Delete trainer_state.json
Browse files- trainer_state.json +0 -2509
trainer_state.json
DELETED
|
@@ -1,2509 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_global_step": 2750,
|
| 3 |
-
"best_metric": 0.8479926448053938,
|
| 4 |
-
"best_model_checkpoint": "dinov2-fonts-with-subfonts-2/checkpoint-2750",
|
| 5 |
-
"epoch": 1.0,
|
| 6 |
-
"eval_steps": 50,
|
| 7 |
-
"global_step": 2752,
|
| 8 |
-
"is_hyper_param_search": false,
|
| 9 |
-
"is_local_process_zero": true,
|
| 10 |
-
"is_world_process_zero": true,
|
| 11 |
-
"log_history": [
|
| 12 |
-
{
|
| 13 |
-
"epoch": 0.003633720930232558,
|
| 14 |
-
"grad_norm": 15.892566680908203,
|
| 15 |
-
"learning_rate": 9.967296511627907e-05,
|
| 16 |
-
"loss": 2.5094,
|
| 17 |
-
"step": 10
|
| 18 |
-
},
|
| 19 |
-
{
|
| 20 |
-
"epoch": 0.007267441860465116,
|
| 21 |
-
"grad_norm": 13.693017959594727,
|
| 22 |
-
"learning_rate": 9.930959302325582e-05,
|
| 23 |
-
"loss": 2.4643,
|
| 24 |
-
"step": 20
|
| 25 |
-
},
|
| 26 |
-
{
|
| 27 |
-
"epoch": 0.010901162790697675,
|
| 28 |
-
"grad_norm": 16.248794555664062,
|
| 29 |
-
"learning_rate": 9.894622093023256e-05,
|
| 30 |
-
"loss": 2.4288,
|
| 31 |
-
"step": 30
|
| 32 |
-
},
|
| 33 |
-
{
|
| 34 |
-
"epoch": 0.014534883720930232,
|
| 35 |
-
"grad_norm": 14.924266815185547,
|
| 36 |
-
"learning_rate": 9.85828488372093e-05,
|
| 37 |
-
"loss": 2.1981,
|
| 38 |
-
"step": 40
|
| 39 |
-
},
|
| 40 |
-
{
|
| 41 |
-
"epoch": 0.018168604651162792,
|
| 42 |
-
"grad_norm": 17.095857620239258,
|
| 43 |
-
"learning_rate": 9.821947674418606e-05,
|
| 44 |
-
"loss": 2.3055,
|
| 45 |
-
"step": 50
|
| 46 |
-
},
|
| 47 |
-
{
|
| 48 |
-
"epoch": 0.018168604651162792,
|
| 49 |
-
"eval_accuracy": 0.28256205945448976,
|
| 50 |
-
"eval_loss": 2.221597671508789,
|
| 51 |
-
"eval_model_preparation_time": 0.0015,
|
| 52 |
-
"eval_runtime": 45.2864,
|
| 53 |
-
"eval_samples_per_second": 72.053,
|
| 54 |
-
"eval_steps_per_second": 2.252,
|
| 55 |
-
"step": 50
|
| 56 |
-
},
|
| 57 |
-
{
|
| 58 |
-
"epoch": 0.02180232558139535,
|
| 59 |
-
"grad_norm": 15.624826431274414,
|
| 60 |
-
"learning_rate": 9.78561046511628e-05,
|
| 61 |
-
"loss": 2.2321,
|
| 62 |
-
"step": 60
|
| 63 |
-
},
|
| 64 |
-
{
|
| 65 |
-
"epoch": 0.025436046511627907,
|
| 66 |
-
"grad_norm": 15.980948448181152,
|
| 67 |
-
"learning_rate": 9.749273255813955e-05,
|
| 68 |
-
"loss": 2.1783,
|
| 69 |
-
"step": 70
|
| 70 |
-
},
|
| 71 |
-
{
|
| 72 |
-
"epoch": 0.029069767441860465,
|
| 73 |
-
"grad_norm": 16.875125885009766,
|
| 74 |
-
"learning_rate": 9.712936046511628e-05,
|
| 75 |
-
"loss": 2.1456,
|
| 76 |
-
"step": 80
|
| 77 |
-
},
|
| 78 |
-
{
|
| 79 |
-
"epoch": 0.032703488372093026,
|
| 80 |
-
"grad_norm": 14.524847030639648,
|
| 81 |
-
"learning_rate": 9.676598837209303e-05,
|
| 82 |
-
"loss": 2.0414,
|
| 83 |
-
"step": 90
|
| 84 |
-
},
|
| 85 |
-
{
|
| 86 |
-
"epoch": 0.036337209302325583,
|
| 87 |
-
"grad_norm": 19.023685455322266,
|
| 88 |
-
"learning_rate": 9.640261627906977e-05,
|
| 89 |
-
"loss": 2.0327,
|
| 90 |
-
"step": 100
|
| 91 |
-
},
|
| 92 |
-
{
|
| 93 |
-
"epoch": 0.036337209302325583,
|
| 94 |
-
"eval_accuracy": 0.3444682807232608,
|
| 95 |
-
"eval_loss": 2.0124428272247314,
|
| 96 |
-
"eval_model_preparation_time": 0.0015,
|
| 97 |
-
"eval_runtime": 55.6946,
|
| 98 |
-
"eval_samples_per_second": 58.587,
|
| 99 |
-
"eval_steps_per_second": 1.831,
|
| 100 |
-
"step": 100
|
| 101 |
-
},
|
| 102 |
-
{
|
| 103 |
-
"epoch": 0.03997093023255814,
|
| 104 |
-
"grad_norm": 18.07843589782715,
|
| 105 |
-
"learning_rate": 9.603924418604651e-05,
|
| 106 |
-
"loss": 1.9096,
|
| 107 |
-
"step": 110
|
| 108 |
-
},
|
| 109 |
-
{
|
| 110 |
-
"epoch": 0.0436046511627907,
|
| 111 |
-
"grad_norm": 15.953253746032715,
|
| 112 |
-
"learning_rate": 9.567587209302325e-05,
|
| 113 |
-
"loss": 1.9289,
|
| 114 |
-
"step": 120
|
| 115 |
-
},
|
| 116 |
-
{
|
| 117 |
-
"epoch": 0.047238372093023256,
|
| 118 |
-
"grad_norm": 16.393022537231445,
|
| 119 |
-
"learning_rate": 9.53125e-05,
|
| 120 |
-
"loss": 1.898,
|
| 121 |
-
"step": 130
|
| 122 |
-
},
|
| 123 |
-
{
|
| 124 |
-
"epoch": 0.050872093023255814,
|
| 125 |
-
"grad_norm": 15.503422737121582,
|
| 126 |
-
"learning_rate": 9.494912790697676e-05,
|
| 127 |
-
"loss": 1.9764,
|
| 128 |
-
"step": 140
|
| 129 |
-
},
|
| 130 |
-
{
|
| 131 |
-
"epoch": 0.05450581395348837,
|
| 132 |
-
"grad_norm": 17.98733139038086,
|
| 133 |
-
"learning_rate": 9.458575581395349e-05,
|
| 134 |
-
"loss": 1.8097,
|
| 135 |
-
"step": 150
|
| 136 |
-
},
|
| 137 |
-
{
|
| 138 |
-
"epoch": 0.05450581395348837,
|
| 139 |
-
"eval_accuracy": 0.3781795893349678,
|
| 140 |
-
"eval_loss": 1.8244749307632446,
|
| 141 |
-
"eval_model_preparation_time": 0.0015,
|
| 142 |
-
"eval_runtime": 50.7499,
|
| 143 |
-
"eval_samples_per_second": 64.296,
|
| 144 |
-
"eval_steps_per_second": 2.01,
|
| 145 |
-
"step": 150
|
| 146 |
-
},
|
| 147 |
-
{
|
| 148 |
-
"epoch": 0.05813953488372093,
|
| 149 |
-
"grad_norm": 22.832233428955078,
|
| 150 |
-
"learning_rate": 9.422238372093024e-05,
|
| 151 |
-
"loss": 1.8411,
|
| 152 |
-
"step": 160
|
| 153 |
-
},
|
| 154 |
-
{
|
| 155 |
-
"epoch": 0.06177325581395349,
|
| 156 |
-
"grad_norm": 17.715545654296875,
|
| 157 |
-
"learning_rate": 9.385901162790698e-05,
|
| 158 |
-
"loss": 1.7486,
|
| 159 |
-
"step": 170
|
| 160 |
-
},
|
| 161 |
-
{
|
| 162 |
-
"epoch": 0.06540697674418605,
|
| 163 |
-
"grad_norm": 18.01825714111328,
|
| 164 |
-
"learning_rate": 9.349563953488372e-05,
|
| 165 |
-
"loss": 1.7325,
|
| 166 |
-
"step": 180
|
| 167 |
-
},
|
| 168 |
-
{
|
| 169 |
-
"epoch": 0.0690406976744186,
|
| 170 |
-
"grad_norm": 17.555883407592773,
|
| 171 |
-
"learning_rate": 9.313226744186046e-05,
|
| 172 |
-
"loss": 1.772,
|
| 173 |
-
"step": 190
|
| 174 |
-
},
|
| 175 |
-
{
|
| 176 |
-
"epoch": 0.07267441860465117,
|
| 177 |
-
"grad_norm": 14.410489082336426,
|
| 178 |
-
"learning_rate": 9.276889534883722e-05,
|
| 179 |
-
"loss": 1.7379,
|
| 180 |
-
"step": 200
|
| 181 |
-
},
|
| 182 |
-
{
|
| 183 |
-
"epoch": 0.07267441860465117,
|
| 184 |
-
"eval_accuracy": 0.4112779650628256,
|
| 185 |
-
"eval_loss": 1.7361937761306763,
|
| 186 |
-
"eval_model_preparation_time": 0.0015,
|
| 187 |
-
"eval_runtime": 47.8089,
|
| 188 |
-
"eval_samples_per_second": 68.251,
|
| 189 |
-
"eval_steps_per_second": 2.133,
|
| 190 |
-
"step": 200
|
| 191 |
-
},
|
| 192 |
-
{
|
| 193 |
-
"epoch": 0.07630813953488372,
|
| 194 |
-
"grad_norm": 17.80829429626465,
|
| 195 |
-
"learning_rate": 9.240552325581396e-05,
|
| 196 |
-
"loss": 1.7533,
|
| 197 |
-
"step": 210
|
| 198 |
-
},
|
| 199 |
-
{
|
| 200 |
-
"epoch": 0.07994186046511628,
|
| 201 |
-
"grad_norm": 19.89047622680664,
|
| 202 |
-
"learning_rate": 9.20421511627907e-05,
|
| 203 |
-
"loss": 1.7556,
|
| 204 |
-
"step": 220
|
| 205 |
-
},
|
| 206 |
-
{
|
| 207 |
-
"epoch": 0.08357558139534883,
|
| 208 |
-
"grad_norm": 17.062580108642578,
|
| 209 |
-
"learning_rate": 9.167877906976745e-05,
|
| 210 |
-
"loss": 1.6221,
|
| 211 |
-
"step": 230
|
| 212 |
-
},
|
| 213 |
-
{
|
| 214 |
-
"epoch": 0.0872093023255814,
|
| 215 |
-
"grad_norm": 20.477750778198242,
|
| 216 |
-
"learning_rate": 9.131540697674419e-05,
|
| 217 |
-
"loss": 1.6176,
|
| 218 |
-
"step": 240
|
| 219 |
-
},
|
| 220 |
-
{
|
| 221 |
-
"epoch": 0.09084302325581395,
|
| 222 |
-
"grad_norm": 19.113245010375977,
|
| 223 |
-
"learning_rate": 9.095203488372093e-05,
|
| 224 |
-
"loss": 1.7862,
|
| 225 |
-
"step": 250
|
| 226 |
-
},
|
| 227 |
-
{
|
| 228 |
-
"epoch": 0.09084302325581395,
|
| 229 |
-
"eval_accuracy": 0.4511186025130248,
|
| 230 |
-
"eval_loss": 1.5864135026931763,
|
| 231 |
-
"eval_model_preparation_time": 0.0015,
|
| 232 |
-
"eval_runtime": 47.5524,
|
| 233 |
-
"eval_samples_per_second": 68.619,
|
| 234 |
-
"eval_steps_per_second": 2.145,
|
| 235 |
-
"step": 250
|
| 236 |
-
},
|
| 237 |
-
{
|
| 238 |
-
"epoch": 0.09447674418604651,
|
| 239 |
-
"grad_norm": 17.91750144958496,
|
| 240 |
-
"learning_rate": 9.058866279069767e-05,
|
| 241 |
-
"loss": 1.5788,
|
| 242 |
-
"step": 260
|
| 243 |
-
},
|
| 244 |
-
{
|
| 245 |
-
"epoch": 0.09811046511627906,
|
| 246 |
-
"grad_norm": 19.93201446533203,
|
| 247 |
-
"learning_rate": 9.022529069767443e-05,
|
| 248 |
-
"loss": 1.6572,
|
| 249 |
-
"step": 270
|
| 250 |
-
},
|
| 251 |
-
{
|
| 252 |
-
"epoch": 0.10174418604651163,
|
| 253 |
-
"grad_norm": 14.712456703186035,
|
| 254 |
-
"learning_rate": 8.986191860465117e-05,
|
| 255 |
-
"loss": 1.6514,
|
| 256 |
-
"step": 280
|
| 257 |
-
},
|
| 258 |
-
{
|
| 259 |
-
"epoch": 0.10537790697674419,
|
| 260 |
-
"grad_norm": 17.98506736755371,
|
| 261 |
-
"learning_rate": 8.94985465116279e-05,
|
| 262 |
-
"loss": 1.555,
|
| 263 |
-
"step": 290
|
| 264 |
-
},
|
| 265 |
-
{
|
| 266 |
-
"epoch": 0.10901162790697674,
|
| 267 |
-
"grad_norm": 18.016740798950195,
|
| 268 |
-
"learning_rate": 8.913517441860465e-05,
|
| 269 |
-
"loss": 1.4337,
|
| 270 |
-
"step": 300
|
| 271 |
-
},
|
| 272 |
-
{
|
| 273 |
-
"epoch": 0.10901162790697674,
|
| 274 |
-
"eval_accuracy": 0.4566349984676678,
|
| 275 |
-
"eval_loss": 1.5329961776733398,
|
| 276 |
-
"eval_model_preparation_time": 0.0015,
|
| 277 |
-
"eval_runtime": 49.8886,
|
| 278 |
-
"eval_samples_per_second": 65.406,
|
| 279 |
-
"eval_steps_per_second": 2.045,
|
| 280 |
-
"step": 300
|
| 281 |
-
},
|
| 282 |
-
{
|
| 283 |
-
"epoch": 0.11264534883720931,
|
| 284 |
-
"grad_norm": 18.44303321838379,
|
| 285 |
-
"learning_rate": 8.87718023255814e-05,
|
| 286 |
-
"loss": 1.6438,
|
| 287 |
-
"step": 310
|
| 288 |
-
},
|
| 289 |
-
{
|
| 290 |
-
"epoch": 0.11627906976744186,
|
| 291 |
-
"grad_norm": 19.64215660095215,
|
| 292 |
-
"learning_rate": 8.840843023255815e-05,
|
| 293 |
-
"loss": 1.4625,
|
| 294 |
-
"step": 320
|
| 295 |
-
},
|
| 296 |
-
{
|
| 297 |
-
"epoch": 0.11991279069767442,
|
| 298 |
-
"grad_norm": 23.59469985961914,
|
| 299 |
-
"learning_rate": 8.804505813953488e-05,
|
| 300 |
-
"loss": 1.5685,
|
| 301 |
-
"step": 330
|
| 302 |
-
},
|
| 303 |
-
{
|
| 304 |
-
"epoch": 0.12354651162790697,
|
| 305 |
-
"grad_norm": 19.073352813720703,
|
| 306 |
-
"learning_rate": 8.768168604651164e-05,
|
| 307 |
-
"loss": 1.4693,
|
| 308 |
-
"step": 340
|
| 309 |
-
},
|
| 310 |
-
{
|
| 311 |
-
"epoch": 0.12718023255813954,
|
| 312 |
-
"grad_norm": 16.183441162109375,
|
| 313 |
-
"learning_rate": 8.731831395348838e-05,
|
| 314 |
-
"loss": 1.4731,
|
| 315 |
-
"step": 350
|
| 316 |
-
},
|
| 317 |
-
{
|
| 318 |
-
"epoch": 0.12718023255813954,
|
