Virtue-AI-HUB/VulnLLM-R-7B
2471.5k
1{2 "best_global_step": null,3 "best_metric": null,4 "best_model_checkpoint": null,5 "epoch": 1.998837479655894,6 "eval_steps": 500,7 "global_step": 1432,8 "is_hyper_param_search": false,9 "is_local_process_zero": true,10 "is_world_process_zero": true,11 "log_history": [12 {13 "epoch": 0.0013950244129272262,14 "grad_norm": 9.077165796122205,15 "learning_rate": 0.0,16 "loss": 1.244,17 "step": 118 },19 {20 "epoch": 0.0027900488258544524,21 "grad_norm": 7.807074173265791,22 "learning_rate": 6.944444444444444e-08,23 "loss": 1.1223,24 "step": 225 },26 {27 "epoch": 0.0041850732387816785,28 "grad_norm": 6.324174799146362,29 "learning_rate": 1.3888888888888888e-07,30 "loss": 0.9673,31 "step": 332 },33 {34 "epoch": 0.005580097651708905,35 "grad_norm": 8.27030483810195,36 "learning_rate": 2.0833333333333333e-07,37 "loss": 1.1685,38 "step": 439 },40 {41 "epoch": 0.006975122064636131,42 "grad_norm": 7.60016514591344,43 "learning_rate": 2.7777777777777776e-07,44 "loss": 1.0968,45 "step": 546 },47 {48 "epoch": 0.008370146477563357,49 "grad_norm": 8.060333500293979,50 "learning_rate": 3.472222222222223e-07,51 "loss": 1.1373,52 "step": 653 },54 {55 "epoch": 0.009765170890490584,56 "grad_norm": 8.048732320406836,57 "learning_rate": 4.1666666666666667e-07,58 "loss": 1.2183,59 "step": 760 },61 {62 "epoch": 0.01116019530341781,63 "grad_norm": 8.367676393723716,64 "learning_rate": 4.861111111111112e-07,65 "loss": 1.2232,66 "step": 867 },68 {69 "epoch": 0.012555219716345037,70 "grad_norm": 6.936859591765737,71 "learning_rate": 5.555555555555555e-07,72 "loss": 1.0223,73 "step": 974 },75 {76 "epoch": 0.013950244129272262,77 "grad_norm": 7.474340880350743,78 "learning_rate": 6.25e-07,79 "loss": 1.0451,80 "step": 1081 },82 {83 "epoch": 0.015345268542199489,84 "grad_norm": 7.924791845739248,85 "learning_rate": 6.944444444444446e-07,86 "loss": 1.0904,87 "step": 1188 },89 {90 "epoch": 0.016740292955126714,91 "grad_norm": 6.700238239267023,92 "learning_rate": 7.63888888888889e-07,93 "loss": 1.0017,94 "step": 1295 },96 {97 "epoch": 0.01813531736805394,98 "grad_norm": 7.121912596616418,99 "learning_rate": 8.333333333333333e-07,100 "loss": 1.1195,101 "step": 13102 },103 {104 "epoch": 0.01953034178098117,105 "grad_norm": 7.593714162127442,106 "learning_rate": 9.027777777777779e-07,107 "loss": 1.1526,108 "step": 14109 },110 {111 "epoch": 0.020925366193908394,112 "grad_norm": 5.598325711309053,113 "learning_rate": 9.722222222222224e-07,114 "loss": 0.9568,115 "step": 15116 },117 {118 "epoch": 0.02232039060683562,119 "grad_norm": 6.502502784546973,120 "learning_rate": 1.0416666666666667e-06,121 "loss": 1.0338,122 "step": 16123 },124 {125 "epoch": 0.023715415019762844,126 "grad_norm": 4.2688358482531585,127 "learning_rate": 1.111111111111111e-06,128 "loss": 0.8272,129 "step": 17130 },131 {132 "epoch": 0.025110439432690073,133 "grad_norm": 6.141756294060148,134 "learning_rate": 1.1805555555555556e-06,135 "loss": 1.1201,136 "step": 18137 },138 {139 "epoch": 0.0265054638456173,140 "grad_norm": 3.803027333138855,141 "learning_rate": 1.25e-06,142 "loss": 0.873,143 "step": 19144 },145 {146 "epoch": 0.027900488258544524,147 "grad_norm": 5.014334478810172,148 "learning_rate": 1.3194444444444446e-06,149 "loss": 0.9899,150 "step": 20151 },152 {153 "epoch": 0.029295512671471752,154 "grad_norm": 