forcemultiplier/GlassPolymorphicHTML-Qwen3-VL-4B-Instruct-adapter
025
1{2 "train_runtime": 15528.6205,3 "train_samples_per_second": 0.103,4 "train_steps_per_second": 0.103,5 "train_loss": 0.19463951266836374,6 "epoch": 1.0,7 "config": {8 "vein_name": "html_r64_v2",9 "start_step": 600,10 "end_step": 2200,11 "batch_size": 1,12 "grad_accum": 1,13 "lora_r": 64,14 "lora_alpha": 64,15 "warmup_steps": 10,16 "rs_lora": false,17 "learning_rate": 0.0002,18 "max_length": 23401,19 "dataset_path": "dataset.jsonl",20 "dataset_index_start": 1618,21 "dataset_index_end": 1436,22 "total_samples_processed": 500023 },24 "gpu_memory": {25 "peak_reserved_gb": 19.13926 },27 "step_by_step_metrics": [28 {29 "step": 601,30 "timestamp": "2025-12-28T08:58:29.750718",31 "elapsed_time": 24.035809755325317,32 "loss": 0.2155,33 "grad_norm": 0.1604655683040619,34 "learning_rate": 0.0,35 "epoch": 0.00062536 },37 {38 "step": 602,39 "timestamp": "2025-12-28T08:58:36.494748",40 "elapsed_time": 30.779838800430298,41 "loss": 0.152,42 "grad_norm": 0.1441534161567688,43 "learning_rate": 2e-05,44 "epoch": 0.0012545 },46 {47 "step": 603,48 "timestamp": "2025-12-28T08:58:46.390445",49 "elapsed_time": 40.67553472518921,50 "loss": 0.1768,51 "grad_norm": 0.14501173794269562,52 "learning_rate": 4e-05,53 "epoch": 0.00187554 },55 {56 "step": 604,57 "timestamp": "2025-12-28T08:58:52.949267",58 "elapsed_time": 47.234357595443726,59 "loss": 0.3154,60 "grad_norm": 0.20344674587249756,61 "learning_rate": 6e-05,62 "epoch": 0.002563 },64 {65 "step": 605,66 "timestamp": "2025-12-28T08:59:02.976637",67 "elapsed_time": 57.26172733306885,68 "loss": 0.1981,69 "grad_norm": 0.1389472484588623,70 "learning_rate": 8e-05,71 "epoch": 0.00312572 },73 {74 "step": 606,75 "timestamp": "2025-12-28T08:59:14.217365",76 "elapsed_time": 68.50245547294617,77 "loss": 0.1454,78 "grad_norm": 0.12427599728107452,79 "learning_rate": 0.0001,80 "epoch": 0.0037581 },82 {83 "step": 607,84 "timestamp": "2025-12-28T08:59:19.569352",85 "elapsed_time": 73.85444259643555,86 "loss": 0.3674,87 "grad_norm": 0.21498622000217438,88 "learning_rate": 0.00012,89 "epoch": 0.00437590 },91 {92 "step": 608,93 "timestamp": "2025-12-28T08:59:32.803346",94 "elapsed_time": 87.08843612670898,95 "loss": 0.1358,96 "grad_norm": 0.1065230667591095,97 "learning_rate": 0.00014,98 "epoch": 0.00599 },100 {101 "step": 609,102 "timestamp": "2025-12-28T08:59:43.029459",103 "elapsed_time": 97.31454968452454,104 "loss": 0.1995,105 "grad_norm": 0.19915856420993805,106 "learning_rate": 0.00016,107 "epoch": 0.005625108 },109 {110 "step": 610,111 "timestamp": "2025-12-28T08:59:47.972807",112 "elapsed_time": 102.25789737701416,113 "loss": 0.2193,114 "grad_norm": 0.18390510976314545,115 "learning_rate": 0.00018,116 "epoch": 0.00625117 },118 {119 "step": 611,120 "timestamp": "2025-12-28T08:59:56.025895",121 "elapsed_time": 110.31098580360413,122 "loss": 0.1661,123 "grad_norm": 0.14340169727802277,124 "learning_rate": 0.0002,125 "epoch": 0.006875126 },127 {128 "step": 612,129 "timestamp": "2025-12-28T09:00:04.192186",130 "elapsed_time": 118.47727656364441,131 "loss": 0.1867,132 "grad_norm": 0.17027480900287628,133 "learning_rate": 0.000199874213836478,134 "epoch": 0.0075135 },136 {137 "step": 613,138 "timestamp": "2025-12-28T09:00:15.363335",139 "elapsed_time": 129.64842581748962,140 "loss": 0.1322,141 "grad_norm": 0.12804803252220154,142 "learning_rate": 0.000199748427672956,143 "epoch": 0.008125144 },145 {146 "step": 614,147 "timestamp": "2025-12-28T09:00:22.801954",148 "elapsed_time": 137.0870442390442,149 "loss": 0.3998,150 "grad_norm": 0.2402307242155075,151 "learning_rate": 0.00019962264150943397,152 "epoch": 0.00875153 },154 {155 "step": 615,156 "timestamp": "2025-12-28T09:00:41.397275",157 "elapsed_time": 155.68236541748047,158 "loss": 0.167,159 "grad_norm": 0.12692536413669586,160 "learning_rate": 0.00019949685534591195,161 "epoch": 0.009375162 },163 {164 "step": 616,165 "timestamp": "2025-12-28T09:00:57.925605",166 "elapsed_time": 172.2106957435608,167 "loss": 0.1226,168 "grad_norm": 0.1139947846531868,169 "learning_rate": 0.00019937106918238996,170 "epoch": 0.01171 },172 {173 "step": 617,174 "timestamp": "2025-12-28T09:01:03.902990",175 "elapsed_time": 178.1880807876587,176 "loss": 0.2534,177 "grad_norm": 0.2593400478363037,178 "learning_rate": 0.00019924528301886794,179 "epoch": 0.010625180 },181 {182 "step": 618,183 "timestamp": "2025-12-28T09:01:19.300000",184 "elapsed_time": 193.58509039878845,185 "loss": 0.1422,186 "grad_norm": 0.12689131498336792,187 "learning_rate": 0.00019911949685534592,188 "epoch": 0.01125189 },190 {191 "step": 619,192 "timestamp": "2025-12-28T09:01:25.737299",193 "elapsed_time": 200.0223891735077,194 "loss": 0.1783,195 "grad_norm": 0.16301578283309937,196 "learning_rate": 0.0001989937106918239,197 "epoch": 0.011875198 },199 {200 "step": 620,201 "timestamp": "2025-12-28T09:01:38.363267",202 "elapsed_time": 212.64835739135742,203 "loss": 0.1295,204 "grad_norm": 0.13712646067142487,205 "learning_rate": 0.0001988679245283019,206 "epoch": 0.0125207 },208 {209 "step": 621,210 "timestamp": "2025-12-28T09:01:43.657825",211 "elapsed_time": 217.9429154396057,212 "loss": 0.2815,213 "grad_norm": 0.21860435605049133,214 "learning_rate": 0.00019874213836477988,215 "epoch": 0.013125216 },217 {218 "step": 622,219 "timestamp": "2025-12-28T09:01:52.793187",220 "elapsed_time": 227.07827711105347,221 "loss": 0.3943,222 "grad_norm": 0.20962341129779816,223 "learning_rate": 0.00019861635220125786,224 "epoch": 0.01375225 },226 {227 "step": 623,228 "timestamp": "2025-12-28T09:02:00.534713",229 "elapsed_time": 234.81980347633362,230 "loss": 0.3958,231 "grad_norm": 0.17121204733848572,232 "learning_rate": 0.00019849056603773587,233 "epoch": 0.014375234 },235 {236 "step": 624,237 "timestamp": "2025-12-28T09:02:09.703390",238 "elapsed_time": 243.98848390579224,239 "loss": 0.2354,240 "grad_norm": 0.16160890460014343,241 "learning_rate": 0.00019836477987421385,242 "epoch": 0.015243 },244 {245 "step": 625,246 "timestamp": "2025-12-28T09:02:15.193169",247 "elapsed_time": 249.47825932502747,248 "loss": 0.2254,249 "grad_norm": 0.2050420343875885,250 "learning_rate": 0.00019823899371069183,251 "epoch": 0.015625252 },253 {254 "step": 626,255 "timestamp": "2025-12-28T09:02:23.621480",256 "elapsed_time": 257.9065706729889,257 "loss": 0.3533,258 "grad_norm": 0.16951978206634521,259 "learning_rate": 0.00019811320754716983,260 "epoch": 0.01625261 },262 {263 "step": 627,264 "timestamp": "2025-12-28T09:02:40.925797",265 "elapsed_time": 275.21088790893555,266 "loss": 0.1368,267 "grad_norm": 0.12023195624351501,268 "learning_rate": 0.0001979874213836478,269 "epoch": 0.016875270 },271 {272 "step": 628,273 "timestamp": "2025-12-28T09:02:47.264513",274 "elapsed_time": 281.54960775375366,275 "loss": 0.1796,276 "grad_norm": 0.3685634434223175,277 "learning_rate": 0.0001978616352201258,278 "epoch": 0.0175279 },280 {281 "step": 629,282 "timestamp": "2025-12-28T09:02:54.630161",283 "elapsed_time": 288.9152555465698,284 "loss": 0.1811,285 "grad_norm": 0.1793571263551712,286 "learning_rate": 0.0001977358490566038,287 "epoch": 0.018125288 },289 {290 "step": 630,291 "timestamp": "2025-12-28T09:03:01.180041",292 "elapsed_time": 295.4651312828064,293 "loss": 0.2804,294 "grad_norm": 0.23330993950366974,295 "learning_rate": 0.00019761006289308177,296 "epoch": 0.01875297 },298 {299 "step": 631,300 "timestamp": "2025-12-28T09:03:11.837408",301 "elapsed_time": 306.12249875068665,302 "loss": 0.2404,303 "grad_norm": 0.20730850100517273,304 "learning_rate": 0.00019748427672955975,305 "epoch": 0.019375306 },307 {308 "step": 632,309 "timestamp": "2025-12-28T09:03:16.778563",310 "elapsed_time": 311.0636534690857,311 "loss": 0.3396,312 "grad_norm": 0.22279325127601624,313 "learning_rate": 0.00019735849056603773,314 "epoch": 0.02315 },316 {317 "step": 633,318 "timestamp": "2025-12-28T09:03:25.959314",319 "elapsed_time": 320.2444043159485,320 "loss": 0.161,321 "grad_norm": 0.17951494455337524,322 "learning_rate": 0.00019723270440251574,323 "epoch": 0.020625324 },325 {326 "step": 634,327 "timestamp": "2025-12-28T09:03:42.789283",328 "elapsed_time": 337.07437324523926,329 "loss": 0.1691,330 "grad_norm": 0.12446315586566925,331 "learning_rate": 0.00019710691823899372,332 "epoch": 0.02125333 },334 {335 "step": 635,336 "timestamp": "2025-12-28T09:03:54.312342",337 "elapsed_time": 348.5974371433258,338 "loss": 0.1439,339 "grad_norm": 0.19256795942783356,340 "learning_rate": 0.0001969811320754717,341 "epoch": 0.021875342 },343 {344 "step": 636,345 "timestamp": "2025-12-28T09:04:03.177467",346 "elapsed_time": 357.46255707740784,347 "loss": 0.2008,348 "grad_norm": 0.13904313743114471,349 "learning_rate": 0.0001968553459119497,350 "epoch": 0.0225351 },352 {353 "step": 637,354 "timestamp": "2025-12-28T09:04:10.990148",355 "elapsed_time": 365.2752380371094,356 "loss": 0.1878,357 "grad_norm": 0.1624336838722229,358 "learning_rate": 0.00019672955974842768,359 "epoch": 0.023125360 },361 {362 "step": 638,363 "timestamp": "2025-12-28T09:04:17.546438",364 "elapsed_time": 371.83152866363525,365 "loss": 0.1937,366 "grad_norm": 0.17041485011577606,367 "learning_rate": 0.00019660377358490566,368 "epoch": 0.02375369 },370 {371 "step": 639,372 "timestamp": "2025-12-28T09:04:21.596846",373 "elapsed_time": 375.88193678855896,374 "loss": 0.2582,375 "grad_norm": 0.20617352426052094,376 "learning_rate": 0.00019647798742138367,377 "epoch": 0.024375378 },379 {380 "step": 640,381 "timestamp": "2025-12-28T09:04:32.606180",382 "elapsed_time": 386.8912706375122,383 "loss": 0.1758,384 "grad_norm": 0.1377355009317398,385 "learning_rate": 0.00019635220125786165,386 "epoch": 0.025387 },388 {389 "step": 641,390 "timestamp": "2025-12-28T09:04:43.506700",391 "elapsed_time": 397.7917902469635,392 "loss": 0.3234,393 "grad_norm": 0.1705474555492401,394 "learning_rate": 0.00019622641509433963,395 "epoch": 0.025625396 },397 {398 "step": 642,399 "timestamp": "2025-12-28T09:04:51.282799",400 "elapsed_time": 405.5678901672363,401 "loss": 0.2184,402 "grad_norm": 0.2311810404062271,403 "learning_rate": 0.00019610062893081763,404 "epoch": 0.02625405 },406 {407 "step": 643,408 "timestamp": "2025-12-28T09:04:57.361632",409 "elapsed_time": 411.6467225551605,410 "loss": 0.188,411 "grad_norm": 0.1845218986272812,412 "learning_rate": 0.0001959748427672956,413 "epoch": 0.026875414 },415 {416 "step": 644,417 "timestamp": "2025-12-28T09:05:06.307667",418 "elapsed_time": 420.5927574634552,419 "loss": 0.2218,420 "grad_norm": 0.18984770774841309,421 "learning_rate": 0.0001958490566037736,422 "epoch": 0.0275423 },424 {425 "step": 645,426 "timestamp": "2025-12-28T09:05:20.346611",427 "elapsed_time": 434.6317012310028,428 "loss": 0.1774,429 "grad_norm": 0.1433676928281784,430 "learning_rate": 0.00019572327044025157,431 "epoch": 0.028125432 },433 {434 "step": 646,435 "timestamp": "2025-12-28T09:05:25.128238",436 "elapsed_time": 439.4133291244507,437 "loss": 0.3369,438 "grad_norm": 0.22627809643745422,439 "learning_rate": 0.00019559748427672958,440 "epoch": 0.02875441 },442 {443 "step": 647,444 "timestamp": "2025-12-28T09:05:36.797870",445 "elapsed_time": 451.08296036720276,446 "loss": 0.1735,447 "grad_norm": 0.16844865679740906,448 "learning_rate": 0.00019547169811320755,449 "epoch": 0.029375450 },451 {452 "step": 648,453 "timestamp": "2025-12-28T09:05:57.683316",454 "elapsed_time": 471.96840620040894,455 "loss": 0.1199,456 "grad_norm": 0.11961396783590317,457 "learning_rate": 0.00019534591194968553,458 "epoch": 0.03459 },460 {461 "step": 649,462 "timestamp": "2025-12-28T09:06:05.657286",463 "elapsed_time": 479.9423773288727,464 "loss": 0.2306,465 "grad_norm": 0.1685563325881958,466 "learning_rate": 0.00019522012578616354,467 "epoch": 0.030625468 },469 {470 "step": 650,471 "timestamp": "2025-12-28T09:06:20.462627",472 "elapsed_time": 494.7477180957794,473 "loss": 0.1896,474 "grad_norm": 0.12992839515209198,475 "learning_rate": 0.00019509433962264152,476 "epoch": 0.03125477 },478 {479 "step": 651,480 "timestamp": "2025-12-28T09:06:31.640433",481 "elapsed_time": 505.92552399635315,482 "loss": 0.135,483 "grad_norm": 0.12081814557313919,484 "learning_rate": 0.0001949685534591195,485 "epoch": 0.031875486 },487 {488 "step": 652,489 "timestamp": "2025-12-28T09:06:42.823577",490 "elapsed_time": 517.1086673736572,491 "loss": 0.1369,492 "grad_norm": 0.11642343550920486,493 "learning_rate": 0.0001948427672955975,494 "epoch": 0.0325495 },496 {497 "step": 653,498 "timestamp": "2025-12-28T09:06:51.916795",499 "elapsed_time": 526.2018857002258,500 "loss": 0.1889,501 "grad_norm": 0.13910572230815887,502 "learning_rate": 0.00019471698113207548,503 "epoch": 0.033125504 },505 {506 "step": 654,507 "timestamp": "2025-12-28T09:07:02.155700",508 "elapsed_time": 536.4407908916473,509 "loss": 0.3567,510 "grad_norm": 0.1917208731174469,511 "learning_rate": 0.00019459119496855346,512 "epoch": 0.03375513 },514 {515 "step": 655,516 "timestamp": "2025-12-28T09:07:15.706369",517 "elapsed_time": 549.9914598464966,518 "loss": 0.1709,519 "grad_norm": 0.12028059363365173,520 "learning_rate": 0.00019446540880503147,521 "epoch": 0.034375522 },523 {524 "step": 656,525 "timestamp": "2025-12-28T09:07:32.250659",526 "elapsed_time": 566.535749912262,527 "loss": 0.1228,528 "grad_norm": 0.19263313710689545,529 "learning_rate": 0.00019433962264150945,530 "epoch": 0.035531 },532 {533 "step": 657,534 "timestamp": "2025-12-28T09:07:39.316479",535 "elapsed_time": 573.601569890976,536 "loss": 0.2289,537 "grad_norm": 0.2995343506336212,538 "learning_rate": 0.00019421383647798743,539 "epoch": 0.035625540 },541 {542 "step": 658,543 "timestamp": "2025-12-28T09:07:54.181478",544 "elapsed_time": 588.4665679931641,545 "loss": 0.1498,546 "grad_norm": 0.13047035038471222,547 "learning_rate": 0.00019408805031446543,548 "epoch": 0.03625549 },550 {551 "step": 659,552 "timestamp": "2025-12-28T09:08:01.427506",553 "elapsed_time": 595.7125968933105,554 "loss": 0.1957,555 "grad_norm": 0.16221193969249725,556 "learning_rate": 0.0001939622641509434,557 "epoch": 0.036875558 },559 {560 "step": 660,561 "timestamp": "2025-12-28T09:08:07.362296",562 "elapsed_time": 601.6473863124847,563 "loss": 0.1755,564 "grad_norm": 0.1594441831111908,565 "learning_rate": 0.0001938364779874214,566 "epoch": 0.0375567 },568 {569 "step": 661,570 "timestamp": "2025-12-28T09:08:13.438049",571 "elapsed_time": 607.7231397628784,572 "loss": 0.2449,573 "grad_norm": 0.18605917692184448,574 "learning_rate": 0.00019371069182389937,575 "epoch": 0.038125576 },577 {578 "step": 662,579 "timestamp": "2025-12-28T09:08:25.983999",580 "elapsed_time": 620.2690892219543,581 "loss": 0.1445,582 "grad_norm": 0.11945810914039612,583 "learning_rate": 0.00019358490566037738,584 "epoch": 0.03875585 },586 {587 "step": 663,588 "timestamp": "2025-12-28T09:08:34.320553",589 "elapsed_time": 628.6056432723999,590 "loss": 0.1952,591 "grad_norm": 0.15212717652320862,592 "learning_rate": 0.00019345911949685536,593 "epoch": 0.039375594 },595 {596 "step": 664,597 "timestamp": "2025-12-28T09:08:47.204012",598 "elapsed_time": 641.4891028404236,599 "loss": 0.1264,600 "grad_norm": 0.1063343733549118,601 "learning_rate": 0.00019333333333333333,602 "epoch": 0.04603 },604 {605 "step": 665,606 "timestamp": "2025-12-28T09:08:55.268548",607 "elapsed_time": 649.5536382198334,608 "loss": 0.1998,609 "grad_norm": 