| 319 |
-
"eval_accuracy": 0.5099601593625498,
|
| 320 |
-
"eval_loss": 1.4183763265609741,
|
| 321 |
-
"eval_model_preparation_time": 0.0015,
|
| 322 |
-
"eval_runtime": 47.7302,
|
| 323 |
-
"eval_samples_per_second": 68.363,
|
| 324 |
-
"eval_steps_per_second": 2.137,
|
| 325 |
-
"step": 350
|
| 326 |
-
},
|
| 327 |
-
{
|
| 328 |
-
"epoch": 0.1308139534883721,
|
| 329 |
-
"grad_norm": 22.20075035095215,
|
| 330 |
-
"learning_rate": 8.695494186046512e-05,
|
| 331 |
-
"loss": 1.4671,
|
| 332 |
-
"step": 360
|
| 333 |
-
},
|
| 334 |
-
{
|
| 335 |
-
"epoch": 0.13444767441860464,
|
| 336 |
-
"grad_norm": 19.052248001098633,
|
| 337 |
-
"learning_rate": 8.659156976744186e-05,
|
| 338 |
-
"loss": 1.4519,
|
| 339 |
-
"step": 370
|
| 340 |
-
},
|
| 341 |
-
{
|
| 342 |
-
"epoch": 0.1380813953488372,
|
| 343 |
-
"grad_norm": 17.498851776123047,
|
| 344 |
-
"learning_rate": 8.622819767441861e-05,
|
| 345 |
-
"loss": 1.4895,
|
| 346 |
-
"step": 380
|
| 347 |
-
},
|
| 348 |
-
{
|
| 349 |
-
"epoch": 0.14171511627906977,
|
| 350 |
-
"grad_norm": 17.81024932861328,
|
| 351 |
-
"learning_rate": 8.586482558139536e-05,
|
| 352 |
-
"loss": 1.5058,
|
| 353 |
-
"step": 390
|
| 354 |
-
},
|
| 355 |
-
{
|
| 356 |
-
"epoch": 0.14534883720930233,
|
| 357 |
-
"grad_norm": 22.155494689941406,
|
| 358 |
-
"learning_rate": 8.550145348837209e-05,
|
| 359 |
-
"loss": 1.4192,
|
| 360 |
-
"step": 400
|
| 361 |
-
},
|
| 362 |
-
{
|
| 363 |
-
"epoch": 0.14534883720930233,
|
| 364 |
-
"eval_accuracy": 0.5163959546429666,
|
| 365 |
-
"eval_loss": 1.3699551820755005,
|
| 366 |
-
"eval_model_preparation_time": 0.0015,
|
| 367 |
-
"eval_runtime": 47.8531,
|
| 368 |
-
"eval_samples_per_second": 68.188,
|
| 369 |
-
"eval_steps_per_second": 2.132,
|
| 370 |
-
"step": 400
|
| 371 |
-
},
|
| 372 |
-
{
|
| 373 |
-
"epoch": 0.14898255813953487,
|
| 374 |
-
"grad_norm": 17.518573760986328,
|
| 375 |
-
"learning_rate": 8.513808139534885e-05,
|
| 376 |
-
"loss": 1.3937,
|
| 377 |
-
"step": 410
|
| 378 |
-
},
|
| 379 |
-
{
|
| 380 |
-
"epoch": 0.15261627906976744,
|
| 381 |
-
"grad_norm": 18.192092895507812,
|
| 382 |
-
"learning_rate": 8.477470930232559e-05,
|
| 383 |
-
"loss": 1.3298,
|
| 384 |
-
"step": 420
|
| 385 |
-
},
|
| 386 |
-
{
|
| 387 |
-
"epoch": 0.15625,
|
| 388 |
-
"grad_norm": 19.992328643798828,
|
| 389 |
-
"learning_rate": 8.441133720930233e-05,
|
| 390 |
-
"loss": 1.3802,
|
| 391 |
-
"step": 430
|
| 392 |
-
},
|
| 393 |
-
{
|
| 394 |
-
"epoch": 0.15988372093023256,
|
| 395 |
-
"grad_norm": 27.304393768310547,
|
| 396 |
-
"learning_rate": 8.404796511627907e-05,
|
| 397 |
-
"loss": 1.3234,
|
| 398 |
-
"step": 440
|
| 399 |
-
},
|
| 400 |
-
{
|
| 401 |
-
"epoch": 0.16351744186046513,
|
| 402 |
-
"grad_norm": 24.619159698486328,
|
| 403 |
-
"learning_rate": 8.368459302325582e-05,
|
| 404 |
-
"loss": 1.415,
|
| 405 |
-
"step": 450
|
| 406 |
-
},
|
| 407 |
-
{
|
| 408 |
-
"epoch": 0.16351744186046513,
|
| 409 |
-
"eval_accuracy": 0.5262028807845541,
|
| 410 |
-
"eval_loss": 1.3008671998977661,
|
| 411 |
-
"eval_model_preparation_time": 0.0015,
|
| 412 |
-
"eval_runtime": 48.1216,
|
| 413 |
-
"eval_samples_per_second": 67.807,
|
| 414 |
-
"eval_steps_per_second": 2.12,
|
| 415 |
-
"step": 450
|
| 416 |
-
},
|
| 417 |
-
{
|
| 418 |
-
"epoch": 0.16715116279069767,
|
| 419 |
-
"grad_norm": 19.95876121520996,
|
| 420 |
-
"learning_rate": 8.332122093023256e-05,
|
| 421 |
-
"loss": 1.3458,
|
| 422 |
-
"step": 460
|
| 423 |
-
},
|
| 424 |
-
{
|
| 425 |
-
"epoch": 0.17078488372093023,
|
| 426 |
-
"grad_norm": 18.42659568786621,
|
| 427 |
-
"learning_rate": 8.29578488372093e-05,
|
| 428 |
-
"loss": 1.4143,
|
| 429 |
-
"step": 470
|
| 430 |
-
},
|
| 431 |
-
{
|
| 432 |
-
"epoch": 0.1744186046511628,
|
| 433 |
-
"grad_norm": 19.090171813964844,
|
| 434 |
-
"learning_rate": 8.259447674418606e-05,
|
| 435 |
-
"loss": 1.3685,
|
| 436 |
-
"step": 480
|
| 437 |
-
},
|
| 438 |
-
{
|
| 439 |
-
"epoch": 0.17805232558139536,
|
| 440 |
-
"grad_norm": 23.138212203979492,
|
| 441 |
-
"learning_rate": 8.22311046511628e-05,
|
| 442 |
-
"loss": 1.3492,
|
| 443 |
-
"step": 490
|
| 444 |
-
},
|
| 445 |
-
{
|
| 446 |
-
"epoch": 0.1816860465116279,
|
| 447 |
-
"grad_norm": 24.334434509277344,
|
| 448 |
-
"learning_rate": 8.186773255813954e-05,
|
| 449 |
-
"loss": 1.4102,
|
| 450 |
-
"step": 500
|
| 451 |
-
},
|
| 452 |
-
{
|
| 453 |
-
"epoch": 0.1816860465116279,
|
| 454 |
-
"eval_accuracy": 0.5455102666258045,
|
| 455 |
-
"eval_loss": 1.2436403036117554,
|
| 456 |
-
"eval_model_preparation_time": 0.0015,
|
| 457 |
-
"eval_runtime": 48.5657,
|
| 458 |
-
"eval_samples_per_second": 67.187,
|
| 459 |
-
"eval_steps_per_second": 2.1,
|
| 460 |
-
"step": 500
|
| 461 |
-
},
|
| 462 |
-
{
|
| 463 |
-
"epoch": 0.18531976744186046,
|
| 464 |
-
"grad_norm": 20.45575714111328,
|
| 465 |
-
"learning_rate": 8.150436046511628e-05,
|
| 466 |
-
"loss": 1.2621,
|
| 467 |
-
"step": 510
|
| 468 |
-
},
|
| 469 |
-
{
|
| 470 |
-
"epoch": 0.18895348837209303,
|
| 471 |
-
"grad_norm": 15.790328979492188,
|
| 472 |
-
"learning_rate": 8.114098837209303e-05,
|
| 473 |
-
"loss": 1.2724,
|
| 474 |
-
"step": 520
|
| 475 |
-
},
|
| 476 |
-
{
|
| 477 |
-
"epoch": 0.1925872093023256,
|
| 478 |
-
"grad_norm": 21.53169059753418,
|
| 479 |
-
"learning_rate": 8.077761627906977e-05,
|
| 480 |
-
"loss": 1.3039,
|
| 481 |
-
"step": 530
|
| 482 |
-
},
|
| 483 |
-
{
|
| 484 |
-
"epoch": 0.19622093023255813,
|
| 485 |
-
"grad_norm": 17.059200286865234,
|
| 486 |
-
"learning_rate": 8.041424418604651e-05,
|
| 487 |
-
"loss": 1.2784,
|
| 488 |
-
"step": 540
|
| 489 |
-
},
|
| 490 |
-
{
|
| 491 |
-
"epoch": 0.1998546511627907,
|
| 492 |
-
"grad_norm": 19.423311233520508,
|
| 493 |
-
"learning_rate": 8.005087209302325e-05,
|
| 494 |
-
"loss": 1.2175,
|
| 495 |
-
"step": 550
|
| 496 |
-
},
|
| 497 |
-
{
|
| 498 |
-
"epoch": 0.1998546511627907,
|
| 499 |
-
"eval_accuracy": 0.5675758504443763,
|
| 500 |
-
"eval_loss": 1.1887367963790894,
|
| 501 |
-
"eval_model_preparation_time": 0.0015,
|
| 502 |
-
"eval_runtime": 48.5535,
|
| 503 |
-
"eval_samples_per_second": 67.204,
|
| 504 |
-
"eval_steps_per_second": 2.101,
|
| 505 |
-
"step": 550
|
| 506 |
-
},
|
| 507 |
-
{
|
| 508 |
-
"epoch": 0.20348837209302326,
|
| 509 |
-
"grad_norm": 21.524168014526367,
|
| 510 |
-
"learning_rate": 7.96875e-05,
|
| 511 |
-
"loss": 1.1391,
|
| 512 |
-
"step": 560
|
| 513 |
-
},
|
| 514 |
-
{
|
| 515 |
-
"epoch": 0.20712209302325582,
|
| 516 |
-
"grad_norm": 15.95803165435791,
|
| 517 |
-
"learning_rate": 7.932412790697675e-05,
|
| 518 |
-
"loss": 1.1714,
|
| 519 |
-
"step": 570
|
| 520 |
-
},
|
| 521 |
-
{
|
| 522 |
-
"epoch": 0.21075581395348839,
|
| 523 |
-
"grad_norm": 17.44819450378418,
|
| 524 |
-
"learning_rate": 7.896075581395349e-05,
|
| 525 |
-
"loss": 1.2085,
|
| 526 |
-
"step": 580
|
| 527 |
-
},
|
| 528 |
-
{
|
| 529 |
-
"epoch": 0.21438953488372092,
|
| 530 |
-
"grad_norm": 20.14234161376953,
|
| 531 |
-
"learning_rate": 7.859738372093024e-05,
|
| 532 |
-
"loss": 1.1547,
|
| 533 |
-
"step": 590
|
| 534 |
-
},
|
| 535 |
-
{
|
| 536 |
-
"epoch": 0.2180232558139535,
|
| 537 |
-
"grad_norm": 22.286245346069336,
|
| 538 |
-
"learning_rate": 7.823401162790698e-05,
|
| 539 |
-
"loss": 1.1583,
|
| 540 |
-
"step": 600
|
| 541 |
-
},
|
| 542 |
-
{
|
| 543 |
-
"epoch": 0.2180232558139535,
|
| 544 |
-
"eval_accuracy": 0.5770763101440393,
|
| 545 |
-
"eval_loss": 1.1267926692962646,
|
| 546 |
-
"eval_model_preparation_time": 0.0015,
|
| 547 |
-
"eval_runtime": 47.6542,
|
| 548 |
-
"eval_samples_per_second": 68.472,
|
| 549 |
-
"eval_steps_per_second": 2.14,
|
| 550 |
-
"step": 600
|
| 551 |
-
},
|
| 552 |
-
{
|
| 553 |
-
"epoch": 0.22165697674418605,
|
| 554 |
-
"grad_norm": 24.456897735595703,
|
| 555 |
-
"learning_rate": 7.787063953488372e-05,
|
| 556 |
-
"loss": 1.1663,
|
| 557 |
-
"step": 610
|
| 558 |
-
},
|
| 559 |
-
{
|
| 560 |
-
"epoch": 0.22529069767441862,
|
| 561 |
-
"grad_norm": 19.741336822509766,
|
| 562 |
-
"learning_rate": 7.750726744186046e-05,
|
| 563 |
-
"loss": 1.1761,
|
| 564 |
-
"step": 620
|
| 565 |
-
},
|
| 566 |
-
{
|
| 567 |
-
"epoch": 0.22892441860465115,
|
| 568 |
-
"grad_norm": 19.847604751586914,
|
| 569 |
-
"learning_rate": 7.714389534883722e-05,
|
| 570 |
-
"loss": 1.1423,
|
| 571 |
-
"step": 630
|
| 572 |
-
},
|
| 573 |
-
{
|
| 574 |
-
"epoch": 0.23255813953488372,
|
| 575 |
-
"grad_norm": 16.832901000976562,
|
| 576 |
-
"learning_rate": 7.678052325581396e-05,
|
| 577 |
-
"loss": 1.0611,
|
| 578 |
-
"step": 640
|
| 579 |
-
},
|
| 580 |
-
{
|
| 581 |
-
"epoch": 0.23619186046511628,
|
| 582 |
-
"grad_norm": 19.98552703857422,
|
| 583 |
-
"learning_rate": 7.64171511627907e-05,
|
| 584 |
-
"loss": 1.1858,
|
| 585 |
-
"step": 650
|
| 586 |
-
},
|
| 587 |
-
{
|
| 588 |
-
"epoch": 0.23619186046511628,
|
| 589 |
-
"eval_accuracy": 0.6196751455715599,
|
| 590 |
-
"eval_loss": 1.0860530138015747,
|
| 591 |
-
"eval_model_preparation_time": 0.0015,
|
| 592 |
-
"eval_runtime": 50.2713,
|
| 593 |
-
"eval_samples_per_second": 64.908,
|
| 594 |
-
"eval_steps_per_second": 2.029,
|
| 595 |
-
"step": 650
|
| 596 |
-
},
|
| 597 |
-
{
|
| 598 |
-
"epoch": 0.23982558139534885,
|
| 599 |
-
"grad_norm": 22.90323257446289,
|
| 600 |
-
"learning_rate": 7.605377906976745e-05,
|
| 601 |
-
"loss": 1.2555,
|
| 602 |
-
"step": 660
|
| 603 |
-
},
|
| 604 |
-
{
|
| 605 |
-
"epoch": 0.24345930232558138,
|
| 606 |
-
"grad_norm": 18.252866744995117,
|
| 607 |
-
"learning_rate": 7.569040697674419e-05,
|
| 608 |
-
"loss": 1.1472,
|
| 609 |
-
"step": 670
|
| 610 |
-
},
|
| 611 |
-
{
|
| 612 |
-
"epoch": 0.24709302325581395,
|
| 613 |
-
"grad_norm": 29.458932876586914,
|
| 614 |
-
"learning_rate": 7.532703488372093e-05,
|
| 615 |
-
"loss": 1.2043,
|
| 616 |
-
"step": 680
|
| 617 |
-
},
|
| 618 |
-
{
|
| 619 |
-
"epoch": 0.2507267441860465,
|
| 620 |
-
"grad_norm": 26.31637954711914,
|
| 621 |
-
"learning_rate": 7.496366279069767e-05,
|
| 622 |
-
"loss": 1.1212,
|
| 623 |
-
"step": 690
|
| 624 |
-
},
|
| 625 |
-
{
|
| 626 |
-
"epoch": 0.2543604651162791,
|
| 627 |
-
"grad_norm": 19.821483612060547,
|
| 628 |
-
"learning_rate": 7.460029069767443e-05,
|
| 629 |
-
"loss": 1.0821,
|
| 630 |
-
"step": 700
|
| 631 |
-
},
|
| 632 |
-
{
|
| 633 |
-
"epoch": 0.2543604651162791,
|
| 634 |
-
"eval_accuracy": 0.622739809990806,
|
| 635 |
-
"eval_loss": 1.0653626918792725,
|
| 636 |
-
"eval_model_preparation_time": 0.0015,
|
| 637 |
-
"eval_runtime": 47.867,
|