4.551325462075463,155 "learning_rate": 1.3888888888888892e-06,156 "loss": 0.942,157 "step": 21158 },159 {160 "epoch": 0.030690537084398978,161 "grad_norm": 4.812375868902633,162 "learning_rate": 1.4583333333333335e-06,163 "loss": 0.9865,164 "step": 22165 },166 {167 "epoch": 0.03208556149732621,168 "grad_norm": 4.357883881047429,169 "learning_rate": 1.527777777777778e-06,170 "loss": 0.9614,171 "step": 23172 },173 {174 "epoch": 0.03348058591025343,175 "grad_norm": 3.6268224514828318,176 "learning_rate": 1.5972222222222221e-06,177 "loss": 0.8257,178 "step": 24179 },180 {181 "epoch": 0.03487561032318066,182 "grad_norm": 3.4656554743615047,183 "learning_rate": 1.6666666666666667e-06,184 "loss": 0.9127,185 "step": 25186 },187 {188 "epoch": 0.03627063473610788,189 "grad_norm": 3.876455217129128,190 "learning_rate": 1.7361111111111112e-06,191 "loss": 0.9278,192 "step": 26193 },194 {195 "epoch": 0.03766565914903511,196 "grad_norm": 4.09517147857438,197 "learning_rate": 1.8055555555555557e-06,198 "loss": 0.9556,199 "step": 27200 },201 {202 "epoch": 0.03906068356196234,203 "grad_norm": 3.5545716555392737,204 "learning_rate": 1.8750000000000003e-06,205 "loss": 0.8878,206 "step": 28207 },208 {209 "epoch": 0.04045570797488956,210 "grad_norm": 3.835208660111137,211 "learning_rate": 1.944444444444445e-06,212 "loss": 0.885,213 "step": 29214 },215 {216 "epoch": 0.04185073238781679,217 "grad_norm": 3.531205403980982,218 "learning_rate": 2.0138888888888893e-06,219 "loss": 0.886,220 "step": 30221 },222 {223 "epoch": 0.043245756800744016,224 "grad_norm": 4.231398251952698,225 "learning_rate": 2.0833333333333334e-06,226 "loss": 0.8223,227 "step": 31228 },229 {230 "epoch": 0.04464078121367124,231 "grad_norm": 3.3069565195805386,232 "learning_rate": 2.152777777777778e-06,233 "loss": 0.8934,234 "step": 32235 },236 {237 "epoch": 0.04603580562659847,238 "grad_norm": 3.3388892924336737,239 "learning_rate": 2.222222222222222e-06,240 "loss": 0.9336,241 "step": 33242 },243 {244 "epoch": 0.04743083003952569,245 "grad_norm": 3.0257164444225895,246 "learning_rate": 2.2916666666666666e-06,247 "loss": 0.8879,248 "step": 34249 },250 {251 "epoch": 0.04882585445245292,252 "grad_norm": 3.228639273179126,253 "learning_rate": 2.361111111111111e-06,254 "loss": 0.8922,255 "step": 35256 },257 {258 "epoch": 0.050220878865380146,259 "grad_norm": 3.620966182021972,260 "learning_rate": 2.4305555555555557e-06,261 "loss": 0.9343,262 "step": 36263 },264 {265 "epoch": 0.05161590327830737,266 "grad_norm": 3.182907050050726,267 "learning_rate": 2.5e-06,268 "loss": 0.8324,269 "step": 37270 },271 {272 "epoch": 0.0530109276912346,273 "grad_norm": 3.232818032867581,274 "learning_rate": 2.5694444444444443e-06,275 "loss": 0.7873,276 "step": 38277 },278 {279 "epoch": 0.054405952104161825,280 "grad_norm": 3.2312814843076434,281 "learning_rate": 2.6388888888888893e-06,282 "loss": 0.8887,283 "step": 39284 },285 {286 "epoch": 0.05580097651708905,287 "grad_norm": 3.356427492997714,288 "learning_rate": 2.7083333333333334e-06,289 "loss": 0.8288,290 "step": 40291 },292 {293 "epoch": 0.057196000930016276,294 "grad_norm": 2.8004715481014286,295 "learning_rate": 2.7777777777777783e-06,296 "loss": 0.8025,297 "step": 41298 },299 {300 "epoch": 0.058591025342943505,301 "grad_norm": 2.872064290513942,302 "learning_rate": 2.8472222222222224e-06,303 "loss": 0.7969,304 "step": 42305 },306 {307 "epoch": 0.05998604975587073,308 "grad_norm": 2.604055696429484,309 "learning_rate": 2.916666666666667e-06,310 "loss": 0.7796,311 "step": 43312 },313 {314 "epoch": 0.061381074168797956,315 "grad_norm": 2.588383255024964,316 "learning_rate": 2.986111111111111e-06,317 "loss": 0.8146,318 "step": 44319 },320 {321 "epoch": 0.06277609858172518,322 "grad_norm": 2.957391150131729,323 "learning_rate": 3.055555555555556e-06,324 "loss": 0.8706,325 "step": 45326 },327 {328 "epoch": 0.06417112299465241,329 "grad_norm": 2.7716857456581208,330 "learning_rate": 3.125e-06,331 "loss": 0.7553,332 "step": 46333 },334 {335 "epoch": 0.06556614740757963,336 "grad_norm": 2.8704927650550305,337 "learning_rate": 3.1944444444444443e-06,338 "loss": 0.835,339 "step": 47340 },341 {342 "epoch": 0.06696117182050686,343 "grad_norm": 2.926448629599372,344 "learning_rate": 3.2638888888888892e-06,345 "loss": 0.8358,346 "step": 48347 },348 {349 "epoch": 0.06835619623343409,350 "grad_norm": 2.653881772418661,351 "learning_rate": 3.3333333333333333e-06,352 "loss": 0.8573,353 "step": 49354 },355 {356 "epoch": 0.06975122064636131,357 "grad_norm": 2.7680654495558796,358 "learning_rate": 3.4027777777777783e-06,359 "loss": 0.8155,360 "step": 50361 },362 {363 "epoch": 0.07114624505928854,364 "grad_norm": 2.690527707536472,365 "learning_rate": 3.4722222222222224e-06,366 "loss": 0.8718,367 "step": 51368 },369 {370 "epoch": 0.07254126947221576,371 "grad_norm": 2.539274614289565,372 "learning_rate": 3.5416666666666673e-06,373 "loss": 0.8143,374 "step": 52375 },376 {377 "epoch": 0.07393629388514299,378 "grad_norm": 2.6150798045040564,379 "learning_rate": 3.6111111111111115e-06,380 "loss": 0.8129,381 "step": 53382 },383 {384 "epoch": 0.07533131829807022,385 "grad_norm": 2.77487818448589,386 "learning_rate": 3.680555555555556e-06,387 "loss": 0.8431,388 "step": 54389 },390 {391 "epoch": 0.07672634271099744,392 "grad_norm": 2.4190012994996404,393 "learning_rate": 3.7500000000000005e-06,394 "loss": 0.7949,395 "step": 55396 },397 {398 "epoch": 0.07812136712392467,399 "grad_norm": 2.5658926847545143,400 "learning_rate": 3.819444444444444e-06,401 "loss": 0.8349,402 "step": 56403 },404 {405 "epoch": 0.07951639153685189,406 "grad_norm": 2.465553073665557,407 "learning_rate": 3.88888888888889e-06,408 "loss": 0.8001,409 "step": 57410 },411 {412 "epoch": 0.08091141594977912,413 "grad_norm": 2.5769268931786113,414 "learning_rate": 3.958333333333333e-06,415 "loss": 0.7853,416 "step": 58417 },418 {419 "epoch": 0.08230644036270635,420 "grad_norm": 2.762238617657559,421 "learning_rate": 4.027777777777779e-06,422 "loss": 0.8858,423 "step": 59424 },425 {426 "epoch": 0.08370146477563357,427 "grad_norm": 2.459676043622874,428 "learning_rate": 4.097222222222222e-06,429 "loss": 0.7484,430 "step": 60431 },432 {433 "epoch": 0.0850964891885608,434 "grad_norm": 2.281452061978854,435 "learning_rate": 4.166666666666667e-06,436 "loss": 0.7395,437 "step": 61438 },439 {440 "epoch": 0.08649151360148803,441 "grad_norm": 2.5945093959933923,442 "learning_rate": 4.236111111111111e-06,443 "loss": 0.8383,444 "step": 62445 },446 {447 "epoch": 0.08788653801441525,448 "grad_norm": 2.4907580232536337,449 "learning_rate": 4.305555555555556e-06,450 "loss": 0.7387,451 "step": 63452 },453 {454 "epoch": 0.08928156242734248,455 "grad_norm": 2.5357156725837844,456 "learning_rate": 4.3750000000000005e-06,457 "loss": 0.8378,458 "step": 64459 },460 {461 "epoch": 0.0906765868402697,462 "grad_norm": 2.3775000896329814,463 "learning_rate": 4.444444444444444e-06,464 "loss": 0.7606,465 "step": 65466 },467 {468 "epoch": 0.09207161125319693,469 "grad_norm": 2.6462676515975367,470 "learning_rate": 4.5138888888888895e-06,471 "loss": 0.8067,472 "step": 66473 },474 {475 "epoch": 0.09346663566612416,476 "grad_norm": 2.484589313471558,477 "learning_rate": 4.583333333333333e-06,478 "loss": 0.8517,479 "step": 67480 },481 {482 "epoch": 0.09486166007905138,483 "grad_norm": 2.5630782397634135,484 "learning_rate": 4.652777777777779e-06,485 "loss": 0.8104,486 "step": 68487 },488 {489 "epoch": 0.0962566844919786,490 "grad_norm": 2.603099792013807,491 "learning_rate": 4.722222222222222e-06,492 "loss": 0.7562,493 "step": 69494 },495 {496 "epoch": 0.09765170890490583,497 "grad_norm": 2.458040997496572,498 "learning_rate": 4.791666666666668e-06,499 "loss": 0.7245,500 "step": 70501 },502 {503 "epoch": 0.09904673331783306,504 "grad_norm": 2.6548832786314387,505 "learning_rate": 4.861111111111111e-06,506 "loss": 0.7604,507 "step": 71508 },509 {510 "epoch": 0.10044175773076029,511 "grad_norm": 2.5407350711188137,512 "learning_rate": 4.930555555555556e-06,513 "loss": 0.7614,514 "step": 72515 },516 {517 "epoch": 0.10183678214368752,518 "grad_norm": 2.466098001195273,519 "learning_rate": 5e-06,520 "loss": 0.7708,521 "step": 73522 },523 {524 "epoch": 0.10323180655661474,525 "grad_norm": 2.4710838556933634,526 "learning_rate": 5.069444444444445e-06,527 "loss": 0.781,528 "step": 74529 },530 {531 "epoch": 0.10462683096954196,532 "grad_norm": 2.5745603388615788,533 "learning_rate": 5.138888888888889e-06,534 "loss": 0.7617,535 "step": 75536 },537 {538 "epoch": 0.1060218553824692,539 "grad_norm": 2.4760378463602617,540 "learning_rate": 5.208333333333334e-06,541 "loss": 0.6586,542 "step": 76543 },544 {545 "epoch": 0.10741687979539642,546 "grad_norm": 2.1046185393371637,547 "learning_rate": 5.2777777777777785e-06,548 "loss": 0.6515,549 "step": 77550 },551 {552 "epoch": 0.10881190420832365,553 "grad_norm": 2.57807326774727,554 "learning_rate": 5.347222222222222e-06,555 "loss": 0.7987,556 "step": 78557 },558 {559 "epoch": 0.11020692862125087,560 "grad_norm": 2.4541665474964884,561 "learning_rate": 5.416666666666667e-06,562 "loss": 0.7797,563 "step": 79564 },565 {566 "epoch": 0.1116019530341781,567 "grad_norm": 2.7192596934225883,568 "learning_rate": 5.486111111111112e-06,569 "loss": 0.8144,570 "step": 80571 },572 {573 "epoch": 0.11299697744710532,574 "grad_norm": 2.587955726978526,575 "learning_rate": 5.555555555555557e-06,576 "loss": 0.7718,577 "step": 81578 },579 {580 "epoch": 0.11439200186003255,581 "grad_norm": 2.8624670000905508,582 "learning_rate": 5.625e-06,583 "loss": 0.8642,584 "step": 82585 },586 {587 "epoch": 0.11578702627295978,588 "grad_norm": 2.3985540385123785,589 "learning_rate": 5.694444444444445e-06,590 "loss": 0.7585,591 "step": 83592 },593 {594 "epoch": 0.11718205068588701,595 "grad_norm": 2.4347959569209743,596 "learning_rate": 5.7638888888888886e-06,597 "loss": 0.7652,598 "step": 84599 },600 {601 "epoch": 0.11857707509881422,602 "grad_norm": 2.472216781380437,603 "learning_rate": 5.833333333333334e-06,604 "loss": 0.7593,605 "step": 85606 },607 {608 "epoch": 