| 1641 |
-
},
|
| 1642 |
-
{
|
| 1643 |
-
"epoch": 0.26260249425308163,
|
| 1644 |
-
"grad_norm": 1.5660549402236938,
|
| 1645 |
-
"learning_rate": 4.533662329951336e-05,
|
| 1646 |
-
"loss": 1.6827,
|
| 1647 |
-
"step": 7254
|
| 1648 |
-
},
|
| 1649 |
-
{
|
| 1650 |
-
"epoch": 0.26372472713450507,
|
| 1651 |
-
"grad_norm": 1.555421233177185,
|
| 1652 |
-
"learning_rate": 4.528766329570536e-05,
|
| 1653 |
-
"loss": 1.6755,
|
| 1654 |
-
"step": 7285
|
| 1655 |
-
},
|
| 1656 |
-
{
|
| 1657 |
-
"epoch": 0.26484696001592845,
|
| 1658 |
-
"grad_norm": 1.603285312652588,
|
| 1659 |
-
"learning_rate": 4.523847434837447e-05,
|
| 1660 |
-
"loss": 1.6455,
|
| 1661 |
-
"step": 7316
|
| 1662 |
-
},
|
| 1663 |
-
{
|
| 1664 |
-
"epoch": 0.2659691928973519,
|
| 1665 |
-
"grad_norm": 1.510772943496704,
|
| 1666 |
-
"learning_rate": 4.518905701261128e-05,
|
| 1667 |
-
"loss": 1.6736,
|
| 1668 |
-
"step": 7347
|
| 1669 |
-
},
|
| 1670 |
-
{
|
| 1671 |
-
"epoch": 0.2670914257787753,
|
| 1672 |
-
"grad_norm": 1.6260360479354858,
|
| 1673 |
-
"learning_rate": 4.5139411846083715e-05,
|
| 1674 |
-
"loss": 1.6643,
|
| 1675 |
-
"step": 7378
|
| 1676 |
-
},
|
| 1677 |
-
{
|
| 1678 |
-
"epoch": 0.26821365866019875,
|
| 1679 |
-
"grad_norm": 3.0237209796905518,
|
| 1680 |
-
"learning_rate": 4.508953940903073e-05,
|
| 1681 |
-
"loss": 1.6615,
|
| 1682 |
-
"step": 7409
|
| 1683 |
-
},
|
| 1684 |
-
{
|
| 1685 |
-
"epoch": 0.2693358915416222,
|
| 1686 |
-
"grad_norm": 1.4725430011749268,
|
| 1687 |
-
"learning_rate": 4.5039440264255994e-05,
|
| 1688 |
-
"loss": 1.6582,
|
| 1689 |
-
"step": 7440
|
| 1690 |
-
},
|
| 1691 |
-
{
|
| 1692 |
-
"epoch": 0.2704581244230456,
|
| 1693 |
-
"grad_norm": 1.5135307312011719,
|
| 1694 |
-
"learning_rate": 4.498911497712155e-05,
|
| 1695 |
-
"loss": 1.6754,
|
| 1696 |
-
"step": 7471
|
| 1697 |
-
},
|
| 1698 |
-
{
|
| 1699 |
-
"epoch": 0.271580357304469,
|
| 1700 |
-
"grad_norm": 1.5741811990737915,
|
| 1701 |
-
"learning_rate": 4.493856411554142e-05,
|
| 1702 |
-
"loss": 1.6889,
|
| 1703 |
-
"step": 7502
|
| 1704 |
-
},
|
| 1705 |
-
{
|
| 1706 |
-
"epoch": 0.27270259018589244,
|
| 1707 |
-
"grad_norm": 1.5469688177108765,
|
| 1708 |
-
"learning_rate": 4.4887788249975206e-05,
|
| 1709 |
-
"loss": 1.6542,
|
| 1710 |
-
"step": 7533
|
| 1711 |
-
},
|
| 1712 |
-
{
|
| 1713 |
-
"epoch": 0.27382482306731587,
|
| 1714 |
-
"grad_norm": 1.4596927165985107,
|
| 1715 |
-
"learning_rate": 4.4836787953421656e-05,
|
| 1716 |
-
"loss": 1.6365,
|
| 1717 |
-
"step": 7564
|
| 1718 |
-
},
|
| 1719 |
-
{
|
| 1720 |
-
"epoch": 0.2749470559487393,
|
| 1721 |
-
"grad_norm": 1.566522479057312,
|
| 1722 |
-
"learning_rate": 4.478556380141218e-05,
|
| 1723 |
-
"loss": 1.657,
|
| 1724 |
-
"step": 7595
|
| 1725 |
-
},
|
| 1726 |
-
{
|
| 1727 |
-
"epoch": 0.27606928883016274,
|
| 1728 |
-
"grad_norm": 1.5141624212265015,
|
| 1729 |
-
"learning_rate": 4.4734116372004375e-05,
|
| 1730 |
-
"loss": 1.6695,
|
| 1731 |
-
"step": 7626
|
| 1732 |
-
},
|
| 1733 |
-
{
|
| 1734 |
-
"epoch": 0.2771915217115862,
|
| 1735 |
-
"grad_norm": 1.4138630628585815,
|
| 1736 |
-
"learning_rate": 4.4682446245775477e-05,
|
| 1737 |
-
"loss": 1.6638,
|
| 1738 |
-
"step": 7657
|
| 1739 |
-
},
|
| 1740 |
-
{
|
| 1741 |
-
"epoch": 0.27831375459300955,
|
| 1742 |
-
"grad_norm": 1.4885402917861938,
|
| 1743 |
-
"learning_rate": 4.463055400581586e-05,
|
| 1744 |
-
"loss": 1.6817,
|
| 1745 |
-
"step": 7688
|
| 1746 |
-
},
|
| 1747 |
-
{
|
| 1748 |
-
"epoch": 0.279435987474433,
|
| 1749 |
-
"grad_norm": 1.645486831665039,
|
| 1750 |
-
"learning_rate": 4.4578440237722374e-05,
|
| 1751 |
-
"loss": 1.6392,
|
| 1752 |
-
"step": 7719
|
| 1753 |
-
},
|
| 1754 |
-
{
|
| 1755 |
-
"epoch": 0.2805582203558564,
|
| 1756 |
-
"grad_norm": 1.5977535247802734,
|
| 1757 |
-
"learning_rate": 4.452610552959183e-05,
|
| 1758 |
-
"loss": 1.6557,
|
| 1759 |
-
"step": 7750
|
| 1760 |
-
},
|
| 1761 |
-
{
|
| 1762 |
-
"epoch": 0.28168045323727986,
|
| 1763 |
-
"grad_norm": 1.6347745656967163,
|
| 1764 |
-
"learning_rate": 4.447355047201428e-05,
|
| 1765 |
-
"loss": 1.6573,
|
| 1766 |
-
"step": 7781
|
| 1767 |
-
},
|
| 1768 |
-
{
|
| 1769 |
-
"epoch": 0.2828026861187033,
|
| 1770 |
-
"grad_norm": 1.5288081169128418,
|
| 1771 |
-
"learning_rate": 4.4420775658066414e-05,
|
| 1772 |
-
"loss": 1.638,
|
| 1773 |
-
"step": 7812
|
| 1774 |
-
},
|
| 1775 |
-
{
|
| 1776 |
-
"epoch": 0.28392491900012673,
|
| 1777 |
-
"grad_norm": 1.4643625020980835,
|
| 1778 |
-
"learning_rate": 4.436778168330484e-05,
|
| 1779 |
-
"loss": 1.6402,
|
| 1780 |
-
"step": 7843
|
| 1781 |
-
},
|
| 1782 |
-
{
|
| 1783 |
-
"epoch": 0.2850471518815501,
|
| 1784 |
-
"grad_norm": 1.568663239479065,
|
| 1785 |
-
"learning_rate": 4.4314569145759353e-05,
|
| 1786 |
-
"loss": 1.6565,
|
| 1787 |
-
"step": 7874
|
| 1788 |
-
},
|
| 1789 |
-
{
|
| 1790 |
-
"epoch": 0.28616938476297354,
|
| 1791 |
-
"grad_norm": 1.476515293121338,
|
| 1792 |
-
"learning_rate": 4.42611386459262e-05,
|
| 1793 |
-
"loss": 1.6709,
|
| 1794 |
-
"step": 7905
|
| 1795 |
-
},
|
| 1796 |
-
{
|
| 1797 |
-
"epoch": 0.287291617644397,
|
| 1798 |
-
"grad_norm": 1.532404899597168,
|
| 1799 |
-
"learning_rate": 4.420749078676133e-05,
|
| 1800 |
-
"loss": 1.6333,
|
| 1801 |
-
"step": 7936
|
| 1802 |
-
},
|
| 1803 |
-
{
|
| 1804 |
-
"epoch": 0.2884138505258204,
|
| 1805 |
-
"grad_norm": 1.5388779640197754,
|
| 1806 |
-
"learning_rate": 4.4153626173673516e-05,
|
| 1807 |
-
"loss": 1.6494,
|
| 1808 |
-
"step": 7967
|
| 1809 |
-
},
|
| 1810 |
-
{
|
| 1811 |
-
"epoch": 0.28953608340724385,
|
| 1812 |
-
"grad_norm": 1.5787324905395508,
|
| 1813 |
-
"learning_rate": 4.409954541451762e-05,
|
| 1814 |
-
"loss": 1.6362,
|
| 1815 |
-
"step": 7998
|
| 1816 |
-
},
|
| 1817 |
-
{
|
| 1818 |
-
"epoch": 0.2906583162886673,
|
| 1819 |
-
"grad_norm": 1.4780092239379883,
|
| 1820 |
-
"learning_rate": 4.404524911958764e-05,
|
| 1821 |
-
"loss": 1.643,
|
| 1822 |
-
"step": 8029
|
| 1823 |
-
},
|
| 1824 |
-
{
|
| 1825 |
-
"epoch": 0.29178054917009066,
|
| 1826 |
-
"grad_norm": 1.5434736013412476,
|
| 1827 |
-
"learning_rate": 4.399073790160989e-05,
|
| 1828 |
-
"loss": 1.6472,
|
| 1829 |
-
"step": 8060
|
| 1830 |
-
},
|
| 1831 |
-
{
|
| 1832 |
-
"epoch": 0.2929027820515141,
|
| 1833 |
-
"grad_norm": 1.4898840188980103,
|
| 1834 |
-
"learning_rate": 4.393601237573607e-05,
|
| 1835 |
-
"loss": 1.6483,
|
| 1836 |
-
"step": 8091
|
| 1837 |
-
},
|
| 1838 |
-
{
|
| 1839 |
-
"epoch": 0.29402501493293753,
|
| 1840 |
-
"grad_norm": 1.5529502630233765,
|
| 1841 |
-
"learning_rate": 4.388107315953628e-05,
|
| 1842 |
-
"loss": 1.6291,
|
| 1843 |
-
"step": 8122
|
| 1844 |
-
},
|
| 1845 |
-
{
|
| 1846 |
-
"epoch": 0.29514724781436097,
|
| 1847 |
-
"grad_norm": 1.4831997156143188,
|
| 1848 |
-
"learning_rate": 4.382592087299212e-05,
|
| 1849 |
-
"loss": 1.6518,
|
| 1850 |
-
"step": 8153
|
| 1851 |
-
},
|
| 1852 |
-
{
|
| 1853 |
-
"epoch": 0.2962694806957844,
|
| 1854 |
-
"grad_norm": 1.4568578004837036,
|
| 1855 |
-
"learning_rate": 4.377055613848964e-05,
|
| 1856 |
-
"loss": 1.6465,
|
| 1857 |
-
"step": 8184
|
| 1858 |
-
},
|
| 1859 |
-
{
|
| 1860 |
-
"epoch": 0.29739171357720784,
|
| 1861 |
-
"grad_norm": 1.4941576719284058,
|
| 1862 |
-
"learning_rate": 4.3714979580812355e-05,
|
| 1863 |
-
"loss": 1.634,
|
| 1864 |
-
"step": 8215
|
| 1865 |
-
},
|
| 1866 |
-
{
|
| 1867 |
-
"epoch": 0.2985139464586312,
|
| 1868 |
-
"grad_norm": 1.5891722440719604,
|
| 1869 |
-
"learning_rate": 4.365919182713416e-05,
|
| 1870 |
-
"loss": 1.6422,
|