| 638 |
-
"eval_samples_per_second": 68.168,
|
| 639 |
-
"eval_steps_per_second": 2.131,
|
| 640 |
-
"step": 700
|
| 641 |
-
},
|
| 642 |
-
{
|
| 643 |
-
"epoch": 0.25799418604651164,
|
| 644 |
-
"grad_norm": 20.264490127563477,
|
| 645 |
-
"learning_rate": 7.423691860465117e-05,
|
| 646 |
-
"loss": 1.0817,
|
| 647 |
-
"step": 710
|
| 648 |
-
},
|
| 649 |
-
{
|
| 650 |
-
"epoch": 0.2616279069767442,
|
| 651 |
-
"grad_norm": 16.901201248168945,
|
| 652 |
-
"learning_rate": 7.38735465116279e-05,
|
| 653 |
-
"loss": 1.0836,
|
| 654 |
-
"step": 720
|
| 655 |
-
},
|
| 656 |
-
{
|
| 657 |
-
"epoch": 0.26526162790697677,
|
| 658 |
-
"grad_norm": 21.42996597290039,
|
| 659 |
-
"learning_rate": 7.351017441860465e-05,
|
| 660 |
-
"loss": 1.0995,
|
| 661 |
-
"step": 730
|
| 662 |
-
},
|
| 663 |
-
{
|
| 664 |
-
"epoch": 0.2688953488372093,
|
| 665 |
-
"grad_norm": 27.091205596923828,
|
| 666 |
-
"learning_rate": 7.31468023255814e-05,
|
| 667 |
-
"loss": 1.2028,
|
| 668 |
-
"step": 740
|
| 669 |
-
},
|
| 670 |
-
{
|
| 671 |
-
"epoch": 0.27252906976744184,
|
| 672 |
-
"grad_norm": 26.723642349243164,
|
| 673 |
-
"learning_rate": 7.278343023255814e-05,
|
| 674 |
-
"loss": 1.1347,
|
| 675 |
-
"step": 750
|
| 676 |
-
},
|
| 677 |
-
{
|
| 678 |
-
"epoch": 0.27252906976744184,
|
| 679 |
-
"eval_accuracy": 0.6356114005516396,
|
| 680 |
-
"eval_loss": 1.023024082183838,
|
| 681 |
-
"eval_model_preparation_time": 0.0015,
|
| 682 |
-
"eval_runtime": 48.1088,
|
| 683 |
-
"eval_samples_per_second": 67.825,
|
| 684 |
-
"eval_steps_per_second": 2.12,
|
| 685 |
-
"step": 750
|
| 686 |
-
},
|
| 687 |
-
{
|
| 688 |
-
"epoch": 0.2761627906976744,
|
| 689 |
-
"grad_norm": 15.63192367553711,
|
| 690 |
-
"learning_rate": 7.242005813953488e-05,
|
| 691 |
-
"loss": 1.1222,
|
| 692 |
-
"step": 760
|
| 693 |
-
},
|
| 694 |
-
{
|
| 695 |
-
"epoch": 0.279796511627907,
|
| 696 |
-
"grad_norm": 16.611923217773438,
|
| 697 |
-
"learning_rate": 7.205668604651164e-05,
|
| 698 |
-
"loss": 1.1061,
|
| 699 |
-
"step": 770
|
| 700 |
-
},
|
| 701 |
-
{
|
| 702 |
-
"epoch": 0.28343023255813954,
|
| 703 |
-
"grad_norm": 21.829530715942383,
|
| 704 |
-
"learning_rate": 7.169331395348838e-05,
|
| 705 |
-
"loss": 1.0047,
|
| 706 |
-
"step": 780
|
| 707 |
-
},
|
| 708 |
-
{
|
| 709 |
-
"epoch": 0.2870639534883721,
|
| 710 |
-
"grad_norm": 22.85479736328125,
|
| 711 |
-
"learning_rate": 7.132994186046512e-05,
|
| 712 |
-
"loss": 1.1656,
|
| 713 |
-
"step": 790
|
| 714 |
-
},
|
| 715 |
-
{
|
| 716 |
-
"epoch": 0.29069767441860467,
|
| 717 |
-
"grad_norm": 24.8774356842041,
|
| 718 |
-
"learning_rate": 7.096656976744186e-05,
|
| 719 |
-
"loss": 1.0365,
|
| 720 |
-
"step": 800
|
| 721 |
-
},
|
| 722 |
-
{
|
| 723 |
-
"epoch": 0.29069767441860467,
|
| 724 |
-
"eval_accuracy": 0.6472571253447748,
|
| 725 |
-
"eval_loss": 0.9910984635353088,
|
| 726 |
-
"eval_model_preparation_time": 0.0015,
|
| 727 |
-
"eval_runtime": 49.0197,
|
| 728 |
-
"eval_samples_per_second": 66.565,
|
| 729 |
-
"eval_steps_per_second": 2.081,
|
| 730 |
-
"step": 800
|
| 731 |
-
},
|
| 732 |
-
{
|
| 733 |
-
"epoch": 0.29433139534883723,
|
| 734 |
-
"grad_norm": 24.75929069519043,
|
| 735 |
-
"learning_rate": 7.060319767441861e-05,
|
| 736 |
-
"loss": 1.0438,
|
| 737 |
-
"step": 810
|
| 738 |
-
},
|
| 739 |
-
{
|
| 740 |
-
"epoch": 0.29796511627906974,
|
| 741 |
-
"grad_norm": 28.923444747924805,
|
| 742 |
-
"learning_rate": 7.023982558139535e-05,
|
| 743 |
-
"loss": 1.0488,
|
| 744 |
-
"step": 820
|
| 745 |
-
},
|
| 746 |
-
{
|
| 747 |
-
"epoch": 0.3015988372093023,
|
| 748 |
-
"grad_norm": 18.869667053222656,
|
| 749 |
-
"learning_rate": 6.987645348837209e-05,
|
| 750 |
-
"loss": 1.0892,
|
| 751 |
-
"step": 830
|
| 752 |
-
},
|
| 753 |
-
{
|
| 754 |
-
"epoch": 0.30523255813953487,
|
| 755 |
-
"grad_norm": 18.0045108795166,
|
| 756 |
-
"learning_rate": 6.951308139534885e-05,
|
| 757 |
-
"loss": 1.0249,
|
| 758 |
-
"step": 840
|
| 759 |
-
},
|
| 760 |
-
{
|
| 761 |
-
"epoch": 0.30886627906976744,
|
| 762 |
-
"grad_norm": 18.63671875,
|
| 763 |
-
"learning_rate": 6.914970930232559e-05,
|
| 764 |
-
"loss": 0.9398,
|
| 765 |
-
"step": 850
|
| 766 |
-
},
|
| 767 |
-
{
|
| 768 |
-
"epoch": 0.30886627906976744,
|
| 769 |
-
"eval_accuracy": 0.6420471958320564,
|
| 770 |
-
"eval_loss": 0.9642446041107178,
|
| 771 |
-
"eval_model_preparation_time": 0.0015,
|
| 772 |
-
"eval_runtime": 47.8675,
|
| 773 |
-
"eval_samples_per_second": 68.167,
|
| 774 |
-
"eval_steps_per_second": 2.131,
|
| 775 |
-
"step": 850
|
| 776 |
-
},
|
| 777 |
-
{
|
| 778 |
-
"epoch": 0.3125,
|
| 779 |
-
"grad_norm": 22.47454261779785,
|
| 780 |
-
"learning_rate": 6.878633720930233e-05,
|
| 781 |
-
"loss": 1.0515,
|
| 782 |
-
"step": 860
|
| 783 |
-
},
|
| 784 |
-
{
|
| 785 |
-
"epoch": 0.31613372093023256,
|
| 786 |
-
"grad_norm": 21.17203712463379,
|
| 787 |
-
"learning_rate": 6.842296511627907e-05,
|
| 788 |
-
"loss": 0.973,
|
| 789 |
-
"step": 870
|
| 790 |
-
},
|
| 791 |
-
{
|
| 792 |
-
"epoch": 0.31976744186046513,
|
| 793 |
-
"grad_norm": 20.848777770996094,
|
| 794 |
-
"learning_rate": 6.805959302325582e-05,
|
| 795 |
-
"loss": 0.9193,
|
| 796 |
-
"step": 880
|
| 797 |
-
},
|
| 798 |
-
{
|
| 799 |
-
"epoch": 0.3234011627906977,
|
| 800 |
-
"grad_norm": 25.05883026123047,
|
| 801 |
-
"learning_rate": 6.769622093023256e-05,
|
| 802 |
-
"loss": 0.9351,
|
| 803 |
-
"step": 890
|
| 804 |
-
},
|
| 805 |
-
{
|
| 806 |
-
"epoch": 0.32703488372093026,
|
| 807 |
-
"grad_norm": 22.536279678344727,
|
| 808 |
-
"learning_rate": 6.73328488372093e-05,
|
| 809 |
-
"loss": 1.0203,
|
| 810 |
-
"step": 900
|
| 811 |
-
},
|
| 812 |
-
{
|
| 813 |
-
"epoch": 0.32703488372093026,
|
| 814 |
-
"eval_accuracy": 0.6736132393502912,
|
| 815 |
-
"eval_loss": 0.9405654072761536,
|
| 816 |
-
"eval_model_preparation_time": 0.0015,
|
| 817 |
-
"eval_runtime": 49.3771,
|
| 818 |
-
"eval_samples_per_second": 66.083,
|
| 819 |
-
"eval_steps_per_second": 2.066,
|
| 820 |
-
"step": 900
|
| 821 |
-
},
|
| 822 |
-
{
|
| 823 |
-
"epoch": 0.33066860465116277,
|
| 824 |
-
"grad_norm": 14.16507339477539,
|
| 825 |
-
"learning_rate": 6.696947674418606e-05,
|
| 826 |
-
"loss": 1.0585,
|
| 827 |
-
"step": 910
|
| 828 |
-
},
|
| 829 |
-
{
|
| 830 |
-
"epoch": 0.33430232558139533,
|
| 831 |
-
"grad_norm": 19.16563606262207,
|
| 832 |
-
"learning_rate": 6.66061046511628e-05,
|
| 833 |
-
"loss": 0.9585,
|
| 834 |
-
"step": 920
|
| 835 |
-
},
|
| 836 |
-
{
|
| 837 |
-
"epoch": 0.3379360465116279,
|
| 838 |
-
"grad_norm": 26.094350814819336,
|
| 839 |
-
"learning_rate": 6.624273255813954e-05,
|
| 840 |
-
"loss": 1.0055,
|
| 841 |
-
"step": 930
|
| 842 |
-
},
|
| 843 |
-
{
|
| 844 |
-
"epoch": 0.34156976744186046,
|
| 845 |
-
"grad_norm": 18.31908416748047,
|
| 846 |
-
"learning_rate": 6.587936046511628e-05,
|
| 847 |
-
"loss": 0.9208,
|
| 848 |
-
"step": 940
|
| 849 |
-
},
|
| 850 |
-
{
|
| 851 |
-
"epoch": 0.345203488372093,
|
| 852 |
-
"grad_norm": 31.46238136291504,
|
| 853 |
-
"learning_rate": 6.551598837209303e-05,
|
| 854 |
-
"loss": 1.0836,
|
| 855 |
-
"step": 950
|
| 856 |
-
},
|
| 857 |
-
{
|
| 858 |
-
"epoch": 0.345203488372093,
|
| 859 |
-
"eval_accuracy": 0.6647257125344774,
|
| 860 |
-
"eval_loss": 0.9281411170959473,
|
| 861 |
-
"eval_model_preparation_time": 0.0015,
|
| 862 |
-
"eval_runtime": 50.41,
|
| 863 |
-
"eval_samples_per_second": 64.729,
|
| 864 |
-
"eval_steps_per_second": 2.023,
|
| 865 |
-
"step": 950
|
| 866 |
-
},
|
| 867 |
-
{
|
| 868 |
-
"epoch": 0.3488372093023256,
|
| 869 |
-
"grad_norm": 16.519235610961914,
|
| 870 |
-
"learning_rate": 6.515261627906977e-05,
|
| 871 |
-
"loss": 0.9886,
|
| 872 |
-
"step": 960
|
| 873 |
-
},
|
| 874 |
-
{
|
| 875 |
-
"epoch": 0.35247093023255816,
|
| 876 |
-
"grad_norm": 21.729778289794922,
|
| 877 |
-
"learning_rate": 6.478924418604651e-05,
|
| 878 |
-
"loss": 1.0044,
|
| 879 |
-
"step": 970
|
| 880 |
-
},
|
| 881 |
-
{
|
| 882 |
-
"epoch": 0.3561046511627907,
|
| 883 |
-
"grad_norm": 19.362590789794922,
|
| 884 |
-
"learning_rate": 6.442587209302325e-05,
|
| 885 |
-
"loss": 0.9829,
|
| 886 |
-
"step": 980
|
| 887 |
-
},
|
| 888 |
-
{
|
| 889 |
-
"epoch": 0.35973837209302323,
|
| 890 |
-
"grad_norm": 19.202898025512695,
|
| 891 |
-
"learning_rate": 6.40625e-05,
|
| 892 |
-
"loss": 1.0145,
|
| 893 |
-
"step": 990
|
| 894 |
-
},
|
| 895 |
-
{
|
| 896 |
-
"epoch": 0.3633720930232558,
|
| 897 |
-
"grad_norm": 17.671977996826172,
|
| 898 |
-
"learning_rate": 6.369912790697675e-05,
|
| 899 |
-
"loss": 0.9329,
|
| 900 |
-
"step": 1000
|
| 901 |
-
},
|
| 902 |
-
{
|
| 903 |
-
"epoch": 0.3633720930232558,
|
| 904 |
-
"eval_accuracy": 0.6923076923076923,
|
| 905 |
-
"eval_loss": 0.8783280849456787,
|
| 906 |
-
"eval_model_preparation_time": 0.0015,
|
| 907 |
-
"eval_runtime": 49.9909,
|
| 908 |
-
"eval_samples_per_second": 65.272,
|
| 909 |
-
"eval_steps_per_second": 2.04,
|
| 910 |
-
"step": 1000
|
| 911 |
-
},
|
| 912 |
-
{
|
| 913 |
-
"epoch": 0.36700581395348836,
|
| 914 |
-
"grad_norm": 22.96895408630371,
|
| 915 |
-
"learning_rate": 6.333575581395349e-05,
|
| 916 |
-
"loss": 0.9242,
|
| 917 |
-
"step": 1010
|
| 918 |
-
},
|
| 919 |
-
{
|
| 920 |
-
"epoch": 0.3706395348837209,
|
| 921 |
-
"grad_norm": 19.682958602905273,
|
| 922 |
-
"learning_rate": 6.297238372093024e-05,
|
| 923 |
-
"loss": 0.9181,
|
| 924 |
-
"step": 1020
|
| 925 |
-
},
|
| 926 |
-
{
|
| 927 |
-
"epoch": 0.3742732558139535,
|
| 928 |
-
"grad_norm": 21.612184524536133,
|
| 929 |
-
"learning_rate": 6.260901162790698e-05,
|
| 930 |
-
"loss": 0.8911,
|
| 931 |
-
"step": 1030
|
| 932 |
-
},
|
| 933 |
-
{
|
| 934 |
-
"epoch": 0.37790697674418605,
|
| 935 |
-
"grad_norm": 17.922510147094727,
|
| 936 |
-
"learning_rate": 6.224563953488372e-05,
|
| 937 |
-
"loss": 0.8801,
|
| 938 |
-
"step": 1040
|
| 939 |
-
},
|
| 940 |
-
{
|
| 941 |
-
"epoch": 0.3815406976744186,
|
| 942 |
-
"grad_norm": 19.79427719116211,
|
| 943 |
-
"learning_rate": 6.188226744186046e-05,
|
| 944 |
-
"loss": 0.9331,
|
| 945 |
-
"step": 1050
|
| 946 |
-
},
|
| 947 |
-
{
|
| 948 |
-
"epoch": 0.3815406976744186,
|
| 949 |
-
"eval_accuracy": 0.6972111553784861,
|
| 950 |
-
"eval_loss": 0.8626508712768555,
|
| 951 |
-
"eval_model_preparation_time": 0.0015,
|
| 952 |
-
"eval_runtime": 48.7203,
|
| 953 |
-
"eval_samples_per_second": 66.974,
|
| 954 |
-
"eval_steps_per_second": 2.094,
|
| 955 |
-
"step": 1050
|
| 956 |
-
},
|
| 957 |
-
{
|
| 958 |
-
"epoch": 0.3851744186046512,
|
| 959 |
