diff --git "a/checkpoint-763190/trainer_state.json" "b/checkpoint-763190/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-763190/trainer_state.json" @@ -0,0 +1,9045 @@ +{ + "best_metric": 4.074104309082031, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/rel-cl/lstm/4/checkpoints/checkpoint-763190", + "epoch": 0.025000278439663435, + "eval_steps": 10, + "global_step": 763190, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 4.999998362119627e-05, + "loss": 10.8208, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 7.5681, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 7.0543, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 6.9781, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 6.9513, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 6.853, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 6.725, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 6.6242, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 6.5398, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 6.4465, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 6.3928, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 6.3159, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 6.243, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989098268236324e-05, + "loss": 6.1756, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988259673485272e-05, + "loss": 6.1279, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.98742107873422e-05, + "loss": 6.0907, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986582483983168e-05, + "loss": 6.049, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985743889232116e-05, + "loss": 5.995, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984905294481064e-05, + "loss": 5.9568, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984066699730012e-05, + "loss": 5.9174, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.8778, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.982391148108281e-05, + "loss": 5.8494, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.981552553357229e-05, + "loss": 5.8176, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.980713958606178e-05, + "loss": 5.784, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 5.7541, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790384069844466e-05, + "loss": 5.7369, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9781998122333946e-05, + "loss": 5.7035, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773612174823426e-05, + "loss": 5.6817, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 5.6452, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756856658606115e-05, + "loss": 5.6414, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748470711095595e-05, + "loss": 5.6096, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.974008476358507e-05, + "loss": 5.5922, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 5.5836, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.9723329247367764e-05, + "loss": 5.5653, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.9714943299857244e-05, + "loss": 5.5353, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.9706557352346724e-05, + "loss": 5.5227, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969820416244367e-05, + "loss": 5.5151, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968981821493315e-05, + "loss": 5.4915, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.968143226742263e-05, + "loss": 5.4802, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967304631991211e-05, + "loss": 5.4601, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 5.4353, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 5.4248, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 5.4113, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 5.403, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.963113296116324e-05, + "loss": 5.3914, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 5.386, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 5.3616, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 5.3616, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.9597605549924894e-05, + "loss": 5.3657, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.9589219602414374e-05, + "loss": 5.3372, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958083365490385e-05, + "loss": 5.3266, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957244770739333e-05, + "loss": 5.3148, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956407813868654e-05, + "loss": 5.3236, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.955570856997975e-05, + "loss": 5.2862, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.954732262246923e-05, + "loss": 5.3039, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.953893667495871e-05, + "loss": 5.2737, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.953055072744819e-05, + "loss": 5.2707, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.952216477993767e-05, + "loss": 5.2651, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951377883242715e-05, + "loss": 5.2549, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950540926372037e-05, + "loss": 5.2412, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949702331620985e-05, + "loss": 5.2298, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948863736869932e-05, + "loss": 5.2154, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.94802514211888e-05, + "loss": 5.222, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947186547367828e-05, + "loss": 5.2089, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946349590497149e-05, + "loss": 5.1993, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945510995746097e-05, + "loss": 5.1913, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944672400995045e-05, + "loss": 5.182, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943833806243993e-05, + "loss": 5.1639, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 5.1817, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.942156616741889e-05, + "loss": 5.159, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.9413196598712105e-05, + "loss": 5.1512, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404810651201585e-05, + "loss": 5.16, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396424703691065e-05, + "loss": 5.136, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388038756180545e-05, + "loss": 5.1494, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379669187473754e-05, + "loss": 5.1395, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371283239963234e-05, + "loss": 5.1287, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362897292452714e-05, + "loss": 5.1284, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.9354511344942194e-05, + "loss": 5.1021, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.9346125397431674e-05, + "loss": 5.1005, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.9337739449921154e-05, + "loss": 5.0972, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.932936988121436e-05, + "loss": 5.0964, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.932100031250758e-05, + "loss": 5.0856, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931261436499706e-05, + "loss": 5.0738, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930422841748654e-05, + "loss": 5.0588, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929584246997602e-05, + "loss": 5.0659, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.92874565224655e-05, + "loss": 5.0642, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927907057495498e-05, + "loss": 5.0614, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927068462744446e-05, + "loss": 5.0583, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926229867993394e-05, + "loss": 5.0528, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925391273242342e-05, + "loss": 5.0403, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.92455267849129e-05, + "loss": 5.0224, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923715721620611e-05, + "loss": 5.0187, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922877126869559e-05, + "loss": 5.0257, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.92204016999888e-05, + "loss": 5.0202, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921201575247828e-05, + "loss": 4.9978, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920362980496776e-05, + "loss": 5.0022, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919524385745724e-05, + "loss": 5.0014, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918685790994672e-05, + "loss": 5.0008, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.917848834123993e-05, + "loss": 4.9918, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.917010239372941e-05, + "loss": 4.9929, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.916171644621889e-05, + "loss": 4.9855, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.915333049870837e-05, + "loss": 4.9765, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914494455119785e-05, + "loss": 4.9745, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.9136558603687325e-05, + "loss": 4.9757, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.9128172656176805e-05, + "loss": 4.9602, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.9119786708666285e-05, + "loss": 4.9637, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.91114171399595e-05, + "loss": 4.9405, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910304757125272e-05, + "loss": 4.9354, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.90946616237422e-05, + "loss": 4.9348, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908627567623168e-05, + "loss": 4.9409, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907788972872115e-05, + "loss": 4.9314, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.906950378121063e-05, + "loss": 4.9087, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906111783370011e-05, + "loss": 4.9141, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905273188618959e-05, + "loss": 4.919, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904434593867907e-05, + "loss": 4.9243, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903595999116855e-05, + "loss": 4.9111, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.902759042246176e-05, + "loss": 4.9118, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.901920447495124e-05, + "loss": 4.9058, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.901081852744072e-05, + "loss": 4.9083, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.90024325799302e-05, + "loss": 4.8923, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8994046632419686e-05, + "loss": 4.8944, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985660684909166e-05, + "loss": 4.8834, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977274737398646e-05, + "loss": 4.8886, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968905168691855e-05, + "loss": 4.8694, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960519221181335e-05, + "loss": 4.8835, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952149652474544e-05, + "loss": 4.8724, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943763704964024e-05, + "loss": 4.8802, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935377757453504e-05, + "loss": 4.8519, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.8926991809942984e-05, + "loss": 4.8641, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.8918605862432463e-05, + "loss": 4.8732, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.8910219914921943e-05, + "loss": 4.8464, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.8901833967411423e-05, + "loss": 4.8651, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.88934480199009e-05, + "loss": 4.8492, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888506207239038e-05, + "loss": 4.8514, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.887667612487986e-05, + "loss": 4.8419, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886830655617308e-05, + "loss": 4.8377, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885993698746629e-05, + "loss": 4.8368, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.885155103995577e-05, + "loss": 4.8365, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884316509244525e-05, + "loss": 4.8361, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883477914493473e-05, + "loss": 4.8294, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882639319742421e-05, + "loss": 4.8323, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881800724991369e-05, + "loss": 4.8305, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.880962130240316e-05, + "loss": 4.8108, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880123535489264e-05, + "loss": 4.8115, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879284940738212e-05, + "loss": 4.8025, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.87844634598716e-05, + "loss": 4.8038, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877607751236109e-05, + "loss": 4.8039, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.87677079436543e-05, + "loss": 4.7967, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875932199614378e-05, + "loss": 4.7955, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875093604863326e-05, + "loss": 4.7938, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.755862236022949, + "eval_runtime": 556.7302, + "eval_samples_per_second": 685.415, + "eval_steps_per_second": 21.42, + "step": 76319 + }, + { + "epoch": 0.0, + "learning_rate": 4.874255010112274e-05, + "loss": 4.8042, + "step": 76800 + }, + { + "epoch": 0.0, + "learning_rate": 4.873416415361222e-05, + "loss": 4.795, + "step": 77312 + }, + { + "epoch": 0.0, + "learning_rate": 4.87257782061017e-05, + "loss": 4.7841, + "step": 77824 + }, + { + "epoch": 0.0, + "learning_rate": 4.871739225859118e-05, + "loss": 4.7864, + "step": 78336 + }, + { + "epoch": 0.0, + "learning_rate": 4.8709006311080657e-05, + "loss": 4.779, + "step": 78848 + }, + { + "epoch": 0.0, + "learning_rate": 4.8700620363570137e-05, + "loss": 4.7572, + "step": 79360 + }, + { + "epoch": 0.0, + "learning_rate": 4.8692234416059616e-05, + "loss": 4.7721, + "step": 79872 + }, + { + "epoch": 0.0, + "learning_rate": 4.8683848468549096e-05, + "loss": 4.7738, + "step": 80384 + }, + { + "epoch": 0.0, + "learning_rate": 4.8675462521038576e-05, + "loss": 4.7557, + "step": 80896 + }, + { + "epoch": 0.0, + "learning_rate": 4.8667076573528056e-05, + "loss": 4.7694, + "step": 81408 + }, + { + "epoch": 0.0, + "learning_rate": 4.8658690626017536e-05, + "loss": 4.7739, + "step": 81920 + }, + { + "epoch": 0.0, + "learning_rate": 4.8650304678507016e-05, + "loss": 4.7575, + "step": 82432 + }, + { + "epoch": 0.0, + "learning_rate": 4.8641918730996496e-05, + "loss": 4.7523, + "step": 82944 + }, + { + "epoch": 0.0, + "learning_rate": 4.8633532783485976e-05, + "loss": 4.7528, + "step": 83456 + }, + { + "epoch": 0.0, + "learning_rate": 4.8625146835975456e-05, + "loss": 4.7537, + "step": 83968 + }, + { + "epoch": 0.0, + "learning_rate": 4.8616760888464936e-05, + "loss": 4.7464, + "step": 84480 + }, + { + "epoch": 0.0, + "learning_rate": 4.8608391319758145e-05, + "loss": 4.7423, + "step": 84992 + }, + { + "epoch": 0.0, + "learning_rate": 4.8600021751051354e-05, + "loss": 4.7406, + "step": 85504 + }, + { + "epoch": 0.0, + "learning_rate": 4.8591635803540834e-05, + "loss": 4.7362, + "step": 86016 + }, + { + "epoch": 0.0, + "learning_rate": 4.8583249856030314e-05, + "loss": 4.7415, + "step": 86528 + }, + { + "epoch": 0.0, + "learning_rate": 4.8574863908519794e-05, + "loss": 4.7402, + "step": 87040 + }, + { + "epoch": 0.0, + "learning_rate": 4.8566477961009274e-05, + "loss": 4.7392, + "step": 87552 + }, + { + "epoch": 0.0, + "learning_rate": 4.8558092013498754e-05, + "loss": 4.7343, + "step": 88064 + }, + { + "epoch": 0.0, + "learning_rate": 4.854970606598824e-05, + "loss": 4.733, + "step": 88576 + }, + { + "epoch": 0.0, + "learning_rate": 4.854132011847772e-05, + "loss": 4.7277, + "step": 89088 + }, + { + "epoch": 0.0, + "learning_rate": 4.85329341709672e-05, + "loss": 4.7248, + "step": 89600 + }, + { + "epoch": 0.0, + "learning_rate": 4.852456460226041e-05, + "loss": 4.7267, + "step": 90112 + }, + { + "epoch": 0.0, + "learning_rate": 4.851617865474989e-05, + "loss": 4.7086, + "step": 90624 + }, + { + "epoch": 0.0, + "learning_rate": 4.850779270723937e-05, + "loss": 4.7228, + "step": 91136 + }, + { + "epoch": 0.01, + "learning_rate": 4.849940675972885e-05, + "loss": 4.7032, + "step": 91648 + }, + { + "epoch": 0.01, + "learning_rate": 4.849103719102206e-05, + "loss": 4.7088, + "step": 92160 + }, + { + "epoch": 0.01, + "learning_rate": 4.848265124351154e-05, + "loss": 4.7177, + "step": 92672 + }, + { + "epoch": 0.01, + "learning_rate": 4.847426529600102e-05, + "loss": 4.7162, + "step": 93184 + }, + { + "epoch": 0.01, + "learning_rate": 4.84658793484905e-05, + "loss": 4.7015, + "step": 93696 + }, + { + "epoch": 0.01, + "learning_rate": 4.845750977978371e-05, + "loss": 4.693, + "step": 94208 + }, + { + "epoch": 0.01, + "learning_rate": 4.8449123832273194e-05, + "loss": 4.7097, + "step": 94720 + }, + { + "epoch": 0.01, + "learning_rate": 4.8440737884762674e-05, + "loss": 4.6982, + "step": 95232 + }, + { + "epoch": 0.01, + "learning_rate": 4.8432351937252154e-05, + "loss": 4.6967, + "step": 95744 + }, + { + "epoch": 0.01, + "learning_rate": 4.8423965989741634e-05, + "loss": 4.6938, + "step": 96256 + }, + { + "epoch": 0.01, + "learning_rate": 4.8415580042231114e-05, + "loss": 4.6789, + "step": 96768 + }, + { + "epoch": 0.01, + "learning_rate": 4.840719409472059e-05, + "loss": 4.6769, + "step": 97280 + }, + { + "epoch": 0.01, + "learning_rate": 4.83988245260138e-05, + "loss": 4.6778, + "step": 97792 + }, + { + "epoch": 0.01, + "learning_rate": 4.839043857850328e-05, + "loss": 4.6822, + "step": 98304 + }, + { + "epoch": 0.01, + "learning_rate": 4.838205263099276e-05, + "loss": 4.6756, + "step": 98816 + }, + { + "epoch": 0.01, + "learning_rate": 4.8373666683482236e-05, + "loss": 4.6777, + "step": 99328 + }, + { + "epoch": 0.01, + "learning_rate": 4.836529711477545e-05, + "loss": 4.671, + "step": 99840 + }, + { + "epoch": 0.01, + "learning_rate": 4.835691116726493e-05, + "loss": 4.6728, + "step": 100352 + }, + { + "epoch": 0.01, + "learning_rate": 4.834852521975441e-05, + "loss": 4.6835, + "step": 100864 + }, + { + "epoch": 0.01, + "learning_rate": 4.834013927224389e-05, + "loss": 4.6646, + "step": 101376 + }, + { + "epoch": 0.01, + "learning_rate": 4.833175332473337e-05, + "loss": 4.6665, + "step": 101888 + }, + { + "epoch": 0.01, + "learning_rate": 4.832340013483032e-05, + "loss": 4.6554, + "step": 102400 + }, + { + "epoch": 0.01, + "learning_rate": 4.83150141873198e-05, + "loss": 4.6776, + "step": 102912 + }, + { + "epoch": 0.01, + "learning_rate": 4.830662823980928e-05, + "loss": 4.6471, + "step": 103424 + }, + { + "epoch": 0.01, + "learning_rate": 4.829824229229876e-05, + "loss": 4.6699, + "step": 103936 + }, + { + "epoch": 0.01, + "learning_rate": 4.828985634478824e-05, + "loss": 4.6472, + "step": 104448 + }, + { + "epoch": 0.01, + "learning_rate": 4.828147039727771e-05, + "loss": 4.6551, + "step": 104960 + }, + { + "epoch": 0.01, + "learning_rate": 4.827308444976719e-05, + "loss": 4.655, + "step": 105472 + }, + { + "epoch": 0.01, + "learning_rate": 4.826469850225667e-05, + "loss": 4.6509, + "step": 105984 + }, + { + "epoch": 0.01, + "learning_rate": 4.825631255474615e-05, + "loss": 4.6423, + "step": 106496 + }, + { + "epoch": 0.01, + "learning_rate": 4.824792660723563e-05, + "loss": 4.641, + "step": 107008 + }, + { + "epoch": 0.01, + "learning_rate": 4.823954065972511e-05, + "loss": 4.6303, + "step": 107520 + }, + { + "epoch": 0.01, + "learning_rate": 4.8231171091018326e-05, + "loss": 4.6456, + "step": 108032 + }, + { + "epoch": 0.01, + "learning_rate": 4.8222785143507806e-05, + "loss": 4.6371, + "step": 108544 + }, + { + "epoch": 0.01, + "learning_rate": 4.8214399195997286e-05, + "loss": 4.6306, + "step": 109056 + }, + { + "epoch": 0.01, + "learning_rate": 4.8206013248486766e-05, + "loss": 4.6304, + "step": 109568 + }, + { + "epoch": 0.01, + "learning_rate": 4.8197643679779975e-05, + "loss": 4.6295, + "step": 110080 + }, + { + "epoch": 0.01, + "learning_rate": 4.8189257732269455e-05, + "loss": 4.6114, + "step": 110592 + }, + { + "epoch": 0.01, + "learning_rate": 4.8180871784758935e-05, + "loss": 4.6367, + "step": 111104 + }, + { + "epoch": 0.01, + "learning_rate": 4.8172485837248415e-05, + "loss": 4.623, + "step": 111616 + }, + { + "epoch": 0.01, + "learning_rate": 4.8164099889737895e-05, + "loss": 4.6217, + "step": 112128 + }, + { + "epoch": 0.01, + "learning_rate": 4.8155713942227375e-05, + "loss": 4.6306, + "step": 112640 + }, + { + "epoch": 0.01, + "learning_rate": 4.8147327994716854e-05, + "loss": 4.616, + "step": 113152 + }, + { + "epoch": 0.01, + "learning_rate": 4.8138958426010064e-05, + "loss": 4.63, + "step": 113664 + }, + { + "epoch": 0.01, + "learning_rate": 4.813057247849955e-05, + "loss": 4.6321, + "step": 114176 + }, + { + "epoch": 0.01, + "learning_rate": 4.812218653098903e-05, + "loss": 4.6234, + "step": 114688 + }, + { + "epoch": 0.01, + "learning_rate": 4.811380058347851e-05, + "loss": 4.624, + "step": 115200 + }, + { + "epoch": 0.01, + "learning_rate": 4.810541463596799e-05, + "loss": 4.6059, + "step": 115712 + }, + { + "epoch": 0.01, + "learning_rate": 4.809702868845747e-05, + "loss": 4.6017, + "step": 116224 + }, + { + "epoch": 0.01, + "learning_rate": 4.808864274094695e-05, + "loss": 4.6133, + "step": 116736 + }, + { + "epoch": 0.01, + "learning_rate": 4.808027317224016e-05, + "loss": 4.6147, + "step": 117248 + }, + { + "epoch": 0.01, + "learning_rate": 4.807188722472964e-05, + "loss": 4.6061, + "step": 117760 + }, + { + "epoch": 0.01, + "learning_rate": 4.806350127721912e-05, + "loss": 4.6017, + "step": 118272 + }, + { + "epoch": 0.01, + "learning_rate": 4.80551153297086e-05, + "loss": 4.5863, + "step": 118784 + }, + { + "epoch": 0.01, + "learning_rate": 4.804672938219807e-05, + "loss": 4.5953, + "step": 119296 + }, + { + "epoch": 0.01, + "learning_rate": 4.803834343468755e-05, + "loss": 4.5994, + "step": 119808 + }, + { + "epoch": 0.01, + "learning_rate": 4.802997386598077e-05, + "loss": 4.6007, + "step": 120320 + }, + { + "epoch": 0.01, + "learning_rate": 4.802158791847025e-05, + "loss": 4.6059, + "step": 120832 + }, + { + "epoch": 0.01, + "learning_rate": 4.801320197095973e-05, + "loss": 4.6049, + "step": 121344 + }, + { + "epoch": 0.01, + "learning_rate": 4.800481602344921e-05, + "loss": 4.5933, + "step": 121856 + }, + { + "epoch": 0.02, + "learning_rate": 4.799643007593869e-05, + "loss": 4.5851, + "step": 122368 + }, + { + "epoch": 0.02, + "learning_rate": 4.798804412842817e-05, + "loss": 4.5802, + "step": 122880 + }, + { + "epoch": 0.02, + "learning_rate": 4.797965818091765e-05, + "loss": 4.5868, + "step": 123392 + }, + { + "epoch": 0.02, + "learning_rate": 4.797127223340713e-05, + "loss": 4.5881, + "step": 123904 + }, + { + "epoch": 0.02, + "learning_rate": 4.796290266470034e-05, + "loss": 4.5758, + "step": 124416 + }, + { + "epoch": 0.02, + "learning_rate": 4.795451671718982e-05, + "loss": 4.5771, + "step": 124928 + }, + { + "epoch": 0.02, + "learning_rate": 4.79461307696793e-05, + "loss": 4.5847, + "step": 125440 + }, + { + "epoch": 0.02, + "learning_rate": 4.793774482216878e-05, + "loss": 4.5891, + "step": 125952 + }, + { + "epoch": 0.02, + "learning_rate": 4.792935887465826e-05, + "loss": 4.5774, + "step": 126464 + }, + { + "epoch": 0.02, + "learning_rate": 4.792098930595147e-05, + "loss": 4.5832, + "step": 126976 + }, + { + "epoch": 0.02, + "learning_rate": 4.791260335844095e-05, + "loss": 4.5845, + "step": 127488 + }, + { + "epoch": 0.02, + "learning_rate": 4.790421741093043e-05, + "loss": 4.5767, + "step": 128000 + }, + { + "epoch": 0.02, + "learning_rate": 4.789583146341991e-05, + "loss": 4.5713, + "step": 128512 + }, + { + "epoch": 0.02, + "learning_rate": 4.788744551590939e-05, + "loss": 4.5821, + "step": 129024 + }, + { + "epoch": 0.02, + "learning_rate": 4.78790759472026e-05, + "loss": 4.5684, + "step": 129536 + }, + { + "epoch": 0.02, + "learning_rate": 4.787068999969208e-05, + "loss": 4.5789, + "step": 130048 + }, + { + "epoch": 0.02, + "learning_rate": 4.786230405218156e-05, + "loss": 4.5601, + "step": 130560 + }, + { + "epoch": 0.02, + "learning_rate": 4.785391810467104e-05, + "loss": 4.5503, + "step": 131072 + }, + { + "epoch": 0.02, + "learning_rate": 4.784554853596425e-05, + "loss": 4.5574, + "step": 131584 + }, + { + "epoch": 0.02, + "learning_rate": 4.783716258845373e-05, + "loss": 4.5643, + "step": 132096 + }, + { + "epoch": 0.02, + "learning_rate": 4.782877664094321e-05, + "loss": 4.558, + "step": 132608 + }, + { + "epoch": 0.02, + "learning_rate": 4.782039069343269e-05, + "loss": 4.5463, + "step": 133120 + }, + { + "epoch": 0.02, + "learning_rate": 4.781200474592217e-05, + "loss": 4.5446, + "step": 133632 + }, + { + "epoch": 0.02, + "learning_rate": 4.780361879841165e-05, + "loss": 4.5538, + "step": 134144 + }, + { + "epoch": 0.02, + "learning_rate": 4.779523285090114e-05, + "loss": 4.5647, + "step": 134656 + }, + { + "epoch": 0.02, + "learning_rate": 4.7786863282194346e-05, + "loss": 4.5517, + "step": 135168 + }, + { + "epoch": 0.02, + "learning_rate": 4.7778477334683826e-05, + "loss": 4.5597, + "step": 135680 + }, + { + "epoch": 0.02, + "learning_rate": 4.7770091387173306e-05, + "loss": 4.5555, + "step": 136192 + }, + { + "epoch": 0.02, + "learning_rate": 4.7761705439662786e-05, + "loss": 4.5514, + "step": 136704 + }, + { + "epoch": 0.02, + "learning_rate": 4.775331949215226e-05, + "loss": 4.5476, + "step": 137216 + }, + { + "epoch": 0.02, + "learning_rate": 4.774493354464174e-05, + "loss": 4.5453, + "step": 137728 + }, + { + "epoch": 0.02, + "learning_rate": 4.7736563975934955e-05, + "loss": 4.5405, + "step": 138240 + }, + { + "epoch": 0.02, + "learning_rate": 4.7728178028424435e-05, + "loss": 4.5509, + "step": 138752 + }, + { + "epoch": 0.02, + "learning_rate": 4.771979208091391e-05, + "loss": 4.536, + "step": 139264 + }, + { + "epoch": 0.02, + "learning_rate": 4.771140613340339e-05, + "loss": 4.5382, + "step": 139776 + }, + { + "epoch": 0.02, + "learning_rate": 4.7703036564696604e-05, + "loss": 4.5416, + "step": 140288 + }, + { + "epoch": 0.02, + "learning_rate": 4.7694650617186084e-05, + "loss": 4.5494, + "step": 140800 + }, + { + "epoch": 0.02, + "learning_rate": 4.7686264669675564e-05, + "loss": 4.5264, + "step": 141312 + }, + { + "epoch": 0.02, + "learning_rate": 4.7677878722165044e-05, + "loss": 4.5314, + "step": 141824 + }, + { + "epoch": 0.02, + "learning_rate": 4.7669492774654524e-05, + "loss": 4.5525, + "step": 142336 + }, + { + "epoch": 0.02, + "learning_rate": 4.7661106827144004e-05, + "loss": 4.526, + "step": 142848 + }, + { + "epoch": 0.02, + "learning_rate": 4.7652720879633484e-05, + "loss": 4.5463, + "step": 143360 + }, + { + "epoch": 0.02, + "learning_rate": 4.7644334932122964e-05, + "loss": 4.5298, + "step": 143872 + }, + { + "epoch": 0.02, + "learning_rate": 4.7635948984612444e-05, + "loss": 4.5414, + "step": 144384 + }, + { + "epoch": 0.02, + "learning_rate": 4.762757941590565e-05, + "loss": 4.5284, + "step": 144896 + }, + { + "epoch": 0.02, + "learning_rate": 4.761919346839513e-05, + "loss": 4.5239, + "step": 145408 + }, + { + "epoch": 0.02, + "learning_rate": 4.761080752088461e-05, + "loss": 4.53, + "step": 145920 + }, + { + "epoch": 0.02, + "learning_rate": 4.760242157337409e-05, + "loss": 4.528, + "step": 146432 + }, + { + "epoch": 0.02, + "learning_rate": 4.759403562586357e-05, + "loss": 4.5353, + "step": 146944 + }, + { + "epoch": 0.02, + "learning_rate": 4.758564967835306e-05, + "loss": 4.5302, + "step": 147456 + }, + { + "epoch": 0.02, + "learning_rate": 4.757726373084254e-05, + "loss": 4.5306, + "step": 147968 + }, + { + "epoch": 0.02, + "learning_rate": 4.756887778333202e-05, + "loss": 4.5269, + "step": 148480 + }, + { + "epoch": 0.02, + "learning_rate": 4.756050821462523e-05, + "loss": 4.5135, + "step": 148992 + }, + { + "epoch": 0.02, + "learning_rate": 4.755212226711471e-05, + "loss": 4.5213, + "step": 149504 + }, + { + "epoch": 0.02, + "learning_rate": 4.754373631960419e-05, + "loss": 4.5086, + "step": 150016 + }, + { + "epoch": 0.02, + "learning_rate": 4.75353667508974e-05, + "loss": 4.5149, + "step": 150528 + }, + { + "epoch": 0.02, + "learning_rate": 4.752698080338688e-05, + "loss": 4.5172, + "step": 151040 + }, + { + "epoch": 0.02, + "learning_rate": 4.751859485587636e-05, + "loss": 4.5045, + "step": 151552 + }, + { + "epoch": 0.02, + "learning_rate": 4.751020890836584e-05, + "loss": 4.5124, + "step": 152064 + }, + { + "epoch": 0.02, + "learning_rate": 4.7501839339659046e-05, + "loss": 4.5099, + "step": 152576 + }, + { + "epoch": 0.03, + "eval_loss": 4.475570201873779, + "eval_runtime": 580.8128, + "eval_samples_per_second": 656.995, + "eval_steps_per_second": 20.532, + "step": 152638 + }, + { + "epoch": 1.0, + "learning_rate": 4.7493453392148526e-05, + "loss": 4.5196, + "step": 153088 + }, + { + "epoch": 1.0, + "learning_rate": 4.748506744463801e-05, + "loss": 4.5176, + "step": 153600 + }, + { + "epoch": 1.0, + "learning_rate": 4.747669787593122e-05, + "loss": 4.5069, + "step": 154112 + }, + { + "epoch": 1.0, + "learning_rate": 4.74683119284207e-05, + "loss": 4.5055, + "step": 154624 + }, + { + "epoch": 1.0, + "learning_rate": 4.745992598091018e-05, + "loss": 4.5059, + "step": 155136 + }, + { + "epoch": 1.0, + "learning_rate": 4.745154003339966e-05, + "loss": 4.4882, + "step": 155648 + }, + { + "epoch": 1.0, + "learning_rate": 4.744315408588914e-05, + "loss": 4.5031, + "step": 156160 + }, + { + "epoch": 1.0, + "learning_rate": 4.743476813837862e-05, + "loss": 4.5013, + "step": 156672 + }, + { + "epoch": 1.0, + "learning_rate": 4.7426382190868095e-05, + "loss": 4.4868, + "step": 157184 + }, + { + "epoch": 1.0, + "learning_rate": 4.741801262216131e-05, + "loss": 4.5065, + "step": 157696 + }, + { + "epoch": 1.0, + "learning_rate": 4.740962667465079e-05, + "loss": 4.5106, + "step": 158208 + }, + { + "epoch": 1.0, + "learning_rate": 4.7401240727140264e-05, + "loss": 4.495, + "step": 158720 + }, + { + "epoch": 1.0, + "learning_rate": 4.739285477962975e-05, + "loss": 4.4883, + "step": 159232 + }, + { + "epoch": 1.0, + "learning_rate": 4.738446883211923e-05, + "loss": 4.4931, + "step": 159744 + }, + { + "epoch": 1.0, + "learning_rate": 4.737608288460871e-05, + "loss": 4.4957, + "step": 160256 + }, + { + "epoch": 1.0, + "learning_rate": 4.736769693709819e-05, + "loss": 4.4908, + "step": 160768 + }, + { + "epoch": 1.0, + "learning_rate": 4.735931098958767e-05, + "loss": 4.4859, + "step": 161280 + }, + { + "epoch": 1.0, + "learning_rate": 4.735094142088088e-05, + "loss": 4.4854, + "step": 161792 + }, + { + "epoch": 1.0, + "learning_rate": 4.7342571852174095e-05, + "loss": 4.4861, + "step": 162304 + }, + { + "epoch": 1.0, + "learning_rate": 4.733418590466357e-05, + "loss": 4.4893, + "step": 162816 + }, + { + "epoch": 1.0, + "learning_rate": 4.732579995715305e-05, + "loss": 4.4899, + "step": 163328 + }, + { + "epoch": 1.0, + "learning_rate": 4.731741400964253e-05, + "loss": 4.4921, + "step": 163840 + }, + { + "epoch": 1.0, + "learning_rate": 4.730902806213201e-05, + "loss": 4.4912, + "step": 164352 + }, + { + "epoch": 1.0, + "learning_rate": 4.730064211462149e-05, + "loss": 4.4826, + "step": 164864 + }, + { + "epoch": 1.0, + "learning_rate": 4.729225616711097e-05, + "loss": 4.4868, + "step": 165376 + }, + { + "epoch": 1.0, + "learning_rate": 4.728387021960045e-05, + "loss": 4.4839, + "step": 165888 + }, + { + "epoch": 1.0, + "learning_rate": 4.727548427208993e-05, + "loss": 4.4861, + "step": 166400 + }, + { + "epoch": 1.0, + "learning_rate": 4.7267114703383144e-05, + "loss": 4.4695, + "step": 166912 + }, + { + "epoch": 1.0, + "learning_rate": 4.7258728755872624e-05, + "loss": 4.4822, + "step": 167424 + }, + { + "epoch": 1.01, + "learning_rate": 4.7250342808362104e-05, + "loss": 4.4684, + "step": 167936 + }, + { + "epoch": 1.01, + "learning_rate": 4.7241956860851584e-05, + "loss": 4.4734, + "step": 168448 + }, + { + "epoch": 1.01, + "learning_rate": 4.7233570913341064e-05, + "loss": 4.4844, + "step": 168960 + }, + { + "epoch": 1.01, + "learning_rate": 4.7225184965830544e-05, + "loss": 4.4822, + "step": 169472 + }, + { + "epoch": 1.01, + "learning_rate": 4.721681539712375e-05, + "loss": 4.4693, + "step": 169984 + }, + { + "epoch": 1.01, + "learning_rate": 4.720842944961323e-05, + "loss": 4.4644, + "step": 170496 + }, + { + "epoch": 1.01, + "learning_rate": 4.720004350210271e-05, + "loss": 4.4835, + "step": 171008 + }, + { + "epoch": 1.01, + "learning_rate": 4.719165755459219e-05, + "loss": 4.4654, + "step": 171520 + }, + { + "epoch": 1.01, + "learning_rate": 4.71832879858854e-05, + "loss": 4.4729, + "step": 172032 + }, + { + "epoch": 1.01, + "learning_rate": 4.717490203837488e-05, + "loss": 4.4688, + "step": 172544 + }, + { + "epoch": 1.01, + "learning_rate": 4.716651609086437e-05, + "loss": 4.4536, + "step": 173056 + }, + { + "epoch": 1.01, + "learning_rate": 4.715813014335385e-05, + "loss": 4.4532, + "step": 173568 + }, + { + "epoch": 1.01, + "learning_rate": 4.714974419584333e-05, + "loss": 4.4529, + "step": 174080 + }, + { + "epoch": 1.01, + "learning_rate": 4.714137462713654e-05, + "loss": 4.4676, + "step": 174592 + }, + { + "epoch": 1.01, + "learning_rate": 4.713298867962602e-05, + "loss": 4.4585, + "step": 175104 + }, + { + "epoch": 1.01, + "learning_rate": 4.712461911091923e-05, + "loss": 4.4585, + "step": 175616 + }, + { + "epoch": 1.01, + "learning_rate": 4.711623316340871e-05, + "loss": 4.4521, + "step": 176128 + }, + { + "epoch": 1.01, + "learning_rate": 4.710784721589819e-05, + "loss": 4.455, + "step": 176640 + }, + { + "epoch": 1.01, + "learning_rate": 4.7099461268387667e-05, + "loss": 4.47, + "step": 177152 + }, + { + "epoch": 1.01, + "learning_rate": 4.7091075320877147e-05, + "loss": 4.451, + "step": 177664 + }, + { + "epoch": 1.01, + "learning_rate": 4.7082689373366627e-05, + "loss": 4.4511, + "step": 178176 + }, + { + "epoch": 1.01, + "learning_rate": 4.7074303425856106e-05, + "loss": 4.4458, + "step": 178688 + }, + { + "epoch": 1.01, + "learning_rate": 4.7065917478345586e-05, + "loss": 4.4685, + "step": 179200 + }, + { + "epoch": 1.01, + "learning_rate": 4.70575479096388e-05, + "loss": 4.4375, + "step": 179712 + }, + { + "epoch": 1.01, + "learning_rate": 4.704916196212828e-05, + "loss": 4.4592, + "step": 180224 + }, + { + "epoch": 1.01, + "learning_rate": 4.7040776014617755e-05, + "loss": 4.4375, + "step": 180736 + }, + { + "epoch": 1.01, + "learning_rate": 4.7032390067107235e-05, + "loss": 4.4499, + "step": 181248 + }, + { + "epoch": 1.01, + "learning_rate": 4.7024004119596715e-05, + "loss": 4.4518, + "step": 181760 + }, + { + "epoch": 1.01, + "learning_rate": 4.7015618172086195e-05, + "loss": 4.4399, + "step": 182272 + }, + { + "epoch": 1.01, + "learning_rate": 4.7007232224575675e-05, + "loss": 4.4454, + "step": 182784 + }, + { + "epoch": 1.01, + "learning_rate": 4.6998862655868884e-05, + "loss": 4.4386, + "step": 183296 + }, + { + "epoch": 1.01, + "learning_rate": 4.6990476708358364e-05, + "loss": 4.4234, + "step": 183808 + }, + { + "epoch": 1.01, + "learning_rate": 4.6982090760847844e-05, + "loss": 4.4425, + "step": 184320 + }, + { + "epoch": 1.01, + "learning_rate": 4.6973704813337324e-05, + "loss": 4.4416, + "step": 184832 + }, + { + "epoch": 1.01, + "learning_rate": 4.6965318865826804e-05, + "loss": 4.4332, + "step": 185344 + }, + { + "epoch": 1.01, + "learning_rate": 4.695693291831629e-05, + "loss": 4.4333, + "step": 185856 + }, + { + "epoch": 1.01, + "learning_rate": 4.694854697080577e-05, + "loss": 4.4328, + "step": 186368 + }, + { + "epoch": 1.01, + "learning_rate": 4.694016102329525e-05, + "loss": 4.416, + "step": 186880 + }, + { + "epoch": 1.01, + "learning_rate": 4.693177507578473e-05, + "loss": 4.4439, + "step": 187392 + }, + { + "epoch": 1.01, + "learning_rate": 4.692338912827421e-05, + "loss": 4.4246, + "step": 187904 + }, + { + "epoch": 1.01, + "learning_rate": 4.691500318076369e-05, + "loss": 4.4283, + "step": 188416 + }, + { + "epoch": 1.01, + "learning_rate": 4.69066336120569e-05, + "loss": 4.4389, + "step": 188928 + }, + { + "epoch": 1.01, + "learning_rate": 4.689824766454638e-05, + "loss": 4.4266, + "step": 189440 + }, + { + "epoch": 1.01, + "learning_rate": 4.688986171703586e-05, + "loss": 4.4369, + "step": 189952 + }, + { + "epoch": 1.01, + "learning_rate": 4.688147576952534e-05, + "loss": 4.4458, + "step": 190464 + }, + { + "epoch": 1.01, + "learning_rate": 4.687310620081855e-05, + "loss": 4.4315, + "step": 190976 + }, + { + "epoch": 1.01, + "learning_rate": 4.686473663211176e-05, + "loss": 4.4403, + "step": 191488 + }, + { + "epoch": 1.01, + "learning_rate": 4.6856350684601245e-05, + "loss": 4.421, + "step": 192000 + }, + { + "epoch": 1.01, + "learning_rate": 4.6847964737090725e-05, + "loss": 4.4132, + "step": 192512 + }, + { + "epoch": 1.01, + "learning_rate": 4.6839578789580204e-05, + "loss": 4.4257, + "step": 193024 + }, + { + "epoch": 1.01, + "learning_rate": 4.6831192842069684e-05, + "loss": 4.433, + "step": 193536 + }, + { + "epoch": 1.01, + "learning_rate": 4.6822823273362894e-05, + "loss": 4.4239, + "step": 194048 + }, + { + "epoch": 1.01, + "learning_rate": 4.6814437325852373e-05, + "loss": 4.4159, + "step": 194560 + }, + { + "epoch": 1.01, + "learning_rate": 4.6806051378341853e-05, + "loss": 4.4077, + "step": 195072 + }, + { + "epoch": 1.01, + "learning_rate": 4.6797665430831333e-05, + "loss": 4.4131, + "step": 195584 + }, + { + "epoch": 1.01, + "learning_rate": 4.678927948332081e-05, + "loss": 4.4144, + "step": 196096 + }, + { + "epoch": 1.01, + "learning_rate": 4.6780893535810287e-05, + "loss": 4.4198, + "step": 196608 + }, + { + "epoch": 1.01, + "learning_rate": 