paulh27/iwslt_aligned_smallT5_cont0
09
1{2 "best_metric": 65.6358,3 "best_model_checkpoint": "/tmp/finetuned_models/iwslt_aligned_smallT5_cont0/checkpoint-490000",4 "epoch": 38.81384878124515,5 "eval_steps": 10000,6 "global_step": 500000,7 "is_hyper_param_search": false,8 "is_local_process_zero": true,9 "is_world_process_zero": true,10 "log_history": [11 {12 "epoch": 0.08,13 "grad_norm": 3.0081684589385986,14 "learning_rate": 0.0002,15 "loss": 3.3371,16 "step": 100017 },18 {19 "epoch": 0.16,20 "grad_norm": 2.347439765930176,21 "learning_rate": 0.0002,22 "loss": 1.9825,23 "step": 200024 },25 {26 "epoch": 0.23,27 "grad_norm": 3.2636098861694336,28 "learning_rate": 0.0002,29 "loss": 1.7503,30 "step": 300031 },32 {33 "epoch": 0.31,34 "grad_norm": 2.1704177856445312,35 "learning_rate": 0.0002,36 "loss": 1.6063,37 "step": 400038 },39 {40 "epoch": 0.39,41 "grad_norm": 1.8257893323898315,42 "learning_rate": 0.0002,43 "loss": 1.5193,44 "step": 500045 },46 {47 "epoch": 0.47,48 "grad_norm": 2.1923136711120605,49 "learning_rate": 0.0002,50 "loss": 1.4439,51 "step": 600052 },53 {54 "epoch": 0.54,55 "grad_norm": 2.198930501937866,56 "learning_rate": 0.0002,57 "loss": 1.3742,58 "step": 700059 },60 {61 "epoch": 0.62,62 "grad_norm": 1.8519206047058105,63 "learning_rate": 0.0002,64 "loss": 1.3327,65 "step": 800066 },67 {68 "epoch": 0.7,69 "grad_norm": 2.371457576751709,70 "learning_rate": 0.0002,71 "loss": 1.2872,72 "step": 900073 },74 {75 "epoch": 0.78,76 "grad_norm": 2.2528538703918457,77 "learning_rate": 0.0002,78 "loss": 1.2426,79 "step": 1000080 },81 {82 "epoch": 0.78,83 "eval_bleu": 46.2793,84 "eval_gen_len": 28.6532,85 "eval_loss": 0.8300400972366333,86 "eval_runtime": 100.4495,87 "eval_samples_per_second": 8.84,88 "eval_steps_per_second": 1.105,89 "step": 1000090 },91 {92 "epoch": 0.85,93 "grad_norm": 1.8507146835327148,94 "learning_rate": 0.0002,95 "loss": 1.2154,96 "step": 1100097 },98 {99 "epoch": 0.93,100 "grad_norm": 1.629703164100647,101 "learning_rate": 0.0002,102 "loss": 1.1822,103 "step": 12000104 },105 {106 "epoch": 1.01,107 "grad_norm": 1.9470340013504028,108 "learning_rate": 0.0002,109 "loss": 1.1505,110 "step": 13000111 },112 {113 "epoch": 1.09,114 "grad_norm": 1.733299970626831,115 "learning_rate": 0.0002,116 "loss": 1.0877,117 "step": 14000118 },119 {120 "epoch": 1.16,121 "grad_norm": 1.5334522724151611,122 "learning_rate": 0.0002,123 "loss": 1.0647,124 "step": 15000125 },126 {127 "epoch": 1.24,128 "grad_norm": 1.8881198167800903,129 "learning_rate": 0.0002,130 "loss": 1.0595,131 "step": 16000132 },133 {134 "epoch": 1.32,135 "grad_norm": 2.1781082153320312,136 "learning_rate": 0.0002,137 "loss": 1.0441,138 "step": 17000139 },140 {141 "epoch": 1.4,142 "grad_norm": 1.509994387626648,143 "learning_rate": 0.0002,144 "loss": 1.0307,145 "step": 18000146 },147 {148 "epoch": 1.47,149 "grad_norm": 2.5609610080718994,150 "learning_rate": 