| 1871 |
-
"step": 8246
|
| 1872 |
-
},
|
| 1873 |
-
{
|
| 1874 |
-
"epoch": 0.29963617934005465,
|
| 1875 |
-
"grad_norm": 1.5435233116149902,
|
| 1876 |
-
"learning_rate": 4.360319350701226e-05,
|
| 1877 |
-
"loss": 1.6446,
|
| 1878 |
-
"step": 8277
|
| 1879 |
-
},
|
| 1880 |
-
{
|
| 1881 |
-
"epoch": 0.3007584122214781,
|
| 1882 |
-
"grad_norm": 1.4754277467727661,
|
| 1883 |
-
"learning_rate": 4.3546985252380115e-05,
|
| 1884 |
-
"loss": 1.655,
|
| 1885 |
-
"step": 8308
|
| 1886 |
-
},
|
| 1887 |
-
{
|
| 1888 |
-
"epoch": 0.3018806451029015,
|
| 1889 |
-
"grad_norm": 1.5463342666625977,
|
| 1890 |
-
"learning_rate": 4.349056769754021e-05,
|
| 1891 |
-
"loss": 1.6407,
|
| 1892 |
-
"step": 8339
|
| 1893 |
-
},
|
| 1894 |
-
{
|
| 1895 |
-
"epoch": 0.30300287798432496,
|
| 1896 |
-
"grad_norm": 1.4847484827041626,
|
| 1897 |
-
"learning_rate": 4.3433941479156994e-05,
|
| 1898 |
-
"loss": 1.65,
|
| 1899 |
-
"step": 8370
|
| 1900 |
-
},
|
| 1901 |
-
{
|
| 1902 |
-
"epoch": 0.3041251108657484,
|
| 1903 |
-
"grad_norm": 1.475669264793396,
|
| 1904 |
-
"learning_rate": 4.3377107236249647e-05,
|
| 1905 |
-
"loss": 1.6398,
|
| 1906 |
-
"step": 8401
|
| 1907 |
-
},
|
| 1908 |
-
{
|
| 1909 |
-
"epoch": 0.3052473437471718,
|
| 1910 |
-
"grad_norm": 1.558566689491272,
|
| 1911 |
-
"learning_rate": 4.332006561018488e-05,
|
| 1912 |
-
"loss": 1.6501,
|
| 1913 |
-
"step": 8432
|
| 1914 |
-
},
|
| 1915 |
-
{
|
| 1916 |
-
"epoch": 0.3063695766285952,
|
| 1917 |
-
"grad_norm": 1.5497310161590576,
|
| 1918 |
-
"learning_rate": 4.3262817244669683e-05,
|
| 1919 |
-
"loss": 1.6371,
|
| 1920 |
-
"step": 8463
|
| 1921 |
-
},
|
| 1922 |
-
{
|
| 1923 |
-
"epoch": 0.30749180951001864,
|
| 1924 |
-
"grad_norm": 1.464553952217102,
|
| 1925 |
-
"learning_rate": 4.3205362785744083e-05,
|
| 1926 |
-
"loss": 1.6766,
|
| 1927 |
-
"step": 8494
|
| 1928 |
-
},
|
| 1929 |
-
{
|
| 1930 |
-
"epoch": 0.3086140423914421,
|
| 1931 |
-
"grad_norm": 1.5198413133621216,
|
| 1932 |
-
"learning_rate": 4.314770288177384e-05,
|
| 1933 |
-
"loss": 1.633,
|
| 1934 |
-
"step": 8525
|
| 1935 |
-
},
|
| 1936 |
-
{
|
| 1937 |
-
"epoch": 0.3097362752728655,
|
| 1938 |
-
"grad_norm": 1.5493290424346924,
|
| 1939 |
-
"learning_rate": 4.308983818344313e-05,
|
| 1940 |
-
"loss": 1.6465,
|
| 1941 |
-
"step": 8556
|
| 1942 |
-
},
|
| 1943 |
-
{
|
| 1944 |
-
"epoch": 0.31085850815428895,
|
| 1945 |
-
"grad_norm": 1.4413405656814575,
|
| 1946 |
-
"learning_rate": 4.3031769343747206e-05,
|
| 1947 |
-
"loss": 1.6463,
|
| 1948 |
-
"step": 8587
|
| 1949 |
-
},
|
| 1950 |
-
{
|
| 1951 |
-
"epoch": 0.31198074103571233,
|
| 1952 |
-
"grad_norm": 1.508507251739502,
|
| 1953 |
-
"learning_rate": 4.297349701798505e-05,
|
| 1954 |
-
"loss": 1.6262,
|
| 1955 |
-
"step": 8618
|
| 1956 |
-
},
|
| 1957 |
-
{
|
| 1958 |
-
"epoch": 0.31310297391713576,
|
| 1959 |
-
"grad_norm": 1.560054063796997,
|
| 1960 |
-
"learning_rate": 4.2915021863751916e-05,
|
| 1961 |
-
"loss": 1.6484,
|
| 1962 |
-
"step": 8649
|
| 1963 |
-
},
|
| 1964 |
-
{
|
| 1965 |
-
"epoch": 0.3142252067985592,
|
| 1966 |
-
"grad_norm": 1.495651125907898,
|
| 1967 |
-
"learning_rate": 4.285634454093198e-05,
|
| 1968 |
-
"loss": 1.6329,
|
| 1969 |
-
"step": 8680
|
| 1970 |
-
},
|
| 1971 |
-
{
|
| 1972 |
-
"epoch": 0.31534743967998263,
|
| 1973 |
-
"grad_norm": 1.481740117073059,
|
| 1974 |
-
"learning_rate": 4.279746571169086e-05,
|
| 1975 |
-
"loss": 1.6274,
|
| 1976 |
-
"step": 8711
|
| 1977 |
-
},
|
| 1978 |
-
{
|
| 1979 |
-
"epoch": 0.31646967256140607,
|
| 1980 |
-
"grad_norm": 1.53792142868042,
|
| 1981 |
-
"learning_rate": 4.2738386040468136e-05,
|
| 1982 |
-
"loss": 1.6252,
|
| 1983 |
-
"step": 8742
|
| 1984 |
-
},
|
| 1985 |
-
{
|
| 1986 |
-
"epoch": 0.31759190544282945,
|
| 1987 |
-
"grad_norm": 1.4411643743515015,
|
| 1988 |
-
"learning_rate": 4.2679106193969866e-05,
|
| 1989 |
-
"loss": 1.6423,
|
| 1990 |
-
"step": 8773
|
| 1991 |
-
},
|
| 1992 |
-
{
|
| 1993 |
-
"epoch": 0.3187141383242529,
|
| 1994 |
-
"grad_norm": 1.5158967971801758,
|
| 1995 |
-
"learning_rate": 4.261962684116106e-05,
|
| 1996 |
-
"loss": 1.6596,
|
| 1997 |
-
"step": 8804
|
| 1998 |
-
},
|
| 1999 |
-
{
|
| 2000 |
-
"epoch": 0.3198363712056763,
|
| 2001 |
-
"grad_norm": 1.6026604175567627,
|
| 2002 |
-
"learning_rate": 4.2559948653258145e-05,
|
| 2003 |
-
"loss": 1.6399,
|
| 2004 |
-
"step": 8835
|
| 2005 |
-
},
|
| 2006 |
-
{
|
| 2007 |
-
"epoch": 0.32095860408709975,
|
| 2008 |
-
"grad_norm": 1.4422760009765625,
|
| 2009 |
-
"learning_rate": 4.250007230372134e-05,
|
| 2010 |
-
"loss": 1.646,
|
| 2011 |
-
"step": 8866
|
| 2012 |
-
},
|
| 2013 |
-
{
|
| 2014 |
-
"epoch": 0.3220808369685232,
|
| 2015 |
-
"grad_norm": 1.4450057744979858,
|
| 2016 |
-
"learning_rate": 4.2439998468247126e-05,
|
| 2017 |
-
"loss": 1.6311,
|
| 2018 |
-
"step": 8897
|
| 2019 |
-
},
|
| 2020 |
-
{
|
| 2021 |
-
"epoch": 0.3232030698499466,
|
| 2022 |
-
"grad_norm": 1.432768702507019,
|
| 2023 |
-
"learning_rate": 4.2379727824760566e-05,
|
| 2024 |
-
"loss": 1.6234,
|
| 2025 |
-
"step": 8928
|
| 2026 |
-
},
|
| 2027 |
-
{
|
| 2028 |
-
"epoch": 0.32432530273137,
|
| 2029 |
-
"grad_norm": 1.5206103324890137,
|
| 2030 |
-
"learning_rate": 4.231926105340768e-05,
|
| 2031 |
-
"loss": 1.6268,
|
| 2032 |
-
"step": 8959
|
| 2033 |
-
},
|
| 2034 |
-
{
|
| 2035 |
-
"epoch": 0.32544753561279344,
|
| 2036 |
-
"grad_norm": 1.5703397989273071,
|
| 2037 |
-
"learning_rate": 4.225859883654776e-05,
|
| 2038 |
-
"loss": 1.6409,
|
| 2039 |
-
"step": 8990
|
| 2040 |
-
},
|
| 2041 |
-
{
|
| 2042 |
-
"epoch": 0.32656976849421687,
|
| 2043 |
-
"grad_norm": 1.4549362659454346,
|
| 2044 |
-
"learning_rate": 4.219774185874569e-05,
|
| 2045 |
-
"loss": 1.6471,
|
| 2046 |
-
"step": 9021
|
| 2047 |
-
},
|
| 2048 |
-
{
|
| 2049 |
-
"epoch": 0.3276920013756403,
|
| 2050 |
-
"grad_norm": 1.669263243675232,
|
| 2051 |
-
"learning_rate": 4.213669080676418e-05,
|
| 2052 |
-
"loss": 1.6355,
|
| 2053 |
-
"step": 9052
|
| 2054 |
-
},
|
| 2055 |
-
{
|
| 2056 |
-
"epoch": 0.32881423425706374,
|
| 2057 |
-
"grad_norm": 1.4004725217819214,
|
| 2058 |
-
"learning_rate": 4.2075446369556056e-05,
|
| 2059 |
-
"loss": 1.6046,
|
| 2060 |
-
"step": 9083
|
| 2061 |
-
},
|
| 2062 |
-
{
|
| 2063 |
-
"epoch": 0.3299364671384872,
|
| 2064 |
-
"grad_norm": 1.4844101667404175,
|
| 2065 |
-
"learning_rate": 4.201400923825648e-05,
|
| 2066 |
-
"loss": 1.6357,
|
| 2067 |
-
"step": 9114
|
| 2068 |
-
},
|
| 2069 |
-
{
|
| 2070 |
-
"epoch": 0.33105870001991056,
|
| 2071 |
-
"grad_norm": 1.5377836227416992,
|
| 2072 |
-
"learning_rate": 4.195238010617511e-05,
|
| 2073 |
-
"loss": 1.6425,
|
| 2074 |
-
"step": 9145
|
| 2075 |
-
},
|
| 2076 |
-
{
|
| 2077 |
-
"epoch": 0.332180932901334,
|
| 2078 |
-
"grad_norm": 1.4880887269973755,
|
| 2079 |
-
"learning_rate": 4.1890559668788344e-05,
|
| 2080 |
-
"loss": 1.6368,
|
| 2081 |
-
"step": 9176
|
| 2082 |
-
},
|
| 2083 |
-
{
|
| 2084 |
-
"epoch": 0.3333031657827574,
|
| 2085 |
-
"grad_norm": 1.5786559581756592,
|
| 2086 |
-
"learning_rate": 4.1828548623731405e-05,
|
| 2087 |
-
"loss": 1.6327,
|
| 2088 |
-
"step": 9207
|
| 2089 |
-
},
|
| 2090 |
-
{
|
| 2091 |
-
"epoch": 0.33442539866418086,
|
| 2092 |
-
"grad_norm": 1.4619288444519043,
|
| 2093 |
-
"learning_rate": 4.1766347670790506e-05,
|
| 2094 |
-
"loss": 1.6431,
|
| 2095 |
-
"step": 9238
|
| 2096 |
-
},
|
| 2097 |
-
{
|
| 2098 |
-
"epoch": 0.3355476315456043,
|
| 2099 |
-
"grad_norm": 1.4946295022964478,
|
| 2100 |
-
"learning_rate": 4.170395751189495e-05,
|