4.6772507588299766e-05, + "loss": 4.4269, + "step": 197120 + }, + { + "epoch": 1.01, + "learning_rate": 4.6764121640789246e-05, + "loss": 4.4257, + "step": 197632 + }, + { + "epoch": 1.01, + "learning_rate": 4.6755735693278726e-05, + "loss": 4.4144, + "step": 198144 + }, + { + "epoch": 1.02, + "learning_rate": 4.6747349745768206e-05, + "loss": 4.4102, + "step": 198656 + }, + { + "epoch": 1.02, + "learning_rate": 4.673896379825769e-05, + "loss": 4.4057, + "step": 199168 + }, + { + "epoch": 1.02, + "learning_rate": 4.673057785074717e-05, + "loss": 4.411, + "step": 199680 + }, + { + "epoch": 1.02, + "learning_rate": 4.672222466084412e-05, + "loss": 4.4095, + "step": 200192 + }, + { + "epoch": 1.02, + "learning_rate": 4.671383871333359e-05, + "loss": 4.4066, + "step": 200704 + }, + { + "epoch": 1.02, + "learning_rate": 4.670545276582307e-05, + "loss": 4.4037, + "step": 201216 + }, + { + "epoch": 1.02, + "learning_rate": 4.669706681831255e-05, + "loss": 4.4139, + "step": 201728 + }, + { + "epoch": 1.02, + "learning_rate": 4.668868087080203e-05, + "loss": 4.4117, + "step": 202240 + }, + { + "epoch": 1.02, + "learning_rate": 4.668031130209524e-05, + "loss": 4.4108, + "step": 202752 + }, + { + "epoch": 1.02, + "learning_rate": 4.667192535458472e-05, + "loss": 4.4111, + "step": 203264 + }, + { + "epoch": 1.02, + "learning_rate": 4.66635394070742e-05, + "loss": 4.4153, + "step": 203776 + }, + { + "epoch": 1.02, + "learning_rate": 4.665515345956368e-05, + "loss": 4.4077, + "step": 204288 + }, + { + "epoch": 1.02, + "learning_rate": 4.6646783890856896e-05, + "loss": 4.4005, + "step": 204800 + }, + { + "epoch": 1.02, + "learning_rate": 4.6638397943346376e-05, + "loss": 4.4196, + "step": 205312 + }, + { + "epoch": 1.02, + "learning_rate": 4.6630011995835856e-05, + "loss": 4.3968, + "step": 205824 + }, + { + "epoch": 1.02, + "learning_rate": 4.6621626048325336e-05, + "loss": 4.4186, + "step": 206336 + }, + { + "epoch": 1.02, + "learning_rate": 4.6613240100814816e-05, + "loss": 4.3909, + "step": 206848 + }, + { + "epoch": 1.02, + "learning_rate": 4.6604854153304296e-05, + "loss": 4.3842, + "step": 207360 + }, + { + "epoch": 1.02, + "learning_rate": 4.6596468205793776e-05, + "loss": 4.3936, + "step": 207872 + }, + { + "epoch": 1.02, + "learning_rate": 4.6588082258283256e-05, + "loss": 4.4058, + "step": 208384 + }, + { + "epoch": 1.02, + "learning_rate": 4.6579712689576465e-05, + "loss": 4.3966, + "step": 208896 + }, + { + "epoch": 1.02, + "learning_rate": 4.6571326742065945e-05, + "loss": 4.3838, + "step": 209408 + }, + { + "epoch": 1.02, + "learning_rate": 4.6562940794555425e-05, + "loss": 4.3827, + "step": 209920 + }, + { + "epoch": 1.02, + "learning_rate": 4.6554554847044905e-05, + "loss": 4.3919, + "step": 210432 + }, + { + "epoch": 1.02, + "learning_rate": 4.6546185278338114e-05, + "loss": 4.406, + "step": 210944 + }, + { + "epoch": 1.02, + "learning_rate": 4.65377993308276e-05, + "loss": 4.3915, + "step": 211456 + }, + { + "epoch": 1.02, + "learning_rate": 4.652941338331708e-05, + "loss": 4.4, + "step": 211968 + }, + { + "epoch": 1.02, + "learning_rate": 4.652102743580656e-05, + "loss": 4.3953, + "step": 212480 + }, + { + "epoch": 1.02, + "learning_rate": 4.651264148829604e-05, + "loss": 4.3924, + "step": 212992 + }, + { + "epoch": 1.02, + "learning_rate": 4.650425554078552e-05, + "loss": 4.3948, + "step": 213504 + }, + { + "epoch": 1.02, + "learning_rate": 4.649588597207873e-05, + "loss": 4.386, + "step": 214016 + }, + { + "epoch": 1.02, + "learning_rate": 4.648750002456821e-05, + "loss": 4.3865, + "step": 214528 + }, + { + "epoch": 1.02, + "learning_rate": 4.647911407705769e-05, + "loss": 4.3941, + "step": 215040 + }, + { + "epoch": 1.02, + "learning_rate": 4.647072812954717e-05, + "loss": 4.3791, + "step": 215552 + }, + { + "epoch": 1.02, + "learning_rate": 4.646234218203665e-05, + "loss": 4.3858, + "step": 216064 + }, + { + "epoch": 1.02, + "learning_rate": 4.645395623452612e-05, + "loss": 4.3886, + "step": 216576 + }, + { + "epoch": 1.02, + "learning_rate": 4.644558666581934e-05, + "loss": 4.3922, + "step": 217088 + }, + { + "epoch": 1.02, + "learning_rate": 4.643720071830882e-05, + "loss": 4.3756, + "step": 217600 + }, + { + "epoch": 1.02, + "learning_rate": 4.64288147707983e-05, + "loss": 4.377, + "step": 218112 + }, + { + "epoch": 1.02, + "learning_rate": 4.642042882328778e-05, + "loss": 4.4018, + "step": 218624 + }, + { + "epoch": 1.02, + "learning_rate": 4.6412059254580994e-05, + "loss": 4.378, + "step": 219136 + }, + { + "epoch": 1.02, + "learning_rate": 4.6403673307070474e-05, + "loss": 4.3905, + "step": 219648 + }, + { + "epoch": 1.02, + "learning_rate": 4.639528735955995e-05, + "loss": 4.3833, + "step": 220160 + }, + { + "epoch": 1.02, + "learning_rate": 4.638690141204943e-05, + "loss": 4.3897, + "step": 220672 + }, + { + "epoch": 1.02, + "learning_rate": 4.637851546453891e-05, + "loss": 4.3791, + "step": 221184 + }, + { + "epoch": 1.02, + "learning_rate": 4.637012951702839e-05, + "loss": 4.378, + "step": 221696 + }, + { + "epoch": 1.02, + "learning_rate": 4.6361759948321596e-05, + "loss": 4.3854, + "step": 222208 + }, + { + "epoch": 1.02, + "learning_rate": 4.6353374000811076e-05, + "loss": 4.3759, + "step": 222720 + }, + { + "epoch": 1.02, + "learning_rate": 4.6344988053300556e-05, + "loss": 4.3895, + "step": 223232 + }, + { + "epoch": 1.02, + "learning_rate": 4.6336602105790036e-05, + "loss": 4.3863, + "step": 223744 + }, + { + "epoch": 1.02, + "learning_rate": 4.632823253708325e-05, + "loss": 4.3843, + "step": 224256 + }, + { + "epoch": 1.02, + "learning_rate": 4.631984658957273e-05, + "loss": 4.3792, + "step": 224768 + }, + { + "epoch": 1.02, + "learning_rate": 4.631146064206221e-05, + "loss": 4.3718, + "step": 225280 + }, + { + "epoch": 1.02, + "learning_rate": 4.630307469455169e-05, + "loss": 4.3783, + "step": 225792 + }, + { + "epoch": 1.02, + "learning_rate": 4.629468874704117e-05, + "loss": 4.3663, + "step": 226304 + }, + { + "epoch": 1.02, + "learning_rate": 4.628630279953065e-05, + "loss": 4.3711, + "step": 226816 + }, + { + "epoch": 1.02, + "learning_rate": 4.627791685202013e-05, + "loss": 4.3718, + "step": 227328 + }, + { + "epoch": 1.02, + "learning_rate": 4.626953090450961e-05, + "loss": 4.3645, + "step": 227840 + }, + { + "epoch": 1.02, + "learning_rate": 4.626114495699909e-05, + "loss": 4.3696, + "step": 228352 + }, + { + "epoch": 1.02, + "learning_rate": 4.625275900948857e-05, + "loss": 4.3688, + "step": 228864 + }, + { + "epoch": 1.03, + "eval_loss": 4.342700958251953, + "eval_runtime": 554.1608, + "eval_samples_per_second": 688.593, + "eval_steps_per_second": 21.519, + "step": 228957 + }, + { + "epoch": 0.0, + "learning_rate": 4.624437306197805e-05, + "loss": 4.3768, + "step": 229376 + }, + { + "epoch": 0.0, + "learning_rate": 4.623598711446753e-05, + "loss": 4.3819, + "step": 229888 + }, + { + "epoch": 0.0, + "learning_rate": 4.622760116695701e-05, + "loss": 4.3674, + "step": 230400 + }, + { + "epoch": 0.0, + "learning_rate": 4.6219215219446484e-05, + "loss": 4.3656, + "step": 230912 + }, + { + "epoch": 0.0, + "learning_rate": 4.621082927193597e-05, + "loss": 4.3698, + "step": 231424 + }, + { + "epoch": 0.0, + "learning_rate": 4.620244332442545e-05, + "loss": 4.3501, + "step": 231936 + }, + { + "epoch": 0.0, + "learning_rate": 4.619405737691493e-05, + "loss": 4.3649, + "step": 232448 + }, + { + "epoch": 0.0, + "learning_rate": 4.618567142940441e-05, + "loss": 4.3663, + "step": 232960 + }, + { + "epoch": 0.0, + "learning_rate": 4.617728548189389e-05, + "loss": 4.3541, + "step": 233472 + }, + { + "epoch": 0.0, + "learning_rate": 4.616889953438337e-05, + "loss": 4.369, + "step": 233984 + }, + { + "epoch": 0.0, + "learning_rate": 4.616051358687285e-05, + "loss": 4.3763, + "step": 234496 + }, + { + "epoch": 0.0, + "learning_rate": 4.615212763936233e-05, + "loss": 4.3564, + "step": 235008 + }, + { + "epoch": 0.0, + "learning_rate": 4.614374169185181e-05, + "loss": 4.3548, + "step": 235520 + }, + { + "epoch": 0.0, + "learning_rate": 4.613535574434129e-05, + "loss": 4.3592, + "step": 236032 + }, + { + "epoch": 0.0, + "learning_rate": 4.612696979683077e-05, + "loss": 4.362, + "step": 236544 + }, + { + "epoch": 0.0, + "learning_rate": 4.611860022812398e-05, + "loss": 4.3564, + "step": 237056 + }, + { + "epoch": 0.0, + "learning_rate": 4.611021428061346e-05, + "loss": 4.3529, + "step": 237568 + }, + { + "epoch": 0.0, + "learning_rate": 4.610182833310294e-05, + "loss": 4.3531, + "step": 238080 + }, + { + "epoch": 0.0, + "learning_rate": 4.609344238559242e-05, + "loss": 4.3553, + "step": 238592 + }, + { + "epoch": 0.0, + "learning_rate": 4.60850564380819e-05, + "loss": 4.3616, + "step": 239104 + }, + { + "epoch": 0.0, + "learning_rate": 4.607667049057138e-05, + "loss": 4.3574, + "step": 239616 + }, + { + "epoch": 0.0, + "learning_rate": 4.606828454306086e-05, + "loss": 4.362, + "step": 240128 + }, + { + "epoch": 0.0, + "learning_rate": 4.6059914974354075e-05, + "loss": 4.3602, + "step": 240640 + }, + { + "epoch": 0.0, + "learning_rate": 4.6051529026843555e-05, + "loss": 4.3544, + "step": 241152 + }, + { + "epoch": 0.0, + "learning_rate": 4.604314307933303e-05, + "loss": 4.3517, + "step": 241664 + }, + { + "epoch": 0.0, + "learning_rate": 4.603475713182251e-05, + "loss": 4.3517, + "step": 242176 + }, + { + "epoch": 0.0, + "learning_rate": 4.602637118431199e-05, + "loss": 4.3578, + "step": 242688 + }, + { + "epoch": 0.0, + "learning_rate": 4.601798523680147e-05, + "loss": 4.345, + "step": 243200 + }, + { + "epoch": 0.0, + "learning_rate": 4.600959928929095e-05, + "loss": 4.3536, + "step": 243712 + }, + { + "epoch": 0.01, + "learning_rate": 4.600121334178043e-05, + "loss": 4.3409, + "step": 244224 + }, + { + "epoch": 0.01, + "learning_rate": 4.599284377307364e-05, + "loss": 4.345, + "step": 244736 + }, + { + "epoch": 0.01, + "learning_rate": 4.5984457825563124e-05, + "loss": 4.3589, + "step": 245248 + }, + { + "epoch": 0.01, + "learning_rate": 4.597608825685633e-05, + "loss": 4.3536, + "step": 245760 + }, + { + "epoch": 0.01, + "learning_rate": 4.596770230934581e-05, + "loss": 4.3451, + "step": 246272 + }, + { + "epoch": 0.01, + "learning_rate": 4.595931636183529e-05, + "loss": 4.341, + "step": 246784 + }, + { + "epoch": 0.01, + "learning_rate": 4.59509467931285e-05, + "loss": 4.3541, + "step": 247296 + }, + { + "epoch": 0.01, + "learning_rate": 4.594256084561798e-05, + "loss": 4.3413, + "step": 247808 + }, + { + "epoch": 0.01, + "learning_rate": 4.593417489810746e-05, + "loss": 4.3528, + "step": 248320 + }, + { + "epoch": 0.01, + "learning_rate": 4.592578895059694e-05, + "loss": 4.3436, + "step": 248832 + }, + { + "epoch": 0.01, + "learning_rate": 4.591740300308642e-05, + "loss": 4.332, + "step": 249344 + }, + { + "epoch": 0.01, + "learning_rate": 4.59090170555759e-05, + "loss": 4.3331, + "step": 249856 + }, + { + "epoch": 0.01, + "learning_rate": 4.590063110806538e-05, + "loss": 4.3344, + "step": 250368 + }, + { + "epoch": 0.01, + "learning_rate": 4.589224516055486e-05, + "loss": 4.3441, + "step": 250880 + }, + { + "epoch": 0.01, + "learning_rate": 4.588385921304434e-05, + "loss": 4.3359, + "step": 251392 + }, + { + "epoch": 0.01, + "learning_rate": 4.587547326553382e-05, + "loss": 4.3373, + "step": 251904 + }, + { + "epoch": 0.01, + "learning_rate": 4.58670873180233e-05, + "loss": 4.3334, + "step": 252416 + }, + { + "epoch": 0.01, + "learning_rate": 4.585870137051279e-05, + "loss": 4.3356, + "step": 252928 + }, + { + "epoch": 0.01, + "learning_rate": 4.5850331801806e-05, + "loss": 4.3503, + "step": 253440 + }, + { + "epoch": 0.01, + "learning_rate": 4.584194585429548e-05, + "loss": 4.3303, + "step": 253952 + }, + { + "epoch": 0.01, + "learning_rate": 4.583355990678496e-05, + "loss": 4.3302, + "step": 254464 + }, + { + "epoch": 0.01, + "learning_rate": 4.582517395927444e-05, + "loss": 4.3331, + "step": 254976 + }, + { + "epoch": 0.01, + "learning_rate": 4.581678801176391e-05, + "loss": 4.3439, + "step": 255488 + }, + { + "epoch": 0.01, + "learning_rate": 4.580840206425339e-05, + "loss": 4.3237, + "step": 256000 + }, + { + "epoch": 0.01, + "learning_rate": 4.580001611674287e-05, + "loss": 4.3381, + "step": 256512 + }, + { + "epoch": 0.01, + "learning_rate": 4.579163016923235e-05, + "loss": 4.3206, + "step": 257024 + }, + { + "epoch": 0.01, + "learning_rate": 4.578324422172183e-05, + "loss": 4.3281, + "step": 257536 + }, + { + "epoch": 0.01, + "learning_rate": 4.577487465301504e-05, + "loss": 4.3363, + "step": 258048 + }, + { + "epoch": 0.01, + "learning_rate": 4.5766488705504526e-05, + "loss": 4.3203, + "step": 258560 + }, + { + "epoch": 0.01, + "learning_rate": 4.5758102757994006e-05, + "loss": 4.3331, + "step": 259072 + }, + { + "epoch": 0.01, + "learning_rate": 4.5749716810483486e-05, + "loss": 4.328, + "step": 259584 + }, + { + "epoch": 0.01, + "learning_rate": 4.5741347241776695e-05, + "loss": 4.3084, + "step": 260096 + }, + { + "epoch": 0.01, + "learning_rate": 4.5732961294266175e-05, + "loss": 4.3234, + "step": 260608 + }, + { + "epoch": 0.01, + "learning_rate": 4.5724575346755655e-05, + "loss": 4.3263, + "step": 261120 + }, + { + "epoch": 0.01, + "learning_rate": 4.5716189399245135e-05, + "loss": 4.3244, + "step": 261632 + }, + { + "epoch": 0.01, + "learning_rate": 4.5707819830538344e-05, + "loss": 4.3199, + "step": 262144 + }, + { + "epoch": 0.01, + "learning_rate": 4.5699433883027824e-05, + "loss": 4.3203, + "step": 262656 + }, + { + "epoch": 0.01, + "learning_rate": 4.5691047935517304e-05, + "loss": 4.3036, + "step": 263168 + }, + { + "epoch": 0.01, + "learning_rate": 4.568267836681051e-05, + "loss": 4.33, + "step": 263680 + }, + { + "epoch": 0.01, + "learning_rate": 4.567429241929999e-05, + "loss": 4.3113, + "step": 264192 + }, + { + "epoch": 0.01, + "learning_rate": 4.566590647178948e-05, + "loss": 4.3172, + "step": 264704 + }, + { + "epoch": 0.01, + "learning_rate": 4.565752052427896e-05, + "loss": 4.3276, + "step": 265216 + }, + { + "epoch": 0.01, + "learning_rate": 4.564913457676844e-05, + "loss": 4.3155, + "step": 265728 + }, + { + "epoch": 0.01, + "learning_rate": 4.564074862925792e-05, + "loss": 4.3255, + "step": 266240 + }, + { + "epoch": 0.01, + "learning_rate": 4.56323626817474e-05, + "loss": 4.3313, + "step": 266752 + }, + { + "epoch": 0.01, + "learning_rate": 4.562399311304061e-05, + "loss": 4.3251, + "step": 267264 + }, + { + "epoch": 0.01, + "learning_rate": 4.561560716553009e-05, + "loss": 4.3301, + "step": 267776 + }, + { + "epoch": 0.01, + "learning_rate": 4.560722121801957e-05, + "loss": 4.3089, + "step": 268288 + }, + { + "epoch": 0.01, + "learning_rate": 4.559883527050905e-05, + "loss": 4.3067, + "step": 268800 + }, + { + "epoch": 0.01, + "learning_rate": 4.559044932299853e-05, + "loss": 4.3155, + "step": 269312 + }, + { + "epoch": 0.01, + "learning_rate": 4.558207975429174e-05, + "loss": 4.3283, + "step": 269824 + }, + { + "epoch": 0.01, + "learning_rate": 4.557369380678122e-05, + "loss": 4.3145, + "step": 270336 + }, + { + "epoch": 0.01, + "learning_rate": 4.55653078592707e-05, + "loss": 4.3079, + "step": 270848 + }, + { + "epoch": 0.01, + "learning_rate": 4.555692191176018e-05, + "loss": 4.2981, + "step": 271360 + }, + { + "epoch": 0.01, + "learning_rate": 4.5548552343053394e-05, + "loss": 4.3094, + "step": 271872 + }, + { + "epoch": 0.01, + "learning_rate": 4.5540166395542874e-05, + "loss": 4.306, + "step": 272384 + }, + { + "epoch": 0.01, + "learning_rate": 4.553179682683608e-05, + "loss": 4.3107, + "step": 272896 + }, + { + "epoch": 0.01, + "learning_rate": 4.552341087932556e-05, + "loss": 4.3178, + "step": 273408 + }, + { + "epoch": 0.01, + "learning_rate": 4.551502493181504e-05, + "loss": 4.321, + "step": 273920 + }, + { + "epoch": 0.01, + "learning_rate": 4.550663898430452e-05, + "loss": 4.3087, + "step": 274432 + }, + { + "epoch": 0.02, + "learning_rate": 4.549826941559773e-05, + "loss": 4.307, + "step": 274944 + }, + { + "epoch": 0.02, + "learning_rate": 4.548988346808721e-05, + "loss": 4.2969, + "step": 275456 + }, + { + "epoch": 0.02, + "learning_rate": 4.548149752057669e-05, + "loss": 4.3036, + "step": 275968 + }, + { + "epoch": 0.02, + "learning_rate": 4.547311157306617e-05, + "loss": 4.308, + "step": 276480 + }, + { + "epoch": 0.02, + "learning_rate": 4.546472562555565e-05, + "loss": 4.302, + "step": 276992 + }, + { + "epoch": 0.02, + "learning_rate": 4.545633967804513e-05, + "loss": 4.2973, + "step": 277504 + }, + { + "epoch": 0.02, + "learning_rate": 4.544795373053462e-05, + "loss": 4.3121, + "step": 278016 + }, + { + "epoch": 0.02, + "learning_rate": 4.54395677830241e-05, + "loss": 4.3042, + "step": 278528 + }, + { + "epoch": 0.02, + "learning_rate": 4.543118183551358e-05, + "loss": 4.3154, + "step": 279040 + }, + { + "epoch": 0.02, + "learning_rate": 4.542281226680679e-05, + "loss": 4.3045, + "step": 279552 + }, + { + "epoch": 0.02, + "learning_rate": 4.541442631929627e-05, + "loss": 4.3134, + "step": 280064 + }, + { + "epoch": 0.02, + "learning_rate": 4.540604037178575e-05, + "loss": 4.306, + "step": 280576 + }, + { + "epoch": 0.02, + "learning_rate": 4.539765442427522e-05, + "loss": 4.2988, + "step": 281088 + }, + { + "epoch": 0.02, + "learning_rate": 4.5389284855568436e-05, + "loss": 4.317, + "step": 281600 + }, + { + "epoch": 0.02, + "learning_rate": 4.5380898908057916e-05, + "loss": 4.2952, + "step": 282112 + }, + { + "epoch": 0.02, + "learning_rate": 4.5372512960547396e-05, + "loss": 4.3167, + "step": 282624 + }, + { + "epoch": 0.02, + "learning_rate": 4.536412701303687e-05, + "loss": 4.2898, + "step": 283136 + }, + { + "epoch": 0.02, + "learning_rate": 4.5355741065526356e-05, + "loss": 4.2859, + "step": 283648 + }, + { + "epoch": 0.02, + "learning_rate": 4.5347355118015836e-05, + "loss": 4.2914, + "step": 284160 + }, + { + "epoch": 0.02, + "learning_rate": 4.5338985549309045e-05, + "loss": 4.3071, + "step": 284672 + }, + { + "epoch": 0.02, + "learning_rate": 4.5330599601798525e-05, + "loss": 4.2986, + "step": 285184 + }, + { + "epoch": 0.02, + "learning_rate": 4.5322213654288005e-05, + "loss": 4.2848, + "step": 285696 + }, + { + "epoch": 0.02, + "learning_rate": 4.5313827706777485e-05, + "loss": 4.2821, + "step": 286208 + }, + { + "epoch": 0.02, + "learning_rate": 4.5305458138070694e-05, + "loss": 4.2911, + "step": 286720 + }, + { + "epoch": 0.02, + "learning_rate": 4.5297072190560174e-05, + "loss": 4.309, + "step": 287232 + }, + { + "epoch": 0.02, + "learning_rate": 4.5288686243049654e-05, + "loss": 4.2924, + "step": 287744 + }, + { + "epoch": 0.02, + "learning_rate": 4.5280300295539134e-05, + "loss": 4.3041, + "step": 288256 + }, + { + "epoch": 0.02, + "learning_rate": 4.5271914348028614e-05, + "loss": 4.2967, + "step": 288768 + }, + { + "epoch": 0.02, + "learning_rate": 4.5263528400518094e-05, + "loss": 4.2971, + "step": 289280 + }, + { + "epoch": 0.02, + "learning_rate": 4.5255142453007574e-05, + "loss": 4.297, + "step": 289792 + }, + { + "epoch": 0.02, + "learning_rate": 4.524677288430079e-05, + "loss": 4.2884, + "step": 