-
"grad_norm": 23.669225692749023,
|
| 960 |
-
"learning_rate": 6.151889534883722e-05,
|
| 961 |
-
"loss": 0.9045,
|
| 962 |
-
"step": 1060
|
| 963 |
-
},
|
| 964 |
-
{
|
| 965 |
-
"epoch": 0.38880813953488375,
|
| 966 |
-
"grad_norm": 19.99860191345215,
|
| 967 |
-
"learning_rate": 6.115552325581396e-05,
|
| 968 |
-
"loss": 0.9222,
|
| 969 |
-
"step": 1070
|
| 970 |
-
},
|
| 971 |
-
{
|
| 972 |
-
"epoch": 0.39244186046511625,
|
| 973 |
-
"grad_norm": 43.26332092285156,
|
| 974 |
-
"learning_rate": 6.07921511627907e-05,
|
| 975 |
-
"loss": 0.9973,
|
| 976 |
-
"step": 1080
|
| 977 |
-
},
|
| 978 |
-
{
|
| 979 |
-
"epoch": 0.3960755813953488,
|
| 980 |
-
"grad_norm": 25.616634368896484,
|
| 981 |
-
"learning_rate": 6.042877906976745e-05,
|
| 982 |
-
"loss": 0.9616,
|
| 983 |
-
"step": 1090
|
| 984 |
-
},
|
| 985 |
-
{
|
| 986 |
-
"epoch": 0.3997093023255814,
|
| 987 |
-
"grad_norm": 21.20777702331543,
|
| 988 |
-
"learning_rate": 6.006540697674419e-05,
|
| 989 |
-
"loss": 0.9042,
|
| 990 |
-
"step": 1100
|
| 991 |
-
},
|
| 992 |
-
{
|
| 993 |
-
"epoch": 0.3997093023255814,
|
| 994 |
-
"eval_accuracy": 0.7269384002451732,
|
| 995 |
-
"eval_loss": 0.832632303237915,
|
| 996 |
-
"eval_model_preparation_time": 0.0015,
|
| 997 |
-
"eval_runtime": 47.8314,
|
| 998 |
-
"eval_samples_per_second": 68.219,
|
| 999 |
-
"eval_steps_per_second": 2.132,
|
| 1000 |
-
"step": 1100
|
| 1001 |
-
},
|
| 1002 |
-
{
|
| 1003 |
-
"epoch": 0.40334302325581395,
|
| 1004 |
-
"grad_norm": 25.138526916503906,
|
| 1005 |
-
"learning_rate": 5.970203488372094e-05,
|
| 1006 |
-
"loss": 0.9166,
|
| 1007 |
-
"step": 1110
|
| 1008 |
-
},
|
| 1009 |
-
{
|
| 1010 |
-
"epoch": 0.4069767441860465,
|
| 1011 |
-
"grad_norm": 31.42925453186035,
|
| 1012 |
-
"learning_rate": 5.933866279069767e-05,
|
| 1013 |
-
"loss": 0.8452,
|
| 1014 |
-
"step": 1120
|
| 1015 |
-
},
|
| 1016 |
-
{
|
| 1017 |
-
"epoch": 0.4106104651162791,
|
| 1018 |
-
"grad_norm": 21.83854866027832,
|
| 1019 |
-
"learning_rate": 5.8975290697674425e-05,
|
| 1020 |
-
"loss": 0.9061,
|
| 1021 |
-
"step": 1130
|
| 1022 |
-
},
|
| 1023 |
-
{
|
| 1024 |
-
"epoch": 0.41424418604651164,
|
| 1025 |
-
"grad_norm": 24.000688552856445,
|
| 1026 |
-
"learning_rate": 5.861191860465116e-05,
|
| 1027 |
-
"loss": 0.9286,
|
| 1028 |
-
"step": 1140
|
| 1029 |
-
},
|
| 1030 |
-
{
|
| 1031 |
-
"epoch": 0.4178779069767442,
|
| 1032 |
-
"grad_norm": 20.03739356994629,
|
| 1033 |
-
"learning_rate": 5.824854651162791e-05,
|
| 1034 |
-
"loss": 0.8758,
|
| 1035 |
-
"step": 1150
|
| 1036 |
-
},
|
| 1037 |
-
{
|
| 1038 |
-
"epoch": 0.4178779069767442,
|
| 1039 |
-
"eval_accuracy": 0.7247931351517009,
|
| 1040 |
-
"eval_loss": 0.8062854409217834,
|
| 1041 |
-
"eval_model_preparation_time": 0.0015,
|
| 1042 |
-
"eval_runtime": 49.4415,
|
| 1043 |
-
"eval_samples_per_second": 65.997,
|
| 1044 |
-
"eval_steps_per_second": 2.063,
|
| 1045 |
-
"step": 1150
|
| 1046 |
-
},
|
| 1047 |
-
{
|
| 1048 |
-
"epoch": 0.42151162790697677,
|
| 1049 |
-
"grad_norm": 22.991212844848633,
|
| 1050 |
-
"learning_rate": 5.7885174418604646e-05,
|
| 1051 |
-
"loss": 0.8388,
|
| 1052 |
-
"step": 1160
|
| 1053 |
-
},
|
| 1054 |
-
{
|
| 1055 |
-
"epoch": 0.4251453488372093,
|
| 1056 |
-
"grad_norm": 14.57451343536377,
|
| 1057 |
-
"learning_rate": 5.75218023255814e-05,
|
| 1058 |
-
"loss": 0.8124,
|
| 1059 |
-
"step": 1170
|
| 1060 |
-
},
|
| 1061 |
-
{
|
| 1062 |
-
"epoch": 0.42877906976744184,
|
| 1063 |
-
"grad_norm": 16.236392974853516,
|
| 1064 |
-
"learning_rate": 5.715843023255815e-05,
|
| 1065 |
-
"loss": 0.9013,
|
| 1066 |
-
"step": 1180
|
| 1067 |
-
},
|
| 1068 |
-
{
|
| 1069 |
-
"epoch": 0.4324127906976744,
|
| 1070 |
-
"grad_norm": 13.36828327178955,
|
| 1071 |
-
"learning_rate": 5.679505813953489e-05,
|
| 1072 |
-
"loss": 0.8201,
|
| 1073 |
-
"step": 1190
|
| 1074 |
-
},
|
| 1075 |
-
{
|
| 1076 |
-
"epoch": 0.436046511627907,
|
| 1077 |
-
"grad_norm": 25.648473739624023,
|
| 1078 |
-
"learning_rate": 5.6431686046511635e-05,
|
| 1079 |
-
"loss": 0.857,
|
| 1080 |
-
"step": 1200
|
| 1081 |
-
},
|
| 1082 |
-
{
|
| 1083 |
-
"epoch": 0.436046511627907,
|
| 1084 |
-
"eval_accuracy": 0.6993564204719583,
|
| 1085 |
-
"eval_loss": 0.8466485738754272,
|
| 1086 |
-
"eval_model_preparation_time": 0.0015,
|
| 1087 |
-
"eval_runtime": 48.354,
|
| 1088 |
-
"eval_samples_per_second": 67.482,
|
| 1089 |
-
"eval_steps_per_second": 2.109,
|
| 1090 |
-
"step": 1200
|
| 1091 |
-
},
|
| 1092 |
-
{
|
| 1093 |
-
"epoch": 0.43968023255813954,
|
| 1094 |
-
"grad_norm": 18.110530853271484,
|
| 1095 |
-
"learning_rate": 5.606831395348837e-05,
|
| 1096 |
-
"loss": 0.9745,
|
| 1097 |
-
"step": 1210
|
| 1098 |
-
},
|
| 1099 |
-
{
|
| 1100 |
-
"epoch": 0.4433139534883721,
|
| 1101 |
-
"grad_norm": 25.08212661743164,
|
| 1102 |
-
"learning_rate": 5.570494186046512e-05,
|
| 1103 |
-
"loss": 0.8266,
|
| 1104 |
-
"step": 1220
|
| 1105 |
-
},
|
| 1106 |
-
{
|
| 1107 |
-
"epoch": 0.44694767441860467,
|
| 1108 |
-
"grad_norm": 17.428245544433594,
|
| 1109 |
-
"learning_rate": 5.5341569767441856e-05,
|
| 1110 |
-
"loss": 0.8776,
|
| 1111 |
-
"step": 1230
|
| 1112 |
-
},
|
| 1113 |
-
{
|
| 1114 |
-
"epoch": 0.45058139534883723,
|
| 1115 |
-
"grad_norm": 20.17462158203125,
|
| 1116 |
-
"learning_rate": 5.497819767441861e-05,
|
| 1117 |
-
"loss": 0.9266,
|
| 1118 |
-
"step": 1240
|
| 1119 |
-
},
|
| 1120 |
-
{
|
| 1121 |
-
"epoch": 0.45421511627906974,
|
| 1122 |
-
"grad_norm": 19.790435791015625,
|
| 1123 |
-
"learning_rate": 5.461482558139536e-05,
|
| 1124 |
-
"loss": 0.8733,
|
| 1125 |
-
"step": 1250
|
| 1126 |
-
},
|
| 1127 |
-
{
|
| 1128 |
-
"epoch": 0.45421511627906974,
|
| 1129 |
-
"eval_accuracy": 0.7223414036163041,
|
| 1130 |
-
"eval_loss": 0.787076473236084,
|
| 1131 |
-
"eval_model_preparation_time": 0.0015,
|
| 1132 |
-
"eval_runtime": 51.1791,
|
| 1133 |
-
"eval_samples_per_second": 63.756,
|
| 1134 |
-
"eval_steps_per_second": 1.993,
|
| 1135 |
-
"step": 1250
|
| 1136 |
-
},
|
| 1137 |
-
{
|
| 1138 |
-
"epoch": 0.4578488372093023,
|
| 1139 |
-
"grad_norm": 17.204328536987305,
|
| 1140 |
-
"learning_rate": 5.42514534883721e-05,
|
| 1141 |
-
"loss": 0.8393,
|
| 1142 |
-
"step": 1260
|
| 1143 |
-
},
|
| 1144 |
-
{
|
| 1145 |
-
"epoch": 0.46148255813953487,
|
| 1146 |
-
"grad_norm": 16.980710983276367,
|
| 1147 |
-
"learning_rate": 5.3888081395348845e-05,
|
| 1148 |
-
"loss": 0.8185,
|
| 1149 |
-
"step": 1270
|
| 1150 |
-
},
|
| 1151 |
-
{
|
| 1152 |
-
"epoch": 0.46511627906976744,
|
| 1153 |
-
"grad_norm": 21.34583854675293,
|
| 1154 |
-
"learning_rate": 5.352470930232558e-05,
|
| 1155 |
-
"loss": 0.8666,
|
| 1156 |
-
"step": 1280
|
| 1157 |
-
},
|
| 1158 |
-
{
|
| 1159 |
-
"epoch": 0.46875,
|
| 1160 |
-
"grad_norm": 15.561858177185059,
|
| 1161 |
-
"learning_rate": 5.316133720930233e-05,
|
| 1162 |
-
"loss": 0.8883,
|
| 1163 |
-
"step": 1290
|
| 1164 |
-
},
|
| 1165 |
-
{
|
| 1166 |
-
"epoch": 0.47238372093023256,
|
| 1167 |
-
"grad_norm": 24.96396255493164,
|
| 1168 |
-
"learning_rate": 5.2797965116279066e-05,
|
| 1169 |
-
"loss": 0.7988,
|
| 1170 |
-
"step": 1300
|
| 1171 |
-
},
|
| 1172 |
-
{
|
| 1173 |
-
"epoch": 0.47238372093023256,
|
| 1174 |
-
"eval_accuracy": 0.7486975176218205,
|
| 1175 |
-
"eval_loss": 0.7476297616958618,
|
| 1176 |
-
"eval_model_preparation_time": 0.0015,
|
| 1177 |
-
"eval_runtime": 48.5075,
|
| 1178 |
-
"eval_samples_per_second": 67.268,
|
| 1179 |
-
"eval_steps_per_second": 2.103,
|
| 1180 |
-
"step": 1300
|
| 1181 |
-
},
|
| 1182 |
-
{
|
| 1183 |
-
"epoch": 0.47601744186046513,
|
| 1184 |
-
"grad_norm": 25.246776580810547,
|
| 1185 |
-
"learning_rate": 5.243459302325582e-05,
|
| 1186 |
-
"loss": 0.9025,
|
| 1187 |
-
"step": 1310
|
| 1188 |
-
},
|
| 1189 |
-
{
|
| 1190 |
-
"epoch": 0.4796511627906977,
|
| 1191 |
-
"grad_norm": 18.316572189331055,
|
| 1192 |
-
"learning_rate": 5.2071220930232554e-05,
|
| 1193 |
-
"loss": 0.7593,
|
| 1194 |
-
"step": 1320
|
| 1195 |
-
},
|
| 1196 |
-
{
|
| 1197 |
-
"epoch": 0.48328488372093026,
|
| 1198 |
-
"grad_norm": 22.122472763061523,
|
| 1199 |
-
"learning_rate": 5.170784883720931e-05,
|
| 1200 |
-
"loss": 0.8634,
|
| 1201 |
-
"step": 1330
|
| 1202 |
-
},
|
| 1203 |
-
{
|
| 1204 |
-
"epoch": 0.48691860465116277,
|
| 1205 |
-
"grad_norm": 24.7249698638916,
|
| 1206 |
-
"learning_rate": 5.1344476744186055e-05,
|
| 1207 |
-
"loss": 0.7407,
|
| 1208 |
-
"step": 1340
|
| 1209 |
-
},
|
| 1210 |
-
{
|
| 1211 |
-
"epoch": 0.49055232558139533,
|
| 1212 |
-
"grad_norm": 27.893335342407227,
|
| 1213 |
-
"learning_rate": 5.0981104651162795e-05,
|
| 1214 |
-
"loss": 0.9492,
|
| 1215 |
-
"step": 1350
|
| 1216 |
-
},
|
| 1217 |
-
{
|
| 1218 |
-
"epoch": 0.49055232558139533,
|
| 1219 |
-
"eval_accuracy": 0.6944529574011645,
|
| 1220 |
-
"eval_loss": 0.8117865920066833,
|
| 1221 |
-
"eval_model_preparation_time": 0.0015,
|
| 1222 |
-
"eval_runtime": 48.5657,
|
| 1223 |
-
"eval_samples_per_second": 67.187,
|
| 1224 |
-
"eval_steps_per_second": 2.1,
|
| 1225 |
-
"step": 1350
|
| 1226 |
-
},
|
| 1227 |
-
{
|
| 1228 |
-
"epoch": 0.4941860465116279,
|
| 1229 |
-
"grad_norm": 19.129026412963867,
|
| 1230 |
-
"learning_rate": 5.061773255813954e-05,
|
| 1231 |
-
"loss": 0.9274,
|
| 1232 |
-
"step": 1360
|
| 1233 |
-
},
|
| 1234 |
-
{
|
| 1235 |
-
"epoch": 0.49781976744186046,
|
| 1236 |
-
"grad_norm": 18.911165237426758,
|
| 1237 |
-
"learning_rate": 5.0254360465116276e-05,
|
| 1238 |
-
"loss": 0.807,
|
| 1239 |
-
"step": 1370
|
| 1240 |
-
},
|
| 1241 |
-
{
|
| 1242 |
-
"epoch": 0.501453488372093,
|
| 1243 |
-
"grad_norm": 19.536846160888672,
|
| 1244 |
-
"learning_rate": 4.989098837209303e-05,
|
| 1245 |
-
"loss": 0.8404,
|
| 1246 |
-
"step": 1380
|
| 1247 |
-
},
|
| 1248 |
-
{
|
| 1249 |
-
"epoch": 0.5050872093023255,
|
| 1250 |
-
"grad_norm": 23.16112518310547,
|
| 1251 |
-
"learning_rate": 4.952761627906977e-05,
|
| 1252 |
-
"loss": 0.812,
|
| 1253 |
-
"step": 1390
|
| 1254 |
-
},
|
| 1255 |
-
{
|
| 1256 |
-
"epoch": 0.5087209302325582,
|
| 1257 |
-
"grad_norm": 24.2547664642334,
|
| 1258 |
-
"learning_rate": 4.916424418604652e-05,
|
| 1259 |
-
"loss": 0.8047,
|
| 1260 |
-
"step": 1400
|
| 1261 |
-
},
|
| 1262 |
-
{
|
| 1263 |
-
"epoch": 0.5087209302325582,
|
| 1264 |
-
"eval_accuracy": 0.7391970579221575,
|
| 1265 |
-
"eval_loss": 0.7529688477516174,
|
| 1266 |
-
"eval_model_preparation_time": 0.0015,
|
| 1267 |
-
"eval_runtime": 50.0516,
|
| 1268 |
-
"eval_samples_per_second": 65.193,
|
| 1269 |
-