| 2101 |
-
"loss": 1.6265,
|
| 2102 |
-
"step": 9269
|
| 2103 |
-
},
|
| 2104 |
-
{
|
| 2105 |
-
"epoch": 0.33666986442702773,
|
| 2106 |
-
"grad_norm": 1.4698960781097412,
|
| 2107 |
-
"learning_rate": 4.164137885110921e-05,
|
| 2108 |
-
"loss": 1.6356,
|
| 2109 |
-
"step": 9300
|
| 2110 |
-
},
|
| 2111 |
-
{
|
| 2112 |
-
"epoch": 0.3377920973084511,
|
| 2113 |
-
"grad_norm": 1.4136701822280884,
|
| 2114 |
-
"learning_rate": 4.157861239462495e-05,
|
| 2115 |
-
"loss": 1.606,
|
| 2116 |
-
"step": 9331
|
| 2117 |
-
},
|
| 2118 |
-
{
|
| 2119 |
-
"epoch": 0.33891433018987455,
|
| 2120 |
-
"grad_norm": 1.5250601768493652,
|
| 2121 |
-
"learning_rate": 4.1515658850753114e-05,
|
| 2122 |
-
"loss": 1.6266,
|
| 2123 |
-
"step": 9362
|
| 2124 |
-
},
|
| 2125 |
-
{
|
| 2126 |
-
"epoch": 0.340036563071298,
|
| 2127 |
-
"grad_norm": 1.5827070474624634,
|
| 2128 |
-
"learning_rate": 4.145251892991588e-05,
|
| 2129 |
-
"loss": 1.618,
|
| 2130 |
-
"step": 9393
|
| 2131 |
-
},
|
| 2132 |
-
{
|
| 2133 |
-
"epoch": 0.3411587959527214,
|
| 2134 |
-
"grad_norm": 1.4887738227844238,
|
| 2135 |
-
"learning_rate": 4.138919334463868e-05,
|
| 2136 |
-
"loss": 1.6196,
|
| 2137 |
-
"step": 9424
|
| 2138 |
-
},
|
| 2139 |
-
{
|
| 2140 |
-
"epoch": 0.34228102883414485,
|
| 2141 |
-
"grad_norm": 1.5627696514129639,
|
| 2142 |
-
"learning_rate": 4.1325682809542124e-05,
|
| 2143 |
-
"loss": 1.6155,
|
| 2144 |
-
"step": 9455
|
| 2145 |
-
},
|
| 2146 |
-
{
|
| 2147 |
-
"epoch": 0.3434032617155683,
|
| 2148 |
-
"grad_norm": 1.4552607536315918,
|
| 2149 |
-
"learning_rate": 4.126198804133398e-05,
|
| 2150 |
-
"loss": 1.6272,
|
| 2151 |
-
"step": 9486
|
| 2152 |
-
},
|
| 2153 |
-
{
|
| 2154 |
-
"epoch": 0.34452549459699167,
|
| 2155 |
-
"grad_norm": 1.5104546546936035,
|
| 2156 |
-
"learning_rate": 4.1198109758801055e-05,
|
| 2157 |
-
"loss": 1.6245,
|
| 2158 |
-
"step": 9517
|
| 2159 |
-
},
|
| 2160 |
-
{
|
| 2161 |
-
"epoch": 0.3456477274784151,
|
| 2162 |
-
"grad_norm": 1.4588383436203003,
|
| 2163 |
-
"learning_rate": 4.113404868280107e-05,
|
| 2164 |
-
"loss": 1.6285,
|
| 2165 |
-
"step": 9548
|
| 2166 |
-
},
|
| 2167 |
-
{
|
| 2168 |
-
"epoch": 0.34676996035983854,
|
| 2169 |
-
"grad_norm": 1.40166437625885,
|
| 2170 |
-
"learning_rate": 4.106980553625457e-05,
|
| 2171 |
-
"loss": 1.6181,
|
| 2172 |
-
"step": 9579
|
| 2173 |
-
},
|
| 2174 |
-
{
|
| 2175 |
-
"epoch": 0.34789219324126197,
|
| 2176 |
-
"grad_norm": 1.4949356317520142,
|
| 2177 |
-
"learning_rate": 4.100538104413674e-05,
|
| 2178 |
-
"loss": 1.6148,
|
| 2179 |
-
"step": 9610
|
| 2180 |
-
},
|
| 2181 |
-
{
|
| 2182 |
-
"epoch": 0.3490144261226854,
|
| 2183 |
-
"grad_norm": 1.4863393306732178,
|
| 2184 |
-
"learning_rate": 4.09407759334692e-05,
|
| 2185 |
-
"loss": 1.6218,
|
| 2186 |
-
"step": 9641
|
| 2187 |
-
},
|
| 2188 |
-
{
|
| 2189 |
-
"epoch": 0.35013665900410884,
|
| 2190 |
-
"grad_norm": 1.4831593036651611,
|
| 2191 |
-
"learning_rate": 4.087599093331186e-05,
|
| 2192 |
-
"loss": 1.6201,
|
| 2193 |
-
"step": 9672
|
| 2194 |
-
},
|
| 2195 |
-
{
|
| 2196 |
-
"epoch": 0.3512588918855322,
|
| 2197 |
-
"grad_norm": 1.487328052520752,
|
| 2198 |
-
"learning_rate": 4.081102677475462e-05,
|
| 2199 |
-
"loss": 1.6203,
|
| 2200 |
-
"step": 9703
|
| 2201 |
-
},
|
| 2202 |
-
{
|
| 2203 |
-
"epoch": 0.35238112476695566,
|
| 2204 |
-
"grad_norm": 1.560600996017456,
|
| 2205 |
-
"learning_rate": 4.0745884190909194e-05,
|
| 2206 |
-
"loss": 1.6099,
|
| 2207 |
-
"step": 9734
|
| 2208 |
-
},
|
| 2209 |
-
{
|
| 2210 |
-
"epoch": 0.3535033576483791,
|
| 2211 |
-
"grad_norm": 1.45511794090271,
|
| 2212 |
-
"learning_rate": 4.0680563916900796e-05,
|
| 2213 |
-
"loss": 1.6494,
|
| 2214 |
-
"step": 9765
|
| 2215 |
-
},
|
| 2216 |
-
{
|
| 2217 |
-
"epoch": 0.3546255905298025,
|
| 2218 |
-
"grad_norm": 1.4966280460357666,
|
| 2219 |
-
"learning_rate": 4.0615066689859815e-05,
|
| 2220 |
-
"loss": 1.6157,
|
| 2221 |
-
"step": 9796
|
| 2222 |
-
},
|
| 2223 |
-
{
|
| 2224 |
-
"epoch": 0.35574782341122596,
|
| 2225 |
-
"grad_norm": 1.4888532161712646,
|
| 2226 |
-
"learning_rate": 4.0549393248913584e-05,
|
| 2227 |
-
"loss": 1.6203,
|
| 2228 |
-
"step": 9827
|
| 2229 |
-
},
|
| 2230 |
-
{
|
| 2231 |
-
"epoch": 0.3568700562926494,
|
| 2232 |
-
"grad_norm": 1.5495861768722534,
|
| 2233 |
-
"learning_rate": 4.048354433517794e-05,
|
| 2234 |
-
"loss": 1.6131,
|
| 2235 |
-
"step": 9858
|
| 2236 |
-
},
|
| 2237 |
-
{
|
| 2238 |
-
"epoch": 0.3579922891740728,
|
| 2239 |
-
"grad_norm": 1.4991432428359985,
|
| 2240 |
-
"learning_rate": 4.0417520691748916e-05,
|
| 2241 |
-
"loss": 1.6371,
|
| 2242 |
-
"step": 9889
|
| 2243 |
-
},
|
| 2244 |
-
{
|
| 2245 |
-
"epoch": 0.3591145220554962,
|
| 2246 |
-
"grad_norm": 1.5163663625717163,
|
| 2247 |
-
"learning_rate": 4.035132306369438e-05,
|
| 2248 |
-
"loss": 1.5911,
|
| 2249 |
-
"step": 9920
|
| 2250 |
-
},
|
| 2251 |
-
{
|
| 2252 |
-
"epoch": 0.36023675493691965,
|
| 2253 |
-
"grad_norm": 1.439622402191162,
|
| 2254 |
-
"learning_rate": 4.028495219804555e-05,
|
| 2255 |
-
"loss": 1.6218,
|
| 2256 |
-
"step": 9951
|
| 2257 |
-
},
|
| 2258 |
-
{
|
| 2259 |
-
"epoch": 0.3613589878183431,
|
| 2260 |
-
"grad_norm": 1.4068893194198608,
|
| 2261 |
-
"learning_rate": 4.021840884378864e-05,
|
| 2262 |
-
"loss": 1.6284,
|
| 2263 |
-
"step": 9982
|
| 2264 |
-
},
|
| 2265 |
-
{
|
| 2266 |
-
"epoch": 0.3624812206997665,
|
| 2267 |
-
"grad_norm": 1.4577332735061646,
|
| 2268 |
-
"learning_rate": 4.015169375185633e-05,
|
| 2269 |
-
"loss": 1.6104,
|
| 2270 |
-
"step": 10013
|
| 2271 |
-
},
|
| 2272 |
-
{
|
| 2273 |
-
"epoch": 0.36360345358118995,
|
| 2274 |
-
"grad_norm": 1.448833703994751,
|
| 2275 |
-
"learning_rate": 4.0084807675119396e-05,
|
| 2276 |
-
"loss": 1.6299,
|
| 2277 |
-
"step": 10044
|
| 2278 |
-
},
|
| 2279 |
-
{
|
| 2280 |
-
"epoch": 0.36472568646261333,
|
| 2281 |
-
"grad_norm": 1.440450668334961,
|
| 2282 |
-
"learning_rate": 4.0017751368378106e-05,
|
| 2283 |
-
"loss": 1.6255,
|
| 2284 |
-
"step": 10075
|
| 2285 |
-
},
|
| 2286 |
-
{
|
| 2287 |
-
"epoch": 0.36584791934403676,
|
| 2288 |
-
"grad_norm": 1.3380858898162842,
|
| 2289 |
-
"learning_rate": 3.995052558835377e-05,
|
| 2290 |
-
"loss": 1.6162,
|
| 2291 |
-
"step": 10106
|
| 2292 |
-
},
|
| 2293 |
-
{
|
| 2294 |
-
"epoch": 0.3669701522254602,
|
| 2295 |
-
"grad_norm": 1.4549713134765625,
|
| 2296 |
-
"learning_rate": 3.988313109368017e-05,
|
| 2297 |
-
"loss": 1.6181,
|
| 2298 |
-
"step": 10137
|
| 2299 |
-
},
|
| 2300 |
-
{
|
| 2301 |
-
"epoch": 0.36809238510688363,
|
| 2302 |
-
"grad_norm": 1.4933863878250122,
|
| 2303 |
-
"learning_rate": 3.981556864489504e-05,
|
| 2304 |
-
"loss": 1.634,
|
| 2305 |
-
"step": 10168
|
| 2306 |
-
},
|
| 2307 |
-
{
|
| 2308 |
-
"epoch": 0.36921461798830707,
|
| 2309 |
-
"grad_norm": 1.5157703161239624,
|
| 2310 |
-
"learning_rate": 3.974783900443142e-05,
|
| 2311 |
-
"loss": 1.6258,
|
| 2312 |
-
"step": 10199
|
| 2313 |
-
},
|
| 2314 |
-
{
|
| 2315 |
-
"epoch": 0.3703368508697305,
|
| 2316 |
-
"grad_norm": 1.464006781578064,
|
| 2317 |
-
"learning_rate": 3.9679942936609095e-05,
|
| 2318 |
-
"loss": 1.6235,
|
| 2319 |
-
"step": 10230
|
| 2320 |
-
},
|
| 2321 |
-
{
|
| 2322 |
-
"epoch": 0.3714590837511539,
|
| 2323 |
-
"grad_norm": 1.3768154382705688,
|
| 2324 |
-
"learning_rate": 3.961188120762596e-05,
|
| 2325 |
-
"loss": 1.6044,
|
| 2326 |
-
"step": 10261
|
| 2327 |
-
},
|
| 2328 |
-
{
|
| 2329 |
-
"epoch": 0.3725813166325773,
|
| 2330 |
-
"grad_norm": 1.4427024126052856,
|
| 2331 |
-