0.11997209951174145,609 "grad_norm": 2.3683241185527684,610 "learning_rate": 5.9027777777777785e-06,611 "loss": 0.6797,612 "step": 86613 },614 {615 "epoch": 0.12136712392466868,616 "grad_norm": 2.585048523140377,617 "learning_rate": 5.972222222222222e-06,618 "loss": 0.8135,619 "step": 87620 },621 {622 "epoch": 0.12276214833759591,623 "grad_norm": 2.583706669085246,624 "learning_rate": 6.041666666666667e-06,625 "loss": 0.8272,626 "step": 88627 },628 {629 "epoch": 0.12415717275052314,630 "grad_norm": 2.4831147364219253,631 "learning_rate": 6.111111111111112e-06,632 "loss": 0.8588,633 "step": 89634 },635 {636 "epoch": 0.12555219716345037,637 "grad_norm": 2.372052290928504,638 "learning_rate": 6.180555555555557e-06,639 "loss": 0.7559,640 "step": 90641 },642 {643 "epoch": 0.12694722157637758,644 "grad_norm": 2.3693742709173997,645 "learning_rate": 6.25e-06,646 "loss": 0.7523,647 "step": 91648 },649 {650 "epoch": 0.12834224598930483,651 "grad_norm": 2.56593824677806,652 "learning_rate": 6.319444444444445e-06,653 "loss": 0.7976,654 "step": 92655 },656 {657 "epoch": 0.12973727040223204,658 "grad_norm": 2.6643468086221485,659 "learning_rate": 6.3888888888888885e-06,660 "loss": 0.7603,661 "step": 93662 },663 {664 "epoch": 0.13113229481515926,665 "grad_norm": 2.431324445820708,666 "learning_rate": 6.458333333333334e-06,667 "loss": 0.7177,668 "step": 94669 },670 {671 "epoch": 0.1325273192280865,672 "grad_norm": 2.0286167424640786,673 "learning_rate": 6.5277777777777784e-06,674 "loss": 0.6637,675 "step": 95676 },677 {678 "epoch": 0.1339223436410137,679 "grad_norm": 2.381250278728561,680 "learning_rate": 6.597222222222223e-06,681 "loss": 0.7543,682 "step": 96683 },684 {685 "epoch": 0.13531736805394096,686 "grad_norm": 2.5224874846398304,687 "learning_rate": 6.666666666666667e-06,688 "loss": 0.748,689 "step": 97690 },691 {692 "epoch": 0.13671239246686817,693 "grad_norm": 2.367382093641696,694 "learning_rate": 6.736111111111112e-06,695 "loss": 0.7078,696 "step": 98697 },698 {699 "epoch": 0.13810741687979539,700 "grad_norm": 2.2891454288500785,701 "learning_rate": 6.8055555555555566e-06,702 "loss": 0.7778,703 "step": 99704 },705 {706 "epoch": 0.13950244129272263,707 "grad_norm": 2.326427675547096,708 "learning_rate": 6.875e-06,709 "loss": 0.7,710 "step": 100711 },712 {713 "epoch": 0.14089746570564984,714 "grad_norm": 2.43784471948663,715 "learning_rate": 6.944444444444445e-06,716 "loss": 0.7845,717 "step": 101718 },719 {720 "epoch": 0.1422924901185771,721 "grad_norm": 2.434928494698733,722 "learning_rate": 7.013888888888889e-06,723 "loss": 0.7741,724 "step": 102725 },726 {727 "epoch": 0.1436875145315043,728 "grad_norm": 2.544677188997524,729 "learning_rate": 7.083333333333335e-06,730 "loss": 0.7321,731 "step": 103732 },733 {734 "epoch": 0.14508253894443152,735 "grad_norm": 2.4317471320917314,736 "learning_rate": 7.152777777777778e-06,737 "loss": 0.7301,738 "step": 104739 },740 {741 "epoch": 0.14647756335735876,742 "grad_norm": 2.3758040864865535,743 "learning_rate": 7.222222222222223e-06,744 "loss": 0.7168,745 "step": 105746 },747 {748 "epoch": 0.14787258777028597,749 "grad_norm": 2.427323974558636,750 "learning_rate": 7.291666666666667e-06,751 "loss": 0.7122,752 "step": 106753 },754 {755 "epoch": 0.14926761218321322,756 "grad_norm": 2.5718099527792515,757 "learning_rate": 7.361111111111112e-06,758 "loss": 