0.1476004421710968,610 "learning_rate": 0.00019320754716981134,611 "epoch": 0.040625612 },613 {614 "step": 666,615 "timestamp": "2025-12-28T09:09:11.683318",616 "elapsed_time": 665.9684083461761,617 "loss": 0.1221,618 "grad_norm": 0.1132006123661995,619 "learning_rate": 0.00019308176100628932,620 "epoch": 0.04125621 },622 {623 "step": 667,624 "timestamp": "2025-12-28T09:09:22.208240",625 "elapsed_time": 676.493331193924,626 "loss": 0.1504,627 "grad_norm": 0.13121221959590912,628 "learning_rate": 0.0001929559748427673,629 "epoch": 0.041875630 },631 {632 "step": 668,633 "timestamp": "2025-12-28T09:09:42.700506",634 "elapsed_time": 696.9855964183807,635 "loss": 0.121,636 "grad_norm": 0.0900096669793129,637 "learning_rate": 0.0001928301886792453,638 "epoch": 0.0425639 },640 {641 "step": 669,642 "timestamp": "2025-12-28T09:09:57.623005",643 "elapsed_time": 711.9080958366394,644 "loss": 0.1276,645 "grad_norm": 0.11430996656417847,646 "learning_rate": 0.00019270440251572328,647 "epoch": 0.043125648 },649 {650 "step": 670,651 "timestamp": "2025-12-28T09:10:04.247302",652 "elapsed_time": 718.5323920249939,653 "loss": 0.1923,654 "grad_norm": 0.19039106369018555,655 "learning_rate": 0.00019257861635220126,656 "epoch": 0.04375657 },658 {659 "step": 671,660 "timestamp": "2025-12-28T09:10:16.730363",661 "elapsed_time": 731.0154540538788,662 "loss": 0.314,663 "grad_norm": 0.1691213995218277,664 "learning_rate": 0.00019245283018867927,665 "epoch": 0.044375666 },667 {668 "step": 672,669 "timestamp": "2025-12-28T09:10:26.112523",670 "elapsed_time": 740.3976130485535,671 "loss": 0.164,672 "grad_norm": 0.13402487337589264,673 "learning_rate": 0.00019232704402515725,674 "epoch": 0.045675 },676 {677 "step": 673,678 "timestamp": "2025-12-28T09:10:34.372277",679 "elapsed_time": 748.6573669910431,680 "loss": 0.1849,681 "grad_norm": 0.14694516360759735,682 "learning_rate": 0.00019220125786163523,683 "epoch": 0.045625684 },685 {686 "step": 674,687 "timestamp": "2025-12-28T09:10:44.792607",688 "elapsed_time": 759.0776975154877,689 "loss": 0.1962,690 "grad_norm": 0.15182200074195862,691 "learning_rate": 0.0001920754716981132,692 "epoch": 0.04625693 },694 {695 "step": 675,696 "timestamp": "2025-12-28T09:10:54.996775",697 "elapsed_time": 769.2818658351898,698 "loss": 0.1313,699 "grad_norm": 0.11995584517717361,700 "learning_rate": 0.0001919496855345912,701 "epoch": 0.046875702 },703 {704 "step": 676,705 "timestamp": "2025-12-28T09:11:03.629001",706 "elapsed_time": 777.9140913486481,707 "loss": 0.2438,708 "grad_norm": 0.14396265149116516,709 "learning_rate": 0.0001918238993710692,710 "epoch": 0.0475711 },712 {713 "step": 677,714 "timestamp": "2025-12-28T09:11:12.607355",715 "elapsed_time": 786.8924453258514,716 "loss": 0.2567,717 "grad_norm": 0.1717308908700943,718 "learning_rate": 0.00019169811320754717,719 "epoch": 0.048125720 },721 {722 "step": 678,723 "timestamp": "2025-12-28T09:11:25.911563",724 "elapsed_time": 800.196653842926,725 "loss": 0.1644,726 "grad_norm": 0.14998085796833038,727 "learning_rate": 0.00019157232704402518,728 "epoch": 0.04875729 },730 {731 "step": 679,732 "timestamp": "2025-12-28T09:11:33.380615",733 "elapsed_time": 807.6657054424286,734 "loss": 0.3003,735 "grad_norm": 0.16212862730026245,736 "learning_rate": 0.00019144654088050316,737 "epoch": 0.049375738 },739 {740 "step": 680,741 "timestamp": "2025-12-28T09:11:39.286109",742 "elapsed_time": 813.5711998939514,743 "loss": 0.261,744 "grad_norm": 0.19972242414951324,745 "learning_rate": 0.00019132075471698114,746 "epoch": 0.05747 },748 {749 "step": 681,750 "timestamp": "2025-12-28T09:11:48.163985",751 "elapsed_time": 822.4490756988525,752 "loss": 0.3926,753 "grad_norm": 0.17470583319664001,754 "learning_rate": 0.00019119496855345914,755 "epoch": 0.050625756 },757 {758 "step": 682,759 "timestamp": "2025-12-28T09:12:01.357382",760 "elapsed_time": 835.6424729824066,761 "loss": 0.1516,762 "grad_norm": 0.1337703913450241,763 "learning_rate": 0.00019106918238993712,764 "epoch": 0.05125765 },766 {767 "step": 683,768 "timestamp": "2025-12-28T09:12:11.393661",769 "elapsed_time": 845.678751707077,770 "loss": 0.2966,771 "grad_norm": 0.14767307043075562,772 "learning_rate": 0.0001909433962264151,773 "epoch": 0.051875774 },775 {776 "step": 684,777 "timestamp": "2025-12-28T09:12:17.843729",778 "elapsed_time": 852.1288199424744,779 "loss": 0.217,780 "grad_norm": 0.16958969831466675,781 "learning_rate": 0.0001908176100628931,782 "epoch": 0.0525783 },784 {785 "step": 685,786 "timestamp": "2025-12-28T09:12:25.829441",787 "elapsed_time": 860.1145317554474,788 "loss": 0.1656,789 "grad_norm": 0.14111389219760895,790 "learning_rate": 0.00019069182389937108,791 "epoch": 0.053125792 },793 {794 "step": 686,795 "timestamp": "2025-12-28T09:12:37.674364",796 "elapsed_time": 871.9594547748566,797 "loss": 0.1438,798 "grad_norm": 0.11669319868087769,799 "learning_rate": 0.00019056603773584906,800 "epoch": 0.05375801 },802 {803 "step": 687,804 "timestamp": "2025-12-28T09:12:56.652637",805 "elapsed_time": 890.9377274513245,806 "loss": 0.1478,807 "grad_norm": 0.12338529527187347,808 "learning_rate": 0.00019044025157232704,809 "epoch": 0.054375810 },811 {812 "step": 688,813 "timestamp": "2025-12-28T09:13:02.953778",814 "elapsed_time": 897.2388682365417,815 "loss": 0.198,816 "grad_norm": 0.1538494974374771,817 "learning_rate": 0.00019031446540880505,818 "epoch": 0.055819 },820 {821 "step": 689,822 "timestamp": "2025-12-28T09:13:11.878858",823 "elapsed_time": 906.1639485359192,824 "loss": 0.1424,825 "grad_norm": 0.12444575875997543,826 "learning_rate": 0.00019018867924528303,827 "epoch": 0.055625828 },829 {830 "step": 690,831 "timestamp": "2025-12-28T09:13:20.334671",832 "elapsed_time": 914.61976146698,833 "loss": 0.1823,834 "grad_norm": 0.19447259604930878,835 "learning_rate": 0.000190062893081761,836 "epoch": 0.05625837 },838 {839 "step": 691,840 "timestamp": "2025-12-28T09:13:27.616304",841 "elapsed_time": 921.9013941287994,842 "loss": 0.1547,843 "grad_norm": 0.14511334896087646,844 "learning_rate": 0.00018993710691823901,845 "epoch": 0.056875846 },847 {848 "step": 692,849 "timestamp": "2025-12-28T09:13:41.557565",850 "elapsed_time": 935.8426558971405,851 "loss": 0.1594,852 "grad_norm": 0.11656054854393005,853 "learning_rate": 0.000189811320754717,854 "epoch": 0.0575855 },856 {857 "step": 693,858 "timestamp": "2025-12-28T09:13:51.373998",859 "elapsed_time": 945.6590890884399,860 "loss": 0.2355,861 "grad_norm": 0.1568254977464676,862 "learning_rate": 0.00018968553459119497,863 "epoch": 0.058125864 },865 {866 "step": 694,867 "timestamp": "2025-12-28T09:14:06.517264",868 "elapsed_time": 960.8023540973663,869 "loss": 0.2098,870 "grad_norm": 0.12919512391090393,871 "learning_rate": 0.00018955974842767298,872 "epoch": 0.05875873 },874 {875 "step": 695,876 "timestamp": "2025-12-28T09:14:14.033362",877 "elapsed_time": 968.3184523582458,878 "loss": 0.2264,879 "grad_norm": 0.21954892575740814,880 "learning_rate": 0.00018943396226415096,881 "epoch": 0.059375882 },883 {884 "step": 696,885 "timestamp": "2025-12-28T09:14:23.154345",886 "elapsed_time": 977.4394352436066,887 "loss": 0.197,888 "grad_norm": 0.1527150720357895,889 "learning_rate": 0.00018930817610062894,890 "epoch": 0.06891 },892 {893 "step": 697,894 "timestamp": "2025-12-28T09:14:30.973861",895 "elapsed_time": 985.258951663971,896 "loss": 0.2027,897 "grad_norm": 0.16911649703979492,898 "learning_rate": 0.00018918238993710694,899 "epoch": 0.060625900 },901 {902 "step": 698,903 "timestamp": "2025-12-28T09:14:38.748666",904 "elapsed_time": 993.0337567329407,905 "loss": 0.2625,906 "grad_norm": 0.15294122695922852,907 "learning_rate": 0.00018905660377358492,908 "epoch": 0.06125909 },910 {911 "step": 699,912 "timestamp": "2025-12-28T09:14:46.484732",913 "elapsed_time": 1000.7698221206665,914 "loss": 0.2257,915 "grad_norm": 0.16110914945602417,916 "learning_rate": 0.0001889308176100629,917 "epoch": 0.061875918 },919 {920 "step": 700,921 "timestamp": "2025-12-28T09:14:52.017443",922 "elapsed_time": 1006.3025336265564,923 "loss": 0.2229,924 "grad_norm": 0.19415181875228882,925 "learning_rate": 0.00018880503144654088,926 "epoch": 0.0625927 },928 {929 "step": 701,930 "timestamp": "2025-12-28T09:15:00.051403",931 "elapsed_time": 1014.336493730545,932 "loss": 0.1913,933 "grad_norm": 0.1673995554447174,934 "learning_rate": 0.00018867924528301889,935 "epoch": 0.063125936 },937 {938 "step": 702,939 "timestamp": "2025-12-28T09:15:16.601964",940 "elapsed_time": 1030.8870537281036,941 "loss": 0.1377,942 "grad_norm": 0.09899748116731644,943 "learning_rate": 0.00018855345911949686,944 "epoch": 0.06375945 },946 {947 "step": 703,948 "timestamp": "2025-12-28T09:15:30.488977",949 "elapsed_time": 1044.7740678787231,950 "loss": 0.1405,951 "grad_norm": 0.11365586519241333,952 "learning_rate": 0.00018842767295597484,953 "epoch": 0.064375954 },955 {956 "step": 704,957 "timestamp": "2025-12-28T09:15:36.750160",958 "elapsed_time": 1051.0352516174316,959 "loss": 0.1852,960 "grad_norm": 0.1651289463043213,961 "learning_rate": 0.00018830188679245285,962 "epoch": 0.065963 },964 {965 "step": 705,966 "timestamp": "2025-12-28T09:15:49.379817",967 "elapsed_time": 1063.6649072170258,968 "loss": 0.1602,969 "grad_norm": 0.12038940191268921,970 "learning_rate": 0.00018817610062893083,971 "epoch": 0.065625972 },973 {974 "step": 706,975 "timestamp": "2025-12-28T09:15:54.708518",976 "elapsed_time": 1068.9936089515686,977 "loss": 0.3003,978 "grad_norm": 0.26949650049209595,979 "learning_rate": 0.0001880503144654088,980 "epoch": 0.06625981 },982 {983 "step": 707,984 "timestamp": "2025-12-28T09:16:05.981736",985 "elapsed_time": 1080.2668268680573,986 "loss": 0.1754,987 "grad_norm": 0.133348748087883,988 "learning_rate": 0.00018792452830188681,989 "epoch": 0.066875990 },991 {992 "step": 708,993 "timestamp": "2025-12-28T09:16:11.541142",994 "elapsed_time": 1085.8262326717377,995 "loss": 0.1986,996 "grad_norm": 0.1636824756860733,997 "learning_rate": 0.0001877987421383648,998 "epoch": 0.0675999 },1000 {1001 "step": 709,1002 "timestamp": "2025-12-28T09:16:17.744602",1003 "elapsed_time": 1092.0296926498413,1004 "loss": 0.2282,1005 "grad_norm": 0.18413999676704407,1006 "learning_rate": 0.00018767295597484277,1007 "epoch": 0.0681251008 },1009 {1010 "step": 710,1011 "timestamp": "2025-12-28T09:16:28.622419",1012 "elapsed_time": 1102.9075095653534,1013 "loss": 0.1403,1014 "grad_norm": 0.1099625825881958,1015 "learning_rate": 0.00018754716981132078,1016 "epoch": 0.068751017 },1018 {1019 "step": 711,1020 "timestamp": "2025-12-28T09:16:38.899862",1021 "elapsed_time": 1113.1849522590637,1022 "loss": 0.3365,1023 "grad_norm": 0.1869092434644699,1024 "learning_rate": 0.00018742138364779876,1025 "epoch": 0.0693751026 },1027 {1028 "step": 712,1029 "timestamp": "2025-12-28T09:16:58.976813",1030 "elapsed_time": 1133.2619035243988,1031 "loss": 0.1024,1032 "grad_norm": 0.08866474777460098,1033 "learning_rate": 0.00018729559748427674,1034 "epoch": 0.071035 },1036 {1037 "step": 713,1038 "timestamp": "2025-12-28T09:17:05.528653",1039 "elapsed_time": 1139.8137435913086,1040 "loss": 0.2417,1041 "grad_norm": 0.1919388324022293,1042 "learning_rate": 0.00018716981132075472,1043 "epoch": 0.0706251044 },1045 {1046 "step": 714,1047 "timestamp": "2025-12-28T09:17:16.181514",1048 "elapsed_time": 1150.466604232788,1049 "loss": 0.1628,1050 "grad_norm": 0.12882591784000397,1051 "learning_rate": 0.00018704402515723272,1052 "epoch": 0.071251053 },1054 {1055 "step": 715,1056 "timestamp": "2025-12-28T09:17:21.921176",1057 "elapsed_time": 1156.2062666416168,1058 "loss": 0.2503,1059 "grad_norm": 0.17477668821811676,1060 "learning_rate": 0.0001869182389937107,1061 "epoch": 0.0718751062 },1063 {1064 "step": 716,1065 "timestamp": "2025-12-28T09:17:31.060009",1066 "elapsed_time": 1165.3450994491577,1067 "loss": 0.19,1068 "grad_norm": 0.15098389983177185,1069 "learning_rate": 0.00018679245283018868,1070 "epoch": 0.07251071 },1072 {1073 "step": 717,1074 "timestamp": "2025-12-28T09:17:51.950466",1075 "elapsed_time": 1186.235556602478,1076 "loss": 0.1353,1077 "grad_norm": 0.12708379328250885,1078 "learning_rate": 0.0001866666666666667,1079 "epoch": 0.0731251080 },1081 {1082 "step": 718,1083 "timestamp": "2025-12-28T09:17:57.215989",1084 "elapsed_time": 1191.5010793209076,1085 "loss": 0.2758,1086 "grad_norm": 0.20731349289417267,1087 "learning_rate": 0.00018654088050314467,1088 "epoch": 0.073751089 },1090 {1091 "step": 719,1092 "timestamp": "2025-12-28T09:18:05.159270",1093 "elapsed_time": 1199.4443612098694,1094 "loss": 0.226,1095 "grad_norm": 0.16173875331878662,1096 "learning_rate": 0.00018641509433962264,1097 "epoch": 0.0743751098 },1099 {1100 "step": 720,1101 "timestamp": "2025-12-28T09:18:10.909682",1102 "elapsed_time": 1205.1947722434998,1103 "loss": 0.2709,1104 "grad_norm": 0.21631106734275818,1105 "learning_rate": 0.00018628930817610065,1106 "epoch": 0.0751107 },1108 {1109 "step": 721,1110 "timestamp": "2025-12-28T09:18:23.590226",1111 "elapsed_time": 1217.875316619873,1112 "loss": 0.2306,1113 "grad_norm": 0.12810084223747253,1114 "learning_rate": 0.00018616352201257863,1115 "epoch": 0.0756251116 },1117 {1118 "step": 722,1119 "timestamp": "2025-12-28T09:18:38.922154",1120 "elapsed_time": 1233.2072455883026,1121 "loss": 0.1657,1122 "grad_norm": 0.10849788039922714,1123 "learning_rate": 0.0001860377358490566,1124 "epoch": 0.076251125 },1126 {1127 "step": 723,1128 "timestamp": "2025-12-28T09:18:48.500418",1129 "elapsed_time": 1242.7855124473572,1130 "loss": 0.1657,1131 "grad_norm": 0.17049764096736908,1132 "learning_rate": 0.00018591194968553462,1133 "epoch": 0.0768751134 },1135 {1136 "step": 724,1137 "timestamp": "2025-12-28T09:18:57.124927",1138 "elapsed_time": 1251.4100172519684,1139 "loss": 0.1443,1140 "grad_norm": 0.1467668116092682,1141 "learning_rate": 0.0001857861635220126,1142 "epoch": 0.07751143 },1144 {1145 "step": 725,1146 "timestamp": "2025-12-28T09:19:04.646596",1147 "elapsed_time": 1258.9316868782043,1148 "loss": 0.2106,1149 "grad_norm": 0.16145600378513336,1150 "learning_rate": 0.00018566037735849057,1151 "epoch": 0.0781251152 },1153 {1154 "step": 726,1155 "timestamp": "2025-12-28T09:19:13.415801",1156 "elapsed_time": 1267.7008922100067,1157 "loss": 0.1683,1158 "grad_norm": 0.13938355445861816,1159 "learning_rate": 0.00018553459119496855,1160 "epoch": 0.078751161 },1162 {1163 "step": 727,1164 "timestamp": "2025-12-28T09:19:19.791168",1165 "elapsed_time": 1274.0762577056885,1166 "loss": 0.1834,1167 "grad_norm": 0.16343441605567932,1168 "learning_rate": 0.00018540880503144656,1169 "epoch": 0.0793751170 },1171 {1172 "step": 728,1173 "timestamp": "2025-12-28T09:19:26.780643",1174 "elapsed_time": 1281.065733909607,1175 "loss": 0.3605,1176 "grad_norm": 0.18578511476516724,1177 "learning_rate": 0.00018528301886792454,1178 "epoch": 0.081179 },1180 {1181 "step": 729,1182 "timestamp": "2025-12-28T09:19:40.770904",1183 "elapsed_time": 1295.0559949874878,1184 "loss": 0.1423,1185 "grad_norm": 0.10042066127061844,1186 "learning_rate": 0.00018515723270440252,1187 "epoch": 0.0806251188 },1189 {1190 "step": 730,1191 "timestamp": "2025-12-28T09:19:46.875385",1192 "elapsed_time": 1301.1604759693146,1193 "loss": 0.2364,1194 "grad_norm": 0.2259899079799652,1195 "learning_rate": 0.00018503144654088052,1196 "epoch": 0.081251197 },1198 {1199 "step": 731,1200 "timestamp": "2025-12-28T09:19:57.704231",