0.0002,151 "loss": 1.0165,152 "step": 19000153 },154 {155 "epoch": 1.55,156 "grad_norm": 1.512005090713501,157 "learning_rate": 0.0002,158 "loss": 0.9931,159 "step": 20000160 },161 {162 "epoch": 1.55,163 "eval_bleu": 52.2709,164 "eval_gen_len": 28.6441,165 "eval_loss": 0.6755661368370056,166 "eval_runtime": 99.4907,167 "eval_samples_per_second": 8.925,168 "eval_steps_per_second": 1.116,169 "step": 20000170 },171 {172 "epoch": 1.63,173 "grad_norm": 1.4830211400985718,174 "learning_rate": 0.0002,175 "loss": 0.9854,176 "step": 21000177 },178 {179 "epoch": 1.71,180 "grad_norm": 1.8581557273864746,181 "learning_rate": 0.0002,182 "loss": 0.9736,183 "step": 22000184 },185 {186 "epoch": 1.79,187 "grad_norm": 1.589917778968811,188 "learning_rate": 0.0002,189 "loss": 0.9642,190 "step": 23000191 },192 {193 "epoch": 1.86,194 "grad_norm": 2.332538604736328,195 "learning_rate": 0.0002,196 "loss": 0.9476,197 "step": 24000198 },199 {200 "epoch": 1.94,201 "grad_norm": 1.61520516872406,202 "learning_rate": 0.0002,203 "loss": 0.943,204 "step": 25000205 },206 {207 "epoch": 2.02,208 "grad_norm": 1.2320265769958496,209 "learning_rate": 0.0002,210 "loss": 0.9135,211 "step": 26000212 },213 {214 "epoch": 2.1,215 "grad_norm": 1.543626308441162,216 "learning_rate": 0.0002,217 "loss": 0.8763,218 "step": 27000219 },220 {221 "epoch": 2.17,222 "grad_norm": 1.7634472846984863,223 "learning_rate": 0.0002,224 "loss": 0.8664,225 "step": 28000226 },227 {228 "epoch": 2.25,229 "grad_norm": 1.1254847049713135,230 "learning_rate": 0.0002,231 "loss": 0.8625,232 "step": 29000233 },234 {235 "epoch": 2.33,236 "grad_norm": 1.390243649482727,237 "learning_rate": 0.0002,238 "loss": 0.8573,239 "step": 30000240 },241 {242 "epoch": 2.33,243 "eval_bleu": 55.8294,244 "eval_gen_len": 28.5405,245 "eval_loss": 0.6142958998680115,246 "eval_runtime": 100.5081,247 "eval_samples_per_second": 8.835,248 "eval_steps_per_second": 1.104,249 "step": 30000250 },251 {252 "epoch": 2.41,253 "grad_norm": 1.592313289642334,254 "learning_rate": 0.0002,255 "loss": 0.855,256 "step": 31000257 },258 {259 "epoch": 2.48,260 "grad_norm": 1.1361020803451538,261 "learning_rate": 0.0002,262 "loss": 0.8487,263 "step": 32000264 },265 {266 "epoch": 2.56,267 "grad_norm": 1.2688100337982178,268 "learning_rate": 0.0002,269 "loss": 0.8417,270 "step": 33000271 },272 {273 "epoch": 2.64,274 "grad_norm": 1.3345963954925537,275 "learning_rate": 0.0002,276 "loss": 0.829,277 "step": 34000278 },279 {280 "epoch": 2.72,281 "grad_norm": 1.4640212059020996,282 "learning_rate": 0.0002,283 "loss": 0.8264,284 "step": 35000285 },286 {287 "epoch": 2.79,288 "grad_norm": 1.4818629026412964,289 "learning_rate": 0.0002,290 "loss": 0.8207,291 "step": 36000292 },293 {294 "epoch": 2.87,295 "grad_norm": 1.4580553770065308,296 "learning_rate": 0.0002,297 "loss": 0.8155,298 "step": 37000299 },300 {301 "epoch": 2.95,302 "grad_norm": 1.8713078498840332,303 "learning_rate": 0.0002,304 "loss": 0.8134,305 "step": 38000306 },307 {308 "epoch": 3.03,309 "grad_norm": 1.295332670211792,310 "learning_rate": 0.0002,311 "loss": 0.787,312 "step": 39000313 },314 {315 "epoch": 3.11,316 "grad_norm": 1.532378077507019,317 "learning_rate": 0.0002,318 "loss": 0.762,319 "step": 40000320 },321 {322 "epoch": 3.11,323 "eval_bleu": 57.5135,324 "eval_gen_len": 28.366,325 "eval_loss": 0.581108570098877,326 "eval_runtime": 98.8348,327 "eval_samples_per_second": 8.985,328 "eval_steps_per_second": 1.123,329 "step": 40000330 },331 {332 "epoch": 3.18,333 "grad_norm": 1.3924858570098877,334 "learning_rate": 0.0002,335 "loss": 0.7577,336 "step": 41000337 },338 {339 "epoch": 3.26,340 "grad_norm": 1.4161888360977173,341 "learning_rate": 0.0002,342 "loss": 0.7482,343 "step": 42000344 },345 {346 "epoch": 3.34,347 "grad_norm": 1.639460802078247,348 "learning_rate": 0.0002,349 "loss": 0.7582,350 "step": 43000351 },352 {353 "epoch": 3.42,354 "grad_norm": 1.3779182434082031,355 "learning_rate": 0.0002,356 "loss": 0.7474,357 "step": 44000358 },359 {360 "epoch": 3.49,361 "grad_norm": 1.8350883722305298,362 "learning_rate": 0.0002,363 "loss": 0.751,364 "step": 45000365 },366 {367 "epoch": 3.57,368 "grad_norm": 1.2075496912002563,369 "learning_rate": 0.0002,370 "loss": 0.7371,371 "step": 46000372 },373 {374 "epoch": 3.65,375 "grad_norm": 1.3083984851837158,376 "learning_rate": 0.0002,377 "loss": 0.7318,378 "step": 47000379 },380 {381 "epoch": 3.73,382 "grad_norm": 1.5021324157714844,383 "learning_rate": 0.0002,384 "loss": 0.7376,385 "step": 48000386 },387 {388 "epoch": 3.8,389 "grad_norm": 1.1597286462783813,390 "learning_rate": 0.0002,391 "loss": 0.7336,392 "step": 49000393 },394 {395 "epoch": 3.88,396 "grad_norm": 1.3814338445663452,397 "learning_rate": 0.0002,398 "loss": 0.734,399 "step": 50000400 },401 {402 "epoch": 3.88,403 "eval_bleu": 58.6125,404 "eval_gen_len": 28.5101,405 "eval_loss": 0.5499288439750671,406 "eval_runtime": 99.2548,407 "eval_samples_per_second": 8.947,408 "eval_steps_per_second": 1.118,409 "step": 50000410 },411 {412 "epoch": 3.96,413 "grad_norm": 1.0968077182769775,414 "learning_rate": 0.0002,415 "loss": 0.7288,416 "step": 51000417 },418 {419 "epoch": 4.04,420 "grad_norm": 1.9418740272521973,421 "learning_rate": 0.0002,422 "loss": 0.7057,423 "step": 52000424 },425 {426 "epoch": 4.11,427 "grad_norm": 1.1883801221847534,428 "learning_rate": 0.0002,429 "loss": 0.6761,430 "step": 53000431 },432 {433 "epoch": 4.19,434 "grad_norm": 1.1581670045852661,435 "learning_rate": 0.0002,436 "loss": 0.6812,437 "step": 54000438 },439 {440 "epoch": 4.27,441 "grad_norm": 1.4657800197601318,442 "learning_rate": 0.0002,443 "loss": 0.6783,444 "step": 55000445 },446 {447 "epoch": 4.35,448 "grad_norm": 1.1991990804672241,449 "learning_rate": 0.0002,450 "loss": 0.6764,451 "step": 56000452 },453 {454 "epoch": 4.42,455 "grad_norm": 1.5376391410827637,456 "learning_rate": 0.0002,457 "loss": 0.6805,458 "step": 57000459 },460 {461 "epoch": 4.5,462 "grad_norm": 1.228727102279663,463 "learning_rate": 0.0002,464 "loss": 0.6734,465 "step": 58000466 },467 {468 "epoch": 4.58,469 "grad_norm": 0.949891984462738,470 "learning_rate": 0.0002,471 "loss": 0.6702,472 "step": 59000473 },474 {475 "epoch": 4.66,476 "grad_norm": 1.5632683038711548,477 "learning_rate": 0.0002,478 "loss": 0.6722,479 "step": 60000480 },481 {482 "epoch": 4.66,483 "eval_bleu": 59.6427,484 "eval_gen_len": 28.8356,485 "eval_loss": 0.522808849811554,486 "eval_runtime": 101.7798,487 "eval_samples_per_second": 8.725,488 "eval_steps_per_second": 1.091,489 "step": 60000490 },491 {492 "epoch": 4.74,493 "grad_norm": 1.2885149717330933,494 "learning_rate": 0.0002,495 "loss": 0.67,496 "step": 61000497 },498 {499 "epoch": 4.81,500 "grad_norm": 1.7992392778396606,501 "learning_rate": 0.0002,502 "loss": 0.6686,503 "step": 62000504 },505 {506 "epoch": 4.89,507 "grad_norm": 1.7027188539505005,508 "learning_rate": 0.0002,509 "loss": 0.6682,510 "step": 63000511 },512 {513 "epoch": 4.97,514 "grad_norm": 1.2083909511566162,515 "learning_rate": 0.0002,516 "loss": 0.6545,517 "step": 64000518 },519 {520 "epoch": 5.05,521 "grad_norm": 1.1508337259292603,522 "learning_rate": 0.0002,523 "loss": 0.6308,524 "step": 65000525 },526 {527 "epoch": 5.12,528 "grad_norm": 1.0901002883911133,529 "learning_rate": 0.0002,530 "loss": 0.6192,531 "step": 66000532 },533 {534 "epoch": 5.2,535 "grad_norm": 1.3939250707626343,536 "learning_rate": 0.0002,537 "loss": 0.6217,538 "step": 67000539 },540 {541 "epoch": 5.28,542 "grad_norm": 0.9105481505393982,543 "learning_rate": 0.0002,544 "loss": 0.6177,545 "step": 68000546 },547 {548 "epoch": 5.36,549 "grad_norm": 0.944652795791626,550 "learning_rate": 0.0002,551 "loss": 0.6227,552 "step": 69000553 },554 {555 "epoch": 5.43,556 "grad_norm": 1.1488838195800781,557 "learning_rate": 0.0002,558 "loss": 0.6215,559 "step": 70000560 },561 {562 "epoch": 5.43,563 "eval_bleu": 60.4701,564 "eval_gen_len": 28.7534,565 "eval_loss": 0.5161064863204956,566 "eval_runtime": 100.914,567 "eval_samples_per_second": 8.8,568 "eval_steps_per_second": 1.1,569 "step": 70000570 },571 {572 "epoch": 5.51,573 "grad_norm": 1.0799453258514404,574 "learning_rate": 0.0002,575 "loss": 0.6173,576 "step": 71000577 },578 {579 "epoch": 5.59,580 "grad_norm": 1.2405527830123901,581 "learning_rate": 0.0002,582 "loss": 0.6229,583 "step": 72000584 },585 {586 "epoch": 5.67,587 "grad_norm": 1.045590877532959,588 "learning_rate": 0.0002,589 "loss": 0.6183,590 "step": 73000591 },592 {593 "epoch": 5.74,594 "grad_norm": 1.4318771362304688,595 "learning_rate": 0.0002,596 "loss": 0.6146,597 "step": 74000598 },599 {600 "epoch": 5.82,601 "grad_norm": 1.0059374570846558,602 "learning_rate": 0.0002,603 "loss": 0.6175,604 "step": 75000605 },606 {607 "epoch": 5.9,608 "grad_norm": 1.0831586122512817,609 "learning_rate": 0.0002,610 "loss": 0.6165,611 "step": 76000612 },613 {614 "epoch": 5.98,615 "grad_norm": 1.4094606637954712,616 "learning_rate": 0.0002,617 "loss": 0.6158,618 "step": 77000619 },620 {621 "epoch": 6.05,622 "grad_norm": 1.2640748023986816,623 "learning_rate": 0.0002,624 "loss": 0.5827,625 "step": 78000626 },627 {628 "epoch": 6.13,629 "grad_norm": 1.0088295936584473,630 "learning_rate": 0.0002,631 "loss": 0.5699,632 "step": 79000633 },634 {635 "epoch": 6.21,636 "grad_norm": 0.9942078590393066,637 "learning_rate": 0.0002,638 "loss": 0.5756,639 "step": 80000640 },641 {642 "epoch": 6.21,643 "eval_bleu": 62.0864,644 "eval_gen_len": 28.6498,645 "eval_loss": 0.5067651867866516,646 "eval_runtime": 99.2392,647 "eval_samples_per_second": 8.948,648 "eval_steps_per_second": 1.119,649 "step": 80000650 },651 {652 "epoch": 6.29,653 "grad_norm": 1.838376522064209,654 "learning_rate": 0.0002,655 "loss": 0.5784,656 "step": 81000657 },658 {659 "epoch": 6.37,660 "grad_norm": 1.477137804031372,661 "learning_rate": 0.0002,662 "loss": 0.5743,663 "step": 82000664 },665 {666 "epoch": 6.44,667 "grad_norm": 1.1481742858886719,668 "learning_rate": 0.0002,669 "loss": 0.578,670 "step": 83000671 },672 {673 "epoch": 6.52,674 "grad_norm": 1.1412264108657837,675 "learning_rate": 0.0002,676 "loss": 0.5785,677 "step": 84000678 },679 {680 "epoch": 6.6,681 "grad_norm": 0.9707184433937073,682 "learning_rate": 0.0002,683 "loss": 0.5746,684 "step": 85000685 },686 {687 "epoch": 6.68,688 "grad_norm": 0.9683183431625366,689 "learning_rate": 0.0002,690 "loss": 0.5794,691 "step": 86000692 },693 {694 "epoch": 6.75,695 "grad_norm": 1.2322285175323486,696 "learning_rate": 0.0002,697 "loss": 0.5765,698 "step": 87000699 },700 {701 "epoch": 6.83,702 "grad_norm": 1.1276684999465942,703 "learning_rate": 0.0002,704 "loss": 0.5767,705 "step": 88000706 },707 {708 "epoch": 6.91,709 "grad_norm": 1.4353203773498535,710 "learning_rate": 0.0002,711 "loss": 0.5776,712 "step": 89000713 },714 {715 "epoch": 6.99,716 "grad_norm": 1.116827368736267,717 "learning_rate": 0.0002,718 "loss": 0.5738,719 "step": 90000720 },721 {722 "epoch": 6.99,723 "eval_bleu": 61.9714,724 "eval_gen_len": 28.5788,725 "eval_loss": 0.5005396008491516,726 "eval_runtime": 98.6774,727 "eval_samples_per_second": 8.999,728 "eval_steps_per_second": 1.125,729 "step": 90000730 },731 {732 "epoch": 7.06,733 "grad_norm": 1.0088461637496948,734 "learning_rate": 0.0002,735 "loss": 0.538,736 "step": 91000737 },738 {739 "epoch": 7.14,740 "grad_norm": 1.1016899347305298,741 "learning_rate": 0.0002,742 "loss": 0.5349,743 "step": 92000744 },745 {746 "epoch": 7.22,747 "grad_norm": 1.4406321048736572,748 "learning_rate": 0.0002,749 "loss": 0.5408,750 "step": 93000751 },752 {753 "epoch": 7.3,754 "grad_norm": 1.1226301193237305,755 "learning_rate": 0.0002,756 "loss": 0.5362,757 "step": 94000758 },759 {760 "epoch": 7.37,761 "grad_norm": 1.4062280654907227,762 "learning_rate": 0.0002,763 "loss": 0.5381,764 "step": 95000765 },766 {767 "epoch": 7.45,768 "grad_norm": 1.2851547002792358,769 "learning_rate": 0.0002,770 "loss": 0.5438,771 "step": 96000772 },773 {774 "epoch": 7.53,775 "grad_norm": 0.9344896078109741,776 "learning_rate": 0.0002,777 "loss": 0.5442,778 "step": 97000779 },780 {781 "epoch": 7.61,782 "grad_norm": 1.7169030904769897,783 "learning_rate": 0.0002,784 "loss": 0.539,785 "step": 98000786 },787 {788 "epoch": 7.69,789 "grad_norm": 1.1855800151824951,790 "learning_rate": 0.0002,791 "loss": 0.543,792 "step": 99000793 },794 {795 "epoch": 7.76,796 "grad_norm": 1.093122959136963,797 "learning_rate": 0.0002,798 "loss": 0.5384,799 "step": 100000800 },801 {802 "epoch": 7.76,803 "eval_bleu": 62.407,804 "eval_gen_len": 28.5282,805 "eval_loss": 0.49085742235183716,806 "eval_runtime": 98.8889,807 "eval_samples_per_second": 8.98,808 "eval_steps_per_second": 1.122,809 "step": 100000810 },811 {812 "epoch": 7.84,813 "grad_norm": 1.3849202394485474,814 "learning_rate": 0.0002,815 "loss": 0.5381,816 "step": 101000817 },818 {819 "epoch": 7.92,820 "grad_norm": 1.12773859500885,821 "learning_rate": 0.0002,822 "loss": 0.544,823 "step": 102000824 },825 {826 "epoch": 8.0,827 "grad_norm": 0.9132428169250488,828 "learning_rate": 0.0002,829 "loss": 0.5371,830 "step": 103000831 },832 {833 "epoch": 8.07,834 "grad_norm": 1.5978176593780518,835 "learning_rate": 0.0002,836 "loss": 0.5015,837 "step": 104000838 },839 {840 "epoch": 8.15,841 "grad_norm": 1.028082013130188,842 "learning_rate": 0.0002,843 "loss": 0.4956,844 "step": 105000845 },846 {847 "epoch": 8.23,848 "grad_norm": 1.0597223043441772,849 "learning_rate": 0.0002,850 "loss": 0.5074,851 "step": 106000852 },853 {854 "epoch": 8.31,855 "grad_norm": 1.47709059715271,856 "learning_rate": 0.0002,857 "loss": 0.5022,858 "step": 107000859 },860 {861 "epoch": 8.38,862 "grad_norm": 1.1731916666030884,863 "learning_rate": 0.0002,864 "loss": 0.5039,865 "step": 108000866 },867 {868 "epoch": 8.46,869 "grad_norm": 1.2147469520568848,870 "learning_rate": 0.0002,871 "loss": 0.5121,872 "step": 109000873 },874 {875 "epoch": 8.54,876 "grad_norm": 0.8521010279655457,877 "learning_rate": 0.0002,878 "loss": 0.5109,879 "step": 110000880 },881 {882 "epoch": 8.54,883 "eval_bleu": 62.1452,884 "eval_gen_len": 28.4617,885 "eval_loss": 0.4901648759841919,886 "eval_runtime": 98.4744,887 "eval_samples_per_second": 9.018,888 "eval_steps_per_second": 1.127,889 "step": 110000890 },891 {892 "epoch": 8.62,893 "grad_norm": 1.250752568244934,894 "learning_rate": 0.0002,895 "loss": 0.5072,896 "step": 111000897 },898 {899 "epoch": 8.69,900 "grad_norm": 1.2694823741912842,901 "learning_rate": 0.0002,902 "loss": 0.5126,903 "step": 112000904 },905 {906 "epoch": 8.77,907 "grad_norm": 1.0290015935897827,908 "learning_rate": 