"eval_steps_per_second": 2.038,
|
| 1270 |
-
"step": 1400
|
| 1271 |
-
},
|
| 1272 |
-
{
|
| 1273 |
-
"epoch": 0.5123546511627907,
|
| 1274 |
-
"grad_norm": 21.53682518005371,
|
| 1275 |
-
"learning_rate": 4.880087209302326e-05,
|
| 1276 |
-
"loss": 0.799,
|
| 1277 |
-
"step": 1410
|
| 1278 |
-
},
|
| 1279 |
-
{
|
| 1280 |
-
"epoch": 0.5159883720930233,
|
| 1281 |
-
"grad_norm": 23.544010162353516,
|
| 1282 |
-
"learning_rate": 4.8437500000000005e-05,
|
| 1283 |
-
"loss": 0.7933,
|
| 1284 |
-
"step": 1420
|
| 1285 |
-
},
|
| 1286 |
-
{
|
| 1287 |
-
"epoch": 0.5196220930232558,
|
| 1288 |
-
"grad_norm": 19.342622756958008,
|
| 1289 |
-
"learning_rate": 4.8074127906976745e-05,
|
| 1290 |
-
"loss": 0.8245,
|
| 1291 |
-
"step": 1430
|
| 1292 |
-
},
|
| 1293 |
-
{
|
| 1294 |
-
"epoch": 0.5232558139534884,
|
| 1295 |
-
"grad_norm": 20.08898162841797,
|
| 1296 |
-
"learning_rate": 4.771075581395349e-05,
|
| 1297 |
-
"loss": 0.8104,
|
| 1298 |
-
"step": 1440
|
| 1299 |
-
},
|
| 1300 |
-
{
|
| 1301 |
-
"epoch": 0.5268895348837209,
|
| 1302 |
-
"grad_norm": 36.42573165893555,
|
| 1303 |
-
"learning_rate": 4.734738372093023e-05,
|
| 1304 |
-
"loss": 0.8601,
|
| 1305 |
-
"step": 1450
|
| 1306 |
-
},
|
| 1307 |
-
{
|
| 1308 |
-
"epoch": 0.5268895348837209,
|
| 1309 |
-
"eval_accuracy": 0.7477781182960466,
|
| 1310 |
-
"eval_loss": 0.7395877838134766,
|
| 1311 |
-
"eval_model_preparation_time": 0.0015,
|
| 1312 |
-
"eval_runtime": 48.2379,
|
| 1313 |
-
"eval_samples_per_second": 67.644,
|
| 1314 |
-
"eval_steps_per_second": 2.115,
|
| 1315 |
-
"step": 1450
|
| 1316 |
-
},
|
| 1317 |
-
{
|
| 1318 |
-
"epoch": 0.5305232558139535,
|
| 1319 |
-
"grad_norm": 18.966615676879883,
|
| 1320 |
-
"learning_rate": 4.6984011627906973e-05,
|
| 1321 |
-
"loss": 0.8142,
|
| 1322 |
-
"step": 1460
|
| 1323 |
-
},
|
| 1324 |
-
{
|
| 1325 |
-
"epoch": 0.534156976744186,
|
| 1326 |
-
"grad_norm": 19.256010055541992,
|
| 1327 |
-
"learning_rate": 4.662063953488373e-05,
|
| 1328 |
-
"loss": 0.7733,
|
| 1329 |
-
"step": 1470
|
| 1330 |
-
},
|
| 1331 |
-
{
|
| 1332 |
-
"epoch": 0.5377906976744186,
|
| 1333 |
-
"grad_norm": 17.08919334411621,
|
| 1334 |
-
"learning_rate": 4.625726744186047e-05,
|
| 1335 |
-
"loss": 0.7369,
|
| 1336 |
-
"step": 1480
|
| 1337 |
-
},
|
| 1338 |
-
{
|
| 1339 |
-
"epoch": 0.5414244186046512,
|
| 1340 |
-
"grad_norm": 30.637798309326172,
|
| 1341 |
-
"learning_rate": 4.5893895348837215e-05,
|
| 1342 |
-
"loss": 0.7535,
|
| 1343 |
-
"step": 1490
|
| 1344 |
-
},
|
| 1345 |
-
{
|
| 1346 |
-
"epoch": 0.5450581395348837,
|
| 1347 |
-
"grad_norm": 16.82142448425293,
|
| 1348 |
-
"learning_rate": 4.5530523255813955e-05,
|
| 1349 |
-
"loss": 0.7873,
|
| 1350 |
-
"step": 1500
|
| 1351 |
-
},
|
| 1352 |
-
{
|
| 1353 |
-
"epoch": 0.5450581395348837,
|
| 1354 |
-
"eval_accuracy": 0.7618755746245786,
|
| 1355 |
-
"eval_loss": 0.7191266417503357,
|
| 1356 |
-
"eval_model_preparation_time": 0.0015,
|
| 1357 |
-
"eval_runtime": 47.9425,
|
| 1358 |
-
"eval_samples_per_second": 68.061,
|
| 1359 |
-
"eval_steps_per_second": 2.128,
|
| 1360 |
-
"step": 1500
|
| 1361 |
-
},
|
| 1362 |
-
{
|
| 1363 |
-
"epoch": 0.5486918604651163,
|
| 1364 |
-
"grad_norm": 15.000924110412598,
|
| 1365 |
-
"learning_rate": 4.51671511627907e-05,
|
| 1366 |
-
"loss": 0.7462,
|
| 1367 |
-
"step": 1510
|
| 1368 |
-
},
|
| 1369 |
-
{
|
| 1370 |
-
"epoch": 0.5523255813953488,
|
| 1371 |
-
"grad_norm": 19.328227996826172,
|
| 1372 |
-
"learning_rate": 4.480377906976744e-05,
|
| 1373 |
-
"loss": 0.7997,
|
| 1374 |
-
"step": 1520
|
| 1375 |
-
},
|
| 1376 |
-
{
|
| 1377 |
-
"epoch": 0.5559593023255814,
|
| 1378 |
-
"grad_norm": 17.77477264404297,
|
| 1379 |
-
"learning_rate": 4.444040697674418e-05,
|
| 1380 |
-
"loss": 0.7797,
|
| 1381 |
-
"step": 1530
|
| 1382 |
-
},
|
| 1383 |
-
{
|
| 1384 |
-
"epoch": 0.559593023255814,
|
| 1385 |
-
"grad_norm": 19.144107818603516,
|
| 1386 |
-
"learning_rate": 4.407703488372093e-05,
|
| 1387 |
-
"loss": 0.7292,
|
| 1388 |
-
"step": 1540
|
| 1389 |
-
},
|
| 1390 |
-
{
|
| 1391 |
-
"epoch": 0.5632267441860465,
|
| 1392 |
-
"grad_norm": 23.17219352722168,
|
| 1393 |
-
"learning_rate": 4.371366279069768e-05,
|
| 1394 |
-
"loss": 0.704,
|
| 1395 |
-
"step": 1550
|
| 1396 |
-
},
|
| 1397 |
-
{
|
| 1398 |
-
"epoch": 0.5632267441860465,
|
| 1399 |
-
"eval_accuracy": 0.7581979773214833,
|
| 1400 |
-
"eval_loss": 0.6839959621429443,
|
| 1401 |
-
"eval_model_preparation_time": 0.0015,
|
| 1402 |
-
"eval_runtime": 48.3014,
|
| 1403 |
-
"eval_samples_per_second": 67.555,
|
| 1404 |
-
"eval_steps_per_second": 2.112,
|
| 1405 |
-
"step": 1550
|
| 1406 |
-
},
|
| 1407 |
-
{
|
| 1408 |
-
"epoch": 0.5668604651162791,
|
| 1409 |
-
"grad_norm": 17.988855361938477,
|
| 1410 |
-
"learning_rate": 4.3350290697674425e-05,
|
| 1411 |
-
"loss": 0.8192,
|
| 1412 |
-
"step": 1560
|
| 1413 |
-
},
|
| 1414 |
-
{
|
| 1415 |
-
"epoch": 0.5704941860465116,
|
| 1416 |
-
"grad_norm": 39.58876037597656,
|
| 1417 |
-
"learning_rate": 4.2986918604651165e-05,
|
| 1418 |
-
"loss": 0.7845,
|
| 1419 |
-
"step": 1570
|
| 1420 |
-
},
|
| 1421 |
-
{
|
| 1422 |
-
"epoch": 0.5741279069767442,
|
| 1423 |
-
"grad_norm": 24.698930740356445,
|
| 1424 |
-
"learning_rate": 4.262354651162791e-05,
|
| 1425 |
-
"loss": 0.7521,
|
| 1426 |
-
"step": 1580
|
| 1427 |
-
},
|
| 1428 |
-
{
|
| 1429 |
-
"epoch": 0.5777616279069767,
|
| 1430 |
-
"grad_norm": 17.967649459838867,
|
| 1431 |
-
"learning_rate": 4.226017441860465e-05,
|
| 1432 |
-
"loss": 0.8063,
|
| 1433 |
-
"step": 1590
|
| 1434 |
-
},
|
| 1435 |
-
{
|
| 1436 |
-
"epoch": 0.5813953488372093,
|
| 1437 |
-
"grad_norm": 25.17499351501465,
|
| 1438 |
-
"learning_rate": 4.18968023255814e-05,
|
| 1439 |
-
"loss": 0.8536,
|
| 1440 |
-
"step": 1600
|
| 1441 |
-
},
|
| 1442 |
-
{
|
| 1443 |
-
"epoch": 0.5813953488372093,
|
| 1444 |
-
"eval_accuracy": 0.7581979773214833,
|
| 1445 |
-
"eval_loss": 0.6965886950492859,
|
| 1446 |
-
"eval_model_preparation_time": 0.0015,
|
| 1447 |
-
"eval_runtime": 48.257,
|
| 1448 |
-
"eval_samples_per_second": 67.617,
|
| 1449 |
-
"eval_steps_per_second": 2.114,
|
| 1450 |
-
"step": 1600
|
| 1451 |
-
},
|
| 1452 |
-
{
|
| 1453 |
-
"epoch": 0.5850290697674418,
|
| 1454 |
-
"grad_norm": 27.656429290771484,
|
| 1455 |
-
"learning_rate": 4.153343023255814e-05,
|
| 1456 |
-
"loss": 0.7501,
|
| 1457 |
-
"step": 1610
|
| 1458 |
-
},
|
| 1459 |
-
{
|
| 1460 |
-
"epoch": 0.5886627906976745,
|
| 1461 |
-
"grad_norm": 19.678503036499023,
|
| 1462 |
-
"learning_rate": 4.117005813953488e-05,
|
| 1463 |
-
"loss": 0.7515,
|
| 1464 |
-
"step": 1620
|
| 1465 |
-
},
|
| 1466 |
-
{
|
| 1467 |
-
"epoch": 0.592296511627907,
|
| 1468 |
-
"grad_norm": 19.597240447998047,
|
| 1469 |
-
"learning_rate": 4.080668604651163e-05,
|
| 1470 |
-
"loss": 0.7465,
|
| 1471 |
-
"step": 1630
|
| 1472 |
-
},
|
| 1473 |
-
{
|
| 1474 |
-
"epoch": 0.5959302325581395,
|
| 1475 |
-
"grad_norm": 24.52513885498047,
|
| 1476 |
-
"learning_rate": 4.0443313953488375e-05,
|
| 1477 |
-
"loss": 0.6374,
|
| 1478 |
-
"step": 1640
|
| 1479 |
-
},
|
| 1480 |
-
{
|
| 1481 |
-
"epoch": 0.5995639534883721,
|
| 1482 |
-
"grad_norm": 27.33843231201172,
|
| 1483 |
-
"learning_rate": 4.007994186046512e-05,
|
| 1484 |
-
"loss": 0.7612,
|
| 1485 |
-
"step": 1650
|
| 1486 |
-
},
|
| 1487 |
-
{
|
| 1488 |
-
"epoch": 0.5995639534883721,
|
| 1489 |
-
"eval_accuracy": 0.7894575543977934,
|
| 1490 |
-
"eval_loss": 0.6561300754547119,
|
| 1491 |
-
"eval_model_preparation_time": 0.0015,
|
| 1492 |
-
"eval_runtime": 53.5897,
|
| 1493 |
-
"eval_samples_per_second": 60.889,
|
| 1494 |
-
"eval_steps_per_second": 1.903,
|
| 1495 |
-
"step": 1650
|
| 1496 |
-
},
|
| 1497 |
-
{
|
| 1498 |
-
"epoch": 0.6031976744186046,
|
| 1499 |
-
"grad_norm": 17.966524124145508,
|
| 1500 |
-
"learning_rate": 3.971656976744186e-05,
|
| 1501 |
-
"loss": 0.6416,
|
| 1502 |
-
"step": 1660
|
| 1503 |
-
},
|
| 1504 |
-
{
|
| 1505 |
-
"epoch": 0.6068313953488372,
|
| 1506 |
-
"grad_norm": 24.99458885192871,
|
| 1507 |
-
"learning_rate": 3.935319767441861e-05,
|
| 1508 |
-
"loss": 0.7307,
|
| 1509 |
-
"step": 1670
|
| 1510 |
-
},
|
| 1511 |
-
{
|
| 1512 |
-
"epoch": 0.6104651162790697,
|
| 1513 |
-
"grad_norm": 17.375545501708984,
|
| 1514 |
-
"learning_rate": 3.898982558139535e-05,
|
| 1515 |
-
"loss": 0.6845,
|
| 1516 |
-
"step": 1680
|
| 1517 |
-
},
|
| 1518 |
-
{
|
| 1519 |
-
"epoch": 0.6140988372093024,
|
| 1520 |
-
"grad_norm": 21.309844970703125,
|
| 1521 |
-
"learning_rate": 3.86264534883721e-05,
|
| 1522 |
-
"loss": 0.7197,
|
| 1523 |
-
"step": 1690
|
| 1524 |
-
},
|
| 1525 |
-
{
|
| 1526 |
-
"epoch": 0.6177325581395349,
|
| 1527 |
-
"grad_norm": 19.636783599853516,
|
| 1528 |
-
"learning_rate": 3.826308139534884e-05,
|
| 1529 |
-
"loss": 0.7701,
|
| 1530 |
-
"step": 1700
|
| 1531 |
-
},
|
| 1532 |
-
{
|
| 1533 |
-
"epoch": 0.6177325581395349,
|
| 1534 |
-
"eval_accuracy": 0.7931351517008888,
|
| 1535 |
-
"eval_loss": 0.6381626725196838,
|
| 1536 |
-
"eval_model_preparation_time": 0.0015,
|
| 1537 |
-
"eval_runtime": 51.3975,
|
| 1538 |
-
"eval_samples_per_second": 63.486,
|
| 1539 |
-
"eval_steps_per_second": 1.985,
|
| 1540 |
-
"step": 1700
|
| 1541 |
-
},
|
| 1542 |
-
{
|
| 1543 |
-
"epoch": 0.6213662790697675,
|
| 1544 |
-
"grad_norm": 16.005521774291992,
|
| 1545 |
-
"learning_rate": 3.789970930232558e-05,
|
| 1546 |
-
"loss": 0.73,
|
| 1547 |
-
"step": 1710
|
| 1548 |
-
},
|
| 1549 |
-
{
|
| 1550 |
-
"epoch": 0.625,
|
| 1551 |
-
"grad_norm": 22.36250114440918,
|
| 1552 |
-
"learning_rate": 3.7536337209302325e-05,
|
| 1553 |
-
"loss": 0.7021,
|
| 1554 |
-
"step": 1720
|
| 1555 |
-
},
|
| 1556 |
-
{
|
| 1557 |
-
"epoch": 0.6286337209302325,
|
| 1558 |
-
"grad_norm": 27.990943908691406,
|
| 1559 |
-
"learning_rate": 3.717296511627907e-05,
|
| 1560 |
-
"loss": 0.6955,
|
| 1561 |
-
"step": 1730
|
| 1562 |
-
},
|
| 1563 |
-
{
|
| 1564 |
-
"epoch": 0.6322674418604651,
|
| 1565 |
-
"grad_norm": 16.45665168762207,
|
| 1566 |
-
"learning_rate": 3.680959302325582e-05,
|
| 1567 |
-
"loss": 0.7612,
|
| 1568 |
-
"step": 1740
|
| 1569 |
-
},
|
| 1570 |
-
{
|
| 1571 |
-
"epoch": 0.6359011627906976,
|
| 1572 |
-
"grad_norm": 37.34355163574219,
|
| 1573 |
-
"learning_rate": 3.644622093023256e-05,
|
| 1574 |
-
"loss": 0.7538,
|
| 1575 |
-
"step": 1750
|
| 1576 |
-
},
|
| 1577 |
-
{
|
| 1578 |
-
"epoch": 0.6359011627906976,
|
| 1579 |
-
"eval_accuracy": 0.7821023597916028,
|
| 1580 |
-
"eval_loss": 0.6540101766586304,