0.7777,759 "step": 107760 },761 {762 "epoch": 0.15066263659614043,763 "grad_norm": 2.3984442193810303,764 "learning_rate": 7.4305555555555565e-06,765 "loss": 0.76,766 "step": 108767 },768 {769 "epoch": 0.15205766100906765,770 "grad_norm": 2.809886900720292,771 "learning_rate": 7.500000000000001e-06,772 "loss": 0.9409,773 "step": 109774 },775 {776 "epoch": 0.1534526854219949,777 "grad_norm": 2.1909629178912735,778 "learning_rate": 7.569444444444445e-06,779 "loss": 0.6928,780 "step": 110781 },782 {783 "epoch": 0.1548477098349221,784 "grad_norm": 2.299999050133801,785 "learning_rate": 7.638888888888888e-06,786 "loss": 0.7331,787 "step": 111788 },789 {790 "epoch": 0.15624273424784935,791 "grad_norm": 2.4657027253176658,792 "learning_rate": 7.708333333333334e-06,793 "loss": 0.7734,794 "step": 112795 },796 {797 "epoch": 0.15763775866077656,798 "grad_norm": 2.499003482696436,799 "learning_rate": 7.77777777777778e-06,800 "loss": 0.7568,801 "step": 113802 },803 {804 "epoch": 0.15903278307370378,805 "grad_norm": 2.556353786561783,806 "learning_rate": 7.847222222222223e-06,807 "loss": 0.7813,808 "step": 114809 },810 {811 "epoch": 0.16042780748663102,812 "grad_norm": 2.398942685028162,813 "learning_rate": 7.916666666666667e-06,814 "loss": 0.773,815 "step": 115816 },817 {818 "epoch": 0.16182283189955823,819 "grad_norm": 2.437022751579472,820 "learning_rate": 7.986111111111112e-06,821 "loss": 0.7423,822 "step": 116823 },824 {825 "epoch": 0.16321785631248548,826 "grad_norm": 2.5361969141214753,827 "learning_rate": 8.055555555555557e-06,828 "loss": 0.8085,829 "step": 117830 },831 {832 "epoch": 0.1646128807254127,833 "grad_norm": 2.5686473875754148,834 "learning_rate": 8.125000000000001e-06,835 "loss": 0.7602,836 "step": 118837 },838 {839 "epoch": 0.16600790513833993,840 "grad_norm": 2.6355454558922786,841 "learning_rate": 8.194444444444445e-06,842 "loss": 0.7348,843 "step": 119844 },845 {846 "epoch": 0.16740292955126715,847 "grad_norm": 2.5297512188295457,848 "learning_rate": 8.263888888888888e-06,849 "loss": 0.7398,850 "step": 120851 },852 {853 "epoch": 0.16879795396419436,854 "grad_norm": 2.4649882854746354,855 "learning_rate": 8.333333333333334e-06,856 "loss": 0.7636,857 "step": 121858 },859 {860 "epoch": 0.1701929783771216,861 "grad_norm": 2.4209538379807443,862 "learning_rate": 8.402777777777779e-06,863 "loss": 0.7799,864 "step": 122865 },866 {867 "epoch": 0.17158800279004882,868 "grad_norm": 2.7076603164565665,869 "learning_rate": 8.472222222222223e-06,870 "loss": 0.8096,871 "step": 123872 },873 {874 "epoch": 0.17298302720297606,875 "grad_norm": 2.5198462673809643,876 "learning_rate": 8.541666666666666e-06,877 "loss": 0.7566,878 "step": 124879 },880 {881 "epoch": 0.17437805161590328,882 "grad_norm": 2.3301540316911935,883 "learning_rate": 8.611111111111112e-06,884 "loss": 0.7885,885 "step": 125886 },887 {888 "epoch": 0.1757730760288305,889 "grad_norm": 2.528981320323845,890 "learning_rate": 8.680555555555557e-06,891 "loss": 0.7747,892 "step": 126893 },894 {895 "epoch": 0.17716810044175774,896 "grad_norm": 2.6228409614962938,897 "learning_rate": 8.750000000000001e-06,898 "loss": 0.7827,899 "step": 127900 },901 {902 "epoch": 0.17856312485468495,903 "grad_norm": 2.3530092565699805,904 "learning_rate": 8.819444444444445e-06,905 "loss": 0.775,906 "step": 128907 },908 {909 "epoch": 0.1799581492676122,910 "grad_norm": 2.4030846577696834,911 "learning_rate": 8.888888888888888e-06,912 "loss": 0.8468,913 "step": 129914 },915 {916 "epoch": 0.1813531736805394,917 "grad_norm": 2.397665315329076,918 "learning_rate": 8.958333333333334e-06,919 "loss": 0.7555,920 "step": 130921 },922 {923 "epoch": 0.18274819809346662,924 "grad_norm": 2.4944187750790165,925 "learning_rate": 9.027777777777779e-06,926 "loss": 0.6983,927 "step": 131928 },929 {930 "epoch": 0.18414322250639387,931 "grad_norm": 2.4633848637523266,932 "learning_rate": 9.097222222222223e-06,933 "loss": 0.8095,934 "step": 132935 },936 {937 "epoch": 0.18553824691932108,938 "grad_norm": 2.4514234526609755,939 "learning_rate": 9.166666666666666e-06,940 "loss": 0.7669,941 "step": 133942 },943 {944 "epoch": 0.18693327133224832,945 "grad_norm": 2.2348180975167002,946 "learning_rate": 9.236111111111112e-06,947 "loss": 0.7445,948 "step": 134949 },950 {951 "epoch": 0.18832829574517554,952 "grad_norm": 2.7654592189288127,953 "learning_rate": 9.305555555555557e-06,954 "loss": 0.8222,955 "step": 135956 },957 {958 "epoch": 0.18972332015810275,959 "grad_norm": 2.657505427715525,960 "learning_rate": 9.375000000000001e-06,961 "loss": 0.7993,962 "step": 136963 },964 {965 "epoch": 0.19111834457103,966 "grad_norm": 2.4757416453669037,967 "learning_rate": 9.444444444444445e-06,968 "loss": 0.7553,969 "step": 137970 },971 {972 "epoch": 0.1925133689839572,973 "grad_norm": 2.4710024870459546,974 "learning_rate": 9.51388888888889e-06,975 "loss": 0.7893,976 "step": 138977 },978 {979 "epoch": 0.19390839339688445,980 "grad_norm": 2.484340628816311,981 "learning_rate": 9.583333333333335e-06,982 "loss": 0.7435,983 "step": 139984 },985 {986 "epoch": 0.19530341780981167,987 "grad_norm": 2.3567750021925864,988 "learning_rate": 9.652777777777779e-06,989 "loss": 0.7991,990 "step": 140991 },992 {993 "epoch": 0.1966984422227389,994 "grad_norm": 2.6403706679259376,995 "learning_rate": 9.722222222222223e-06,996 "loss": 0.8204,997 "step": 141998 },999 {1000 "epoch": 0.19809346663566613,1001 "grad_norm": 2.7772690056581406,1002 "learning_rate": 9.791666666666666e-06,1003 "loss": 0.764,1004 "step": 1421005 },1006 {1007 "epoch": 0.19948849104859334,1008 "grad_norm": 2.38948338269402,1009 "learning_rate": 9.861111111111112e-06,1010 "loss": 0.7588,1011 "step": 1431012 },1013 {1014 "epoch": 0.20088351546152058,1015 "grad_norm": 2.364591011786826,1016 "learning_rate": 9.930555555555557e-06,1017 "loss": 0.7382,1018 "step": 1441019 },1020 {1021 "epoch": 0.2022785398744478,1022 "grad_norm": 2.39460109071618,1023 "learning_rate": 1e-05,1024 "loss": 0.8297,1025 "step": 1451026 },1027 {1028 "epoch": 0.20367356428737504,1029 "grad_norm": 2.385277772966096,1030 "learning_rate": 9.99998512668374e-06,1031 "loss": 0.762,1032 "step": 1461033 },1034 {1035 "epoch": 0.20506858870030226,1036 "grad_norm": 2.550269196061235,1037 "learning_rate": 9.999940506823446e-06,1038 "loss": 0.8577,1039 "step": 1471040 },1041 {1042 "epoch": 0.20646361311322947,1043 "grad_norm": 2.3828419813394768,1044 "learning_rate": 9.999866140684576e-06,1045 "loss": 0.7526,1046 "step": 1481047 },1048 {1049 "epoch": 0.20785863752615671,1050 "grad_norm": 2.674659581827359,1051 "learning_rate": 9.999762028709558e-06,1052 "loss": 0.8444,1053 "step": 1491054 },1055 {1056 "epoch": 0.20925366193908393,1057 "grad_norm": 