"learning_rate": 3.954365458554938e-05,
|
| 2332 |
-
"loss": 1.6403,
|
| 2333 |
-
"step": 10292
|
| 2334 |
-
},
|
| 2335 |
-
{
|
| 2336 |
-
"epoch": 0.37370354951400075,
|
| 2337 |
-
"grad_norm": 1.3831264972686768,
|
| 2338 |
-
"learning_rate": 3.947526384030751e-05,
|
| 2339 |
-
"loss": 1.6136,
|
| 2340 |
-
"step": 10323
|
| 2341 |
-
},
|
| 2342 |
-
{
|
| 2343 |
-
"epoch": 0.3748257823954242,
|
| 2344 |
-
"grad_norm": 1.4275633096694946,
|
| 2345 |
-
"learning_rate": 3.9406709743680624e-05,
|
| 2346 |
-
"loss": 1.6167,
|
| 2347 |
-
"step": 10354
|
| 2348 |
-
},
|
| 2349 |
-
{
|
| 2350 |
-
"epoch": 0.3759480152768476,
|
| 2351 |
-
"grad_norm": 1.4378384351730347,
|
| 2352 |
-
"learning_rate": 3.9337993069292366e-05,
|
| 2353 |
-
"loss": 1.6231,
|
| 2354 |
-
"step": 10385
|
| 2355 |
-
},
|
| 2356 |
-
{
|
| 2357 |
-
"epoch": 0.37707024815827106,
|
| 2358 |
-
"grad_norm": 1.3743884563446045,
|
| 2359 |
-
"learning_rate": 3.926911459260109e-05,
|
| 2360 |
-
"loss": 1.6171,
|
| 2361 |
-
"step": 10416
|
| 2362 |
-
},
|
| 2363 |
-
{
|
| 2364 |
-
"epoch": 0.37819248103969444,
|
| 2365 |
-
"grad_norm": 1.496160864830017,
|
| 2366 |
-
"learning_rate": 3.920007509089102e-05,
|
| 2367 |
-
"loss": 1.6234,
|
| 2368 |
-
"step": 10447
|
| 2369 |
-
},
|
| 2370 |
-
{
|
| 2371 |
-
"epoch": 0.3793147139211179,
|
| 2372 |
-
"grad_norm": 1.4610028266906738,
|
| 2373 |
-
"learning_rate": 3.913087534326357e-05,
|
| 2374 |
-
"loss": 1.5963,
|
| 2375 |
-
"step": 10478
|
| 2376 |
-
},
|
| 2377 |
-
{
|
| 2378 |
-
"epoch": 0.3804369468025413,
|
| 2379 |
-
"grad_norm": 1.483314037322998,
|
| 2380 |
-
"learning_rate": 3.9061516130628475e-05,
|
| 2381 |
-
"loss": 1.6021,
|
| 2382 |
-
"step": 10509
|
| 2383 |
-
},
|
| 2384 |
-
{
|
| 2385 |
-
"epoch": 0.38155917968396474,
|
| 2386 |
-
"grad_norm": 1.4944846630096436,
|
| 2387 |
-
"learning_rate": 3.8991998235695025e-05,
|
| 2388 |
-
"loss": 1.5833,
|
| 2389 |
-
"step": 10540
|
| 2390 |
-
},
|
| 2391 |
-
{
|
| 2392 |
-
"epoch": 0.3826814125653882,
|
| 2393 |
-
"grad_norm": 1.3831861019134521,
|
| 2394 |
-
"learning_rate": 3.8922322442963224e-05,
|
| 2395 |
-
"loss": 1.624,
|
| 2396 |
-
"step": 10571
|
| 2397 |
-
},
|
| 2398 |
-
{
|
| 2399 |
-
"epoch": 0.3838036454468116,
|
| 2400 |
-
"grad_norm": 1.4178634881973267,
|
| 2401 |
-
"learning_rate": 3.885248953871491e-05,
|
| 2402 |
-
"loss": 1.6188,
|
| 2403 |
-
"step": 10602
|
| 2404 |
-
},
|
| 2405 |
-
{
|
| 2406 |
-
"epoch": 0.384925878328235,
|
| 2407 |
-
"grad_norm": 1.4889320135116577,
|
| 2408 |
-
"learning_rate": 3.8782500311004915e-05,
|
| 2409 |
-
"loss": 1.608,
|
| 2410 |
-
"step": 10633
|
| 2411 |
-
},
|
| 2412 |
-
{
|
| 2413 |
-
"epoch": 0.38604811120965843,
|
| 2414 |
-
"grad_norm": 1.3335620164871216,
|
| 2415 |
-
"learning_rate": 3.871235554965218e-05,
|
| 2416 |
-
"loss": 1.6182,
|
| 2417 |
-
"step": 10664
|
| 2418 |
-
},
|
| 2419 |
-
{
|
| 2420 |
-
"epoch": 0.38717034409108186,
|
| 2421 |
-
"grad_norm": 1.4620449542999268,
|
| 2422 |
-
"learning_rate": 3.864205604623078e-05,
|
| 2423 |
-
"loss": 1.5848,
|
| 2424 |
-
"step": 10695
|
| 2425 |
-
},
|
| 2426 |
-
{
|
| 2427 |
-
"epoch": 0.3882925769725053,
|
| 2428 |
-
"grad_norm": 1.3857917785644531,
|
| 2429 |
-
"learning_rate": 3.857160259406107e-05,
|
| 2430 |
-
"loss": 1.6048,
|
| 2431 |
-
"step": 10726
|
| 2432 |
-
},
|
| 2433 |
-
{
|
| 2434 |
-
"epoch": 0.38941480985392873,
|
| 2435 |
-
"grad_norm": 1.4226957559585571,
|
| 2436 |
-
"learning_rate": 3.8500995988200674e-05,
|
| 2437 |
-
"loss": 1.6052,
|
| 2438 |
-
"step": 10757
|
| 2439 |
-
},
|
| 2440 |
-
{
|
| 2441 |
-
"epoch": 0.39053704273535217,
|
| 2442 |
-
"grad_norm": 1.478182077407837,
|
| 2443 |
-
"learning_rate": 3.843023702543556e-05,
|
| 2444 |
-
"loss": 1.6268,
|
| 2445 |
-
"step": 10788
|
| 2446 |
-
},
|
| 2447 |
-
{
|
| 2448 |
-
"epoch": 0.39165927561677555,
|
| 2449 |
-
"grad_norm": 1.431401014328003,
|
| 2450 |
-
"learning_rate": 3.8359326504270984e-05,
|
| 2451 |
-
"loss": 1.6176,
|
| 2452 |
-
"step": 10819
|
| 2453 |
-
},
|
| 2454 |
-
{
|
| 2455 |
-
"epoch": 0.392781508498199,
|
| 2456 |
-
"grad_norm": 1.339880108833313,
|
| 2457 |
-
"learning_rate": 3.828826522492255e-05,
|
| 2458 |
-
"loss": 1.5902,
|
| 2459 |
-
"step": 10850
|
| 2460 |
-
},
|
| 2461 |
-
{
|
| 2462 |
-
"epoch": 0.3939037413796224,
|
| 2463 |
-
"grad_norm": 1.4537174701690674,
|
| 2464 |
-
"learning_rate": 3.821705398930713e-05,
|
| 2465 |
-
"loss": 1.6107,
|
| 2466 |
-
"step": 10881
|
| 2467 |
-
},
|
| 2468 |
-
{
|
| 2469 |
-
"epoch": 0.39502597426104585,
|
| 2470 |
-
"grad_norm": 1.3559256792068481,
|
| 2471 |
-
"learning_rate": 3.814569360103385e-05,
|
| 2472 |
-
"loss": 1.5879,
|
| 2473 |
-
"step": 10912
|
| 2474 |
-
},
|
| 2475 |
-
{
|
| 2476 |
-
"epoch": 0.3961482071424693,
|
| 2477 |
-
"grad_norm": 1.3561891317367554,
|
| 2478 |
-
"learning_rate": 3.807418486539499e-05,
|
| 2479 |
-
"loss": 1.6162,
|
| 2480 |
-
"step": 10943
|
| 2481 |
-
},
|
| 2482 |
-
{
|
| 2483 |
-
"epoch": 0.3972704400238927,
|
| 2484 |
-
"grad_norm": 1.471112847328186,
|
| 2485 |
-
"learning_rate": 3.80025285893569e-05,
|
| 2486 |
-
"loss": 1.5968,
|
| 2487 |
-
"step": 10974
|
| 2488 |
-
},
|
| 2489 |
-
{
|
| 2490 |
-
"epoch": 0.3983926729053161,
|
| 2491 |
-
"grad_norm": 1.3438925743103027,
|
| 2492 |
-
"learning_rate": 3.793072558155093e-05,
|
| 2493 |
-
"loss": 1.5876,
|
| 2494 |
-
"step": 11005
|
| 2495 |
-
},
|
| 2496 |
-
{
|
| 2497 |
-
"epoch": 0.39951490578673954,
|
| 2498 |
-
"grad_norm": 1.4102482795715332,
|
| 2499 |
-
"learning_rate": 3.785877665226426e-05,
|
| 2500 |
-
"loss": 1.5886,
|
| 2501 |
-
"step": 11036
|
| 2502 |
-
},
|
| 2503 |
-
{
|
| 2504 |
-
"epoch": 0.400637138668163,
|
| 2505 |
-
"grad_norm": 1.4435259103775024,
|
| 2506 |
-
"learning_rate": 3.778668261343079e-05,
|
| 2507 |
-
"loss": 1.5999,
|
| 2508 |
-
"step": 11067
|
| 2509 |
-
},
|
| 2510 |
-
{
|
| 2511 |
-
"epoch": 0.4017593715495864,
|
| 2512 |
-
"grad_norm": 1.4556541442871094,
|
| 2513 |
-
"learning_rate": 3.771444427862192e-05,
|
| 2514 |
-
"loss": 1.6185,
|
| 2515 |
-
"step": 11098
|
| 2516 |
-
},
|
| 2517 |
-
{
|
| 2518 |
-
"epoch": 0.40288160443100984,
|
| 2519 |
-
"grad_norm": 1.370553970336914,
|
| 2520 |
-
"learning_rate": 3.7642062463037465e-05,
|
| 2521 |
-
"loss": 1.6005,
|
| 2522 |
-
"step": 11129
|
| 2523 |
-
},
|
| 2524 |
-
{
|
| 2525 |
-
"epoch": 0.4040038373124333,
|
| 2526 |
-
"grad_norm": 1.368855595588684,
|
| 2527 |
-
"learning_rate": 3.7569537983496373e-05,
|
| 2528 |
-
"loss": 1.6024,
|
| 2529 |
-
"step": 11160
|
| 2530 |
-
},
|
| 2531 |
-
{
|
| 2532 |
-
"epoch": 0.40512607019385666,
|
| 2533 |
-
"grad_norm": 1.4200265407562256,
|
| 2534 |
-
"learning_rate": 3.749687165842753e-05,
|
| 2535 |
-
"loss": 1.6082,
|
| 2536 |
-
"step": 11191
|
| 2537 |
-
},
|
| 2538 |
-
{
|
| 2539 |
-
"epoch": 0.4062483030752801,
|
| 2540 |
-
"grad_norm": 1.4704499244689941,
|
| 2541 |
-
"learning_rate": 3.7424064307860536e-05,
|
| 2542 |
-
"loss": 1.6227,
|
| 2543 |
-
"step": 11222
|
| 2544 |
-
},
|
| 2545 |
-
{
|
| 2546 |
-
"epoch": 0.40737053595670353,
|
| 2547 |
-
"grad_norm": 1.3868876695632935,
|
| 2548 |
-
"learning_rate": 3.735111675341645e-05,
|
| 2549 |
-
"loss": 1.6008,
|
| 2550 |
-
"step": 11253
|
| 2551 |
-
},
|
| 2552 |
-
{
|
| 2553 |
-
"epoch": 0.40849276883812696,
|
| 2554 |
-
"grad_norm": 1.473650574684143,
|
| 2555 |
-
"learning_rate": 3.7278029818298524e-05,
|
| 2556 |
-
"loss": 1.5825,
|
| 2557 |
-
"step": 11284
|
| 2558 |
-
},
|
| 2559 |
-
{
|
| 2560 |
-
"epoch": 0.4096150017195504,
|
| 2561 |
-
