diff --git "a/checkpoint-2289591/trainer_state.json" "b/checkpoint-2289591/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2289591/trainer_state.json" @@ -0,0 +1,27091 @@ +{ + "best_metric": 3.831275463104248, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/full/transformer/0/checkpoints/checkpoint-992151", + "epoch": 1.0250006060157382, + "eval_steps": 10, + "global_step": 2289591, + "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": 10.982, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.8398, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.183, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.9655, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.8118, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.689, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.5876, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5224, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4693, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.3896, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3519, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.3107, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989938500867749e-05, + "loss": 5.2697, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 5.2083, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 5.1825, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 5.1515, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.1131, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.0791, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.0586, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0309, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.0015, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.9823927859886547e-05, + "loss": 4.9745, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.9626, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.9332, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.924, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790400448648195e-05, + "loss": 4.8959, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782014501137675e-05, + "loss": 4.8843, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.8658, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.8313, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756873037409844e-05, + "loss": 4.8339, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748487089899324e-05, + "loss": 4.8042, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 4.7936, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 4.7818, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.97233456261715e-05, + "loss": 4.7759, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.971495967866098e-05, + "loss": 4.7511, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.7411, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 4.7401, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968981821493315e-05, + "loss": 4.7212, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.968143226742263e-05, + "loss": 4.7135, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967304631991211e-05, + "loss": 4.6947, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 4.6779, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.96562908036948e-05, + "loss": 4.6717, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964790485618428e-05, + "loss": 4.6499, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963951890867376e-05, + "loss": 4.6675, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.963113296116324e-05, + "loss": 4.6405, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.9622763392456454e-05, + "loss": 4.6411, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.9614377444945934e-05, + "loss": 4.6313, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.9605991497435414e-05, + "loss": 4.6276, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.9597605549924894e-05, + "loss": 4.6183, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.9589219602414374e-05, + "loss": 4.5944, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958085003370758e-05, + "loss": 4.5865, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957246408619706e-05, + "loss": 4.5785, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956407813868654e-05, + "loss": 4.5848, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.9555692191176016e-05, + "loss": 4.5635, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.954732262246923e-05, + "loss": 4.5746, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.953893667495871e-05, + "loss": 4.5474, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.953055072744819e-05, + "loss": 4.5418, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.952216477993767e-05, + "loss": 4.5388, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951379521123089e-05, + "loss": 4.5332, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950540926372037e-05, + "loss": 4.5289, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949702331620985e-05, + "loss": 4.5126, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948863736869932e-05, + "loss": 4.5086, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.9480267799992536e-05, + "loss": 4.5181, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.9471881852482016e-05, + "loss": 4.4981, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946349590497149e-05, + "loss": 4.4936, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945510995746097e-05, + "loss": 4.4908, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.9446740388754185e-05, + "loss": 4.4893, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.9438354441243665e-05, + "loss": 4.47, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.9429968493733145e-05, + "loss": 4.4831, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.9421582546222625e-05, + "loss": 4.4693, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.941321297751584e-05, + "loss": 4.46, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.940482703000532e-05, + "loss": 4.4651, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396441082494794e-05, + "loss": 4.4522, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.938807151378801e-05, + "loss": 4.4648, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.937968556627749e-05, + "loss": 4.4649, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.937129961876696e-05, + "loss": 4.4546, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.936291367125644e-05, + "loss": 4.4386, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.935452772374592e-05, + "loss": 4.4281, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.93461417762354e-05, + "loss": 4.4171, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.933775582872488e-05, + "loss": 4.432, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.932936988121436e-05, + "loss": 4.431, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.932100031250758e-05, + "loss": 4.4292, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931261436499706e-05, + "loss": 4.4043, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930422841748654e-05, + "loss": 4.4005, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929584246997602e-05, + "loss": 4.4067, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.928747290126923e-05, + "loss": 4.3927, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927908695375871e-05, + "loss": 4.3993, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927070100624819e-05, + "loss": 4.3949, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926231505873767e-05, + "loss": 4.3965, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925394549003088e-05, + "loss": 4.3856, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924555954252036e-05, + "loss": 4.3816, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923717359500984e-05, + "loss": 4.3706, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922878764749932e-05, + "loss": 4.3849, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.922043445759626e-05, + "loss": 4.3677, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921204851008574e-05, + "loss": 4.3526, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920366256257522e-05, + "loss": 4.3604, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.91952766150647e-05, + "loss": 4.3716, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918689066755418e-05, + "loss": 4.3648, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.917850472004366e-05, + "loss": 4.3623, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.917011877253314e-05, + "loss": 4.342, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.916173282502262e-05, + "loss": 4.3582, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.915336325631583e-05, + "loss": 4.3338, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914497730880531e-05, + "loss": 4.3492, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.913659136129479e-05, + "loss": 4.3538, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.9128221792588e-05, + "loss": 4.3365, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.9119835845077486e-05, + "loss": 4.3319, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.9111449897566966e-05, + "loss": 4.3071, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.9103063950056446e-05, + "loss": 4.3209, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.9094678002545926e-05, + "loss": 4.3212, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.9086292055035406e-05, + "loss": 4.3166, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.9077922486328615e-05, + "loss": 4.3221, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.9069536538818095e-05, + "loss": 4.3058, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.9061150591307575e-05, + "loss": 4.3082, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.9052764643797055e-05, + "loss": 4.3137, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.9044378696286535e-05, + "loss": 4.3173, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.9035992748776015e-05, + "loss": 4.3033, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.9027623180069224e-05, + "loss": 4.3012, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.9019237232558704e-05, + "loss": 4.2974, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.9010851285048184e-05, + "loss": 4.2981, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.900246533753767e-05, + "loss": 4.3012, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.899409576883088e-05, + "loss": 4.2872, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.898570982132036e-05, + "loss": 4.2833, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.897732387380984e-05, + "loss": 4.2808, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.896893792629932e-05, + "loss": 4.2777, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.89605519787888e-05, + "loss": 4.2802, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.895216603127827e-05, + "loss": 4.2814, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.894378008376775e-05, + "loss": 4.2854, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.893539413625723e-05, + "loss": 4.2625, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.892702456755045e-05, + "loss": 4.2758, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.891863862003992e-05, + "loss": 4.278, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.891025267252941e-05, + "loss": 4.2657, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890186672501889e-05, + "loss": 4.2814, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.88934971563121e-05, + "loss": 4.2626, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888511120880158e-05, + "loss": 4.2754, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.887672526129106e-05, + "loss": 4.2653, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886833931378054e-05, + "loss": 4.2452, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.8859969745073747e-05, + "loss": 4.2471, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.8851583797563226e-05, + "loss": 4.2492, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884321422885644e-05, + "loss": 4.2562, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883482828134592e-05, + "loss": 4.2575, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.8826442333835395e-05, + "loss": 4.2572, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.8818056386324875e-05, + "loss": 4.247, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.880967043881436e-05, + "loss": 4.2411, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880128449130384e-05, + "loss": 4.2348, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879289854379332e-05, + "loss": 4.2305, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.87845125962828e-05, + "loss": 4.2408, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877614302757601e-05, + "loss": 4.2516, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876777345886922e-05, + "loss": 4.2423, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.87593875113587e-05, + "loss": 4.2226, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875100156384818e-05, + "loss": 4.2272, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.192169189453125, + "eval_runtime": 580.6732, + "eval_samples_per_second": 657.153, + "eval_steps_per_second": 20.537, + "step": 76319 + }, + { + "epoch": 0.0, + "learning_rate": 4.874261561633766e-05, + "loss": 4.2276, + "step": 76800 + }, + { + "epoch": 0.0, + "learning_rate": 4.873422966882714e-05, + "loss": 4.2215, + "step": 77312 + }, + { + "epoch": 0.0, + "learning_rate": 4.872584372131662e-05, + "loss": 4.2167, + "step": 77824 + }, + { + "epoch": 0.0, + "learning_rate": 4.87174577738061e-05, + "loss": 4.2184, + "step": 78336 + }, + { + "epoch": 0.0, + "learning_rate": 4.870907182629558e-05, + "loss": 4.2098, + "step": 78848 + }, + { + "epoch": 0.0, + "learning_rate": 4.870068587878506e-05, + "loss": 4.1937, + "step": 79360 + }, + { + "epoch": 0.0, + "learning_rate": 4.869229993127454e-05, + "loss": 4.2, + "step": 79872 + }, + { + "epoch": 0.0, + "learning_rate": 4.8683913983764027e-05, + "loss": 4.2122, + "step": 80384 + }, + { + "epoch": 0.0, + "learning_rate": 4.8675528036253507e-05, + "loss": 4.2016, + "step": 80896 + }, + { + "epoch": 0.0, + "learning_rate": 4.8667142088742986e-05, + "loss": 4.2048, + "step": 81408 + }, + { + "epoch": 0.0, + "learning_rate": 4.865875614123246e-05, + "loss": 4.2067, + "step": 81920 + }, + { + "epoch": 0.0, + "learning_rate": 4.865037019372194e-05, + "loss": 4.2057, + "step": 82432 + }, + { + "epoch": 0.0, + "learning_rate": 4.8642000625015155e-05, + "loss": 4.1975, + "step": 82944 + }, + { + "epoch": 0.0, + "learning_rate": 4.8633614677504635e-05, + "loss": 4.1985, + "step": 83456 + }, + { + "epoch": 0.0, + "learning_rate": 4.862522872999411e-05, + "loss": 4.1919, + "step": 83968 + }, + { + "epoch": 0.0, + "learning_rate": 4.861684278248359e-05, + "loss": 4.1776, + "step": 84480 + }, + { + "epoch": 0.0, + "learning_rate": 4.860845683497307e-05, + "loss": 4.1862, + "step": 84992 + }, + { + "epoch": 0.0, + "learning_rate": 4.860007088746255e-05, + "loss": 4.1896, + "step": 85504 + }, + { + "epoch": 0.0, + "learning_rate": 4.859168493995203e-05, + "loss": 4.1873, + "step": 86016 + }, + { + "epoch": 0.0, + "learning_rate": 4.8583315371245244e-05, + "loss": 4.1902, + "step": 86528 + }, + { + "epoch": 0.0, + "learning_rate": 4.8574929423734724e-05, + "loss": 4.1753, + "step": 87040 + }, + { + "epoch": 0.0, + "learning_rate": 4.8566543476224204e-05, + "loss": 4.1867, + "step": 87552 + }, + { + "epoch": 0.0, + "learning_rate": 4.8558157528713684e-05, + "loss": 4.1738, + "step": 88064 + }, + { + "epoch": 0.0, + "learning_rate": 4.854978796000689e-05, + "loss": 4.1843, + "step": 88576 + }, + { + "epoch": 0.0, + "learning_rate": 4.854140201249637e-05, + "loss": 4.1753, + "step": 89088 + }, + { + "epoch": 0.0, + "learning_rate": 4.853301606498585e-05, + "loss": 4.1716, + "step": 89600 + }, + { + "epoch": 0.0, + "learning_rate": 4.852463011747533e-05, + "loss": 4.1775, + "step": 90112 + }, + { + "epoch": 0.0, + "learning_rate": 4.851624416996481e-05, + "loss": 4.1595, + "step": 90624 + }, + { + "epoch": 0.0, + "learning_rate": 4.850787460125802e-05, + "loss": 4.1745, + "step": 91136 + }, + { + "epoch": 0.01, + "learning_rate": 4.84994886537475e-05, + "loss": 4.1558, + "step": 91648 + }, + { + "epoch": 0.01, + "learning_rate": 4.849110270623698e-05, + "loss": 4.161, + "step": 92160 + }, + { + "epoch": 0.01, + "learning_rate": 4.848271675872646e-05, + "loss": 4.1622, + "step": 92672 + }, + { + "epoch": 0.01, + "learning_rate": 4.847434719001968e-05, + "loss": 4.1679, + "step": 93184 + }, + { + "epoch": 0.01, + "learning_rate": 4.846596124250916e-05, + "loss": 4.156, + "step": 93696 + }, + { + "epoch": 0.01, + "learning_rate": 4.845757529499864e-05, + "loss": 4.1519, + "step": 94208 + }, + { + "epoch": 0.01, + "learning_rate": 4.844918934748812e-05, + "loss": 4.1647, + "step": 94720 + }, + { + "epoch": 0.01, + "learning_rate": 4.84408033999776e-05, + "loss": 4.1547, + "step": 95232 + }, + { + "epoch": 0.01, + "learning_rate": 4.843243383127081e-05, + "loss": 4.1617, + "step": 95744 + }, + { + "epoch": 0.01, + "learning_rate": 4.842404788376029e-05, + "loss": 4.1452, + "step": 96256 + }, + { + "epoch": 0.01, + "learning_rate": 4.841566193624977e-05, + "loss": 4.1355, + "step": 96768 + }, + { + "epoch": 0.01, + "learning_rate": 4.840727598873925e-05, + "loss": 4.1396, + "step": 97280 + }, + { + "epoch": 0.01, + "learning_rate": 4.8398906420032456e-05, + "loss": 4.1349, + "step": 97792 + }, + { + "epoch": 0.01, + "learning_rate": 4.8390520472521936e-05, + "loss": 4.1501, + "step": 98304 + }, + { + "epoch": 0.01, + "learning_rate": 4.8382134525011416e-05, + "loss": 4.1371, + "step": 98816 + }, + { + "epoch": 0.01, + "learning_rate": 4.83737485775009e-05, + "loss": 4.1449, + "step": 99328 + }, + { + "epoch": 0.01, + "learning_rate": 4.836536262999038e-05, + "loss": 4.1375, + "step": 99840 + }, + { + "epoch": 0.01, + "learning_rate": 4.835699306128359e-05, + "loss": 4.1433, + "step": 100352 + }, + { + "epoch": 0.01, + "learning_rate": 4.834860711377307e-05, + "loss": 4.1412, + "step": 100864 + }, + { + "epoch": 0.01, + "learning_rate": 4.834022116626255e-05, + "loss": 4.118, + "step": 101376 + }, + { + "epoch": 0.01, + "learning_rate": 4.833183521875203e-05, + "loss": 4.1238, + "step": 101888 + }, + { + "epoch": 0.01, + "learning_rate": 4.832346565004524e-05, + "loss": 4.1211, + "step": 102400 + }, + { + "epoch": 0.01, + "learning_rate": 4.831507970253472e-05, + "loss": 4.1346, + "step": 102912 + }, + { + "epoch": 0.01, + "learning_rate": 4.83066937550242e-05, + "loss": 4.1128, + "step": 103424 + }, + { + "epoch": 0.01, + "learning_rate": 4.829830780751368e-05, + "loss": 4.1367, + "step": 103936 + }, + { + "epoch": 0.01, + "learning_rate": 4.828993823880689e-05, + "loss": 4.1107, + "step": 104448 + }, + { + "epoch": 0.01, + "learning_rate": 4.828155229129637e-05, + "loss": 4.1105, + "step": 104960 + }, + { + "epoch": 0.01, + "learning_rate": 4.8273166343785856e-05, + "loss": 4.1192, + "step": 105472 + }, + { + "epoch": 0.01, + "learning_rate": 4.8264780396275336e-05, + "loss": 4.1133, + "step": 105984 + }, + { + "epoch": 0.01, + "learning_rate": 4.8256394448764816e-05, + "loss": 4.1135, + "step": 106496 + }, + { + "epoch": 0.01, + "learning_rate": 4.8248024880058025e-05, + "loss": 4.1073, + "step": 107008 + }, + { + "epoch": 0.01, + "learning_rate": 4.8239638932547505e-05, + "loss": 4.1033, + "step": 107520 + }, + { + "epoch": 0.01, + "learning_rate": 4.8231252985036985e-05, + "loss": 4.1164, + "step": 108032 + }, + { + "epoch": 0.01, + "learning_rate": 4.8222867037526465e-05, + "loss": 4.1049, + "step": 108544 + }, + { + "epoch": 0.01, + "learning_rate": 4.8214497468819674e-05, + "loss": 4.104, + "step": 109056 + }, + { + "epoch": 0.01, + "learning_rate": 4.8206111521309154e-05, + "loss": 4.1057, + "step": 109568 + }, + { + "epoch": 0.01, + "learning_rate": 4.8197725573798634e-05, + "loss": 4.1084, + "step": 110080 + }, + { + "epoch": 0.01, + "learning_rate": 4.8189339626288114e-05, + "loss": 4.0875, + "step": 110592 + }, + { + "epoch": 0.01, + "learning_rate": 4.818097005758132e-05, + "loss": 4.1093, + "step": 111104 + }, + { + "epoch": 0.01, + "learning_rate": 4.817258411007081e-05, + "loss": 4.0951, + "step": 111616 + }, + { + "epoch": 0.01, + "learning_rate": 4.816419816256029e-05, + "loss": 4.0955, + "step": 112128 + }, + { + "epoch": 0.01, + "learning_rate": 4.815581221504977e-05, + "loss": 4.1026, + "step": 112640 + }, + { + "epoch": 0.01, + "learning_rate": 4.814744264634298e-05, + "loss": 4.0931, + "step": 113152 + }, + { + "epoch": 0.01, + "learning_rate": 4.813905669883246e-05, + "loss": 4.1091, + "step": 113664 + }, + { + "epoch": 0.01, + "learning_rate": 4.813067075132194e-05, + "loss": 4.1147, + "step": 114176 + }, + { + "epoch": 0.01, + "learning_rate": 4.812228480381141e-05, + "loss": 4.1082, + "step": 114688 + }, + { + "epoch": 0.01, + "learning_rate": 4.811391523510463e-05, + "loss": 4.0923, + "step": 115200 + }, + { + "epoch": 0.01, + "learning_rate": 4.810552928759411e-05, + "loss": 4.0847, + "step": 115712 + }, + { + "epoch": 0.01, + "learning_rate": 4.809714334008359e-05, + "loss": 4.081, + "step": 116224 + }, + { + "epoch": 0.01, + "learning_rate": 4.808875739257306e-05, + "loss": 4.0924, + "step": 116736 + }, + { + "epoch": 0.01, + "learning_rate": 4.808037144506255e-05, + "loss": 4.1051, + "step": 117248 + }, + { + "epoch": 0.01, + "learning_rate": 4.807200187635576e-05, + "loss": 4.0972, + "step": 117760 + }, + { + "epoch": 0.01, + "learning_rate": 4.8063615928845243e-05, + "loss": 4.0815, + "step": 118272 + }, + { + "epoch": 0.01, + "learning_rate": 4.8055229981334717e-05, + "loss": 4.0737, + "step": 118784 + }, + { + "epoch": 0.01, + "learning_rate": 4.8046844033824197e-05, + "loss": 4.0869, + "step": 119296 + }, + { + "epoch": 0.01, + "learning_rate": 4.803849084392114e-05, + "loss": 4.0743, + "step": 119808 + }, + { + "epoch": 0.01, + "learning_rate": 4.803010489641062e-05, + "loss": 4.0806, + "step": 120320 + }, + { + "epoch": 0.01, + "learning_rate": 4.80217189489001e-05, + "loss": 4.0831, + "step": 120832 + }, + { + "epoch": 0.01, + "learning_rate": 4.801333300138958e-05, + "loss": 4.0881, + "step": 121344 + }, + { + "epoch": 0.01, + "learning_rate": 4.800494705387906e-05, + "loss": 4.0761, + "step": 121856 + }, + { + "epoch": 0.02, + "learning_rate": 4.799657748517227e-05, + "loss": 4.0775, + "step": 122368 + }, + { + "epoch": 0.02, + "learning_rate": 4.798819153766175e-05, + "loss": 4.0702, + "step": 122880 + }, + { + "epoch": 0.02, + "learning_rate": 4.797980559015123e-05, + "loss": 4.0813, + "step": 123392 + }, + { + "epoch": 0.02, + "learning_rate": 4.797141964264071e-05, + "loss": 4.0783, + "step": 123904 + }, + { + "epoch": 0.02, + "learning_rate": 4.796303369513019e-05, + "loss": 4.0581, + "step": 124416 + }, + { + "epoch": 0.02, + "learning_rate": 4.795464774761967e-05, + "loss": 4.0688, + "step": 124928 + }, + { + "epoch": 0.02, + "learning_rate": 4.7946278178912886e-05, + "loss": 4.0794, + "step": 125440 + }, + { + "epoch": 0.02, + "learning_rate": 4.793789223140236e-05, + "loss": 4.0847, + "step": 125952 + }, + { + "epoch": 0.02, + "learning_rate": 4.792950628389184e-05, + "loss": 4.0721, + "step": 126464 + }, + { + "epoch": 0.02, + "learning_rate": 4.792112033638132e-05, + "loss": 4.0636, + "step": 126976 + }, + { + "epoch": 0.02, + "learning_rate": 4.79127343888708e-05, + "loss": 4.0768, + "step": 127488 + }, + { + "epoch": 0.02, + "learning_rate": 4.790434844136028e-05, + "loss": 4.0554, + "step": 128000 + }, + { + "epoch": 0.02, + "learning_rate": 4.789596249384976e-05, + "loss": 4.0713, + "step": 128512 + }, + { + "epoch": 0.02, + "learning_rate": 4.788757654633924e-05, + "loss": 4.0784, + "step": 129024 + }, + { + "epoch": 0.02, + "learning_rate": 4.787920697763245e-05, + "loss": 4.067, + "step": 129536 + }, + { + "epoch": 0.02, + "learning_rate": 4.7870821030121935e-05, + "loss": 4.0665, + "step": 130048 + }, + { + "epoch": 0.02, + "learning_rate": 4.7862435082611415e-05, + "loss": 4.0455, + "step": 130560 + }, + { + "epoch": 0.02, + "learning_rate": 4.7854049135100895e-05, + "loss": 4.0492, + "step": 131072 + }, + { + "epoch": 0.02, + "learning_rate": 4.7845679566394104e-05, + "loss": 4.055, + "step": 131584 + }, + { + "epoch": 0.02, + "learning_rate": 4.7837293618883584e-05, + "loss": 4.056, + "step": 132096 + }, + { + "epoch": 0.02, + "learning_rate": 4.7828907671373064e-05, + "loss": 4.0621, + "step": 132608 + }, + { + "epoch": 0.02, + "learning_rate": 4.7820521723862544e-05, + "loss": 4.051, + "step": 133120 + }, + { + "epoch": 0.02, + "learning_rate": 4.781215215515575e-05, + "loss": 4.0478, + "step": 133632 + }, + { + "epoch": 0.02, + "learning_rate": 4.780376620764523e-05, + "loss": 4.059, + "step": 134144 + }, + { + "epoch": 0.02, + "learning_rate": 4.779538026013471e-05, + "loss": 4.0647, + "step": 134656 + }, + { + "epoch": 0.02, + "learning_rate": 4.778699431262419e-05, + "loss": 4.0511, + "step": 135168 + }, + { + "epoch": 0.02, + "learning_rate": 4.77786247439174e-05, + "loss": 4.0573, + "step": 135680 + }, + { + "epoch": 0.02, + "learning_rate": 4.777023879640689e-05, + "loss": 4.0488, + "step": 136192 + }, + { + "epoch": 0.02, + "learning_rate": 4.776185284889637e-05, + "loss": 4.0521, + "step": 136704 + }, + { + "epoch": 0.02, + "learning_rate": 4.775346690138585e-05, + "loss": 4.0556, + "step": 137216 + }, + { + "epoch": 0.02, + "learning_rate": 4.774509733267906e-05, + "loss": 4.0414, + "step": 137728 + }, + { + "epoch": 0.02, + "learning_rate": 4.773671138516854e-05, + "loss": 4.0435, + "step": 138240 + }, + { + "epoch": 0.02, + "learning_rate": 4.772832543765802e-05, + "loss": 4.0411, + "step": 138752 + }, + { + "epoch": 0.02, + "learning_rate": 4.77199394901475e-05, + "loss": 4.0395, + "step": 139264 + }, + { + "epoch": 0.02, + "learning_rate": 4.771155354263698e-05, + "loss": 4.042, + "step": 139776 + }, + { + "epoch": 0.02, + "learning_rate": 4.770316759512646e-05, + "loss": 4.0471, + "step": 140288 + }, + { + "epoch": 0.02, + "learning_rate": 4.769478164761594e-05, + "loss": 4.0515, + "step": 140800 + }, + { + "epoch": 0.02, + "learning_rate": 4.768639570010542e-05, + "loss": 4.0351, + "step": 141312 + }, + { + "epoch": 0.02, + "learning_rate": 4.7678026131398626e-05, + "loss": 4.0396, + "step": 141824 + }, + { + "epoch": 0.02, + "learning_rate": 4.7669640183888106e-05, + "loss": 4.0517, + "step": 142336 + }, + { + "epoch": 0.02, + "learning_rate": 4.7661254236377586e-05, + "loss": 4.037, + "step": 142848 + }, + { + "epoch": 0.02, + "learning_rate": 4.765286828886707e-05, + "loss": 4.0511, + "step": 143360 + }, + { + "epoch": 0.02, + "learning_rate": 4.764449872016028e-05, + "loss": 4.0337, + "step": 143872 + }, + { + "epoch": 0.02, + "learning_rate": 4.763611277264976e-05, + "loss": 4.0522, + "step": 144384 + }, + { + "epoch": 0.02, + "learning_rate": 4.762772682513924e-05, + "loss": 4.0406, + "step": 144896 + }, + { + "epoch": 0.02, + "learning_rate": 4.761934087762872e-05, + "loss": 4.0243, + "step": 145408 + }, + { + "epoch": 0.02, + "learning_rate": 4.761097130892193e-05, + "loss": 4.0282, + "step": 145920 + }, + { + "epoch": 0.02, + "learning_rate": 4.760258536141141e-05, + "loss": 4.0293, + "step": 146432 + }, + { + "epoch": 0.02, + "learning_rate": 4.759419941390089e-05, + "loss": 4.0418, + "step": 146944 + }, + { + "epoch": 0.02, + "learning_rate": 4.758581346639037e-05, + "loss": 4.038, + "step": 147456 + }, + { + "epoch": 0.02, + "learning_rate": 4.757746027648731e-05, + "loss": 4.0425, + "step": 147968 + }, + { + "epoch": 0.02, + "learning_rate": 4.7569074328976796e-05, + "loss": 4.0333, + "step": 148480 + }, + { + "epoch": 0.02, + "learning_rate": 4.7560688381466276e-05, + "loss": 4.0257, + "step": 148992 + }, + { + "epoch": 0.02, + "learning_rate": 4.7552302433955756e-05, + "loss": 4.0273, + "step": 149504 + }, + { + "epoch": 0.02, + "learning_rate": 4.7543916486445236e-05, + "loss": 4.0213, + "step": 150016 + }, + { + "epoch": 0.02, + "learning_rate": 4.7535530538934716e-05, + "loss": 4.0295, + "step": 150528 + }, + { + "epoch": 0.02, + "learning_rate": 4.7527144591424196e-05, + "loss": 4.0451, + "step": 151040 + }, + { + "epoch": 0.02, + "learning_rate": 4.7518775022717405e-05, + "loss": 4.0283, + "step": 151552 + }, + { + "epoch": 0.02, + "learning_rate": 4.7510389075206885e-05, + "loss": 4.0217, + "step": 152064 + }, + { + "epoch": 0.02, + "learning_rate": 4.7502003127696365e-05, + "loss": 4.0217, + "step": 152576 + }, + { + "epoch": 0.03, + "eval_loss": 4.023455619812012, + "eval_runtime": 555.0126, + "eval_samples_per_second": 687.536, + "eval_steps_per_second": 21.486, + "step": 152638 + }, + { + "epoch": 0.0, + "learning_rate": 4.7493617180185845e-05, + "loss": 4.0272, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748523123267532e-05, + "loss": 4.0233, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.74768452851648e-05, + "loss": 4.0156, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.746845933765428e-05, + "loss": 4.02, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.7460073390143764e-05, + "loss": 4.0156, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.7451687442633244e-05, + "loss": 3.9971, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.7443301495122724e-05, + "loss": 4.0057, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.7434915547612204e-05, + "loss": 4.021, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.7426529600101684e-05, + "loss": 4.0041, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.741816003139489e-05, + "loss": 4.0103, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740977408388437e-05, + "loss": 4.0203, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.740138813637385e-05, + "loss": 4.0157, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739301856766706e-05, + "loss": 4.0066, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738463262015654e-05, + "loss": 4.0121, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.737624667264602e-05, + "loss": 4.0033, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.73678607251355e-05, + "loss": 3.9951, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735947477762498e-05, + "loss": 4.0001, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.735108883011446e-05, + "loss": 4.0066, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734270288260394e-05, + "loss": 4.0084, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733431693509343e-05, + "loss": 4.0109, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732593098758291e-05, + "loss": 3.9947, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731754504007238e-05, + "loss": 4.0095, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.730915909256186e-05, + "loss": 3.9987, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730078952385508e-05, + "loss": 4.0044, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.729240357634456e-05, + "loss": 4.0, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.728401762883403e-05, + "loss": 3.9987, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727563168132351e-05, + "loss": 4.005, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.726724573381299e-05, + "loss": 3.9863, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.725887616510621e-05, + "loss": 4.0013, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.725049021759568e-05, + "loss": 3.9861, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.724210427008517e-05, + "loss": 3.9912, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.7233718322574647e-05, + "loss": 3.993, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.7225332375064127e-05, + "loss": 3.9965, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.7216962806357336e-05, + "loss": 3.9921, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.7208576858846816e-05, + "loss": 3.9846, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.7200190911336296e-05, + "loss": 3.9988, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.7191804963825775e-05, + "loss": 3.9888, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.7183419016315255e-05, + "loss": 4.0003, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.7175033068804735e-05, + "loss": 3.9834, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.7166647121294215e-05, + "loss": 3.9711, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.7158277552587424e-05, + "loss": 3.9748, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.7149891605076904e-05, + "loss": 3.9788, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.7141505657566384e-05, + "loss": 3.9945, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.7133119710055864e-05, + "loss": 3.9715, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.712473376254535e-05, + "loss": 3.989, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.711634781503483e-05, + "loss": 3.9816, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.710797824632804e-05, + "loss": 3.9812, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.709959229881752e-05, + "loss": 3.9875, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.7091206351307e-05, + "loss": 3.9632, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.708282040379648e-05, + "loss": 3.9676, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.707443445628596e-05, + "loss": 3.9627, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.706604850877544e-05, + "loss": 3.9841, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705766256126492e-05, + "loss": 3.963, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704927661375439e-05, + "loss": 3.9845, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.704090704504761e-05, + "loss": 3.96, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703252109753709e-05, + "loss": 3.961, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.702413515002657e-05, + "loss": 3.9678, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.701574920251605e-05, + "loss": 3.9615, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.700736325500553e-05, + "loss": 3.9675, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.699897730749501e-05, + "loss": 3.9642, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699060773878822e-05, + "loss": 3.9513, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.69822217912777e-05, + "loss": 3.9671, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.697383584376718e-05, + "loss": 3.9589, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696544989625666e-05, + "loss": 3.9639, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.695708032754987e-05, + "loss": 3.9571, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694869438003935e-05, + "loss": 3.9656, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694030843252883e-05, + "loss": 3.9423, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.6931922485018307e-05, + "loss": 3.9668, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.6923536537507787e-05, + "loss": 3.9521, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.6915150589997267e-05, + "loss": 3.958, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690676464248675e-05, + "loss": 3.9594, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.689839507377996e-05, + "loss": 3.9539, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.689000912626944e-05, + "loss": 3.9674, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.688162317875892e-05, + "loss": 3.9762, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.68732372312484e-05, + "loss": 3.9726, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.686485128373788e-05, + "loss": 3.958, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.685648171503109e-05, + "loss": 3.9475, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.684809576752057e-05, + "loss": 3.9399, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.683970982001005e-05, + "loss": 3.9614, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.683132387249953e-05, + "loss": 3.9662, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.682295430379274e-05, + "loss": 3.962, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.681456835628222e-05, + "loss": 3.9466, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.680618240877171e-05, + "loss": 3.9418, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679779646126119e-05, + "loss": 3.9502, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678941051375067e-05, + "loss": 3.9382, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.6781040945043876e-05, + "loss": 3.9475, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.6772654997533356e-05, + "loss": 3.9541, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.6764269050022836e-05, + "loss": 