290304 + }, + { + "epoch": 0.02, + "learning_rate": 4.523838693679027e-05, + "loss": 4.2915, + "step": 290816 + }, + { + "epoch": 0.02, + "learning_rate": 4.523000098927975e-05, + "loss": 4.2955, + "step": 291328 + }, + { + "epoch": 0.02, + "learning_rate": 4.522161504176923e-05, + "loss": 4.2852, + "step": 291840 + }, + { + "epoch": 0.02, + "learning_rate": 4.521322909425871e-05, + "loss": 4.2889, + "step": 292352 + }, + { + "epoch": 0.02, + "learning_rate": 4.520485952555192e-05, + "loss": 4.2955, + "step": 292864 + }, + { + "epoch": 0.02, + "learning_rate": 4.51964735780414e-05, + "loss": 4.2928, + "step": 293376 + }, + { + "epoch": 0.02, + "learning_rate": 4.518808763053088e-05, + "loss": 4.2841, + "step": 293888 + }, + { + "epoch": 0.02, + "learning_rate": 4.517970168302036e-05, + "loss": 4.2816, + "step": 294400 + }, + { + "epoch": 0.02, + "learning_rate": 4.517131573550984e-05, + "loss": 4.3032, + "step": 294912 + }, + { + "epoch": 0.02, + "learning_rate": 4.516292978799932e-05, + "loss": 4.2848, + "step": 295424 + }, + { + "epoch": 0.02, + "learning_rate": 4.515456021929253e-05, + "loss": 4.2973, + "step": 295936 + }, + { + "epoch": 0.02, + "learning_rate": 4.514617427178201e-05, + "loss": 4.2899, + "step": 296448 + }, + { + "epoch": 0.02, + "learning_rate": 4.513778832427149e-05, + "loss": 4.2936, + "step": 296960 + }, + { + "epoch": 0.02, + "learning_rate": 4.5129402376760974e-05, + "loss": 4.2853, + "step": 297472 + }, + { + "epoch": 0.02, + "learning_rate": 4.5121016429250454e-05, + "loss": 4.2873, + "step": 297984 + }, + { + "epoch": 0.02, + "learning_rate": 4.5112630481739934e-05, + "loss": 4.2904, + "step": 298496 + }, + { + "epoch": 0.02, + "learning_rate": 4.510424453422941e-05, + "loss": 4.2848, + "step": 299008 + }, + { + "epoch": 0.02, + "learning_rate": 4.509589134432635e-05, + "loss": 4.2984, + "step": 299520 + }, + { + "epoch": 0.02, + "learning_rate": 4.508750539681583e-05, + "loss": 4.2871, + "step": 300032 + }, + { + "epoch": 0.02, + "learning_rate": 4.507911944930531e-05, + "loss": 4.2933, + "step": 300544 + }, + { + "epoch": 0.02, + "learning_rate": 4.507073350179479e-05, + "loss": 4.2916, + "step": 301056 + }, + { + "epoch": 0.02, + "learning_rate": 4.506234755428427e-05, + "loss": 4.2791, + "step": 301568 + }, + { + "epoch": 0.02, + "learning_rate": 4.505396160677375e-05, + "loss": 4.2859, + "step": 302080 + }, + { + "epoch": 0.02, + "learning_rate": 4.504557565926323e-05, + "loss": 4.2771, + "step": 302592 + }, + { + "epoch": 0.02, + "learning_rate": 4.503718971175271e-05, + "loss": 4.2805, + "step": 303104 + }, + { + "epoch": 0.02, + "learning_rate": 4.502882014304593e-05, + "loss": 4.2792, + "step": 303616 + }, + { + "epoch": 0.02, + "learning_rate": 4.502043419553541e-05, + "loss": 4.2783, + "step": 304128 + }, + { + "epoch": 0.02, + "learning_rate": 4.501204824802488e-05, + "loss": 4.2731, + "step": 304640 + }, + { + "epoch": 0.02, + "learning_rate": 4.500366230051436e-05, + "loss": 4.2817, + "step": 305152 + }, + { + "epoch": 0.03, + "eval_loss": 4.261253356933594, + "eval_runtime": 535.2839, + "eval_samples_per_second": 712.876, + "eval_steps_per_second": 22.278, + "step": 305276 + }, + { + "epoch": 1.0, + "learning_rate": 4.499527635300384e-05, + "loss": 4.2865, + "step": 305664 + }, + { + "epoch": 1.0, + "learning_rate": 4.498689040549332e-05, + "loss": 4.2884, + "step": 306176 + }, + { + "epoch": 1.0, + "learning_rate": 4.497852083678653e-05, + "loss": 4.2791, + "step": 306688 + }, + { + "epoch": 1.0, + "learning_rate": 4.497013488927601e-05, + "loss": 4.2755, + "step": 307200 + }, + { + "epoch": 1.0, + "learning_rate": 4.496174894176549e-05, + "loss": 4.2828, + "step": 307712 + }, + { + "epoch": 1.0, + "learning_rate": 4.495336299425497e-05, + "loss": 4.2597, + "step": 308224 + }, + { + "epoch": 1.0, + "learning_rate": 4.494497704674445e-05, + "loss": 4.2793, + "step": 308736 + }, + { + "epoch": 1.0, + "learning_rate": 4.4936607478037665e-05, + "loss": 4.2741, + "step": 309248 + }, + { + "epoch": 1.0, + "learning_rate": 4.4928221530527145e-05, + "loss": 4.2683, + "step": 309760 + }, + { + "epoch": 1.0, + "learning_rate": 4.4919851961820354e-05, + "loss": 4.2798, + "step": 310272 + }, + { + "epoch": 1.0, + "learning_rate": 4.4911466014309834e-05, + "loss": 4.2875, + "step": 310784 + }, + { + "epoch": 1.0, + "learning_rate": 4.4903080066799314e-05, + "loss": 4.2676, + "step": 311296 + }, + { + "epoch": 1.0, + "learning_rate": 4.4894694119288794e-05, + "loss": 4.2711, + "step": 311808 + }, + { + "epoch": 1.0, + "learning_rate": 4.4886308171778274e-05, + "loss": 4.2717, + "step": 312320 + }, + { + "epoch": 1.0, + "learning_rate": 4.4877922224267754e-05, + "loss": 4.2768, + "step": 312832 + }, + { + "epoch": 1.0, + "learning_rate": 4.4869536276757234e-05, + "loss": 4.2657, + "step": 313344 + }, + { + "epoch": 1.0, + "learning_rate": 4.4861150329246714e-05, + "loss": 4.266, + "step": 313856 + }, + { + "epoch": 1.0, + "learning_rate": 4.4852764381736194e-05, + "loss": 4.2659, + "step": 314368 + }, + { + "epoch": 1.0, + "learning_rate": 4.4844378434225674e-05, + "loss": 4.267, + "step": 314880 + }, + { + "epoch": 1.0, + "learning_rate": 4.4835992486715154e-05, + "loss": 4.2779, + "step": 315392 + }, + { + "epoch": 1.0, + "learning_rate": 4.4827606539204634e-05, + "loss": 4.2693, + "step": 315904 + }, + { + "epoch": 1.0, + "learning_rate": 4.481923697049785e-05, + "loss": 4.2777, + "step": 316416 + }, + { + "epoch": 1.0, + "learning_rate": 4.481085102298733e-05, + "loss": 4.2783, + "step": 316928 + }, + { + "epoch": 1.0, + "learning_rate": 4.480246507547681e-05, + "loss": 4.2689, + "step": 317440 + }, + { + "epoch": 1.0, + "learning_rate": 4.479407912796629e-05, + "loss": 4.2651, + "step": 317952 + }, + { + "epoch": 1.0, + "learning_rate": 4.47857095592595e-05, + "loss": 4.2665, + "step": 318464 + }, + { + "epoch": 1.0, + "learning_rate": 4.477732361174898e-05, + "loss": 4.2734, + "step": 318976 + }, + { + "epoch": 1.0, + "learning_rate": 4.476893766423846e-05, + "loss": 4.2627, + "step": 319488 + }, + { + "epoch": 1.0, + "learning_rate": 4.476055171672794e-05, + "loss": 4.2666, + "step": 320000 + }, + { + "epoch": 1.0, + "learning_rate": 4.475218214802115e-05, + "loss": 4.2651, + "step": 320512 + }, + { + "epoch": 1.01, + "learning_rate": 4.474379620051063e-05, + "loss": 4.2566, + "step": 321024 + }, + { + "epoch": 1.01, + "learning_rate": 4.473541025300011e-05, + "loss": 4.2719, + "step": 321536 + }, + { + "epoch": 1.01, + "learning_rate": 4.472704068429332e-05, + "loss": 4.2737, + "step": 322048 + }, + { + "epoch": 1.01, + "learning_rate": 4.4718654736782804e-05, + "loss": 4.2657, + "step": 322560 + }, + { + "epoch": 1.01, + "learning_rate": 4.4710268789272283e-05, + "loss": 4.2581, + "step": 323072 + }, + { + "epoch": 1.01, + "learning_rate": 4.470189922056549e-05, + "loss": 4.2673, + "step": 323584 + }, + { + "epoch": 1.01, + "learning_rate": 4.469351327305497e-05, + "loss": 4.2668, + "step": 324096 + }, + { + "epoch": 1.01, + "learning_rate": 4.468512732554445e-05, + "loss": 4.2661, + "step": 324608 + }, + { + "epoch": 1.01, + "learning_rate": 4.467674137803393e-05, + "loss": 4.2625, + "step": 325120 + }, + { + "epoch": 1.01, + "learning_rate": 4.466835543052341e-05, + "loss": 4.2522, + "step": 325632 + }, + { + "epoch": 1.01, + "learning_rate": 4.465996948301289e-05, + "loss": 4.2503, + "step": 326144 + }, + { + "epoch": 1.01, + "learning_rate": 4.4651583535502366e-05, + "loss": 4.2516, + "step": 326656 + }, + { + "epoch": 1.01, + "learning_rate": 4.4643197587991846e-05, + "loss": 4.2631, + "step": 327168 + }, + { + "epoch": 1.01, + "learning_rate": 4.4634811640481325e-05, + "loss": 4.2571, + "step": 327680 + }, + { + "epoch": 1.01, + "learning_rate": 4.4626425692970805e-05, + "loss": 4.2543, + "step": 328192 + }, + { + "epoch": 1.01, + "learning_rate": 4.4618039745460285e-05, + "loss": 4.2545, + "step": 328704 + }, + { + "epoch": 1.01, + "learning_rate": 4.4609653797949765e-05, + "loss": 4.2549, + "step": 329216 + }, + { + "epoch": 1.01, + "learning_rate": 4.460128422924298e-05, + "loss": 4.271, + "step": 329728 + }, + { + "epoch": 1.01, + "learning_rate": 4.459289828173246e-05, + "loss": 4.2514, + "step": 330240 + }, + { + "epoch": 1.01, + "learning_rate": 4.458451233422194e-05, + "loss": 4.2495, + "step": 330752 + }, + { + "epoch": 1.01, + "learning_rate": 4.457612638671142e-05, + "loss": 4.2563, + "step": 331264 + }, + { + "epoch": 1.01, + "learning_rate": 4.456775681800463e-05, + "loss": 4.2615, + "step": 331776 + }, + { + "epoch": 1.01, + "learning_rate": 4.455937087049411e-05, + "loss": 4.2475, + "step": 332288 + }, + { + "epoch": 1.01, + "learning_rate": 4.455098492298359e-05, + "loss": 4.2546, + "step": 332800 + }, + { + "epoch": 1.01, + "learning_rate": 4.454259897547307e-05, + "loss": 4.2458, + "step": 333312 + }, + { + "epoch": 1.01, + "learning_rate": 4.453422940676628e-05, + "loss": 4.2511, + "step": 333824 + }, + { + "epoch": 1.01, + "learning_rate": 4.452584345925576e-05, + "loss": 4.256, + "step": 334336 + }, + { + "epoch": 1.01, + "learning_rate": 4.451745751174524e-05, + "loss": 4.2391, + "step": 334848 + }, + { + "epoch": 1.01, + "learning_rate": 4.450907156423472e-05, + "loss": 4.2586, + "step": 335360 + }, + { + "epoch": 1.01, + "learning_rate": 4.4500685616724206e-05, + "loss": 4.2466, + "step": 335872 + }, + { + "epoch": 1.01, + "learning_rate": 4.4492316048017415e-05, + "loss": 4.236, + "step": 336384 + }, + { + "epoch": 1.01, + "learning_rate": 4.4483930100506895e-05, + "loss": 4.2431, + "step": 336896 + }, + { + "epoch": 1.01, + "learning_rate": 4.4475544152996375e-05, + "loss": 4.2492, + "step": 337408 + }, + { + "epoch": 1.01, + "learning_rate": 4.4467158205485855e-05, + "loss": 4.2527, + "step": 337920 + }, + { + "epoch": 1.01, + "learning_rate": 4.4458772257975335e-05, + "loss": 4.2419, + "step": 338432 + }, + { + "epoch": 1.01, + "learning_rate": 4.4450386310464815e-05, + "loss": 4.2471, + "step": 338944 + }, + { + "epoch": 1.01, + "learning_rate": 4.4442000362954295e-05, + "loss": 4.2235, + "step": 339456 + }, + { + "epoch": 1.01, + "learning_rate": 4.4433614415443775e-05, + "loss": 4.2536, + "step": 339968 + }, + { + "epoch": 1.01, + "learning_rate": 4.4425244846736984e-05, + "loss": 4.2372, + "step": 340480 + }, + { + "epoch": 1.01, + "learning_rate": 4.441687527803019e-05, + "loss": 4.2404, + "step": 340992 + }, + { + "epoch": 1.01, + "learning_rate": 4.440848933051967e-05, + "loss": 4.2513, + "step": 341504 + }, + { + "epoch": 1.01, + "learning_rate": 4.440010338300916e-05, + "loss": 4.242, + "step": 342016 + }, + { + "epoch": 1.01, + "learning_rate": 4.439171743549864e-05, + "loss": 4.246, + "step": 342528 + }, + { + "epoch": 1.01, + "learning_rate": 4.438333148798812e-05, + "loss": 4.2547, + "step": 343040 + }, + { + "epoch": 1.01, + "learning_rate": 4.43749455404776e-05, + "loss": 4.2506, + "step": 343552 + }, + { + "epoch": 1.01, + "learning_rate": 4.436655959296708e-05, + "loss": 4.2522, + "step": 344064 + }, + { + "epoch": 1.01, + "learning_rate": 4.435817364545655e-05, + "loss": 4.2374, + "step": 344576 + }, + { + "epoch": 1.01, + "learning_rate": 4.434980407674977e-05, + "loss": 4.2314, + "step": 345088 + }, + { + "epoch": 1.01, + "learning_rate": 4.434141812923925e-05, + "loss": 4.2423, + "step": 345600 + }, + { + "epoch": 1.01, + "learning_rate": 4.433304856053246e-05, + "loss": 4.2516, + "step": 346112 + }, + { + "epoch": 1.01, + "learning_rate": 4.432466261302194e-05, + "loss": 4.2404, + "step": 346624 + }, + { + "epoch": 1.01, + "learning_rate": 4.431627666551142e-05, + "loss": 4.2384, + "step": 347136 + }, + { + "epoch": 1.01, + "learning_rate": 4.43078907180009e-05, + "loss": 4.2226, + "step": 347648 + }, + { + "epoch": 1.01, + "learning_rate": 4.429950477049038e-05, + "loss": 4.2349, + "step": 348160 + }, + { + "epoch": 1.01, + "learning_rate": 4.429111882297986e-05, + "loss": 4.231, + "step": 348672 + }, + { + "epoch": 1.01, + "learning_rate": 4.428273287546934e-05, + "loss": 4.242, + "step": 349184 + }, + { + "epoch": 1.01, + "learning_rate": 4.427434692795882e-05, + "loss": 4.2392, + "step": 349696 + }, + { + "epoch": 1.01, + "learning_rate": 4.4265977359252026e-05, + "loss": 4.2501, + "step": 350208 + }, + { + "epoch": 1.01, + "learning_rate": 4.4257591411741506e-05, + "loss": 4.233, + "step": 350720 + }, + { + "epoch": 1.02, + "learning_rate": 4.4249205464230986e-05, + "loss": 4.2383, + "step": 351232 + }, + { + "epoch": 1.02, + "learning_rate": 4.4240819516720466e-05, + "loss": 4.2233, + "step": 351744 + }, + { + "epoch": 1.02, + "learning_rate": 4.4232433569209946e-05, + "loss": 4.2317, + "step": 352256 + }, + { + "epoch": 1.02, + "learning_rate": 4.4224047621699426e-05, + "loss": 4.2364, + "step": 352768 + }, + { + "epoch": 1.02, + "learning_rate": 4.4215678052992635e-05, + "loss": 4.2269, + "step": 353280 + }, + { + "epoch": 1.02, + "learning_rate": 4.4207292105482115e-05, + "loss": 4.2275, + "step": 353792 + }, + { + "epoch": 1.02, + "learning_rate": 4.4198906157971595e-05, + "loss": 4.2411, + "step": 354304 + }, + { + "epoch": 1.02, + "learning_rate": 4.419052021046108e-05, + "loss": 4.2279, + "step": 354816 + }, + { + "epoch": 1.02, + "learning_rate": 4.418213426295056e-05, + "loss": 4.2489, + "step": 355328 + }, + { + "epoch": 1.02, + "learning_rate": 4.417374831544004e-05, + "loss": 4.2298, + "step": 355840 + }, + { + "epoch": 1.02, + "learning_rate": 4.416536236792952e-05, + "loss": 4.2416, + "step": 356352 + }, + { + "epoch": 1.02, + "learning_rate": 4.4156976420419e-05, + "loss": 4.2313, + "step": 356864 + }, + { + "epoch": 1.02, + "learning_rate": 4.414860685171221e-05, + "loss": 4.2293, + "step": 357376 + }, + { + "epoch": 1.02, + "learning_rate": 4.414023728300542e-05, + "loss": 4.2468, + "step": 357888 + }, + { + "epoch": 1.02, + "learning_rate": 4.41318513354949e-05, + "loss": 4.2257, + "step": 358400 + }, + { + "epoch": 1.02, + "learning_rate": 4.412346538798438e-05, + "loss": 4.2446, + "step": 358912 + }, + { + "epoch": 1.02, + "learning_rate": 4.411507944047386e-05, + "loss": 4.2225, + "step": 359424 + }, + { + "epoch": 1.02, + "learning_rate": 4.410669349296334e-05, + "loss": 4.2194, + "step": 359936 + }, + { + "epoch": 1.02, + "learning_rate": 4.409832392425655e-05, + "loss": 4.2202, + "step": 360448 + }, + { + "epoch": 1.02, + "learning_rate": 4.408993797674603e-05, + "loss": 4.2346, + "step": 360960 + }, + { + "epoch": 1.02, + "learning_rate": 4.4081552029235515e-05, + "loss": 4.2308, + "step": 361472 + }, + { + "epoch": 1.02, + "learning_rate": 4.4073166081724995e-05, + "loss": 4.2189, + "step": 361984 + }, + { + "epoch": 1.02, + "learning_rate": 4.4064780134214475e-05, + "loss": 4.2119, + "step": 362496 + }, + { + "epoch": 1.02, + "learning_rate": 4.4056394186703955e-05, + "loss": 4.2224, + "step": 363008 + }, + { + "epoch": 1.02, + "learning_rate": 4.4048008239193435e-05, + "loss": 4.2388, + "step": 363520 + }, + { + "epoch": 1.02, + "learning_rate": 4.4039622291682915e-05, + "loss": 4.2232, + "step": 364032 + }, + { + "epoch": 1.02, + "learning_rate": 4.4031252722976124e-05, + "loss": 4.2369, + "step": 364544 + }, + { + "epoch": 1.02, + "learning_rate": 4.4022866775465604e-05, + "loss": 4.2263, + "step": 365056 + }, + { + "epoch": 1.02, + "learning_rate": 4.4014480827955084e-05, + "loss": 4.2293, + "step": 365568 + }, + { + "epoch": 1.02, + "learning_rate": 4.400609488044456e-05, + "loss": 4.2306, + "step": 366080 + }, + { + "epoch": 1.02, + "learning_rate": 4.399772531173777e-05, + "loss": 4.22, + "step": 366592 + }, + { + "epoch": 1.02, + "learning_rate": 4.398933936422725e-05, + "loss": 4.2214, + "step": 367104 + }, + { + "epoch": 1.02, + "learning_rate": 4.398095341671673e-05, + "loss": 4.2262, + "step": 367616 + }, + { + "epoch": 1.02, + "learning_rate": 4.397258384800995e-05, + "loss": 4.2188, + "step": 368128 + }, + { + "epoch": 1.02, + "learning_rate": 4.396419790049943e-05, + "loss": 4.2225, + "step": 368640 + }, + { + "epoch": 1.02, + "learning_rate": 4.395582833179264e-05, + "loss": 4.2259, + "step": 369152 + }, + { + "epoch": 1.02, + "learning_rate": 4.394744238428212e-05, + "loss": 4.2251, + "step": 369664 + }, + { + "epoch": 1.02, + "learning_rate": 4.39390564367716e-05, + "loss": 4.2162, + "step": 370176 + }, + { + "epoch": 1.02, + "learning_rate": 4.393067048926108e-05, + "loss": 4.2157, + "step": 370688 + }, + { + "epoch": 1.02, + "learning_rate": 4.392228454175056e-05, + "loss": 4.2326, + "step": 371200 + }, + { + "epoch": 1.02, + "learning_rate": 4.391391497304377e-05, + "loss": 4.2176, + "step": 371712 + }, + { + "epoch": 1.02, + "learning_rate": 4.390552902553325e-05, + "loss": 4.2322, + "step": 372224 + }, + { + "epoch": 1.02, + "learning_rate": 4.389714307802273e-05, + "loss": 4.2272, + "step": 372736 + }, + { + "epoch": 1.02, + "learning_rate": 4.3888773509315936e-05, + "loss": 4.2242, + "step": 373248 + }, + { + "epoch": 1.02, + "learning_rate": 4.388038756180542e-05, + "loss": 4.2214, + "step": 373760 + }, + { + "epoch": 1.02, + "learning_rate": 4.38720016142949e-05, + "loss": 4.22, + "step": 374272 + }, + { + "epoch": 1.02, + "learning_rate": 4.386361566678438e-05, + "loss": 4.2235, + "step": 374784 + }, + { + "epoch": 1.02, + "learning_rate": 4.385522971927386e-05, + "loss": 4.2185, + "step": 375296 + }, + { + "epoch": 1.02, + "learning_rate": 4.3846843771763336e-05, + "loss": 4.2333, + "step": 375808 + }, + { + "epoch": 1.02, + "learning_rate": 4.3838457824252816e-05, + "loss": 4.2247, + "step": 376320 + }, + { + "epoch": 1.02, + "learning_rate": 4.3830071876742296e-05, + "loss": 4.2277, + "step": 376832 + }, + { + "epoch": 1.02, + "learning_rate": 4.3821685929231775e-05, + "loss": 4.2254, + "step": 377344 + }, + { + "epoch": 1.02, + "learning_rate": 4.3813316360524985e-05, + "loss": 4.2174, + "step": 377856 + }, + { + "epoch": 1.02, + "learning_rate": 4.3804930413014465e-05, + "loss": 4.2174, + "step": 378368 + }, + { + "epoch": 1.02, + "learning_rate": 4.3796544465503944e-05, + "loss": 4.2132, + "step": 378880 + }, + { + "epoch": 1.02, + "learning_rate": 4.3788158517993424e-05, + "loss": 4.2139, + "step": 379392 + }, + { + "epoch": 1.02, + "learning_rate": 4.377978894928664e-05, + "loss": 4.2176, + "step": 379904 + }, + { + "epoch": 1.02, + "learning_rate": 4.377140300177612e-05, + "loss": 4.2147, + "step": 380416 + }, + { + "epoch": 1.02, + "learning_rate": 4.37630170542656e-05, + "loss": 4.2057, + "step": 380928 + }, + { + "epoch": 1.02, + "learning_rate": 4.375463110675508e-05, + "loss": 4.2191, + "step": 381440 + }, + { + "epoch": 1.03, + "eval_loss": 4.204667568206787, + "eval_runtime": 534.7648, + "eval_samples_per_second": 713.568, + "eval_steps_per_second": 22.3, + "step": 381595 + }, + { + "epoch": 0.0, + "learning_rate": 4.374624515924456e-05, + "loss": 4.2284, + "step": 381952 + }, + { + "epoch": 0.0, + "learning_rate": 4.373785921173404e-05, + "loss": 4.2211, + "step": 382464 + }, + { + "epoch": 0.0, + "learning_rate": 