"grad_norm": 1.412559986114502,
|
| 2562 |
-
"learning_rate": 3.720480432728287e-05,
|
| 2563 |
-
"loss": 1.5971,
|
| 2564 |
-
"step": 11315
|
| 2565 |
-
},
|
| 2566 |
-
{
|
| 2567 |
-
"epoch": 0.41073723460097383,
|
| 2568 |
-
"grad_norm": 1.4288370609283447,
|
| 2569 |
-
"learning_rate": 3.71314411067092e-05,
|
| 2570 |
-
"loss": 1.6079,
|
| 2571 |
-
"step": 11346
|
| 2572 |
-
},
|
| 2573 |
-
{
|
| 2574 |
-
"epoch": 0.4118594674823972,
|
| 2575 |
-
"grad_norm": 1.4781348705291748,
|
| 2576 |
-
"learning_rate": 3.70579409844715e-05,
|
| 2577 |
-
"loss": 1.5904,
|
| 2578 |
-
"step": 11377
|
| 2579 |
-
},
|
| 2580 |
-
{
|
| 2581 |
-
"epoch": 0.41298170036382065,
|
| 2582 |
-
"grad_norm": 1.377030611038208,
|
| 2583 |
-
"learning_rate": 3.698430479000865e-05,
|
| 2584 |
-
"loss": 1.5804,
|
| 2585 |
-
"step": 11408
|
| 2586 |
-
},
|
| 2587 |
-
{
|
| 2588 |
-
"epoch": 0.4141039332452441,
|
| 2589 |
-
"grad_norm": 1.4176589250564575,
|
| 2590 |
-
"learning_rate": 3.691053335429509e-05,
|
| 2591 |
-
"loss": 1.6046,
|
| 2592 |
-
"step": 11439
|
| 2593 |
-
},
|
| 2594 |
-
{
|
| 2595 |
-
"epoch": 0.4152261661266675,
|
| 2596 |
-
"grad_norm": 1.4933243989944458,
|
| 2597 |
-
"learning_rate": 3.683662750983147e-05,
|
| 2598 |
-
"loss": 1.6018,
|
| 2599 |
-
"step": 11470
|
| 2600 |
-
},
|
| 2601 |
-
{
|
| 2602 |
-
"epoch": 0.41634839900809095,
|
| 2603 |
-
"grad_norm": 1.4382365942001343,
|
| 2604 |
-
"learning_rate": 3.676258809063518e-05,
|
| 2605 |
-
"loss": 1.5962,
|
| 2606 |
-
"step": 11501
|
| 2607 |
-
},
|
| 2608 |
-
{
|
| 2609 |
-
"epoch": 0.4174706318895144,
|
| 2610 |
-
"grad_norm": 1.468005657196045,
|
| 2611 |
-
"learning_rate": 3.6688415932231004e-05,
|
| 2612 |
-
"loss": 1.6044,
|
| 2613 |
-
"step": 11532
|
| 2614 |
-
},
|
| 2615 |
-
{
|
| 2616 |
-
"epoch": 0.41859286477093777,
|
| 2617 |
-
"grad_norm": 1.4858007431030273,
|
| 2618 |
-
"learning_rate": 3.661411187164166e-05,
|
| 2619 |
-
"loss": 1.5973,
|
| 2620 |
-
"step": 11563
|
| 2621 |
-
},
|
| 2622 |
-
{
|
| 2623 |
-
"epoch": 0.4197150976523612,
|
| 2624 |
-
"grad_norm": 1.457524061203003,
|
| 2625 |
-
"learning_rate": 3.65396767473784e-05,
|
| 2626 |
-
"loss": 1.5872,
|
| 2627 |
-
"step": 11594
|
| 2628 |
-
},
|
| 2629 |
-
{
|
| 2630 |
-
"epoch": 0.42083733053378464,
|
| 2631 |
-
"grad_norm": 1.4685806035995483,
|
| 2632 |
-
"learning_rate": 3.6465111399431465e-05,
|
| 2633 |
-
"loss": 1.6072,
|
| 2634 |
-
"step": 11625
|
| 2635 |
-
},
|
| 2636 |
-
{
|
| 2637 |
-
"epoch": 0.42195956341520807,
|
| 2638 |
-
"grad_norm": 1.4355812072753906,
|
| 2639 |
-
"learning_rate": 3.6390416669260674e-05,
|
| 2640 |
-
"loss": 1.6005,
|
| 2641 |
-
"step": 11656
|
| 2642 |
-
},
|
| 2643 |
-
{
|
| 2644 |
-
"epoch": 0.4230817962966315,
|
| 2645 |
-
"grad_norm": 1.4105843305587769,
|
| 2646 |
-
"learning_rate": 3.63155933997859e-05,
|
| 2647 |
-
"loss": 1.5999,
|
| 2648 |
-
"step": 11687
|
| 2649 |
-
},
|
| 2650 |
-
{
|
| 2651 |
-
"epoch": 0.42420402917805494,
|
| 2652 |
-
"grad_norm": 1.4515639543533325,
|
| 2653 |
-
"learning_rate": 3.624064243537758e-05,
|
| 2654 |
-
"loss": 1.5903,
|
| 2655 |
-
"step": 11718
|
| 2656 |
-
},
|
| 2657 |
-
{
|
| 2658 |
-
"epoch": 0.4253262620594783,
|
| 2659 |
-
"grad_norm": 1.4507205486297607,
|
| 2660 |
-
"learning_rate": 3.616556462184716e-05,
|
| 2661 |
-
"loss": 1.6004,
|
| 2662 |
-
"step": 11749
|
| 2663 |
-
},
|
| 2664 |
-
{
|
| 2665 |
-
"epoch": 0.42644849494090176,
|
| 2666 |
-
"grad_norm": 1.3846348524093628,
|
| 2667 |
-
"learning_rate": 3.609036080643755e-05,
|
| 2668 |
-
"loss": 1.5878,
|
| 2669 |
-
"step": 11780
|
| 2670 |
-
},
|
| 2671 |
-
{
|
| 2672 |
-
"epoch": 0.4275707278223252,
|
| 2673 |
-
"grad_norm": 1.4062190055847168,
|
| 2674 |
-
"learning_rate": 3.60150318378136e-05,
|
| 2675 |
-
"loss": 1.6049,
|
| 2676 |
-
"step": 11811
|
| 2677 |
-
},
|
| 2678 |
-
{
|
| 2679 |
-
"epoch": 0.4286929607037486,
|
| 2680 |
-
"grad_norm": 1.5231355428695679,
|
| 2681 |
-
"learning_rate": 3.5939578566052465e-05,
|
| 2682 |
-
"loss": 1.5972,
|
| 2683 |
-
"step": 11842
|
| 2684 |
-
},
|
| 2685 |
-
{
|
| 2686 |
-
"epoch": 0.42981519358517206,
|
| 2687 |
-
"grad_norm": 1.4500449895858765,
|
| 2688 |
-
"learning_rate": 3.586400184263408e-05,
|
| 2689 |
-
"loss": 1.5918,
|
| 2690 |
-
"step": 11873
|
| 2691 |
-
},
|
| 2692 |
-
{
|
| 2693 |
-
"epoch": 0.4309374264665955,
|
| 2694 |
-
"grad_norm": 1.415440559387207,
|
| 2695 |
-
"learning_rate": 3.578830252043148e-05,
|
| 2696 |
-
"loss": 1.6111,
|
| 2697 |
-
"step": 11904
|
| 2698 |
-
},
|
| 2699 |
-
{
|
| 2700 |
-
"epoch": 0.4320596593480189,
|
| 2701 |
-
"grad_norm": 1.3857108354568481,
|
| 2702 |
-
"learning_rate": 3.571248145370125e-05,
|
| 2703 |
-
"loss": 1.5882,
|
| 2704 |
-
"step": 11935
|
| 2705 |
-
},
|
| 2706 |
-
{
|
| 2707 |
-
"epoch": 0.4331818922294423,
|
| 2708 |
-
"grad_norm": 1.442830204963684,
|
| 2709 |
-
"learning_rate": 3.5636539498073794e-05,
|
| 2710 |
-
"loss": 1.587,
|
| 2711 |
-
"step": 11966
|
| 2712 |
-
},
|
| 2713 |
-
{
|
| 2714 |
-
"epoch": 0.43430412511086575,
|
| 2715 |
-
"grad_norm": 1.3706488609313965,
|
| 2716 |
-
"learning_rate": 3.556047751054378e-05,
|
| 2717 |
-
"loss": 1.5942,
|
| 2718 |
-
"step": 11997
|
| 2719 |
-
},
|
| 2720 |
-
{
|
| 2721 |
-
"epoch": 0.4354263579922892,
|
| 2722 |
-
"grad_norm": 1.450567364692688,
|
| 2723 |
-
"learning_rate": 3.548429634946039e-05,
|
| 2724 |
-
"loss": 1.6011,
|
| 2725 |
-
"step": 12028
|
| 2726 |
-
},
|
| 2727 |
-
{
|
| 2728 |
-
"epoch": 0.4365485908737126,
|
| 2729 |
-
"grad_norm": 1.4172272682189941,
|
| 2730 |
-
"learning_rate": 3.540799687451768e-05,
|
| 2731 |
-
"loss": 1.5726,
|
| 2732 |
-
"step": 12059
|
| 2733 |
-
},
|
| 2734 |
-
{
|
| 2735 |
-
"epoch": 0.43767082375513605,
|
| 2736 |
-
"grad_norm": 1.4156157970428467,
|
| 2737 |
-
"learning_rate": 3.533157994674485e-05,
|
| 2738 |
-
"loss": 1.5848,
|
| 2739 |
-
"step": 12090
|
| 2740 |
-
},
|
| 2741 |
-
{
|
| 2742 |
-
"epoch": 0.43879305663655943,
|
| 2743 |
-
"grad_norm": 1.3843419551849365,
|
| 2744 |
-
"learning_rate": 3.5255046428496546e-05,
|
| 2745 |
-
"loss": 1.5893,
|
| 2746 |
-
"step": 12121
|
| 2747 |
-
},
|
| 2748 |
-
{
|
| 2749 |
-
"epoch": 0.43991528951798287,
|
| 2750 |
-
"grad_norm": 1.43569815158844,
|
| 2751 |
-
"learning_rate": 3.517839718344311e-05,
|
| 2752 |
-
"loss": 1.5922,
|
| 2753 |
-
"step": 12152
|
| 2754 |
-
},
|
| 2755 |
-
{
|
| 2756 |
-
"epoch": 0.4410375223994063,
|
| 2757 |
-
"grad_norm": 1.4200314283370972,
|
| 2758 |
-
"learning_rate": 3.510163307656086e-05,
|
| 2759 |
-
"loss": 1.6047,
|
| 2760 |
-
"step": 12183
|
| 2761 |
-
},
|
| 2762 |
-
{
|
| 2763 |
-
"epoch": 0.44215975528082974,
|
| 2764 |
-
"grad_norm": 1.4956674575805664,
|
| 2765 |
-
"learning_rate": 3.5024754974122324e-05,
|
| 2766 |
-
"loss": 1.5802,
|
| 2767 |
-
"step": 12214
|
| 2768 |
-
},
|
| 2769 |
-
{
|
| 2770 |
-
"epoch": 0.44328198816225317,
|
| 2771 |
-
"grad_norm": 1.4289231300354004,
|
| 2772 |
-
"learning_rate": 3.494776374368643e-05,
|
| 2773 |
-
"loss": 1.6193,
|
| 2774 |
-
"step": 12245
|
| 2775 |
-
},
|
| 2776 |
-
{
|
| 2777 |
-
"epoch": 0.4444042210436766,
|
| 2778 |
-
"grad_norm": 1.389282464981079,
|
| 2779 |
-
"learning_rate": 3.4870660254088724e-05,
|
| 2780 |
-
"loss": 1.5977,
|
| 2781 |
-
"step": 12276
|
| 2782 |
-
},
|
| 2783 |
-
{
|
| 2784 |
-
"epoch": 0.4455264539251,
|
| 2785 |
-
"grad_norm": 1.4207974672317505,
|
| 2786 |
-
"learning_rate": 3.479344537543164e-05,
|
| 2787 |
-
"loss": 1.5789,
|
| 2788 |
-
"step": 12307
|
| 2789 |
-
},
|
| 2790 |
-
{
|