3.9526, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.6755883102512316e-05, + "loss": 3.9473, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.6747513533805525e-05, + "loss": 3.9496, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.6739127586295005e-05, + "loss": 3.9389, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.6730741638784485e-05, + "loss": 3.9521, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.6722355691273965e-05, + "loss": 3.9466, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.6713986122567174e-05, + "loss": 3.9349, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.670560017505666e-05, + "loss": 3.9392, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.669723060634987e-05, + "loss": 3.9509, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.668884465883935e-05, + "loss": 3.9574, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668045871132883e-05, + "loss": 3.9434, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667207276381831e-05, + "loss": 3.9418, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.666368681630779e-05, + "loss": 3.9485, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665530086879727e-05, + "loss": 3.9313, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664691492128675e-05, + "loss": 3.9479, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663852897377623e-05, + "loss": 3.9525, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.663015940506944e-05, + "loss": 3.9422, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662177345755892e-05, + "loss": 3.9483, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.66133875100484e-05, + "loss": 3.9258, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660500156253788e-05, + "loss": 3.9235, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.6596631993831094e-05, + "loss": 3.9333, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.6588246046320574e-05, + "loss": 3.9349, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.6579860098810054e-05, + "loss": 3.9433, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657147415129953e-05, + "loss": 3.9295, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.656308820378901e-05, + "loss": 3.925, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655471863508222e-05, + "loss": 3.9341, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.65463326875717e-05, + "loss": 3.9462, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.6537946740061176e-05, + "loss": 3.9359, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.652957717135439e-05, + "loss": 3.9443, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.652119122384387e-05, + "loss": 3.9282, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.651280527633335e-05, + "loss": 3.9291, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650441932882283e-05, + "loss": 3.9419, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.649603338131231e-05, + "loss": 3.9241, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648764743380179e-05, + "loss": 3.9262, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.647926148629127e-05, + "loss": 3.9255, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.647087553878075e-05, + "loss": 3.9228, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.646250597007396e-05, + "loss": 3.928, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.645412002256344e-05, + "loss": 3.929, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.644573407505292e-05, + "loss": 3.9396, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.64373481275424e-05, + "loss": 3.9192, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.642897855883561e-05, + "loss": 3.9236, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642059261132509e-05, + "loss": 3.9423, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.641220666381457e-05, + "loss": 3.9225, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640382071630405e-05, + "loss": 3.9384, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.6395434768793536e-05, + "loss": 3.9233, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.6387065200086746e-05, + "loss": 3.9396, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.6378679252576226e-05, + "loss": 3.9295, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.6370293305065705e-05, + "loss": 3.9158, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.6361907357555185e-05, + "loss": 3.9181, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.6353521410044665e-05, + "loss": 3.9168, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.6345151841337874e-05, + "loss": 3.9293, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.6336765893827354e-05, + "loss": 3.9325, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.6328379946316834e-05, + "loss": 3.9305, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.6319993998806314e-05, + "loss": 3.9241, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.6311624430099523e-05, + "loss": 3.9173, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.6303238482589003e-05, + "loss": 3.9199, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629485253507848e-05, + "loss": 3.9121, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.628646658756797e-05, + "loss": 3.9221, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.627808064005745e-05, + "loss": 3.933, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626971107135066e-05, + "loss": 3.9211, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626132512384014e-05, + "loss": 3.9158, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625293917632962e-05, + "loss": 3.9137, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.9498324394226074, + "eval_runtime": 561.8831, + "eval_samples_per_second": 679.129, + "eval_steps_per_second": 21.223, + "step": 228957 + }, + { + "epoch": 0.0, + "learning_rate": 4.62445532288191e-05, + "loss": 3.9169, + "step": 229376 + }, + { + "epoch": 0.0, + "learning_rate": 4.623616728130858e-05, + "loss": 3.922, + "step": 229888 + }, + { + "epoch": 0.0, + "learning_rate": 4.622778133379806e-05, + "loss": 3.91, + "step": 230400 + }, + { + "epoch": 0.0, + "learning_rate": 4.621939538628753e-05, + "loss": 3.9128, + "step": 230912 + }, + { + "epoch": 0.0, + "learning_rate": 4.621100943877701e-05, + "loss": 3.9153, + "step": 231424 + }, + { + "epoch": 0.0, + "learning_rate": 4.620262349126649e-05, + "loss": 3.893, + "step": 231936 + }, + { + "epoch": 0.0, + "learning_rate": 4.619423754375597e-05, + "loss": 3.9021, + "step": 232448 + }, + { + "epoch": 0.0, + "learning_rate": 4.618585159624545e-05, + "loss": 3.9146, + "step": 232960 + }, + { + "epoch": 0.0, + "learning_rate": 4.617748202753867e-05, + "loss": 3.9037, + "step": 233472 + }, + { + "epoch": 0.0, + "learning_rate": 4.616909608002815e-05, + "loss": 3.9098, + "step": 233984 + }, + { + "epoch": 0.0, + "learning_rate": 4.616071013251763e-05, + "loss": 3.9149, + "step": 234496 + }, + { + "epoch": 0.0, + "learning_rate": 4.615232418500711e-05, + "loss": 3.9097, + "step": 235008 + }, + { + "epoch": 0.0, + "learning_rate": 4.614395461630032e-05, + "loss": 3.9051, + "step": 235520 + }, + { + "epoch": 0.0, + "learning_rate": 4.61355686687898e-05, + "loss": 3.9123, + "step": 236032 + }, + { + "epoch": 0.0, + "learning_rate": 4.612718272127928e-05, + "loss": 3.8991, + "step": 236544 + }, + { + "epoch": 0.0, + "learning_rate": 4.611879677376876e-05, + "loss": 3.8956, + "step": 237056 + }, + { + "epoch": 0.0, + "learning_rate": 4.6110427205061966e-05, + "loss": 3.8975, + "step": 237568 + }, + { + "epoch": 0.0, + "learning_rate": 4.6102041257551446e-05, + "loss": 3.9038, + "step": 238080 + }, + { + "epoch": 0.0, + "learning_rate": 4.6093655310040926e-05, + "loss": 3.9049, + "step": 238592 + }, + { + "epoch": 0.0, + "learning_rate": 4.6085269362530406e-05, + "loss": 3.9112, + "step": 239104 + }, + { + "epoch": 0.0, + "learning_rate": 4.607689979382362e-05, + "loss": 3.8971, + "step": 239616 + }, + { + "epoch": 0.0, + "learning_rate": 4.60685138463131e-05, + "loss": 3.9112, + "step": 240128 + }, + { + "epoch": 0.0, + "learning_rate": 4.606012789880258e-05, + "loss": 3.9014, + "step": 240640 + }, + { + "epoch": 0.0, + "learning_rate": 4.605174195129206e-05, + "loss": 3.9015, + "step": 241152 + }, + { + "epoch": 0.0, + "learning_rate": 4.604335600378154e-05, + "loss": 3.9035, + "step": 241664 + }, + { + "epoch": 0.0, + "learning_rate": 4.603498643507475e-05, + "loss": 3.8968, + "step": 242176 + }, + { + "epoch": 0.0, + "learning_rate": 4.602660048756423e-05, + "loss": 3.9063, + "step": 242688 + }, + { + "epoch": 0.0, + "learning_rate": 4.601821454005371e-05, + "loss": 3.8892, + "step": 243200 + }, + { + "epoch": 0.0, + "learning_rate": 4.600984497134692e-05, + "loss": 3.9058, + "step": 243712 + }, + { + "epoch": 0.01, + "learning_rate": 4.60014590238364e-05, + "loss": 3.8897, + "step": 244224 + }, + { + "epoch": 0.01, + "learning_rate": 4.599307307632588e-05, + "loss": 3.892, + "step": 244736 + }, + { + "epoch": 0.01, + "learning_rate": 4.598468712881536e-05, + "loss": 3.8971, + "step": 245248 + }, + { + "epoch": 0.01, + "learning_rate": 4.5976301181304846e-05, + "loss": 3.9059, + "step": 245760 + }, + { + "epoch": 0.01, + "learning_rate": 4.5967915233794326e-05, + "loss": 3.8931, + "step": 246272 + }, + { + "epoch": 0.01, + "learning_rate": 4.5959529286283806e-05, + "loss": 3.8933, + "step": 246784 + }, + { + "epoch": 0.01, + "learning_rate": 4.5951143338773286e-05, + "loss": 3.8987, + "step": 247296 + }, + { + "epoch": 0.01, + "learning_rate": 4.5942773770066495e-05, + "loss": 3.8937, + "step": 247808 + }, + { + "epoch": 0.01, + "learning_rate": 4.5934387822555975e-05, + "loss": 3.9083, + "step": 248320 + }, + { + "epoch": 0.01, + "learning_rate": 4.5926001875045455e-05, + "loss": 3.8897, + "step": 248832 + }, + { + "epoch": 0.01, + "learning_rate": 4.5917615927534935e-05, + "loss": 3.8772, + "step": 249344 + }, + { + "epoch": 0.01, + "learning_rate": 4.5909246358828144e-05, + "loss": 3.8852, + "step": 249856 + }, + { + "epoch": 0.01, + "learning_rate": 4.5900860411317624e-05, + "loss": 3.8809, + "step": 250368 + }, + { + "epoch": 0.01, + "learning_rate": 4.5892474463807104e-05, + "loss": 3.903, + "step": 250880 + }, + { + "epoch": 0.01, + "learning_rate": 4.5884088516296584e-05, + "loss": 3.8827, + "step": 251392 + }, + { + "epoch": 0.01, + "learning_rate": 4.58757189475898e-05, + "loss": 3.8937, + "step": 251904 + }, + { + "epoch": 0.01, + "learning_rate": 4.586733300007928e-05, + "loss": 3.888, + "step": 252416 + }, + { + "epoch": 0.01, + "learning_rate": 4.585894705256876e-05, + "loss": 3.8911, + "step": 252928 + }, + { + "epoch": 0.01, + "learning_rate": 4.585056110505824e-05, + "loss": 3.8943, + "step": 253440 + }, + { + "epoch": 0.01, + "learning_rate": 4.584219153635145e-05, + "loss": 3.8734, + "step": 253952 + }, + { + "epoch": 0.01, + "learning_rate": 4.583380558884093e-05, + "loss": 3.8725, + "step": 254464 + }, + { + "epoch": 0.01, + "learning_rate": 4.582541964133041e-05, + "loss": 3.8785, + "step": 254976 + }, + { + "epoch": 0.01, + "learning_rate": 4.581703369381989e-05, + "loss": 3.8926, + "step": 255488 + }, + { + "epoch": 0.01, + "learning_rate": 4.58086641251131e-05, + "loss": 3.8746, + "step": 256000 + }, + { + "epoch": 0.01, + "learning_rate": 4.580027817760258e-05, + "loss": 3.8894, + "step": 256512 + }, + { + "epoch": 0.01, + "learning_rate": 4.579189223009206e-05, + "loss": 3.8712, + "step": 257024 + }, + { + "epoch": 0.01, + "learning_rate": 4.578350628258154e-05, + "loss": 3.8701, + "step": 257536 + }, + { + "epoch": 0.01, + "learning_rate": 4.577513671387475e-05, + "loss": 3.8823, + "step": 258048 + }, + { + "epoch": 0.01, + "learning_rate": 4.576675076636423e-05, + "loss": 3.8688, + "step": 258560 + }, + { + "epoch": 0.01, + "learning_rate": 4.575836481885371e-05, + "loss": 3.8843, + "step": 259072 + }, + { + "epoch": 0.01, + "learning_rate": 4.574997887134319e-05, + "loss": 3.8775, + "step": 259584 + }, + { + "epoch": 0.01, + "learning_rate": 4.57416093026364e-05, + "loss": 3.8641, + "step": 260096 + }, + { + "epoch": 0.01, + "learning_rate": 4.573322335512588e-05, + "loss": 3.8778, + "step": 260608 + }, + { + "epoch": 0.01, + "learning_rate": 4.572483740761536e-05, + "loss": 3.8692, + "step": 261120 + }, + { + "epoch": 0.01, + "learning_rate": 4.571645146010484e-05, + "loss": 3.8793, + "step": 261632 + }, + { + "epoch": 0.01, + "learning_rate": 4.570808189139805e-05, + "loss": 3.8666, + "step": 262144 + }, + { + "epoch": 0.01, + "learning_rate": 4.569969594388753e-05, + "loss": 3.8797, + "step": 262656 + }, + { + "epoch": 0.01, + "learning_rate": 4.569130999637701e-05, + "loss": 3.8583, + "step": 263168 + }, + { + "epoch": 0.01, + "learning_rate": 4.568292404886649e-05, + "loss": 3.8771, + "step": 263680 + }, + { + "epoch": 0.01, + "learning_rate": 4.567455448015971e-05, + "loss": 3.8648, + "step": 264192 + }, + { + "epoch": 0.01, + "learning_rate": 4.566616853264919e-05, + "loss": 3.8694, + "step": 264704 + }, + { + "epoch": 0.01, + "learning_rate": 4.565778258513867e-05, + "loss": 3.8751, + "step": 265216 + }, + { + "epoch": 0.01, + "learning_rate": 4.564939663762814e-05, + "loss": 3.8723, + "step": 265728 + }, + { + "epoch": 0.01, + "learning_rate": 4.5641027068921356e-05, + "loss": 3.8774, + "step": 266240 + }, + { + "epoch": 0.01, + "learning_rate": 4.5632641121410836e-05, + "loss": 3.8919, + "step": 266752 + }, + { + "epoch": 0.01, + "learning_rate": 4.5624255173900316e-05, + "loss": 3.8838, + "step": 267264 + }, + { + "epoch": 0.01, + "learning_rate": 4.561586922638979e-05, + "loss": 3.8731, + "step": 267776 + }, + { + "epoch": 0.01, + "learning_rate": 4.5607499657683005e-05, + "loss": 3.8666, + "step": 268288 + }, + { + "epoch": 0.01, + "learning_rate": 4.5599113710172485e-05, + "loss": 3.857, + "step": 268800 + }, + { + "epoch": 0.01, + "learning_rate": 4.5590727762661965e-05, + "loss": 3.8757, + "step": 269312 + }, + { + "epoch": 0.01, + "learning_rate": 4.5582341815151445e-05, + "loss": 3.8827, + "step": 269824 + }, + { + "epoch": 0.01, + "learning_rate": 4.5573972246444654e-05, + "loss": 3.8793, + "step": 270336 + }, + { + "epoch": 0.01, + "learning_rate": 4.556558629893414e-05, + "loss": 3.8606, + "step": 270848 + }, + { + "epoch": 0.01, + "learning_rate": 4.5557200351423614e-05, + "loss": 3.8586, + "step": 271360 + }, + { + "epoch": 0.01, + "learning_rate": 4.5548814403913094e-05, + "loss": 3.8714, + "step": 271872 + }, + { + "epoch": 0.01, + "learning_rate": 4.554044483520631e-05, + "loss": 3.8486, + "step": 272384 + }, + { + "epoch": 0.01, + "learning_rate": 4.553207526649952e-05, + "loss": 3.8665, + "step": 272896 + }, + { + "epoch": 0.01, + "learning_rate": 4.5523689318989e-05, + "loss": 3.8668, + "step": 273408 + }, + { + "epoch": 0.01, + "learning_rate": 4.551530337147848e-05, + "loss": 3.8709, + "step": 273920 + }, + { + "epoch": 0.01, + "learning_rate": 4.550691742396796e-05, + "loss": 3.8658, + "step": 274432 + }, + { + "epoch": 0.02, + "learning_rate": 4.549854785526117e-05, + "loss": 3.871, + "step": 274944 + }, + { + "epoch": 0.02, + "learning_rate": 4.549016190775065e-05, + "loss": 3.855, + "step": 275456 + }, + { + "epoch": 0.02, + "learning_rate": 4.548177596024013e-05, + "loss": 3.8682, + "step": 275968 + }, + { + "epoch": 0.02, + "learning_rate": 4.547339001272961e-05, + "loss": 3.863, + "step": 276480 + }, + { + "epoch": 0.02, + "learning_rate": 4.546500406521909e-05, + "loss": 3.8578, + "step": 276992 + }, + { + "epoch": 0.02, + "learning_rate": 4.545661811770857e-05, + "loss": 3.8567, + "step": 277504 + }, + { + "epoch": 0.02, + "learning_rate": 4.544824854900178e-05, + "loss": 3.873, + "step": 278016 + }, + { + "epoch": 0.02, + "learning_rate": 4.543986260149126e-05, + "loss": 3.872, + "step": 278528 + }, + { + "epoch": 0.02, + "learning_rate": 4.5431476653980736e-05, + "loss": 3.8693, + "step": 279040 + }, + { + "epoch": 0.02, + "learning_rate": 4.5423090706470216e-05, + "loss": 3.8599, + "step": 279552 + }, + { + "epoch": 0.02, + "learning_rate": 4.5414704758959696e-05, + "loss": 3.8694, + "step": 280064 + }, + { + "epoch": 0.02, + "learning_rate": 4.5406318811449176e-05, + "loss": 3.8529, + "step": 280576 + }, + { + "epoch": 0.02, + "learning_rate": 4.5397932863938656e-05, + "loss": 3.8674, + "step": 281088 + }, + { + "epoch": 0.02, + "learning_rate": 4.5389546916428136e-05, + "loss": 3.8739, + "step": 281600 + }, + { + "epoch": 0.02, + "learning_rate": 4.5381177347721345e-05, + "loss": 3.8603, + "step": 282112 + }, + { + "epoch": 0.02, + "learning_rate": 4.537279140021083e-05, + "loss": 3.8733, + "step": 282624 + }, + { + "epoch": 0.02, + "learning_rate": 4.536440545270031e-05, + "loss": 3.8415, + "step": 283136 + }, + { + "epoch": 0.02, + "learning_rate": 4.535601950518979e-05, + "loss": 3.8465, + "step": 283648 + }, + { + "epoch": 0.02, + "learning_rate": 4.5347649936483e-05, + "loss": 3.8572, + "step": 284160 + }, + { + "epoch": 0.02, + "learning_rate": 4.533926398897248e-05, + "loss": 3.8568, + "step": 284672 + }, + { + "epoch": 0.02, + "learning_rate": 4.533089442026569e-05, + "loss": 3.8654, + "step": 285184 + }, + { + "epoch": 0.02, + "learning_rate": 4.532250847275517e-05, + "loss": 3.8507, + "step": 285696 + }, + { + "epoch": 0.02, + "learning_rate": 4.531412252524465e-05, + "loss": 3.8483, + "step": 286208 + }, + { + "epoch": 0.02, + "learning_rate": 4.530573657773413e-05, + "loss": 3.8545, + "step": 286720 + }, + { + "epoch": 0.02, + "learning_rate": 4.529735063022361e-05, + "loss": 3.8683, + "step": 287232 + }, + { + "epoch": 0.02, + "learning_rate": 4.528896468271309e-05, + "loss": 3.861, + "step": 287744 + }, + { + "epoch": 0.02, + "learning_rate": 4.528057873520257e-05, + "loss": 3.866, + "step": 288256 + }, + { + "epoch": 0.02, + "learning_rate": 4.527219278769205e-05, + "loss": 3.8509, + "step": 288768 + }, + { + "epoch": 0.02, + "learning_rate": 4.5263823218985266e-05, + "loss": 3.8512, + "step": 289280 + }, + { + "epoch": 0.02, + "learning_rate": 4.5255437271474746e-05, + "loss": 3.8679, + "step": 289792 + }, + { + "epoch": 0.02, + "learning_rate": 4.5247051323964226e-05, + "loss": 3.8497, + "step": 290304 + }, + { + "epoch": 0.02, + "learning_rate": 4.5238665376453706e-05, + "loss": 3.8461, + "step": 290816 + }, + { + "epoch": 0.02, + "learning_rate": 4.5230295807746915e-05, + "loss": 3.8504, + "step": 291328 + }, + { + "epoch": 0.02, + "learning_rate": 4.5221909860236395e-05, + "loss": 3.8452, + "step": 291840 + }, + { + "epoch": 0.02, + "learning_rate": 4.5213523912725875e-05, + "loss": 3.854, + "step": 292352 + }, + { + "epoch": 0.02, + "learning_rate": 4.5205154344019084e-05, + "loss": 3.8536, + "step": 292864 + }, + { + "epoch": 0.02, + "learning_rate": 4.5196768396508564e-05, + "loss": 3.866, + "step": 293376 + }, + { + "epoch": 0.02, + "learning_rate": 4.5188382448998044e-05, + "loss": 3.846, + "step": 293888 + }, + { + "epoch": 0.02, + "learning_rate": 4.5179996501487524e-05, + "loss": 3.8443, + "step": 294400 + }, + { + "epoch": 0.02, + "learning_rate": 4.517162693278074e-05, + "loss": 3.8698, + "step": 294912 + }, + { + "epoch": 0.02, + "learning_rate": 4.516324098527022e-05, + "loss": 3.8465, + "step": 295424 + }, + { + "epoch": 0.02, + "learning_rate": 4.51548550377597e-05, + "loss": 3.8589, + "step": 295936 + }, + { + "epoch": 0.02, + "learning_rate": 4.514646909024918e-05, + "loss": 3.8536, + "step": 296448 + }, + { + "epoch": 0.02, + "learning_rate": 4.513808314273866e-05, + "loss": 3.865, + "step": 296960 + }, + { + "epoch": 0.02, + "learning_rate": 4.512971357403187e-05, + "loss": 3.8556, + "step": 297472 + }, + { + "epoch": 0.02, + "learning_rate": 4.512132762652135e-05, + "loss": 3.8453, + "step": 297984 + }, + { + "epoch": 0.02, + "learning_rate": 4.511294167901083e-05, + "loss": 3.841, + "step": 298496 + }, + { + "epoch": 0.02, + "learning_rate": 4.510455573150031e-05, + "loss": 3.8419, + "step": 299008 + }, + { + "epoch": 0.02, + "learning_rate": 4.509618616279352e-05, + "loss": 3.8544, + "step": 299520 + }, + { + "epoch": 0.02, + "learning_rate": 4.5087800215283e-05, + "loss": 3.8609, + "step": 300032 + }, + { + "epoch": 0.02, + "learning_rate": 4.5079430646576206e-05, + "loss": 3.8524, + "step": 300544 + }, + { + "epoch": 0.02, + "learning_rate": 4.507104469906569e-05, + "loss": 3.8552, + "step": 301056 + }, + { + "epoch": 0.02, + "learning_rate": 4.506265875155517e-05, + "loss": 3.8424, + "step": 301568 + }, + { + "epoch": 0.02, + "learning_rate": 4.505427280404465e-05, + "loss": 3.8482, + "step": 302080 + }, + { + "epoch": 0.02, + "learning_rate": 4.504588685653413e-05, + "loss": 3.838, + "step": 302592 + }, + { + "epoch": 0.02, + "learning_rate": 4.503750090902361e-05, + "loss": 3.8506, + "step": 303104 + }, + { + "epoch": 0.02, + "learning_rate": 4.502911496151309e-05, + "loss": 3.8554, + "step": 303616 + }, + { + "epoch": 0.02, + "learning_rate": 4.502072901400257e-05, + "loss": 3.8567, + "step": 304128 + }, + { + "epoch": 0.02, + "learning_rate": 4.501235944529578e-05, + "loss": 3.8435, + "step": 304640 + }, + { + "epoch": 0.02, + "learning_rate": 4.500397349778526e-05, + "loss": 3.8418, + "step": 305152 + }, + { + "epoch": 0.03, + "eval_loss": 3.9088995456695557, + "eval_runtime": 571.3357, + "eval_samples_per_second": 667.893, + "eval_steps_per_second": 20.872, + "step": 305276 + }, + { + "epoch": 0.0, + "learning_rate": 4.499560392907847e-05, + "loss": 3.8499, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.498721798156795e-05, + "loss": 3.8474, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.497883203405743e-05, + "loss": 3.8402, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.497044608654691e-05, + "loss": 3.8408, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.496206013903639e-05, + "loss": 3.8421, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.495367419152587e-05, + "loss": 3.8272, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.494528824401535e-05, + "loss": 3.8316, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.493690229650483e-05, + "loss": 3.8386, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.4928532727798047e-05, + "loss": 3.8389, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.4920163159091256e-05, + "loss": 3.84, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.4911777211580736e-05, + "loss": 3.8423, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.4903391264070216e-05, + "loss": 3.8355, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.4895021695363425e-05, + "loss": 3.837, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.4886635747852905e-05, + "loss": 3.8426, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.4878249800342385e-05, + "loss": 3.8314, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.4869863852831864e-05, + "loss": 3.8252, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.4861477905321344e-05, + "loss": 3.8254, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.4853091957810824e-05, + "loss": 3.8394, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.4844706010300304e-05, + "loss": 3.8325, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.4836320062789784e-05, + "loss": 3.8461, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.4827934115279264e-05, + "loss": 3.8295, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.4819548167768744e-05, + "loss": 3.8417, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.4811162220258224e-05, + "loss": 3.8343, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480279265155143e-05, + "loss": 3.834, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479440670404091e-05, + "loss": 3.8338, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478602075653039e-05, + "loss": 3.8284, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477763480901987e-05, + "loss": 3.8379, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476926524031308e-05, + "loss": 3.8225, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.47608956716063e-05, + "loss": 3.836, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475250972409578e-05, + "loss": 3.8264, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474412377658526e-05, + "loss": 3.8207, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473573782907474e-05, + "loss": 3.8316, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472735188156422e-05, + "loss": 3.8372, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.47189659340537e-05, + "loss": 3.8291, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.471057998654318e-05, + "loss": 3.826, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.470219403903266e-05, + "loss": 3.8297, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469382447032587e-05, + "loss": 3.8316, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468543852281535e-05, + "loss": 3.8414, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.467705257530483e-05, + "loss": 3.8249, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.466866662779431e-05, + "loss": 3.8114, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.4660297059087516e-05, + "loss": 3.8202, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.4651911111577e-05, + "loss": 3.8169, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464352516406648e-05, + "loss": 3.8328, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463513921655596e-05, + "loss": 3.8211, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.462676964784917e-05, + "loss": 3.8298, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461838370033865e-05, + "loss": 3.8234, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.460999775282813e-05, + "loss": 3.8231, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.460161180531761e-05, + "loss": 3.8304, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.459324223661082e-05, + "loss": 3.8119, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.45848562891003e-05, + "loss": 3.8054, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.457647034158978e-05, + "loss": 3.8184, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.456808439407926e-05, + "loss": 3.8231, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.455971482537247e-05, + "loss": 3.8111, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.4551328877861956e-05, + "loss": 3.8262, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.4542942930351436e-05, + "loss": 3.8082, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.4534556982840916e-05, + "loss": 3.8042, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.4526187414134125e-05, + "loss": 3.8174, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.4517801466623605e-05, + "loss": 3.8065, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.4509415519113085e-05, + "loss": 3.8247, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.4501045950406294e-05, + "loss": 3.8166, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.4492660002895774e-05, + "loss": 3.7971, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.4484274055385254e-05, + "loss": 3.8129, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.4475888107874734e-05, + "loss": 3.8078, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446751853916794e-05, + "loss": 3.8214, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445913259165742e-05, + "loss": 3.8025, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445074664414691e-05, + "loss": 3.815, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444236069663639e-05, + "loss": 3.7976, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.44339911279296e-05, + "loss": 3.8138, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.442560518041908e-05, + "loss": 3.805, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441721923290856e-05, + "loss": 3.807, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.440883328539804e-05, + "loss": 3.8164, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440046371669125e-05, + "loss": 3.8082, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.439207776918073e-05, + "loss": 3.8156, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438369182167021e-05, + "loss": 3.8275, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437530587415969e-05, + "loss": 3.8242, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.43669363054529e-05, + "loss": 3.8129, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435855035794238e-05, + "loss": 3.8056, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.4350164410431864e-05, + "loss": 3.7974, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.4341778462921344e-05, + "loss": 3.8112, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.433340889421455e-05, + "loss": 3.8247, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.432502294670403e-05, + "loss": 3.8152, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431663699919351e-05, + "loss": 3.8027, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.430825105168299e-05, + "loss": 3.7954, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.42998814829762e-05, + "loss": 3.8165, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.429149553546568e-05, + "loss": 3.7923, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.428312596675889e-05, + "loss": 3.8032, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.427474001924837e-05, + "loss": 3.8052, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.426635407173785e-05, + "loss": 3.8092, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.425796812422733e-05, + "loss": 3.8094, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.4249598555520546e-05, + "loss": 3.813, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.4241212608010026e-05, + "loss": 3.7977, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.4232826660499506e-05, + "loss": 3.8078, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.4224440712988986e-05, + "loss": 3.8049, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.4216054765478466e-05, + "loss": 3.7985, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.4207668817967946e-05, + "loss": 3.7971, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.4199299249261155e-05, + "loss": 3.8157, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.4190913301750635e-05, + "loss": 3.8121, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.4182527354240115e-05, + "loss": 3.8143, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.4174141406729595e-05, + "loss": 3.802, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.416575545921907e-05, + "loss": 3.8073, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.4157369511708555e-05, + "loss": 3.7941, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.4148983564198035e-05, + "loss": 3.811, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.4140597616687515e-05, + "loss": 3.8111, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.413224442678446e-05, + "loss": 3.8021, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.412385847927394e-05, + "loss": 3.8169, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.411547253176342e-05, + "loss": 3.7853, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.410708658425289e-05, + "loss": 3.7907, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409870063674237e-05, + "loss": 3.7973, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.409031468923185e-05, + "loss": 3.7991, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.408194512052507e-05, + "loss": 3.8071, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407355917301454e-05, + "loss": 3.7988, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.406517322550402e-05, + "loss": 3.7883, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.405678727799351e-05, + "loss": 3.7974, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404840133048299e-05, + "loss": 3.8111, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.404001538297247e-05, + "loss": 3.8041, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.403162943546195e-05, + "loss": 3.8093, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402324348795143e-05, + "loss": 3.7951, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.401487391924464e-05, + "loss": 3.7941, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400648797173412e-05, + "loss": 3.808, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.39981020242236e-05, + "loss": 3.7954, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398971607671308e-05, + "loss": 3.7913, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.3981346508006287e-05, + "loss": 3.7912, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.3972960560495767e-05, + "loss": 3.7897, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.3964574612985247e-05, + "loss": 3.7995, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.3956188665474726e-05, + "loss": 3.7983, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394781909676794e-05, + "loss": 3.8078, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.393943314925742e-05, + "loss": 3.7893, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.39310472017469e-05, + "loss": 3.7909, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.392267763304011e-05, + "loss": 3.8118, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.391429168552959e-05, + "loss": 3.7939, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.390590573801907e-05, + "loss": 3.8029, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.389751979050855e-05, + "loss": 3.8023, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.388915022180176e-05, + "loss": 3.8045, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.388076427429124e-05, + "loss": 3.8025, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.387237832678072e-05, + "loss": 3.7887, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.38639923792702e-05, + "loss": 3.7873, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.385562281056341e-05, + "loss": 3.794, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.3847236863052896e-05, + "loss": 3.7992, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.3838850915542376e-05, + "loss": 3.8024, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.3830481346835585e-05, + "loss": 3.801, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.3822095399325065e-05, + "loss": 3.7989, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.3813709451814545e-05, + "loss": 3.7908, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.3805323504304025e-05, + "loss": 3.7938, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.3796937556793505e-05, + "loss": 3.7826, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.3788551609282985e-05, + "loss": 3.7992, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.3780165661772465e-05, + "loss": 3.8022, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.3771779714261945e-05, + "loss": 3.8015, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.3763410145555154e-05, + "loss": 3.7859, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.3755024198044634e-05, + "loss": 3.7884, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.883521556854248, + "eval_runtime": 575.2508, + "eval_samples_per_second": 663.347, + "eval_steps_per_second": 20.73, + "step": 381595 + }, + { + "epoch": 0.0, + "learning_rate": 4.374665462933785e-05, + "loss": 3.8031, + "step": 381952 + }, + { + "epoch": 0.0, + "learning_rate": 4.373826868182733e-05, + "loss": 3.7915, + "step": 382464 + }, + { + "epoch": 0.0, + "learning_rate": 4.372988273431681e-05, + "loss": 3.7888, + "step": 382976 + }, + { + "epoch": 0.0, + "learning_rate": 4.372149678680629e-05, + "loss": 3.7849, + "step": 383488 + }, + { + "epoch": 0.0, + "learning_rate": 4.371311083929577e-05, + "loss": 3.7881, + "step": 384000 + }, + { + "epoch": 0.0, + "learning_rate": 4.370472489178525e-05, + "loss": 3.7764, + "step": 384512 + }, + { + "epoch": 0.0, + "learning_rate": 4.369633894427473e-05, + "loss": 3.7807, + "step": 385024 + }, + { + "epoch": 0.0, + "learning_rate": 4.36879529967642e-05, + "loss": 3.7791, + "step": 385536 + }, + { + "epoch": 0.0, + "learning_rate": 4.367958342805742e-05, + "loss": 3.7885, + "step": 386048 + }, + { + "epoch": 0.0, + "learning_rate": 4.367121385935063e-05, + "loss": 3.7918, + "step": 386560 + }, + { + "epoch": 0.0, + "learning_rate": 4.366282791184011e-05, + "loss": 3.7863, + "step": 387072 + }, + { + "epoch": 0.0, + "learning_rate": 4.365444196432959e-05, + "loss": 3.7833, + "step": 387584 + }, + { + "epoch": 0.0, + "learning_rate": 4.364605601681907e-05, + "loss": 3.7889, + "step": 388096 + }, + { + "epoch": 0.0, + "learning_rate": 4.363767006930855e-05, + "loss": 3.7887, + "step": 388608 + }, + { + "epoch": 0.0, + "learning_rate": 4.362928412179803e-05, + "loss": 3.7814, + "step": 389120 + }, + { + "epoch": 0.0, + "learning_rate": 4.362089817428751e-05, + "loss": 3.773, + "step": 389632 + }, + { + "epoch": 0.0, + "learning_rate": 4.361251222677699e-05, + "loss": 3.7751, + "step": 390144 + }, + { + "epoch": 