|
| 1581 |
-
"eval_model_preparation_time": 0.0015,
|
| 1582 |
-
"eval_runtime": 50.9202,
|
| 1583 |
-
"eval_samples_per_second": 64.081,
|
| 1584 |
-
"eval_steps_per_second": 2.003,
|
| 1585 |
-
"step": 1750
|
| 1586 |
-
},
|
| 1587 |
-
{
|
| 1588 |
-
"epoch": 0.6395348837209303,
|
| 1589 |
-
"grad_norm": 22.030466079711914,
|
| 1590 |
-
"learning_rate": 3.608284883720931e-05,
|
| 1591 |
-
"loss": 0.7048,
|
| 1592 |
-
"step": 1760
|
| 1593 |
-
},
|
| 1594 |
-
{
|
| 1595 |
-
"epoch": 0.6431686046511628,
|
| 1596 |
-
"grad_norm": 16.459775924682617,
|
| 1597 |
-
"learning_rate": 3.571947674418605e-05,
|
| 1598 |
-
"loss": 0.7338,
|
| 1599 |
-
"step": 1770
|
| 1600 |
-
},
|
| 1601 |
-
{
|
| 1602 |
-
"epoch": 0.6468023255813954,
|
| 1603 |
-
"grad_norm": 20.406429290771484,
|
| 1604 |
-
"learning_rate": 3.535610465116279e-05,
|
| 1605 |
-
"loss": 0.7017,
|
| 1606 |
-
"step": 1780
|
| 1607 |
-
},
|
| 1608 |
-
{
|
| 1609 |
-
"epoch": 0.6504360465116279,
|
| 1610 |
-
"grad_norm": 32.876670837402344,
|
| 1611 |
-
"learning_rate": 3.4992732558139535e-05,
|
| 1612 |
-
"loss": 0.7467,
|
| 1613 |
-
"step": 1790
|
| 1614 |
-
},
|
| 1615 |
-
{
|
| 1616 |
-
"epoch": 0.6540697674418605,
|
| 1617 |
-
"grad_norm": 21.809101104736328,
|
| 1618 |
-
"learning_rate": 3.4629360465116276e-05,
|
| 1619 |
-
"loss": 0.7496,
|
| 1620 |
-
"step": 1800
|
| 1621 |
-
},
|
| 1622 |
-
{
|
| 1623 |
-
"epoch": 0.6540697674418605,
|
| 1624 |
-
"eval_accuracy": 0.7735212994177137,
|
| 1625 |
-
"eval_loss": 0.6603609323501587,
|
| 1626 |
-
"eval_model_preparation_time": 0.0015,
|
| 1627 |
-
"eval_runtime": 54.6689,
|
| 1628 |
-
"eval_samples_per_second": 59.687,
|
| 1629 |
-
"eval_steps_per_second": 1.866,
|
| 1630 |
-
"step": 1800
|
| 1631 |
-
},
|
| 1632 |
-
{
|
| 1633 |
-
"epoch": 0.657703488372093,
|
| 1634 |
-
"grad_norm": 17.124296188354492,
|
| 1635 |
-
"learning_rate": 3.426598837209303e-05,
|
| 1636 |
-
"loss": 0.6712,
|
| 1637 |
-
"step": 1810
|
| 1638 |
-
},
|
| 1639 |
-
{
|
| 1640 |
-
"epoch": 0.6613372093023255,
|
| 1641 |
-
"grad_norm": 17.997486114501953,
|
| 1642 |
-
"learning_rate": 3.390261627906977e-05,
|
| 1643 |
-
"loss": 0.6917,
|
| 1644 |
-
"step": 1820
|
| 1645 |
-
},
|
| 1646 |
-
{
|
| 1647 |
-
"epoch": 0.6649709302325582,
|
| 1648 |
-
"grad_norm": 30.947837829589844,
|
| 1649 |
-
"learning_rate": 3.353924418604652e-05,
|
| 1650 |
-
"loss": 0.7091,
|
| 1651 |
-
"step": 1830
|
| 1652 |
-
},
|
| 1653 |
-
{
|
| 1654 |
-
"epoch": 0.6686046511627907,
|
| 1655 |
-
"grad_norm": 24.643381118774414,
|
| 1656 |
-
"learning_rate": 3.317587209302326e-05,
|
| 1657 |
-
"loss": 0.6695,
|
| 1658 |
-
"step": 1840
|
| 1659 |
-
},
|
| 1660 |
-
{
|
| 1661 |
-
"epoch": 0.6722383720930233,
|
| 1662 |
-
"grad_norm": 23.651065826416016,
|
| 1663 |
-
"learning_rate": 3.2812500000000005e-05,
|
| 1664 |
-
"loss": 0.7512,
|
| 1665 |
-
"step": 1850
|
| 1666 |
-
},
|
| 1667 |
-
{
|
| 1668 |
-
"epoch": 0.6722383720930233,
|
| 1669 |
-
"eval_accuracy": 0.8032485442844008,
|
| 1670 |
-
"eval_loss": 0.6195615530014038,
|
| 1671 |
-
"eval_model_preparation_time": 0.0015,
|
| 1672 |
-
"eval_runtime": 51.8657,
|
| 1673 |
-
"eval_samples_per_second": 62.913,
|
| 1674 |
-
"eval_steps_per_second": 1.967,
|
| 1675 |
-
"step": 1850
|
| 1676 |
-
},
|
| 1677 |
-
{
|
| 1678 |
-
"epoch": 0.6758720930232558,
|
| 1679 |
-
"grad_norm": 19.081098556518555,
|
| 1680 |
-
"learning_rate": 3.2449127906976745e-05,
|
| 1681 |
-
"loss": 0.6343,
|
| 1682 |
-
"step": 1860
|
| 1683 |
-
},
|
| 1684 |
-
{
|
| 1685 |
-
"epoch": 0.6795058139534884,
|
| 1686 |
-
"grad_norm": 23.336320877075195,
|
| 1687 |
-
"learning_rate": 3.2085755813953486e-05,
|
| 1688 |
-
"loss": 0.7375,
|
| 1689 |
-
"step": 1870
|
| 1690 |
-
},
|
| 1691 |
-
{
|
| 1692 |
-
"epoch": 0.6831395348837209,
|
| 1693 |
-
"grad_norm": 19.397146224975586,
|
| 1694 |
-
"learning_rate": 3.172238372093023e-05,
|
| 1695 |
-
"loss": 0.6674,
|
| 1696 |
-
"step": 1880
|
| 1697 |
-
},
|
| 1698 |
-
{
|
| 1699 |
-
"epoch": 0.6867732558139535,
|
| 1700 |
-
"grad_norm": 21.171167373657227,
|
| 1701 |
-
"learning_rate": 3.135901162790697e-05,
|
| 1702 |
-
"loss": 0.7242,
|
| 1703 |
-
"step": 1890
|
| 1704 |
-
},
|
| 1705 |
-
{
|
| 1706 |
-
"epoch": 0.690406976744186,
|
| 1707 |
-
"grad_norm": 24.170560836791992,
|
| 1708 |
-
"learning_rate": 3.099563953488373e-05,
|
| 1709 |
-
"loss": 0.6773,
|
| 1710 |
-
"step": 1900
|
| 1711 |
-
},
|
| 1712 |
-
{
|
| 1713 |
-
"epoch": 0.690406976744186,
|
| 1714 |
-
"eval_accuracy": 0.8075390744713454,
|
| 1715 |
-
"eval_loss": 0.6085334420204163,
|
| 1716 |
-
"eval_model_preparation_time": 0.0015,
|
| 1717 |
-
"eval_runtime": 50.933,
|
| 1718 |
-
"eval_samples_per_second": 64.065,
|
| 1719 |
-
"eval_steps_per_second": 2.003,
|
| 1720 |
-
"step": 1900
|
| 1721 |
-
},
|
| 1722 |
-
{
|
| 1723 |
-
"epoch": 0.6940406976744186,
|
| 1724 |
-
"grad_norm": 19.82205581665039,
|
| 1725 |
-
"learning_rate": 3.063226744186047e-05,
|
| 1726 |
-
"loss": 0.7194,
|
| 1727 |
-
"step": 1910
|
| 1728 |
-
},
|
| 1729 |
-
{
|
| 1730 |
-
"epoch": 0.6976744186046512,
|
| 1731 |
-
"grad_norm": 19.169923782348633,
|
| 1732 |
-
"learning_rate": 3.026889534883721e-05,
|
| 1733 |
-
"loss": 0.6967,
|
| 1734 |
-
"step": 1920
|
| 1735 |
-
},
|
| 1736 |
-
{
|
| 1737 |
-
"epoch": 0.7013081395348837,
|
| 1738 |
-
"grad_norm": 18.116230010986328,
|
| 1739 |
-
"learning_rate": 2.9905523255813955e-05,
|
| 1740 |
-
"loss": 0.705,
|
| 1741 |
-
"step": 1930
|
| 1742 |
-
},
|
| 1743 |
-
{
|
| 1744 |
-
"epoch": 0.7049418604651163,
|
| 1745 |
-
"grad_norm": 16.55962562561035,
|
| 1746 |
-
"learning_rate": 2.95421511627907e-05,
|
| 1747 |
-
"loss": 0.6809,
|
| 1748 |
-
"step": 1940
|
| 1749 |
-
},
|
| 1750 |
-
{
|
| 1751 |
-
"epoch": 0.7085755813953488,
|
| 1752 |
-
"grad_norm": 34.48362731933594,
|
| 1753 |
-
"learning_rate": 2.9178779069767443e-05,
|
| 1754 |
-
"loss": 0.6655,
|
| 1755 |
-
"step": 1950
|
| 1756 |
-
},
|
| 1757 |
-
{
|
| 1758 |
-
"epoch": 0.7085755813953488,
|
| 1759 |
-
"eval_accuracy": 0.7995709469813056,
|
| 1760 |
-
"eval_loss": 0.6168962717056274,
|
| 1761 |
-
"eval_model_preparation_time": 0.0015,
|
| 1762 |
-
"eval_runtime": 49.9889,
|
| 1763 |
-
"eval_samples_per_second": 65.274,
|
| 1764 |
-
"eval_steps_per_second": 2.04,
|
| 1765 |
-
"step": 1950
|
| 1766 |
-
},
|
| 1767 |
-
{
|
| 1768 |
-
"epoch": 0.7122093023255814,
|
| 1769 |
-
"grad_norm": 27.100082397460938,
|
| 1770 |
-
"learning_rate": 2.8815406976744186e-05,
|
| 1771 |
-
"loss": 0.6525,
|
| 1772 |
-
"step": 1960
|
| 1773 |
-
},
|
| 1774 |
-
{
|
| 1775 |
-
"epoch": 0.715843023255814,
|
| 1776 |
-
"grad_norm": 15.424944877624512,
|
| 1777 |
-
"learning_rate": 2.845203488372093e-05,
|
| 1778 |
-
"loss": 0.7398,
|
| 1779 |
-
"step": 1970
|
| 1780 |
-
},
|
| 1781 |
-
{
|
| 1782 |
-
"epoch": 0.7194767441860465,
|
| 1783 |
-
"grad_norm": 18.602054595947266,
|
| 1784 |
-
"learning_rate": 2.8088662790697677e-05,
|
| 1785 |
-
"loss": 0.7341,
|
| 1786 |
-
"step": 1980
|
| 1787 |
-
},
|
| 1788 |
-
{
|
| 1789 |
-
"epoch": 0.7231104651162791,
|
| 1790 |
-
"grad_norm": 18.60715675354004,
|
| 1791 |
-
"learning_rate": 2.772529069767442e-05,
|
| 1792 |
-
"loss": 0.62,
|
| 1793 |
-
"step": 1990
|
| 1794 |
-
},
|
| 1795 |
-
{
|
| 1796 |
-
"epoch": 0.7267441860465116,
|
| 1797 |
-
"grad_norm": 18.766788482666016,
|
| 1798 |
-
"learning_rate": 2.7361918604651165e-05,
|
| 1799 |
-
"loss": 0.5997,
|
| 1800 |
-
"step": 2000
|
| 1801 |
-
},
|
| 1802 |
-
{
|
| 1803 |
-
"epoch": 0.7267441860465116,
|
| 1804 |
-
"eval_accuracy": 0.8004903463070794,
|
| 1805 |
-
"eval_loss": 0.6034106016159058,
|
| 1806 |
-
"eval_model_preparation_time": 0.0015,
|
| 1807 |
-
"eval_runtime": 50.3413,
|
| 1808 |
-
"eval_samples_per_second": 64.818,
|
| 1809 |
-
"eval_steps_per_second": 2.026,
|
| 1810 |
-
"step": 2000
|
| 1811 |
-
},
|
| 1812 |
-
{
|
| 1813 |
-
"epoch": 0.7303779069767442,
|
| 1814 |
-
"grad_norm": 20.883230209350586,
|
| 1815 |
-
"learning_rate": 2.699854651162791e-05,
|
| 1816 |
-
"loss": 0.6445,
|
| 1817 |
-
"step": 2010
|
| 1818 |
-
},
|
| 1819 |
-
{
|
| 1820 |
-
"epoch": 0.7340116279069767,
|
| 1821 |
-
"grad_norm": 17.367563247680664,
|
| 1822 |
-
"learning_rate": 2.6635174418604652e-05,
|
| 1823 |
-
"loss": 0.6727,
|
| 1824 |
-
"step": 2020
|
| 1825 |
-
},
|
| 1826 |
-
{
|
| 1827 |
-
"epoch": 0.7376453488372093,
|
| 1828 |
-
"grad_norm": 21.541458129882812,
|
| 1829 |
-
"learning_rate": 2.6271802325581396e-05,
|
| 1830 |
-
"loss": 0.6984,
|
| 1831 |
-
"step": 2030
|
| 1832 |
-
},
|
| 1833 |
-
{
|
| 1834 |
-
"epoch": 0.7412790697674418,
|
| 1835 |
-
"grad_norm": 25.181142807006836,
|
| 1836 |
-
"learning_rate": 2.590843023255814e-05,
|
| 1837 |
-
"loss": 0.6668,
|
| 1838 |
-
"step": 2040
|
| 1839 |
-
},
|
| 1840 |
-
{
|
| 1841 |
-
"epoch": 0.7449127906976745,
|
| 1842 |
-
"grad_norm": 19.112144470214844,
|
| 1843 |
-
"learning_rate": 2.5545058139534884e-05,
|
| 1844 |
-
"loss": 0.6144,
|
| 1845 |
-
"step": 2050
|
| 1846 |
-
},
|
| 1847 |
-
{
|
| 1848 |
-
"epoch": 0.7449127906976745,
|
| 1849 |
-
"eval_accuracy": 0.8075390744713454,
|
| 1850 |
-
"eval_loss": 0.6008254885673523,
|
| 1851 |
-
"eval_model_preparation_time": 0.0015,
|
| 1852 |
-
"eval_runtime": 50.7754,
|
| 1853 |
-
"eval_samples_per_second": 64.263,
|
| 1854 |
-
"eval_steps_per_second": 2.009,
|
| 1855 |
-
"step": 2050
|
| 1856 |
-
},
|
| 1857 |
-
{
|
| 1858 |
-
"epoch": 0.748546511627907,
|
| 1859 |
-
"grad_norm": 23.80943489074707,
|
| 1860 |
-
"learning_rate": 2.5181686046511628e-05,
|
| 1861 |
-
"loss": 0.6887,
|
| 1862 |
-
"step": 2060
|
| 1863 |
-
},
|
| 1864 |
-
{
|
| 1865 |
-
"epoch": 0.7521802325581395,
|
| 1866 |
-
"grad_norm": 22.5864200592041,
|
| 1867 |
-
"learning_rate": 2.481831395348837e-05,
|
| 1868 |
-
"loss": 0.6269,
|
| 1869 |
-
"step": 2070
|
| 1870 |
-
},
|
| 1871 |
-
{
|
| 1872 |
-
"epoch": 0.7558139534883721,
|
| 1873 |
-
"grad_norm": 20.330726623535156,
|
| 1874 |
-
"learning_rate": 2.4454941860465115e-05,
|
| 1875 |
-
"loss": 0.6929,
|
| 1876 |
-
"step": 2080
|
| 1877 |
-
},
|
| 1878 |
-
{
|
| 1879 |
-
"epoch": 0.7594476744186046,
|
| 1880 |
-
"grad_norm": 24.566627502441406,
|
| 1881 |
-
"learning_rate": 2.4091569767441862e-05,
|
| 1882 |
-
"loss": 0.5906,
|
| 1883 |
-
"step": 2090
|
| 1884 |
-
},
|
| 1885 |
-
{
|
| 1886 |
-
"epoch": 0.7630813953488372,
|
| 1887 |
-
"grad_norm": 23.221717834472656,
|
| 1888 |
-
"learning_rate": 2.3728197674418606e-05,
|
| 1889 |
-