| 2791 |
-
"epoch": 0.4466486868065234,
|
| 2792 |
-
"grad_norm": 1.355353832244873,
|
| 2793 |
-
"learning_rate": 3.4716119979074565e-05,
|
| 2794 |
-
"loss": 1.5889,
|
| 2795 |
-
"step": 12338
|
| 2796 |
-
},
|
| 2797 |
-
{
|
| 2798 |
-
"epoch": 0.44777091968794686,
|
| 2799 |
-
"grad_norm": 1.3336408138275146,
|
| 2800 |
-
"learning_rate": 3.463868493762412e-05,
|
| 2801 |
-
"loss": 1.5865,
|
| 2802 |
-
"step": 12369
|
| 2803 |
-
},
|
| 2804 |
-
{
|
| 2805 |
-
"epoch": 0.4488931525693703,
|
| 2806 |
-
"grad_norm": 1.5265244245529175,
|
| 2807 |
-
"learning_rate": 3.456114112492418e-05,
|
| 2808 |
-
"loss": 1.5993,
|
| 2809 |
-
"step": 12400
|
| 2810 |
-
},
|
| 2811 |
-
{
|
| 2812 |
-
"epoch": 0.4500153854507937,
|
| 2813 |
-
"grad_norm": 1.4629555940628052,
|
| 2814 |
-
"learning_rate": 3.4483489416046164e-05,
|
| 2815 |
-
"loss": 1.5982,
|
| 2816 |
-
"step": 12431
|
| 2817 |
-
},
|
| 2818 |
-
{
|
| 2819 |
-
"epoch": 0.45113761833221716,
|
| 2820 |
-
"grad_norm": 1.43988835811615,
|
| 2821 |
-
"learning_rate": 3.440573068727905e-05,
|
| 2822 |
-
"loss": 1.5816,
|
| 2823 |
-
"step": 12462
|
| 2824 |
-
},
|
| 2825 |
-
{
|
| 2826 |
-
"epoch": 0.45225985121364054,
|
| 2827 |
-
"grad_norm": 1.4607633352279663,
|
| 2828 |
-
"learning_rate": 3.4327865816119495e-05,
|
| 2829 |
-
"loss": 1.571,
|
| 2830 |
-
"step": 12493
|
| 2831 |
-
},
|
| 2832 |
-
{
|
| 2833 |
-
"epoch": 0.453382084095064,
|
| 2834 |
-
"grad_norm": 1.3664649724960327,
|
| 2835 |
-
"learning_rate": 3.4249895681262025e-05,
|
| 2836 |
-
"loss": 1.5736,
|
| 2837 |
-
"step": 12524
|
| 2838 |
-
},
|
| 2839 |
-
{
|
| 2840 |
-
"epoch": 0.4545043169764874,
|
| 2841 |
-
"grad_norm": 1.436094880104065,
|
| 2842 |
-
"learning_rate": 3.417182116258899e-05,
|
| 2843 |
-
"loss": 1.5829,
|
| 2844 |
-
"step": 12555
|
| 2845 |
-
},
|
| 2846 |
-
{
|
| 2847 |
-
"epoch": 0.45562654985791085,
|
| 2848 |
-
"grad_norm": 1.3681309223175049,
|
| 2849 |
-
"learning_rate": 3.409364314116074e-05,
|
| 2850 |
-
"loss": 1.5938,
|
| 2851 |
-
"step": 12586
|
| 2852 |
-
},
|
| 2853 |
-
{
|
| 2854 |
-
"epoch": 0.4567487827393343,
|
| 2855 |
-
"grad_norm": 1.3929277658462524,
|
| 2856 |
-
"learning_rate": 3.401536249920559e-05,
|
| 2857 |
-
"loss": 1.572,
|
| 2858 |
-
"step": 12617
|
| 2859 |
-
},
|
| 2860 |
-
{
|
| 2861 |
-
"epoch": 0.4578710156207577,
|
| 2862 |
-
"grad_norm": 1.3980777263641357,
|
| 2863 |
-
"learning_rate": 3.393698012010998e-05,
|
| 2864 |
-
"loss": 1.5941,
|
| 2865 |
-
"step": 12648
|
| 2866 |
-
},
|
| 2867 |
-
{
|
| 2868 |
-
"epoch": 0.4589932485021811,
|
| 2869 |
-
"grad_norm": 1.4055850505828857,
|
| 2870 |
-
"learning_rate": 3.385849688840839e-05,
|
| 2871 |
-
"loss": 1.5818,
|
| 2872 |
-
"step": 12679
|
| 2873 |
-
},
|
| 2874 |
-
{
|
| 2875 |
-
"epoch": 0.46011548138360453,
|
| 2876 |
-
"grad_norm": 1.3678046464920044,
|
| 2877 |
-
"learning_rate": 3.3779913689773414e-05,
|
| 2878 |
-
"loss": 1.5759,
|
| 2879 |
-
"step": 12710
|
| 2880 |
-
},
|
| 2881 |
-
{
|
| 2882 |
-
"epoch": 0.46123771426502796,
|
| 2883 |
-
"grad_norm": 1.468201994895935,
|
| 2884 |
-
"learning_rate": 3.370123141100578e-05,
|
| 2885 |
-
"loss": 1.5792,
|
| 2886 |
-
"step": 12741
|
| 2887 |
-
},
|
| 2888 |
-
{
|
| 2889 |
-
"epoch": 0.4623599471464514,
|
| 2890 |
-
"grad_norm": 1.346614122390747,
|
| 2891 |
-
"learning_rate": 3.3622450940024305e-05,
|
| 2892 |
-
"loss": 1.5983,
|
| 2893 |
-
"step": 12772
|
| 2894 |
-
},
|
| 2895 |
-
{
|
| 2896 |
-
"epoch": 0.46348218002787483,
|
| 2897 |
-
"grad_norm": 1.3895704746246338,
|
| 2898 |
-
"learning_rate": 3.35435731658559e-05,
|
| 2899 |
-
"loss": 1.5809,
|
| 2900 |
-
"step": 12803
|
| 2901 |
-
},
|
| 2902 |
-
{
|
| 2903 |
-
"epoch": 0.46460441290929827,
|
| 2904 |
-
"grad_norm": 1.3664804697036743,
|
| 2905 |
-
"learning_rate": 3.346459897862552e-05,
|
| 2906 |
-
"loss": 1.5788,
|
| 2907 |
-
"step": 12834
|
| 2908 |
-
},
|
| 2909 |
-
{
|
| 2910 |
-
"epoch": 0.46572664579072165,
|
| 2911 |
-
"grad_norm": 1.4561264514923096,
|
| 2912 |
-
"learning_rate": 3.338552926954613e-05,
|
| 2913 |
-
"loss": 1.5867,
|
| 2914 |
-
"step": 12865
|
| 2915 |
-
},
|
| 2916 |
-
{
|
| 2917 |
-
"epoch": 0.4668488786721451,
|
| 2918 |
-
"grad_norm": 1.3407316207885742,
|
| 2919 |
-
"learning_rate": 3.330636493090868e-05,
|
| 2920 |
-
"loss": 1.5729,
|
| 2921 |
-
"step": 12896
|
| 2922 |
-
},
|
| 2923 |
-
{
|
| 2924 |
-
"epoch": 0.4679711115535685,
|
| 2925 |
-
"grad_norm": 1.3465179204940796,
|
| 2926 |
-
"learning_rate": 3.322710685607193e-05,
|
| 2927 |
-
"loss": 1.5915,
|
| 2928 |
-
"step": 12927
|
| 2929 |
-
},
|
| 2930 |
-
{
|
| 2931 |
-
"epoch": 0.46909334443499195,
|
| 2932 |
-
"grad_norm": 1.553585171699524,
|
| 2933 |
-
"learning_rate": 3.314775593945251e-05,
|
| 2934 |
-
"loss": 1.5875,
|
| 2935 |
-
"step": 12958
|
| 2936 |
-
},
|
| 2937 |
-
{
|
| 2938 |
-
"epoch": 0.4702155773164154,
|
| 2939 |
-
"grad_norm": 1.3964170217514038,
|
| 2940 |
-
"learning_rate": 3.3068313076514714e-05,
|
| 2941 |
-
"loss": 1.5783,
|
| 2942 |
-
"step": 12989
|
| 2943 |
-
},
|
| 2944 |
-
{
|
| 2945 |
-
"epoch": 0.47133781019783877,
|
| 2946 |
-
"grad_norm": 1.3884953260421753,
|
| 2947 |
-
"learning_rate": 3.298877916376047e-05,
|
| 2948 |
-
"loss": 1.5577,
|
| 2949 |
-
"step": 13020
|
| 2950 |
-
},
|
| 2951 |
-
{
|
| 2952 |
-
"epoch": 0.4724600430792622,
|
| 2953 |
-
"grad_norm": 1.3421337604522705,
|
| 2954 |
-
"learning_rate": 3.290915509871915e-05,
|
| 2955 |
-
"loss": 1.5791,
|
| 2956 |
-
"step": 13051
|
| 2957 |
-
},
|
| 2958 |
-
{
|
| 2959 |
-
"epoch": 0.47358227596068564,
|
| 2960 |
-
"grad_norm": 1.297429084777832,
|
| 2961 |
-
"learning_rate": 3.282944177993753e-05,
|
| 2962 |
-
"loss": 1.5699,
|
| 2963 |
-
"step": 13082
|
| 2964 |
-
},
|
| 2965 |
-
{
|
| 2966 |
-
"epoch": 0.4747045088421091,
|
| 2967 |
-
"grad_norm": 1.3672280311584473,
|
| 2968 |
-
"learning_rate": 3.274964010696957e-05,
|
| 2969 |
-
"loss": 1.5711,
|
| 2970 |
-
"step": 13113
|
| 2971 |
-
},
|
| 2972 |
-
{
|
| 2973 |
-
"epoch": 0.4758267417235325,
|
| 2974 |
-
"grad_norm": 1.4202091693878174,
|
| 2975 |
-
"learning_rate": 3.266975098036629e-05,
|
| 2976 |
-
"loss": 1.5679,
|
| 2977 |
-
"step": 13144
|
| 2978 |
-
},
|
| 2979 |
-
{
|
| 2980 |
-
"epoch": 0.47694897460495594,
|
| 2981 |
-
"grad_norm": 1.383973479270935,
|
| 2982 |
-
"learning_rate": 3.258977530166562e-05,
|
| 2983 |
-
"loss": 1.6019,
|
| 2984 |
-
"step": 13175
|
| 2985 |
-
},
|
| 2986 |
-
{
|
| 2987 |
-
"epoch": 0.4780712074863793,
|
| 2988 |
-
"grad_norm": 1.3134119510650635,
|
| 2989 |
-
"learning_rate": 3.250971397338227e-05,
|
| 2990 |
-
"loss": 1.5721,
|
| 2991 |
-
"step": 13206
|
| 2992 |
-
},
|
| 2993 |
-
{
|
| 2994 |
-
"epoch": 0.47919344036780276,
|
| 2995 |
-
"grad_norm": 1.3229272365570068,
|
| 2996 |
-
"learning_rate": 3.2429567898997404e-05,
|
| 2997 |
-
"loss": 1.5812,
|
| 2998 |
-
"step": 13237
|
| 2999 |
-
},
|
| 3000 |
-
{
|
| 3001 |
-
"epoch": 0.4803156732492262,
|
| 3002 |
-
"grad_norm": 1.2991341352462769,
|
| 3003 |
-
"learning_rate": 3.234933798294859e-05,
|
| 3004 |
-
"loss": 1.5793,
|
| 3005 |
-
"step": 13268
|
| 3006 |
-
},
|
| 3007 |
-
{
|
| 3008 |
-
"epoch": 0.48143790613064963,
|
| 3009 |
-
"grad_norm": 1.384522795677185,
|
| 3010 |
-
"learning_rate": 3.2269025130619535e-05,
|
| 3011 |
-
"loss": 1.5592,
|
| 3012 |
-
"step": 13299
|
| 3013 |
-
},
|
| 3014 |
-
{
|
| 3015 |
-
"epoch": 0.48256013901207306,
|
| 3016 |
-
"grad_norm": 1.3743617534637451,
|
| 3017 |
-
"learning_rate": 3.218863024832985e-05,
|
| 3018 |
-
"loss": 1.5785,
|