0.0, + "learning_rate": 4.36041426580702e-05, + "loss": 3.7842, + "step": 390656 + }, + { + "epoch": 0.0, + "learning_rate": 4.3595756710559676e-05, + "loss": 3.7825, + "step": 391168 + }, + { + "epoch": 0.0, + "learning_rate": 4.3587370763049156e-05, + "loss": 3.7958, + "step": 391680 + }, + { + "epoch": 0.0, + "learning_rate": 4.3578984815538636e-05, + "loss": 3.7797, + "step": 392192 + }, + { + "epoch": 0.0, + "learning_rate": 4.3570615246831845e-05, + "loss": 3.7883, + "step": 392704 + }, + { + "epoch": 0.0, + "learning_rate": 4.3562229299321325e-05, + "loss": 3.7851, + "step": 393216 + }, + { + "epoch": 0.0, + "learning_rate": 4.3553843351810805e-05, + "loss": 3.7818, + "step": 393728 + }, + { + "epoch": 0.0, + "learning_rate": 4.3545457404300285e-05, + "loss": 3.7818, + "step": 394240 + }, + { + "epoch": 0.0, + "learning_rate": 4.353707145678977e-05, + "loss": 3.7774, + "step": 394752 + }, + { + "epoch": 0.0, + "learning_rate": 4.352868550927925e-05, + "loss": 3.7859, + "step": 395264 + }, + { + "epoch": 0.0, + "learning_rate": 4.352029956176873e-05, + "loss": 3.771, + "step": 395776 + }, + { + "epoch": 0.0, + "learning_rate": 4.351192999306194e-05, + "loss": 3.7872, + "step": 396288 + }, + { + "epoch": 0.0, + "learning_rate": 4.350354404555142e-05, + "loss": 3.7752, + "step": 396800 + }, + { + "epoch": 0.01, + "learning_rate": 4.34951580980409e-05, + "loss": 3.7668, + "step": 397312 + }, + { + "epoch": 0.01, + "learning_rate": 4.348677215053038e-05, + "loss": 3.7832, + "step": 397824 + }, + { + "epoch": 0.01, + "learning_rate": 4.347838620301986e-05, + "loss": 3.7857, + "step": 398336 + }, + { + "epoch": 0.01, + "learning_rate": 4.347001663431307e-05, + "loss": 3.7833, + "step": 398848 + }, + { + "epoch": 0.01, + "learning_rate": 4.346163068680255e-05, + "loss": 3.7775, + "step": 399360 + }, + { + "epoch": 0.01, + "learning_rate": 4.345324473929203e-05, + "loss": 3.7758, + "step": 399872 + }, + { + "epoch": 0.01, + "learning_rate": 4.344485879178151e-05, + "loss": 3.7803, + "step": 400384 + }, + { + "epoch": 0.01, + "learning_rate": 4.343647284427099e-05, + "loss": 3.7915, + "step": 400896 + }, + { + "epoch": 0.01, + "learning_rate": 4.342808689676047e-05, + "loss": 3.776, + "step": 401408 + }, + { + "epoch": 0.01, + "learning_rate": 4.341970094924995e-05, + "loss": 3.7627, + "step": 401920 + }, + { + "epoch": 0.01, + "learning_rate": 4.3411315001739436e-05, + "loss": 3.7702, + "step": 402432 + }, + { + "epoch": 0.01, + "learning_rate": 4.3402945433032645e-05, + "loss": 3.7664, + "step": 402944 + }, + { + "epoch": 0.01, + "learning_rate": 4.3394559485522125e-05, + "loss": 3.7827, + "step": 403456 + }, + { + "epoch": 0.01, + "learning_rate": 4.3386173538011605e-05, + "loss": 3.7741, + "step": 403968 + }, + { + "epoch": 0.01, + "learning_rate": 4.3377803969304814e-05, + "loss": 3.7762, + "step": 404480 + }, + { + "epoch": 0.01, + "learning_rate": 4.3369418021794294e-05, + "loss": 3.7764, + "step": 404992 + }, + { + "epoch": 0.01, + "learning_rate": 4.3361032074283774e-05, + "loss": 3.7736, + "step": 405504 + }, + { + "epoch": 0.01, + "learning_rate": 4.3352646126773254e-05, + "loss": 3.783, + "step": 406016 + }, + { + "epoch": 0.01, + "learning_rate": 4.334427655806646e-05, + "loss": 3.7637, + "step": 406528 + }, + { + "epoch": 0.01, + "learning_rate": 4.333589061055594e-05, + "loss": 3.7544, + "step": 407040 + }, + { + "epoch": 0.01, + "learning_rate": 4.332750466304542e-05, + "loss": 3.7724, + "step": 407552 + }, + { + "epoch": 0.01, + "learning_rate": 4.33191187155349e-05, + "loss": 3.769, + "step": 408064 + }, + { + "epoch": 0.01, + "learning_rate": 4.331074914682812e-05, + "loss": 3.7661, + "step": 408576 + }, + { + "epoch": 0.01, + "learning_rate": 4.33023631993176e-05, + "loss": 3.7774, + "step": 409088 + }, + { + "epoch": 0.01, + "learning_rate": 4.329397725180708e-05, + "loss": 3.7566, + "step": 409600 + }, + { + "epoch": 0.01, + "learning_rate": 4.328559130429656e-05, + "loss": 3.7594, + "step": 410112 + }, + { + "epoch": 0.01, + "learning_rate": 4.327722173558977e-05, + "loss": 3.7683, + "step": 410624 + }, + { + "epoch": 0.01, + "learning_rate": 4.326883578807925e-05, + "loss": 3.7581, + "step": 411136 + }, + { + "epoch": 0.01, + "learning_rate": 4.326044984056873e-05, + "loss": 3.7756, + "step": 411648 + }, + { + "epoch": 0.01, + "learning_rate": 4.325206389305821e-05, + "loss": 3.7646, + "step": 412160 + }, + { + "epoch": 0.01, + "learning_rate": 4.324367794554768e-05, + "loss": 3.7579, + "step": 412672 + }, + { + "epoch": 0.01, + "learning_rate": 4.323529199803716e-05, + "loss": 3.7605, + "step": 413184 + }, + { + "epoch": 0.01, + "learning_rate": 4.322690605052664e-05, + "loss": 3.7558, + "step": 413696 + }, + { + "epoch": 0.01, + "learning_rate": 4.321853648181986e-05, + "loss": 3.7767, + "step": 414208 + }, + { + "epoch": 0.01, + "learning_rate": 4.321015053430934e-05, + "loss": 3.757, + "step": 414720 + }, + { + "epoch": 0.01, + "learning_rate": 4.320176458679882e-05, + "loss": 3.7717, + "step": 415232 + }, + { + "epoch": 0.01, + "learning_rate": 4.31933786392883e-05, + "loss": 3.7484, + "step": 415744 + }, + { + "epoch": 0.01, + "learning_rate": 4.3185009070581506e-05, + "loss": 3.7639, + "step": 416256 + }, + { + "epoch": 0.01, + "learning_rate": 4.3176623123070986e-05, + "loss": 3.7591, + "step": 416768 + }, + { + "epoch": 0.01, + "learning_rate": 4.3168237175560466e-05, + "loss": 3.7571, + "step": 417280 + }, + { + "epoch": 0.01, + "learning_rate": 4.3159851228049946e-05, + "loss": 3.7671, + "step": 417792 + }, + { + "epoch": 0.01, + "learning_rate": 4.3151481659343155e-05, + "loss": 3.7643, + "step": 418304 + }, + { + "epoch": 0.01, + "learning_rate": 4.3143095711832635e-05, + "loss": 3.7655, + "step": 418816 + }, + { + "epoch": 0.01, + "learning_rate": 4.3134709764322115e-05, + "loss": 3.7787, + "step": 419328 + }, + { + "epoch": 0.01, + "learning_rate": 4.3126323816811595e-05, + "loss": 3.7764, + "step": 419840 + }, + { + "epoch": 0.01, + "learning_rate": 4.311795424810481e-05, + "loss": 3.7701, + "step": 420352 + }, + { + "epoch": 0.01, + "learning_rate": 4.310956830059429e-05, + "loss": 3.7589, + "step": 420864 + }, + { + "epoch": 0.01, + "learning_rate": 4.3101198731887506e-05, + "loss": 3.7537, + "step": 421376 + }, + { + "epoch": 0.01, + "learning_rate": 4.309281278437698e-05, + "loss": 3.7618, + "step": 421888 + }, + { + "epoch": 0.01, + "learning_rate": 4.308442683686646e-05, + "loss": 3.7768, + "step": 422400 + }, + { + "epoch": 0.01, + "learning_rate": 4.307604088935594e-05, + "loss": 3.7673, + "step": 422912 + }, + { + "epoch": 0.01, + "learning_rate": 4.306765494184542e-05, + "loss": 3.7566, + "step": 423424 + }, + { + "epoch": 0.01, + "learning_rate": 4.30592689943349e-05, + "loss": 3.7472, + "step": 423936 + }, + { + "epoch": 0.01, + "learning_rate": 4.305088304682438e-05, + "loss": 3.7727, + "step": 424448 + }, + { + "epoch": 0.01, + "learning_rate": 4.304249709931386e-05, + "loss": 3.7404, + "step": 424960 + }, + { + "epoch": 0.01, + "learning_rate": 4.303412753060707e-05, + "loss": 3.7584, + "step": 425472 + }, + { + "epoch": 0.01, + "learning_rate": 4.302574158309655e-05, + "loss": 3.7591, + "step": 425984 + }, + { + "epoch": 0.01, + "learning_rate": 4.3017355635586035e-05, + "loss": 3.7626, + "step": 426496 + }, + { + "epoch": 0.01, + "learning_rate": 4.3008969688075515e-05, + "loss": 3.7622, + "step": 427008 + }, + { + "epoch": 0.02, + "learning_rate": 4.3000600119368724e-05, + "loss": 3.7693, + "step": 427520 + }, + { + "epoch": 0.02, + "learning_rate": 4.2992214171858204e-05, + "loss": 3.7476, + "step": 428032 + }, + { + "epoch": 0.02, + "learning_rate": 4.2983828224347684e-05, + "loss": 3.7598, + "step": 428544 + }, + { + "epoch": 0.02, + "learning_rate": 4.2975442276837164e-05, + "loss": 3.7616, + "step": 429056 + }, + { + "epoch": 0.02, + "learning_rate": 4.2967056329326644e-05, + "loss": 3.7537, + "step": 429568 + }, + { + "epoch": 0.02, + "learning_rate": 4.2958670381816124e-05, + "loss": 3.7505, + "step": 430080 + }, + { + "epoch": 0.02, + "learning_rate": 4.295030081310933e-05, + "loss": 3.7695, + "step": 430592 + }, + { + "epoch": 0.02, + "learning_rate": 4.294191486559881e-05, + "loss": 3.7637, + "step": 431104 + }, + { + "epoch": 0.02, + "learning_rate": 4.293352891808829e-05, + "loss": 3.775, + "step": 431616 + }, + { + "epoch": 0.02, + "learning_rate": 4.292514297057777e-05, + "loss": 3.7561, + "step": 432128 + }, + { + "epoch": 0.02, + "learning_rate": 4.291675702306725e-05, + "loss": 3.7597, + "step": 432640 + }, + { + "epoch": 0.02, + "learning_rate": 4.290837107555673e-05, + "loss": 3.748, + "step": 433152 + }, + { + "epoch": 0.02, + "learning_rate": 4.289998512804622e-05, + "loss": 3.7637, + "step": 433664 + }, + { + "epoch": 0.02, + "learning_rate": 4.28915991805357e-05, + "loss": 3.7693, + "step": 434176 + }, + { + "epoch": 0.02, + "learning_rate": 4.288322961182891e-05, + "loss": 3.7573, + "step": 434688 + }, + { + "epoch": 0.02, + "learning_rate": 4.287484366431839e-05, + "loss": 3.768, + "step": 435200 + }, + { + "epoch": 0.02, + "learning_rate": 4.286645771680787e-05, + "loss": 3.7416, + "step": 435712 + }, + { + "epoch": 0.02, + "learning_rate": 4.285807176929734e-05, + "loss": 3.748, + "step": 436224 + }, + { + "epoch": 0.02, + "learning_rate": 4.284970220059056e-05, + "loss": 3.7461, + "step": 436736 + }, + { + "epoch": 0.02, + "learning_rate": 4.284133263188377e-05, + "loss": 3.7528, + "step": 437248 + }, + { + "epoch": 0.02, + "learning_rate": 4.2832946684373247e-05, + "loss": 3.7636, + "step": 437760 + }, + { + "epoch": 0.02, + "learning_rate": 4.2824560736862727e-05, + "loss": 3.7598, + "step": 438272 + }, + { + "epoch": 0.02, + "learning_rate": 4.2816174789352207e-05, + "loss": 3.7348, + "step": 438784 + }, + { + "epoch": 0.02, + "learning_rate": 4.2807788841841686e-05, + "loss": 3.7588, + "step": 439296 + }, + { + "epoch": 0.02, + "learning_rate": 4.27994192731349e-05, + "loss": 3.7647, + "step": 439808 + }, + { + "epoch": 0.02, + "learning_rate": 4.279103332562438e-05, + "loss": 3.7623, + "step": 440320 + }, + { + "epoch": 0.02, + "learning_rate": 4.278264737811386e-05, + "loss": 3.7604, + "step": 440832 + }, + { + "epoch": 0.02, + "learning_rate": 4.277426143060334e-05, + "loss": 3.7508, + "step": 441344 + }, + { + "epoch": 0.02, + "learning_rate": 4.2765875483092815e-05, + "loss": 3.7485, + "step": 441856 + }, + { + "epoch": 0.02, + "learning_rate": 4.2757489535582295e-05, + "loss": 3.7668, + "step": 442368 + }, + { + "epoch": 0.02, + "learning_rate": 4.2749103588071775e-05, + "loss": 3.7489, + "step": 442880 + }, + { + "epoch": 0.02, + "learning_rate": 4.2740717640561255e-05, + "loss": 3.7477, + "step": 443392 + }, + { + "epoch": 0.02, + "learning_rate": 4.2732348071854464e-05, + "loss": 3.7433, + "step": 443904 + }, + { + "epoch": 0.02, + "learning_rate": 4.2723962124343944e-05, + "loss": 3.7462, + "step": 444416 + }, + { + "epoch": 0.02, + "learning_rate": 4.2715576176833424e-05, + "loss": 3.7541, + "step": 444928 + }, + { + "epoch": 0.02, + "learning_rate": 4.270720660812664e-05, + "loss": 3.7538, + "step": 445440 + }, + { + "epoch": 0.02, + "learning_rate": 4.269882066061612e-05, + "loss": 3.7623, + "step": 445952 + }, + { + "epoch": 0.02, + "learning_rate": 4.26904347131056e-05, + "loss": 3.7474, + "step": 446464 + }, + { + "epoch": 0.02, + "learning_rate": 4.268204876559508e-05, + "loss": 3.747, + "step": 446976 + }, + { + "epoch": 0.02, + "learning_rate": 4.267367919688829e-05, + "loss": 3.7663, + "step": 447488 + }, + { + "epoch": 0.02, + "learning_rate": 4.266529324937777e-05, + "loss": 3.7493, + "step": 448000 + }, + { + "epoch": 0.02, + "learning_rate": 4.265690730186725e-05, + "loss": 3.7557, + "step": 448512 + }, + { + "epoch": 0.02, + "learning_rate": 4.264852135435673e-05, + "loss": 3.7604, + "step": 449024 + }, + { + "epoch": 0.02, + "learning_rate": 4.264015178564994e-05, + "loss": 3.763, + "step": 449536 + }, + { + "epoch": 0.02, + "learning_rate": 4.263176583813942e-05, + "loss": 3.7606, + "step": 450048 + }, + { + "epoch": 0.02, + "learning_rate": 4.26233798906289e-05, + "loss": 3.7474, + "step": 450560 + }, + { + "epoch": 0.02, + "learning_rate": 4.261499394311838e-05, + "loss": 3.7408, + "step": 451072 + }, + { + "epoch": 0.02, + "learning_rate": 4.2606624374411594e-05, + "loss": 3.75, + "step": 451584 + }, + { + "epoch": 0.02, + "learning_rate": 4.2598238426901074e-05, + "loss": 3.7551, + "step": 452096 + }, + { + "epoch": 0.02, + "learning_rate": 4.2589852479390554e-05, + "loss": 3.7614, + "step": 452608 + }, + { + "epoch": 0.02, + "learning_rate": 4.2581466531880034e-05, + "loss": 3.7559, + "step": 453120 + }, + { + "epoch": 0.02, + "learning_rate": 4.257309696317324e-05, + "loss": 3.7549, + "step": 453632 + }, + { + "epoch": 0.02, + "learning_rate": 4.256471101566272e-05, + "loss": 3.752, + "step": 454144 + }, + { + "epoch": 0.02, + "learning_rate": 4.25563250681522e-05, + "loss": 3.7518, + "step": 454656 + }, + { + "epoch": 0.02, + "learning_rate": 4.254793912064168e-05, + "loss": 3.7413, + "step": 455168 + }, + { + "epoch": 0.02, + "learning_rate": 4.253956955193489e-05, + "loss": 3.7481, + "step": 455680 + }, + { + "epoch": 0.02, + "learning_rate": 4.253118360442437e-05, + "loss": 3.7607, + "step": 456192 + }, + { + "epoch": 0.02, + "learning_rate": 4.252279765691385e-05, + "loss": 3.7608, + "step": 456704 + }, + { + "epoch": 0.02, + "learning_rate": 4.251441170940333e-05, + "loss": 3.7444, + "step": 457216 + }, + { + "epoch": 0.02, + "learning_rate": 4.250604214069655e-05, + "loss": 3.7434, + "step": 457728 + }, + { + "epoch": 0.03, + "eval_loss": 3.867556095123291, + "eval_runtime": 550.8728, + "eval_samples_per_second": 692.703, + "eval_steps_per_second": 21.647, + "step": 457914 + }, + { + "epoch": 0.0, + "learning_rate": 4.249767257198976e-05, + "loss": 3.7619, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.2489286624479237e-05, + "loss": 3.7493, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.2480900676968716e-05, + "loss": 3.7432, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.2472514729458196e-05, + "loss": 3.7467, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.2464128781947676e-05, + "loss": 3.7424, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.2455742834437156e-05, + "loss": 3.7358, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.2447356886926636e-05, + "loss": 3.7354, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.2438970939416116e-05, + "loss": 3.7401, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.2430601370709325e-05, + "loss": 3.7466, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.2422215423198805e-05, + "loss": 3.7471, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.241384585449202e-05, + "loss": 3.7459, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.24054599069815e-05, + "loss": 3.7376, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.239707395947098e-05, + "loss": 3.7508, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.238868801196046e-05, + "loss": 3.7457, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.238031844325367e-05, + "loss": 3.7429, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.237193249574315e-05, + "loss": 3.7285, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.236354654823263e-05, + "loss": 3.7312, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.235516060072211e-05, + "loss": 3.7465, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.234677465321159e-05, + "loss": 3.7388, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233838870570107e-05, + "loss": 3.7533, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.233000275819055e-05, + "loss": 3.7374, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232161681068003e-05, + "loss": 3.7484, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.231324724197324e-05, + "loss": 3.7429, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.2304877673266455e-05, + "loss": 3.7402, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.2296491725755935e-05, + "loss": 3.7395, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.2288105778245415e-05, + "loss": 3.7375, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.2279719830734895e-05, + "loss": 3.7467, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.2271350262028104e-05, + "loss": 3.7304, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.2262964314517584e-05, + "loss": 3.7463, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.2254578367007064e-05, + "loss": 3.736, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.2246192419496544e-05, + "loss": 3.7251, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.2237806471986024e-05, + "loss": 3.7397, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.2229420524475504e-05, + "loss": 3.7437, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.2221034576964983e-05, + "loss": 3.7461, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.2212648629454463e-05, + "loss": 3.734, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.220427906074767e-05, + "loss": 3.7396, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.219589311323716e-05, + "loss": 3.7378, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.218750716572664e-05, + "loss": 3.7472, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.217912121821612e-05, + "loss": 3.7388, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.217075164950933e-05, + "loss": 3.721, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.216238208080254e-05, + "loss": 3.73, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.215399613329202e-05, + "loss": 3.7251, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.21456101857815e-05, + "loss": 3.7466, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.213722423827098e-05, + "loss": 3.7343, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.212883829076046e-05, + "loss": 3.7351, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.212045234324994e-05, + "loss": 3.7408, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.211206639573942e-05, + "loss": 3.7302, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.21036804482289e-05, + "loss": 3.7433, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209531087952211e-05, + "loss": 3.7253, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208692493201159e-05, + "loss": 3.7164, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.207853898450107e-05, + "loss": 3.7327, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.2070153036990546e-05, + "loss": 3.7253, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.206178346828376e-05, + "loss": 3.7311, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.205339752077324e-05, + "loss": 3.7321, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.204501157326272e-05, + "loss": 3.7214, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.2036625625752195e-05, + "loss": 3.721, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.2028239678241675e-05, + "loss": 3.7252, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.201987010953489e-05, + "loss": 3.7246, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.2011484162024364e-05, + "loss": 3.7349, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.200309821451385e-05, + "loss": 3.7251, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.199471226700333e-05, + "loss": 3.7161, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.198632631949281e-05, + "loss": 3.7243, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.197794037198229e-05, + "loss": 3.7111, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.196955442447177e-05, + "loss": 3.7401, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.196116847696125e-05, + "loss": 3.7205, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195279890825446e-05, + "loss": 3.7284, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.194441296074394e-05, + "loss": 3.7152, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.193602701323342e-05, + "loss": 3.7191, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.19276410657229e-05, + "loss": 3.7232, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.191925511821238e-05, + "loss": 3.7193, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.191086917070186e-05, + "loss": 3.7283, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.190248322319134e-05, + "loss": 3.7242, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.189411365448455e-05, + "loss": 3.7281, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.1885744085777764e-05, + "loss": 3.7386, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.1877358138267244e-05, + "loss": 3.7361, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.1868972190756724e-05, + "loss": 3.7358, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.1860586243246204e-05, + "loss": 3.7211, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.185221667453941e-05, + "loss": 3.7157, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.184383072702889e-05, + "loss": 3.7231, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.183544477951837e-05, + "loss": 3.7376, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.182705883200785e-05, + "loss": 3.7306, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.181867288449733e-05, + "loss": 3.7188, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.181028693698681e-05, + "loss": 3.7071, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.180190098947629e-05, + "loss": 3.7376, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.179351504196577e-05, + "loss": 3.7009, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.178514547325898e-05, + "loss": 3.7214, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.177675952574847e-05, + "loss": 3.7241, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.176837357823795e-05, + "loss": 3.7215, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.175998763072743e-05, + "loss": 3.7273, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.175161806202064e-05, + "loss": 3.7345, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.174323211451012e-05, + "loss": 3.7081, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.17348461669996e-05, + "loss": 3.7234, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.172646021948908e-05, + "loss": 3.7262, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.171807427197855e-05, + "loss": 3.7149, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170968832446803e-05, + "loss": 3.7136, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.170131875576125e-05, + "loss": 3.7321, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.169293280825073e-05, + "loss": 3.7259, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.1684546860740207e-05, + "loss": 3.7392, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.1676160913229687e-05, + "loss": 3.7167, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.1667774965719167e-05, + "loss": 3.7243, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.1659389018208646e-05, + "loss": 3.7096, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.1651003070698126e-05, + "loss": 3.7246, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.1642617123187606e-05, + "loss": 3.7322, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.163426393328455e-05, + "loss": 3.7248, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.1625877985774025e-05, + "loss": 3.7312, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.1617492038263505e-05, + "loss": 3.7058, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.1609106090752984e-05, + "loss": 3.7065, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.1600720143242464e-05, + "loss": 3.7077, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.1592350574535674e-05, + "loss": 3.717, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.158396462702516e-05, + "loss": 3.7246, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.157557867951464e-05, + "loss": 3.7251, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.156719273200412e-05, + "loss": 3.6969, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.15588067844936e-05, + "loss": 3.7203, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.155043721578681e-05, + "loss": 3.7279, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154205126827629e-05, + "loss": 3.7257, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153366532076577e-05, + "loss": 3.7245, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152527937325525e-05, + "loss": 3.7146, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151689342574473e-05, + "loss": 3.7151, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.150850747823421e-05, + "loss": 3.7247, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.150012153072369e-05, + "loss": 3.7171, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.14917519620169e-05, + "loss": 3.711, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.148336601450638e-05, + "loss": 3.7068, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.147498006699586e-05, + "loss": 3.7118, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.1466594119485345e-05, + "loss": 3.7212, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.1458224550778554e-05, + "loss": 3.7173, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.1449838603268034e-05, + "loss": 3.7239, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.1441452655757514e-05, + "loss": 3.7126, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.1433066708246994e-05, + "loss": 3.7093, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.14246971395402e-05, + "loss": 3.7308, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.141632757083341e-05, + "loss": 3.7094, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.140794162332289e-05, + "loss": 3.7223, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.139955567581237e-05, + "loss": 3.7269, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.139116972830185e-05, + "loss": 3.7237, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.138278378079133e-05, + "loss": 3.7248, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.137441421208455e-05, + "loss": 3.716, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.136602826457403e-05, + "loss": 3.703, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.135764231706351e-05, + "loss": 3.7133, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.134925636955299e-05, + "loss": 3.7155, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.1340886800846197e-05, + "loss": 3.729, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.1332500853335676e-05, + "loss": 3.7161, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.1324114905825156e-05, + "loss": 3.7223, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.1315728958314636e-05, + "loss": 3.714, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.1307343010804116e-05, + "loss": 3.7172, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.1298957063293596e-05, + "loss": 3.7049, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.1290571115783076e-05, + "loss": 3.714, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.1282201547076285e-05, + "loss": 3.728, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.1273815599565765e-05, + "loss": 3.7259, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.1265429652055245e-05, + "loss": 3.7052, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125704370454473e-05, + "loss": 3.7119, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 3.8561525344848633, + "eval_runtime": 588.1234, + "eval_samples_per_second": 648.828, + "eval_steps_per_second": 20.276, + "step": 534233 + }, + { + "epoch": 0.0, + "learning_rate": 4.124865775703421e-05, + "loss": 3.7309, + "step": 534528 + }, + { + "epoch": 0.0, + "learning_rate": 4.1240271809523685e-05, + "loss": 3.7137, + "step": 535040 + }, + { + "epoch": 0.0, + "learning_rate": 4.1231885862013165e-05, + "loss": 3.708, + "step": 535552 + }, + { + "epoch": 0.0, + "learning_rate": 4.1223499914502645e-05, + "loss": 3.7142, + "step": 536064 + }, + { + "epoch": 0.0, + "learning_rate": 4.121513034579586e-05, + "loss": 3.7038, + "step": 536576 + }, + { + "epoch": 0.0, + "learning_rate": 4.1206744398285334e-05, + "loss": 3.7061, + "step": 537088 + }, + { + "epoch": 0.0, + "learning_rate": 4.1198358450774814e-05, + "loss": 3.6959, + "step": 537600 + }, + { + "epoch": 0.0, + "learning_rate": 4.1189972503264294e-05, + "loss": 3.7078, + "step": 538112 + }, + { + "epoch": 0.0, + "learning_rate": 4.1181586555753774e-05, + "loss": 3.7068, + "step": 538624 + }, + { + "epoch": 0.0, + "learning_rate": 4.1173200608243254e-05, + "loss": 3.7118, + "step": 539136 + }, + { + "epoch": 0.0, + "learning_rate": 4.116483103953647e-05, + "loss": 3.7105, + "step": 539648 + }, + { + "epoch": 0.0, + "learning_rate": 4.115644509202595e-05, + "loss": 3.7045, + "step": 540160 + }, + { + "epoch": 0.0, + "learning_rate": 4.114805914451543e-05, + "loss": 3.7157, + "step": 540672 + }, + { + "epoch": 0.0, + "learning_rate": 4.113967319700491e-05, + "loss": 3.707, + "step": 541184 + }, + { + "epoch": 0.0, + "learning_rate": 4.113128724949439e-05, + "loss": 3.7146, + "step": 541696 + }, + { + "epoch": 0.0, + "learning_rate": 4.11229176807876e-05, + "loss": 3.6903, + "step": 542208 + }, + { + "epoch": 0.0, + "learning_rate": 4.111453173327708e-05, + "loss": 3.6993, + "step": 542720 + }, + { + "epoch": 0.0, + "learning_rate": 4.110614578576656e-05, + "loss": 3.7109, + "step": 543232 + }, + { + "epoch": 0.0, + "learning_rate": 4.109775983825604e-05, + "loss": 3.7026, + "step": 543744 + }, + { + "epoch": 0.0, + "learning_rate": 4.108937389074552e-05, + "loss": 3.72, + "step": 544256 + }, + { + "epoch": 0.0, + "learning_rate": 4.108100432203873e-05, + "loss": 3.7057, + "step": 544768 + }, + { + "epoch": 0.0, + "learning_rate": 4.107261837452821e-05, + "loss": 3.7112, + "step": 545280 + }, + { + "epoch": 0.0, + "learning_rate": 4.106423242701769e-05, + "loss": 3.7094, + "step": 545792 + }, + { + "epoch": 0.0, + "learning_rate": 4.105584647950717e-05, + "loss": 3.7036, + "step": 546304 + }, + { + "epoch": 0.0, + "learning_rate": 4.1047460531996654e-05, + "loss": 3.7087, + "step": 546816 + }, + { + "epoch": 0.0, + "learning_rate": 4.1039074584486134e-05, + "loss": 3.6992, + "step": 547328 + }, + { + "epoch": 0.0, + "learning_rate": 4.103070501577934e-05, + "loss": 3.7112, + "step": 547840 + }, + { + "epoch": 0.0, + "learning_rate": 4.102231906826882e-05, + "loss": 3.7024, + "step": 548352 + }, + { + "epoch": 0.0, + "learning_rate": 4.10139331207583e-05, + "loss": 3.7086, + "step": 548864 + }, + { + "epoch": 0.0, + "learning_rate": 4.100554717324778e-05, + "loss": 3.7015, + "step": 549376 + }, + { + "epoch": 0.01, + "learning_rate": 4.099716122573726e-05, + "loss": 3.6928, + "step": 549888 + }, + { + "epoch": 0.01, + "learning_rate": 4.098877527822674e-05, + "loss": 3.7054, + "step": 550400 + }, + { + "epoch": 0.01, + "learning_rate": 4.098038933071622e-05, + "loss": 3.7089, + "step": 550912 + }, + { + "epoch": 0.01, + "learning_rate": 4.0972003383205696e-05, + "loss": 3.71, + "step": 551424 + }, + { + "epoch": 0.01, + "learning_rate": 4.096363381449891e-05, + "loss": 3.7053, + "step": 551936 + }, + { + "epoch": 0.01, + "learning_rate": 4.095524786698839e-05, + "loss": 3.6999, + "step": 552448 + }, + { + "epoch": 0.01, + "learning_rate": 4.094687829828161e-05, + "loss": 3.7055, + "step": 552960 + }, + { + "epoch": 0.01, + "learning_rate": 4.093849235077109e-05, + "loss": 3.7126, + "step": 553472 + }, + { + "epoch": 0.01, + "learning_rate": 4.093010640326057e-05, + "loss": 3.7053, + "step": 553984 + }, + { + "epoch": 0.01, + "learning_rate": 4.092172045575005e-05, + "loss": 3.6913, + "step": 554496 + }, + { + "epoch": 0.01, + "learning_rate": 4.091333450823952e-05, + "loss": 3.6936, + "step": 555008 + }, + { + "epoch": 0.01, + "learning_rate": 4.090496493953274e-05, + "loss": 3.6943, + "step": 555520 + }, + { + "epoch": 0.01, + "learning_rate": 4.089657899202222e-05, + "loss": 3.7123, + "step": 556032 + }, + { + "epoch": 0.01, + "learning_rate": 4.08881930445117e-05, + "loss": 3.7009, + "step": 556544 + }, + { + "epoch": 0.01, + "learning_rate": 4.087980709700117e-05, + "loss": 3.6973, + "step": 557056 + }, + { + "epoch": 0.01, + "learning_rate": 4.0871437528294386e-05, + "loss": 3.7108, + "step": 557568 + }, + { + "epoch": 0.01, + "learning_rate": 4.0863051580783866e-05, + "loss": 3.6964, + "step": 558080 + }, + { + "epoch": 0.01, + "learning_rate": 4.0854665633273346e-05, + "loss": 3.7088, + "step": 558592 + }, + { + "epoch": 0.01, + "learning_rate": 4.0846279685762826e-05, + "loss": 3.6929, + "step": 559104 + }, + { + "epoch": 0.01, + "learning_rate": 4.0837893738252306e-05, + "loss": 3.6834, + "step": 559616 + }, + { + "epoch": 0.01, + "learning_rate": 4.0829507790741786e-05, + "loss": 3.6977, + "step": 560128 + }, + { + "epoch": 0.01, + "learning_rate": 4.0821138222034995e-05, + "loss": 3.6969, + "step": 560640 + }, + { + "epoch": 0.01, + "learning_rate": 4.0812752274524475e-05, + "loss": 3.6927, + "step": 561152 + }, + { + "epoch": 0.01, + "learning_rate": 4.0804366327013955e-05, + "loss": 3.7033, + "step": 561664 + }, + { + "epoch": 0.01, + "learning_rate": 4.0795980379503435e-05, + "loss": 3.6913, + "step": 562176 + }, + { + "epoch": 0.01, + "learning_rate": 4.0787610810796644e-05, + "loss": 3.6848, + "step": 562688 + }, + { + "epoch": 0.01, + "learning_rate": 4.0779224863286124e-05, + "loss": 3.6972, + "step": 563200 + }, + { + "epoch": 0.01, + "learning_rate": 4.0770838915775604e-05, + "loss": 3.6864, + "step": 563712 + }, + { + "epoch": 0.01, + "learning_rate": 4.0762452968265083e-05, + "loss": 3.7015, + "step": 564224 + }, + { + "epoch": 0.01, + "learning_rate": 4.0754067020754563e-05, + "loss": 3.6931, + "step": 564736 + }, + { + "epoch": 0.01, + "learning_rate": 4.074568107324404e-05, + "loss": 3.6875, + "step": 565248 + }, + { + "epoch": 0.01, + "learning_rate": 4.073731150453726e-05, + "loss": 3.689, + "step": 565760 + }, + { + "epoch": 0.01, + "learning_rate": 4.072892555702674e-05, + "loss": 3.6832, + "step": 566272 + }, + { + "epoch": 0.01, + "learning_rate": 4.072053960951622e-05, + "loss": 3.7047, + "step": 566784 + }, + { + "epoch": 0.01, + "learning_rate": 4.07121536620057e-05, + "loss": 3.686, + "step": 567296 + }, + { + "epoch": 0.01, + "learning_rate": 4.070378409329891e-05, + "loss": 3.6971, + "step": 567808 + }, + { + "epoch": 0.01, + "learning_rate": 4.069539814578839e-05, + "loss": 3.686, + "step": 568320 + }, + { + "epoch": 0.01, + "learning_rate": 4.068701219827787e-05, + "loss": 3.6869, + "step": 568832 + }, + { + "epoch": 0.01, + "learning_rate": 4.067862625076735e-05, + "loss": 3.6875, + "step": 569344 + }, + { + "epoch": 0.01, + "learning_rate": 4.067025668206056e-05, + "loss": 3.6881, + "step": 569856 + }, + { + "epoch": 0.01, + "learning_rate": 4.066187073455004e-05, + "loss": 3.6944, + "step": 570368 + }, + { + "epoch": 0.01, + "learning_rate": 4.065348478703952e-05, + "loss": 3.6914, + "step": 570880 + }, + { + "epoch": 0.01, + "learning_rate": 4.0645098839529e-05, + "loss": 3.697, + "step": 571392 + }, + { + "epoch": 0.01, + "learning_rate": 4.063671289201848e-05, + "loss": 3.708, + "step": 571904 + }, + { + "epoch": 0.01, + "learning_rate": 4.062834332331169e-05, + "loss": 3.7037, + "step": 572416 + }, + { + "epoch": 0.01, + "learning_rate": 4.061995737580117e-05, + "loss": 3.6975, + "step": 572928 + }, + { + "epoch": 0.01, + "learning_rate": 4.061157142829065e-05, + "loss": 3.6959, + "step": 573440 + }, + { + "epoch": 0.01, + "learning_rate": 4.060318548078013e-05, + "loss": 3.6777, + "step": 573952 + }, + { + "epoch": 0.01, + "learning_rate": 4.059479953326961e-05, + "loss": 3.6926, + "step": 574464 + }, + { + "epoch": 0.01, + "learning_rate": 4.058642996456282e-05, + "loss": 3.7062, + "step": 574976 + }, + { + "epoch": 0.01, + "learning_rate": 4.05780440170523e-05, + "loss": 3.6976, + "step": 575488 + }, + { + "epoch": 0.01, + "learning_rate": 4.056965806954178e-05, + "loss": 3.6934, + "step": 576000 + }, + { + "epoch": 0.01, + "learning_rate": 4.056127212203126e-05, + "loss": 3.6754, + "step": 576512 + }, + { + "epoch": 0.01, + "learning_rate": 4.055290255332447e-05, + "loss": 3.6995, + "step": 577024 + }, + { + "epoch": 0.01, + "learning_rate": 4.054451660581395e-05, + "loss": 3.6733, + "step": 577536 + }, + { + "epoch": 0.01, + "learning_rate": 4.053613065830343e-05, + "loss": 3.688, + "step": 578048 + }, + { + "epoch": 0.01, + "learning_rate": 4.052774471079292e-05, + "loss": 3.6873, + "step": 578560 + }, + { + "epoch": 0.01, + "learning_rate": 4.0519375142086127e-05, + "loss": 3.6909, + "step": 579072 + }, + { + "epoch": 0.01, + "learning_rate": 4.0510989194575606e-05, + "loss": 3.6981, + "step": 579584 + }, + { + "epoch": 0.02, + "learning_rate": 4.0502603247065086e-05, + "loss": 3.6969, + "step": 