4.372947326422352e-05, + "loss": 4.2171, + "step": 382976 + }, + { + "epoch": 0.0, + "learning_rate": 4.3721087316713e-05, + "loss": 4.2143, + "step": 383488 + }, + { + "epoch": 0.0, + "learning_rate": 4.371270136920248e-05, + "loss": 4.2142, + "step": 384000 + }, + { + "epoch": 0.0, + "learning_rate": 4.370431542169196e-05, + "loss": 4.1992, + "step": 384512 + }, + { + "epoch": 0.0, + "learning_rate": 4.369592947418144e-05, + "loss": 4.2138, + "step": 385024 + }, + { + "epoch": 0.0, + "learning_rate": 4.368754352667092e-05, + "loss": 4.2069, + "step": 385536 + }, + { + "epoch": 0.0, + "learning_rate": 4.367915757916039e-05, + "loss": 4.2114, + "step": 386048 + }, + { + "epoch": 0.0, + "learning_rate": 4.367077163164987e-05, + "loss": 4.2164, + "step": 386560 + }, + { + "epoch": 0.0, + "learning_rate": 4.366238568413936e-05, + "loss": 4.2203, + "step": 387072 + }, + { + "epoch": 0.0, + "learning_rate": 4.365399973662884e-05, + "loss": 4.2051, + "step": 387584 + }, + { + "epoch": 0.0, + "learning_rate": 4.364561378911832e-05, + "loss": 4.2108, + "step": 388096 + }, + { + "epoch": 0.0, + "learning_rate": 4.36372278416078e-05, + "loss": 4.2071, + "step": 388608 + }, + { + "epoch": 0.0, + "learning_rate": 4.362884189409728e-05, + "loss": 4.2143, + "step": 389120 + }, + { + "epoch": 0.0, + "learning_rate": 4.362045594658676e-05, + "loss": 4.2041, + "step": 389632 + }, + { + "epoch": 0.0, + "learning_rate": 4.361206999907624e-05, + "loss": 4.203, + "step": 390144 + }, + { + "epoch": 0.0, + "learning_rate": 4.360370043036945e-05, + "loss": 4.2042, + "step": 390656 + }, + { + "epoch": 0.0, + "learning_rate": 4.359531448285893e-05, + "loss": 4.2096, + "step": 391168 + }, + { + "epoch": 0.0, + "learning_rate": 4.358692853534841e-05, + "loss": 4.216, + "step": 391680 + }, + { + "epoch": 0.0, + "learning_rate": 4.357854258783789e-05, + "loss": 4.2063, + "step": 392192 + }, + { + "epoch": 0.0, + "learning_rate": 4.35701730191311e-05, + "loss": 4.2191, + "step": 392704 + }, + { + "epoch": 0.0, + "learning_rate": 4.356178707162058e-05, + "loss": 4.2124, + "step": 393216 + }, + { + "epoch": 0.0, + "learning_rate": 4.355340112411006e-05, + "loss": 4.2114, + "step": 393728 + }, + { + "epoch": 0.0, + "learning_rate": 4.354501517659954e-05, + "loss": 4.203, + "step": 394240 + }, + { + "epoch": 0.0, + "learning_rate": 4.3536629229089024e-05, + "loss": 4.2052, + "step": 394752 + }, + { + "epoch": 0.0, + "learning_rate": 4.3528243281578504e-05, + "loss": 4.2164, + "step": 395264 + }, + { + "epoch": 0.0, + "learning_rate": 4.3519857334067984e-05, + "loss": 4.2015, + "step": 395776 + }, + { + "epoch": 0.0, + "learning_rate": 4.351148776536119e-05, + "loss": 4.209, + "step": 396288 + }, + { + "epoch": 0.0, + "learning_rate": 4.350310181785067e-05, + "loss": 4.201, + "step": 396800 + }, + { + "epoch": 0.01, + "learning_rate": 4.349471587034015e-05, + "loss": 4.1947, + "step": 397312 + }, + { + "epoch": 0.01, + "learning_rate": 4.348632992282963e-05, + "loss": 4.2158, + "step": 397824 + }, + { + "epoch": 0.01, + "learning_rate": 4.3477943975319106e-05, + "loss": 4.2106, + "step": 398336 + }, + { + "epoch": 0.01, + "learning_rate": 4.346957440661232e-05, + "loss": 4.2095, + "step": 398848 + }, + { + "epoch": 0.01, + "learning_rate": 4.34611884591018e-05, + "loss": 4.196, + "step": 399360 + }, + { + "epoch": 0.01, + "learning_rate": 4.345280251159128e-05, + "loss": 4.211, + "step": 399872 + }, + { + "epoch": 0.01, + "learning_rate": 4.344443294288449e-05, + "loss": 4.2024, + "step": 400384 + }, + { + "epoch": 0.01, + "learning_rate": 4.343604699537398e-05, + "loss": 4.2113, + "step": 400896 + }, + { + "epoch": 0.01, + "learning_rate": 4.342766104786346e-05, + "loss": 4.2032, + "step": 401408 + }, + { + "epoch": 0.01, + "learning_rate": 4.341927510035294e-05, + "loss": 4.1939, + "step": 401920 + }, + { + "epoch": 0.01, + "learning_rate": 4.341088915284241e-05, + "loss": 4.1916, + "step": 402432 + }, + { + "epoch": 0.01, + "learning_rate": 4.340250320533189e-05, + "loss": 4.1898, + "step": 402944 + }, + { + "epoch": 0.01, + "learning_rate": 4.339411725782137e-05, + "loss": 4.208, + "step": 403456 + }, + { + "epoch": 0.01, + "learning_rate": 4.338574768911458e-05, + "loss": 4.198, + "step": 403968 + }, + { + "epoch": 0.01, + "learning_rate": 4.337736174160406e-05, + "loss": 4.1923, + "step": 404480 + }, + { + "epoch": 0.01, + "learning_rate": 4.336897579409354e-05, + "loss": 4.1994, + "step": 404992 + }, + { + "epoch": 0.01, + "learning_rate": 4.336058984658302e-05, + "loss": 4.1965, + "step": 405504 + }, + { + "epoch": 0.01, + "learning_rate": 4.33522038990725e-05, + "loss": 4.2103, + "step": 406016 + }, + { + "epoch": 0.01, + "learning_rate": 4.334381795156198e-05, + "loss": 4.1913, + "step": 406528 + }, + { + "epoch": 0.01, + "learning_rate": 4.333543200405146e-05, + "loss": 4.1944, + "step": 407040 + }, + { + "epoch": 0.01, + "learning_rate": 4.3327046056540946e-05, + "loss": 4.1976, + "step": 407552 + }, + { + "epoch": 0.01, + "learning_rate": 4.3318676487834155e-05, + "loss": 4.2006, + "step": 408064 + }, + { + "epoch": 0.01, + "learning_rate": 4.3310306919127365e-05, + "loss": 4.1882, + "step": 408576 + }, + { + "epoch": 0.01, + "learning_rate": 4.3301920971616844e-05, + "loss": 4.1948, + "step": 409088 + }, + { + "epoch": 0.01, + "learning_rate": 4.3293535024106324e-05, + "loss": 4.1901, + "step": 409600 + }, + { + "epoch": 0.01, + "learning_rate": 4.3285149076595804e-05, + "loss": 4.1966, + "step": 410112 + }, + { + "epoch": 0.01, + "learning_rate": 4.3276763129085284e-05, + "loss": 4.1932, + "step": 410624 + }, + { + "epoch": 0.01, + "learning_rate": 4.3268377181574764e-05, + "loss": 4.1895, + "step": 411136 + }, + { + "epoch": 0.01, + "learning_rate": 4.3259991234064244e-05, + "loss": 4.2013, + "step": 411648 + }, + { + "epoch": 0.01, + "learning_rate": 4.3251605286553724e-05, + "loss": 4.1858, + "step": 412160 + }, + { + "epoch": 0.01, + "learning_rate": 4.3243219339043204e-05, + "loss": 4.1827, + "step": 412672 + }, + { + "epoch": 0.01, + "learning_rate": 4.323484977033641e-05, + "loss": 4.1846, + "step": 413184 + }, + { + "epoch": 0.01, + "learning_rate": 4.32264638228259e-05, + "loss": 4.1877, + "step": 413696 + }, + { + "epoch": 0.01, + "learning_rate": 4.321807787531538e-05, + "loss": 4.203, + "step": 414208 + }, + { + "epoch": 0.01, + "learning_rate": 4.320969192780486e-05, + "loss": 4.1839, + "step": 414720 + }, + { + "epoch": 0.01, + "learning_rate": 4.320130598029434e-05, + "loss": 4.1912, + "step": 415232 + }, + { + "epoch": 0.01, + "learning_rate": 4.319293641158755e-05, + "loss": 4.1707, + "step": 415744 + }, + { + "epoch": 0.01, + "learning_rate": 4.318455046407703e-05, + "loss": 4.1917, + "step": 416256 + }, + { + "epoch": 0.01, + "learning_rate": 4.317618089537024e-05, + "loss": 4.1812, + "step": 416768 + }, + { + "epoch": 0.01, + "learning_rate": 4.316779494785972e-05, + "loss": 4.1833, + "step": 417280 + }, + { + "epoch": 0.01, + "learning_rate": 4.31594090003492e-05, + "loss": 4.1942, + "step": 417792 + }, + { + "epoch": 0.01, + "learning_rate": 4.315102305283868e-05, + "loss": 4.187, + "step": 418304 + }, + { + "epoch": 0.01, + "learning_rate": 4.314263710532816e-05, + "loss": 4.1912, + "step": 418816 + }, + { + "epoch": 0.01, + "learning_rate": 4.313426753662137e-05, + "loss": 4.1991, + "step": 419328 + }, + { + "epoch": 0.01, + "learning_rate": 4.312589796791458e-05, + "loss": 4.192, + "step": 419840 + }, + { + "epoch": 0.01, + "learning_rate": 4.311751202040406e-05, + "loss": 4.1997, + "step": 420352 + }, + { + "epoch": 0.01, + "learning_rate": 4.310912607289354e-05, + "loss": 4.1841, + "step": 420864 + }, + { + "epoch": 0.01, + "learning_rate": 4.310074012538302e-05, + "loss": 4.1749, + "step": 421376 + }, + { + "epoch": 0.01, + "learning_rate": 4.30923541778725e-05, + "loss": 4.1875, + "step": 421888 + }, + { + "epoch": 0.01, + "learning_rate": 4.308398460916571e-05, + "loss": 4.1967, + "step": 422400 + }, + { + "epoch": 0.01, + "learning_rate": 4.307559866165519e-05, + "loss": 4.1837, + "step": 422912 + }, + { + "epoch": 0.01, + "learning_rate": 4.306721271414467e-05, + "loss": 4.1825, + "step": 423424 + }, + { + "epoch": 0.01, + "learning_rate": 4.305882676663415e-05, + "loss": 4.1698, + "step": 423936 + }, + { + "epoch": 0.01, + "learning_rate": 4.305044081912363e-05, + "loss": 4.1811, + "step": 424448 + }, + { + "epoch": 0.01, + "learning_rate": 4.304205487161311e-05, + "loss": 4.1746, + "step": 424960 + }, + { + "epoch": 0.01, + "learning_rate": 4.303366892410259e-05, + "loss": 4.1865, + "step": 425472 + }, + { + "epoch": 0.01, + "learning_rate": 4.302528297659207e-05, + "loss": 4.1872, + "step": 425984 + }, + { + "epoch": 0.01, + "learning_rate": 4.301691340788529e-05, + "loss": 4.1918, + "step": 426496 + }, + { + "epoch": 0.01, + "learning_rate": 4.300852746037477e-05, + "loss": 4.1822, + "step": 427008 + }, + { + "epoch": 0.02, + "learning_rate": 4.300014151286425e-05, + "loss": 4.1845, + "step": 427520 + }, + { + "epoch": 0.02, + "learning_rate": 4.299175556535372e-05, + "loss": 4.17, + "step": 428032 + }, + { + "epoch": 0.02, + "learning_rate": 4.29833696178432e-05, + "loss": 4.1767, + "step": 428544 + }, + { + "epoch": 0.02, + "learning_rate": 4.297498367033268e-05, + "loss": 4.1818, + "step": 429056 + }, + { + "epoch": 0.02, + "learning_rate": 4.296661410162589e-05, + "loss": 4.1752, + "step": 429568 + }, + { + "epoch": 0.02, + "learning_rate": 4.295822815411537e-05, + "loss": 4.1743, + "step": 430080 + }, + { + "epoch": 0.02, + "learning_rate": 4.294984220660485e-05, + "loss": 4.1888, + "step": 430592 + }, + { + "epoch": 0.02, + "learning_rate": 4.294145625909433e-05, + "loss": 4.1739, + "step": 431104 + }, + { + "epoch": 0.02, + "learning_rate": 4.293308669038754e-05, + "loss": 4.1978, + "step": 431616 + }, + { + "epoch": 0.02, + "learning_rate": 4.2924700742877025e-05, + "loss": 4.1726, + "step": 432128 + }, + { + "epoch": 0.02, + "learning_rate": 4.2916314795366505e-05, + "loss": 4.1899, + "step": 432640 + }, + { + "epoch": 0.02, + "learning_rate": 4.2907928847855985e-05, + "loss": 4.178, + "step": 433152 + }, + { + "epoch": 0.02, + "learning_rate": 4.2899542900345465e-05, + "loss": 4.1768, + "step": 433664 + }, + { + "epoch": 0.02, + "learning_rate": 4.2891156952834945e-05, + "loss": 4.196, + "step": 434176 + }, + { + "epoch": 0.02, + "learning_rate": 4.2882771005324425e-05, + "loss": 4.1706, + "step": 434688 + }, + { + "epoch": 0.02, + "learning_rate": 4.2874401436617634e-05, + "loss": 4.1915, + "step": 435200 + }, + { + "epoch": 0.02, + "learning_rate": 4.2866015489107114e-05, + "loss": 4.1688, + "step": 435712 + }, + { + "epoch": 0.02, + "learning_rate": 4.2857629541596594e-05, + "loss": 4.1677, + "step": 436224 + }, + { + "epoch": 0.02, + "learning_rate": 4.2849243594086074e-05, + "loss": 4.166, + "step": 436736 + }, + { + "epoch": 0.02, + "learning_rate": 4.284087402537928e-05, + "loss": 4.1802, + "step": 437248 + }, + { + "epoch": 0.02, + "learning_rate": 4.283248807786876e-05, + "loss": 4.1796, + "step": 437760 + }, + { + "epoch": 0.02, + "learning_rate": 4.282410213035824e-05, + "loss": 4.1712, + "step": 438272 + }, + { + "epoch": 0.02, + "learning_rate": 4.281571618284772e-05, + "loss": 4.1582, + "step": 438784 + }, + { + "epoch": 0.02, + "learning_rate": 4.280734661414094e-05, + "loss": 4.1719, + "step": 439296 + }, + { + "epoch": 0.02, + "learning_rate": 4.279896066663042e-05, + "loss": 4.1838, + "step": 439808 + }, + { + "epoch": 0.02, + "learning_rate": 4.27905747191199e-05, + "loss": 4.1784, + "step": 440320 + }, + { + "epoch": 0.02, + "learning_rate": 4.278218877160938e-05, + "loss": 4.1824, + "step": 440832 + }, + { + "epoch": 0.02, + "learning_rate": 4.277380282409886e-05, + "loss": 4.1765, + "step": 441344 + }, + { + "epoch": 0.02, + "learning_rate": 4.276541687658834e-05, + "loss": 4.1772, + "step": 441856 + }, + { + "epoch": 0.02, + "learning_rate": 4.275703092907782e-05, + "loss": 4.1807, + "step": 442368 + }, + { + "epoch": 0.02, + "learning_rate": 4.27486449815673e-05, + "loss": 4.1717, + "step": 442880 + }, + { + "epoch": 0.02, + "learning_rate": 4.274027541286051e-05, + "loss": 4.1702, + "step": 443392 + }, + { + "epoch": 0.02, + "learning_rate": 4.273188946534999e-05, + "loss": 4.1741, + "step": 443904 + }, + { + "epoch": 0.02, + "learning_rate": 4.272350351783947e-05, + "loss": 4.1678, + "step": 444416 + }, + { + "epoch": 0.02, + "learning_rate": 4.2715133949132676e-05, + "loss": 4.1717, + "step": 444928 + }, + { + "epoch": 0.02, + "learning_rate": 4.270674800162216e-05, + "loss": 4.1749, + "step": 445440 + }, + { + "epoch": 0.02, + "learning_rate": 4.269836205411164e-05, + "loss": 4.173, + "step": 445952 + }, + { + "epoch": 0.02, + "learning_rate": 4.268997610660112e-05, + "loss": 4.1703, + "step": 446464 + }, + { + "epoch": 0.02, + "learning_rate": 4.26815901590906e-05, + "loss": 4.1638, + "step": 446976 + }, + { + "epoch": 0.02, + "learning_rate": 4.2673204211580076e-05, + "loss": 4.1805, + "step": 447488 + }, + { + "epoch": 0.02, + "learning_rate": 4.2664818264069556e-05, + "loss": 4.1661, + "step": 448000 + }, + { + "epoch": 0.02, + "learning_rate": 4.2656432316559036e-05, + "loss": 4.1784, + "step": 448512 + }, + { + "epoch": 0.02, + "learning_rate": 4.264806274785225e-05, + "loss": 4.1814, + "step": 449024 + }, + { + "epoch": 0.02, + "learning_rate": 4.2639676800341725e-05, + "loss": 4.1736, + "step": 449536 + }, + { + "epoch": 0.02, + "learning_rate": 4.2631290852831205e-05, + "loss": 4.1755, + "step": 450048 + }, + { + "epoch": 0.02, + "learning_rate": 4.2622904905320685e-05, + "loss": 4.1708, + "step": 450560 + }, + { + "epoch": 0.02, + "learning_rate": 4.2614518957810165e-05, + "loss": 4.1721, + "step": 451072 + }, + { + "epoch": 0.02, + "learning_rate": 4.2606133010299645e-05, + "loss": 4.1652, + "step": 451584 + }, + { + "epoch": 0.02, + "learning_rate": 4.259776344159286e-05, + "loss": 4.183, + "step": 452096 + }, + { + "epoch": 0.02, + "learning_rate": 4.258937749408234e-05, + "loss": 4.1798, + "step": 452608 + }, + { + "epoch": 0.02, + "learning_rate": 4.258099154657182e-05, + "loss": 4.1746, + "step": 453120 + }, + { + "epoch": 0.02, + "learning_rate": 4.25726055990613e-05, + "loss": 4.1739, + "step": 453632 + }, + { + "epoch": 0.02, + "learning_rate": 4.256421965155078e-05, + "loss": 4.17, + "step": 454144 + }, + { + "epoch": 0.02, + "learning_rate": 4.255583370404026e-05, + "loss": 4.1712, + "step": 454656 + }, + { + "epoch": 0.02, + "learning_rate": 4.254744775652974e-05, + "loss": 4.1641, + "step": 455168 + }, + { + "epoch": 0.02, + "learning_rate": 4.253906180901922e-05, + "loss": 4.1593, + "step": 455680 + }, + { + "epoch": 0.02, + "learning_rate": 4.253069224031243e-05, + "loss": 4.1722, + "step": 456192 + }, + { + "epoch": 0.02, + "learning_rate": 4.252230629280191e-05, + "loss": 4.1643, + "step": 456704 + }, + { + "epoch": 0.02, + "learning_rate": 4.251392034529139e-05, + "loss": 4.155, + "step": 457216 + }, + { + "epoch": 0.02, + "learning_rate": 4.250553439778087e-05, + "loss": 4.1676, + "step": 457728 + }, + { + "epoch": 0.03, + "eval_loss": 4.164071083068848, + "eval_runtime": 556.8816, + "eval_samples_per_second": 685.228, + "eval_steps_per_second": 21.414, + "step": 457914 + }, + { + "epoch": 0.0, + "learning_rate": 4.2497164829074085e-05, + "loss": 4.1795, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.2488778881563565e-05, + "loss": 4.1726, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.2480392934053045e-05, + "loss": 4.1683, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.2472006986542525e-05, + "loss": 4.166, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.2463621039032005e-05, + "loss": 4.1672, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.2455251470325214e-05, + "loss": 4.1548, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.2446865522814694e-05, + "loss": 4.1647, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.2438479575304174e-05, + "loss": 4.1585, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.2430093627793654e-05, + "loss": 4.1624, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.2421707680283134e-05, + "loss": 4.1668, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.2413321732772614e-05, + "loss": 4.1758, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.240493578526209e-05, + "loss": 4.1526, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.239654983775157e-05, + "loss": 4.168, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.238816389024105e-05, + "loss": 4.1594, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.2379777942730534e-05, + "loss": 4.1705, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.2371391995220014e-05, + "loss": 4.153, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.2363006047709494e-05, + "loss": 4.1546, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.2354620100198974e-05, + "loss": 4.1608, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.2346234152688454e-05, + "loss": 4.158, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.2337848205177934e-05, + "loss": 4.1671, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.2329462257667414e-05, + "loss": 4.1604, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232109268896062e-05, + "loss": 4.17, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.23127067414501e-05, + "loss": 4.1673, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.230432079393958e-05, + "loss": 4.1609, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.229593484642906e-05, + "loss": 4.1549, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.228754889891854e-05, + "loss": 4.1578, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.227916295140802e-05, + "loss": 4.1693, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.22707770038975e-05, + "loss": 4.157, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.226239105638698e-05, + "loss": 4.16, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.22540214876802e-05, + "loss": 4.1582, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.224563554016968e-05, + "loss": 4.1493, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.223724959265915e-05, + "loss": 4.1659, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.222886364514863e-05, + "loss": 4.1654, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.222047769763811e-05, + "loss": 4.1647, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.221210812893133e-05, + "loss": 4.1479, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.22037221814208e-05, + "loss": 4.1636, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.219533623391028e-05, + "loss": 4.1563, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.218695028639976e-05, + "loss": 4.1634, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.217856433888924e-05, + "loss": 4.1579, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.217017839137872e-05, + "loss": 4.1493, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.21617924438682e-05, + "loss": 