| 3019 |
-
"step": 13330
|
| 3020 |
-
},
|
| 3021 |
-
{
|
| 3022 |
-
"epoch": 0.4836823718934965,
|
| 3023 |
-
"grad_norm": 1.4512649774551392,
|
| 3024 |
-
"learning_rate": 3.2108154243324864e-05,
|
| 3025 |
-
"loss": 1.5703,
|
| 3026 |
-
"step": 13361
|
| 3027 |
-
},
|
| 3028 |
-
{
|
| 3029 |
-
"epoch": 0.4848046047749199,
|
| 3030 |
-
"grad_norm": 1.2982932329177856,
|
| 3031 |
-
"learning_rate": 3.2027598023765345e-05,
|
| 3032 |
-
"loss": 1.5609,
|
| 3033 |
-
"step": 13392
|
| 3034 |
-
},
|
| 3035 |
-
{
|
| 3036 |
-
"epoch": 0.4859268376563433,
|
| 3037 |
-
"grad_norm": 1.3747495412826538,
|
| 3038 |
-
"learning_rate": 3.194696249871729e-05,
|
| 3039 |
-
"loss": 1.5766,
|
| 3040 |
-
"step": 13423
|
| 3041 |
-
},
|
| 3042 |
-
{
|
| 3043 |
-
"epoch": 0.48704907053776675,
|
| 3044 |
-
"grad_norm": 1.3155137300491333,
|
| 3045 |
-
"learning_rate": 3.186624857814164e-05,
|
| 3046 |
-
"loss": 1.57,
|
| 3047 |
-
"step": 13454
|
| 3048 |
-
},
|
| 3049 |
-
{
|
| 3050 |
-
"epoch": 0.4881713034191902,
|
| 3051 |
-
"grad_norm": 1.4094924926757812,
|
| 3052 |
-
"learning_rate": 3.178545717288401e-05,
|
| 3053 |
-
"loss": 1.5855,
|
| 3054 |
-
"step": 13485
|
| 3055 |
-
},
|
| 3056 |
-
{
|
| 3057 |
-
"epoch": 0.4892935363006136,
|
| 3058 |
-
"grad_norm": 1.3931294679641724,
|
| 3059 |
-
"learning_rate": 3.170458919466444e-05,
|
| 3060 |
-
"loss": 1.5486,
|
| 3061 |
-
"step": 13516
|
| 3062 |
-
},
|
| 3063 |
-
{
|
| 3064 |
-
"epoch": 0.49041576918203705,
|
| 3065 |
-
"grad_norm": 1.48263418674469,
|
| 3066 |
-
"learning_rate": 3.1623645556067063e-05,
|
| 3067 |
-
"loss": 1.5829,
|
| 3068 |
-
"step": 13547
|
| 3069 |
-
},
|
| 3070 |
-
{
|
| 3071 |
-
"epoch": 0.49153800206346043,
|
| 3072 |
-
"grad_norm": 1.3016873598098755,
|
| 3073 |
-
"learning_rate": 3.154262717052985e-05,
|
| 3074 |
-
"loss": 1.5808,
|
| 3075 |
-
"step": 13578
|
| 3076 |
-
},
|
| 3077 |
-
{
|
| 3078 |
-
"epoch": 0.49266023494488387,
|
| 3079 |
-
"grad_norm": 1.623724102973938,
|
| 3080 |
-
"learning_rate": 3.146153495233426e-05,
|
| 3081 |
-
"loss": 1.5582,
|
| 3082 |
-
"step": 13609
|
| 3083 |
-
},
|
| 3084 |
-
{
|
| 3085 |
-
"epoch": 0.4937824678263073,
|
| 3086 |
-
"grad_norm": 1.3603851795196533,
|
| 3087 |
-
"learning_rate": 3.1380369816594944e-05,
|
| 3088 |
-
"loss": 1.5703,
|
| 3089 |
-
"step": 13640
|
| 3090 |
-
},
|
| 3091 |
-
{
|
| 3092 |
-
"epoch": 0.49490470070773074,
|
| 3093 |
-
"grad_norm": 1.4793063402175903,
|
| 3094 |
-
"learning_rate": 3.129913267924946e-05,
|
| 3095 |
-
"loss": 1.5739,
|
| 3096 |
-
"step": 13671
|
| 3097 |
-
},
|
| 3098 |
-
{
|
| 3099 |
-
"epoch": 0.4960269335891542,
|
| 3100 |
-
"grad_norm": 1.4615710973739624,
|
| 3101 |
-
"learning_rate": 3.121782445704782e-05,
|
| 3102 |
-
"loss": 1.5846,
|
| 3103 |
-
"step": 13702
|
| 3104 |
-
},
|
| 3105 |
-
{
|
| 3106 |
-
"epoch": 0.4971491664705776,
|
| 3107 |
-
"grad_norm": 1.419823408126831,
|
| 3108 |
-
"learning_rate": 3.11364460675423e-05,
|
| 3109 |
-
"loss": 1.5702,
|
| 3110 |
-
"step": 13733
|
| 3111 |
-
},
|
| 3112 |
-
{
|
| 3113 |
-
"epoch": 0.498271399352001,
|
| 3114 |
-
"grad_norm": 1.429337501525879,
|
| 3115 |
-
"learning_rate": 3.1054998429076934e-05,
|
| 3116 |
-
"loss": 1.5825,
|
| 3117 |
-
"step": 13764
|
| 3118 |
-
},
|
| 3119 |
-
{
|
| 3120 |
-
"epoch": 0.4993936322334244,
|
| 3121 |
-
"grad_norm": 1.3171850442886353,
|
| 3122 |
-
"learning_rate": 3.097348246077728e-05,
|
| 3123 |
-
"loss": 1.5721,
|
| 3124 |
-
"step": 13795
|
| 3125 |
-
},
|
| 3126 |
-
{
|
| 3127 |
-
"epoch": 0.5005158651148479,
|
| 3128 |
-
"grad_norm": 1.487111210823059,
|
| 3129 |
-
"learning_rate": 3.0891899082539924e-05,
|
| 3130 |
-
"loss": 1.5879,
|
| 3131 |
-
"step": 13826
|
| 3132 |
-
},
|
| 3133 |
-
{
|
| 3134 |
-
"epoch": 0.5016380979962712,
|
| 3135 |
-
"grad_norm": 1.4311749935150146,
|
| 3136 |
-
"learning_rate": 3.0810249215022233e-05,
|
| 3137 |
-
"loss": 1.5843,
|
| 3138 |
-
"step": 13857
|
| 3139 |
-
},
|
| 3140 |
-
{
|
| 3141 |
-
"epoch": 0.5027603308776947,
|
| 3142 |
-
"grad_norm": 1.468863844871521,
|
| 3143 |
-
"learning_rate": 3.0728533779631865e-05,
|
| 3144 |
-
"loss": 1.5884,
|
| 3145 |
-
"step": 13888
|
| 3146 |
-
},
|
| 3147 |
-
{
|
| 3148 |
-
"epoch": 0.5038825637591181,
|
| 3149 |
-
"grad_norm": 1.3970764875411987,
|
| 3150 |
-
"learning_rate": 3.064675369851637e-05,
|
| 3151 |
-
"loss": 1.5769,
|
| 3152 |
-
"step": 13919
|
| 3153 |
-
},
|
| 3154 |
-
{
|
| 3155 |
-
"epoch": 0.5050047966405415,
|
| 3156 |
-
"grad_norm": 1.3623278141021729,
|
| 3157 |
-
"learning_rate": 3.056490989455289e-05,
|
| 3158 |
-
"loss": 1.5706,
|
| 3159 |
-
"step": 13950
|
| 3160 |
-
},
|
| 3161 |
-
{
|
| 3162 |
-
"epoch": 0.506127029521965,
|
| 3163 |
-
"grad_norm": 1.3077219724655151,
|
| 3164 |
-
"learning_rate": 3.0483003291337596e-05,
|
| 3165 |
-
"loss": 1.5761,
|
| 3166 |
-
"step": 13981
|
| 3167 |
-
},
|
| 3168 |
-
{
|
| 3169 |
-
"epoch": 0.5072492624033884,
|
| 3170 |
-
"grad_norm": 1.3295941352844238,
|
| 3171 |
-
"learning_rate": 3.040103481317539e-05,
|
| 3172 |
-
"loss": 1.5776,
|
| 3173 |
-
"step": 14012
|
| 3174 |
-
},
|
| 3175 |
-
{
|
| 3176 |
-
"epoch": 0.5083714952848118,
|
| 3177 |
-
"grad_norm": 1.3900631666183472,
|
| 3178 |
-
"learning_rate": 3.03190053850694e-05,
|
| 3179 |
-
"loss": 1.5777,
|
| 3180 |
-
"step": 14043
|
| 3181 |
-
},
|
| 3182 |
-
{
|
| 3183 |
-
"epoch": 0.5094937281662353,
|
| 3184 |
-
"grad_norm": 1.3359615802764893,
|
| 3185 |
-
"learning_rate": 3.0236915932710573e-05,
|
| 3186 |
-
"loss": 1.5569,
|
| 3187 |
-
"step": 14074
|
| 3188 |
-
},
|
| 3189 |
-
{
|
| 3190 |
-
"epoch": 0.5106159610476587,
|
| 3191 |
-
"grad_norm": 1.2790296077728271,
|
| 3192 |
-
"learning_rate": 3.0154767382467232e-05,
|
| 3193 |
-
"loss": 1.5598,
|
| 3194 |
-
"step": 14105
|
| 3195 |
-
},
|
| 3196 |
-
{
|
| 3197 |
-
"epoch": 0.5117381939290822,
|
| 3198 |
-
"grad_norm": 1.5767478942871094,
|
| 3199 |
-
"learning_rate": 3.0072560661374582e-05,
|
| 3200 |
-
"loss": 1.5483,
|
| 3201 |
-
"step": 14136
|
| 3202 |
-
},
|
| 3203 |
-
{
|
| 3204 |
-
"epoch": 0.5128604268105056,
|
| 3205 |
-
"grad_norm": 1.343381404876709,
|
| 3206 |
-
"learning_rate": 2.999029669712431e-05,
|
| 3207 |
-
"loss": 1.5689,
|
| 3208 |
-
"step": 14167
|
| 3209 |
-
},
|
| 3210 |
-
{
|
| 3211 |
-
"epoch": 0.513982659691929,
|
| 3212 |
-
"grad_norm": 1.4147651195526123,
|
| 3213 |
-
"learning_rate": 2.990797641805408e-05,
|
| 3214 |
-
"loss": 1.5643,
|
| 3215 |
-
"step": 14198
|
| 3216 |
-
},
|
| 3217 |
-
{
|
| 3218 |
-
"epoch": 0.5151048925733523,
|
| 3219 |
-
"grad_norm": 1.3360931873321533,
|
| 3220 |
-
"learning_rate": 2.982560075313704e-05,
|
| 3221 |
-
"loss": 1.5689,
|
| 3222 |
-
"step": 14229
|
| 3223 |
-
},
|
| 3224 |
-
{
|
| 3225 |
-
"epoch": 0.5162271254547758,
|
| 3226 |
-
"grad_norm": 1.458016037940979,
|
| 3227 |
-
"learning_rate": 2.9743170631971368e-05,
|
| 3228 |
-
"loss": 1.5633,
|
| 3229 |
-
"step": 14260
|
| 3230 |
-
},
|
| 3231 |
-
{
|
| 3232 |
-
"epoch": 0.5173493583361992,
|
| 3233 |
-
"grad_norm": 1.430955171585083,
|
| 3234 |
-
"learning_rate": 2.9660686984769792e-05,
|
| 3235 |
-
"loss": 1.5559,
|
| 3236 |
-
"step": 14291
|
| 3237 |
-
},
|
| 3238 |
-
{
|
| 3239 |
-
"epoch": 0.5184715912176227,
|
| 3240 |
-
"grad_norm": 1.3806464672088623,
|
| 3241 |
-
"learning_rate": 2.9578150742349047e-05,
|
| 3242 |
-
"loss": 1.577,
|
| 3243 |
-
"step": 14322
|
| 3244 |
-
},
|
| 3245 |
-
{
|
| 3246 |
-
"epoch": 0.5195938240990461,
|
| 3247 |
-
"grad_norm": 1.359813928604126,
|
| 3248 |
-
"learning_rate": 2.949556283611942e-05,