580096 + }, + { + "epoch": 0.02, + "learning_rate": 4.0494217299554566e-05, + "loss": 3.6794, + "step": 580608 + }, + { + "epoch": 0.02, + "learning_rate": 4.0485847730847775e-05, + "loss": 3.6952, + "step": 581120 + }, + { + "epoch": 0.02, + "learning_rate": 4.0477461783337255e-05, + "loss": 3.69, + "step": 581632 + }, + { + "epoch": 0.02, + "learning_rate": 4.0469075835826735e-05, + "loss": 3.6863, + "step": 582144 + }, + { + "epoch": 0.02, + "learning_rate": 4.0460689888316215e-05, + "loss": 3.6807, + "step": 582656 + }, + { + "epoch": 0.02, + "learning_rate": 4.0452303940805695e-05, + "loss": 3.6973, + "step": 583168 + }, + { + "epoch": 0.02, + "learning_rate": 4.0443934372098904e-05, + "loss": 3.6955, + "step": 583680 + }, + { + "epoch": 0.02, + "learning_rate": 4.0435548424588384e-05, + "loss": 3.707, + "step": 584192 + }, + { + "epoch": 0.02, + "learning_rate": 4.042716247707787e-05, + "loss": 3.6909, + "step": 584704 + }, + { + "epoch": 0.02, + "learning_rate": 4.041877652956735e-05, + "loss": 3.693, + "step": 585216 + }, + { + "epoch": 0.02, + "learning_rate": 4.041039058205683e-05, + "loss": 3.6794, + "step": 585728 + }, + { + "epoch": 0.02, + "learning_rate": 4.0402004634546304e-05, + "loss": 3.6942, + "step": 586240 + }, + { + "epoch": 0.02, + "learning_rate": 4.0393618687035784e-05, + "loss": 3.6971, + "step": 586752 + }, + { + "epoch": 0.02, + "learning_rate": 4.038526549713273e-05, + "loss": 3.6953, + "step": 587264 + }, + { + "epoch": 0.02, + "learning_rate": 4.037687954962221e-05, + "loss": 3.6956, + "step": 587776 + }, + { + "epoch": 0.02, + "learning_rate": 4.036849360211169e-05, + "loss": 3.6777, + "step": 588288 + }, + { + "epoch": 0.02, + "learning_rate": 4.036010765460117e-05, + "loss": 3.6755, + "step": 588800 + }, + { + "epoch": 0.02, + "learning_rate": 4.035172170709065e-05, + "loss": 3.6765, + "step": 589312 + }, + { + "epoch": 0.02, + "learning_rate": 4.034335213838386e-05, + "loss": 3.6848, + "step": 589824 + }, + { + "epoch": 0.02, + "learning_rate": 4.033496619087334e-05, + "loss": 3.6943, + "step": 590336 + }, + { + "epoch": 0.02, + "learning_rate": 4.0326580243362825e-05, + "loss": 3.6944, + "step": 590848 + }, + { + "epoch": 0.02, + "learning_rate": 4.0318194295852305e-05, + "loss": 3.663, + "step": 591360 + }, + { + "epoch": 0.02, + "learning_rate": 4.0309824727145514e-05, + "loss": 3.6944, + "step": 591872 + }, + { + "epoch": 0.02, + "learning_rate": 4.0301438779634994e-05, + "loss": 3.6972, + "step": 592384 + }, + { + "epoch": 0.02, + "learning_rate": 4.0293052832124474e-05, + "loss": 3.6931, + "step": 592896 + }, + { + "epoch": 0.02, + "learning_rate": 4.0284666884613954e-05, + "loss": 3.692, + "step": 593408 + }, + { + "epoch": 0.02, + "learning_rate": 4.027628093710343e-05, + "loss": 3.6882, + "step": 593920 + }, + { + "epoch": 0.02, + "learning_rate": 4.026791136839664e-05, + "loss": 3.6785, + "step": 594432 + }, + { + "epoch": 0.02, + "learning_rate": 4.025952542088612e-05, + "loss": 3.695, + "step": 594944 + }, + { + "epoch": 0.02, + "learning_rate": 4.0251139473375596e-05, + "loss": 3.6854, + "step": 595456 + }, + { + "epoch": 0.02, + "learning_rate": 4.0242753525865076e-05, + "loss": 3.6797, + "step": 595968 + }, + { + "epoch": 0.02, + "learning_rate": 4.023438395715829e-05, + "loss": 3.6727, + "step": 596480 + }, + { + "epoch": 0.02, + "learning_rate": 4.022599800964778e-05, + "loss": 3.6831, + "step": 596992 + }, + { + "epoch": 0.02, + "learning_rate": 4.021761206213725e-05, + "loss": 3.6866, + "step": 597504 + }, + { + "epoch": 0.02, + "learning_rate": 4.020922611462673e-05, + "loss": 3.6861, + "step": 598016 + }, + { + "epoch": 0.02, + "learning_rate": 4.020085654591995e-05, + "loss": 3.6968, + "step": 598528 + }, + { + "epoch": 0.02, + "learning_rate": 4.019247059840943e-05, + "loss": 3.6827, + "step": 599040 + }, + { + "epoch": 0.02, + "learning_rate": 4.01840846508989e-05, + "loss": 3.6797, + "step": 599552 + }, + { + "epoch": 0.02, + "learning_rate": 4.017569870338838e-05, + "loss": 3.7023, + "step": 600064 + }, + { + "epoch": 0.02, + "learning_rate": 4.0167329134681596e-05, + "loss": 3.679, + "step": 600576 + }, + { + "epoch": 0.02, + "learning_rate": 4.015894318717107e-05, + "loss": 3.6918, + "step": 601088 + }, + { + "epoch": 0.02, + "learning_rate": 4.015055723966055e-05, + "loss": 3.6956, + "step": 601600 + }, + { + "epoch": 0.02, + "learning_rate": 4.014217129215003e-05, + "loss": 3.6921, + "step": 602112 + }, + { + "epoch": 0.02, + "learning_rate": 4.0133801723443245e-05, + "loss": 3.6943, + "step": 602624 + }, + { + "epoch": 0.02, + "learning_rate": 4.0125415775932725e-05, + "loss": 3.6872, + "step": 603136 + }, + { + "epoch": 0.02, + "learning_rate": 4.0117029828422205e-05, + "loss": 3.6734, + "step": 603648 + }, + { + "epoch": 0.02, + "learning_rate": 4.0108643880911685e-05, + "loss": 3.6802, + "step": 604160 + }, + { + "epoch": 0.02, + "learning_rate": 4.0100257933401165e-05, + "loss": 3.6877, + "step": 604672 + }, + { + "epoch": 0.02, + "learning_rate": 4.0091888364694374e-05, + "loss": 3.6948, + "step": 605184 + }, + { + "epoch": 0.02, + "learning_rate": 4.0083502417183854e-05, + "loss": 3.6908, + "step": 605696 + }, + { + "epoch": 0.02, + "learning_rate": 4.0075116469673334e-05, + "loss": 3.6929, + "step": 606208 + }, + { + "epoch": 0.02, + "learning_rate": 4.0066730522162814e-05, + "loss": 3.6785, + "step": 606720 + }, + { + "epoch": 0.02, + "learning_rate": 4.0058344574652294e-05, + "loss": 3.6858, + "step": 607232 + }, + { + "epoch": 0.02, + "learning_rate": 4.0049958627141774e-05, + "loss": 3.6755, + "step": 607744 + }, + { + "epoch": 0.02, + "learning_rate": 4.0041572679631254e-05, + "loss": 3.6843, + "step": 608256 + }, + { + "epoch": 0.02, + "learning_rate": 4.003320311092447e-05, + "loss": 3.6957, + "step": 608768 + }, + { + "epoch": 0.02, + "learning_rate": 4.002481716341395e-05, + "loss": 3.6961, + "step": 609280 + }, + { + "epoch": 0.02, + "learning_rate": 4.001643121590343e-05, + "loss": 3.6739, + "step": 609792 + }, + { + "epoch": 0.02, + "learning_rate": 4.000804526839291e-05, + "loss": 3.6842, + "step": 610304 + }, + { + "epoch": 0.03, + "eval_loss": 3.849558115005493, + "eval_runtime": 577.8869, + "eval_samples_per_second": 660.321, + "eval_steps_per_second": 20.636, + "step": 610552 + }, + { + "epoch": 0.0, + "learning_rate": 3.999965932088239e-05, + "loss": 3.6999, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.999127337337187e-05, + "loss": 3.6863, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.998288742586135e-05, + "loss": 3.6796, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.997450147835083e-05, + "loss": 3.6842, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.996613190964404e-05, + "loss": 3.6715, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.995774596213352e-05, + "loss": 3.6751, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.9949360014623e-05, + "loss": 3.6731, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.994097406711248e-05, + "loss": 3.6727, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.993258811960196e-05, + "loss": 3.6761, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.992421855089517e-05, + "loss": 3.684, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.991583260338465e-05, + "loss": 3.6795, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.9907446655874134e-05, + "loss": 3.6772, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.9899060708363614e-05, + "loss": 3.687, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.989069113965682e-05, + "loss": 3.6724, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.98823051921463e-05, + "loss": 3.6869, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.987391924463578e-05, + "loss": 3.6622, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.9865533297125256e-05, + "loss": 3.6679, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.9857147349614736e-05, + "loss": 3.6808, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.984877778090795e-05, + "loss": 3.6744, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.984039183339743e-05, + "loss": 3.6899, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.9832005885886905e-05, + "loss": 3.6764, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.9823619938376385e-05, + "loss": 3.6798, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.98152503696696e-05, + "loss": 3.681, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.980686442215909e-05, + "loss": 3.6737, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.979847847464856e-05, + "loss": 3.6805, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.979009252713804e-05, + "loss": 3.672, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.978172295843126e-05, + "loss": 3.6819, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.977333701092073e-05, + "loss": 3.6701, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.976495106341021e-05, + "loss": 3.6829, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.975656511589969e-05, + "loss": 3.6692, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.9748195547192906e-05, + "loss": 3.6636, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.973980959968238e-05, + "loss": 3.6769, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.973142365217186e-05, + "loss": 3.6795, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.972303770466134e-05, + "loss": 3.681, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.9714651757150826e-05, + "loss": 3.675, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.9706282188444035e-05, + "loss": 3.6752, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.9697896240933515e-05, + "loss": 3.6734, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.9689510293422995e-05, + "loss": 3.6824, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.9681124345912475e-05, + "loss": 3.6778, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.9672754777205684e-05, + "loss": 3.6633, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.9664368829695164e-05, + "loss": 3.6645, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.9655982882184644e-05, + "loss": 3.663, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.9647596934674124e-05, + "loss": 3.6824, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.9639210987163604e-05, + "loss": 3.6772, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.9630825039653084e-05, + "loss": 3.6662, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.962245547094629e-05, + "loss": 3.6839, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.961406952343578e-05, + "loss": 3.6653, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.960568357592526e-05, + "loss": 3.68, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.959729762841474e-05, + "loss": 3.6681, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958892805970795e-05, + "loss": 3.6576, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.958054211219743e-05, + "loss": 3.6673, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.957215616468691e-05, + "loss": 3.6656, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.956377021717639e-05, + "loss": 3.6733, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.955538426966587e-05, + "loss": 3.6668, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.954701470095908e-05, + "loss": 3.6657, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.953862875344856e-05, + "loss": 3.6556, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.953024280593804e-05, + "loss": 3.668, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.952185685842752e-05, + "loss": 3.6601, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.951348728972073e-05, + "loss": 3.6722, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.950510134221021e-05, + "loss": 3.6592, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.949671539469969e-05, + "loss": 3.6629, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.948832944718917e-05, + "loss": 3.6628, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.947995987848238e-05, + "loss": 3.6543, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.947157393097186e-05, + "loss": 3.6737, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.946318798346134e-05, + "loss": 3.6609, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.945480203595082e-05, + "loss": 3.6683, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.94464160884403e-05, + "loss": 3.66, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.943804651973351e-05, + "loss": 3.656, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.942966057222299e-05, + "loss": 3.6595, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.942127462471247e-05, + "loss": 3.6604, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.941288867720195e-05, + "loss": 3.6653, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.940450272969143e-05, + "loss": 3.6657, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.939613316098465e-05, + "loss": 3.6661, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.9387747213474127e-05, + "loss": 3.6849, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.9379361265963607e-05, + "loss": 3.6748, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.9370975318453086e-05, + "loss": 3.6682, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.9362605749746296e-05, + "loss": 3.6665, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.9354219802235776e-05, + "loss": 3.6526, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.9345833854725256e-05, + "loss": 3.662, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.9337447907214735e-05, + "loss": 3.6761, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.9329061959704215e-05, + "loss": 3.6744, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.9320692390997425e-05, + "loss": 3.6624, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.9312306443486904e-05, + "loss": 3.6495, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.9303920495976384e-05, + "loss": 3.6705, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.9295534548465864e-05, + "loss": 3.6439, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.928716497975908e-05, + "loss": 3.6617, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.927877903224856e-05, + "loss": 3.6606, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.927039308473804e-05, + "loss": 3.6598, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.926200713722751e-05, + "loss": 3.6729, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925362118971699e-05, + "loss": 3.6702, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.924525162101021e-05, + "loss": 3.6553, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923686567349969e-05, + "loss": 3.6619, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.922847972598916e-05, + "loss": 3.6643, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.922009377847864e-05, + "loss": 3.6594, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.921172420977186e-05, + "loss": 3.6565, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.920333826226134e-05, + "loss": 3.6656, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.919495231475082e-05, + "loss": 3.6715, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.91865663672403e-05, + "loss": 3.6821, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.9178196798533514e-05, + "loss": 3.66, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.916981085102299e-05, + "loss": 3.6653, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.916142490351247e-05, + "loss": 3.6553, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.915303895600195e-05, + "loss": 3.6634, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.914465300849143e-05, + "loss": 3.6717, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.9136283439784636e-05, + "loss": 3.6674, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.9127897492274116e-05, + "loss": 3.6726, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.9119511544763596e-05, + "loss": 3.6485, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.9111125597253076e-05, + "loss": 3.6526, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.9102739649742556e-05, + "loss": 3.6492, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.909437008103577e-05, + "loss": 3.6592, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.908598413352525e-05, + "loss": 3.6619, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.907759818601473e-05, + "loss": 3.6677, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.906921223850421e-05, + "loss": 3.6362, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.906084266979742e-05, + "loss": 3.6665, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.90524567222869e-05, + "loss": 3.6696, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.904407077477638e-05, + "loss": 3.6637, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.903568482726586e-05, + "loss": 3.6659, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.902729887975534e-05, + "loss": 3.6649, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.901892931104855e-05, + "loss": 3.6502, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.901054336353803e-05, + "loss": 3.6679, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.900215741602751e-05, + "loss": 3.6655, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.8993771468516996e-05, + "loss": 3.6498, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.8985401899810205e-05, + "loss": 3.6496, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.8977015952299685e-05, + "loss": 3.6558, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.8968630004789165e-05, + "loss": 3.6597, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.8960244057278645e-05, + "loss": 3.6565, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.8951858109768125e-05, + "loss": 3.6676, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.8943488541061334e-05, + "loss": 3.6603, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.8935102593550814e-05, + "loss": 3.6491, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.8926716646040294e-05, + "loss": 3.6765, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.8918330698529774e-05, + "loss": 3.6514, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.890996112982298e-05, + "loss": 3.6629, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.890157518231246e-05, + "loss": 3.6735, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.889318923480195e-05, + "loss": 3.6646, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.888480328729143e-05, + "loss": 3.6668, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.887643371858464e-05, + "loss": 3.6625, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.886804777107412e-05, + "loss": 3.6468, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.88596618235636e-05, + "loss": 3.6569, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.885127587605308e-05, + "loss": 3.6579, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.884290630734629e-05, + "loss": 3.6698, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.883452035983577e-05, + "loss": 3.6632, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.882613441232525e-05, + "loss": 3.6638, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.881774846481473e-05, + "loss": 3.6593, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.880937889610794e-05, + "loss": 3.6566, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.880099294859742e-05, + "loss": 3.6482, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.8792607001086904e-05, + "loss": 3.6583, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.8784221053576384e-05, + "loss": 3.67, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.877585148486959e-05, + "loss": 3.6714, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.876746553735907e-05, + "loss": 3.6504, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.875907958984855e-05, + "loss": 3.6538, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 3.8449654579162598, + "eval_runtime": 315.7226, + "eval_samples_per_second": 1208.628, + "eval_steps_per_second": 37.771, + "step": 686871 + }, + { + "epoch": 0.0, + "learning_rate": 3.875069364233803e-05, + "loss": 3.6705, + "step": 687104 + }, + { + "epoch": 0.0, + "learning_rate": 3.874230769482751e-05, + "loss": 3.6799, + "step": 687616 + }, + { + "epoch": 0.0, + "learning_rate": 3.873392174731699e-05, + "loss": 3.6526, + "step": 688128 + }, + { + "epoch": 0.0, + "learning_rate": 3.8725535799806466e-05, + "loss": 3.6429, + "step": 688640 + }, + { + "epoch": 0.0, + "learning_rate": 3.871716623109968e-05, + "loss": 3.6634, + "step": 689152 + }, + { + "epoch": 0.0, + "learning_rate": 3.870878028358916e-05, + "loss": 3.6561, + "step": 689664 + }, + { + "epoch": 0.0, + "learning_rate": 3.870039433607864e-05, + "loss": 3.6652, + "step": 690176 + }, + { + "epoch": 0.0, + "learning_rate": 3.869200838856812e-05, + "loss": 3.653, + "step": 690688 + }, + { + "epoch": 0.0, + "learning_rate": 3.868363881986134e-05, + "loss": 3.6474, + "step": 691200 + }, + { + "epoch": 0.0, + "learning_rate": 3.867525287235082e-05, + "loss": 3.6523, + "step": 691712 + }, + { + "epoch": 0.0, + "learning_rate": 3.86668669248403e-05, + "loss": 3.6672, + "step": 692224 + }, + { + "epoch": 0.0, + "learning_rate": 3.865848097732977e-05, + "loss": 3.6601, + "step": 692736 + }, + { + "epoch": 0.0, + "learning_rate": 3.865009502981925e-05, + "loss": 3.668, + "step": 693248 + }, + { + "epoch": 0.0, + "learning_rate": 3.8641725461112466e-05, + "loss": 3.6611, + "step": 693760 + }, + { + "epoch": 0.0, + "learning_rate": 3.863333951360194e-05, + "loss": 3.6632, + "step": 694272 + }, + { + "epoch": 0.0, + "learning_rate": 3.862495356609142e-05, + "loss": 3.6558, + "step": 694784 + }, + { + "epoch": 0.0, + "learning_rate": 3.86165676185809e-05, + "loss": 3.6671, + "step": 695296 + }, + { + "epoch": 0.0, + "learning_rate": 3.8608198049874115e-05, + "loss": 3.6557, + "step": 695808 + }, + { + "epoch": 0.0, + "learning_rate": 3.8599812102363595e-05, + "loss": 3.6556, + "step": 696320 + }, + { + "epoch": 0.0, + "learning_rate": 3.8591426154853075e-05, + "loss": 3.6791, + "step": 696832 + }, + { + "epoch": 0.0, + "learning_rate": 3.8583040207342555e-05, + "loss": 3.6713, + "step": 697344 + }, + { + "epoch": 0.0, + "learning_rate": 3.857467063863577e-05, + "loss": 3.6621, + "step": 697856 + }, + { + "epoch": 0.0, + "learning_rate": 3.8566284691125244e-05, + "loss": 3.6618, + "step": 698368 + }, + { + "epoch": 0.0, + "learning_rate": 3.8557898743614724e-05, + "loss": 3.6531, + "step": 698880 + }, + { + "epoch": 0.0, + "learning_rate": 3.8549512796104204e-05, + "loss": 3.6653, + "step": 699392 + }, + { + "epoch": 0.0, + "learning_rate": 3.8541126848593684e-05, + "loss": 3.6378, + "step": 699904 + }, + { + "epoch": 0.0, + "learning_rate": 3.853275727988689e-05, + "loss": 3.6625, + "step": 700416 + }, + { + "epoch": 0.0, + "learning_rate": 3.852437133237637e-05, + "loss": 3.6478, + "step": 700928 + }, + { + "epoch": 0.0, + "learning_rate": 3.851598538486585e-05, + "loss": 3.657, + "step": 701440 + }, + { + "epoch": 0.0, + "learning_rate": 3.850759943735533e-05, + "loss": 3.6662, + "step": 701952 + }, + { + "epoch": 0.01, + "learning_rate": 3.849921348984481e-05, + "loss": 3.6627, + "step": 702464 + }, + { + "epoch": 0.01, + "learning_rate": 3.849084392113803e-05, + "loss": 3.6556, + "step": 702976 + }, + { + "epoch": 0.01, + "learning_rate": 3.848245797362751e-05, + "loss": 3.6496, + "step": 703488 + }, + { + "epoch": 0.01, + "learning_rate": 3.847407202611699e-05, + "loss": 3.67, + "step": 704000 + }, + { + "epoch": 0.01, + "learning_rate": 3.846568607860647e-05, + "loss": 3.6549, + "step": 704512 + }, + { + "epoch": 0.01, + "learning_rate": 3.845731650989968e-05, + "loss": 3.6529, + "step": 705024 + }, + { + "epoch": 0.01, + "learning_rate": 3.844893056238916e-05, + "loss": 3.6529, + "step": 705536 + }, + { + "epoch": 0.01, + "learning_rate": 3.844054461487864e-05, + "loss": 3.6649, + "step": 706048 + }, + { + "epoch": 0.01, + "learning_rate": 3.843215866736812e-05, + "loss": 3.6752, + "step": 706560 + }, + { + "epoch": 0.01, + "learning_rate": 3.8423789098661327e-05, + "loss": 3.6708, + "step": 707072 + }, + { + "epoch": 0.01, + "learning_rate": 3.8415403151150807e-05, + "loss": 3.6546, + "step": 707584 + }, + { + "epoch": 0.01, + "learning_rate": 3.8407017203640286e-05, + "loss": 3.6612, + "step": 708096 + }, + { + "epoch": 0.01, + "learning_rate": 3.8398631256129766e-05, + "loss": 3.6504, + "step": 708608 + }, + { + "epoch": 0.01, + "learning_rate": 3.8390245308619246e-05, + "loss": 3.6513, + "step": 709120 + }, + { + "epoch": 0.01, + "learning_rate": 3.8381859361108726e-05, + "loss": 3.6459, + "step": 709632 + }, + { + "epoch": 0.01, + "learning_rate": 3.837348979240194e-05, + "loss": 3.6424, + "step": 710144 + }, + { + "epoch": 0.01, + "learning_rate": 3.836510384489142e-05, + "loss": 3.6482, + "step": 710656 + }, + { + "epoch": 0.01, + "learning_rate": 3.83567178973809e-05, + "loss": 3.645, + "step": 711168 + }, + { + "epoch": 0.01, + "learning_rate": 3.834833194987038e-05, + "loss": 3.6552, + "step": 711680 + }, + { + "epoch": 0.01, + "learning_rate": 3.833996238116359e-05, + "loss": 3.6515, + "step": 712192 + }, + { + "epoch": 0.01, + "learning_rate": 3.833157643365307e-05, + "loss": 3.6471, + "step": 712704 + }, + { + "epoch": 0.01, + "learning_rate": 3.832319048614255e-05, + "loss": 3.6557, + "step": 713216 + }, + { + "epoch": 0.01, + "learning_rate": 3.831480453863203e-05, + "loss": 3.6444, + "step": 713728 + }, + { + "epoch": 0.01, + "learning_rate": 3.830641859112151e-05, + "loss": 3.6393, + "step": 714240 + }, + { + "epoch": 0.01, + "learning_rate": 3.829804902241472e-05, + "loss": 3.6376, + "step": 714752 + }, + { + "epoch": 0.01, + "learning_rate": 3.82896630749042e-05, + "loss": 3.6551, + "step": 715264 + }, + { + "epoch": 0.01, + "learning_rate": 3.828127712739368e-05, + "loss": 3.6595, + "step": 715776 + }, + { + "epoch": 0.01, + "learning_rate": 3.827289117988317e-05, + "loss": 3.6427, + "step": 716288 + }, + { + "epoch": 0.01, + "learning_rate": 3.8264521611176376e-05, + "loss": 3.6524, + "step": 716800 + }, + { + "epoch": 0.01, + "learning_rate": 3.8256135663665856e-05, + "loss": 3.6557, + "step": 717312 + }, + { + "epoch": 0.01, + "learning_rate": 3.8247749716155336e-05, + "loss": 3.6417, + "step": 717824 + }, + { + "epoch": 0.01, + "learning_rate": 3.8239363768644816e-05, + "loss": 3.649, + "step": 718336 + }, + { + "epoch": 0.01, + "learning_rate": 3.8230994199938025e-05, + "loss": 3.627, + "step": 718848 + }, + { + "epoch": 0.01, + "learning_rate": 3.8222608252427505e-05, + "loss": 3.6329, + "step": 719360 + }, + { + "epoch": 0.01, + "learning_rate": 3.8214222304916985e-05, + "loss": 3.6655, + "step": 719872 + }, + { + "epoch": 0.01, + "learning_rate": 3.8205836357406465e-05, + "loss": 3.6607, + "step": 720384 + }, + { + "epoch": 0.01, + "learning_rate": 3.8197466788699674e-05, + "loss": 3.6356, + "step": 720896 + }, + { + "epoch": 0.01, + "learning_rate": 3.8189080841189154e-05, + "loss": 3.6513, + "step": 721408 + }, + { + "epoch": 0.01, + "learning_rate": 3.8180694893678634e-05, + "loss": 3.6552, + "step": 721920 + }, + { + "epoch": 0.01, + "learning_rate": 3.817230894616812e-05, + "loss": 3.6395, + "step": 722432 + }, + { + "epoch": 0.01, + "learning_rate": 3.81639229986576e-05, + "loss": 3.656, + "step": 722944 + }, + { + "epoch": 0.01, + "learning_rate": 3.815555342995081e-05, + "loss": 3.6494, + "step": 723456 + }, + { + "epoch": 0.01, + "learning_rate": 3.814716748244029e-05, + "loss": 3.6459, + "step": 723968 + }, + { + "epoch": 0.01, + "learning_rate": 3.813878153492977e-05, + "loss": 3.6466, + "step": 724480 + }, + { + "epoch": 0.01, + "learning_rate": 3.813039558741925e-05, + "loss": 3.6606, + "step": 724992 + }, + { + "epoch": 0.01, + "learning_rate": 3.812202601871246e-05, + "loss": 3.6432, + "step": 725504 + }, + { + "epoch": 0.01, + "learning_rate": 3.811364007120194e-05, + "loss": 3.6571, + "step": 726016 + }, + { + "epoch": 0.01, + "learning_rate": 3.810525412369142e-05, + "loss": 3.6531, + "step": 726528 + }, + { + "epoch": 0.01, + "learning_rate": 3.80968681761809e-05, + "loss": 3.6414, + "step": 727040 + }, + { + "epoch": 0.01, + "learning_rate": 3.808848222867037e-05, + "loss": 3.6531, + "step": 727552 + }, + { + "epoch": 0.01, + "learning_rate": 3.808011265996359e-05, + "loss": 3.64, + "step": 728064 + }, + { + "epoch": 0.01, + "learning_rate": 3.8071726712453074e-05, + "loss": 3.6433, + "step": 728576 + }, + { + "epoch": 0.01, + "learning_rate": 3.806334076494255e-05, + "loss": 3.6467, + "step": 729088 + }, + { + "epoch": 0.01, + "learning_rate": 3.805495481743203e-05, + "loss": 3.6386, + "step": 729600 + }, + { + "epoch": 0.01, + "learning_rate": 3.804658524872524e-05, + "loss": 3.6295, + "step": 730112 + }, + { + "epoch": 0.01, + "learning_rate": 3.803819930121472e-05, + "loss": 3.6468, + "step": 730624 + }, + { + "epoch": 0.01, + "learning_rate": 3.8029813353704196e-05, + "loss": 3.6407, + "step": 731136 + }, + { + "epoch": 0.01, + "learning_rate": 3.8021427406193676e-05, + "loss": 3.6462, + "step": 731648 + }, + { + "epoch": 0.01, + "learning_rate": 3.801305783748689e-05, + "loss": 3.6343, + "step": 732160 + }, + { + "epoch": 0.02, + "learning_rate": 3.800467188997637e-05, + "loss": 3.6535, + "step": 732672 + }, + { + "epoch": 0.02, + "learning_rate": 3.7996285942465845e-05, + "loss": 3.6515, + "step": 733184 + }, + { + "epoch": 0.02, + "learning_rate": 3.7987899994955325e-05, + "loss": 3.6573, + "step": 733696 + }, + { + "epoch": 0.02, + "learning_rate": 3.797951404744481e-05, + "loss": 3.6546, + "step": 734208 + }, + { + "epoch": 0.02, + "learning_rate": 3.797114447873802e-05, + "loss": 3.6334, + "step": 734720 + }, + { + "epoch": 0.02, + "learning_rate": 3.79627585312275e-05, + "loss": 3.6563, + "step": 735232 + }, + { + "epoch": 0.02, + "learning_rate": 3.795437258371698e-05, + "loss": 3.6416, + "step": 735744 + }, + { + "epoch": 0.02, + "learning_rate": 3.794598663620646e-05, + "loss": 3.6499, + "step": 736256 + }, + { + "epoch": 0.02, + "learning_rate": 3.793761706749967e-05, + "loss": 3.6312, + "step": 736768 + }, + { + "epoch": 0.02, + "learning_rate": 3.792923111998915e-05, + "loss": 3.6537, + "step": 737280 + }, + { + "epoch": 0.02, + "learning_rate": 3.792084517247863e-05, + "loss": 3.6478, + "step": 737792 + }, + { + "epoch": 0.02, + "learning_rate": 3.791245922496811e-05, + "loss": 3.6433, + "step": 738304 + }, + { + "epoch": 0.02, + "learning_rate": 3.790407327745759e-05, + "loss": 3.654, + "step": 738816 + }, + { + "epoch": 0.02, + "learning_rate": 3.789568732994707e-05, + "loss": 3.6491, + "step": 739328 + }, + { + "epoch": 0.02, + "learning_rate": 3.788731776124028e-05, + "loss": 3.6442, + "step": 739840 + }, + { + "epoch": 0.02, + "learning_rate": 3.7878931813729766e-05, + "loss": 3.6315, + "step": 740352 + }, + { + "epoch": 0.02, + "learning_rate": 3.7870545866219246e-05, + "loss": 3.641, + "step": 740864 + }, + { + "epoch": 0.02, + "learning_rate": 3.7862159918708725e-05, + "loss": 3.6435, + "step": 741376 + }, + { + "epoch": 0.02, + "learning_rate": 3.7853790350001935e-05, + "loss": 3.6556, + "step": 741888 + }, + { + "epoch": 0.02, + "learning_rate": 3.7845404402491415e-05, + "loss": 3.6354, + "step": 742400 + }, + { + "epoch": 0.02, + "learning_rate": 3.7837018454980894e-05, + "loss": 3.6395, + "step": 742912 + }, + { + "epoch": 0.02, + "learning_rate": 3.7828632507470374e-05, + "loss": 3.6383, + "step": 743424 + }, + { + "epoch": 0.02, + "learning_rate": 3.7820262938763584e-05, + "loss": 3.6451, + "step": 743936 + }, + { + "epoch": 0.02, + "learning_rate": 3.7811876991253063e-05, + "loss": 3.6418, + "step": 744448 + }, + { + "epoch": 0.02, + "learning_rate": 3.7803491043742543e-05, + "loss": 3.6448, + "step": 744960 + }, + { + "epoch": 0.02, + "learning_rate": 3.7795105096232023e-05, + "loss": 3.6424, + "step": 745472 + }, + { + "epoch": 0.02, + "learning_rate": 3.77867191487215e-05, + "loss": 3.6339, + "step": 745984 + }, + { + "epoch": 0.02, + "learning_rate": 3.777834958001471e-05, + "loss": 3.6453, + "step": 746496 + }, + { + "epoch": 0.02, + "learning_rate": 3.77699636325042e-05, + "loss": 3.6418, + "step": 747008 + }, + { + "epoch": 0.02, + "learning_rate": 3.776157768499368e-05, + "loss": 3.6444, + "step": 747520 + }, + { + "epoch": 0.02, + "learning_rate": 3.775319173748316e-05, + "loss": 3.6414, + "step": 748032 + }, + { + "epoch": 0.02, + "learning_rate": 3.774482216877637e-05, + "loss": 3.6539, + "step": 748544 + }, + { + "epoch": 0.02, + "learning_rate": 3.773643622126585e-05, + "loss": 3.6575, + "step": 749056 + }, + { + "epoch": 0.02, + "learning_rate": 3.772805027375533e-05, + "loss": 3.6429, + "step": 749568 + }, + { + "epoch": 0.02, + "learning_rate": 3.771966432624481e-05, + "loss": 3.6419, + "step": 750080 + }, + { + "epoch": 0.02, + "learning_rate": 3.771129475753802e-05, + "loss": 3.6414, + "step": 750592 + }, + { + "epoch": 0.02, + "learning_rate": 3.77029088100275e-05, + "loss": 3.6329, + "step": 751104 + }, + { + "epoch": 0.02, + "learning_rate": 3.769452286251698e-05, + "loss": 3.6487, + "step": 751616 + }, + { + "epoch": 0.02, + "learning_rate": 3.768613691500646e-05, + "loss": 3.6489, + "step": 752128 + }, + { + "epoch": 0.02, + "learning_rate": 3.767775096749594e-05, + "loss": 3.638, + "step": 752640 + }, + { + "epoch": 0.02, + "learning_rate": 3.766938139878915e-05, + "loss": 3.6427, + "step": 753152 + }, + { + "epoch": 0.02, + "learning_rate": 3.766099545127863e-05, + "loss": 3.643, + "step": 753664 + }, + { + "epoch": 0.02, + "learning_rate": 3.765260950376811e-05, + "loss": 3.6479, + "step": 754176 + }, + { + "epoch": 0.02, + "learning_rate": 3.764422355625759e-05, + "loss": 3.6569, + "step": 754688 + }, + { + "epoch": 0.02, + "learning_rate": 3.76358539875508e-05, + "loss": 3.6525, + "step": 755200 + }, + { + "epoch": 0.02, + "learning_rate": 3.762746804004028e-05, + "loss": 3.6473, + "step": 755712 + }, + { + "epoch": 0.02, + "learning_rate": 3.761908209252976e-05, + "loss": 3.6403, + "step": 756224 + }, + { + "epoch": 0.02, + "learning_rate": 3.761069614501924e-05, + "loss": 3.6476, + "step": 756736 + }, + { + "epoch": 0.02, + "learning_rate": 3.760232657631245e-05, + "loss": 3.6508, + "step": 757248 + }, + { + "epoch": 0.02, + "learning_rate": 3.759394062880193e-05, + "loss": 3.6359, + "step": 757760 + }, + { + "epoch": 0.02, + "learning_rate": 3.758555468129141e-05, + "loss": 3.6422, + "step": 758272 + }, + { + "epoch": 0.02, + "learning_rate": 3.757716873378089e-05, + "loss": 3.6448, + "step": 758784 + }, + { + "epoch": 0.02, + "learning_rate": 3.7568799165074107e-05, + "loss": 3.6402, + "step": 759296 + }, + { + "epoch": 0.02, + "learning_rate": 3.7560413217563586e-05, + "loss": 3.6382, + "step": 759808 + }, + { + "epoch": 0.02, + "learning_rate": 3.7552027270053066e-05, + "loss": 3.6508, + "step": 760320 + }, + { + "epoch": 0.02, + "learning_rate": 3.7543641322542546e-05, + "loss": 3.6382, + "step": 760832 + }, + { + "epoch": 0.02, + "learning_rate": 3.7535271753835755e-05, + "loss": 3.6457, + "step": 761344 + }, + { + "epoch": 0.02, + "learning_rate": 3.7526885806325235e-05, + "loss": 3.6334, + "step": 761856 + }, + { + "epoch": 0.02, + "learning_rate": 3.7518499858814715e-05, + "loss": 3.6399, + "step": 762368 + }, + { + "epoch": 0.02, + "learning_rate": 3.7510113911304195e-05, + "loss": 3.6357, + "step": 762880 + }, + { + "epoch": 0.03, + "eval_loss": 3.8363986015319824, + "eval_runtime": 308.9163, + "eval_samples_per_second": 1235.257, + "eval_steps_per_second": 38.603, + "step": 763191 + }, + { + "epoch": 1.0, + "learning_rate": 3.7501744342597404e-05, + "loss": 3.646, + "step": 763392 + }, + { + "epoch": 1.0, + "learning_rate": 3.7493358395086884e-05, + "loss": 3.6587, + "step": 763904 + }, + { + "epoch": 1.0, + "learning_rate": 3.7484972447576364e-05, + "loss": 3.6289, + "step": 764416 + }, + { + "epoch": 1.0, + "learning_rate": 3.7476586500065844e-05, + "loss": 3.6155, + "step": 764928 + }, + { + "epoch": 1.0, + "learning_rate": 3.746821693135906e-05, + "loss": 3.6431, + "step": 765440 + }, + { + "epoch": 1.0, + "learning_rate": 3.745983098384854e-05, + "loss": 3.6304, + "step": 765952 + }, + { + "epoch": 1.0, + "learning_rate": 3.745144503633802e-05, + "loss": 3.6356, + "step": 766464 + }, + { + "epoch": 1.0, + "learning_rate": 3.74430590888275e-05, + "loss": 3.6323, + "step": 766976 + }, + { + "epoch": 1.0, + "learning_rate": 3.743468952012071e-05, + "loss": 3.6229, + "step": 767488 + }, + { + "epoch": 1.0, + "learning_rate": 3.742630357261019e-05, + "loss": 3.6219, + "step": 768000 + }, + { + "epoch": 1.0, + "learning_rate": 3.741791762509967e-05, + "loss": 3.6456, + "step": 768512 + }, + { + "epoch": 1.0, + "learning_rate": 3.740953167758915e-05, + "loss": 3.6322, + "step": 