0.0002,909 "loss": 0.5065,910 "step": 113000911 },912 {913 "epoch": 8.85,914 "grad_norm": 1.222034215927124,915 "learning_rate": 0.0002,916 "loss": 0.514,917 "step": 114000918 },919 {920 "epoch": 8.93,921 "grad_norm": 1.0359649658203125,922 "learning_rate": 0.0002,923 "loss": 0.5127,924 "step": 115000925 },926 {927 "epoch": 9.0,928 "grad_norm": 1.19712495803833,929 "learning_rate": 0.0002,930 "loss": 0.5114,931 "step": 116000932 },933 {934 "epoch": 9.08,935 "grad_norm": 1.1766573190689087,936 "learning_rate": 0.0002,937 "loss": 0.4698,938 "step": 117000939 },940 {941 "epoch": 9.16,942 "grad_norm": 1.2681427001953125,943 "learning_rate": 0.0002,944 "loss": 0.4755,945 "step": 118000946 },947 {948 "epoch": 9.24,949 "grad_norm": 1.2988672256469727,950 "learning_rate": 0.0002,951 "loss": 0.4772,952 "step": 119000953 },954 {955 "epoch": 9.32,956 "grad_norm": 1.440721035003662,957 "learning_rate": 0.0002,958 "loss": 0.4816,959 "step": 120000960 },961 {962 "epoch": 9.32,963 "eval_bleu": 62.6499,964 "eval_gen_len": 28.5518,965 "eval_loss": 0.48750796914100647,966 "eval_runtime": 99.0223,967 "eval_samples_per_second": 8.968,968 "eval_steps_per_second": 1.121,969 "step": 120000970 },971 {972 "epoch": 9.39,973 "grad_norm": 1.038442611694336,974 "learning_rate": 0.0002,975 "loss": 0.4792,976 "step": 121000977 },978 {979 "epoch": 9.47,980 "grad_norm": 1.3428473472595215,981 "learning_rate": 0.0002,982 "loss": 0.4827,983 "step": 122000984 },985 {986 "epoch": 9.55,987 "grad_norm": 1.4756362438201904,988 "learning_rate": 0.0002,989 "loss": 0.4832,990 "step": 123000991 },992 {993 "epoch": 9.63,994 "grad_norm": 1.2109817266464233,995 "learning_rate": 0.0002,996 "loss": 0.481,997 "step": 124000998 },999 {1000 "epoch": 9.7,1001 "grad_norm": 1.2007863521575928,1002 "learning_rate": 0.0002,1003 "loss": 0.4815,1004 "step": 1250001005 },1006 {1007 "epoch": 9.78,1008 "grad_norm": 1.1711379289627075,1009 "learning_rate": 0.0002,1010 "loss": 0.488,1011 "step": 1260001012 },1013 {1014 "epoch": 9.86,1015 "grad_norm": 1.1571533679962158,1016 "learning_rate": 0.0002,1017 "loss": 0.4827,1018 "step": 1270001019 },1020 {1021 "epoch": 9.94,1022 "grad_norm": 1.2341859340667725,1023 "learning_rate": 0.0002,1024 "loss": 0.4844,1025 "step": 1280001026 },1027 {1028 "epoch": 10.01,1029 "grad_norm": 1.5796501636505127,1030 "learning_rate": 0.0002,1031 "loss": 0.4741,1032 "step": 1290001033 },1034 {1035 "epoch": 10.09,1036 "grad_norm": 0.8122438788414001,1037 "learning_rate": 0.0002,1038 "loss": 0.4493,1039 "step": 1300001040 },1041 {1042 "epoch": 10.09,1043 "eval_bleu": 62.6694,1044 "eval_gen_len": 28.6993,1045 "eval_loss": 0.4866686761379242,1046 "eval_runtime": 100.7784,1047 "eval_samples_per_second": 8.811,1048 "eval_steps_per_second": 1.101,1049 "step": 1300001050 },1051 {1052 "epoch": 10.17,1053 "grad_norm": 1.1835366487503052,1054 "learning_rate": 0.0002,1055 "loss": 