4.1411, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.215340649635769e-05, + "loss": 4.1419, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.214502054884717e-05, + "loss": 4.1662, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.2136650980140376e-05, + "loss": 4.1512, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.2128265032629856e-05, + "loss": 4.1462, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.2119879085119336e-05, + "loss": 4.1583, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.2111493137608816e-05, + "loss": 4.1503, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.2103123568902025e-05, + "loss": 4.1624, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.2094737621391505e-05, + "loss": 4.1492, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.2086351673880985e-05, + "loss": 4.1524, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.2077965726370465e-05, + "loss": 4.1501, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.2069596157663674e-05, + "loss": 4.155, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.2061210210153154e-05, + "loss": 4.1483, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.2052824262642634e-05, + "loss": 4.1462, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.204443831513212e-05, + "loss": 4.1475, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.20360523676216e-05, + "loss": 4.1539, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.202766642011108e-05, + "loss": 4.1452, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.201928047260056e-05, + "loss": 4.1438, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.201089452509004e-05, + "loss": 4.157, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.200252495638325e-05, + "loss": 4.1438, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.199413900887273e-05, + "loss": 4.1383, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.198575306136221e-05, + "loss": 4.1396, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.197736711385169e-05, + "loss": 4.1433, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.19689975451449e-05, + "loss": 4.1615, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.196061159763438e-05, + "loss": 4.1395, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195222565012386e-05, + "loss": 4.1466, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.194383970261334e-05, + "loss": 4.1284, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.1935470133906554e-05, + "loss": 4.1468, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.1927084186396034e-05, + "loss": 4.1369, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.1918698238885514e-05, + "loss": 4.1417, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.191031229137499e-05, + "loss": 4.1482, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.19019427226682e-05, + "loss": 4.1426, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.189355677515768e-05, + "loss": 4.1491, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.188517082764716e-05, + "loss": 4.1538, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.1876784880136636e-05, + "loss": 4.1502, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.186841531142985e-05, + "loss": 4.1541, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.186002936391933e-05, + "loss": 4.147, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.185165979521254e-05, + "loss": 4.1302, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.184327384770203e-05, + "loss": 4.1426, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.183488790019151e-05, + "loss": 4.1487, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.182650195268099e-05, + "loss": 4.1454, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.181811600517046e-05, + "loss": 4.1424, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.180974643646368e-05, + "loss": 4.1233, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.180136048895316e-05, + "loss": 4.1409, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.179297454144264e-05, + "loss": 4.131, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.178458859393211e-05, + "loss": 4.1467, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.177620264642159e-05, + "loss": 4.1427, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.176781669891107e-05, + "loss": 4.1505, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.175943075140055e-05, + "loss": 4.1371, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.1751061182693766e-05, + "loss": 4.1414, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.1742675235183246e-05, + "loss": 4.1297, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.1734289287672726e-05, + "loss": 4.1405, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.1725903340162206e-05, + "loss": 4.1347, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.1717517392651685e-05, + "loss": 4.1353, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.1709131445141165e-05, + "loss": 4.1292, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.1700745497630645e-05, + "loss": 4.1426, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.1692375928923855e-05, + "loss": 4.1338, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.1683989981413334e-05, + "loss": 4.1579, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.1675604033902814e-05, + "loss": 4.1319, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.1667218086392294e-05, + "loss": 4.1482, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.1658832138881774e-05, + "loss": 4.1373, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.1650446191371254e-05, + "loss": 4.1361, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.1642060243860734e-05, + "loss": 4.1511, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.163369067515395e-05, + "loss": 4.1359, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.162530472764343e-05, + "loss": 4.1468, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.161691878013291e-05, + "loss": 4.1339, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.160853283262239e-05, + "loss": 4.1226, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160014688511187e-05, + "loss": 4.1253, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.159176093760135e-05, + "loss": 4.14, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.158337499009082e-05, + "loss": 4.138, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.15749890425803e-05, + "loss": 4.1339, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.156663585267725e-05, + "loss": 4.1123, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155824990516673e-05, + "loss": 4.13, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.154988033645994e-05, + "loss": 4.1438, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154149438894942e-05, + "loss": 4.1374, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.1533108441438904e-05, + "loss": 4.1424, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.1524722493928384e-05, + "loss": 4.1376, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.1516336546417864e-05, + "loss": 4.1371, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.1507950598907344e-05, + "loss": 4.1392, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.149958103020055e-05, + "loss": 4.1334, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.149119508269003e-05, + "loss": 4.1273, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.148280913517951e-05, + "loss": 4.1333, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.147442318766899e-05, + "loss": 4.1296, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.146603724015847e-05, + "loss": 4.1325, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.1457651292647946e-05, + "loss": 4.1366, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.1449265345137426e-05, + "loss": 4.1324, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.1440879397626906e-05, + "loss": 4.128, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.1432493450116386e-05, + "loss": 4.1261, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.1424107502605866e-05, + "loss": 4.1396, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.141572155509535e-05, + "loss": 4.1261, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.140733560758483e-05, + "loss": 4.1408, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.139896603887804e-05, + "loss": 4.1443, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.139058009136752e-05, + "loss": 4.1328, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.138221052266073e-05, + "loss": 4.136, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.137382457515021e-05, + "loss": 4.1329, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.136543862763969e-05, + "loss": 4.1302, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.135705268012917e-05, + "loss": 4.1267, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.134866673261865e-05, + "loss": 4.144, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.134028078510813e-05, + "loss": 4.1404, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.133189483759761e-05, + "loss": 4.1378, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.132350889008709e-05, + "loss": 4.136, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.1315139321380306e-05, + "loss": 4.1283, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.1306753373869786e-05, + "loss": 4.1301, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.1298367426359266e-05, + "loss": 4.1274, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.1289997857652475e-05, + "loss": 4.1204, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.1281611910141955e-05, + "loss": 4.1365, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.1273225962631435e-05, + "loss": 4.1263, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.1264840015120915e-05, + "loss": 4.1168, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.1256454067610395e-05, + "loss": 4.1315, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 4.133627414703369, + "eval_runtime": 530.381, + "eval_samples_per_second": 719.466, + "eval_steps_per_second": 22.484, + "step": 534233 + }, + { + "epoch": 0.0, + "learning_rate": 4.1248084498903604e-05, + "loss": 4.1414, + "step": 534528 + }, + { + "epoch": 0.0, + "learning_rate": 4.1239698551393084e-05, + "loss": 4.1321, + "step": 535040 + }, + { + "epoch": 0.0, + "learning_rate": 4.1231312603882564e-05, + "loss": 4.1368, + "step": 535552 + }, + { + "epoch": 0.0, + "learning_rate": 4.1222926656372044e-05, + "loss": 4.127, + "step": 536064 + }, + { + "epoch": 0.0, + "learning_rate": 4.1214540708861524e-05, + "loss": 4.1244, + "step": 536576 + }, + { + "epoch": 0.0, + "learning_rate": 4.1206154761351004e-05, + "loss": 4.1207, + "step": 537088 + }, + { + "epoch": 0.0, + "learning_rate": 4.1197768813840484e-05, + "loss": 4.1247, + "step": 537600 + }, + { + "epoch": 0.0, + "learning_rate": 4.1189382866329964e-05, + "loss": 4.122, + "step": 538112 + }, + { + "epoch": 0.0, + "learning_rate": 4.1180996918819444e-05, + "loss": 4.1231, + "step": 538624 + }, + { + "epoch": 0.0, + "learning_rate": 4.1172610971308923e-05, + "loss": 4.1242, + "step": 539136 + }, + { + "epoch": 0.0, + "learning_rate": 4.1164225023798403e-05, + "loss": 4.139, + "step": 539648 + }, + { + "epoch": 0.0, + "learning_rate": 4.1155839076287883e-05, + "loss": 4.1183, + "step": 540160 + }, + { + "epoch": 0.0, + "learning_rate": 4.114745312877736e-05, + "loss": 4.1303, + "step": 540672 + }, + { + "epoch": 0.0, + "learning_rate": 4.113906718126684e-05, + "loss": 4.1162, + "step": 541184 + }, + { + "epoch": 0.0, + "learning_rate": 4.113068123375632e-05, + "loss": 4.133, + "step": 541696 + }, + { + "epoch": 0.0, + "learning_rate": 4.11222952862458e-05, + "loss": 4.116, + "step": 542208 + }, + { + "epoch": 0.0, + "learning_rate": 4.111390933873528e-05, + "loss": 4.1184, + "step": 542720 + }, + { + "epoch": 0.0, + "learning_rate": 4.110552339122476e-05, + "loss": 4.1206, + "step": 543232 + }, + { + "epoch": 0.0, + "learning_rate": 4.109717020132171e-05, + "loss": 4.1204, + "step": 543744 + }, + { + "epoch": 0.0, + "learning_rate": 4.108878425381119e-05, + "loss": 4.1288, + "step": 544256 + }, + { + "epoch": 0.0, + "learning_rate": 4.108039830630067e-05, + "loss": 4.1241, + "step": 544768 + }, + { + "epoch": 0.0, + "learning_rate": 4.107201235879015e-05, + "loss": 4.1362, + "step": 545280 + }, + { + "epoch": 0.0, + "learning_rate": 4.106362641127963e-05, + "loss": 4.1254, + "step": 545792 + }, + { + "epoch": 0.0, + "learning_rate": 4.105524046376911e-05, + "loss": 4.1264, + "step": 546304 + }, + { + "epoch": 0.0, + "learning_rate": 4.104685451625859e-05, + "loss": 4.1208, + "step": 546816 + }, + { + "epoch": 0.0, + "learning_rate": 4.103846856874807e-05, + "loss": 4.1218, + "step": 547328 + }, + { + "epoch": 0.0, + "learning_rate": 4.103008262123755e-05, + "loss": 4.1272, + "step": 547840 + }, + { + "epoch": 0.0, + "learning_rate": 4.102169667372702e-05, + "loss": 4.1196, + "step": 548352 + }, + { + "epoch": 0.0, + "learning_rate": 4.10133107262165e-05, + "loss": 4.1257, + "step": 548864 + }, + { + "epoch": 0.0, + "learning_rate": 4.100494115750972e-05, + "loss": 4.1202, + "step": 549376 + }, + { + "epoch": 0.01, + "learning_rate": 4.09965552099992e-05, + "loss": 4.1142, + "step": 549888 + }, + { + "epoch": 0.01, + "learning_rate": 4.098816926248868e-05, + "loss": 4.1261, + "step": 550400 + }, + { + "epoch": 0.01, + "learning_rate": 4.097978331497816e-05, + "loss": 4.1309, + "step": 550912 + }, + { + "epoch": 0.01, + "learning_rate": 4.097141374627137e-05, + "loss": 4.125, + "step": 551424 + }, + { + "epoch": 0.01, + "learning_rate": 4.0963027798760846e-05, + "loss": 4.1142, + "step": 551936 + }, + { + "epoch": 0.01, + "learning_rate": 4.0954641851250326e-05, + "loss": 4.1273, + "step": 552448 + }, + { + "epoch": 0.01, + "learning_rate": 4.0946255903739806e-05, + "loss": 4.1206, + "step": 552960 + }, + { + "epoch": 0.01, + "learning_rate": 4.0937869956229286e-05, + "loss": 4.1269, + "step": 553472 + }, + { + "epoch": 0.01, + "learning_rate": 4.0929484008718766e-05, + "loss": 4.1211, + "step": 553984 + }, + { + "epoch": 0.01, + "learning_rate": 4.0921098061208245e-05, + "loss": 4.1156, + "step": 554496 + }, + { + "epoch": 0.01, + "learning_rate": 4.0912712113697725e-05, + "loss": 4.1069, + "step": 555008 + }, + { + "epoch": 0.01, + "learning_rate": 4.0904326166187205e-05, + "loss": 4.108, + "step": 555520 + }, + { + "epoch": 0.01, + "learning_rate": 4.0895956597480414e-05, + "loss": 4.1261, + "step": 556032 + }, + { + "epoch": 0.01, + "learning_rate": 4.0887570649969894e-05, + "loss": 4.1168, + "step": 556544 + }, + { + "epoch": 0.01, + "learning_rate": 4.087920108126311e-05, + "loss": 4.1115, + "step": 557056 + }, + { + "epoch": 0.01, + "learning_rate": 4.087081513375259e-05, + "loss": 4.1215, + "step": 557568 + }, + { + "epoch": 0.01, + "learning_rate": 4.086242918624207e-05, + "loss": 4.1138, + "step": 558080 + }, + { + "epoch": 0.01, + "learning_rate": 4.085404323873155e-05, + "loss": 4.1268, + "step": 558592 + }, + { + "epoch": 0.01, + "learning_rate": 4.084565729122103e-05, + "loss": 4.1122, + "step": 559104 + }, + { + "epoch": 0.01, + "learning_rate": 4.083727134371051e-05, + "loss": 4.1195, + "step": 559616 + }, + { + "epoch": 0.01, + "learning_rate": 4.082888539619999e-05, + "loss": 4.1115, + "step": 560128 + }, + { + "epoch": 0.01, + "learning_rate": 4.08205158274932e-05, + "loss": 4.1199, + "step": 560640 + }, + { + "epoch": 0.01, + "learning_rate": 4.081212987998268e-05, + "loss": 4.1133, + "step": 561152 + }, + { + "epoch": 0.01, + "learning_rate": 4.080374393247216e-05, + "loss": 4.1078, + "step": 561664 + }, + { + "epoch": 0.01, + "learning_rate": 4.079535798496164e-05, + "loss": 4.1158, + "step": 562176 + }, + { + "epoch": 0.01, + "learning_rate": 4.078697203745112e-05, + "loss": 4.1149, + "step": 562688 + }, + { + "epoch": 0.01, + "learning_rate": 4.07785860899406e-05, + "loss": 4.1107, + "step": 563200 + }, + { + "epoch": 0.01, + "learning_rate": 4.0770216521233815e-05, + "loss": 4.1109, + "step": 563712 + }, + { + "epoch": 0.01, + "learning_rate": 4.0761830573723295e-05, + "loss": 4.1234, + "step": 564224 + }, + { + "epoch": 0.01, + "learning_rate": 4.0753444626212775e-05, + "loss": 4.102, + "step": 564736 + }, + { + "epoch": 0.01, + "learning_rate": 4.0745058678702255e-05, + "loss": 4.1062, + "step": 565248 + }, + { + "epoch": 0.01, + "learning_rate": 4.0736672731191735e-05, + "loss": 4.1045, + "step": 565760 + }, + { + "epoch": 0.01, + "learning_rate": 4.072828678368121e-05, + "loss": 4.1094, + "step": 566272 + }, + { + "epoch": 0.01, + "learning_rate": 4.071990083617069e-05, + "loss": 4.1234, + "step": 566784 + }, + { + "epoch": 0.01, + "learning_rate": 4.071151488866017e-05, + "loss": 4.1058, + "step": 567296 + }, + { + "epoch": 0.01, + "learning_rate": 4.070312894114965e-05, + "loss": 4.1117, + "step": 567808 + }, + { + "epoch": 0.01, + "learning_rate": 4.069475937244286e-05, + "loss": 4.096, + "step": 568320 + }, + { + "epoch": 0.01, + "learning_rate": 4.068638980373607e-05, + "loss": 4.1105, + "step": 568832 + }, + { + "epoch": 0.01, + "learning_rate": 4.067800385622555e-05, + "loss": 4.1026, + "step": 569344 + }, + { + "epoch": 0.01, + "learning_rate": 4.066961790871503e-05, + "loss": 4.1097, + "step": 569856 + }, + { + "epoch": 0.01, + "learning_rate": 4.066123196120451e-05, + "loss": 4.1127, + "step": 570368 + }, + { + "epoch": 0.01, + "learning_rate": 4.065284601369399e-05, + "loss": 4.1084, + "step": 570880 + }, + { + "epoch": 0.01, + "learning_rate": 4.064447644498721e-05, + "loss": 4.1122, + "step": 571392 + }, + { + "epoch": 0.01, + "learning_rate": 4.063609049747668e-05, + "loss": 4.1213, + "step": 571904 + }, + { + "epoch": 0.01, + "learning_rate": 4.062770454996616e-05, + "loss": 4.1122, + "step": 572416 + }, + { + "epoch": 0.01, + "learning_rate": 4.061931860245564e-05, + "loss": 4.1195, + "step": 572928 + }, + { + "epoch": 0.01, + "learning_rate": 4.061093265494512e-05, + "loss": 4.1101, + "step": 573440 + }, + { + "epoch": 0.01, + "learning_rate": 4.06025467074346e-05, + "loss": 4.0985, + "step": 573952 + }, + { + "epoch": 0.01, + "learning_rate": 4.059417713872781e-05, + "loss": 4.108, + "step": 574464 + }, + { + "epoch": 0.01, + "learning_rate": 4.0585807570021026e-05, + "loss": 4.1142, + "step": 574976 + }, + { + "epoch": 0.01, + "learning_rate": 4.0577421622510506e-05, + "loss": 4.1132, + "step": 575488 + }, + { + "epoch": 0.01, + "learning_rate": 4.0569035674999986e-05, + "loss": 4.107, + "step": 576000 + }, + { + "epoch": 0.01, + "learning_rate": 4.0560649727489466e-05, + "loss": 4.0924, + "step": 576512 + }, + { + "epoch": 0.01, + "learning_rate": 4.0552263779978946e-05, + "loss": 4.1027, + "step": 577024 + }, + { + "epoch": 0.01, + "learning_rate": 4.0543877832468426e-05, + "loss": 4.0989, + "step": 577536 + }, + { + "epoch": 