"loss": 0.6519,
|
| 1890 |
-
"step": 2100
|
| 1891 |
-
},
|
| 1892 |
-
{
|
| 1893 |
-
"epoch": 0.7630813953488372,
|
| 1894 |
-
"eval_accuracy": 0.8231688630095004,
|
| 1895 |
-
"eval_loss": 0.5798885822296143,
|
| 1896 |
-
"eval_model_preparation_time": 0.0015,
|
| 1897 |
-
"eval_runtime": 52.3499,
|
| 1898 |
-
"eval_samples_per_second": 62.331,
|
| 1899 |
-
"eval_steps_per_second": 1.948,
|
| 1900 |
-
"step": 2100
|
| 1901 |
-
},
|
| 1902 |
-
{
|
| 1903 |
-
"epoch": 0.7667151162790697,
|
| 1904 |
-
"grad_norm": 25.42754364013672,
|
| 1905 |
-
"learning_rate": 2.336482558139535e-05,
|
| 1906 |
-
"loss": 0.6025,
|
| 1907 |
-
"step": 2110
|
| 1908 |
-
},
|
| 1909 |
-
{
|
| 1910 |
-
"epoch": 0.7703488372093024,
|
| 1911 |
-
"grad_norm": 17.46138572692871,
|
| 1912 |
-
"learning_rate": 2.3001453488372094e-05,
|
| 1913 |
-
"loss": 0.6702,
|
| 1914 |
-
"step": 2120
|
| 1915 |
-
},
|
| 1916 |
-
{
|
| 1917 |
-
"epoch": 0.7739825581395349,
|
| 1918 |
-
"grad_norm": 19.8096923828125,
|
| 1919 |
-
"learning_rate": 2.263808139534884e-05,
|
| 1920 |
-
"loss": 0.6543,
|
| 1921 |
-
"step": 2130
|
| 1922 |
-
},
|
| 1923 |
-
{
|
| 1924 |
-
"epoch": 0.7776162790697675,
|
| 1925 |
-
"grad_norm": 18.788450241088867,
|
| 1926 |
-
"learning_rate": 2.2274709302325585e-05,
|
| 1927 |
-
"loss": 0.704,
|
| 1928 |
-
"step": 2140
|
| 1929 |
-
},
|
| 1930 |
-
{
|
| 1931 |
-
"epoch": 0.78125,
|
| 1932 |
-
"grad_norm": 21.987895965576172,
|
| 1933 |
-
"learning_rate": 2.1911337209302325e-05,
|
| 1934 |
-
"loss": 0.6834,
|
| 1935 |
-
"step": 2150
|
| 1936 |
-
},
|
| 1937 |
-
{
|
| 1938 |
-
"epoch": 0.78125,
|
| 1939 |
-
"eval_accuracy": 0.8292981918479927,
|
| 1940 |
-
"eval_loss": 0.5684976577758789,
|
| 1941 |
-
"eval_model_preparation_time": 0.0015,
|
| 1942 |
-
"eval_runtime": 51.8943,
|
| 1943 |
-
"eval_samples_per_second": 62.878,
|
| 1944 |
-
"eval_steps_per_second": 1.966,
|
| 1945 |
-
"step": 2150
|
| 1946 |
-
},
|
| 1947 |
-
{
|
| 1948 |
-
"epoch": 0.7848837209302325,
|
| 1949 |
-
"grad_norm": 22.958097457885742,
|
| 1950 |
-
"learning_rate": 2.154796511627907e-05,
|
| 1951 |
-
"loss": 0.631,
|
| 1952 |
-
"step": 2160
|
| 1953 |
-
},
|
| 1954 |
-
{
|
| 1955 |
-
"epoch": 0.7885174418604651,
|
| 1956 |
-
"grad_norm": 20.562345504760742,
|
| 1957 |
-
"learning_rate": 2.1184593023255813e-05,
|
| 1958 |
-
"loss": 0.6287,
|
| 1959 |
-
"step": 2170
|
| 1960 |
-
},
|
| 1961 |
-
{
|
| 1962 |
-
"epoch": 0.7921511627906976,
|
| 1963 |
-
"grad_norm": 14.870391845703125,
|
| 1964 |
-
"learning_rate": 2.082122093023256e-05,
|
| 1965 |
-
"loss": 0.5629,
|
| 1966 |
-
"step": 2180
|
| 1967 |
-
},
|
| 1968 |
-
{
|
| 1969 |
-
"epoch": 0.7957848837209303,
|
| 1970 |
-
"grad_norm": 23.68880844116211,
|
| 1971 |
-
"learning_rate": 2.0457848837209304e-05,
|
| 1972 |
-
"loss": 0.6285,
|
| 1973 |
-
"step": 2190
|
| 1974 |
-
},
|
| 1975 |
-
{
|
| 1976 |
-
"epoch": 0.7994186046511628,
|
| 1977 |
-
"grad_norm": 23.51922035217285,
|
| 1978 |
-
"learning_rate": 2.0094476744186047e-05,
|
| 1979 |
-
"loss": 0.6258,
|
| 1980 |
-
"step": 2200
|
| 1981 |
-
},
|
| 1982 |
-
{
|
| 1983 |
-
"epoch": 0.7994186046511628,
|
| 1984 |
-
"eval_accuracy": 0.8240882623352743,
|
| 1985 |
-
"eval_loss": 0.5687205791473389,
|
| 1986 |
-
"eval_model_preparation_time": 0.0015,
|
| 1987 |
-
"eval_runtime": 51.3481,
|
| 1988 |
-
"eval_samples_per_second": 63.547,
|
| 1989 |
-
"eval_steps_per_second": 1.986,
|
| 1990 |
-
"step": 2200
|
| 1991 |
-
},
|
| 1992 |
-
{
|
| 1993 |
-
"epoch": 0.8030523255813954,
|
| 1994 |
-
"grad_norm": 18.42901611328125,
|
| 1995 |
-
"learning_rate": 1.973110465116279e-05,
|
| 1996 |
-
"loss": 0.6338,
|
| 1997 |
-
"step": 2210
|
| 1998 |
-
},
|
| 1999 |
-
{
|
| 2000 |
-
"epoch": 0.8066860465116279,
|
| 2001 |
-
"grad_norm": 24.76369857788086,
|
| 2002 |
-
"learning_rate": 1.936773255813954e-05,
|
| 2003 |
-
"loss": 0.6247,
|
| 2004 |
-
"step": 2220
|
| 2005 |
-
},
|
| 2006 |
-
{
|
| 2007 |
-
"epoch": 0.8103197674418605,
|
| 2008 |
-
"grad_norm": 21.530895233154297,
|
| 2009 |
-
"learning_rate": 1.9004360465116282e-05,
|
| 2010 |
-
"loss": 0.5696,
|
| 2011 |
-
"step": 2230
|
| 2012 |
-
},
|
| 2013 |
-
{
|
| 2014 |
-
"epoch": 0.813953488372093,
|
| 2015 |
-
"grad_norm": 24.415956497192383,
|
| 2016 |
-
"learning_rate": 1.8640988372093023e-05,
|
| 2017 |
-
"loss": 0.621,
|
| 2018 |
-
"step": 2240
|
| 2019 |
-
},
|
| 2020 |
-
{
|
| 2021 |
-
"epoch": 0.8175872093023255,
|
| 2022 |
-
"grad_norm": 24.22767448425293,
|
| 2023 |
-
"learning_rate": 1.8277616279069766e-05,
|
| 2024 |
-
"loss": 0.6685,
|
| 2025 |
-
"step": 2250
|
| 2026 |
-
},
|
| 2027 |
-
{
|
| 2028 |
-
"epoch": 0.8175872093023255,
|
| 2029 |
-
"eval_accuracy": 0.8243947287771989,
|
| 2030 |
-
"eval_loss": 0.5570237636566162,
|
| 2031 |
-
"eval_model_preparation_time": 0.0015,
|
| 2032 |
-
"eval_runtime": 52.4926,
|
| 2033 |
-
"eval_samples_per_second": 62.161,
|
| 2034 |
-
"eval_steps_per_second": 1.943,
|
| 2035 |
-
"step": 2250
|
| 2036 |
-
},
|
| 2037 |
-
{
|
| 2038 |
-
"epoch": 0.8212209302325582,
|
| 2039 |
-
"grad_norm": 15.582283973693848,
|
| 2040 |
-
"learning_rate": 1.7914244186046513e-05,
|
| 2041 |
-
"loss": 0.6792,
|
| 2042 |
-
"step": 2260
|
| 2043 |
-
},
|
| 2044 |
-
{
|
| 2045 |
-
"epoch": 0.8248546511627907,
|
| 2046 |
-
"grad_norm": 21.79721450805664,
|
| 2047 |
-
"learning_rate": 1.7550872093023257e-05,
|
| 2048 |
-
"loss": 0.5503,
|
| 2049 |
-
"step": 2270
|
| 2050 |
-
},
|
| 2051 |
-
{
|
| 2052 |
-
"epoch": 0.8284883720930233,
|
| 2053 |
-
"grad_norm": 17.022436141967773,
|
| 2054 |
-
"learning_rate": 1.71875e-05,
|
| 2055 |
-
"loss": 0.5733,
|
| 2056 |
-
"step": 2280
|
| 2057 |
-
},
|
| 2058 |
-
{
|
| 2059 |
-
"epoch": 0.8321220930232558,
|
| 2060 |
-
"grad_norm": 19.0545711517334,
|
| 2061 |
-
"learning_rate": 1.6824127906976745e-05,
|
| 2062 |
-
"loss": 0.5846,
|
| 2063 |
-
"step": 2290
|
| 2064 |
-
},
|
| 2065 |
-
{
|
| 2066 |
-
"epoch": 0.8357558139534884,
|
| 2067 |
-
"grad_norm": 23.020610809326172,
|
| 2068 |
-
"learning_rate": 1.646075581395349e-05,
|
| 2069 |
-
"loss": 0.6844,
|
| 2070 |
-
"step": 2300
|
| 2071 |
-
},
|
| 2072 |
-
{
|
| 2073 |
-
"epoch": 0.8357558139534884,
|
| 2074 |
-
"eval_accuracy": 0.8253141281029728,
|
| 2075 |
-
"eval_loss": 0.5579020977020264,
|
| 2076 |
-
"eval_model_preparation_time": 0.0015,
|
| 2077 |
-
"eval_runtime": 50.8057,
|
| 2078 |
-
"eval_samples_per_second": 64.225,
|
| 2079 |
-
"eval_steps_per_second": 2.008,
|
| 2080 |
-
"step": 2300
|
| 2081 |
-
},
|
| 2082 |
-
{
|
| 2083 |
-
"epoch": 0.8393895348837209,
|
| 2084 |
-
"grad_norm": 20.574384689331055,
|
| 2085 |
-
"learning_rate": 1.6097383720930236e-05,
|
| 2086 |
-
"loss": 0.6167,
|
| 2087 |
-
"step": 2310
|
| 2088 |
-
},
|
| 2089 |
-
{
|
| 2090 |
-
"epoch": 0.8430232558139535,
|
| 2091 |
-
"grad_norm": 28.64992332458496,
|
| 2092 |
-
"learning_rate": 1.5734011627906976e-05,
|
| 2093 |
-
"loss": 0.6587,
|
| 2094 |
-
"step": 2320
|
| 2095 |
-
},
|
| 2096 |
-
{
|
| 2097 |
-
"epoch": 0.846656976744186,
|
| 2098 |
-
"grad_norm": 15.830301284790039,
|
| 2099 |
-
"learning_rate": 1.537063953488372e-05,
|
| 2100 |
-
"loss": 0.6342,
|
| 2101 |
-
"step": 2330
|
| 2102 |
-
},
|
| 2103 |
-
{
|
| 2104 |
-
"epoch": 0.8502906976744186,
|
| 2105 |
-
"grad_norm": 18.624250411987305,
|
| 2106 |
-
"learning_rate": 1.5007267441860465e-05,
|
| 2107 |
-
"loss": 0.6572,
|
| 2108 |
-
"step": 2340
|
| 2109 |
-
},
|
| 2110 |
-
{
|
| 2111 |
-
"epoch": 0.8539244186046512,
|
| 2112 |
-
"grad_norm": 30.454252243041992,
|
| 2113 |
-
"learning_rate": 1.4643895348837211e-05,
|
| 2114 |
-
"loss": 0.6446,
|
| 2115 |
-
"step": 2350
|
| 2116 |
-
},
|
| 2117 |
-
{
|
| 2118 |
-
"epoch": 0.8539244186046512,
|
| 2119 |
-
"eval_accuracy": 0.8243947287771989,
|
| 2120 |
-
"eval_loss": 0.5529566407203674,
|
| 2121 |
-
"eval_model_preparation_time": 0.0015,
|
| 2122 |
-
"eval_runtime": 51.0771,
|
| 2123 |
-
"eval_samples_per_second": 63.884,
|
| 2124 |
-
"eval_steps_per_second": 1.997,
|
| 2125 |
-
"step": 2350
|
| 2126 |
-
},
|
| 2127 |
-
{
|
| 2128 |
-
"epoch": 0.8575581395348837,
|
| 2129 |
-
"grad_norm": 25.79448127746582,
|
| 2130 |
-
"learning_rate": 1.4280523255813955e-05,
|
| 2131 |
-
"loss": 0.6686,
|
| 2132 |
-
"step": 2360
|
| 2133 |
-
},
|
| 2134 |
-
{
|
| 2135 |
-
"epoch": 0.8611918604651163,
|
| 2136 |
-
"grad_norm": 17.485763549804688,
|
| 2137 |
-
"learning_rate": 1.3917151162790698e-05,
|
| 2138 |
-
"loss": 0.5882,
|
| 2139 |
-
"step": 2370
|
| 2140 |
-
},
|
| 2141 |
-
{
|
| 2142 |
-
"epoch": 0.8648255813953488,
|
| 2143 |
-
"grad_norm": 19.48297691345215,
|
| 2144 |
-
"learning_rate": 1.3553779069767442e-05,
|
| 2145 |
-
"loss": 0.6424,
|
| 2146 |
-
"step": 2380
|
| 2147 |
-
},
|
| 2148 |
-
{
|
| 2149 |
-
"epoch": 0.8684593023255814,
|
| 2150 |
-
"grad_norm": 28.619121551513672,
|
| 2151 |
-
"learning_rate": 1.3190406976744188e-05,
|
| 2152 |
-
"loss": 0.5695,
|
| 2153 |
-
"step": 2390
|
| 2154 |
-
},
|
| 2155 |
-
{
|
| 2156 |
-
"epoch": 0.872093023255814,
|
| 2157 |
-
"grad_norm": 16.906198501586914,
|
| 2158 |
-
"learning_rate": 1.2827034883720932e-05,
|
| 2159 |
-
"loss": 0.6243,
|
| 2160 |
-
"step": 2400
|
| 2161 |
-
},
|
| 2162 |
-
{
|
| 2163 |
-
"epoch": 0.872093023255814,
|
| 2164 |
-
"eval_accuracy": 0.8277658596383696,
|
| 2165 |
-
"eval_loss": 0.5536515712738037,
|
| 2166 |
-
"eval_model_preparation_time": 0.0015,
|
| 2167 |
-
"eval_runtime": 50.8517,
|
| 2168 |
-
"eval_samples_per_second": 64.167,
|
| 2169 |
-
"eval_steps_per_second": 2.006,
|
| 2170 |
-
"step": 2400
|
| 2171 |
-
},
|
| 2172 |
-
{
|
| 2173 |
-
"epoch": 0.8757267441860465,
|
| 2174 |
-
"grad_norm": 21.633602142333984,
|
| 2175 |
-
"learning_rate": 1.2463662790697675e-05,
|
| 2176 |
-
"loss": 0.5708,
|
| 2177 |
-
"step": 2410
|
| 2178 |
-
},
|
| 2179 |
-
{
|
| 2180 |
-
"epoch": 0.8793604651162791,
|
| 2181 |
-
"grad_norm": 28.101240158081055,
|
| 2182 |
-
"learning_rate": 1.2100290697674419e-05,
|
| 2183 |
-
"loss": 0.6923,
|
| 2184 |
-
"step": 2420
|
| 2185 |
-
},
|
| 2186 |
-
{
|
| 2187 |
-
"epoch": 0.8829941860465116,
|
| 2188 |
-
"grad_norm": 16.087495803833008,
|
| 2189 |
-
"learning_rate": 1.1736918604651163e-05,
|
| 2190 |
-
"loss": 0.4912,
|
| 2191 |
-
"step": 2430
|
| 2192 |
-
},
|
| 2193 |
-
{
|
| 2194 |
-
"epoch": 0.8866279069767442,
|
| 2195 |
-
"grad_norm": 18.913463592529297,
|
| 2196 |
-
"learning_rate": 1.1373546511627907e-05,
|
| 2197 |
-
"loss": 0.583,
|
| 2198 |
-
"step": 2440
|
| 2199 |
-
},
|
| 2200 |
-