769024 + }, + { + "epoch": 1.0, + "learning_rate": 3.740114573007862e-05, + "loss": 3.6383, + "step": 769536 + }, + { + "epoch": 1.0, + "learning_rate": 3.739277616137184e-05, + "loss": 3.6318, + "step": 770048 + }, + { + "epoch": 1.0, + "learning_rate": 3.738439021386132e-05, + "loss": 3.6421, + "step": 770560 + }, + { + "epoch": 1.0, + "learning_rate": 3.73760042663508e-05, + "loss": 3.6281, + "step": 771072 + }, + { + "epoch": 1.0, + "learning_rate": 3.736761831884028e-05, + "loss": 3.6413, + "step": 771584 + }, + { + "epoch": 1.0, + "learning_rate": 3.7359248750133494e-05, + "loss": 3.6282, + "step": 772096 + }, + { + "epoch": 1.0, + "learning_rate": 3.7350862802622974e-05, + "loss": 3.6282, + "step": 772608 + }, + { + "epoch": 1.0, + "learning_rate": 3.7342476855112454e-05, + "loss": 3.6527, + "step": 773120 + }, + { + "epoch": 1.0, + "learning_rate": 3.733409090760193e-05, + "loss": 3.6466, + "step": 773632 + }, + { + "epoch": 1.0, + "learning_rate": 3.732572133889514e-05, + "loss": 3.6357, + "step": 774144 + }, + { + "epoch": 1.0, + "learning_rate": 3.731733539138462e-05, + "loss": 3.6353, + "step": 774656 + }, + { + "epoch": 1.0, + "learning_rate": 3.7308949443874096e-05, + "loss": 3.6306, + "step": 775168 + }, + { + "epoch": 1.0, + "learning_rate": 3.7300563496363576e-05, + "loss": 3.6407, + "step": 775680 + }, + { + "epoch": 1.0, + "learning_rate": 3.729219392765679e-05, + "loss": 3.6172, + "step": 776192 + }, + { + "epoch": 1.0, + "learning_rate": 3.728380798014627e-05, + "loss": 3.6302, + "step": 776704 + }, + { + "epoch": 1.0, + "learning_rate": 3.727542203263575e-05, + "loss": 3.628, + "step": 777216 + }, + { + "epoch": 1.0, + "learning_rate": 3.726703608512523e-05, + "loss": 3.6282, + "step": 777728 + }, + { + "epoch": 1.0, + "learning_rate": 3.725866651641845e-05, + "loss": 3.6413, + "step": 778240 + }, + { + "epoch": 1.01, + "learning_rate": 3.725028056890793e-05, + "loss": 3.6389, + "step": 778752 + }, + { + "epoch": 1.01, + "learning_rate": 3.72418946213974e-05, + "loss": 3.6287, + "step": 779264 + }, + { + "epoch": 1.01, + "learning_rate": 3.723350867388688e-05, + "loss": 3.6221, + "step": 779776 + }, + { + "epoch": 1.01, + "learning_rate": 3.7225139105180096e-05, + "loss": 3.6425, + "step": 780288 + }, + { + "epoch": 1.01, + "learning_rate": 3.721675315766957e-05, + "loss": 3.6281, + "step": 780800 + }, + { + "epoch": 1.01, + "learning_rate": 3.720836721015905e-05, + "loss": 3.6275, + "step": 781312 + }, + { + "epoch": 1.01, + "learning_rate": 3.719998126264853e-05, + "loss": 3.6263, + "step": 781824 + }, + { + "epoch": 1.01, + "learning_rate": 3.7191611693941745e-05, + "loss": 3.6374, + "step": 782336 + }, + { + "epoch": 1.01, + "learning_rate": 3.718322574643122e-05, + "loss": 3.6489, + "step": 782848 + }, + { + "epoch": 1.01, + "learning_rate": 3.7174839798920705e-05, + "loss": 3.6415, + "step": 783360 + }, + { + "epoch": 1.01, + "learning_rate": 3.7166453851410185e-05, + "loss": 3.6351, + "step": 783872 + }, + { + "epoch": 1.01, + "learning_rate": 3.71580842827034e-05, + "loss": 3.634, + "step": 784384 + }, + { + "epoch": 1.01, + "learning_rate": 3.7149698335192874e-05, + "loss": 3.6294, + "step": 784896 + }, + { + "epoch": 1.01, + "learning_rate": 3.7141312387682354e-05, + "loss": 3.6223, + "step": 785408 + }, + { + "epoch": 1.01, + "learning_rate": 3.7132926440171834e-05, + "loss": 3.6222, + "step": 785920 + }, + { + "epoch": 1.01, + "learning_rate": 3.7124540492661314e-05, + "loss": 3.6202, + "step": 786432 + }, + { + "epoch": 1.01, + "learning_rate": 3.711617092395452e-05, + "loss": 3.6239, + "step": 786944 + }, + { + "epoch": 1.01, + "learning_rate": 3.7107784976444e-05, + "loss": 3.6201, + "step": 787456 + }, + { + "epoch": 1.01, + "learning_rate": 3.709939902893348e-05, + "loss": 3.6276, + "step": 787968 + }, + { + "epoch": 1.01, + "learning_rate": 3.709101308142296e-05, + "loss": 3.6254, + "step": 788480 + }, + { + "epoch": 1.01, + "learning_rate": 3.708264351271617e-05, + "loss": 3.62, + "step": 788992 + }, + { + "epoch": 1.01, + "learning_rate": 3.707425756520566e-05, + "loss": 3.6274, + "step": 789504 + }, + { + "epoch": 1.01, + "learning_rate": 3.706587161769514e-05, + "loss": 3.6243, + "step": 790016 + }, + { + "epoch": 1.01, + "learning_rate": 3.705748567018462e-05, + "loss": 3.6113, + "step": 790528 + }, + { + "epoch": 1.01, + "learning_rate": 3.704911610147783e-05, + "loss": 3.6128, + "step": 791040 + }, + { + "epoch": 1.01, + "learning_rate": 3.704073015396731e-05, + "loss": 3.6305, + "step": 791552 + }, + { + "epoch": 1.01, + "learning_rate": 3.703234420645679e-05, + "loss": 3.6353, + "step": 792064 + }, + { + "epoch": 1.01, + "learning_rate": 3.702395825894627e-05, + "loss": 3.6149, + "step": 792576 + }, + { + "epoch": 1.01, + "learning_rate": 3.701558869023948e-05, + "loss": 3.6279, + "step": 793088 + }, + { + "epoch": 1.01, + "learning_rate": 3.700720274272896e-05, + "loss": 3.6332, + "step": 793600 + }, + { + "epoch": 1.01, + "learning_rate": 3.699881679521844e-05, + "loss": 3.6181, + "step": 794112 + }, + { + "epoch": 1.01, + "learning_rate": 3.699043084770792e-05, + "loss": 3.6212, + "step": 794624 + }, + { + "epoch": 1.01, + "learning_rate": 3.6982061279001126e-05, + "loss": 3.6057, + "step": 795136 + }, + { + "epoch": 1.01, + "learning_rate": 3.6973675331490606e-05, + "loss": 3.6107, + "step": 795648 + }, + { + "epoch": 1.01, + "learning_rate": 3.696528938398009e-05, + "loss": 3.6413, + "step": 796160 + }, + { + "epoch": 1.01, + "learning_rate": 3.695690343646957e-05, + "loss": 3.6362, + "step": 796672 + }, + { + "epoch": 1.01, + "learning_rate": 3.694853386776278e-05, + "loss": 3.6133, + "step": 797184 + }, + { + "epoch": 1.01, + "learning_rate": 3.694014792025226e-05, + "loss": 3.6245, + "step": 797696 + }, + { + "epoch": 1.01, + "learning_rate": 3.693176197274174e-05, + "loss": 3.6305, + "step": 798208 + }, + { + "epoch": 1.01, + "learning_rate": 3.692337602523122e-05, + "loss": 3.6109, + "step": 798720 + }, + { + "epoch": 1.01, + "learning_rate": 3.691500645652443e-05, + "loss": 3.6358, + "step": 799232 + }, + { + "epoch": 1.01, + "learning_rate": 3.690662050901391e-05, + "loss": 3.6256, + "step": 799744 + }, + { + "epoch": 1.01, + "learning_rate": 3.689823456150339e-05, + "loss": 3.6143, + "step": 800256 + }, + { + "epoch": 1.01, + "learning_rate": 3.688984861399287e-05, + "loss": 3.6222, + "step": 800768 + }, + { + "epoch": 1.01, + "learning_rate": 3.688147904528608e-05, + "loss": 3.6294, + "step": 801280 + }, + { + "epoch": 1.01, + "learning_rate": 3.687309309777556e-05, + "loss": 3.6224, + "step": 801792 + }, + { + "epoch": 1.01, + "learning_rate": 3.6864707150265046e-05, + "loss": 3.6355, + "step": 802304 + }, + { + "epoch": 1.01, + "learning_rate": 3.6856321202754526e-05, + "loss": 3.6295, + "step": 802816 + }, + { + "epoch": 1.01, + "learning_rate": 3.6847951634047735e-05, + "loss": 3.6203, + "step": 803328 + }, + { + "epoch": 1.01, + "learning_rate": 3.6839565686537215e-05, + "loss": 3.6225, + "step": 803840 + }, + { + "epoch": 1.01, + "learning_rate": 3.6831179739026695e-05, + "loss": 3.6199, + "step": 804352 + }, + { + "epoch": 1.01, + "learning_rate": 3.6822793791516175e-05, + "loss": 3.6188, + "step": 804864 + }, + { + "epoch": 1.01, + "learning_rate": 3.6814424222809384e-05, + "loss": 3.6208, + "step": 805376 + }, + { + "epoch": 1.01, + "learning_rate": 3.6806038275298864e-05, + "loss": 3.6178, + "step": 805888 + }, + { + "epoch": 1.01, + "learning_rate": 3.6797652327788344e-05, + "loss": 3.6033, + "step": 806400 + }, + { + "epoch": 1.01, + "learning_rate": 3.6789266380277824e-05, + "loss": 3.6258, + "step": 806912 + }, + { + "epoch": 1.01, + "learning_rate": 3.678089681157103e-05, + "loss": 3.6141, + "step": 807424 + }, + { + "epoch": 1.01, + "learning_rate": 3.677251086406051e-05, + "loss": 3.622, + "step": 807936 + }, + { + "epoch": 1.01, + "learning_rate": 3.676412491655e-05, + "loss": 3.6098, + "step": 808448 + }, + { + "epoch": 1.01, + "learning_rate": 3.675573896903948e-05, + "loss": 3.6271, + "step": 808960 + }, + { + "epoch": 1.02, + "learning_rate": 3.674735302152896e-05, + "loss": 3.6291, + "step": 809472 + }, + { + "epoch": 1.02, + "learning_rate": 3.673898345282217e-05, + "loss": 3.6315, + "step": 809984 + }, + { + "epoch": 1.02, + "learning_rate": 3.673059750531165e-05, + "loss": 3.6271, + "step": 810496 + }, + { + "epoch": 1.02, + "learning_rate": 3.672221155780113e-05, + "loss": 3.6118, + "step": 811008 + }, + { + "epoch": 1.02, + "learning_rate": 3.671382561029061e-05, + "loss": 3.6279, + "step": 811520 + }, + { + "epoch": 1.02, + "learning_rate": 3.670545604158382e-05, + "loss": 3.6195, + "step": 812032 + }, + { + "epoch": 1.02, + "learning_rate": 3.66970700940733e-05, + "loss": 3.626, + "step": 812544 + }, + { + "epoch": 1.02, + "learning_rate": 3.668868414656278e-05, + "loss": 3.6093, + "step": 813056 + }, + { + "epoch": 1.02, + "learning_rate": 3.668029819905226e-05, + "loss": 3.6238, + "step": 813568 + }, + { + "epoch": 1.02, + "learning_rate": 3.667192863034547e-05, + "loss": 3.6236, + "step": 814080 + }, + { + "epoch": 1.02, + "learning_rate": 3.6663542682834954e-05, + "loss": 3.6243, + "step": 814592 + }, + { + "epoch": 1.02, + "learning_rate": 3.6655156735324434e-05, + "loss": 3.6271, + "step": 815104 + }, + { + "epoch": 1.02, + "learning_rate": 3.6646770787813914e-05, + "loss": 3.6284, + "step": 815616 + }, + { + "epoch": 1.02, + "learning_rate": 3.663840121910712e-05, + "loss": 3.6218, + "step": 816128 + }, + { + "epoch": 1.02, + "learning_rate": 3.66300152715966e-05, + "loss": 3.6075, + "step": 816640 + }, + { + "epoch": 1.02, + "learning_rate": 3.662162932408608e-05, + "loss": 3.619, + "step": 817152 + }, + { + "epoch": 1.02, + "learning_rate": 3.661324337657556e-05, + "loss": 3.6231, + "step": 817664 + }, + { + "epoch": 1.02, + "learning_rate": 3.660487380786877e-05, + "loss": 3.6263, + "step": 818176 + }, + { + "epoch": 1.02, + "learning_rate": 3.659648786035825e-05, + "loss": 3.6131, + "step": 818688 + }, + { + "epoch": 1.02, + "learning_rate": 3.658810191284773e-05, + "loss": 3.6125, + "step": 819200 + }, + { + "epoch": 1.02, + "learning_rate": 3.657971596533721e-05, + "loss": 3.6162, + "step": 819712 + }, + { + "epoch": 1.02, + "learning_rate": 3.657134639663042e-05, + "loss": 3.6198, + "step": 820224 + }, + { + "epoch": 1.02, + "learning_rate": 3.656296044911991e-05, + "loss": 3.6194, + "step": 820736 + }, + { + "epoch": 1.02, + "learning_rate": 3.655457450160939e-05, + "loss": 3.6176, + "step": 821248 + }, + { + "epoch": 1.02, + "learning_rate": 3.654618855409887e-05, + "loss": 3.6198, + "step": 821760 + }, + { + "epoch": 1.02, + "learning_rate": 3.653780260658835e-05, + "loss": 3.6123, + "step": 822272 + }, + { + "epoch": 1.02, + "learning_rate": 3.6529433037881556e-05, + "loss": 3.6205, + "step": 822784 + }, + { + "epoch": 1.02, + "learning_rate": 3.6521047090371036e-05, + "loss": 3.6171, + "step": 823296 + }, + { + "epoch": 1.02, + "learning_rate": 3.6512661142860516e-05, + "loss": 3.6208, + "step": 823808 + }, + { + "epoch": 1.02, + "learning_rate": 3.6504275195349996e-05, + "loss": 3.618, + "step": 824320 + }, + { + "epoch": 1.02, + "learning_rate": 3.6495905626643205e-05, + "loss": 3.6328, + "step": 824832 + }, + { + "epoch": 1.02, + "learning_rate": 3.6487519679132685e-05, + "loss": 3.6341, + "step": 825344 + }, + { + "epoch": 1.02, + "learning_rate": 3.6479133731622165e-05, + "loss": 3.616, + "step": 825856 + }, + { + "epoch": 1.02, + "learning_rate": 3.6470747784111645e-05, + "loss": 3.6185, + "step": 826368 + }, + { + "epoch": 1.02, + "learning_rate": 3.646237821540486e-05, + "loss": 3.6181, + "step": 826880 + }, + { + "epoch": 1.02, + "learning_rate": 3.645399226789434e-05, + "loss": 3.6122, + "step": 827392 + }, + { + "epoch": 1.02, + "learning_rate": 3.644560632038382e-05, + "loss": 3.623, + "step": 827904 + }, + { + "epoch": 1.02, + "learning_rate": 3.64372203728733e-05, + "loss": 3.6201, + "step": 828416 + }, + { + "epoch": 1.02, + "learning_rate": 3.6428834425362774e-05, + "loss": 3.6166, + "step": 828928 + }, + { + "epoch": 1.02, + "learning_rate": 3.642046485665599e-05, + "loss": 3.6153, + "step": 829440 + }, + { + "epoch": 1.02, + "learning_rate": 3.641207890914547e-05, + "loss": 3.624, + "step": 829952 + }, + { + "epoch": 1.02, + "learning_rate": 3.640369296163495e-05, + "loss": 3.6206, + "step": 830464 + }, + { + "epoch": 1.02, + "learning_rate": 3.639530701412442e-05, + "loss": 3.6358, + "step": 830976 + }, + { + "epoch": 1.02, + "learning_rate": 3.638693744541764e-05, + "loss": 3.6272, + "step": 831488 + }, + { + "epoch": 1.02, + "learning_rate": 3.637855149790712e-05, + "loss": 3.6252, + "step": 832000 + }, + { + "epoch": 1.02, + "learning_rate": 3.63701655503966e-05, + "loss": 3.6164, + "step": 832512 + }, + { + "epoch": 1.02, + "learning_rate": 3.636177960288608e-05, + "loss": 3.6251, + "step": 833024 + }, + { + "epoch": 1.02, + "learning_rate": 3.6353410034179295e-05, + "loss": 3.6288, + "step": 833536 + }, + { + "epoch": 1.02, + "learning_rate": 3.6345024086668775e-05, + "loss": 3.6113, + "step": 834048 + }, + { + "epoch": 1.02, + "learning_rate": 3.633663813915825e-05, + "loss": 3.6205, + "step": 834560 + }, + { + "epoch": 1.02, + "learning_rate": 3.632825219164773e-05, + "loss": 3.6196, + "step": 835072 + }, + { + "epoch": 1.02, + "learning_rate": 3.6319882622940944e-05, + "loss": 3.62, + "step": 835584 + }, + { + "epoch": 1.02, + "learning_rate": 3.631149667543042e-05, + "loss": 3.6123, + "step": 836096 + }, + { + "epoch": 1.02, + "learning_rate": 3.63031107279199e-05, + "loss": 3.6286, + "step": 836608 + }, + { + "epoch": 1.02, + "learning_rate": 3.6294724780409377e-05, + "loss": 3.6176, + "step": 837120 + }, + { + "epoch": 1.02, + "learning_rate": 3.628635521170259e-05, + "loss": 3.6204, + "step": 837632 + }, + { + "epoch": 1.02, + "learning_rate": 3.6277969264192066e-05, + "loss": 3.6138, + "step": 838144 + }, + { + "epoch": 1.02, + "learning_rate": 3.626958331668155e-05, + "loss": 3.6151, + "step": 838656 + }, + { + "epoch": 1.02, + "learning_rate": 3.626119736917103e-05, + "loss": 3.6082, + "step": 839168 + }, + { + "epoch": 1.03, + "eval_loss": 3.834686517715454, + "eval_runtime": 308.9705, + "eval_samples_per_second": 1235.04, + "eval_steps_per_second": 38.596, + "step": 839511 + }, + { + "epoch": 0.0, + "learning_rate": 3.625282780046425e-05, + "loss": 3.5995, + "step": 839680 + }, + { + "epoch": 0.0, + "learning_rate": 3.624444185295372e-05, + "loss": 3.6149, + "step": 840192 + }, + { + "epoch": 0.0, + "learning_rate": 3.62360559054432e-05, + "loss": 3.6174, + "step": 840704 + }, + { + "epoch": 0.0, + "learning_rate": 3.622766995793268e-05, + "loss": 3.6195, + "step": 841216 + }, + { + "epoch": 0.0, + "learning_rate": 3.621930038922589e-05, + "loss": 3.6314, + "step": 841728 + }, + { + "epoch": 0.0, + "learning_rate": 3.621091444171537e-05, + "loss": 3.6091, + "step": 842240 + }, + { + "epoch": 0.0, + "learning_rate": 3.620252849420485e-05, + "loss": 3.6156, + "step": 842752 + }, + { + "epoch": 0.0, + "learning_rate": 3.619414254669433e-05, + "loss": 3.6132, + "step": 843264 + }, + { + "epoch": 0.0, + "learning_rate": 3.618577297798754e-05, + "loss": 3.6088, + "step": 843776 + }, + { + "epoch": 0.0, + "learning_rate": 3.617738703047702e-05, + "loss": 3.6078, + "step": 844288 + }, + { + "epoch": 0.0, + "learning_rate": 3.6169001082966506e-05, + "loss": 3.6195, + "step": 844800 + }, + { + "epoch": 0.0, + "learning_rate": 3.6160615135455986e-05, + "loss": 3.6284, + "step": 845312 + }, + { + "epoch": 0.0, + "learning_rate": 3.6152245566749195e-05, + "loss": 3.6193, + "step": 845824 + }, + { + "epoch": 0.0, + "learning_rate": 3.6143859619238675e-05, + "loss": 3.5968, + "step": 846336 + }, + { + "epoch": 0.0, + "learning_rate": 3.6135473671728155e-05, + "loss": 3.6168, + "step": 846848 + }, + { + "epoch": 0.0, + "learning_rate": 3.6127087724217635e-05, + "loss": 3.5992, + "step": 847360 + }, + { + "epoch": 0.0, + "learning_rate": 3.6118718155510844e-05, + "loss": 3.6133, + "step": 847872 + }, + { + "epoch": 0.0, + "learning_rate": 3.6110332208000324e-05, + "loss": 3.6138, + "step": 848384 + }, + { + "epoch": 0.0, + "learning_rate": 3.6101946260489804e-05, + "loss": 3.6133, + "step": 848896 + }, + { + "epoch": 0.0, + "learning_rate": 3.6093560312979284e-05, + "loss": 3.6187, + "step": 849408 + }, + { + "epoch": 0.0, + "learning_rate": 3.6085174365468764e-05, + "loss": 3.6245, + "step": 849920 + }, + { + "epoch": 0.0, + "learning_rate": 3.607680479676197e-05, + "loss": 3.6132, + "step": 850432 + }, + { + "epoch": 0.0, + "learning_rate": 3.606841884925145e-05, + "loss": 3.6118, + "step": 850944 + }, + { + "epoch": 0.0, + "learning_rate": 3.606003290174094e-05, + "loss": 3.6013, + "step": 851456 + }, + { + "epoch": 0.0, + "learning_rate": 3.605164695423042e-05, + "loss": 3.6148, + "step": 851968 + }, + { + "epoch": 0.0, + "learning_rate": 3.604327738552363e-05, + "loss": 3.6124, + "step": 852480 + }, + { + "epoch": 0.0, + "learning_rate": 3.603489143801311e-05, + "loss": 3.6081, + "step": 852992 + }, + { + "epoch": 0.0, + "learning_rate": 3.602650549050259e-05, + "loss": 3.6111, + "step": 853504 + }, + { + "epoch": 0.0, + "learning_rate": 3.601811954299207e-05, + "loss": 3.6044, + "step": 854016 + }, + { + "epoch": 0.0, + "learning_rate": 3.600974997428528e-05, + "loss": 3.6107, + "step": 854528 + }, + { + "epoch": 0.01, + "learning_rate": 3.600136402677476e-05, + "loss": 3.6051, + "step": 855040 + }, + { + "epoch": 0.01, + "learning_rate": 3.599297807926424e-05, + "loss": 3.6174, + "step": 855552 + }, + { + "epoch": 0.01, + "learning_rate": 3.598459213175372e-05, + "loss": 3.618, + "step": 856064 + }, + { + "epoch": 0.01, + "learning_rate": 3.597622256304693e-05, + "loss": 3.6174, + "step": 856576 + }, + { + "epoch": 0.01, + "learning_rate": 3.596783661553641e-05, + "loss": 3.6133, + "step": 857088 + }, + { + "epoch": 0.01, + "learning_rate": 3.595945066802589e-05, + "loss": 3.6095, + "step": 857600 + }, + { + "epoch": 0.01, + "learning_rate": 3.595106472051537e-05, + "loss": 3.6195, + "step": 858112 + }, + { + "epoch": 0.01, + "learning_rate": 3.594269515180858e-05, + "loss": 3.6085, + "step": 858624 + }, + { + "epoch": 0.01, + "learning_rate": 3.593430920429806e-05, + "loss": 3.6013, + "step": 859136 + }, + { + "epoch": 0.01, + "learning_rate": 3.592592325678754e-05, + "loss": 3.6081, + "step": 859648 + }, + { + "epoch": 0.01, + "learning_rate": 3.591753730927702e-05, + "loss": 3.5984, + "step": 860160 + }, + { + "epoch": 0.01, + "learning_rate": 3.590916774057023e-05, + "loss": 3.6082, + "step": 860672 + }, + { + "epoch": 0.01, + "learning_rate": 3.590078179305971e-05, + "loss": 3.604, + "step": 861184 + }, + { + "epoch": 0.01, + "learning_rate": 3.589239584554919e-05, + "loss": 3.6069, + "step": 861696 + }, + { + "epoch": 0.01, + "learning_rate": 3.588400989803867e-05, + "loss": 3.6123, + "step": 862208 + }, + { + "epoch": 0.01, + "learning_rate": 3.587562395052815e-05, + "loss": 3.6116, + "step": 862720 + }, + { + "epoch": 0.01, + "learning_rate": 3.586725438182136e-05, + "loss": 3.6127, + "step": 863232 + }, + { + "epoch": 0.01, + "learning_rate": 3.585886843431085e-05, + "loss": 3.6086, + "step": 863744 + }, + { + "epoch": 0.01, + "learning_rate": 3.585048248680033e-05, + "loss": 3.5849, + "step": 864256 + }, + { + "epoch": 0.01, + "learning_rate": 3.584209653928981e-05, + "loss": 3.6154, + "step": 864768 + }, + { + "epoch": 0.01, + "learning_rate": 3.5833726970583016e-05, + "loss": 3.6043, + "step": 865280 + }, + { + "epoch": 0.01, + "learning_rate": 3.5825341023072496e-05, + "loss": 3.6074, + "step": 865792 + }, + { + "epoch": 0.01, + "learning_rate": 3.5816955075561976e-05, + "loss": 3.6137, + "step": 866304 + }, + { + "epoch": 0.01, + "learning_rate": 3.5808569128051456e-05, + "loss": 3.6063, + "step": 866816 + }, + { + "epoch": 0.01, + "learning_rate": 3.5800199559344665e-05, + "loss": 3.5888, + "step": 867328 + }, + { + "epoch": 0.01, + "learning_rate": 3.5791813611834145e-05, + "loss": 3.598, + "step": 867840 + }, + { + "epoch": 0.01, + "learning_rate": 3.5783427664323625e-05, + "loss": 3.6068, + "step": 868352 + }, + { + "epoch": 0.01, + "learning_rate": 3.5775041716813105e-05, + "loss": 3.5969, + "step": 868864 + }, + { + "epoch": 0.01, + "learning_rate": 3.5766672148106314e-05, + "loss": 3.6169, + "step": 869376 + }, + { + "epoch": 0.01, + "learning_rate": 3.57582862005958e-05, + "loss": 3.6012, + "step": 869888 + }, + { + "epoch": 0.01, + "learning_rate": 3.574990025308528e-05, + "loss": 3.591, + "step": 870400 + }, + { + "epoch": 0.01, + "learning_rate": 3.574151430557476e-05, + "loss": 3.6163, + "step": 870912 + }, + { + "epoch": 0.01, + "learning_rate": 3.573314473686797e-05, + "loss": 3.597, + "step": 871424 + }, + { + "epoch": 0.01, + "learning_rate": 3.572475878935745e-05, + "loss": 3.5877, + "step": 871936 + }, + { + "epoch": 0.01, + "learning_rate": 3.571637284184693e-05, + "loss": 3.604, + "step": 872448 + }, + { + "epoch": 0.01, + "learning_rate": 3.570798689433641e-05, + "loss": 3.5996, + "step": 872960 + }, + { + "epoch": 0.01, + "learning_rate": 3.569961732562962e-05, + "loss": 3.5959, + "step": 873472 + }, + { + "epoch": 0.01, + "learning_rate": 3.56912313781191e-05, + "loss": 3.5994, + "step": 873984 + }, + { + "epoch": 0.01, + "learning_rate": 3.568284543060858e-05, + "loss": 3.59, + "step": 874496 + }, + { + "epoch": 0.01, + "learning_rate": 3.567445948309806e-05, + "loss": 3.5949, + "step": 875008 + }, + { + "epoch": 0.01, + "learning_rate": 3.566607353558754e-05, + "loss": 3.6107, + "step": 875520 + }, + { + "epoch": 0.01, + "learning_rate": 3.5657703966880754e-05, + "loss": 3.6037, + "step": 876032 + }, + { + "epoch": 0.01, + "learning_rate": 3.5649318019370234e-05, + "loss": 3.6149, + "step": 876544 + }, + { + "epoch": 0.01, + "learning_rate": 3.5640932071859714e-05, + "loss": 3.6043, + "step": 877056 + }, + { + "epoch": 0.01, + "learning_rate": 3.5632546124349194e-05, + "loss": 3.6201, + "step": 877568 + }, + { + "epoch": 0.01, + "learning_rate": 3.56241765556424e-05, + "loss": 3.5963, + "step": 878080 + }, + { + "epoch": 0.01, + "learning_rate": 3.561579060813188e-05, + "loss": 3.6121, + "step": 878592 + }, + { + "epoch": 0.01, + "learning_rate": 3.560740466062136e-05, + "loss": 3.6037, + "step": 879104 + }, + { + "epoch": 0.01, + "learning_rate": 3.559901871311084e-05, + "loss": 3.5889, + "step": 879616 + }, + { + "epoch": 0.01, + "learning_rate": 3.559064914440405e-05, + "loss": 3.612, + "step": 880128 + }, + { + "epoch": 0.01, + "learning_rate": 3.558226319689353e-05, + "loss": 3.6099, + "step": 880640 + }, + { + "epoch": 0.01, + "learning_rate": 3.557387724938301e-05, + "loss": 3.6058, + "step": 881152 + }, + { + "epoch": 0.01, + "learning_rate": 3.556549130187249e-05, + "loss": 3.6092, + "step": 881664 + }, + { + "epoch": 0.01, + "learning_rate": 3.555712173316571e-05, + "loss": 3.5886, + "step": 882176 + }, + { + "epoch": 0.01, + "learning_rate": 3.554873578565519e-05, + "loss": 3.585, + "step": 882688 + }, + { + "epoch": 0.01, + "learning_rate": 3.554034983814467e-05, + "loss": 3.5973, + "step": 883200 + }, + { + "epoch": 0.01, + "learning_rate": 3.553196389063415e-05, + "loss": 3.6092, + "step": 883712 + }, + { + "epoch": 0.01, + "learning_rate": 3.552359432192736e-05, + "loss": 3.5994, + "step": 884224 + }, + { + "epoch": 0.01, + "learning_rate": 3.551520837441684e-05, + "loss": 3.5946, + "step": 884736 + }, + { + "epoch": 0.01, + "learning_rate": 3.550682242690632e-05, + "loss": 3.5988, + "step": 885248 + }, + { + "epoch": 0.02, + "learning_rate": 3.54984364793958e-05, + "loss": 3.6019, + "step": 885760 + }, + { + "epoch": 0.02, + "learning_rate": 3.5490066910689006e-05, + "loss": 3.5989, + "step": 886272 + }, + { + "epoch": 0.02, + "learning_rate": 3.5481680963178486e-05, + "loss": 3.6001, + "step": 886784 + }, + { + "epoch": 0.02, + "learning_rate": 3.5473295015667966e-05, + "loss": 3.6107, + "step": 887296 + }, + { + "epoch": 0.02, + "learning_rate": 3.5464909068157446e-05, + "loss": 3.6194, + "step": 887808 + }, + { + "epoch": 0.02, + "learning_rate": 3.5456523120646926e-05, + "loss": 3.607, + "step": 888320 + }, + { + "epoch": 0.02, + "learning_rate": 3.544815355194014e-05, + "loss": 3.5944, + "step": 888832 + }, + { + "epoch": 0.02, + "learning_rate": 3.543976760442962e-05, + "loss": 3.5948, + "step": 889344 + }, + { + "epoch": 0.02, + "learning_rate": 3.5431381656919095e-05, + "loss": 3.5979, + "step": 889856 + }, + { + "epoch": 0.02, + "learning_rate": 3.5422995709408575e-05, + "loss": 3.6083, + "step": 890368 + }, + { + "epoch": 0.02, + "learning_rate": 3.541462614070179e-05, + "loss": 3.5991, + "step": 890880 + }, + { + "epoch": 0.02, + "learning_rate": 3.540624019319127e-05, + "loss": 3.5989, + "step": 891392 + }, + { + "epoch": 0.02, + "learning_rate": 3.5397854245680744e-05, + "loss": 3.5971, + "step": 891904 + }, + { + "epoch": 0.02, + "learning_rate": 3.5389468298170224e-05, + "loss": 3.6033, + "step": 892416 + }, + { + "epoch": 0.02, + "learning_rate": 3.538109872946344e-05, + "loss": 3.604, + "step": 892928 + }, + { + "epoch": 0.02, + "learning_rate": 3.537271278195291e-05, + "loss": 3.5961, + "step": 893440 + }, + { + "epoch": 0.02, + "learning_rate": 3.53643268344424e-05, + "loss": 3.5921, + "step": 893952 + }, + { + "epoch": 0.02, + "learning_rate": 3.535594088693188e-05, + "loss": 3.5937, + "step": 894464 + }, + { + "epoch": 0.02, + "learning_rate": 3.534755493942136e-05, + "loss": 3.5992, + "step": 894976 + }, + { + "epoch": 0.02, + "learning_rate": 3.533918537071457e-05, + "loss": 3.5914, + "step": 895488 + }, + { + "epoch": 0.02, + "learning_rate": 3.533079942320405e-05, + "loss": 3.5964, + "step": 896000 + }, + { + "epoch": 0.02, + "learning_rate": 3.532241347569353e-05, + "loss": 3.5974, + "step": 896512 + }, + { + "epoch": 0.02, + "learning_rate": 3.5314043906986744e-05, + "loss": 3.6023, + "step": 897024 + }, + { + "epoch": 0.02, + "learning_rate": 3.530565795947622e-05, + "loss": 3.5929, + "step": 897536 + }, + { + "epoch": 0.02, + "learning_rate": 3.52972720119657e-05, + "loss": 3.6096, + "step": 898048 + }, + { + "epoch": 0.02, + "learning_rate": 3.528888606445518e-05, + "loss": 3.611, + "step": 898560 + }, + { + "epoch": 0.02, + "learning_rate": 3.5280516495748386e-05, + "loss": 3.599, + "step": 899072 + }, + { + "epoch": 0.02, + "learning_rate": 3.5272130548237866e-05, + "loss": 3.608, + "step": 899584 + }, + { + "epoch": 0.02, + "learning_rate": 3.526374460072735e-05, + "loss": 3.5962, + "step": 900096 + }, + { + "epoch": 0.02, + "learning_rate": 3.525535865321683e-05, + "loss": 3.595, + "step": 900608 + }, + { + "epoch": 0.02, + "learning_rate": 3.524698908451004e-05, + "loss": 3.5933, + "step": 901120 + }, + { + "epoch": 0.02, + "learning_rate": 3.523860313699952e-05, + "loss": 3.5851, + "step": 901632 + }, + { + "epoch": 0.02, + "learning_rate": 3.5230217189489e-05, + "loss": 3.5966, + "step": 902144 + }, + { + "epoch": 0.02, + "learning_rate": 3.522183124197848e-05, + "loss": 3.5966, + "step": 902656 + }, + { + "epoch": 0.02, + "learning_rate": 3.521346167327169e-05, + "loss": 3.6035, + "step": 903168 + }, + { + "epoch": 0.02, + "learning_rate": 3.520507572576117e-05, + "loss": 3.5937, + "step": 903680 + }, + { + "epoch": 0.02, + "learning_rate": 3.519668977825065e-05, + "loss": 3.6038, + "step": 904192 + }, + { + "epoch": 0.02, + "learning_rate": 3.518830383074013e-05, + "loss": 3.5978, + "step": 904704 + }, + { + "epoch": 0.02, + "learning_rate": 3.517993426203334e-05, + "loss": 3.5939, + "step": 905216 + }, + { + "epoch": 0.02, + "learning_rate": 3.517154831452282e-05, + "loss": 3.6013, + "step": 905728 + }, + { + "epoch": 0.02, + "learning_rate": 3.51631623670123e-05, + "loss": 3.6043, + "step": 906240 + }, + { + "epoch": 0.02, + "learning_rate": 3.515477641950179e-05, + "loss": 3.6097, + "step": 906752 + }, + { + "epoch": 0.02, + "learning_rate": 3.5146406850794996e-05, + "loss": 3.589, + "step": 907264 + }, + { + "epoch": 0.02, + "learning_rate": 3.5138020903284476e-05, + "loss": 3.6121, + "step": 907776 + }, + { + "epoch": 0.02, + "learning_rate": 3.5129634955773956e-05, + "loss": 3.5948, + "step": 908288 + }, + { + "epoch": 0.02, + "learning_rate": 3.5121249008263436e-05, + "loss": 3.6046, + "step": 908800 + }, + { + "epoch": 0.02, + "learning_rate": 3.5112879439556645e-05, + "loss": 3.6019, + "step": 909312 + }, + { + "epoch": 0.02, + "learning_rate": 3.5104493492046125e-05, + "loss": 3.5957, + "step": 909824 + }, + { + "epoch": 0.02, + "learning_rate": 3.5096107544535605e-05, + "loss": 3.5897, + "step": 910336 + }, + { + "epoch": 0.02, + "learning_rate": 3.5087721597025085e-05, + "loss": 3.6108, + "step": 910848 + }, + { + "epoch": 0.02, + "learning_rate": 3.5079352028318294e-05, + "loss": 3.588, + "step": 911360 + }, + { + "epoch": 0.02, + "learning_rate": 3.5070966080807774e-05, + "loss": 3.6013, + "step": 911872 + }, + { + "epoch": 0.02, + "learning_rate": 3.5062580133297254e-05, + "loss": 3.5988, + "step": 912384 + }, + { + "epoch": 0.02, + "learning_rate": 3.505419418578674e-05, + "loss": 3.6019, + "step": 912896 + }, + { + "epoch": 0.02, + "learning_rate": 3.504582461707995e-05, + "loss": 3.5937, + "step": 913408 + }, + { + "epoch": 0.02, + "learning_rate": 3.503743866956943e-05, + "loss": 3.6019, + "step": 913920 + }, + { + "epoch": 0.02, + "learning_rate": 3.502905272205891e-05, + "loss": 3.5994, + "step": 914432 + }, + { + "epoch": 0.02, + "learning_rate": 3.502066677454839e-05, + "loss": 3.6077, + "step": 914944 + }, + { + "epoch": 0.02, + "learning_rate": 3.50122972058416e-05, + "loss": 3.598, + "step": 915456 + }, + { + "epoch": 0.03, + "eval_loss": 3.831312417984009, + "eval_runtime": 306.2564, + "eval_samples_per_second": 1245.985, + "eval_steps_per_second": 38.938, + "step": 915831 + }, + { + "epoch": 1.0, + "learning_rate": 3.500391125833108e-05, + "loss": 3.5927, + "step": 915968 + }, + { + "epoch": 1.0, + "learning_rate": 3.499552531082056e-05, + "loss": 3.5888, + "step": 916480 + }, + { + "epoch": 1.0, + "learning_rate": 3.498713936331004e-05, + "loss": 3.5972, + "step": 916992 + }, + { + "epoch": 1.0, + "learning_rate": 3.497876979460325e-05, + "loss": 3.6006, + "step": 917504 + }, + { + "epoch": 1.0, + "learning_rate": 3.497038384709273e-05, + "loss": 3.6025, + "step": 918016 + }, + { + "epoch": 1.0, + "learning_rate": 3.496199789958221e-05, + "loss": 3.5915, + "step": 918528 + }, + { + "epoch": 1.0, + "learning_rate": 3.4953611952071694e-05, + "loss": 3.5945, + "step": 919040 + }, + { + "epoch": 1.0, + "learning_rate": 3.49452423833649e-05, + "loss": 3.5906, + "step": 919552 + }, + { + "epoch": 1.0, + "learning_rate": 3.493685643585438e-05, + "loss": 3.5851, + "step": 920064 + }, + { + "epoch": 1.0, + "learning_rate": 3.492847048834386e-05, + "loss": 3.5801, + "step": 920576 + }, + { + "epoch": 1.0, + "learning_rate": 3.492008454083334e-05, + "loss": 3.6033, + "step": 921088 + }, + { + "epoch": 1.0, + "learning_rate": 3.491169859332282e-05, + "loss": 3.6034, + "step": 921600 + }, + { + "epoch": 1.0, + "learning_rate": 3.490332902461603e-05, + "loss": 3.598, + "step": 922112 + }, + { + "epoch": 1.0, + "learning_rate": 3.489494307710551e-05, + "loss": 3.5719, + "step": 922624 + }, + { + "epoch": 1.0, + "learning_rate": 3.488655712959499e-05, + "loss": 3.5929, + "step": 923136 + }, + { + "epoch": 1.0, + "learning_rate": 3.487817118208447e-05, + "loss": 3.5743, + "step": 923648 + }, + { + "epoch": 1.0, + "learning_rate": 3.486980161337768e-05, + "loss": 3.5929, + "step": 924160 + }, + { + "epoch": 1.0, + "learning_rate": 3.486141566586716e-05, + "loss": 3.5896, + "step": 924672 + }, + { + "epoch": 1.0, + "learning_rate": 3.485302971835665e-05, + "loss": 3.5894, + "step": 925184 + }, + { + "epoch": 1.0, + "learning_rate": 3.484464377084613e-05, + "loss": 3.5955, + "step": 925696 + }, + { + "epoch": 1.0, + "learning_rate": 3.483627420213934e-05, + "loss": 3.603, + "step": 926208 + }, + { + "epoch": 1.0, + "learning_rate": 3.482788825462882e-05, + "loss": 3.5918, + "step": 926720 + }, + { + "epoch": 1.0, + "learning_rate": 3.48195023071183e-05, + "loss": 3.5913, + "step": 927232 + }, + { + "epoch": 1.0, + "learning_rate": 3.481111635960778e-05, + "loss": 3.5861, + "step": 927744 + }, + { + "epoch": 1.0, + "learning_rate": 3.4802746790900986e-05, + "loss": 3.5929, + "step": 928256 + }, + { + "epoch": 1.0, + "learning_rate": 3.4794360843390466e-05, + "loss": 3.5915, + "step": 928768 + }, + { + "epoch": 1.0, + "learning_rate": 3.4785974895879946e-05, + "loss": 3.5838, + "step": 929280 + }, + { + "epoch": 1.0, + "learning_rate": 3.4777588948369426e-05, + "loss": 3.59, + "step": 929792 + }, + { + "epoch": 1.0, + "learning_rate": 3.4769219379662635e-05, + "loss": 3.5861, + "step": 930304 + }, + { + "epoch": 1.0, + "learning_rate": 3.4760833432152115e-05, + "loss": 3.5847, + "step": 930816 + }, + { + "epoch": 1.01, + "learning_rate": 3.47524474846416e-05, + "loss": 3.5842, + "step": 931328 + }, + { + "epoch": 1.01, + "learning_rate": 3.474406153713108e-05, + "loss": 3.5942, + "step": 931840 + }, + { + "epoch": 1.01, + "learning_rate": 3.473569196842429e-05, + "loss": 3.5911, + "step": 932352 + }, + { + "epoch": 1.01, + "learning_rate": 3.472730602091377e-05, + "loss": 3.5989, + "step": 932864 + }, + { + "epoch": 1.01, + "learning_rate": 3.471892007340325e-05, + "loss": 3.5885, + "step": 933376 + }, + { + "epoch": 1.01, + "learning_rate": 3.471053412589273e-05, + "loss": 3.5868, + "step": 933888 + }, + { + "epoch": 1.01, + "learning_rate": 3.470216455718594e-05, + "loss": 3.5987, + "step": 934400 + }, + { + "epoch": 1.01, + "learning_rate": 3.469377860967542e-05, + "loss": 3.5819, + "step": 934912 + }, + { + "epoch": 1.01, + "learning_rate": 3.46853926621649e-05, + "loss": 3.5836, + "step": 935424 + }, + { + "epoch": 1.01, + "learning_rate": 3.467700671465438e-05, + "loss": 3.5853, + "step": 935936 + }, + { + "epoch": 1.01, + "learning_rate": 3.466863714594759e-05, + "loss": 3.582, + "step": 936448 + }, + { + "epoch": 1.01, + "learning_rate": 3.466025119843707e-05, + "loss": 3.5846, + "step": 936960 + }, + { + "epoch": 1.01, + "learning_rate": 3.4651865250926555e-05, + "loss": 3.5833, + "step": 937472 + }, + { + "epoch": 1.01, + "learning_rate": 3.4643479303416035e-05, + "loss": 3.5871, + "step": 937984 + }, + { + "epoch": 1.01, + "learning_rate": 3.4635109734709244e-05, + "loss": 3.5896, + "step": 938496 + }, + { + "epoch": 1.01, + "learning_rate": 3.4626723787198724e-05, + "loss": 3.5923, + "step": 939008 + }, + { + "epoch": 1.01, + "learning_rate": 3.4618337839688204e-05, + "loss": 3.5909, + "step": 939520 + }, + { + "epoch": 1.01, + "learning_rate": 3.4609951892177684e-05, + "loss": 3.5872, + "step": 940032 + }, + { + "epoch": 1.01, + "learning_rate": 3.460158232347089e-05, + "loss": 3.5664, + "step": 940544 + }, + { + "epoch": 1.01, + "learning_rate": 3.459319637596037e-05, + "loss": 3.5946, + "step": 941056 + }, + { + "epoch": 1.01, + "learning_rate": 3.458481042844985e-05, + "loss": 3.5827, + "step": 941568 + }, + { + "epoch": 1.01, + "learning_rate": 3.457642448093933e-05, + "loss": 3.5855, + "step": 942080 + }, + { + "epoch": 1.01, + "learning_rate": 3.456805491223254e-05, + "loss": 3.588, + "step": 942592 + }, + { + "epoch": 1.01, + "learning_rate": 3.455966896472202e-05, + "loss": 3.5836, + "step": 943104 + }, + { + "epoch": 1.01, + "learning_rate": 3.455128301721151e-05, + "loss": 3.5705, + "step": 943616 + }, + { + "epoch": 1.01, + "learning_rate": 3.454289706970099e-05, + "loss": 3.5784, + "step": 944128 + }, + { + "epoch": 1.01, + "learning_rate": 3.45345275009942e-05, + "loss": 3.586, + "step": 944640 + }, + { + "epoch": 1.01, + "learning_rate": 3.452614155348368e-05, + "loss": 3.5767, + "step": 945152 + }, + { + "epoch": 1.01, + "learning_rate": 3.451775560597316e-05, + "loss": 3.5947, + "step": 945664 + }, + { + "epoch": 1.01, + "learning_rate": 3.450936965846264e-05, + "loss": 3.5829, + "step": 946176 + }, + { + "epoch": 1.01, + "learning_rate": 3.450100008975585e-05, + "loss": 3.5684, + "step": 946688 + }, + { + "epoch": 1.01, + "learning_rate": 3.449261414224533e-05, + "loss": 3.598, + "step": 947200 + }, + { + "epoch": 1.01, + "learning_rate": 3.448422819473481e-05, + "loss": 3.5752, + "step": 947712 + }, + { + "epoch": 1.01, + "learning_rate": 3.447584224722429e-05, + "loss": 3.5705, + "step": 948224 + }, + { + "epoch": 1.01, + "learning_rate": 3.4467456299713767e-05, + "loss": 3.5827, + "step": 948736 + }, + { + "epoch": 1.01, + "learning_rate": 3.4459086731006976e-05, + "loss": 3.5785, + "step": 949248 + }, + { + "epoch": 1.01, + "learning_rate": 3.4450700783496456e-05, + "loss": 3.5742, + "step": 949760 + }, + { + "epoch": 1.01, + "learning_rate": 3.444231483598594e-05, + "loss": 3.5806, + "step": 950272 + }, + { + "epoch": 1.01, + "learning_rate": 3.4433928888475416e-05, + "loss": 3.571, + "step": 950784 + }, + { + "epoch": 1.01, + "learning_rate": 