0.01, + "learning_rate": 4.0535491884957906e-05, + "loss": 4.1117, + "step": 578048 + }, + { + "epoch": 0.01, + "learning_rate": 4.0527105937447386e-05, + "loss": 4.1067, + "step": 578560 + }, + { + "epoch": 0.01, + "learning_rate": 4.0518719989936866e-05, + "loss": 4.1144, + "step": 579072 + }, + { + "epoch": 0.01, + "learning_rate": 4.0510334042426346e-05, + "loss": 4.1075, + "step": 579584 + }, + { + "epoch": 0.02, + "learning_rate": 4.0501964473719555e-05, + "loss": 4.1035, + "step": 580096 + }, + { + "epoch": 0.02, + "learning_rate": 4.0493578526209035e-05, + "loss": 4.0995, + "step": 580608 + }, + { + "epoch": 0.02, + "learning_rate": 4.0485192578698515e-05, + "loss": 4.1046, + "step": 581120 + }, + { + "epoch": 0.02, + "learning_rate": 4.0476806631187995e-05, + "loss": 4.0985, + "step": 581632 + }, + { + "epoch": 0.02, + "learning_rate": 4.0468420683677475e-05, + "loss": 4.1012, + "step": 582144 + }, + { + "epoch": 0.02, + "learning_rate": 4.0460034736166955e-05, + "loss": 4.0981, + "step": 582656 + }, + { + "epoch": 0.02, + "learning_rate": 4.0451648788656435e-05, + "loss": 4.1091, + "step": 583168 + }, + { + "epoch": 0.02, + "learning_rate": 4.0443262841145915e-05, + "loss": 4.1017, + "step": 583680 + }, + { + "epoch": 0.02, + "learning_rate": 4.0434876893635395e-05, + "loss": 4.1251, + "step": 584192 + }, + { + "epoch": 0.02, + "learning_rate": 4.042650732492861e-05, + "loss": 4.0949, + "step": 584704 + }, + { + "epoch": 0.02, + "learning_rate": 4.041812137741809e-05, + "loss": 4.115, + "step": 585216 + }, + { + "epoch": 0.02, + "learning_rate": 4.040973542990757e-05, + "loss": 4.1075, + "step": 585728 + }, + { + "epoch": 0.02, + "learning_rate": 4.0401349482397044e-05, + "loss": 4.1007, + "step": 586240 + }, + { + "epoch": 0.02, + "learning_rate": 4.039297991369026e-05, + "loss": 4.1114, + "step": 586752 + }, + { + "epoch": 0.02, + "learning_rate": 4.038461034498347e-05, + "loss": 4.1052, + "step": 587264 + }, + { + "epoch": 0.02, + "learning_rate": 4.037622439747295e-05, + "loss": 4.1095, + "step": 587776 + }, + { + "epoch": 0.02, + "learning_rate": 4.036783844996243e-05, + "loss": 4.1011, + "step": 588288 + }, + { + "epoch": 0.02, + "learning_rate": 4.035945250245191e-05, + "loss": 4.0909, + "step": 588800 + }, + { + "epoch": 0.02, + "learning_rate": 4.035106655494139e-05, + "loss": 4.0941, + "step": 589312 + }, + { + "epoch": 0.02, + "learning_rate": 4.034268060743087e-05, + "loss": 4.1046, + "step": 589824 + }, + { + "epoch": 0.02, + "learning_rate": 4.0334311038724084e-05, + "loss": 4.1063, + "step": 590336 + }, + { + "epoch": 0.02, + "learning_rate": 4.0325925091213564e-05, + "loss": 4.0988, + "step": 590848 + }, + { + "epoch": 0.02, + "learning_rate": 4.0317539143703044e-05, + "loss": 4.0794, + "step": 591360 + }, + { + "epoch": 0.02, + "learning_rate": 4.030915319619252e-05, + "loss": 4.0974, + "step": 591872 + }, + { + "epoch": 0.02, + "learning_rate": 4.0300767248682e-05, + "loss": 4.1102, + "step": 592384 + }, + { + "epoch": 0.02, + "learning_rate": 4.029238130117148e-05, + "loss": 4.1022, + "step": 592896 + }, + { + "epoch": 0.02, + "learning_rate": 4.028399535366096e-05, + "loss": 4.1129, + "step": 593408 + }, + { + "epoch": 0.02, + "learning_rate": 4.027560940615044e-05, + "loss": 4.1044, + "step": 593920 + }, + { + "epoch": 0.02, + "learning_rate": 4.026722345863992e-05, + "loss": 4.0989, + "step": 594432 + }, + { + "epoch": 0.02, + "learning_rate": 4.0258853889933126e-05, + "loss": 4.1077, + "step": 594944 + }, + { + "epoch": 0.02, + "learning_rate": 4.025050070003008e-05, + "loss": 4.1017, + "step": 595456 + }, + { + "epoch": 0.02, + "learning_rate": 4.024211475251956e-05, + "loss": 4.0945, + "step": 595968 + }, + { + "epoch": 0.02, + "learning_rate": 4.023372880500904e-05, + "loss": 4.1012, + "step": 596480 + }, + { + "epoch": 0.02, + "learning_rate": 4.022534285749852e-05, + "loss": 4.0969, + "step": 596992 + }, + { + "epoch": 0.02, + "learning_rate": 4.021695690998799e-05, + "loss": 4.0971, + "step": 597504 + }, + { + "epoch": 0.02, + "learning_rate": 4.020857096247747e-05, + "loss": 4.0983, + "step": 598016 + }, + { + "epoch": 0.02, + "learning_rate": 4.020018501496695e-05, + "loss": 4.1053, + "step": 598528 + }, + { + "epoch": 0.02, + "learning_rate": 4.019179906745643e-05, + "loss": 4.0962, + "step": 599040 + }, + { + "epoch": 0.02, + "learning_rate": 4.018341311994591e-05, + "loss": 4.0904, + "step": 599552 + }, + { + "epoch": 0.02, + "learning_rate": 4.017502717243539e-05, + "loss": 4.1099, + "step": 600064 + }, + { + "epoch": 0.02, + "learning_rate": 4.016664122492487e-05, + "loss": 4.0902, + "step": 600576 + }, + { + "epoch": 0.02, + "learning_rate": 4.015825527741435e-05, + "loss": 4.1067, + "step": 601088 + }, + { + "epoch": 0.02, + "learning_rate": 4.014988570870756e-05, + "loss": 4.1129, + "step": 601600 + }, + { + "epoch": 0.02, + "learning_rate": 4.0141499761197047e-05, + "loss": 4.103, + "step": 602112 + }, + { + "epoch": 0.02, + "learning_rate": 4.0133113813686527e-05, + "loss": 4.1006, + "step": 602624 + }, + { + "epoch": 0.02, + "learning_rate": 4.0124727866176006e-05, + "loss": 4.0989, + "step": 603136 + }, + { + "epoch": 0.02, + "learning_rate": 4.0116358297469216e-05, + "loss": 4.0993, + "step": 603648 + }, + { + "epoch": 0.02, + "learning_rate": 4.0107972349958696e-05, + "loss": 4.095, + "step": 604160 + }, + { + "epoch": 0.02, + "learning_rate": 4.0099586402448175e-05, + "loss": 4.1138, + "step": 604672 + }, + { + "epoch": 0.02, + "learning_rate": 4.0091200454937655e-05, + "loss": 4.1066, + "step": 605184 + }, + { + "epoch": 0.02, + "learning_rate": 4.0082830886230865e-05, + "loss": 4.1079, + "step": 605696 + }, + { + "epoch": 0.02, + "learning_rate": 4.0074444938720344e-05, + "loss": 4.101, + "step": 606208 + }, + { + "epoch": 0.02, + "learning_rate": 4.0066058991209824e-05, + "loss": 4.097, + "step": 606720 + }, + { + "epoch": 0.02, + "learning_rate": 4.0057673043699304e-05, + "loss": 4.1012, + "step": 607232 + }, + { + "epoch": 0.02, + "learning_rate": 4.0049287096188784e-05, + "loss": 4.0914, + "step": 607744 + }, + { + "epoch": 0.02, + "learning_rate": 4.004093390628573e-05, + "loss": 4.0913, + "step": 608256 + }, + { + "epoch": 0.02, + "learning_rate": 4.003254795877521e-05, + "loss": 4.1022, + "step": 608768 + }, + { + "epoch": 0.02, + "learning_rate": 4.002416201126469e-05, + "loss": 4.0949, + "step": 609280 + }, + { + "epoch": 0.02, + "learning_rate": 4.001577606375417e-05, + "loss": 4.0826, + "step": 609792 + }, + { + "epoch": 0.02, + "learning_rate": 4.000739011624365e-05, + "loss": 4.1017, + "step": 610304 + }, + { + "epoch": 0.03, + "eval_loss": 4.110222339630127, + "eval_runtime": 528.7786, + "eval_samples_per_second": 721.646, + "eval_steps_per_second": 22.552, + "step": 610552 + }, + { + "epoch": 1.0, + "learning_rate": 3.999902054753686e-05, + "loss": 4.0969, + "step": 610816 + }, + { + "epoch": 1.0, + "learning_rate": 3.999063460002634e-05, + "loss": 4.1058, + "step": 611328 + }, + { + "epoch": 1.0, + "learning_rate": 3.998224865251582e-05, + "loss": 4.1019, + "step": 611840 + }, + { + "epoch": 1.0, + "learning_rate": 3.99738627050053e-05, + "loss": 4.0946, + "step": 612352 + }, + { + "epoch": 1.0, + "learning_rate": 3.996547675749478e-05, + "loss": 4.0933, + "step": 612864 + }, + { + "epoch": 1.0, + "learning_rate": 3.995710718878799e-05, + "loss": 4.0908, + "step": 613376 + }, + { + "epoch": 1.0, + "learning_rate": 3.994872124127747e-05, + "loss": 4.0915, + "step": 613888 + }, + { + "epoch": 1.0, + "learning_rate": 3.9940335293766954e-05, + "loss": 4.0893, + "step": 614400 + }, + { + "epoch": 1.0, + "learning_rate": 3.9931949346256434e-05, + "loss": 4.09, + "step": 614912 + }, + { + "epoch": 1.0, + "learning_rate": 3.9923563398745914e-05, + "loss": 4.0954, + "step": 615424 + }, + { + "epoch": 1.0, + "learning_rate": 3.991519383003912e-05, + "loss": 4.1054, + "step": 615936 + }, + { + "epoch": 1.0, + "learning_rate": 3.99068078825286e-05, + "loss": 4.0879, + "step": 616448 + }, + { + "epoch": 1.0, + "learning_rate": 3.989842193501808e-05, + "loss": 4.0988, + "step": 616960 + }, + { + "epoch": 1.0, + "learning_rate": 3.989003598750756e-05, + "loss": 4.0835, + "step": 617472 + }, + { + "epoch": 1.0, + "learning_rate": 3.988165003999704e-05, + "loss": 4.1057, + "step": 617984 + }, + { + "epoch": 1.0, + "learning_rate": 3.987326409248652e-05, + "loss": 4.0811, + "step": 618496 + }, + { + "epoch": 1.0, + "learning_rate": 3.9864878144975996e-05, + "loss": 4.0881, + "step": 619008 + }, + { + "epoch": 1.0, + "learning_rate": 3.9856492197465476e-05, + "loss": 4.0904, + "step": 619520 + }, + { + "epoch": 1.0, + "learning_rate": 3.984813900756242e-05, + "loss": 4.0905, + "step": 620032 + }, + { + "epoch": 1.0, + "learning_rate": 3.983975306005191e-05, + "loss": 4.0971, + "step": 620544 + }, + { + "epoch": 1.0, + "learning_rate": 3.983138349134512e-05, + "loss": 4.0925, + "step": 621056 + }, + { + "epoch": 1.0, + "learning_rate": 3.9822997543834597e-05, + "loss": 4.1076, + "step": 621568 + }, + { + "epoch": 1.0, + "learning_rate": 3.9814611596324077e-05, + "loss": 4.0938, + "step": 622080 + }, + { + "epoch": 1.0, + "learning_rate": 3.9806225648813557e-05, + "loss": 4.0957, + "step": 622592 + }, + { + "epoch": 1.0, + "learning_rate": 3.9797839701303036e-05, + "loss": 4.0866, + "step": 623104 + }, + { + "epoch": 1.0, + "learning_rate": 3.9789453753792516e-05, + "loss": 4.0952, + "step": 623616 + }, + { + "epoch": 1.0, + "learning_rate": 3.9781067806281996e-05, + "loss": 4.0953, + "step": 624128 + }, + { + "epoch": 1.0, + "learning_rate": 3.977268185877147e-05, + "loss": 4.089, + "step": 624640 + }, + { + "epoch": 1.0, + "learning_rate": 3.976429591126095e-05, + "loss": 4.0945, + "step": 625152 + }, + { + "epoch": 1.0, + "learning_rate": 3.975590996375043e-05, + "loss": 4.0905, + "step": 625664 + }, + { + "epoch": 1.01, + "learning_rate": 3.974752401623991e-05, + "loss": 4.0805, + "step": 626176 + }, + { + "epoch": 1.01, + "learning_rate": 3.973913806872939e-05, + "loss": 4.0967, + "step": 626688 + }, + { + "epoch": 1.01, + "learning_rate": 3.9730768500022605e-05, + "loss": 4.0999, + "step": 627200 + }, + { + "epoch": 1.01, + "learning_rate": 3.9722382552512085e-05, + "loss": 4.093, + "step": 627712 + }, + { + "epoch": 1.01, + "learning_rate": 3.9713996605001565e-05, + "loss": 4.0822, + "step": 628224 + }, + { + "epoch": 1.01, + "learning_rate": 3.9705610657491045e-05, + "loss": 4.0973, + "step": 628736 + }, + { + "epoch": 1.01, + "learning_rate": 3.9697241088784254e-05, + "loss": 4.0893, + "step": 629248 + }, + { + "epoch": 1.01, + "learning_rate": 3.9688855141273734e-05, + "loss": 4.0926, + "step": 629760 + }, + { + "epoch": 1.01, + "learning_rate": 3.9680469193763214e-05, + "loss": 4.0931, + "step": 630272 + }, + { + "epoch": 1.01, + "learning_rate": 3.9672083246252694e-05, + "loss": 4.0834, + "step": 630784 + }, + { + "epoch": 1.01, + "learning_rate": 3.9663697298742174e-05, + "loss": 4.0781, + "step": 631296 + }, + { + "epoch": 1.01, + "learning_rate": 3.9655311351231654e-05, + "loss": 4.0748, + "step": 631808 + }, + { + "epoch": 1.01, + "learning_rate": 3.9646925403721134e-05, + "loss": 4.0956, + "step": 632320 + }, + { + "epoch": 1.01, + "learning_rate": 3.9638539456210614e-05, + "loss": 4.0861, + "step": 632832 + }, + { + "epoch": 1.01, + "learning_rate": 3.963016988750382e-05, + "loss": 4.081, + "step": 633344 + }, + { + "epoch": 1.01, + "learning_rate": 3.962180031879704e-05, + "loss": 4.0943, + "step": 633856 + }, + { + "epoch": 1.01, + "learning_rate": 3.961341437128652e-05, + "loss": 4.0767, + "step": 634368 + }, + { + "epoch": 1.01, + "learning_rate": 3.9605028423776e-05, + "loss": 4.0982, + "step": 634880 + }, + { + "epoch": 1.01, + "learning_rate": 3.959664247626548e-05, + "loss": 4.0835, + "step": 635392 + }, + { + "epoch": 1.01, + "learning_rate": 3.958825652875496e-05, + "loss": 4.0893, + "step": 635904 + }, + { + "epoch": 1.01, + "learning_rate": 3.957987058124444e-05, + "loss": 4.0832, + "step": 636416 + }, + { + "epoch": 1.01, + "learning_rate": 3.957148463373392e-05, + "loss": 4.0838, + "step": 636928 + }, + { + "epoch": 1.01, + "learning_rate": 3.95630986862234e-05, + "loss": 4.0898, + "step": 637440 + }, + { + "epoch": 1.01, + "learning_rate": 3.955472911751661e-05, + "loss": 4.0737, + "step": 637952 + }, + { + "epoch": 1.01, + "learning_rate": 3.954635954880982e-05, + "loss": 4.0889, + "step": 638464 + }, + { + "epoch": 1.01, + "learning_rate": 3.95379736012993e-05, + "loss": 4.0834, + "step": 638976 + }, + { + "epoch": 1.01, + "learning_rate": 3.952958765378878e-05, + "loss": 4.0829, + "step": 639488 + }, + { + "epoch": 1.01, + "learning_rate": 3.9521201706278263e-05, + "loss": 4.0827, + "step": 640000 + }, + { + "epoch": 1.01, + "learning_rate": 3.951281575876774e-05, + "loss": 4.093, + "step": 640512 + }, + { + "epoch": 1.01, + "learning_rate": 3.950442981125722e-05, + "loss": 4.0688, + "step": 641024 + }, + { + "epoch": 1.01, + "learning_rate": 3.94960438637467e-05, + "loss": 4.0794, + "step": 641536 + }, + { + "epoch": 1.01, + "learning_rate": 3.948765791623618e-05, + "loss": 4.0752, + "step": 642048 + }, + { + "epoch": 1.01, + "learning_rate": 3.947928834752939e-05, + "loss": 4.0805, + "step": 642560 + }, + { + "epoch": 1.01, + "learning_rate": 3.947090240001887e-05, + "loss": 4.0895, + "step": 643072 + }, + { + "epoch": 1.01, + "learning_rate": 3.946251645250835e-05, + "loss": 4.0782, + "step": 643584 + }, + { + "epoch": 1.01, + "learning_rate": 3.945413050499783e-05, + "loss": 4.0868, + "step": 644096 + }, + { + "epoch": 1.01, + "learning_rate": 3.9445744557487305e-05, + "loss": 4.06, + "step": 644608 + }, + { + "epoch": 1.01, + "learning_rate": 3.943737498878052e-05, + "loss": 4.0859, + "step": 645120 + }, + { + "epoch": 1.01, + "learning_rate": 3.942898904127e-05, + "loss": 4.0734, + "step": 645632 + }, + { + "epoch": 1.01, + "learning_rate": 3.942060309375948e-05, + "loss": 4.0781, + "step": 646144 + }, + { + "epoch": 1.01, + "learning_rate": 3.941221714624896e-05, + "loss": 4.0796, + "step": 646656 + }, + { + "epoch": 1.01, + "learning_rate": 3.940384757754218e-05, + "loss": 4.0816, + "step": 647168 + }, + { + "epoch": 1.01, + "learning_rate": 3.939546163003166e-05, + "loss": 4.0809, + "step": 647680 + }, + { + "epoch": 1.01, + "learning_rate": 3.9387092061324866e-05, + "loss": 4.0954, + "step": 648192 + }, + { + "epoch": 1.01, + "learning_rate": 3.9378706113814346e-05, + "loss": 4.0814, + "step": 648704 + }, + { + "epoch": 1.01, + "learning_rate": 3.9370320166303826e-05, + "loss": 4.0898, + "step": 649216 + }, + { + "epoch": 1.01, + "learning_rate": 3.9361934218793306e-05, + "loss": 4.0847, + "step": 649728 + }, + { + "epoch": 1.01, + "learning_rate": 3.935354827128278e-05, + "loss": 4.0711, + "step": 650240 + }, + { + "epoch": 1.01, + "learning_rate": 3.9345178702575995e-05, + "loss": 4.0727, + "step": 650752 + }, + { + "epoch": 1.01, + "learning_rate": 3.9336792755065475e-05, + "loss": 4.0844, + "step": 651264 + }, + { + "epoch": 1.01, + "learning_rate": 3.9328406807554955e-05, + "loss": 4.089, + "step": 651776 + }, + { + "epoch": 1.01, + "learning_rate": 3.9320020860044435e-05, + "loss": 4.0829, + "step": 652288 + }, + { + "epoch": 1.01, + "learning_rate": 3.9311634912533915e-05, + "loss": 4.0619, + "step": 652800 + }, + { + "epoch": 1.01, + "learning_rate": 3.9303248965023395e-05, + "loss": 4.0702, + "step": 653312 + }, + { + "epoch": 1.01, + "learning_rate": 3.9294863017512875e-05, + "loss": 4.0727, + "step": 653824 + }, + { + "epoch": 1.01, + "learning_rate": 3.9286477070002355e-05, + "loss": 4.08, + "step": 654336 + }, + { + "epoch": 1.01, + "learning_rate": 3.9278107501295564e-05, + "loss": 4.0821, + "step": 654848 + }, + { + "epoch": 1.01, + "learning_rate": 3.926973793258878e-05, + "loss": 4.0838, + "step": 655360 + }, + { + "epoch": 1.01, + "learning_rate": 3.926135198507825e-05, + "loss": 4.0771, + "step": 655872 + }, + { + "epoch": 1.02, + "learning_rate": 3.925296603756773e-05, + "loss": 4.0761, + "step": 656384 + }, + { + "epoch": 1.02, + "learning_rate": 3.924458009005721e-05, + "loss": 4.0727, + "step": 656896 + }, + { + "epoch": 1.02, + "learning_rate": 3.923619414254669e-05, + "loss": 4.0738, + "step": 657408 + }, + { + "epoch": 1.02, + "learning_rate": 3.922784095264364e-05, + "loss": 4.0645, + "step": 657920 + }, + { + "epoch": 1.02, + "learning_rate": 3.9219455005133124e-05, + "loss": 4.0804, + "step": 658432 + }, + { + "epoch": 1.02, + "learning_rate": 3.9211069057622604e-05, + "loss": 4.0714, + "step": 658944 + }, + { + "epoch": 1.02, + "learning_rate": 3.920268311011208e-05, + "loss": 4.0787, + "step": 659456 + }, + { + "epoch": 1.02, + "learning_rate": 3.919429716260156e-05, + "loss": 4.0732, + "step": 659968 + }, + { + "epoch": 1.02, + "learning_rate": 3.918591121509104e-05, + "loss": 4.0928, + "step": 660480 + }, + { + "epoch": 1.02, + "learning_rate": 3.917752526758052e-05, + "loss": 4.0693, + "step": 660992 + }, + { + "epoch": 1.02, + "learning_rate": 3.916913932007e-05, + "loss": 4.0851, + "step": 661504 + }, + { + "epoch": 1.02, + "learning_rate": 3.9160769751363206e-05, + "loss": 4.083, + "step": 662016 + }, + { + "epoch": 1.02, + "learning_rate": 3.9152383803852686e-05, + "loss": 4.0737, + "step": 662528 + }, + { + "epoch": 1.02, + "learning_rate": 3.9143997856342166e-05, + "loss": 4.0803, + "step": 663040 + }, + { + "epoch": 1.02, + "learning_rate": 3.9135611908831646e-05, + "loss": 4.0816, + "step": 663552 + }, + { + "epoch": 1.02, + "learning_rate": 3.912724234012486e-05, + "loss": 4.0823, + "step": 664064 + }, + { + "epoch": 1.02, + "learning_rate": 3.911885639261434e-05, + "loss": 4.0725, + "step": 664576 + }, + { + "epoch": 1.02, + "learning_rate": 3.911047044510382e-05, + "loss": 4.0643, + "step": 665088 + }, + { + "epoch": 1.02, + "learning_rate": 3.91020844975933e-05, + "loss": 4.0684, + "step": 665600 + }, + { + "epoch": 1.02, + "learning_rate": 3.909369855008278e-05, + "loss": 4.0765, + "step": 666112 + }, + { + "epoch": 1.02, + "learning_rate": 3.908531260257226e-05, + "loss": 4.0758, + "step": 666624 + }, + { + "epoch": 1.02, + "learning_rate": 3.907692665506174e-05, + "loss": 4.0754, + "step": 667136 + }, + { + "epoch": 1.02, + "learning_rate": 3.906854070755122e-05, + "loss": 4.0503, + "step": 667648 + }, + { + "epoch": 1.02, + "learning_rate": 3.90601547600407e-05, + "loss": 4.0726, + "step": 668160 + }, + { + "epoch": 1.02, + "learning_rate": 3.905176881253018e-05, + "loss": 4.0792, + "step": 668672 + }, + { + "epoch": 1.02, + "learning_rate": 3.904338286501966e-05, + "loss": 4.0762, + "step": 669184 + }, + { + "epoch": 1.02, + "learning_rate": 3.903499691750914e-05, + "loss": 4.0836, + "step": 669696 + }, + { + "epoch": 1.02, + "learning_rate": 3.902662734880235e-05, + "loss": 4.0784, + "step": 670208 + }, + { + "epoch": 1.02, + "learning_rate": 3.901824140129183e-05, + "loss": 4.0685, + "step": 670720 + }, + { + "epoch": 1.02, + "learning_rate": 