0.448,1056 "step": 1310001057 },1058 {1059 "epoch": 10.25,1060 "grad_norm": 1.0868804454803467,1061 "learning_rate": 0.0002,1062 "loss": 0.4517,1063 "step": 1320001064 },1065 {1066 "epoch": 10.32,1067 "grad_norm": 0.9316431283950806,1068 "learning_rate": 0.0002,1069 "loss": 0.454,1070 "step": 1330001071 },1072 {1073 "epoch": 10.4,1074 "grad_norm": 1.5438517332077026,1075 "learning_rate": 0.0002,1076 "loss": 0.4526,1077 "step": 1340001078 },1079 {1080 "epoch": 10.48,1081 "grad_norm": 1.5842955112457275,1082 "learning_rate": 0.0002,1083 "loss": 0.4576,1084 "step": 1350001085 },1086 {1087 "epoch": 10.56,1088 "grad_norm": 1.450462818145752,1089 "learning_rate": 0.0002,1090 "loss": 0.463,1091 "step": 1360001092 },1093 {1094 "epoch": 10.63,1095 "grad_norm": 0.8578802347183228,1096 "learning_rate": 0.0002,1097 "loss": 0.4588,1098 "step": 1370001099 },1100 {1101 "epoch": 10.71,1102 "grad_norm": 1.1508352756500244,1103 "learning_rate": 0.0002,1104 "loss": 0.4542,1105 "step": 1380001106 },1107 {1108 "epoch": 10.79,1109 "grad_norm": 1.1183589696884155,1110 "learning_rate": 0.0002,1111 "loss": 0.4601,1112 "step": 1390001113 },1114 {1115 "epoch": 10.87,1116 "grad_norm": 0.9286684393882751,1117 "learning_rate": 0.0002,1118 "loss": 0.4648,1119 "step": 1400001120 },1121 {1122 "epoch": 10.87,1123 "eval_bleu": 63.3179,1124 "eval_gen_len": 28.5495,1125 "eval_loss": 0.4774705469608307,1126 "eval_runtime": 98.6639,1127 "eval_samples_per_second": 9.0,1128 "eval_steps_per_second": 1.125,1129 "step": 1400001130 },1131 {1132 "epoch": 10.95,1133 "grad_norm": 1.3315681219100952,1134 "learning_rate": 0.0002,1135 "loss": 0.4627,1136 "step": 1410001137 },1138 {1139 "epoch": 11.02,1140 "grad_norm": 1.204750418663025,1141 "learning_rate": 0.0002,1142 "loss": 0.4497,1143 "step": 1420001144 },1145 {1146 "epoch": 11.1,1147 "grad_norm": 1.0254498720169067,1148 "learning_rate": 0.0002,1149 "loss": 0.4242,1150 "step": 1430001151 },1152 {1153 "epoch": 11.18,1154 "grad_norm": 1.052018404006958,1155 "learning_rate": 0.0002,1156 "loss": 0.4306,1157 "step": 1440001158 },1159 {1160 "epoch": 11.26,1161 "grad_norm": 0.9426015019416809,1162 "learning_rate": 0.0002,1163 "loss": 0.4275,1164 "step": 1450001165 },1166 {1167 "epoch": 11.33,1168 "grad_norm": 1.079633116722107,1169 "learning_rate": 0.0002,1170 "loss": 0.4303,1171 "step": 1460001172 },1173 {1174 "epoch": 11.41,1175 "grad_norm": 1.025631070137024,1176 "learning_rate": 0.0002,1177 "loss": 0.433,1178 "step": 1470001179 },1180 {1181 "epoch": 11.49,1182 "grad_norm": 1.21865713596344,1183 "learning_rate": 0.0002,1184 "loss": 0.4351,1185 "step": 1480001186 },1187 {1188 "epoch": 11.57,1189 "grad_norm": 1.0304579734802246,1190 "learning_rate": 0.0002,1191 "loss": 0.4358,1192 "step": 1490001193 },1194 {1195 "epoch": 11.64,1196 "grad_norm": 1.297282338142395,1197 "learning_rate": 0.0002,1198 "loss": 0.4414,1199 "step": 1500001200 },