3.442555931976863e-05, + "loss": 3.571, + "step": 951296 + }, + { + "epoch": 1.01, + "learning_rate": 3.441717337225811e-05, + "loss": 3.5914, + "step": 951808 + }, + { + "epoch": 1.01, + "learning_rate": 3.440878742474759e-05, + "loss": 3.5841, + "step": 952320 + }, + { + "epoch": 1.01, + "learning_rate": 3.4400401477237065e-05, + "loss": 3.5894, + "step": 952832 + }, + { + "epoch": 1.01, + "learning_rate": 3.439203190853028e-05, + "loss": 3.5836, + "step": 953344 + }, + { + "epoch": 1.01, + "learning_rate": 3.438364596101976e-05, + "loss": 3.5968, + "step": 953856 + }, + { + "epoch": 1.01, + "learning_rate": 3.4375260013509234e-05, + "loss": 3.5744, + "step": 954368 + }, + { + "epoch": 1.01, + "learning_rate": 3.4366874065998713e-05, + "loss": 3.5947, + "step": 954880 + }, + { + "epoch": 1.01, + "learning_rate": 3.435850449729193e-05, + "loss": 3.5812, + "step": 955392 + }, + { + "epoch": 1.01, + "learning_rate": 3.435011854978141e-05, + "loss": 3.5748, + "step": 955904 + }, + { + "epoch": 1.01, + "learning_rate": 3.434173260227089e-05, + "loss": 3.5873, + "step": 956416 + }, + { + "epoch": 1.01, + "learning_rate": 3.433334665476037e-05, + "loss": 3.5928, + "step": 956928 + }, + { + "epoch": 1.01, + "learning_rate": 3.4324977086053585e-05, + "loss": 3.5838, + "step": 957440 + }, + { + "epoch": 1.01, + "learning_rate": 3.4316591138543065e-05, + "loss": 3.591, + "step": 957952 + }, + { + "epoch": 1.01, + "learning_rate": 3.430820519103254e-05, + "loss": 3.5687, + "step": 958464 + }, + { + "epoch": 1.01, + "learning_rate": 3.429981924352202e-05, + "loss": 3.5625, + "step": 958976 + }, + { + "epoch": 1.01, + "learning_rate": 3.4291449674815234e-05, + "loss": 3.5769, + "step": 959488 + }, + { + "epoch": 1.01, + "learning_rate": 3.428306372730471e-05, + "loss": 3.5873, + "step": 960000 + }, + { + "epoch": 1.01, + "learning_rate": 3.427467777979419e-05, + "loss": 3.5801, + "step": 960512 + }, + { + "epoch": 1.01, + "learning_rate": 3.426629183228367e-05, + "loss": 3.5761, + "step": 961024 + }, + { + "epoch": 1.01, + "learning_rate": 3.425792226357688e-05, + "loss": 3.5814, + "step": 961536 + }, + { + "epoch": 1.02, + "learning_rate": 3.424953631606636e-05, + "loss": 3.5807, + "step": 962048 + }, + { + "epoch": 1.02, + "learning_rate": 3.424115036855584e-05, + "loss": 3.5774, + "step": 962560 + }, + { + "epoch": 1.02, + "learning_rate": 3.423276442104532e-05, + "loss": 3.5768, + "step": 963072 + }, + { + "epoch": 1.02, + "learning_rate": 3.422439485233854e-05, + "loss": 3.5875, + "step": 963584 + }, + { + "epoch": 1.02, + "learning_rate": 3.421600890482801e-05, + "loss": 3.5977, + "step": 964096 + }, + { + "epoch": 1.02, + "learning_rate": 3.420762295731749e-05, + "loss": 3.5911, + "step": 964608 + }, + { + "epoch": 1.02, + "learning_rate": 3.419923700980697e-05, + "loss": 3.5743, + "step": 965120 + }, + { + "epoch": 1.02, + "learning_rate": 3.419086744110018e-05, + "loss": 3.5779, + "step": 965632 + }, + { + "epoch": 1.02, + "learning_rate": 3.418248149358966e-05, + "loss": 3.5797, + "step": 966144 + }, + { + "epoch": 1.02, + "learning_rate": 3.417409554607914e-05, + "loss": 3.5885, + "step": 966656 + }, + { + "epoch": 1.02, + "learning_rate": 3.416570959856862e-05, + "loss": 3.5811, + "step": 967168 + }, + { + "epoch": 1.02, + "learning_rate": 3.415734002986184e-05, + "loss": 3.5771, + "step": 967680 + }, + { + "epoch": 1.02, + "learning_rate": 3.414895408235132e-05, + "loss": 3.5784, + "step": 968192 + }, + { + "epoch": 1.02, + "learning_rate": 3.41405681348408e-05, + "loss": 3.5822, + "step": 968704 + }, + { + "epoch": 1.02, + "learning_rate": 3.4132182187330277e-05, + "loss": 3.5812, + "step": 969216 + }, + { + "epoch": 1.02, + "learning_rate": 3.4123812618623486e-05, + "loss": 3.5764, + "step": 969728 + }, + { + "epoch": 1.02, + "learning_rate": 3.4115426671112966e-05, + "loss": 3.5747, + "step": 970240 + }, + { + "epoch": 1.02, + "learning_rate": 3.4107040723602446e-05, + "loss": 3.5714, + "step": 970752 + }, + { + "epoch": 1.02, + "learning_rate": 3.4098654776091926e-05, + "loss": 3.5768, + "step": 971264 + }, + { + "epoch": 1.02, + "learning_rate": 3.4090285207385135e-05, + "loss": 3.5742, + "step": 971776 + }, + { + "epoch": 1.02, + "learning_rate": 3.4081899259874615e-05, + "loss": 3.5735, + "step": 972288 + }, + { + "epoch": 1.02, + "learning_rate": 3.4073513312364095e-05, + "loss": 3.575, + "step": 972800 + }, + { + "epoch": 1.02, + "learning_rate": 3.4065127364853574e-05, + "loss": 3.5809, + "step": 973312 + }, + { + "epoch": 1.02, + "learning_rate": 3.405675779614679e-05, + "loss": 3.5723, + "step": 973824 + }, + { + "epoch": 1.02, + "learning_rate": 3.404837184863627e-05, + "loss": 3.5895, + "step": 974336 + }, + { + "epoch": 1.02, + "learning_rate": 3.403998590112575e-05, + "loss": 3.5951, + "step": 974848 + }, + { + "epoch": 1.02, + "learning_rate": 3.403159995361523e-05, + "loss": 3.5812, + "step": 975360 + }, + { + "epoch": 1.02, + "learning_rate": 3.402323038490844e-05, + "loss": 3.5861, + "step": 975872 + }, + { + "epoch": 1.02, + "learning_rate": 3.401484443739792e-05, + "loss": 3.581, + "step": 976384 + }, + { + "epoch": 1.02, + "learning_rate": 3.40064584898874e-05, + "loss": 3.5753, + "step": 976896 + }, + { + "epoch": 1.02, + "learning_rate": 3.399807254237688e-05, + "loss": 3.5789, + "step": 977408 + }, + { + "epoch": 1.02, + "learning_rate": 3.398970297367009e-05, + "loss": 3.5585, + "step": 977920 + }, + { + "epoch": 1.02, + "learning_rate": 3.398131702615957e-05, + "loss": 3.5796, + "step": 978432 + }, + { + "epoch": 1.02, + "learning_rate": 3.397293107864905e-05, + "loss": 3.5771, + "step": 978944 + }, + { + "epoch": 1.02, + "learning_rate": 3.396454513113853e-05, + "loss": 3.5816, + "step": 979456 + }, + { + "epoch": 1.02, + "learning_rate": 3.3956175562431744e-05, + "loss": 3.5732, + "step": 979968 + }, + { + "epoch": 1.02, + "learning_rate": 3.3947789614921224e-05, + "loss": 3.5857, + "step": 980480 + }, + { + "epoch": 1.02, + "learning_rate": 3.3939403667410704e-05, + "loss": 3.5773, + "step": 980992 + }, + { + "epoch": 1.02, + "learning_rate": 3.3931017719900184e-05, + "loss": 3.5731, + "step": 981504 + }, + { + "epoch": 1.02, + "learning_rate": 3.392264815119339e-05, + "loss": 3.5828, + "step": 982016 + }, + { + "epoch": 1.02, + "learning_rate": 3.391426220368287e-05, + "loss": 3.582, + "step": 982528 + }, + { + "epoch": 1.02, + "learning_rate": 3.390587625617235e-05, + "loss": 3.5924, + "step": 983040 + }, + { + "epoch": 1.02, + "learning_rate": 3.389749030866183e-05, + "loss": 3.5751, + "step": 983552 + }, + { + "epoch": 1.02, + "learning_rate": 3.388912073995504e-05, + "loss": 3.59, + "step": 984064 + }, + { + "epoch": 1.02, + "learning_rate": 3.388073479244452e-05, + "loss": 3.5773, + "step": 984576 + }, + { + "epoch": 1.02, + "learning_rate": 3.3872348844934e-05, + "loss": 3.5837, + "step": 985088 + }, + { + "epoch": 1.02, + "learning_rate": 3.386396289742348e-05, + "loss": 3.5852, + "step": 985600 + }, + { + "epoch": 1.02, + "learning_rate": 3.38555933287167e-05, + "loss": 3.5763, + "step": 986112 + }, + { + "epoch": 1.02, + "learning_rate": 3.384720738120618e-05, + "loss": 3.5712, + "step": 986624 + }, + { + "epoch": 1.02, + "learning_rate": 3.383882143369566e-05, + "loss": 3.5911, + "step": 987136 + }, + { + "epoch": 1.02, + "learning_rate": 3.383043548618514e-05, + "loss": 3.571, + "step": 987648 + }, + { + "epoch": 1.02, + "learning_rate": 3.382206591747835e-05, + "loss": 3.5797, + "step": 988160 + }, + { + "epoch": 1.02, + "learning_rate": 3.381367996996783e-05, + "loss": 3.5803, + "step": 988672 + }, + { + "epoch": 1.02, + "learning_rate": 3.3805294022457307e-05, + "loss": 3.5808, + "step": 989184 + }, + { + "epoch": 1.02, + "learning_rate": 3.3796908074946787e-05, + "loss": 3.5785, + "step": 989696 + }, + { + "epoch": 1.02, + "learning_rate": 3.3788538506239996e-05, + "loss": 3.5787, + "step": 990208 + }, + { + "epoch": 1.02, + "learning_rate": 3.3780152558729476e-05, + "loss": 3.5819, + "step": 990720 + }, + { + "epoch": 1.02, + "learning_rate": 3.3771766611218956e-05, + "loss": 3.5832, + "step": 991232 + }, + { + "epoch": 1.02, + "learning_rate": 3.3763380663708435e-05, + "loss": 3.5812, + "step": 991744 + }, + { + "epoch": 1.03, + "eval_loss": 3.831275463104248, + "eval_runtime": 304.9856, + "eval_samples_per_second": 1251.177, + "eval_steps_per_second": 39.1, + "step": 992151 + }, + { + "epoch": 0.0, + "learning_rate": 3.3754994716197915e-05, + "loss": 3.5799, + "step": 992256 + }, + { + "epoch": 0.0, + "learning_rate": 3.37466087686874e-05, + "loss": 3.5643, + "step": 992768 + }, + { + "epoch": 0.0, + "learning_rate": 3.373822282117688e-05, + "loss": 3.5771, + "step": 993280 + }, + { + "epoch": 0.0, + "learning_rate": 3.372983687366636e-05, + "loss": 3.5876, + "step": 993792 + }, + { + "epoch": 0.0, + "learning_rate": 3.372146730495957e-05, + "loss": 3.5799, + "step": 994304 + }, + { + "epoch": 0.0, + "learning_rate": 3.371308135744905e-05, + "loss": 3.5766, + "step": 994816 + }, + { + "epoch": 0.0, + "learning_rate": 3.370469540993853e-05, + "loss": 3.5762, + "step": 995328 + }, + { + "epoch": 0.0, + "learning_rate": 3.369630946242801e-05, + "loss": 3.5722, + "step": 995840 + }, + { + "epoch": 0.0, + "learning_rate": 3.368793989372122e-05, + "loss": 3.5657, + "step": 996352 + }, + { + "epoch": 0.0, + "learning_rate": 3.36795539462107e-05, + "loss": 3.5666, + "step": 996864 + }, + { + "epoch": 0.0, + "learning_rate": 3.367116799870018e-05, + "loss": 3.5808, + "step": 997376 + }, + { + "epoch": 0.0, + "learning_rate": 3.366278205118966e-05, + "loss": 3.5833, + "step": 997888 + }, + { + "epoch": 0.0, + "learning_rate": 3.365441248248287e-05, + "loss": 3.5838, + "step": 998400 + }, + { + "epoch": 0.0, + "learning_rate": 3.3646026534972356e-05, + "loss": 3.5516, + "step": 998912 + }, + { + "epoch": 0.0, + "learning_rate": 3.3637640587461836e-05, + "loss": 3.5713, + "step": 999424 + }, + { + "epoch": 0.0, + "learning_rate": 3.3629254639951316e-05, + "loss": 3.5598, + "step": 999936 + }, + { + "epoch": 0.0, + "learning_rate": 3.3620885071244525e-05, + "loss": 3.574, + "step": 1000448 + }, + { + "epoch": 0.0, + "learning_rate": 3.3612499123734005e-05, + "loss": 3.5703, + "step": 1000960 + }, + { + "epoch": 0.0, + "learning_rate": 3.3604113176223485e-05, + "loss": 3.5703, + "step": 1001472 + }, + { + "epoch": 0.0, + "learning_rate": 3.3595727228712965e-05, + "loss": 3.5742, + "step": 1001984 + }, + { + "epoch": 0.0, + "learning_rate": 3.358734128120244e-05, + "loss": 3.5895, + "step": 1002496 + }, + { + "epoch": 0.0, + "learning_rate": 3.3578971712495654e-05, + "loss": 3.5745, + "step": 1003008 + }, + { + "epoch": 0.0, + "learning_rate": 3.3570585764985134e-05, + "loss": 3.5709, + "step": 1003520 + }, + { + "epoch": 0.0, + "learning_rate": 3.3562199817474614e-05, + "loss": 3.5672, + "step": 1004032 + }, + { + "epoch": 0.0, + "learning_rate": 3.3553813869964094e-05, + "loss": 3.577, + "step": 1004544 + }, + { + "epoch": 0.0, + "learning_rate": 3.35454443012573e-05, + "loss": 3.5724, + "step": 1005056 + }, + { + "epoch": 0.0, + "learning_rate": 3.353705835374679e-05, + "loss": 3.5633, + "step": 1005568 + }, + { + "epoch": 0.0, + "learning_rate": 3.352867240623626e-05, + "loss": 3.5743, + "step": 1006080 + }, + { + "epoch": 0.0, + "learning_rate": 3.352028645872574e-05, + "loss": 3.5658, + "step": 1006592 + }, + { + "epoch": 0.0, + "learning_rate": 3.351191689001896e-05, + "loss": 3.5661, + "step": 1007104 + }, + { + "epoch": 0.01, + "learning_rate": 3.350353094250844e-05, + "loss": 3.5687, + "step": 1007616 + }, + { + "epoch": 0.01, + "learning_rate": 3.349514499499791e-05, + "loss": 3.5739, + "step": 1008128 + }, + { + "epoch": 0.01, + "learning_rate": 3.348675904748739e-05, + "loss": 3.5697, + "step": 1008640 + }, + { + "epoch": 0.01, + "learning_rate": 3.347838947878061e-05, + "loss": 3.5798, + "step": 1009152 + }, + { + "epoch": 0.01, + "learning_rate": 3.347000353127009e-05, + "loss": 3.5727, + "step": 1009664 + }, + { + "epoch": 0.01, + "learning_rate": 3.346161758375956e-05, + "loss": 3.5686, + "step": 1010176 + }, + { + "epoch": 0.01, + "learning_rate": 3.345323163624904e-05, + "loss": 3.5771, + "step": 1010688 + }, + { + "epoch": 0.01, + "learning_rate": 3.3444862067542256e-05, + "loss": 3.5608, + "step": 1011200 + }, + { + "epoch": 0.01, + "learning_rate": 3.3436476120031736e-05, + "loss": 3.5639, + "step": 1011712 + }, + { + "epoch": 0.01, + "learning_rate": 3.3428090172521216e-05, + "loss": 3.5689, + "step": 1012224 + }, + { + "epoch": 0.01, + "learning_rate": 3.3419704225010696e-05, + "loss": 3.5612, + "step": 1012736 + }, + { + "epoch": 0.01, + "learning_rate": 3.341133465630391e-05, + "loss": 3.5648, + "step": 1013248 + }, + { + "epoch": 0.01, + "learning_rate": 3.3402948708793385e-05, + "loss": 3.5683, + "step": 1013760 + }, + { + "epoch": 0.01, + "learning_rate": 3.3394562761282865e-05, + "loss": 3.5716, + "step": 1014272 + }, + { + "epoch": 0.01, + "learning_rate": 3.3386176813772345e-05, + "loss": 3.5732, + "step": 1014784 + }, + { + "epoch": 0.01, + "learning_rate": 3.337780724506556e-05, + "loss": 3.571, + "step": 1015296 + }, + { + "epoch": 0.01, + "learning_rate": 3.3369421297555034e-05, + "loss": 3.5741, + "step": 1015808 + }, + { + "epoch": 0.01, + "learning_rate": 3.3361035350044514e-05, + "loss": 3.5685, + "step": 1016320 + }, + { + "epoch": 0.01, + "learning_rate": 3.3352649402533994e-05, + "loss": 3.5515, + "step": 1016832 + }, + { + "epoch": 0.01, + "learning_rate": 3.334427983382721e-05, + "loss": 3.5727, + "step": 1017344 + }, + { + "epoch": 0.01, + "learning_rate": 3.333589388631669e-05, + "loss": 3.5676, + "step": 1017856 + }, + { + "epoch": 0.01, + "learning_rate": 3.332750793880617e-05, + "loss": 3.5681, + "step": 1018368 + }, + { + "epoch": 0.01, + "learning_rate": 3.331912199129565e-05, + "loss": 3.5678, + "step": 1018880 + }, + { + "epoch": 0.01, + "learning_rate": 3.331075242258886e-05, + "loss": 3.5615, + "step": 1019392 + }, + { + "epoch": 0.01, + "learning_rate": 3.330236647507834e-05, + "loss": 3.5541, + "step": 1019904 + }, + { + "epoch": 0.01, + "learning_rate": 3.329398052756782e-05, + "loss": 3.558, + "step": 1020416 + }, + { + "epoch": 0.01, + "learning_rate": 3.32855945800573e-05, + "loss": 3.5693, + "step": 1020928 + }, + { + "epoch": 0.01, + "learning_rate": 3.327722501135051e-05, + "loss": 3.5563, + "step": 1021440 + }, + { + "epoch": 0.01, + "learning_rate": 3.326883906383999e-05, + "loss": 3.5789, + "step": 1021952 + }, + { + "epoch": 0.01, + "learning_rate": 3.326045311632947e-05, + "loss": 3.571, + "step": 1022464 + }, + { + "epoch": 0.01, + "learning_rate": 3.325206716881895e-05, + "loss": 3.546, + "step": 1022976 + }, + { + "epoch": 0.01, + "learning_rate": 3.3243697600112164e-05, + "loss": 3.5788, + "step": 1023488 + }, + { + "epoch": 0.01, + "learning_rate": 3.3235311652601644e-05, + "loss": 3.5594, + "step": 1024000 + }, + { + "epoch": 0.01, + "learning_rate": 3.3226925705091124e-05, + "loss": 3.5553, + "step": 1024512 + }, + { + "epoch": 0.01, + "learning_rate": 3.3218539757580604e-05, + "loss": 3.5592, + "step": 1025024 + }, + { + "epoch": 0.01, + "learning_rate": 3.321017018887381e-05, + "loss": 3.5661, + "step": 1025536 + }, + { + "epoch": 0.01, + "learning_rate": 3.320178424136329e-05, + "loss": 3.5533, + "step": 1026048 + }, + { + "epoch": 0.01, + "learning_rate": 3.319339829385277e-05, + "loss": 3.5656, + "step": 1026560 + }, + { + "epoch": 0.01, + "learning_rate": 3.318501234634225e-05, + "loss": 3.5493, + "step": 1027072 + }, + { + "epoch": 0.01, + "learning_rate": 3.317664277763546e-05, + "loss": 3.5553, + "step": 1027584 + }, + { + "epoch": 0.01, + "learning_rate": 3.316825683012494e-05, + "loss": 3.5739, + "step": 1028096 + }, + { + "epoch": 0.01, + "learning_rate": 3.315987088261442e-05, + "loss": 3.5628, + "step": 1028608 + }, + { + "epoch": 0.01, + "learning_rate": 3.31514849351039e-05, + "loss": 3.5746, + "step": 1029120 + }, + { + "epoch": 0.01, + "learning_rate": 3.314311536639712e-05, + "loss": 3.5636, + "step": 1029632 + }, + { + "epoch": 0.01, + "learning_rate": 3.31347294188866e-05, + "loss": 3.5789, + "step": 1030144 + }, + { + "epoch": 0.01, + "learning_rate": 3.312634347137608e-05, + "loss": 3.5566, + "step": 1030656 + }, + { + "epoch": 0.01, + "learning_rate": 3.311795752386556e-05, + "loss": 3.5798, + "step": 1031168 + }, + { + "epoch": 0.01, + "learning_rate": 3.3109587955158766e-05, + "loss": 3.563, + "step": 1031680 + }, + { + "epoch": 0.01, + "learning_rate": 3.3101202007648246e-05, + "loss": 3.5588, + "step": 1032192 + }, + { + "epoch": 0.01, + "learning_rate": 3.3092816060137726e-05, + "loss": 3.568, + "step": 1032704 + }, + { + "epoch": 0.01, + "learning_rate": 3.3084430112627206e-05, + "loss": 3.5797, + "step": 1033216 + }, + { + "epoch": 0.01, + "learning_rate": 3.3076060543920415e-05, + "loss": 3.5623, + "step": 1033728 + }, + { + "epoch": 0.01, + "learning_rate": 3.3067674596409895e-05, + "loss": 3.5751, + "step": 1034240 + }, + { + "epoch": 0.01, + "learning_rate": 3.3059288648899375e-05, + "loss": 3.5489, + "step": 1034752 + }, + { + "epoch": 0.01, + "learning_rate": 3.3050902701388855e-05, + "loss": 3.5477, + "step": 1035264 + }, + { + "epoch": 0.01, + "learning_rate": 3.304253313268207e-05, + "loss": 3.5591, + "step": 1035776 + }, + { + "epoch": 0.01, + "learning_rate": 3.303414718517155e-05, + "loss": 3.5638, + "step": 1036288 + }, + { + "epoch": 0.01, + "learning_rate": 3.302576123766103e-05, + "loss": 3.5616, + "step": 1036800 + }, + { + "epoch": 0.01, + "learning_rate": 3.301737529015051e-05, + "loss": 3.5613, + "step": 1037312 + }, + { + "epoch": 0.01, + "learning_rate": 3.300900572144372e-05, + "loss": 3.5617, + "step": 1037824 + }, + { + "epoch": 0.02, + "learning_rate": 3.30006197739332e-05, + "loss": 3.5623, + "step": 1038336 + }, + { + "epoch": 0.02, + "learning_rate": 3.299223382642268e-05, + "loss": 3.561, + "step": 1038848 + }, + { + "epoch": 0.02, + "learning_rate": 3.298384787891216e-05, + "loss": 3.5571, + "step": 1039360 + }, + { + "epoch": 0.02, + "learning_rate": 3.297547831020537e-05, + "loss": 3.5687, + "step": 1039872 + }, + { + "epoch": 0.02, + "learning_rate": 3.296709236269485e-05, + "loss": 3.5817, + "step": 1040384 + }, + { + "epoch": 0.02, + "learning_rate": 3.295870641518433e-05, + "loss": 3.5733, + "step": 1040896 + }, + { + "epoch": 0.02, + "learning_rate": 3.295032046767381e-05, + "loss": 3.5559, + "step": 1041408 + }, + { + "epoch": 0.02, + "learning_rate": 3.2941950898967025e-05, + "loss": 3.5611, + "step": 1041920 + }, + { + "epoch": 0.02, + "learning_rate": 3.2933564951456505e-05, + "loss": 3.5631, + "step": 1042432 + }, + { + "epoch": 0.02, + "learning_rate": 3.2925179003945985e-05, + "loss": 3.5707, + "step": 1042944 + }, + { + "epoch": 0.02, + "learning_rate": 3.2916793056435465e-05, + "loss": 3.5628, + "step": 1043456 + }, + { + "epoch": 0.02, + "learning_rate": 3.2908423487728674e-05, + "loss": 3.5614, + "step": 1043968 + }, + { + "epoch": 0.02, + "learning_rate": 3.2900037540218154e-05, + "loss": 3.5613, + "step": 1044480 + }, + { + "epoch": 0.02, + "learning_rate": 3.2891651592707634e-05, + "loss": 3.5668, + "step": 1044992 + }, + { + "epoch": 0.02, + "learning_rate": 3.2883265645197114e-05, + "loss": 3.5632, + "step": 1045504 + }, + { + "epoch": 0.02, + "learning_rate": 3.287489607649032e-05, + "loss": 3.5603, + "step": 1046016 + }, + { + "epoch": 0.02, + "learning_rate": 3.28665101289798e-05, + "loss": 3.5581, + "step": 1046528 + }, + { + "epoch": 0.02, + "learning_rate": 3.285812418146928e-05, + "loss": 3.5508, + "step": 1047040 + }, + { + "epoch": 0.02, + "learning_rate": 3.284973823395876e-05, + "loss": 3.5626, + "step": 1047552 + }, + { + "epoch": 0.02, + "learning_rate": 3.284136866525198e-05, + "loss": 3.5552, + "step": 1048064 + }, + { + "epoch": 0.02, + "learning_rate": 3.283298271774146e-05, + "loss": 3.5552, + "step": 1048576 + }, + { + "epoch": 0.02, + "learning_rate": 3.282459677023094e-05, + "loss": 3.5575, + "step": 1049088 + }, + { + "epoch": 0.02, + "learning_rate": 3.281621082272042e-05, + "loss": 3.5629, + "step": 1049600 + }, + { + "epoch": 0.02, + "learning_rate": 3.280784125401363e-05, + "loss": 3.5576, + "step": 1050112 + }, + { + "epoch": 0.02, + "learning_rate": 3.279945530650311e-05, + "loss": 3.5694, + "step": 1050624 + }, + { + "epoch": 0.02, + "learning_rate": 3.279106935899259e-05, + "loss": 3.5749, + "step": 1051136 + }, + { + "epoch": 0.02, + "learning_rate": 3.278268341148207e-05, + "loss": 3.5662, + "step": 1051648 + }, + { + "epoch": 0.02, + "learning_rate": 3.2774313842775276e-05, + "loss": 3.5715, + "step": 1052160 + }, + { + "epoch": 0.02, + "learning_rate": 3.2765927895264756e-05, + "loss": 3.5627, + "step": 1052672 + }, + { + "epoch": 0.02, + "learning_rate": 3.2757541947754236e-05, + "loss": 3.5569, + "step": 1053184 + }, + { + "epoch": 0.02, + "learning_rate": 3.2749156000243716e-05, + "loss": 3.5599, + "step": 1053696 + }, + { + "epoch": 0.02, + "learning_rate": 3.274078643153693e-05, + "loss": 3.5456, + "step": 1054208 + }, + { + "epoch": 0.02, + "learning_rate": 3.273240048402641e-05, + "loss": 3.5623, + "step": 1054720 + }, + { + "epoch": 0.02, + "learning_rate": 3.272401453651589e-05, + "loss": 3.5542, + "step": 1055232 + }, + { + "epoch": 0.02, + "learning_rate": 3.27156449678091e-05, + "loss": 3.5658, + "step": 1055744 + }, + { + "epoch": 0.02, + "learning_rate": 3.270725902029858e-05, + "loss": 3.5621, + "step": 1056256 + }, + { + "epoch": 0.02, + "learning_rate": 3.269887307278806e-05, + "loss": 3.5646, + "step": 1056768 + }, + { + "epoch": 0.02, + "learning_rate": 3.269048712527754e-05, + "loss": 3.5547, + "step": 1057280 + }, + { + "epoch": 0.02, + "learning_rate": 3.268211755657075e-05, + "loss": 3.5548, + "step": 1057792 + }, + { + "epoch": 0.02, + "learning_rate": 3.267373160906023e-05, + "loss": 3.5631, + "step": 1058304 + }, + { + "epoch": 0.02, + "learning_rate": 3.266534566154971e-05, + "loss": 3.5673, + "step": 1058816 + }, + { + "epoch": 0.02, + "learning_rate": 3.265695971403919e-05, + "loss": 3.5749, + "step": 1059328 + }, + { + "epoch": 0.02, + "learning_rate": 3.2648590145332406e-05, + "loss": 3.558, + "step": 1059840 + }, + { + "epoch": 0.02, + "learning_rate": 3.2640204197821886e-05, + "loss": 3.5695, + "step": 1060352 + }, + { + "epoch": 0.02, + "learning_rate": 3.2631818250311366e-05, + "loss": 3.5609, + "step": 1060864 + }, + { + "epoch": 0.02, + "learning_rate": 3.2623432302800846e-05, + "loss": 3.566, + "step": 1061376 + }, + { + "epoch": 0.02, + "learning_rate": 3.2615062734094055e-05, + "loss": 3.5675, + "step": 1061888 + }, + { + "epoch": 0.02, + "learning_rate": 3.2606676786583535e-05, + "loss": 3.5588, + "step": 1062400 + }, + { + "epoch": 0.02, + "learning_rate": 3.2598290839073015e-05, + "loss": 3.5563, + "step": 1062912 + }, + { + "epoch": 0.02, + "learning_rate": 3.2589904891562495e-05, + "loss": 3.5701, + "step": 1063424 + }, + { + "epoch": 0.02, + "learning_rate": 3.2581535322855704e-05, + "loss": 3.5588, + "step": 1063936 + }, + { + "epoch": 0.02, + "learning_rate": 3.2573149375345184e-05, + "loss": 3.5561, + "step": 1064448 + }, + { + "epoch": 0.02, + "learning_rate": 3.2564763427834664e-05, + "loss": 3.5661, + "step": 1064960 + }, + { + "epoch": 0.02, + "learning_rate": 3.2556377480324144e-05, + "loss": 3.5655, + "step": 1065472 + }, + { + "epoch": 0.02, + "learning_rate": 3.254800791161736e-05, + "loss": 3.5593, + "step": 1065984 + }, + { + "epoch": 0.02, + "learning_rate": 3.253962196410684e-05, + "loss": 3.5646, + "step": 1066496 + }, + { + "epoch": 0.02, + "learning_rate": 3.253123601659632e-05, + "loss": 3.5603, + "step": 1067008 + }, + { + "epoch": 0.02, + "learning_rate": 3.25228500690858e-05, + "loss": 3.5694, + "step": 1067520 + }, + { + "epoch": 0.02, + "learning_rate": 3.251448050037901e-05, + "loss": 3.5599, + "step": 1068032 + }, + { + "epoch": 0.03, + "eval_loss": 3.8334579467773438, + "eval_runtime": 302.2005, + "eval_samples_per_second": 1262.708, + "eval_steps_per_second": 39.461, + "step": 1068471 + }, + { + "epoch": 0.0, + "learning_rate": 3.250609455286849e-05, + "loss": 3.5534, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.249770860535797e-05, + "loss": 3.549, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.248932265784745e-05, + "loss": 3.5591, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.248093671033693e-05, + "loss": 3.5731, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.247256714163014e-05, + "loss": 3.5635, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.246418119411962e-05, + "loss": 3.5591, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.24557952466091e-05, + "loss": 3.5546, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.244740929909858e-05, + "loss": 3.556, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.243903973039179e-05, + "loss": 3.5469, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.243065378288127e-05, + "loss": 3.5543, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.242226783537075e-05, + "loss": 3.5595, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.241388188786023e-05, + "loss": 3.5705, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.240551231915344e-05, + "loss": 3.567, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.239712637164292e-05, + "loss": 3.5337, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.23887404241324e-05, + "loss": 3.5541, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.238035447662188e-05, + "loss": 3.5415, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.237198490791509e-05, + "loss": 3.5586, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.236359896040457e-05, + "loss": 3.5518, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.235521301289405e-05, + "loss": 3.557, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.234682706538353e-05, + "loss": 3.5523, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.233845749667675e-05, + "loss": 3.5713, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.233007154916623e-05, + "loss": 3.555, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.232168560165571e-05, + "loss": 3.5563, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.231329965414518e-05, + "loss": 3.5498, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.2304930085438396e-05, + "loss": 3.5648, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.2296544137927876e-05, + "loss": 3.5509, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.2288158190417356e-05, + "loss": 3.549, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.227977224290683e-05, + "loss": 3.5557, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.2271402674200045e-05, + "loss": 3.5514, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.2263016726689525e-05, + "loss": 3.5484, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.2254630779179005e-05, + "loss": 3.5537, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.2246244831668485e-05, + "loss": 3.5542, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.22378752629617e-05, + "loss": 3.5582, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.222948931545118e-05, + "loss": 3.558, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.2221103367940654e-05, + "loss": 3.5584, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.2212717420430134e-05, + "loss": 3.555, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.220434785172335e-05, + "loss": 3.5612, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.219596190421283e-05, + "loss": 3.5402, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.21875759567023e-05, + "loss": 3.5524, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.217919000919178e-05, + "loss": 3.5521, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.2170820440485e-05, + "loss": 3.5414, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.216243449297447e-05, + "loss": 3.552, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.215404854546396e-05, + "loss": 3.5556, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.214566259795344e-05, + "loss": 3.5488, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.2137293029246654e-05, + "loss": 3.5562, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.212890708173613e-05, + "loss": 3.554, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.212052113422561e-05, + "loss": 3.5576, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.211213518671509e-05, + "loss": 3.5523, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.21037656180083e-05, + "loss": 3.5387, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.2095379670497776e-05, + "loss": 3.5537, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.2086993722987256e-05, + "loss": 3.5526, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.2078607775476736e-05, + "loss": 3.556, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.2070238206769945e-05, + "loss": 3.5493, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.2061852259259425e-05, + "loss": 3.5451, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.205348269055264e-05, + "loss": 3.5389, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.204509674304213e-05, + "loss": 3.5408, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.20367107955316e-05, + "loss": 3.5525, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.202832484802108e-05, + "loss": 3.5391, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.201993890051056e-05, + "loss": 3.5609, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.201155295300004e-05, + "loss": 3.5549, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.200316700548952e-05, + "loss": 3.5314, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.199479743678273e-05, + "loss": 3.5612, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.198641148927221e-05, + "loss": 3.5409, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.197802554176169e-05, + "loss": 3.5409, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.196963959425117e-05, + "loss": 3.5384, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.196127002554438e-05, + "loss": 3.5488, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.1952884078033866e-05, + "loss": 3.5382, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.1944498130523346e-05, + "loss": 3.5517, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.1936112183012825e-05, + "loss": 3.5281, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.1927742614306035e-05, + "loss": 3.5413, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.1919356666795515e-05, + "loss": 3.5541, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.1910970719284995e-05, + "loss": 3.5478, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.1902584771774474e-05, + "loss": 3.5581, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.1894215203067684e-05, + "loss": 3.5491, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.1885829255557164e-05, + "loss": 3.5604, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.1877443308046643e-05, + "loss": 3.5437, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.1869057360536123e-05, + "loss": 3.565, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.186068779182933e-05, + "loss": 3.5433, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.185230184431882e-05, + "loss": 3.5437, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.18439158968083e-05, + "loss": 3.5532, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.183552994929778e-05, + "loss": 3.559, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.182716038059099e-05, + "loss": 3.5499, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.181877443308047e-05, + "loss": 3.5559, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.181038848556995e-05, + "loss": 3.5365, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.180200253805943e-05, + "loss": 3.5291, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.179363296935264e-05, + "loss": 3.5425, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.178524702184212e-05, + "loss": 3.5503, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.17768610743316e-05, + "loss": 3.543, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.176847512682108e-05, + "loss": 3.543, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.1760105558114286e-05, + "loss": 3.548, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.175171961060377e-05, + "loss": 3.5436, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.174333366309325e-05, + "loss": 3.5441, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.173494771558273e-05, + "loss": 3.5414, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.172657814687594e-05, + "loss": 3.5549, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.171819219936542e-05, + "loss": 3.5638, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.17098062518549e-05, + "loss": 3.5553, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.170142030434438e-05, + "loss": 3.5385, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.169303435683386e-05, + "loss": 3.5472, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.168466478812707e-05, + "loss": 3.5454, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.167627884061655e-05, + "loss": 3.5535, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.166789289310603e-05, + "loss": 3.5484, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.165952332439924e-05, + "loss": 3.5424, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.165113737688872e-05, + "loss": 3.5448, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.1642751429378207e-05, + "loss": 3.5466, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.1634365481867686e-05, + "loss": 3.548, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.1625995913160896e-05, + "loss": 3.5436, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.1617609965650376e-05, + "loss": 3.5451, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.1609224018139856e-05, + "loss": 3.5348, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.1600838070629335e-05, + "loss": 3.5464, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.1592468501922545e-05, + "loss": 3.5355, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.1584082554412025e-05, + "loss": 3.5375, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.1575696606901504e-05, + "loss": 3.5425, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.1567310659390984e-05, + "loss": 3.5473, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.1558941090684194e-05, + "loss": 3.5424, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.1550555143173673e-05, + "loss": 3.5493, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.154218557446689e-05, + "loss": 3.5574, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.153379962695637e-05, + "loss": 3.5529, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.152541367944585e-05, + "loss": 3.5545, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.151702773193533e-05, + "loss": 3.5437, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.150864178442481e-05, + "loss": 3.5444, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.150025583691429e-05, + "loss": 3.5431, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.149186988940377e-05, + "loss": 3.5281, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.148350032069698e-05, + "loss": 3.5458, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.147511437318646e-05, + "loss": 3.5391, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.146672842567594e-05, + "loss": 3.5497, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.145834247816542e-05, + "loss": 3.5419, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.144997290945863e-05, + "loss": 3.5475, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.1441586961948114e-05, + "loss": 3.5392, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.1433201014437594e-05, + "loss": 3.5409, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.1424815066927074e-05, + "loss": 3.5498, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.141644549822028e-05, + "loss": 3.5478, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.140805955070976e-05, + "loss": 3.5603, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.139967360319924e-05, + "loss": 3.545, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.139128765568872e-05, + "loss": 3.5511, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.138291808698193e-05, + "loss": 3.5465, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.137453213947141e-05, + "loss": 3.5467, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.136614619196089e-05, + "loss": 3.5526, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.135776024445037e-05, + "loss": 3.543, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.134939067574358e-05, + "loss": 3.5471, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.134100472823307e-05, + "loss": 