3.900985545378131e-05, + "loss": 4.0812, + "step": 671232 + }, + { + "epoch": 1.02, + "learning_rate": 3.900146950627079e-05, + "loss": 4.0773, + "step": 671744 + }, + { + "epoch": 1.02, + "learning_rate": 3.8993099937564007e-05, + "loss": 4.0652, + "step": 672256 + }, + { + "epoch": 1.02, + "learning_rate": 3.8984713990053487e-05, + "loss": 4.0736, + "step": 672768 + }, + { + "epoch": 1.02, + "learning_rate": 3.8976328042542966e-05, + "loss": 4.0719, + "step": 673280 + }, + { + "epoch": 1.02, + "learning_rate": 3.896794209503244e-05, + "loss": 4.0705, + "step": 673792 + }, + { + "epoch": 1.02, + "learning_rate": 3.8959572526325656e-05, + "loss": 4.0714, + "step": 674304 + }, + { + "epoch": 1.02, + "learning_rate": 3.8951186578815135e-05, + "loss": 4.0745, + "step": 674816 + }, + { + "epoch": 1.02, + "learning_rate": 3.8942800631304615e-05, + "loss": 4.0735, + "step": 675328 + }, + { + "epoch": 1.02, + "learning_rate": 3.893441468379409e-05, + "loss": 4.0626, + "step": 675840 + }, + { + "epoch": 1.02, + "learning_rate": 3.892602873628357e-05, + "loss": 4.0788, + "step": 676352 + }, + { + "epoch": 1.02, + "learning_rate": 3.891764278877305e-05, + "loss": 4.0647, + "step": 676864 + }, + { + "epoch": 1.02, + "learning_rate": 3.890925684126253e-05, + "loss": 4.0798, + "step": 677376 + }, + { + "epoch": 1.02, + "learning_rate": 3.890087089375201e-05, + "loss": 4.0889, + "step": 677888 + }, + { + "epoch": 1.02, + "learning_rate": 3.889251770384896e-05, + "loss": 4.0731, + "step": 678400 + }, + { + "epoch": 1.02, + "learning_rate": 3.888413175633844e-05, + "loss": 4.075, + "step": 678912 + }, + { + "epoch": 1.02, + "learning_rate": 3.887574580882791e-05, + "loss": 4.0692, + "step": 679424 + }, + { + "epoch": 1.02, + "learning_rate": 3.886735986131739e-05, + "loss": 4.0734, + "step": 679936 + }, + { + "epoch": 1.02, + "learning_rate": 3.885897391380687e-05, + "loss": 4.0676, + "step": 680448 + }, + { + "epoch": 1.02, + "learning_rate": 3.885058796629635e-05, + "loss": 4.0836, + "step": 680960 + }, + { + "epoch": 1.02, + "learning_rate": 3.884221839758956e-05, + "loss": 4.0842, + "step": 681472 + }, + { + "epoch": 1.02, + "learning_rate": 3.883383245007904e-05, + "loss": 4.0757, + "step": 681984 + }, + { + "epoch": 1.02, + "learning_rate": 3.882544650256852e-05, + "loss": 4.0738, + "step": 682496 + }, + { + "epoch": 1.02, + "learning_rate": 3.8817060555058e-05, + "loss": 4.0758, + "step": 683008 + }, + { + "epoch": 1.02, + "learning_rate": 3.880867460754748e-05, + "loss": 4.0706, + "step": 683520 + }, + { + "epoch": 1.02, + "learning_rate": 3.880028866003696e-05, + "loss": 4.0686, + "step": 684032 + }, + { + "epoch": 1.02, + "learning_rate": 3.879191909133018e-05, + "loss": 4.0647, + "step": 684544 + }, + { + "epoch": 1.02, + "learning_rate": 3.878354952262339e-05, + "loss": 4.0733, + "step": 685056 + }, + { + "epoch": 1.02, + "learning_rate": 3.877516357511287e-05, + "loss": 4.0687, + "step": 685568 + }, + { + "epoch": 1.02, + "learning_rate": 3.876677762760235e-05, + "loss": 4.058, + "step": 686080 + }, + { + "epoch": 1.02, + "learning_rate": 3.875839168009183e-05, + "loss": 4.0701, + "step": 686592 + }, + { + "epoch": 1.03, + "eval_loss": 4.090645790100098, + "eval_runtime": 524.3925, + "eval_samples_per_second": 727.682, + "eval_steps_per_second": 22.741, + "step": 686871 + }, + { + "epoch": 0.0, + "learning_rate": 3.875000573258131e-05, + "loss": 4.0753, + "step": 687104 + }, + { + "epoch": 0.0, + "learning_rate": 3.874161978507079e-05, + "loss": 4.0798, + "step": 687616 + }, + { + "epoch": 0.0, + "learning_rate": 3.873323383756027e-05, + "loss": 4.0775, + "step": 688128 + }, + { + "epoch": 0.0, + "learning_rate": 3.872484789004975e-05, + "loss": 4.0634, + "step": 688640 + }, + { + "epoch": 0.0, + "learning_rate": 3.871646194253923e-05, + "loss": 4.0718, + "step": 689152 + }, + { + "epoch": 0.0, + "learning_rate": 3.870807599502871e-05, + "loss": 4.065, + "step": 689664 + }, + { + "epoch": 0.0, + "learning_rate": 3.869969004751819e-05, + "loss": 4.0632, + "step": 690176 + }, + { + "epoch": 0.0, + "learning_rate": 3.8691304100007667e-05, + "loss": 4.0661, + "step": 690688 + }, + { + "epoch": 0.0, + "learning_rate": 3.8682918152497147e-05, + "loss": 4.0613, + "step": 691200 + }, + { + "epoch": 0.0, + "learning_rate": 3.8674532204986626e-05, + "loss": 4.0712, + "step": 691712 + }, + { + "epoch": 0.0, + "learning_rate": 3.8666146257476106e-05, + "loss": 4.0744, + "step": 692224 + }, + { + "epoch": 0.0, + "learning_rate": 3.8657760309965586e-05, + "loss": 4.0611, + "step": 692736 + }, + { + "epoch": 0.0, + "learning_rate": 3.8649374362455066e-05, + "loss": 4.0731, + "step": 693248 + }, + { + "epoch": 0.0, + "learning_rate": 3.8640988414944546e-05, + "loss": 4.0569, + "step": 693760 + }, + { + "epoch": 0.0, + "learning_rate": 3.8632602467434026e-05, + "loss": 4.0745, + "step": 694272 + }, + { + "epoch": 0.0, + "learning_rate": 3.8624216519923506e-05, + "loss": 4.0541, + "step": 694784 + }, + { + "epoch": 0.0, + "learning_rate": 3.8615830572412986e-05, + "loss": 4.0622, + "step": 695296 + }, + { + "epoch": 0.0, + "learning_rate": 3.8607444624902466e-05, + "loss": 4.066, + "step": 695808 + }, + { + "epoch": 0.0, + "learning_rate": 3.8599075056195675e-05, + "loss": 4.0637, + "step": 696320 + }, + { + "epoch": 0.0, + "learning_rate": 3.8590689108685155e-05, + "loss": 4.0741, + "step": 696832 + }, + { + "epoch": 0.0, + "learning_rate": 3.8582303161174635e-05, + "loss": 4.0596, + "step": 697344 + }, + { + "epoch": 0.0, + "learning_rate": 3.8573917213664115e-05, + "loss": 4.0854, + "step": 697856 + }, + { + "epoch": 0.0, + "learning_rate": 3.8565531266153595e-05, + "loss": 4.0647, + "step": 698368 + }, + { + "epoch": 0.0, + "learning_rate": 3.855714531864308e-05, + "loss": 4.0681, + "step": 698880 + }, + { + "epoch": 0.0, + "learning_rate": 3.854875937113256e-05, + "loss": 4.0629, + "step": 699392 + }, + { + "epoch": 0.0, + "learning_rate": 3.854038980242577e-05, + "loss": 4.0718, + "step": 699904 + }, + { + "epoch": 0.0, + "learning_rate": 3.853200385491525e-05, + "loss": 4.0682, + "step": 700416 + }, + { + "epoch": 0.0, + "learning_rate": 3.852361790740473e-05, + "loss": 4.0612, + "step": 700928 + }, + { + "epoch": 0.0, + "learning_rate": 3.851523195989421e-05, + "loss": 4.0691, + "step": 701440 + }, + { + "epoch": 0.0, + "learning_rate": 3.850687876999115e-05, + "loss": 4.0681, + "step": 701952 + }, + { + "epoch": 0.01, + "learning_rate": 3.849849282248063e-05, + "loss": 4.0497, + "step": 702464 + }, + { + "epoch": 0.01, + "learning_rate": 3.849010687497011e-05, + "loss": 4.0718, + "step": 702976 + }, + { + "epoch": 0.01, + "learning_rate": 3.848172092745959e-05, + "loss": 4.0726, + "step": 703488 + }, + { + "epoch": 0.01, + "learning_rate": 3.847333497994907e-05, + "loss": 4.0679, + "step": 704000 + }, + { + "epoch": 0.01, + "learning_rate": 3.846494903243855e-05, + "loss": 4.0569, + "step": 704512 + }, + { + "epoch": 0.01, + "learning_rate": 3.8456563084928035e-05, + "loss": 4.0719, + "step": 705024 + }, + { + "epoch": 0.01, + "learning_rate": 3.8448193516221245e-05, + "loss": 4.0644, + "step": 705536 + }, + { + "epoch": 0.01, + "learning_rate": 3.8439807568710724e-05, + "loss": 4.067, + "step": 706048 + }, + { + "epoch": 0.01, + "learning_rate": 3.8431421621200204e-05, + "loss": 4.0649, + "step": 706560 + }, + { + "epoch": 0.01, + "learning_rate": 3.8423035673689684e-05, + "loss": 4.056, + "step": 707072 + }, + { + "epoch": 0.01, + "learning_rate": 3.8414649726179164e-05, + "loss": 4.0544, + "step": 707584 + }, + { + "epoch": 0.01, + "learning_rate": 3.840626377866864e-05, + "loss": 4.0484, + "step": 708096 + }, + { + "epoch": 0.01, + "learning_rate": 3.839787783115812e-05, + "loss": 4.0706, + "step": 708608 + }, + { + "epoch": 0.01, + "learning_rate": 3.83894918836476e-05, + "loss": 4.0604, + "step": 709120 + }, + { + "epoch": 0.01, + "learning_rate": 3.838110593613708e-05, + "loss": 4.0537, + "step": 709632 + }, + { + "epoch": 0.01, + "learning_rate": 3.8372736367430287e-05, + "loss": 4.0664, + "step": 710144 + }, + { + "epoch": 0.01, + "learning_rate": 3.836435041991977e-05, + "loss": 4.0527, + "step": 710656 + }, + { + "epoch": 0.01, + "learning_rate": 3.835596447240925e-05, + "loss": 4.0701, + "step": 711168 + }, + { + "epoch": 0.01, + "learning_rate": 3.834757852489873e-05, + "loss": 4.0635, + "step": 711680 + }, + { + "epoch": 0.01, + "learning_rate": 3.833919257738821e-05, + "loss": 4.0635, + "step": 712192 + }, + { + "epoch": 0.01, + "learning_rate": 3.833080662987769e-05, + "loss": 4.059, + "step": 712704 + }, + { + "epoch": 0.01, + "learning_rate": 3.832242068236717e-05, + "loss": 4.0552, + "step": 713216 + }, + { + "epoch": 0.01, + "learning_rate": 3.831405111366038e-05, + "loss": 4.0652, + "step": 713728 + }, + { + "epoch": 0.01, + "learning_rate": 3.830566516614986e-05, + "loss": 4.0461, + "step": 714240 + }, + { + "epoch": 0.01, + "learning_rate": 3.829727921863934e-05, + "loss": 4.064, + "step": 714752 + }, + { + "epoch": 0.01, + "learning_rate": 3.828889327112882e-05, + "loss": 4.0533, + "step": 715264 + }, + { + "epoch": 0.01, + "learning_rate": 3.82805073236183e-05, + "loss": 4.0571, + "step": 715776 + }, + { + "epoch": 0.01, + "learning_rate": 3.827213775491151e-05, + "loss": 4.054, + "step": 716288 + }, + { + "epoch": 0.01, + "learning_rate": 3.826375180740099e-05, + "loss": 4.0669, + "step": 716800 + }, + { + "epoch": 0.01, + "learning_rate": 3.825536585989047e-05, + "loss": 4.0506, + "step": 717312 + }, + { + "epoch": 0.01, + "learning_rate": 3.824697991237996e-05, + "loss": 4.0495, + "step": 717824 + }, + { + "epoch": 0.01, + "learning_rate": 3.823859396486944e-05, + "loss": 4.0563, + "step": 718336 + }, + { + "epoch": 0.01, + "learning_rate": 3.823020801735892e-05, + "loss": 4.0487, + "step": 718848 + }, + { + "epoch": 0.01, + "learning_rate": 3.82218220698484e-05, + "loss": 4.0603, + "step": 719360 + }, + { + "epoch": 0.01, + "learning_rate": 3.821345250114161e-05, + "loss": 4.0586, + "step": 719872 + }, + { + "epoch": 0.01, + "learning_rate": 3.8205066553631087e-05, + "loss": 4.0603, + "step": 720384 + }, + { + "epoch": 0.01, + "learning_rate": 3.8196680606120567e-05, + "loss": 4.0364, + "step": 720896 + }, + { + "epoch": 0.01, + "learning_rate": 3.8188294658610047e-05, + "loss": 4.0575, + "step": 721408 + }, + { + "epoch": 0.01, + "learning_rate": 3.817990871109952e-05, + "loss": 4.0492, + "step": 721920 + }, + { + "epoch": 0.01, + "learning_rate": 3.8171522763589e-05, + "loss": 4.0506, + "step": 722432 + }, + { + "epoch": 0.01, + "learning_rate": 3.816313681607848e-05, + "loss": 4.0549, + "step": 722944 + }, + { + "epoch": 0.01, + "learning_rate": 3.8154767247371695e-05, + "loss": 4.0554, + "step": 723456 + }, + { + "epoch": 0.01, + "learning_rate": 3.8146381299861175e-05, + "loss": 4.0567, + "step": 723968 + }, + { + "epoch": 0.01, + "learning_rate": 3.8137995352350655e-05, + "loss": 4.0706, + "step": 724480 + }, + { + "epoch": 0.01, + "learning_rate": 3.8129609404840135e-05, + "loss": 4.0557, + "step": 724992 + }, + { + "epoch": 0.01, + "learning_rate": 3.8121223457329615e-05, + "loss": 4.0624, + "step": 725504 + }, + { + "epoch": 0.01, + "learning_rate": 3.8112837509819095e-05, + "loss": 4.0569, + "step": 726016 + }, + { + "epoch": 0.01, + "learning_rate": 3.8104467941112304e-05, + "loss": 4.0497, + "step": 726528 + }, + { + "epoch": 0.01, + "learning_rate": 3.8096081993601784e-05, + "loss": 4.0488, + "step": 727040 + }, + { + "epoch": 0.01, + "learning_rate": 3.8087712424894993e-05, + "loss": 4.0562, + "step": 727552 + }, + { + "epoch": 0.01, + "learning_rate": 3.807932647738447e-05, + "loss": 4.06, + "step": 728064 + }, + { + "epoch": 0.01, + "learning_rate": 3.807094052987395e-05, + "loss": 4.0627, + "step": 728576 + }, + { + "epoch": 0.01, + "learning_rate": 3.806255458236343e-05, + "loss": 4.0354, + "step": 729088 + }, + { + "epoch": 0.01, + "learning_rate": 3.805416863485291e-05, + "loss": 4.0427, + "step": 729600 + }, + { + "epoch": 0.01, + "learning_rate": 3.804578268734239e-05, + "loss": 4.0479, + "step": 730112 + }, + { + "epoch": 0.01, + "learning_rate": 3.803739673983187e-05, + "loss": 4.055, + "step": 730624 + }, + { + "epoch": 0.01, + "learning_rate": 3.802901079232136e-05, + "loss": 4.0522, + "step": 731136 + }, + { + "epoch": 0.01, + "learning_rate": 3.802064122361457e-05, + "loss": 4.0637, + "step": 731648 + }, + { + "epoch": 0.01, + "learning_rate": 3.801225527610405e-05, + "loss": 4.0514, + "step": 732160 + }, + { + "epoch": 0.02, + "learning_rate": 3.800386932859353e-05, + "loss": 4.0518, + "step": 732672 + }, + { + "epoch": 0.02, + "learning_rate": 3.799548338108301e-05, + "loss": 4.0464, + "step": 733184 + }, + { + "epoch": 0.02, + "learning_rate": 3.798711381237622e-05, + "loss": 4.0484, + "step": 733696 + }, + { + "epoch": 0.02, + "learning_rate": 3.79787278648657e-05, + "loss": 4.0402, + "step": 734208 + }, + { + "epoch": 0.02, + "learning_rate": 3.797034191735518e-05, + "loss": 4.0519, + "step": 734720 + }, + { + "epoch": 0.02, + "learning_rate": 3.796195596984466e-05, + "loss": 4.0502, + "step": 735232 + }, + { + "epoch": 0.02, + "learning_rate": 3.795357002233414e-05, + "loss": 4.0505, + "step": 735744 + }, + { + "epoch": 0.02, + "learning_rate": 3.794518407482362e-05, + "loss": 4.0525, + "step": 736256 + }, + { + "epoch": 0.02, + "learning_rate": 3.79367981273131e-05, + "loss": 4.0644, + "step": 736768 + }, + { + "epoch": 0.02, + "learning_rate": 3.792841217980258e-05, + "loss": 4.0459, + "step": 737280 + }, + { + "epoch": 0.02, + "learning_rate": 3.7920042611095793e-05, + "loss": 4.0598, + "step": 737792 + }, + { + "epoch": 0.02, + "learning_rate": 3.7911673042389e-05, + "loss": 4.0568, + "step": 738304 + }, + { + "epoch": 0.02, + "learning_rate": 3.790328709487848e-05, + "loss": 4.0522, + "step": 738816 + }, + { + "epoch": 0.02, + "learning_rate": 3.789490114736796e-05, + "loss": 4.049, + "step": 739328 + }, + { + "epoch": 0.02, + "learning_rate": 3.788651519985744e-05, + "loss": 4.0574, + "step": 739840 + }, + { + "epoch": 0.02, + "learning_rate": 3.787812925234692e-05, + "loss": 4.0573, + "step": 740352 + }, + { + "epoch": 0.02, + "learning_rate": 3.78697433048364e-05, + "loss": 4.0441, + "step": 740864 + }, + { + "epoch": 0.02, + "learning_rate": 3.786135735732588e-05, + "loss": 4.0433, + "step": 741376 + }, + { + "epoch": 0.02, + "learning_rate": 3.7852971409815355e-05, + "loss": 4.0416, + "step": 741888 + }, + { + "epoch": 0.02, + "learning_rate": 3.784460184110857e-05, + "loss": 4.0467, + "step": 742400 + }, + { + "epoch": 0.02, + "learning_rate": 3.783621589359805e-05, + "loss": 4.0547, + "step": 742912 + }, + { + "epoch": 0.02, + "learning_rate": 3.782782994608753e-05, + "loss": 4.0481, + "step": 743424 + }, + { + "epoch": 0.02, + "learning_rate": 3.781944399857701e-05, + "loss": 4.0323, + "step": 743936 + }, + { + "epoch": 0.02, + "learning_rate": 3.781107442987023e-05, + "loss": 4.0437, + "step": 744448 + }, + { + "epoch": 0.02, + "learning_rate": 3.780268848235971e-05, + "loss": 4.0526, + "step": 744960 + }, + { + "epoch": 0.02, + "learning_rate": 3.779430253484919e-05, + "loss": 4.054, + "step": 745472 + }, + { + "epoch": 0.02, + "learning_rate": 3.778591658733866e-05, + "loss": 4.0622, + "step": 745984 + }, + { + "epoch": 0.02, + "learning_rate": 3.7777547018631876e-05, + "loss": 4.0518, + "step": 746496 + }, + { + "epoch": 0.02, + "learning_rate": 3.7769161071121356e-05, + "loss": 4.046, + "step": 747008 + }, + { + "epoch": 0.02, + "learning_rate": 3.776077512361083e-05, + "loss": 4.0526, + "step": 747520 + }, + { + "epoch": 0.02, + "learning_rate": 3.775238917610031e-05, + "loss": 4.054, + "step": 748032 + }, + { + "epoch": 0.02, + "learning_rate": 3.774400322858979e-05, + "loss": 4.046, + "step": 748544 + }, + { + "epoch": 0.02, + "learning_rate": 3.773561728107927e-05, + "loss": 4.0435, + "step": 749056 + }, + { + "epoch": 0.02, + "learning_rate": 3.772723133356875e-05, + "loss": 4.0517, + "step": 749568 + }, + { + "epoch": 0.02, + "learning_rate": 3.7718845386058236e-05, + "loss": 4.0398, + "step": 750080 + }, + { + "epoch": 0.02, + "learning_rate": 3.7710475817351445e-05, + "loss": 4.0509, + "step": 750592 + }, + { + "epoch": 0.02, + "learning_rate": 3.770210624864466e-05, + "loss": 4.047, + "step": 751104 + }, + { + "epoch": 0.02, + "learning_rate": 3.7693720301134134e-05, + "loss": 4.0508, + "step": 751616 + }, + { + "epoch": 0.02, + "learning_rate": 3.7685334353623614e-05, + "loss": 4.039, + "step": 752128 + }, + { + "epoch": 0.02, + "learning_rate": 3.7676948406113094e-05, + "loss": 4.0535, + "step": 752640 + }, + { + "epoch": 0.02, + "learning_rate": 3.7668562458602574e-05, + "loss": 4.0428, + "step": 753152 + }, + { + "epoch": 0.02, + "learning_rate": 3.7660176511092054e-05, + "loss": 4.0579, + "step": 753664 + }, + { + "epoch": 0.02, + "learning_rate": 3.7651790563581534e-05, + "loss": 4.0632, + "step": 754176 + }, + { + "epoch": 0.02, + "learning_rate": 3.7643404616071014e-05, + "loss": 4.0462, + "step": 754688 + }, + { + "epoch": 0.02, + "learning_rate": 3.763503504736422e-05, + "loss": 4.0468, + "step": 755200 + }, + { + "epoch": 0.02, + "learning_rate": 3.762666547865744e-05, + "loss": 4.0504, + "step": 755712 + }, + { + "epoch": 0.02, + "learning_rate": 3.761827953114692e-05, + "loss": 4.0473, + "step": 756224 + }, + { + "epoch": 0.02, + "learning_rate": 3.76098935836364e-05, + "loss": 4.044, + "step": 756736 + }, + { + "epoch": 0.02, + "learning_rate": 3.760150763612588e-05, + "loss": 4.0583, + "step": 757248 + }, + { + "epoch": 0.02, + "learning_rate": 3.759312168861536e-05, + "loss": 4.0546, + "step": 757760 + }, + { + "epoch": 0.02, + "learning_rate": 3.758473574110484e-05, + "loss": 4.0551, + "step": 758272 + }, + { + "epoch": 0.02, + "learning_rate": 3.757634979359432e-05, + "loss": 4.0515, + "step": 758784 + }, + { + "epoch": 0.02, + "learning_rate": 3.75679638460838e-05, + "loss": 4.0556, + "step": 759296 + }, + { + "epoch": 0.02, + "learning_rate": 3.755957789857328e-05, + "loss": 4.0436, + "step": 759808 + }, + { + "epoch": 0.02, + "learning_rate": 3.755120832986649e-05, + "loss": 4.0429, + "step": 760320 + }, + { + "epoch": 0.02, + "learning_rate": 3.754282238235597e-05, + "loss": 4.0409, + "step": 760832 + }, + { + "epoch": 0.02, + "learning_rate": 3.753443643484545e-05, + "loss": 4.0499, + "step": 761344 + }, + { + "epoch": 0.02, + "learning_rate": 3.752605048733493e-05, + "loss": 4.0465, + "step": 761856 + }, + { + "epoch": 0.02, + "learning_rate": 3.751769729743187e-05, + "loss": 4.0307, + "step": 762368 + }, + { + "epoch": 0.02, + "learning_rate": 3.750931134992135e-05, + "loss": 4.05, + "step": 762880 + }, + { + "epoch": 0.03, + "eval_loss": 4.074104309082031, + "eval_runtime": 536.6879, + "eval_samples_per_second": 711.011, + "eval_steps_per_second": 22.22, + "step": 763190 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 3.090533787047635e+17, + "trial_name": null, + "trial_params": null +}