{
|
| 2201 |
-
"epoch": 0.8902616279069767,
|
| 2202 |
-
"grad_norm": 26.900217056274414,
|
| 2203 |
-
"learning_rate": 1.1010174418604652e-05,
|
| 2204 |
-
"loss": 0.617,
|
| 2205 |
-
"step": 2450
|
| 2206 |
-
},
|
| 2207 |
-
{
|
| 2208 |
-
"epoch": 0.8902616279069767,
|
| 2209 |
-
"eval_accuracy": 0.8372663193380325,
|
| 2210 |
-
"eval_loss": 0.5327870845794678,
|
| 2211 |
-
"eval_model_preparation_time": 0.0015,
|
| 2212 |
-
"eval_runtime": 51.6187,
|
| 2213 |
-
"eval_samples_per_second": 63.214,
|
| 2214 |
-
"eval_steps_per_second": 1.976,
|
| 2215 |
-
"step": 2450
|
| 2216 |
-
},
|
| 2217 |
-
{
|
| 2218 |
-
"epoch": 0.8938953488372093,
|
| 2219 |
-
"grad_norm": 18.022111892700195,
|
| 2220 |
-
"learning_rate": 1.0646802325581396e-05,
|
| 2221 |
-
"loss": 0.547,
|
| 2222 |
-
"step": 2460
|
| 2223 |
-
},
|
| 2224 |
-
{
|
| 2225 |
-
"epoch": 0.8975290697674418,
|
| 2226 |
-
"grad_norm": 16.78557777404785,
|
| 2227 |
-
"learning_rate": 1.028343023255814e-05,
|
| 2228 |
-
"loss": 0.5687,
|
| 2229 |
-
"step": 2470
|
| 2230 |
-
},
|
| 2231 |
-
{
|
| 2232 |
-
"epoch": 0.9011627906976745,
|
| 2233 |
-
"grad_norm": 20.011295318603516,
|
| 2234 |
-
"learning_rate": 9.920058139534884e-06,
|
| 2235 |
-
"loss": 0.6218,
|
| 2236 |
-
"step": 2480
|
| 2237 |
-
},
|
| 2238 |
-
{
|
| 2239 |
-
"epoch": 0.904796511627907,
|
| 2240 |
-
"grad_norm": 22.754287719726562,
|
| 2241 |
-
"learning_rate": 9.556686046511629e-06,
|
| 2242 |
-
"loss": 0.6328,
|
| 2243 |
-
"step": 2490
|
| 2244 |
-
},
|
| 2245 |
-
{
|
| 2246 |
-
"epoch": 0.9084302325581395,
|
| 2247 |
-
"grad_norm": 19.715274810791016,
|
| 2248 |
-
"learning_rate": 9.193313953488373e-06,
|
| 2249 |
-
"loss": 0.5724,
|
| 2250 |
-
"step": 2500
|
| 2251 |
-
},
|
| 2252 |
-
{
|
| 2253 |
-
"epoch": 0.9084302325581395,
|
| 2254 |
-
"eval_accuracy": 0.840024517315354,
|
| 2255 |
-
"eval_loss": 0.5281281471252441,
|
| 2256 |
-
"eval_model_preparation_time": 0.0015,
|
| 2257 |
-
"eval_runtime": 52.2053,
|
| 2258 |
-
"eval_samples_per_second": 62.503,
|
| 2259 |
-
"eval_steps_per_second": 1.954,
|
| 2260 |
-
"step": 2500
|
| 2261 |
-
},
|
| 2262 |
-
{
|
| 2263 |
-
"epoch": 0.9120639534883721,
|
| 2264 |
-
"grad_norm": 19.64166831970215,
|
| 2265 |
-
"learning_rate": 8.829941860465117e-06,
|
| 2266 |
-
"loss": 0.5446,
|
| 2267 |
-
"step": 2510
|
| 2268 |
-
},
|
| 2269 |
-
{
|
| 2270 |
-
"epoch": 0.9156976744186046,
|
| 2271 |
-
"grad_norm": 19.133466720581055,
|
| 2272 |
-
"learning_rate": 8.46656976744186e-06,
|
| 2273 |
-
"loss": 0.569,
|
| 2274 |
-
"step": 2520
|
| 2275 |
-
},
|
| 2276 |
-
{
|
| 2277 |
-
"epoch": 0.9193313953488372,
|
| 2278 |
-
"grad_norm": 20.076690673828125,
|
| 2279 |
-
"learning_rate": 8.103197674418606e-06,
|
| 2280 |
-
"loss": 0.6545,
|
| 2281 |
-
"step": 2530
|
| 2282 |
-
},
|
| 2283 |
-
{
|
| 2284 |
-
"epoch": 0.9229651162790697,
|
| 2285 |
-
"grad_norm": 18.778846740722656,
|
| 2286 |
-
"learning_rate": 7.73982558139535e-06,
|
| 2287 |
-
"loss": 0.5915,
|
| 2288 |
-
"step": 2540
|
| 2289 |
-
},
|
| 2290 |
-
{
|
| 2291 |
-
"epoch": 0.9265988372093024,
|
| 2292 |
-
"grad_norm": 18.11453628540039,
|
| 2293 |
-
"learning_rate": 7.376453488372094e-06,
|
| 2294 |
-
"loss": 0.4931,
|
| 2295 |
-
"step": 2550
|
| 2296 |
-
},
|
| 2297 |
-
{
|
| 2298 |
-
"epoch": 0.9265988372093024,
|
| 2299 |
-
"eval_accuracy": 0.8440085810603739,
|
| 2300 |
-
"eval_loss": 0.5274325609207153,
|
| 2301 |
-
"eval_model_preparation_time": 0.0015,
|
| 2302 |
-
"eval_runtime": 52.3555,
|
| 2303 |
-
"eval_samples_per_second": 62.324,
|
| 2304 |
-
"eval_steps_per_second": 1.948,
|
| 2305 |
-
"step": 2550
|
| 2306 |
-
},
|
| 2307 |
-
{
|
| 2308 |
-
"epoch": 0.9302325581395349,
|
| 2309 |
-
"grad_norm": 26.267868041992188,
|
| 2310 |
-
"learning_rate": 7.013081395348837e-06,
|
| 2311 |
-
"loss": 0.5701,
|
| 2312 |
-
"step": 2560
|
| 2313 |
-
},
|
| 2314 |
-
{
|
| 2315 |
-
"epoch": 0.9338662790697675,
|
| 2316 |
-
"grad_norm": 34.12333679199219,
|
| 2317 |
-
"learning_rate": 6.649709302325581e-06,
|
| 2318 |
-
"loss": 0.5949,
|
| 2319 |
-
"step": 2570
|
| 2320 |
-
},
|
| 2321 |
-
{
|
| 2322 |
-
"epoch": 0.9375,
|
| 2323 |
-
"grad_norm": 18.76346778869629,
|
| 2324 |
-
"learning_rate": 6.286337209302326e-06,
|
| 2325 |
-
"loss": 0.5934,
|
| 2326 |
-
"step": 2580
|
| 2327 |
-
},
|
| 2328 |
-
{
|
| 2329 |
-
"epoch": 0.9411337209302325,
|
| 2330 |
-
"grad_norm": 28.602293014526367,
|
| 2331 |
-
"learning_rate": 5.92296511627907e-06,
|
| 2332 |
-
"loss": 0.5537,
|
| 2333 |
-
"step": 2590
|
| 2334 |
-
},
|
| 2335 |
-
{
|
| 2336 |
-
"epoch": 0.9447674418604651,
|
| 2337 |
-
"grad_norm": 24.983774185180664,
|
| 2338 |
-
"learning_rate": 5.559593023255814e-06,
|
| 2339 |
-
"loss": 0.6459,
|
| 2340 |
-
"step": 2600
|
| 2341 |
-
},
|
| 2342 |
-
{
|
| 2343 |
-
"epoch": 0.9447674418604651,
|
| 2344 |
-
"eval_accuracy": 0.8446215139442231,
|
| 2345 |
-
"eval_loss": 0.5270681977272034,
|
| 2346 |
-
"eval_model_preparation_time": 0.0015,
|
| 2347 |
-
"eval_runtime": 51.3715,
|
| 2348 |
-
"eval_samples_per_second": 63.518,
|
| 2349 |
-
"eval_steps_per_second": 1.986,
|
| 2350 |
-
"step": 2600
|
| 2351 |
-
},
|
| 2352 |
-
{
|
| 2353 |
-
"epoch": 0.9484011627906976,
|
| 2354 |
-
"grad_norm": 20.338668823242188,
|
| 2355 |
-
"learning_rate": 5.196220930232559e-06,
|
| 2356 |
-
"loss": 0.5579,
|
| 2357 |
-
"step": 2610
|
| 2358 |
-
},
|
| 2359 |
-
{
|
| 2360 |
-
"epoch": 0.9520348837209303,
|
| 2361 |
-
"grad_norm": 13.569022178649902,
|
| 2362 |
-
"learning_rate": 4.832848837209302e-06,
|
| 2363 |
-
"loss": 0.5295,
|
| 2364 |
-
"step": 2620
|
| 2365 |
-
},
|
| 2366 |
-
{
|
| 2367 |
-
"epoch": 0.9556686046511628,
|
| 2368 |
-
"grad_norm": 17.16480827331543,
|
| 2369 |
-
"learning_rate": 4.469476744186047e-06,
|
| 2370 |
-
"loss": 0.5583,
|
| 2371 |
-
"step": 2630
|
| 2372 |
-
},
|
| 2373 |
-
{
|
| 2374 |
-
"epoch": 0.9593023255813954,
|
| 2375 |
-
"grad_norm": 25.31192398071289,
|
| 2376 |
-
"learning_rate": 4.106104651162791e-06,
|
| 2377 |
-
"loss": 0.5767,
|
| 2378 |
-
"step": 2640
|
| 2379 |
-
},
|
| 2380 |
-
{
|
| 2381 |
-
"epoch": 0.9629360465116279,
|
| 2382 |
-
"grad_norm": 14.07887077331543,
|
| 2383 |
-
"learning_rate": 3.7427325581395346e-06,
|
| 2384 |
-
"loss": 0.5954,
|
| 2385 |
-
"step": 2650
|
| 2386 |
-
},
|
| 2387 |
-
{
|
| 2388 |
-
"epoch": 0.9629360465116279,
|
| 2389 |
-
"eval_accuracy": 0.8446215139442231,
|
| 2390 |
-
"eval_loss": 0.5231106281280518,
|
| 2391 |
-
"eval_model_preparation_time": 0.0015,
|
| 2392 |
-
"eval_runtime": 52.8556,
|
| 2393 |
-
"eval_samples_per_second": 61.734,
|
| 2394 |
-
"eval_steps_per_second": 1.93,
|
| 2395 |
-
"step": 2650
|
| 2396 |
-
},
|
| 2397 |
-
{
|
| 2398 |
-
"epoch": 0.9665697674418605,
|
| 2399 |
-
"grad_norm": 17.648242950439453,
|
| 2400 |
-
"learning_rate": 3.379360465116279e-06,
|
| 2401 |
-
"loss": 0.5344,
|
| 2402 |
-
"step": 2660
|
| 2403 |
-
},
|
| 2404 |
-
{
|
| 2405 |
-
"epoch": 0.970203488372093,
|
| 2406 |
-
"grad_norm": 15.185200691223145,
|
| 2407 |
-
"learning_rate": 3.0159883720930235e-06,
|
| 2408 |
-
"loss": 0.6055,
|
| 2409 |
-
"step": 2670
|
| 2410 |
-
},
|
| 2411 |
-
{
|
| 2412 |
-
"epoch": 0.9738372093023255,
|
| 2413 |
-
"grad_norm": 23.906478881835938,
|
| 2414 |
-
"learning_rate": 2.6526162790697672e-06,
|
| 2415 |
-
"loss": 0.5212,
|
| 2416 |
-
"step": 2680
|
| 2417 |
-
},
|
| 2418 |
-
{
|
| 2419 |
-
"epoch": 0.9774709302325582,
|
| 2420 |
-
"grad_norm": 22.67589569091797,
|
| 2421 |
-
"learning_rate": 2.2892441860465114e-06,
|
| 2422 |
-
"loss": 0.6287,
|
| 2423 |
-
"step": 2690
|
| 2424 |
-
},
|
| 2425 |
-
{
|
| 2426 |
-
"epoch": 0.9811046511627907,
|
| 2427 |
-
"grad_norm": 18.85926055908203,
|
| 2428 |
-
"learning_rate": 1.9258720930232557e-06,
|
| 2429 |
-
"loss": 0.5407,
|
| 2430 |
-
"step": 2700
|
| 2431 |
-
},
|
| 2432 |
-
{
|
| 2433 |
-
"epoch": 0.9811046511627907,
|
| 2434 |
-
"eval_accuracy": 0.8467667790376954,
|
| 2435 |
-
"eval_loss": 0.5167918801307678,
|
| 2436 |
-
"eval_model_preparation_time": 0.0015,
|
| 2437 |
-
"eval_runtime": 51.0533,
|
| 2438 |
-
"eval_samples_per_second": 63.914,
|
| 2439 |
-
"eval_steps_per_second": 1.998,
|
| 2440 |
-
"step": 2700
|
| 2441 |
-
},
|
| 2442 |
-
{
|
| 2443 |
-
"epoch": 0.9847383720930233,
|
| 2444 |
-
"grad_norm": 17.184297561645508,
|
| 2445 |
-
"learning_rate": 1.5625e-06,
|
| 2446 |
-
"loss": 0.653,
|
| 2447 |
-
"step": 2710
|
| 2448 |
-
},
|
| 2449 |
-
{
|
| 2450 |
-
"epoch": 0.9883720930232558,
|
| 2451 |
-
"grad_norm": 27.768354415893555,
|
| 2452 |
-
"learning_rate": 1.1991279069767443e-06,
|
| 2453 |
-
"loss": 0.5727,
|
| 2454 |
-
"step": 2720
|
| 2455 |
-
},
|
| 2456 |
-
{
|
| 2457 |
-
"epoch": 0.9920058139534884,
|
| 2458 |
-
"grad_norm": 22.3969783782959,
|
| 2459 |
-
"learning_rate": 8.357558139534884e-07,
|
| 2460 |
-
"loss": 0.603,
|
| 2461 |
-
"step": 2730
|
| 2462 |
-
},
|
| 2463 |
-
{
|
| 2464 |
-
"epoch": 0.9956395348837209,
|
| 2465 |
-
"grad_norm": 17.257413864135742,
|
| 2466 |
-
"learning_rate": 4.7238372093023254e-07,
|
| 2467 |
-
"loss": 0.5879,
|
| 2468 |
-
"step": 2740
|
| 2469 |
-
},
|
| 2470 |
-
{
|
| 2471 |
-
"epoch": 0.9992732558139535,
|
| 2472 |
-
"grad_norm": 28.563993453979492,
|
| 2473 |
-
"learning_rate": 1.0901162790697675e-07,
|
| 2474 |
-
"loss": 0.5729,
|
| 2475 |
-
"step": 2750
|
| 2476 |
-
},
|
| 2477 |
-
{
|
| 2478 |
-
"epoch": 0.9992732558139535,
|
| 2479 |
-
"eval_accuracy": 0.8479926448053938,
|
| 2480 |
-
"eval_loss": 0.5158767700195312,
|
| 2481 |
-
"eval_model_preparation_time": 0.0015,
|
| 2482 |
-
"eval_runtime": 51.352,
|
| 2483 |
-
"eval_samples_per_second": 63.542,
|
| 2484 |
-
"eval_steps_per_second": 1.986,
|
| 2485 |
-
"step": 2750
|
| 2486 |
-
}
|
| 2487 |
-
],
|
| 2488 |
-
"logging_steps": 10,
|
| 2489 |
-
"max_steps": 2752,
|
| 2490 |
-
"num_input_tokens_seen": 0,
|
| 2491 |
-
"num_train_epochs": 1,
|
| 2492 |
-
"save_steps": 50,
|
| 2493 |
-
"stateful_callbacks": {
|
| 2494 |
-
"TrainerControl": {
|
| 2495 |
-
"args": {
|
| 2496 |
-
"should_epoch_stop": false,
|
| 2497 |
-
"should_evaluate": false,
|
| 2498 |
-
"should_log": false,
|
| 2499 |
-
"should_save": true,
|
| 2500 |
-
"should_training_stop": true
|
| 2501 |
-
},
|
| 2502 |
-
"attributes": {}
|
| 2503 |
-
}
|
| 2504 |
-
},
|
| 2505 |
-
"total_flos": 9.055112855342285e+18,
|
| 2506 |
-
"train_batch_size": 32,
|
| 2507 |
-
"trial_name": null,
|
| 2508 |
-
"trial_params": null
|
| 2509 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|