2.438042726374861,1058 "learning_rate": 9.999628171517788e-06,1059 "loss": 0.7834,1060 "step": 1501061 },1062 {1063 "epoch": 0.21064868635201117,1064 "grad_norm": 2.527684334680155,1065 "learning_rate": 9.999464569905628e-06,1066 "loss": 0.778,1067 "step": 1511068 },1069 {1070 "epoch": 0.2120437107649384,1071 "grad_norm": 2.164235216275893,1072 "learning_rate": 9.999271224846397e-06,1073 "loss": 0.7357,1074 "step": 1521075 },1076 {1077 "epoch": 0.2134387351778656,1078 "grad_norm": 2.568663637972533,1079 "learning_rate": 9.999048137490364e-06,1080 "loss": 0.7864,1081 "step": 1531082 },1083 {1084 "epoch": 0.21483375959079284,1085 "grad_norm": 2.328376334217868,1086 "learning_rate": 9.998795309164754e-06,1087 "loss": 0.741,1088 "step": 1541089 },1090 {1091 "epoch": 0.21622878400372006,1092 "grad_norm": 2.3440798093116815,1093 "learning_rate": 9.99851274137372e-06,1094 "loss": 0.752,1095 "step": 1551096 },1097 {1098 "epoch": 0.2176238084166473,1099 "grad_norm": 2.3252703261044587,1100 "learning_rate": 9.998200435798355e-06,1101 "loss": 0.7822,1102 "step": 1561103 },1104 {1105 "epoch": 0.21901883282957452,1106 "grad_norm": 2.1066008364671944,1107 "learning_rate": 9.997858394296666e-06,1108 "loss": 0.6879,1109 "step": 1571110 },1111 {1112 "epoch": 0.22041385724250173,1113 "grad_norm": 2.4582290754964067,1114 "learning_rate": 9.997486618903566e-06,1115 "loss": 0.7594,1116 "step": 1581117 },1118 {1119 "epoch": 0.22180888165542897,1120 "grad_norm": 2.202899892319989,1121 "learning_rate": 9.99708511183087e-06,1122 "loss": 0.7461,1123 "step": 1591124 },1125 {1126 "epoch": 0.2232039060683562,1127 "grad_norm": 2.367202675165834,1128 "learning_rate": 9.996653875467278e-06,1129 "loss": 0.7755,1130 "step": 1601131 },1132 {1133 "epoch": 0.22459893048128343,1134 "grad_norm": 2.4283257637167743,1135 "learning_rate": 9.99619291237835e-06,1136 "loss": 0.7694,1137 "step": 1611138 },1139 {1140 "epoch": 0.22599395489421065,1141 "grad_norm": 2.393310544522537,1142 "learning_rate": 9.99570222530651e-06,1143 "loss": 0.7624,1144 "step": 1621145 },1146 {1147 "epoch": 0.22738897930713786,1148 "grad_norm": 2.456620826384989,1149 "learning_rate": 9.995181817171016e-06,1150 "loss": 0.7943,1151 "step": 1631152 },1153 {1154 "epoch": 0.2287840037200651,1155 "grad_norm": 2.33795920230864,1156 "learning_rate": 9.994631691067941e-06,1157 "loss": 0.7064,1158 "step": 1641159 },1160 {1161 "epoch": 0.23017902813299232,1162 "grad_norm": 2.380769585125721,1163 "learning_rate": 9.994051850270172e-06,1164 "loss": 0.7785,1165 "step": 1651166 },1167 {1168 "epoch": 0.23157405254591956,1169 "grad_norm": 2.0565750954623954,1170 "learning_rate": 9.993442298227365e-06,1171 "loss": 0.6899,1172 "step": 1661173 },1174 {1175 "epoch": 0.23296907695884678,1176 "grad_norm": 2.4629114081369154,1177 "learning_rate": 9.992803038565947e-06,1178 "loss": 0.7318,1179 "step": 1671180 },1181 {1182 "epoch": 0.23436410137177402,1183 "grad_norm": 2.5260371511690227,1184 "learning_rate": 9.992134075089085e-06,1185 "loss": 0.7492,1186 "step": 1681187 },1188 {1189 "epoch": 0.23575912578470123,1190 "grad_norm": 2.2870342101598573,1191 "learning_rate": 9.991435411776654e-06,1192 "loss": 0.7546,1193 "step": 1691194 },1195 {1196 "epoch": 0.23715415019762845,1197 "grad_norm": 2.2176561807734463,1198 "learning_rate": 9.990707052785236e-06,1199 "loss": 0.6861,1200 "step": 170