3.5532, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.133261878072255e-05, + "loss": 3.5421, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.132423283321203e-05, + "loss": 3.5417, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.1315863264505237e-05, + "loss": 3.5495, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.1307477316994717e-05, + "loss": 3.5476, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.1299091369484196e-05, + "loss": 3.5422, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.1290705421973676e-05, + "loss": 3.5492, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.1282335853266886e-05, + "loss": 3.5408, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.1273949905756365e-05, + "loss": 3.5598, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.1265563958245845e-05, + "loss": 3.5412, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 3.834336280822754, + "eval_runtime": 312.7533, + "eval_samples_per_second": 1220.102, + "eval_steps_per_second": 38.129, + "step": 1144791 + }, + { + "epoch": 1.0, + "learning_rate": 3.1257178010735325e-05, + "loss": 3.5387, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.1248808442028534e-05, + "loss": 3.5391, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.124042249451802e-05, + "loss": 3.5357, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.12320365470075e-05, + "loss": 3.5578, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.1223650599496974e-05, + "loss": 3.5453, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.121528103079019e-05, + "loss": 3.546, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.120689508327967e-05, + "loss": 3.5361, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.119850913576915e-05, + "loss": 3.5416, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.119012318825862e-05, + "loss": 3.5322, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.118175361955184e-05, + "loss": 3.5385, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.117336767204132e-05, + "loss": 3.5433, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.11649817245308e-05, + "loss": 3.5533, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.115659577702027e-05, + "loss": 3.551, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.114822620831349e-05, + "loss": 3.5204, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.1139840260802975e-05, + "loss": 3.5353, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.113145431329245e-05, + "loss": 3.5299, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.112306836578193e-05, + "loss": 3.5402, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.1114698797075144e-05, + "loss": 3.533, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.1106312849564624e-05, + "loss": 3.5403, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.10979269020541e-05, + "loss": 3.5373, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.108954095454358e-05, + "loss": 3.5572, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.108117138583679e-05, + "loss": 3.5435, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.1072785438326266e-05, + "loss": 3.5364, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.1064399490815746e-05, + "loss": 3.5359, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.1056013543305226e-05, + "loss": 3.5502, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.104764397459844e-05, + "loss": 3.5367, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.103925802708792e-05, + "loss": 3.5312, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.10308720795774e-05, + "loss": 3.5408, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.102248613206688e-05, + "loss": 3.5334, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.10141165633601e-05, + "loss": 3.5314, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.100573061584957e-05, + "loss": 3.5374, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.099734466833905e-05, + "loss": 3.5359, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.098895872082853e-05, + "loss": 3.5434, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.098058915212174e-05, + "loss": 3.5431, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.097220320461122e-05, + "loss": 3.5433, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.09638172571007e-05, + "loss": 3.5385, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.095543130959018e-05, + "loss": 3.5436, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.0947061740883395e-05, + "loss": 3.5274, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.0938675793372875e-05, + "loss": 3.5363, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.0930289845862355e-05, + "loss": 3.5351, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.0921903898351835e-05, + "loss": 3.529, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.0913534329645044e-05, + "loss": 3.5365, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.0905148382134524e-05, + "loss": 3.542, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.0896762434624004e-05, + "loss": 3.5313, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.0888376487113484e-05, + "loss": 3.5406, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.0880006918406693e-05, + "loss": 3.542, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.087162097089617e-05, + "loss": 3.54, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.086323502338565e-05, + "loss": 3.538, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.085484907587513e-05, + "loss": 3.5211, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.084647950716835e-05, + "loss": 3.5349, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.083809355965783e-05, + "loss": 3.5408, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.082970761214731e-05, + "loss": 3.5367, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.082132166463679e-05, + "loss": 3.5342, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.081295209593e-05, + "loss": 3.5275, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.0804582527223214e-05, + "loss": 3.5219, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.079619657971269e-05, + "loss": 3.5245, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.078781063220217e-05, + "loss": 3.5368, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.077942468469165e-05, + "loss": 3.5291, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.077103873718113e-05, + "loss": 3.5423, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.076265278967061e-05, + "loss": 3.537, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.075426684216009e-05, + "loss": 3.5221, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.07458972734533e-05, + "loss": 3.5443, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.073751132594278e-05, + "loss": 3.5224, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.072912537843226e-05, + "loss": 3.5244, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.072073943092174e-05, + "loss": 3.524, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.071236986221495e-05, + "loss": 3.5353, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.070398391470443e-05, + "loss": 3.5219, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.069559796719391e-05, + "loss": 3.5335, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.068721201968339e-05, + "loss": 3.5151, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.06788424509766e-05, + "loss": 3.5238, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.067045650346608e-05, + "loss": 3.5409, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.066207055595556e-05, + "loss": 3.5331, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.065368460844504e-05, + "loss": 3.5348, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.0645315039738256e-05, + "loss": 3.5382, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.0636929092227736e-05, + "loss": 3.5425, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.0628543144717216e-05, + "loss": 3.5295, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.0620157197206696e-05, + "loss": 3.5493, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.0611787628499905e-05, + "loss": 3.5261, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.0603401680989385e-05, + "loss": 3.5271, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.0595015733478865e-05, + "loss": 3.5362, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.0586629785968345e-05, + "loss": 3.5416, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.0578260217261554e-05, + "loss": 3.5331, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.0569874269751034e-05, + "loss": 3.5432, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.0561488322240514e-05, + "loss": 3.5243, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.0553102374729994e-05, + "loss": 3.5103, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.054473280602321e-05, + "loss": 3.5254, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.053634685851269e-05, + "loss": 3.535, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.052796091100217e-05, + "loss": 3.5251, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.051957496349165e-05, + "loss": 3.527, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.051120539478486e-05, + "loss": 3.5349, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.050281944727434e-05, + "loss": 3.5246, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.049443349976382e-05, + "loss": 3.5288, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.04860475522533e-05, + "loss": 3.5266, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.047767798354651e-05, + "loss": 3.5385, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.046929203603599e-05, + "loss": 3.5481, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.046090608852547e-05, + "loss": 3.5432, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.045252014101495e-05, + "loss": 3.5212, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.044415057230816e-05, + "loss": 3.5337, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.043576462479764e-05, + "loss": 3.5308, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.042737867728712e-05, + "loss": 3.5369, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.04189927297766e-05, + "loss": 3.5343, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.0410623161069813e-05, + "loss": 3.5278, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.0402237213559293e-05, + "loss": 3.5291, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.0393851266048773e-05, + "loss": 3.5348, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.0385465318538253e-05, + "loss": 3.533, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.0377095749831465e-05, + "loss": 3.5299, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.0368709802320945e-05, + "loss": 3.5278, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.0360323854810425e-05, + "loss": 3.5212, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.0351937907299905e-05, + "loss": 3.5316, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.0343568338593114e-05, + "loss": 3.5202, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.0335182391082594e-05, + "loss": 3.5207, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.0326796443572074e-05, + "loss": 3.5237, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.0318410496061554e-05, + "loss": 3.5335, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.0310040927354766e-05, + "loss": 3.5299, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.0301654979844246e-05, + "loss": 3.5287, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.0293285411137455e-05, + "loss": 3.5439, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.0284899463626935e-05, + "loss": 3.5395, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.0276513516116415e-05, + "loss": 3.5391, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.02681275686059e-05, + "loss": 3.5294, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.025974162109538e-05, + "loss": 3.529, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.025135567358486e-05, + "loss": 3.5249, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.024296972607434e-05, + "loss": 3.5158, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.023458377856382e-05, + "loss": 3.5286, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.0226214209857028e-05, + "loss": 3.5254, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.0217828262346508e-05, + "loss": 3.5324, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.020944231483599e-05, + "loss": 3.5258, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.02010727461292e-05, + "loss": 3.5345, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.019268679861868e-05, + "loss": 3.5282, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.018430085110816e-05, + "loss": 3.5246, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.017591490359764e-05, + "loss": 3.5309, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.016752895608712e-05, + "loss": 3.5335, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.0159159387380332e-05, + "loss": 3.5426, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.0150773439869812e-05, + "loss": 3.5314, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.0142387492359292e-05, + "loss": 3.536, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.0134001544848765e-05, + "loss": 3.5326, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.012563197614198e-05, + "loss": 3.5308, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.011724602863146e-05, + "loss": 3.5338, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.0108860081120945e-05, + "loss": 3.5295, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.0100474133610418e-05, + "loss": 3.532, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.0092104564903634e-05, + "loss": 3.5385, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.0083718617393114e-05, + "loss": 3.5274, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.0075332669882594e-05, + "loss": 3.5255, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.006694672237207e-05, + "loss": 3.5322, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.0058577153665286e-05, + "loss": 3.5318, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.0050191206154766e-05, + "loss": 3.5267, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.004180525864424e-05, + "loss": 3.539, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.003341931113372e-05, + "loss": 3.5243, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.0025049742426935e-05, + "loss": 3.5408, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.0016663794916415e-05, + "loss": 3.5247, + "step": 1220608 + }, + { + "epoch": 1.03, + "eval_loss": 3.8361692428588867, + "eval_runtime": 308.0274, + "eval_samples_per_second": 1238.822, + "eval_steps_per_second": 38.714, + "step": 1221111 + }, + { + "epoch": 0.0, + "learning_rate": 3.000827784740589e-05, + "loss": 3.48, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 2.999989189989537e-05, + "loss": 3.5243, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.999150595238485e-05, + "loss": 3.5206, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.9983136383678067e-05, + "loss": 3.5417, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.9974750436167544e-05, + "loss": 3.5333, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.9966364488657024e-05, + "loss": 3.5314, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.9957978541146504e-05, + "loss": 3.5209, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.9949592593635984e-05, + "loss": 3.5284, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.9941206646125464e-05, + "loss": 3.5139, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.9932820698614944e-05, + "loss": 3.5277, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.9924434751104424e-05, + "loss": 3.5245, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.9916065182397636e-05, + "loss": 3.5402, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.9907695613690845e-05, + "loss": 3.538, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.9899309666180325e-05, + "loss": 3.5061, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.9890923718669805e-05, + "loss": 3.5178, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.9882537771159285e-05, + "loss": 3.5186, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.9874151823648765e-05, + "loss": 3.5199, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.9865765876138245e-05, + "loss": 3.5256, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.985737992862773e-05, + "loss": 3.5263, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.9848993981117208e-05, + "loss": 3.518, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.9840624412410417e-05, + "loss": 3.542, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.9832238464899897e-05, + "loss": 3.5292, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.9823852517389377e-05, + "loss": 3.5217, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.9815466569878857e-05, + "loss": 3.5192, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.980709700117207e-05, + "loss": 3.5365, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.979871105366155e-05, + "loss": 3.5202, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.979032510615103e-05, + "loss": 3.5181, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.978193915864051e-05, + "loss": 3.5265, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.977356958993372e-05, + "loss": 3.5168, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.97651836424232e-05, + "loss": 3.5191, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.9756797694912682e-05, + "loss": 3.522, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.9748411747402162e-05, + "loss": 3.524, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.974004217869537e-05, + "loss": 3.5241, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.973165623118485e-05, + "loss": 3.5254, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.972327028367433e-05, + "loss": 3.5308, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.971488433616381e-05, + "loss": 3.5238, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.9706514767457023e-05, + "loss": 3.5296, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.9698128819946503e-05, + "loss": 3.5117, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.9689742872435983e-05, + "loss": 3.521, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.9681356924925463e-05, + "loss": 3.5159, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.9672987356218672e-05, + "loss": 3.5189, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.9664601408708152e-05, + "loss": 3.5176, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.9656215461197632e-05, + "loss": 3.5279, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.9647829513687116e-05, + "loss": 3.5178, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.9639443566176596e-05, + "loss": 3.5261, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.9631057618666076e-05, + "loss": 3.5273, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.962267167115555e-05, + "loss": 3.5292, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.961428572364503e-05, + "loss": 3.5209, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.9605916154938245e-05, + "loss": 3.5054, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.9597530207427724e-05, + "loss": 3.5165, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.95891442599172e-05, + "loss": 3.5309, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.958075831240668e-05, + "loss": 3.5233, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.9572388743699897e-05, + "loss": 3.5146, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.956400279618937e-05, + "loss": 3.5147, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.9555633227482586e-05, + "loss": 3.5123, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.954724727997207e-05, + "loss": 3.5059, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.953886133246155e-05, + "loss": 3.5259, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.9530475384951022e-05, + "loss": 3.5106, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.9522089437440502e-05, + "loss": 3.5262, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.9513703489929982e-05, + "loss": 3.5219, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.9505317542419462e-05, + "loss": 3.5086, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.9496947973712675e-05, + "loss": 3.5293, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.9488562026202155e-05, + "loss": 3.5113, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.9480176078691635e-05, + "loss": 3.5156, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.9471790131181115e-05, + "loss": 3.5036, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.9463420562474324e-05, + "loss": 3.5243, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.9455034614963807e-05, + "loss": 3.51, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.9446665046257023e-05, + "loss": 3.5146, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.9438279098746496e-05, + "loss": 3.5021, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.9429893151235976e-05, + "loss": 3.5103, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.9421507203725456e-05, + "loss": 3.5219, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.9413121256214936e-05, + "loss": 3.5248, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.9404735308704416e-05, + "loss": 3.518, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.93963493611939e-05, + "loss": 3.5199, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.938797979248711e-05, + "loss": 3.5292, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.937959384497659e-05, + "loss": 3.5125, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.9371207897466068e-05, + "loss": 3.5352, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.9362821949955548e-05, + "loss": 3.5116, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.935445238124876e-05, + "loss": 3.5146, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.934608281254197e-05, + "loss": 3.5201, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.933769686503145e-05, + "loss": 3.5257, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.932931091752093e-05, + "loss": 3.5184, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.932092497001041e-05, + "loss": 3.532, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.931253902249989e-05, + "loss": 3.5117, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.930415307498937e-05, + "loss": 3.4959, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.9295767127478853e-05, + "loss": 3.5104, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.9287381179968333e-05, + "loss": 3.5175, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.9279011611261542e-05, + "loss": 3.511, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.9270625663751022e-05, + "loss": 3.512, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.9262239716240502e-05, + "loss": 3.5232, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.9253853768729982e-05, + "loss": 3.5122, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.9245484200023194e-05, + "loss": 3.514, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.9237098252512674e-05, + "loss": 3.5135, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.9228712305002154e-05, + "loss": 3.5234, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.9220326357491634e-05, + "loss": 3.5321, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.9211940409981114e-05, + "loss": 3.527, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.9203554462470594e-05, + "loss": 3.5071, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.9195168514960074e-05, + "loss": 3.5178, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.9186782567449554e-05, + "loss": 3.5184, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.9178412998742767e-05, + "loss": 3.5211, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.9170027051232246e-05, + "loss": 3.5202, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.9161641103721726e-05, + "loss": 3.5151, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.9153255156211206e-05, + "loss": 3.5101, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.9144885587504415e-05, + "loss": 3.5215, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.91364996399939e-05, + "loss": 3.5207, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.912811369248338e-05, + "loss": 3.5098, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.911972774497286e-05, + "loss": 3.5176, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.9111358176266068e-05, + "loss": 3.5096, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.9102972228755548e-05, + "loss": 3.5108, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.9094586281245028e-05, + "loss": 3.5084, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.9086200333734504e-05, + "loss": 3.5099, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.907783076502772e-05, + "loss": 3.5059, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.90694448175172e-05, + "loss": 3.5182, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.906105887000668e-05, + "loss": 3.5163, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.9052672922496153e-05, + "loss": 3.5122, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.90443197325931e-05, + "loss": 3.5305, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.903593378508258e-05, + "loss": 3.5252, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.902754783757206e-05, + "loss": 3.5222, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.901916189006154e-05, + "loss": 3.5181, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.901079232135475e-05, + "loss": 3.5146, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.900240637384423e-05, + "loss": 3.5097, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.8994020426333714e-05, + "loss": 3.5046, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.8985634478823194e-05, + "loss": 3.5111, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.8977248531312674e-05, + "loss": 3.5138, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.8968862583802154e-05, + "loss": 3.5166, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.8960476636291627e-05, + "loss": 3.5126, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.8952090688781107e-05, + "loss": 3.5211, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.8943721120074323e-05, + "loss": 3.5152, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.8935335172563803e-05, + "loss": 3.5115, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.892694922505328e-05, + "loss": 3.5103, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.891856327754276e-05, + "loss": 3.5265, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.8910193708835975e-05, + "loss": 3.5261, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.8901807761325452e-05, + "loss": 3.5163, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.8893421813814932e-05, + "loss": 3.5163, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.888503586630441e-05, + "loss": 3.5209, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.8876666297597628e-05, + "loss": 3.5208, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.88682803500871e-05, + "loss": 3.5192, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.885989440257658e-05, + "loss": 3.5145, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.885150845506606e-05, + "loss": 3.5178, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.8843138886359276e-05, + "loss": 3.5213, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.8834752938848753e-05, + "loss": 3.5125, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.8826366991338233e-05, + "loss": 3.5131, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.8817981043827713e-05, + "loss": 3.5168, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.8809611475120922e-05, + "loss": 3.5198, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.8801225527610402e-05, + "loss": 3.5086, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.8792839580099885e-05, + "loss": 3.5253, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.8784453632589365e-05, + "loss": 3.5126, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.8776084063882574e-05, + "loss": 3.5232, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.8767698116372054e-05, + "loss": 3.514, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.8759312168861534e-05, + "loss": 3.5081, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 3.8377773761749268, + "eval_runtime": 321.918, + "eval_samples_per_second": 1185.367, + "eval_steps_per_second": 37.044, + "step": 1297431 + }, + { + "epoch": 0.0, + "learning_rate": 2.8750926221351014e-05, + "loss": 3.5081, + "step": 1297920 + }, + { + "epoch": 0.0, + "learning_rate": 2.8742540273840494e-05, + "loss": 3.5062, + "step": 1298432 + }, + { + "epoch": 0.0, + "learning_rate": 2.8734154326329978e-05, + "loss": 3.527, + "step": 1298944 + }, + { + "epoch": 0.0, + "learning_rate": 2.8725784757623187e-05, + "loss": 3.5139, + "step": 1299456 + }, + { + "epoch": 0.0, + "learning_rate": 2.8717398810112667e-05, + "loss": 3.5209, + "step": 1299968 + }, + { + "epoch": 0.0, + "learning_rate": 2.8709029241405876e-05, + "loss": 3.5116, + "step": 1300480 + }, + { + "epoch": 0.0, + "learning_rate": 2.8700643293895356e-05, + "loss": 3.508, + "step": 1300992 + }, + { + "epoch": 0.0, + "learning_rate": 2.869225734638484e-05, + "loss": 3.5021, + "step": 1301504 + }, + { + "epoch": 0.0, + "learning_rate": 2.868387139887432e-05, + "loss": 3.5139, + "step": 1302016 + }, + { + "epoch": 0.0, + "learning_rate": 2.86754854513638e-05, + "loss": 3.5061, + "step": 1302528 + }, + { + "epoch": 0.0, + "learning_rate": 2.866709950385328e-05, + "loss": 3.5304, + "step": 1303040 + }, + { + "epoch": 0.0, + "learning_rate": 2.865871355634276e-05, + "loss": 3.5191, + "step": 1303552 + }, + { + "epoch": 0.0, + "learning_rate": 2.8650343987635968e-05, + "loss": 3.5001, + "step": 1304064 + }, + { + "epoch": 0.0, + "learning_rate": 2.8641958040125448e-05, + "loss": 3.5022, + "step": 1304576 + }, + { + "epoch": 0.0, + "learning_rate": 2.863357209261493e-05, + "loss": 3.5052, + "step": 1305088 + }, + { + "epoch": 0.0, + "learning_rate": 2.862518614510441e-05, + "loss": 3.4991, + "step": 1305600 + }, + { + "epoch": 0.0, + "learning_rate": 2.861680019759389e-05, + "loss": 3.5123, + "step": 1306112 + }, + { + "epoch": 0.0, + "learning_rate": 2.860841425008337e-05, + "loss": 3.5141, + "step": 1306624 + }, + { + "epoch": 0.0, + "learning_rate": 2.860002830257285e-05, + "loss": 3.5002, + "step": 1307136 + }, + { + "epoch": 0.0, + "learning_rate": 2.859165873386606e-05, + "loss": 3.5304, + "step": 1307648 + }, + { + "epoch": 0.0, + "learning_rate": 2.858327278635554e-05, + "loss": 3.5122, + "step": 1308160 + }, + { + "epoch": 0.0, + "learning_rate": 2.8574886838845023e-05, + "loss": 3.5092, + "step": 1308672 + }, + { + "epoch": 0.0, + "learning_rate": 2.8566500891334503e-05, + "loss": 3.5063, + "step": 1309184 + }, + { + "epoch": 0.0, + "learning_rate": 2.8558131322627713e-05, + "loss": 3.5233, + "step": 1309696 + }, + { + "epoch": 0.0, + "learning_rate": 2.8549745375117192e-05, + "loss": 3.5045, + "step": 1310208 + }, + { + "epoch": 0.0, + "learning_rate": 2.8541359427606672e-05, + "loss": 3.5108, + "step": 1310720 + }, + { + "epoch": 0.0, + "learning_rate": 2.8532973480096152e-05, + "loss": 3.5086, + "step": 1311232 + }, + { + "epoch": 0.0, + "learning_rate": 2.8524603911389365e-05, + "loss": 3.5058, + "step": 1311744 + }, + { + "epoch": 0.0, + "learning_rate": 2.8516217963878845e-05, + "loss": 3.5007, + "step": 1312256 + }, + { + "epoch": 0.01, + "learning_rate": 2.8507832016368325e-05, + "loss": 3.5089, + "step": 1312768 + }, + { + "epoch": 0.01, + "learning_rate": 2.8499446068857805e-05, + "loss": 3.5119, + "step": 1313280 + }, + { + "epoch": 0.01, + "learning_rate": 2.8491076500151014e-05, + "loss": 3.5088, + "step": 1313792 + }, + { + "epoch": 0.01, + "learning_rate": 2.8482690552640494e-05, + "loss": 3.5118, + "step": 1314304 + }, + { + "epoch": 0.01, + "learning_rate": 2.8474304605129977e-05, + "loss": 3.5189, + "step": 1314816 + }, + { + "epoch": 0.01, + "learning_rate": 2.8465918657619457e-05, + "loss": 3.5079, + "step": 1315328 + }, + { + "epoch": 0.01, + "learning_rate": 2.8457549088912666e-05, + "loss": 3.5158, + "step": 1315840 + }, + { + "epoch": 0.01, + "learning_rate": 2.8449163141402146e-05, + "loss": 3.5, + "step": 1316352 + }, + { + "epoch": 0.01, + "learning_rate": 2.8440777193891626e-05, + "loss": 3.511, + "step": 1316864 + }, + { + "epoch": 0.01, + "learning_rate": 2.8432391246381106e-05, + "loss": 3.4996, + "step": 1317376 + }, + { + "epoch": 0.01, + "learning_rate": 2.8424038056478048e-05, + "loss": 3.5086, + "step": 1317888 + }, + { + "epoch": 0.01, + "learning_rate": 2.8415652108967528e-05, + "loss": 3.5043, + "step": 1318400 + }, + { + "epoch": 0.01, + "learning_rate": 2.8407266161457008e-05, + "loss": 3.5143, + "step": 1318912 + }, + { + "epoch": 0.01, + "learning_rate": 2.8398880213946488e-05, + "loss": 3.5029, + "step": 1319424 + }, + { + "epoch": 0.01, + "learning_rate": 2.8390494266435968e-05, + "loss": 3.5136, + "step": 1319936 + }, + { + "epoch": 0.01, + "learning_rate": 2.8382108318925447e-05, + "loss": 3.5122, + "step": 1320448 + }, + { + "epoch": 0.01, + "learning_rate": 2.837372237141493e-05, + "loss": 3.5146, + "step": 1320960 + }, + { + "epoch": 0.01, + "learning_rate": 2.836533642390441e-05, + "loss": 3.5061, + "step": 1321472 + }, + { + "epoch": 0.01, + "learning_rate": 2.835696685519762e-05, + "loss": 3.4963, + "step": 1321984 + }, + { + "epoch": 0.01, + "learning_rate": 2.83485809076871e-05, + "loss": 3.5017, + "step": 1322496 + }, + { + "epoch": 0.01, + "learning_rate": 2.834019496017658e-05, + "loss": 3.5176, + "step": 1323008 + }, + { + "epoch": 0.01, + "learning_rate": 2.8331809012666056e-05, + "loss": 3.5069, + "step": 1323520 + }, + { + "epoch": 0.01, + "learning_rate": 2.8323439443959272e-05, + "loss": 3.5022, + "step": 1324032 + }, + { + "epoch": 0.01, + "learning_rate": 2.8315053496448752e-05, + "loss": 3.4987, + "step": 1324544 + }, + { + "epoch": 0.01, + "learning_rate": 2.830668392774196e-05, + "loss": 3.5041, + "step": 1325056 + }, + { + "epoch": 0.01, + "learning_rate": 2.829829798023144e-05, + "loss": 3.4859, + "step": 1325568 + }, + { + "epoch": 0.01, + "learning_rate": 2.828991203272092e-05, + "loss": 3.5167, + "step": 1326080 + }, + { + "epoch": 0.01, + "learning_rate": 2.82815260852104e-05, + "loss": 3.4954, + "step": 1326592 + }, + { + "epoch": 0.01, + "learning_rate": 2.8273140137699884e-05, + "loss": 3.5119, + "step": 1327104 + }, + { + "epoch": 0.01, + "learning_rate": 2.8264754190189358e-05, + "loss": 3.5098, + "step": 1327616 + }, + { + "epoch": 0.01, + "learning_rate": 2.8256368242678838e-05, + "loss": 3.4966, + "step": 1328128 + }, + { + "epoch": 0.01, + "learning_rate": 2.8247982295168318e-05, + "loss": 3.5106, + "step": 1328640 + }, + { + "epoch": 0.01, + "learning_rate": 2.823961272646153e-05, + "loss": 3.498, + "step": 1329152 + }, + { + "epoch": 0.01, + "learning_rate": 2.823122677895101e-05, + "loss": 3.5027, + "step": 1329664 + }, + { + "epoch": 0.01, + "learning_rate": 2.822284083144049e-05, + "loss": 3.4876, + "step": 1330176 + }, + { + "epoch": 0.01, + "learning_rate": 2.821445488392997e-05, + "loss": 3.5095, + "step": 1330688 + }, + { + "epoch": 0.01, + "learning_rate": 2.820608531522318e-05, + "loss": 3.4968, + "step": 1331200 + }, + { + "epoch": 0.01, + "learning_rate": 2.8197715746516395e-05, + "loss": 3.5045, + "step": 1331712 + }, + { + "epoch": 0.01, + "learning_rate": 2.8189329799005875e-05, + "loss": 3.4866, + "step": 1332224 + }, + { + "epoch": 0.01, + "learning_rate": 2.8180943851495355e-05, + "loss": 3.4965, + "step": 1332736 + }, + { + "epoch": 0.01, + "learning_rate": 2.817255790398483e-05, + "loss": 3.5056, + "step": 1333248 + }, + { + "epoch": 0.01, + "learning_rate": 2.816417195647431e-05, + "loss": 3.509, + "step": 1333760 + }, + { + "epoch": 0.01, + "learning_rate": 2.815578600896379e-05, + "loss": 3.5092, + "step": 1334272 + }, + { + "epoch": 0.01, + "learning_rate": 2.814740006145327e-05, + "loss": 3.5083, + "step": 1334784 + }, + { + "epoch": 0.01, + "learning_rate": 2.813901411394275e-05, + "loss": 3.5115, + "step": 1335296 + }, + { + "epoch": 0.01, + "learning_rate": 2.8130644545235964e-05, + "loss": 3.5043, + "step": 1335808 + }, + { + "epoch": 0.01, + "learning_rate": 2.8122258597725444e-05, + "loss": 