|
| 3249 |
-
"loss": 1.5485,
|
| 3250 |
-
"step": 14353
|
| 3251 |
-
},
|
| 3252 |
-
{
|
| 3253 |
-
"epoch": 0.5207160569804695,
|
| 3254 |
-
"grad_norm": 1.4222601652145386,
|
| 3255 |
-
"learning_rate": 2.9412924198074206e-05,
|
| 3256 |
-
"loss": 1.575,
|
| 3257 |
-
"step": 14384
|
| 3258 |
-
},
|
| 3259 |
-
{
|
| 3260 |
-
"epoch": 0.521838289861893,
|
| 3261 |
-
"grad_norm": 1.3186180591583252,
|
| 3262 |
-
"learning_rate": 2.9330235760779208e-05,
|
| 3263 |
-
"loss": 1.5744,
|
| 3264 |
-
"step": 14415
|
| 3265 |
-
},
|
| 3266 |
-
{
|
| 3267 |
-
"epoch": 0.5229605227433164,
|
| 3268 |
-
"grad_norm": 1.3309999704360962,
|
| 3269 |
-
"learning_rate": 2.9247498457362188e-05,
|
| 3270 |
-
"loss": 1.5664,
|
| 3271 |
-
"step": 14446
|
| 3272 |
-
},
|
| 3273 |
-
{
|
| 3274 |
-
"epoch": 0.5240827556247398,
|
| 3275 |
-
"grad_norm": 1.368514060974121,
|
| 3276 |
-
"learning_rate": 2.9164713221502373e-05,
|
| 3277 |
-
"loss": 1.56,
|
| 3278 |
-
"step": 14477
|
| 3279 |
-
},
|
| 3280 |
-
{
|
| 3281 |
-
"epoch": 0.5252049885061633,
|
| 3282 |
-
"grad_norm": 1.3132268190383911,
|
| 3283 |
-
"learning_rate": 2.9081880987419912e-05,
|
| 3284 |
-
"loss": 1.563,
|
| 3285 |
-
"step": 14508
|
| 3286 |
-
},
|
| 3287 |
-
{
|
| 3288 |
-
"epoch": 0.5263272213875867,
|
| 3289 |
-
"grad_norm": 1.431347131729126,
|
| 3290 |
-
"learning_rate": 2.8999002689865296e-05,
|
| 3291 |
-
"loss": 1.5612,
|
| 3292 |
-
"step": 14539
|
| 3293 |
-
},
|
| 3294 |
-
{
|
| 3295 |
-
"epoch": 0.5274494542690101,
|
| 3296 |
-
"grad_norm": 1.303941249847412,
|
| 3297 |
-
"learning_rate": 2.8916079264108852e-05,
|
| 3298 |
-
"loss": 1.5601,
|
| 3299 |
-
"step": 14570
|
| 3300 |
-
},
|
| 3301 |
-
{
|
| 3302 |
-
"epoch": 0.5285716871504335,
|
| 3303 |
-
"grad_norm": 1.4077236652374268,
|
| 3304 |
-
"learning_rate": 2.883311164593017e-05,
|
| 3305 |
-
"loss": 1.5516,
|
| 3306 |
-
"step": 14601
|
| 3307 |
-
},
|
| 3308 |
-
{
|
| 3309 |
-
"epoch": 0.5296939200318569,
|
| 3310 |
-
"grad_norm": 1.3132708072662354,
|
| 3311 |
-
"learning_rate": 2.875010077160754e-05,
|
| 3312 |
-
"loss": 1.5538,
|
| 3313 |
-
"step": 14632
|
| 3314 |
-
},
|
| 3315 |
-
{
|
| 3316 |
-
"epoch": 0.5308161529132803,
|
| 3317 |
-
"grad_norm": 1.2660679817199707,
|
| 3318 |
-
"learning_rate": 2.866704757790741e-05,
|
| 3319 |
-
"loss": 1.5652,
|
| 3320 |
-
"step": 14663
|
| 3321 |
-
},
|
| 3322 |
-
{
|
| 3323 |
-
"epoch": 0.5319383857947038,
|
| 3324 |
-
"grad_norm": 1.4541290998458862,
|
| 3325 |
-
"learning_rate": 2.858395300207376e-05,
|
| 3326 |
-
"loss": 1.5602,
|
| 3327 |
-
"step": 14694
|
| 3328 |
-
},
|
| 3329 |
-
{
|
| 3330 |
-
"epoch": 0.5330606186761272,
|
| 3331 |
-
"grad_norm": 1.3694487810134888,
|
| 3332 |
-
"learning_rate": 2.8500817981817607e-05,
|
| 3333 |
-
"loss": 1.5483,
|
| 3334 |
-
"step": 14725
|
| 3335 |
-
},
|
| 3336 |
-
{
|
| 3337 |
-
"epoch": 0.5341828515575506,
|
| 3338 |
-
"grad_norm": 1.3493553400039673,
|
| 3339 |
-
"learning_rate": 2.8417643455306336e-05,
|
| 3340 |
-
"loss": 1.5539,
|
| 3341 |
-
"step": 14756
|
| 3342 |
-
},
|
| 3343 |
-
{
|
| 3344 |
-
"epoch": 0.5353050844389741,
|
| 3345 |
-
"grad_norm": 1.4280232191085815,
|
| 3346 |
-
"learning_rate": 2.8334430361153185e-05,
|
| 3347 |
-
"loss": 1.5672,
|
| 3348 |
-
"step": 14787
|
| 3349 |
-
},
|
| 3350 |
-
{
|
| 3351 |
-
"epoch": 0.5364273173203975,
|
| 3352 |
-
"grad_norm": 1.3430079221725464,
|
| 3353 |
-
"learning_rate": 2.8251179638406612e-05,
|
| 3354 |
-
"loss": 1.5474,
|
| 3355 |
-
"step": 14818
|
| 3356 |
-
},
|
| 3357 |
-
{
|
| 3358 |
-
"epoch": 0.5375495502018209,
|
| 3359 |
-
"grad_norm": 1.3380746841430664,
|
| 3360 |
-
"learning_rate": 2.8167892226539704e-05,
|
| 3361 |
-
"loss": 1.5508,
|
| 3362 |
-
"step": 14849
|
| 3363 |
-
},
|
| 3364 |
-
{
|
| 3365 |
-
"epoch": 0.5386717830832444,
|
| 3366 |
-
"grad_norm": 1.3501845598220825,
|
| 3367 |
-
"learning_rate": 2.8084569065439588e-05,
|
| 3368 |
-
"loss": 1.5656,
|
| 3369 |
-
"step": 14880
|
| 3370 |
-
},
|
| 3371 |
-
{
|
| 3372 |
-
"epoch": 0.5397940159646678,
|
| 3373 |
-
"grad_norm": 1.3564043045043945,
|
| 3374 |
-
"learning_rate": 2.8001211095396807e-05,
|
| 3375 |
-
"loss": 1.5726,
|
| 3376 |
-
"step": 14911
|
| 3377 |
-
},
|
| 3378 |
-
{
|
| 3379 |
-
"epoch": 0.5409162488460912,
|
| 3380 |
-
"grad_norm": 1.3949267864227295,
|
| 3381 |
-
"learning_rate": 2.791781925709473e-05,
|
| 3382 |
-
"loss": 1.5635,
|
| 3383 |
-
"step": 14942
|
| 3384 |
-
},
|
| 3385 |
-
{
|
| 3386 |
-
"epoch": 0.5420384817275146,
|
| 3387 |
-
"grad_norm": 1.4317481517791748,
|
| 3388 |
-
"learning_rate": 2.7834394491598908e-05,
|
| 3389 |
-
"loss": 1.5447,
|
| 3390 |
-
"step": 14973
|
| 3391 |
-
},
|
| 3392 |
-
{
|
| 3393 |
-
"epoch": 0.543160714608938,
|
| 3394 |
-
"grad_norm": 1.396610140800476,
|
| 3395 |
-
"learning_rate": 2.7750937740346485e-05,
|
| 3396 |
-
"loss": 1.557,
|
| 3397 |
-
"step": 15004
|
| 3398 |
-
},
|
| 3399 |
-
{
|
| 3400 |
-
"epoch": 0.5442829474903614,
|
| 3401 |
-
"grad_norm": 1.369884967803955,
|
| 3402 |
-
"learning_rate": 2.7667449945135564e-05,
|
| 3403 |
-
"loss": 1.5672,
|
| 3404 |
-
"step": 15035
|
| 3405 |
-
},
|
| 3406 |
-
{
|
| 3407 |
-
"epoch": 0.5454051803717849,
|
| 3408 |
-
"grad_norm": 1.4686237573623657,
|
| 3409 |
-
"learning_rate": 2.7583932048114557e-05,
|
| 3410 |
-
"loss": 1.572,
|
| 3411 |
-
"step": 15066
|
| 3412 |
-
},
|
| 3413 |
-
{
|
| 3414 |
-
"epoch": 0.5465274132532083,
|
| 3415 |
-
"grad_norm": 1.524717926979065,
|
| 3416 |
-
"learning_rate": 2.7500384991771587e-05,
|
| 3417 |
-
"loss": 1.5537,
|
| 3418 |
-
"step": 15097
|
| 3419 |
-
},
|
| 3420 |
-
{
|
| 3421 |
-
"epoch": 0.5476496461346317,
|
| 3422 |
-
"grad_norm": 1.3461147546768188,
|
| 3423 |
-
"learning_rate": 2.7416809718923825e-05,
|
| 3424 |
-
"loss": 1.5321,
|
| 3425 |
-
"step": 15128
|
| 3426 |
-
},
|
| 3427 |
-
{
|
| 3428 |
-
"epoch": 0.5487718790160552,
|
| 3429 |
-
"grad_norm": 1.3704477548599243,
|
| 3430 |
-
"learning_rate": 2.7333207172706864e-05,
|
| 3431 |
-
"loss": 1.5677,
|
| 3432 |
-
"step": 15159
|
| 3433 |
-
},
|
| 3434 |
-
{
|
| 3435 |
-
"epoch": 0.5498941118974786,
|
| 3436 |
-
"grad_norm": 1.3601664304733276,
|
| 3437 |
-
"learning_rate": 2.7249578296564088e-05,
|
| 3438 |
-
"loss": 1.5577,
|
| 3439 |
-
"step": 15190
|
| 3440 |
-
},
|
| 3441 |
-
{
|
| 3442 |
-
"epoch": 0.551016344778902,
|
| 3443 |
-
"grad_norm": 1.4055489301681519,
|
| 3444 |
-
"learning_rate": 2.7165924034235973e-05,
|
| 3445 |
-
"loss": 1.5453,
|
| 3446 |
-
"step": 15221
|
| 3447 |
-
},
|
| 3448 |
-
{
|
| 3449 |
-
"epoch": 0.5521385776603255,
|
| 3450 |
-
"grad_norm": 1.3587946891784668,
|
| 3451 |
-
"learning_rate": 2.708224532974953e-05,
|
| 3452 |
-
"loss": 1.5401,
|
| 3453 |
-
"step": 15252
|
| 3454 |
-
}
|
| 3455 |
-
],
|
| 3456 |
-
"logging_steps": 31,
|
| 3457 |
-
"max_steps": 30517,
|
| 3458 |
-
"num_input_tokens_seen": 0,
|
| 3459 |
-
"num_train_epochs": 2,
|
| 3460 |
-
"save_steps": 3052,
|
| 3461 |
-
"stateful_callbacks": {
|
| 3462 |
-
"TrainerControl": {
|
| 3463 |
-
"args": {
|
| 3464 |
-
"should_epoch_stop": false,
|
| 3465 |
-
"should_evaluate": false,
|
| 3466 |
-
"should_log": false,
|
| 3467 |
-
"should_save": true,
|
| 3468 |
-
"should_training_stop": false
|
| 3469 |
-
},
|
| 3470 |
-
"attributes": {}
|
| 3471 |
-
}
|
| 3472 |
-
},
|
| 3473 |
-
"total_flos": 1.1319725270111355e+19,
|
| 3474 |
-
"train_batch_size": 8,
|
| 3475 |
-
"trial_name": null,
|
| 3476 |
-
"trial_params": null
|
| 3477 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|