3.5162, + "step": 1336320 + }, + { + "epoch": 0.01, + "learning_rate": 2.8113872650214924e-05, + "loss": 3.5038, + "step": 1336832 + }, + { + "epoch": 0.01, + "learning_rate": 2.8105503081508133e-05, + "loss": 3.5013, + "step": 1337344 + }, + { + "epoch": 0.01, + "learning_rate": 2.809713351280135e-05, + "loss": 3.5037, + "step": 1337856 + }, + { + "epoch": 0.01, + "learning_rate": 2.808874756529083e-05, + "loss": 3.5136, + "step": 1338368 + }, + { + "epoch": 0.01, + "learning_rate": 2.8080361617780305e-05, + "loss": 3.5091, + "step": 1338880 + }, + { + "epoch": 0.01, + "learning_rate": 2.8071975670269785e-05, + "loss": 3.5122, + "step": 1339392 + }, + { + "epoch": 0.01, + "learning_rate": 2.8063589722759265e-05, + "loss": 3.5026, + "step": 1339904 + }, + { + "epoch": 0.01, + "learning_rate": 2.8055203775248745e-05, + "loss": 3.4812, + "step": 1340416 + }, + { + "epoch": 0.01, + "learning_rate": 2.8046817827738225e-05, + "loss": 3.4947, + "step": 1340928 + }, + { + "epoch": 0.01, + "learning_rate": 2.8038431880227705e-05, + "loss": 3.5014, + "step": 1341440 + }, + { + "epoch": 0.01, + "learning_rate": 2.8030062311520917e-05, + "loss": 3.5008, + "step": 1341952 + }, + { + "epoch": 0.01, + "learning_rate": 2.8021676364010397e-05, + "loss": 3.4965, + "step": 1342464 + }, + { + "epoch": 0.01, + "learning_rate": 2.8013290416499877e-05, + "loss": 3.5094, + "step": 1342976 + }, + { + "epoch": 0.02, + "learning_rate": 2.8004904468989357e-05, + "loss": 3.4956, + "step": 1343488 + }, + { + "epoch": 0.02, + "learning_rate": 2.7996534900282566e-05, + "loss": 3.4986, + "step": 1344000 + }, + { + "epoch": 0.02, + "learning_rate": 2.7988148952772046e-05, + "loss": 3.5016, + "step": 1344512 + }, + { + "epoch": 0.02, + "learning_rate": 2.7979763005261526e-05, + "loss": 3.5094, + "step": 1345024 + }, + { + "epoch": 0.02, + "learning_rate": 2.797137705775101e-05, + "loss": 3.5134, + "step": 1345536 + }, + { + "epoch": 0.02, + "learning_rate": 2.796300748904422e-05, + "loss": 3.5177, + "step": 1346048 + }, + { + "epoch": 0.02, + "learning_rate": 2.79546215415337e-05, + "loss": 3.4907, + "step": 1346560 + }, + { + "epoch": 0.02, + "learning_rate": 2.794623559402318e-05, + "loss": 3.507, + "step": 1347072 + }, + { + "epoch": 0.02, + "learning_rate": 2.793784964651266e-05, + "loss": 3.5051, + "step": 1347584 + }, + { + "epoch": 0.02, + "learning_rate": 2.792948007780587e-05, + "loss": 3.5057, + "step": 1348096 + }, + { + "epoch": 0.02, + "learning_rate": 2.792109413029535e-05, + "loss": 3.5134, + "step": 1348608 + }, + { + "epoch": 0.02, + "learning_rate": 2.791270818278483e-05, + "loss": 3.497, + "step": 1349120 + }, + { + "epoch": 0.02, + "learning_rate": 2.790432223527431e-05, + "loss": 3.4988, + "step": 1349632 + }, + { + "epoch": 0.02, + "learning_rate": 2.789595266656752e-05, + "loss": 3.511, + "step": 1350144 + }, + { + "epoch": 0.02, + "learning_rate": 2.7887566719057e-05, + "loss": 3.5072, + "step": 1350656 + }, + { + "epoch": 0.02, + "learning_rate": 2.787918077154648e-05, + "loss": 3.4933, + "step": 1351168 + }, + { + "epoch": 0.02, + "learning_rate": 2.7870794824035963e-05, + "loss": 3.5046, + "step": 1351680 + }, + { + "epoch": 0.02, + "learning_rate": 2.7862425255329172e-05, + "loss": 3.4965, + "step": 1352192 + }, + { + "epoch": 0.02, + "learning_rate": 2.7854039307818652e-05, + "loss": 3.497, + "step": 1352704 + }, + { + "epoch": 0.02, + "learning_rate": 2.7845653360308132e-05, + "loss": 3.4957, + "step": 1353216 + }, + { + "epoch": 0.02, + "learning_rate": 2.7837267412797612e-05, + "loss": 3.4957, + "step": 1353728 + }, + { + "epoch": 0.02, + "learning_rate": 2.7828897844090825e-05, + "loss": 3.4938, + "step": 1354240 + }, + { + "epoch": 0.02, + "learning_rate": 2.7820511896580305e-05, + "loss": 3.5034, + "step": 1354752 + }, + { + "epoch": 0.02, + "learning_rate": 2.7812125949069785e-05, + "loss": 3.4996, + "step": 1355264 + }, + { + "epoch": 0.02, + "learning_rate": 2.7803740001559265e-05, + "loss": 3.4996, + "step": 1355776 + }, + { + "epoch": 0.02, + "learning_rate": 2.7795386811656203e-05, + "loss": 3.5169, + "step": 1356288 + }, + { + "epoch": 0.02, + "learning_rate": 2.7787000864145686e-05, + "loss": 3.5125, + "step": 1356800 + }, + { + "epoch": 0.02, + "learning_rate": 2.7778614916635166e-05, + "loss": 3.505, + "step": 1357312 + }, + { + "epoch": 0.02, + "learning_rate": 2.7770228969124646e-05, + "loss": 3.5056, + "step": 1357824 + }, + { + "epoch": 0.02, + "learning_rate": 2.7761859400417855e-05, + "loss": 3.5029, + "step": 1358336 + }, + { + "epoch": 0.02, + "learning_rate": 2.7753473452907335e-05, + "loss": 3.4956, + "step": 1358848 + }, + { + "epoch": 0.02, + "learning_rate": 2.7745087505396815e-05, + "loss": 3.4894, + "step": 1359360 + }, + { + "epoch": 0.02, + "learning_rate": 2.7736701557886295e-05, + "loss": 3.4979, + "step": 1359872 + }, + { + "epoch": 0.02, + "learning_rate": 2.772831561037578e-05, + "loss": 3.5017, + "step": 1360384 + }, + { + "epoch": 0.02, + "learning_rate": 2.7719929662865258e-05, + "loss": 3.5023, + "step": 1360896 + }, + { + "epoch": 0.02, + "learning_rate": 2.7711543715354738e-05, + "loss": 3.5005, + "step": 1361408 + }, + { + "epoch": 0.02, + "learning_rate": 2.7703157767844218e-05, + "loss": 3.5044, + "step": 1361920 + }, + { + "epoch": 0.02, + "learning_rate": 2.7694788199137427e-05, + "loss": 3.502, + "step": 1362432 + }, + { + "epoch": 0.02, + "learning_rate": 2.768641863043064e-05, + "loss": 3.4977, + "step": 1362944 + }, + { + "epoch": 0.02, + "learning_rate": 2.767803268292012e-05, + "loss": 3.4955, + "step": 1363456 + }, + { + "epoch": 0.02, + "learning_rate": 2.76696467354096e-05, + "loss": 3.5136, + "step": 1363968 + }, + { + "epoch": 0.02, + "learning_rate": 2.766126078789908e-05, + "loss": 3.515, + "step": 1364480 + }, + { + "epoch": 0.02, + "learning_rate": 2.765287484038856e-05, + "loss": 3.5066, + "step": 1364992 + }, + { + "epoch": 0.02, + "learning_rate": 2.764448889287804e-05, + "loss": 3.5005, + "step": 1365504 + }, + { + "epoch": 0.02, + "learning_rate": 2.763610294536752e-05, + "loss": 3.5043, + "step": 1366016 + }, + { + "epoch": 0.02, + "learning_rate": 2.7627716997857e-05, + "loss": 3.5065, + "step": 1366528 + }, + { + "epoch": 0.02, + "learning_rate": 2.7619347429150212e-05, + "loss": 3.5079, + "step": 1367040 + }, + { + "epoch": 0.02, + "learning_rate": 2.7610961481639692e-05, + "loss": 3.5032, + "step": 1367552 + }, + { + "epoch": 0.02, + "learning_rate": 2.7602575534129172e-05, + "loss": 3.5024, + "step": 1368064 + }, + { + "epoch": 0.02, + "learning_rate": 2.7594189586618652e-05, + "loss": 3.5013, + "step": 1368576 + }, + { + "epoch": 0.02, + "learning_rate": 2.758582001791186e-05, + "loss": 3.5028, + "step": 1369088 + }, + { + "epoch": 0.02, + "learning_rate": 2.7577450449205073e-05, + "loss": 3.4986, + "step": 1369600 + }, + { + "epoch": 0.02, + "learning_rate": 2.7569064501694553e-05, + "loss": 3.5032, + "step": 1370112 + }, + { + "epoch": 0.02, + "learning_rate": 2.7560678554184033e-05, + "loss": 3.508, + "step": 1370624 + }, + { + "epoch": 0.02, + "learning_rate": 2.7552292606673513e-05, + "loss": 3.4933, + "step": 1371136 + }, + { + "epoch": 0.02, + "learning_rate": 2.7543906659162993e-05, + "loss": 3.5147, + "step": 1371648 + }, + { + "epoch": 0.02, + "learning_rate": 2.7535520711652473e-05, + "loss": 3.5002, + "step": 1372160 + }, + { + "epoch": 0.02, + "learning_rate": 2.7527134764141953e-05, + "loss": 3.5062, + "step": 1372672 + }, + { + "epoch": 0.02, + "learning_rate": 2.7518748816631433e-05, + "loss": 3.501, + "step": 1373184 + }, + { + "epoch": 0.02, + "learning_rate": 2.7510379247924646e-05, + "loss": 3.4931, + "step": 1373696 + }, + { + "epoch": 0.03, + "eval_loss": 3.8380842208862305, + "eval_runtime": 305.6848, + "eval_samples_per_second": 1248.315, + "eval_steps_per_second": 39.011, + "step": 1373751 + }, + { + "epoch": 0.0, + "learning_rate": 2.7501993300414126e-05, + "loss": 3.4941, + "step": 1374208 + }, + { + "epoch": 0.0, + "learning_rate": 2.7493607352903605e-05, + "loss": 3.495, + "step": 1374720 + }, + { + "epoch": 0.0, + "learning_rate": 2.7485237784196815e-05, + "loss": 3.515, + "step": 1375232 + }, + { + "epoch": 0.0, + "learning_rate": 2.7476851836686295e-05, + "loss": 3.4971, + "step": 1375744 + }, + { + "epoch": 0.0, + "learning_rate": 2.7468465889175778e-05, + "loss": 3.51, + "step": 1376256 + }, + { + "epoch": 0.0, + "learning_rate": 2.7460079941665258e-05, + "loss": 3.4944, + "step": 1376768 + }, + { + "epoch": 0.0, + "learning_rate": 2.745169399415473e-05, + "loss": 3.4985, + "step": 1377280 + }, + { + "epoch": 0.0, + "learning_rate": 2.744330804664421e-05, + "loss": 3.4878, + "step": 1377792 + }, + { + "epoch": 0.0, + "learning_rate": 2.743492209913369e-05, + "loss": 3.5005, + "step": 1378304 + }, + { + "epoch": 0.0, + "learning_rate": 2.742653615162317e-05, + "loss": 3.4975, + "step": 1378816 + }, + { + "epoch": 0.0, + "learning_rate": 2.7418166582916383e-05, + "loss": 3.5146, + "step": 1379328 + }, + { + "epoch": 0.0, + "learning_rate": 2.7409780635405863e-05, + "loss": 3.5037, + "step": 1379840 + }, + { + "epoch": 0.0, + "learning_rate": 2.740141106669908e-05, + "loss": 3.4875, + "step": 1380352 + }, + { + "epoch": 0.0, + "learning_rate": 2.7393025119188552e-05, + "loss": 3.4894, + "step": 1380864 + }, + { + "epoch": 0.0, + "learning_rate": 2.7384639171678032e-05, + "loss": 3.5002, + "step": 1381376 + }, + { + "epoch": 0.0, + "learning_rate": 2.7376253224167516e-05, + "loss": 3.4777, + "step": 1381888 + }, + { + "epoch": 0.0, + "learning_rate": 2.7367867276656996e-05, + "loss": 3.5013, + "step": 1382400 + }, + { + "epoch": 0.0, + "learning_rate": 2.7359481329146476e-05, + "loss": 3.4993, + "step": 1382912 + }, + { + "epoch": 0.0, + "learning_rate": 2.7351095381635956e-05, + "loss": 3.4913, + "step": 1383424 + }, + { + "epoch": 0.0, + "learning_rate": 2.7342725812929165e-05, + "loss": 3.5172, + "step": 1383936 + }, + { + "epoch": 0.0, + "learning_rate": 2.7334339865418645e-05, + "loss": 3.4974, + "step": 1384448 + }, + { + "epoch": 0.0, + "learning_rate": 2.7325953917908125e-05, + "loss": 3.4996, + "step": 1384960 + }, + { + "epoch": 0.0, + "learning_rate": 2.7317567970397605e-05, + "loss": 3.4929, + "step": 1385472 + }, + { + "epoch": 0.0, + "learning_rate": 2.7309198401690817e-05, + "loss": 3.5109, + "step": 1385984 + }, + { + "epoch": 0.0, + "learning_rate": 2.7300812454180297e-05, + "loss": 3.4852, + "step": 1386496 + }, + { + "epoch": 0.0, + "learning_rate": 2.7292426506669777e-05, + "loss": 3.4999, + "step": 1387008 + }, + { + "epoch": 0.0, + "learning_rate": 2.7284040559159257e-05, + "loss": 3.4914, + "step": 1387520 + }, + { + "epoch": 0.0, + "learning_rate": 2.7275670990452466e-05, + "loss": 3.4961, + "step": 1388032 + }, + { + "epoch": 0.0, + "learning_rate": 2.726728504294195e-05, + "loss": 3.4931, + "step": 1388544 + }, + { + "epoch": 0.01, + "learning_rate": 2.725889909543143e-05, + "loss": 3.493, + "step": 1389056 + }, + { + "epoch": 0.01, + "learning_rate": 2.725051314792091e-05, + "loss": 3.4989, + "step": 1389568 + }, + { + "epoch": 0.01, + "learning_rate": 2.724214357921412e-05, + "loss": 3.4974, + "step": 1390080 + }, + { + "epoch": 0.01, + "learning_rate": 2.7233757631703598e-05, + "loss": 3.4957, + "step": 1390592 + }, + { + "epoch": 0.01, + "learning_rate": 2.7225371684193078e-05, + "loss": 3.5091, + "step": 1391104 + }, + { + "epoch": 0.01, + "learning_rate": 2.7216985736682558e-05, + "loss": 3.4906, + "step": 1391616 + }, + { + "epoch": 0.01, + "learning_rate": 2.720861616797577e-05, + "loss": 3.4996, + "step": 1392128 + }, + { + "epoch": 0.01, + "learning_rate": 2.720023022046525e-05, + "loss": 3.4902, + "step": 1392640 + }, + { + "epoch": 0.01, + "learning_rate": 2.719184427295473e-05, + "loss": 3.4942, + "step": 1393152 + }, + { + "epoch": 0.01, + "learning_rate": 2.718345832544421e-05, + "loss": 3.486, + "step": 1393664 + }, + { + "epoch": 0.01, + "learning_rate": 2.7175105135541152e-05, + "loss": 3.4946, + "step": 1394176 + }, + { + "epoch": 0.01, + "learning_rate": 2.7166719188030632e-05, + "loss": 3.4915, + "step": 1394688 + }, + { + "epoch": 0.01, + "learning_rate": 2.7158333240520112e-05, + "loss": 3.5029, + "step": 1395200 + }, + { + "epoch": 0.01, + "learning_rate": 2.7149947293009592e-05, + "loss": 3.4885, + "step": 1395712 + }, + { + "epoch": 0.01, + "learning_rate": 2.7141561345499072e-05, + "loss": 3.4966, + "step": 1396224 + }, + { + "epoch": 0.01, + "learning_rate": 2.7133175397988552e-05, + "loss": 3.502, + "step": 1396736 + }, + { + "epoch": 0.01, + "learning_rate": 2.7124789450478032e-05, + "loss": 3.4992, + "step": 1397248 + }, + { + "epoch": 0.01, + "learning_rate": 2.7116403502967512e-05, + "loss": 3.4959, + "step": 1397760 + }, + { + "epoch": 0.01, + "learning_rate": 2.7108033934260724e-05, + "loss": 3.4833, + "step": 1398272 + }, + { + "epoch": 0.01, + "learning_rate": 2.7099647986750204e-05, + "loss": 3.4895, + "step": 1398784 + }, + { + "epoch": 0.01, + "learning_rate": 2.7091262039239684e-05, + "loss": 3.5029, + "step": 1399296 + }, + { + "epoch": 0.01, + "learning_rate": 2.7082876091729164e-05, + "loss": 3.4924, + "step": 1399808 + }, + { + "epoch": 0.01, + "learning_rate": 2.7074506523022373e-05, + "loss": 3.4941, + "step": 1400320 + }, + { + "epoch": 0.01, + "learning_rate": 2.7066120575511857e-05, + "loss": 3.4804, + "step": 1400832 + }, + { + "epoch": 0.01, + "learning_rate": 2.7057751006805066e-05, + "loss": 3.4902, + "step": 1401344 + }, + { + "epoch": 0.01, + "learning_rate": 2.7049365059294546e-05, + "loss": 3.4729, + "step": 1401856 + }, + { + "epoch": 0.01, + "learning_rate": 2.7040979111784026e-05, + "loss": 3.5032, + "step": 1402368 + }, + { + "epoch": 0.01, + "learning_rate": 2.7032593164273506e-05, + "loss": 3.4811, + "step": 1402880 + }, + { + "epoch": 0.01, + "learning_rate": 2.7024207216762986e-05, + "loss": 3.5005, + "step": 1403392 + }, + { + "epoch": 0.01, + "learning_rate": 2.7015821269252466e-05, + "loss": 3.4927, + "step": 1403904 + }, + { + "epoch": 0.01, + "learning_rate": 2.700743532174195e-05, + "loss": 3.4801, + "step": 1404416 + }, + { + "epoch": 0.01, + "learning_rate": 2.699904937423143e-05, + "loss": 3.5, + "step": 1404928 + }, + { + "epoch": 0.01, + "learning_rate": 2.6990679805524638e-05, + "loss": 3.489, + "step": 1405440 + }, + { + "epoch": 0.01, + "learning_rate": 2.6982293858014118e-05, + "loss": 3.4852, + "step": 1405952 + }, + { + "epoch": 0.01, + "learning_rate": 2.6973907910503598e-05, + "loss": 3.4756, + "step": 1406464 + }, + { + "epoch": 0.01, + "learning_rate": 2.6965521962993078e-05, + "loss": 3.4986, + "step": 1406976 + }, + { + "epoch": 0.01, + "learning_rate": 2.695715239428629e-05, + "loss": 3.4846, + "step": 1407488 + }, + { + "epoch": 0.01, + "learning_rate": 2.69487828255795e-05, + "loss": 3.4861, + "step": 1408000 + }, + { + "epoch": 0.01, + "learning_rate": 2.694039687806898e-05, + "loss": 3.4751, + "step": 1408512 + }, + { + "epoch": 0.01, + "learning_rate": 2.693201093055846e-05, + "loss": 3.4863, + "step": 1409024 + }, + { + "epoch": 0.01, + "learning_rate": 2.692362498304794e-05, + "loss": 3.4896, + "step": 1409536 + }, + { + "epoch": 0.01, + "learning_rate": 2.691523903553742e-05, + "loss": 3.4986, + "step": 1410048 + }, + { + "epoch": 0.01, + "learning_rate": 2.6906853088026903e-05, + "loss": 3.4913, + "step": 1410560 + }, + { + "epoch": 0.01, + "learning_rate": 2.6898467140516382e-05, + "loss": 3.4991, + "step": 1411072 + }, + { + "epoch": 0.01, + "learning_rate": 2.6890081193005862e-05, + "loss": 3.4949, + "step": 1411584 + }, + { + "epoch": 0.01, + "learning_rate": 2.688171162429907e-05, + "loss": 3.4898, + "step": 1412096 + }, + { + "epoch": 0.01, + "learning_rate": 2.687332567678855e-05, + "loss": 3.5012, + "step": 1412608 + }, + { + "epoch": 0.01, + "learning_rate": 2.686493972927803e-05, + "loss": 3.4939, + "step": 1413120 + }, + { + "epoch": 0.01, + "learning_rate": 2.685655378176751e-05, + "loss": 3.4871, + "step": 1413632 + }, + { + "epoch": 0.01, + "learning_rate": 2.6848184213060724e-05, + "loss": 3.4908, + "step": 1414144 + }, + { + "epoch": 0.01, + "learning_rate": 2.6839798265550204e-05, + "loss": 3.4966, + "step": 1414656 + }, + { + "epoch": 0.01, + "learning_rate": 2.6831412318039684e-05, + "loss": 3.4978, + "step": 1415168 + }, + { + "epoch": 0.01, + "learning_rate": 2.6823042749332893e-05, + "loss": 3.5009, + "step": 1415680 + }, + { + "epoch": 0.01, + "learning_rate": 2.6814656801822373e-05, + "loss": 3.4882, + "step": 1416192 + }, + { + "epoch": 0.01, + "learning_rate": 2.6806270854311856e-05, + "loss": 3.4649, + "step": 1416704 + }, + { + "epoch": 0.01, + "learning_rate": 2.6797884906801336e-05, + "loss": 3.4823, + "step": 1417216 + }, + { + "epoch": 0.01, + "learning_rate": 2.6789515338094545e-05, + "loss": 3.4915, + "step": 1417728 + }, + { + "epoch": 0.01, + "learning_rate": 2.6781129390584025e-05, + "loss": 3.4877, + "step": 1418240 + }, + { + "epoch": 0.01, + "learning_rate": 2.6772743443073505e-05, + "loss": 3.4833, + "step": 1418752 + }, + { + "epoch": 0.01, + "learning_rate": 2.6764357495562985e-05, + "loss": 3.4973, + "step": 1419264 + }, + { + "epoch": 0.02, + "learning_rate": 2.6755987926856198e-05, + "loss": 3.4884, + "step": 1419776 + }, + { + "epoch": 0.02, + "learning_rate": 2.6747618358149407e-05, + "loss": 3.4794, + "step": 1420288 + }, + { + "epoch": 0.02, + "learning_rate": 2.6739232410638887e-05, + "loss": 3.4902, + "step": 1420800 + }, + { + "epoch": 0.02, + "learning_rate": 2.6730846463128367e-05, + "loss": 3.4983, + "step": 1421312 + }, + { + "epoch": 0.02, + "learning_rate": 2.6722460515617847e-05, + "loss": 3.497, + "step": 1421824 + }, + { + "epoch": 0.02, + "learning_rate": 2.6714074568107327e-05, + "loss": 3.5029, + "step": 1422336 + }, + { + "epoch": 0.02, + "learning_rate": 2.670568862059681e-05, + "loss": 3.4849, + "step": 1422848 + }, + { + "epoch": 0.02, + "learning_rate": 2.6697302673086283e-05, + "loss": 3.4917, + "step": 1423360 + }, + { + "epoch": 0.02, + "learning_rate": 2.6688916725575763e-05, + "loss": 3.4926, + "step": 1423872 + }, + { + "epoch": 0.02, + "learning_rate": 2.668054715686898e-05, + "loss": 3.4917, + "step": 1424384 + }, + { + "epoch": 0.02, + "learning_rate": 2.667216120935846e-05, + "loss": 3.4972, + "step": 1424896 + }, + { + "epoch": 0.02, + "learning_rate": 2.6663775261847935e-05, + "loss": 3.4855, + "step": 1425408 + }, + { + "epoch": 0.02, + "learning_rate": 2.6655389314337415e-05, + "loss": 3.4861, + "step": 1425920 + }, + { + "epoch": 0.02, + "learning_rate": 2.664701974563063e-05, + "loss": 3.4956, + "step": 1426432 + }, + { + "epoch": 0.02, + "learning_rate": 2.6638633798120104e-05, + "loss": 3.496, + "step": 1426944 + }, + { + "epoch": 0.02, + "learning_rate": 2.6630247850609584e-05, + "loss": 3.4805, + "step": 1427456 + }, + { + "epoch": 0.02, + "learning_rate": 2.6621861903099064e-05, + "loss": 3.4874, + "step": 1427968 + }, + { + "epoch": 0.02, + "learning_rate": 2.661349233439228e-05, + "loss": 3.4868, + "step": 1428480 + }, + { + "epoch": 0.02, + "learning_rate": 2.6605106386881757e-05, + "loss": 3.4857, + "step": 1428992 + }, + { + "epoch": 0.02, + "learning_rate": 2.6596720439371237e-05, + "loss": 3.4785, + "step": 1429504 + }, + { + "epoch": 0.02, + "learning_rate": 2.6588334491860717e-05, + "loss": 3.4815, + "step": 1430016 + }, + { + "epoch": 0.02, + "learning_rate": 2.6579964923153926e-05, + "loss": 3.485, + "step": 1430528 + }, + { + "epoch": 0.02, + "learning_rate": 2.657157897564341e-05, + "loss": 3.4895, + "step": 1431040 + }, + { + "epoch": 0.02, + "learning_rate": 2.656319302813289e-05, + "loss": 3.4852, + "step": 1431552 + }, + { + "epoch": 0.02, + "learning_rate": 2.655480708062237e-05, + "loss": 3.4878, + "step": 1432064 + }, + { + "epoch": 0.02, + "learning_rate": 2.6546453890719314e-05, + "loss": 3.503, + "step": 1432576 + }, + { + "epoch": 0.02, + "learning_rate": 2.6538067943208794e-05, + "loss": 3.5018, + "step": 1433088 + }, + { + "epoch": 0.02, + "learning_rate": 2.6529681995698274e-05, + "loss": 3.4927, + "step": 1433600 + }, + { + "epoch": 0.02, + "learning_rate": 2.6521296048187754e-05, + "loss": 3.4936, + "step": 1434112 + }, + { + "epoch": 0.02, + "learning_rate": 2.6512926479480966e-05, + "loss": 3.4889, + "step": 1434624 + }, + { + "epoch": 0.02, + "learning_rate": 2.6504540531970446e-05, + "loss": 3.4833, + "step": 1435136 + }, + { + "epoch": 0.02, + "learning_rate": 2.6496154584459926e-05, + "loss": 3.4801, + "step": 1435648 + }, + { + "epoch": 0.02, + "learning_rate": 2.64877686369494e-05, + "loss": 3.4816, + "step": 1436160 + }, + { + "epoch": 0.02, + "learning_rate": 2.647938268943888e-05, + "loss": 3.4866, + "step": 1436672 + }, + { + "epoch": 0.02, + "learning_rate": 2.6470996741928363e-05, + "loss": 3.4945, + "step": 1437184 + }, + { + "epoch": 0.02, + "learning_rate": 2.6462610794417843e-05, + "loss": 3.4874, + "step": 1437696 + }, + { + "epoch": 0.02, + "learning_rate": 2.6454224846907323e-05, + "loss": 3.4908, + "step": 1438208 + }, + { + "epoch": 0.02, + "learning_rate": 2.6445855278200532e-05, + "loss": 3.4903, + "step": 1438720 + }, + { + "epoch": 0.02, + "learning_rate": 2.6437485709493748e-05, + "loss": 3.4842, + "step": 1439232 + }, + { + "epoch": 0.02, + "learning_rate": 2.6429099761983228e-05, + "loss": 3.4833, + "step": 1439744 + }, + { + "epoch": 0.02, + "learning_rate": 2.6420713814472704e-05, + "loss": 3.4992, + "step": 1440256 + }, + { + "epoch": 0.02, + "learning_rate": 2.6412327866962184e-05, + "loss": 3.5012, + "step": 1440768 + }, + { + "epoch": 0.02, + "learning_rate": 2.6403941919451664e-05, + "loss": 3.4942, + "step": 1441280 + }, + { + "epoch": 0.02, + "learning_rate": 2.6395555971941144e-05, + "loss": 3.4893, + "step": 1441792 + }, + { + "epoch": 0.02, + "learning_rate": 2.6387170024430624e-05, + "loss": 3.4898, + "step": 1442304 + }, + { + "epoch": 0.02, + "learning_rate": 2.6378784076920104e-05, + "loss": 3.4914, + "step": 1442816 + }, + { + "epoch": 0.02, + "learning_rate": 2.6370414508213313e-05, + "loss": 3.5033, + "step": 1443328 + }, + { + "epoch": 0.02, + "learning_rate": 2.6362028560702796e-05, + "loss": 3.4886, + "step": 1443840 + }, + { + "epoch": 0.02, + "learning_rate": 2.6353642613192276e-05, + "loss": 3.4881, + "step": 1444352 + }, + { + "epoch": 0.02, + "learning_rate": 2.6345256665681756e-05, + "loss": 3.488, + "step": 1444864 + }, + { + "epoch": 0.02, + "learning_rate": 2.6336887096974965e-05, + "loss": 3.4903, + "step": 1445376 + }, + { + "epoch": 0.02, + "learning_rate": 2.6328517528268178e-05, + "loss": 3.4856, + "step": 1445888 + }, + { + "epoch": 0.02, + "learning_rate": 2.6320131580757658e-05, + "loss": 3.4928, + "step": 1446400 + }, + { + "epoch": 0.02, + "learning_rate": 2.6311745633247138e-05, + "loss": 3.4962, + "step": 1446912 + }, + { + "epoch": 0.02, + "learning_rate": 2.6303359685736618e-05, + "loss": 3.4806, + "step": 1447424 + }, + { + "epoch": 0.02, + "learning_rate": 2.6294973738226098e-05, + "loss": 3.4981, + "step": 1447936 + }, + { + "epoch": 0.02, + "learning_rate": 2.6286587790715578e-05, + "loss": 3.4945, + "step": 1448448 + }, + { + "epoch": 0.02, + "learning_rate": 2.6278201843205058e-05, + "loss": 3.4897, + "step": 1448960 + }, + { + "epoch": 0.02, + "learning_rate": 2.6269815895694538e-05, + "loss": 3.4891, + "step": 1449472 + }, + { + "epoch": 0.02, + "learning_rate": 2.626144632698775e-05, + "loss": 3.4798, + "step": 1449984 + }, + { + "epoch": 0.03, + "eval_loss": 3.8409264087677, + "eval_runtime": 304.425, + "eval_samples_per_second": 1253.481, + "eval_steps_per_second": 39.172, + "step": 1450071 + }, + { + "epoch": 1.0, + "learning_rate": 2.625306037947723e-05, + "loss": 3.4866, + "step": 1450496 + }, + { + "epoch": 1.0, + "learning_rate": 2.624467443196671e-05, + "loss": 3.4826, + "step": 1451008 + }, + { + "epoch": 1.0, + "learning_rate": 2.623630486325992e-05, + "loss": 3.5037, + "step": 1451520 + }, + { + "epoch": 1.0, + "learning_rate": 2.62279189157494e-05, + "loss": 3.4829, + "step": 1452032 + }, + { + "epoch": 1.0, + "learning_rate": 2.621953296823888e-05, + "loss": 3.4999, + "step": 1452544 + }, + { + "epoch": 1.0, + "learning_rate": 2.621114702072836e-05, + "loss": 3.4801, + "step": 1453056 + }, + { + "epoch": 1.0, + "learning_rate": 2.6202761073217842e-05, + "loss": 3.488, + "step": 1453568 + }, + { + "epoch": 1.0, + "learning_rate": 2.6194375125707322e-05, + "loss": 3.4759, + "step": 1454080 + }, + { + "epoch": 1.0, + "learning_rate": 2.6185989178196802e-05, + "loss": 3.4877, + "step": 1454592 + }, + { + "epoch": 1.0, + "learning_rate": 2.6177603230686282e-05, + "loss": 3.4822, + "step": 1455104 + }, + { + "epoch": 1.0, + "learning_rate": 2.616923366197949e-05, + "loss": 3.5025, + "step": 1455616 + }, + { + "epoch": 1.0, + "learning_rate": 2.616084771446897e-05, + "loss": 3.4905, + "step": 1456128 + }, + { + "epoch": 1.0, + "learning_rate": 2.6152478145762184e-05, + "loss": 3.4742, + "step": 1456640 + }, + { + "epoch": 1.0, + "learning_rate": 2.6144092198251664e-05, + "loss": 3.4767, + "step": 1457152 + }, + { + "epoch": 1.0, + "learning_rate": 2.6135706250741144e-05, + "loss": 3.4872, + "step": 1457664 + }, + { + "epoch": 1.0, + "learning_rate": 2.6127320303230624e-05, + "loss": 3.4712, + "step": 1458176 + }, + { + "epoch": 1.0, + "learning_rate": 2.6118934355720104e-05, + "loss": 3.484, + "step": 1458688 + }, + { + "epoch": 1.0, + "learning_rate": 2.6110548408209583e-05, + "loss": 3.4856, + "step": 1459200 + }, + { + "epoch": 1.0, + "learning_rate": 2.6102162460699063e-05, + "loss": 3.478, + "step": 1459712 + }, + { + "epoch": 1.0, + "learning_rate": 2.6093792891992276e-05, + "loss": 3.5046, + "step": 1460224 + }, + { + "epoch": 1.0, + "learning_rate": 2.6085406944481756e-05, + "loss": 3.4883, + "step": 1460736 + }, + { + "epoch": 1.0, + "learning_rate": 2.6077020996971236e-05, + "loss": 3.4845, + "step": 1461248 + }, + { + "epoch": 1.0, + "learning_rate": 2.606863504946071e-05, + "loss": 3.4803, + "step": 1461760 + }, + { + "epoch": 1.0, + "learning_rate": 2.6060265480753925e-05, + "loss": 3.4951, + "step": 1462272 + }, + { + "epoch": 1.0, + "learning_rate": 2.6051879533243405e-05, + "loss": 3.476, + "step": 1462784 + }, + { + "epoch": 1.0, + "learning_rate": 2.6043493585732888e-05, + "loss": 3.4869, + "step": 1463296 + }, + { + "epoch": 1.0, + "learning_rate": 2.603510763822236e-05, + "loss": 3.4798, + "step": 1463808 + }, + { + "epoch": 1.0, + "learning_rate": 2.6026738069515577e-05, + "loss": 3.4826, + "step": 1464320 + }, + { + "epoch": 1.0, + "learning_rate": 2.6018352122005057e-05, + "loss": 3.4799, + "step": 1464832 + }, + { + "epoch": 1.01, + "learning_rate": 2.6009966174494534e-05, + "loss": 3.477, + "step": 1465344 + }, + { + "epoch": 1.01, + "learning_rate": 2.6001580226984014e-05, + "loss": 3.4882, + "step": 1465856 + }, + { + "epoch": 1.01, + "learning_rate": 2.599321065827723e-05, + "loss": 3.4828, + "step": 1466368 + }, + { + "epoch": 1.01, + "learning_rate": 2.598482471076671e-05, + "loss": 3.4859, + "step": 1466880 + }, + { + "epoch": 1.01, + "learning_rate": 2.5976438763256183e-05, + "loss": 3.4932, + "step": 1467392 + }, + { + "epoch": 1.01, + "learning_rate": 2.5968052815745663e-05, + "loss": 3.4791, + "step": 1467904 + }, + { + "epoch": 1.01, + "learning_rate": 2.595968324703888e-05, + "loss": 3.4869, + "step": 1468416 + }, + { + "epoch": 1.01, + "learning_rate": 2.595129729952836e-05, + "loss": 3.4734, + "step": 1468928 + }, + { + "epoch": 1.01, + "learning_rate": 2.5942911352017835e-05, + "loss": 3.4867, + "step": 1469440 + }, + { + "epoch": 1.01, + "learning_rate": 2.5934525404507315e-05, + "loss": 3.4733, + "step": 1469952 + }, + { + "epoch": 1.01, + "learning_rate": 2.592617221460426e-05, + "loss": 3.48, + "step": 1470464 + }, + { + "epoch": 1.01, + "learning_rate": 2.591778626709374e-05, + "loss": 3.4782, + "step": 1470976 + }, + { + "epoch": 1.01, + "learning_rate": 2.590940031958322e-05, + "loss": 3.4895, + "step": 1471488 + }, + { + "epoch": 1.01, + "learning_rate": 2.5901014372072703e-05, + "loss": 3.4759, + "step": 1472000 + }, + { + "epoch": 1.01, + "learning_rate": 2.5892628424562183e-05, + "loss": 3.4821, + "step": 1472512 + }, + { + "epoch": 1.01, + "learning_rate": 2.5884242477051656e-05, + "loss": 3.4911, + "step": 1473024 + }, + { + "epoch": 1.01, + "learning_rate": 2.5875856529541136e-05, + "loss": 3.4862, + "step": 1473536 + }, + { + "epoch": 1.01, + "learning_rate": 2.5867470582030616e-05, + "loss": 3.4878, + "step": 1474048 + }, + { + "epoch": 1.01, + "learning_rate": 2.5859101013323832e-05, + "loss": 3.4682, + "step": 1474560 + }, + { + "epoch": 1.01, + "learning_rate": 2.585071506581331e-05, + "loss": 3.4748, + "step": 1475072 + }, + { + "epoch": 1.01, + "learning_rate": 2.584232911830279e-05, + "loss": 3.4879, + "step": 1475584 + }, + { + "epoch": 1.01, + "learning_rate": 2.583394317079227e-05, + "loss": 3.4799, + "step": 1476096 + }, + { + "epoch": 1.01, + "learning_rate": 2.5825573602085478e-05, + "loss": 3.4792, + "step": 1476608 + }, + { + "epoch": 1.01, + "learning_rate": 2.5817187654574958e-05, + "loss": 3.473, + "step": 1477120 + }, + { + "epoch": 1.01, + "learning_rate": 2.5808818085868174e-05, + "loss": 3.4803, + "step": 1477632 + }, + { + "epoch": 1.01, + "learning_rate": 2.5800432138357657e-05, + "loss": 3.4592, + "step": 1478144 + }, + { + "epoch": 1.01, + "learning_rate": 2.579204619084713e-05, + "loss": 3.4859, + "step": 1478656 + }, + { + "epoch": 1.01, + "learning_rate": 2.578366024333661e-05, + "loss": 3.4725, + "step": 1479168 + }, + { + "epoch": 1.01, + "learning_rate": 2.577527429582609e-05, + "loss": 3.4825, + "step": 1479680 + }, + { + "epoch": 1.01, + "learning_rate": 2.576688834831557e-05, + "loss": 3.4853, + "step": 1480192 + }, + { + "epoch": 1.01, + "learning_rate": 2.575850240080505e-05, + "loss": 3.4675, + "step": 1480704 + }, + { + "epoch": 1.01, + "learning_rate": 2.5750116453294533e-05, + "loss": 3.486, + "step": 1481216 + }, + { + "epoch": 1.01, + "learning_rate": 2.5741746884587742e-05, + "loss": 3.4785, + "step": 1481728 + }, + { + "epoch": 1.01, + "learning_rate": 2.5733360937077222e-05, + "loss": 3.4747, + "step": 1482240 + }, + { + "epoch": 1.01, + "learning_rate": 2.5724974989566702e-05, + "loss": 3.4638, + "step": 1482752 + }, + { + "epoch": 1.01, + "learning_rate": 2.5716589042056182e-05, + "loss": 3.4836, + "step": 1483264 + }, + { + "epoch": 1.01, + "learning_rate": 2.5708219473349395e-05, + "loss": 3.4726, + "step": 1483776 + }, + { + "epoch": 1.01, + "learning_rate": 2.5699849904642604e-05, + "loss": 3.4766, + "step": 1484288 + }, + { + "epoch": 1.01, + "learning_rate": 2.5691463957132084e-05, + "loss": 3.4614, + "step": 1484800 + }, + { + "epoch": 1.01, + "learning_rate": 2.5683078009621564e-05, + "loss": 3.469, + "step": 1485312 + }, + { + "epoch": 1.01, + "learning_rate": 2.5674692062111044e-05, + "loss": 3.4782, + "step": 1485824 + }, + { + "epoch": 1.01, + "learning_rate": 2.5666306114600524e-05, + "loss": 3.4888, + "step": 1486336 + }, + { + "epoch": 1.01, + "learning_rate": 2.5657920167090004e-05, + "loss": 3.4753, + "step": 1486848 + }, + { + "epoch": 1.01, + "learning_rate": 2.5649534219579484e-05, + "loss": 3.4875, + "step": 1487360 + }, + { + "epoch": 1.01, + "learning_rate": 2.5641148272068967e-05, + "loss": 3.4834, + "step": 1487872 + }, + { + "epoch": 1.01, + "learning_rate": 2.5632778703362176e-05, + "loss": 3.4795, + "step": 1488384 + }, + { + "epoch": 1.01, + "learning_rate": 2.5624392755851656e-05, + "loss": 3.4883, + "step": 1488896 + }, + { + "epoch": 1.01, + "learning_rate": 2.5616006808341136e-05, + "loss": 3.481, + "step": 1489408 + }, + { + "epoch": 1.01, + "learning_rate": 2.5607620860830616e-05, + "loss": 3.4752, + "step": 1489920 + }, + { + "epoch": 1.01, + "learning_rate": 2.5599267670927558e-05, + "loss": 3.4776, + "step": 1490432 + }, + { + "epoch": 1.01, + "learning_rate": 2.5590881723417037e-05, + "loss": 3.4857, + "step": 1490944 + }, + { + "epoch": 1.01, + "learning_rate": 2.5582495775906517e-05, + "loss": 3.4859, + "step": 1491456 + }, + { + "epoch": 1.01, + "learning_rate": 2.5574109828395997e-05, + "loss": 3.4851, + "step": 1491968 + }, + { + "epoch": 1.01, + "learning_rate": 2.5565723880885477e-05, + "loss": 3.4777, + "step": 1492480 + }, + { + "epoch": 1.01, + "learning_rate": 2.5557337933374957e-05, + "loss": 3.4568, + "step": 1492992 + }, + { + "epoch": 1.01, + "learning_rate": 2.5548951985864437e-05, + "loss": 3.469, + "step": 1493504 + }, + { + "epoch": 1.01, + "learning_rate": 2.554056603835392e-05, + "loss": 3.4758, + "step": 1494016 + }, + { + "epoch": 1.01, + "learning_rate": 2.553219646964713e-05, + "loss": 3.478, + "step": 1494528 + }, + { + "epoch": 1.01, + "learning_rate": 2.552381052213661e-05, + "loss": 3.4679, + "step": 1495040 + }, + { + "epoch": 1.01, + "learning_rate": 2.551542457462609e-05, + "loss": 3.4825, + "step": 1495552 + }, + { + "epoch": 1.02, + "learning_rate": 2.550703862711557e-05, + "loss": 3.4763, + "step": 1496064 + }, + { + "epoch": 1.02, + "learning_rate": 2.5498669058408782e-05, + "loss": 3.4664, + "step": 1496576 + }, + { + "epoch": 1.02, + "learning_rate": 2.5490283110898262e-05, + "loss": 3.4781, + "step": 1497088 + }, + { + "epoch": 1.02, + "learning_rate": 2.5481897163387742e-05, + "loss": 3.484, + "step": 1497600 + }, + { + "epoch": 1.02, + "learning_rate": 2.5473511215877222e-05, + "loss": 3.4825, + "step": 1498112 + }, + { + "epoch": 1.02, + "learning_rate": 2.5465125268366702e-05, + "loss": 3.4921, + "step": 1498624 + }, + { + "epoch": 1.02, + "learning_rate": 2.5456739320856182e-05, + "loss": 3.4725, + "step": 1499136 + }, + { + "epoch": 1.02, + "learning_rate": 2.5448353373345662e-05, + "loss": 3.478, + "step": 1499648 + }, + { + "epoch": 1.02, + "learning_rate": 2.5439967425835142e-05, + "loss": 3.4791, + "step": 1500160 + }, + { + "epoch": 1.02, + "learning_rate": 2.5431597857128354e-05, + "loss": 3.4827, + "step": 1500672 + }, + { + "epoch": 1.02, + "learning_rate": 2.5423211909617834e-05, + "loss": 3.4836, + "step": 1501184 + }, + { + "epoch": 1.02, + "learning_rate": 2.5414825962107314e-05, + "loss": 3.4746, + "step": 1501696 + }, + { + "epoch": 1.02, + "learning_rate": 2.5406440014596787e-05, + "loss": 3.4721, + "step": 1502208 + }, + { + "epoch": 1.02, + "learning_rate": 2.5398070445890003e-05, + "loss": 3.4795, + "step": 1502720 + }, + { + "epoch": 1.02, + "learning_rate": 2.5389684498379483e-05, + "loss": 3.4848, + "step": 1503232 + }, + { + "epoch": 1.02, + "learning_rate": 2.5381298550868966e-05, + "loss": 3.4652, + "step": 1503744 + }, + { + "epoch": 1.02, + "learning_rate": 2.537291260335844e-05, + "loss": 3.4788, + "step": 1504256 + }, + { + "epoch": 1.02, + "learning_rate": 2.5364543034651656e-05, + "loss": 3.4758, + "step": 1504768 + }, + { + "epoch": 1.02, + "learning_rate": 2.5356157087141135e-05, + "loss": 3.4717, + "step": 1505280 + }, + { + "epoch": 1.02, + "learning_rate": 2.5347771139630612e-05, + "loss": 3.4652, + "step": 1505792 + }, + { + "epoch": 1.02, + "learning_rate": 2.5339385192120092e-05, + "loss": 3.4726, + "step": 1506304 + }, + { + "epoch": 1.02, + "learning_rate": 2.5331015623413308e-05, + "loss": 3.4726, + "step": 1506816 + }, + { + "epoch": 1.02, + "learning_rate": 2.5322629675902788e-05, + "loss": 3.4733, + "step": 1507328 + }, + { + "epoch": 1.02, + "learning_rate": 2.531424372839226e-05, + "loss": 3.4753, + "step": 1507840 + }, + { + "epoch": 1.02, + "learning_rate": 2.530585778088174e-05, + "loss": 3.4724, + "step": 1508352 + }, + { + "epoch": 1.02, + "learning_rate": 2.529750459097869e-05, + "loss": 3.4928, + "step": 1508864 + }, + { + "epoch": 1.02, + "learning_rate": 2.528911864346817e-05, + "loss": 3.4881, + "step": 1509376 + }, + { + "epoch": 1.02, + "learning_rate": 2.528073269595765e-05, + "loss": 3.4812, + "step": 1509888 + }, + { + "epoch": 1.02, + "learning_rate": 2.527234674844713e-05, + "loss": 3.483, + "step": 1510400 + }, + { + "epoch": 1.02, + "learning_rate": 2.526397717974034e-05, + "loss": 3.4743, + "step": 1510912 + }, + { + "epoch": 1.02, + "learning_rate": 2.5255591232229818e-05, + "loss": 3.4721, + "step": 1511424 + }, + { + "epoch": 1.02, + "learning_rate": 2.5247205284719298e-05, + "loss": 3.467, + "step": 1511936 + }, + { + "epoch": 1.02, + "learning_rate": 2.523881933720878e-05, + "loss": 3.4684, + "step": 1512448 + }, + { + "epoch": 1.02, + "learning_rate": 2.523043338969826e-05, + "loss": 3.4768, + "step": 1512960 + }, + { + "epoch": 1.02, + "learning_rate": 2.5222047442187735e-05, + "loss": 3.4819, + "step": 1513472 + }, + { + "epoch": 1.02, + "learning_rate": 2.5213661494677215e-05, + "loss": 3.4738, + "step": 1513984 + }, + { + "epoch": 1.02, + "learning_rate": 2.5205275547166695e-05, + "loss": 3.4804, + "step": 1514496 + }, + { + "epoch": 1.02, + "learning_rate": 2.519690597845991e-05, + "loss": 3.4748, + "step": 1515008 + }, + { + "epoch": 1.02, + "learning_rate": 2.5188520030949387e-05, + "loss": 3.4722, + "step": 1515520 + }, + { + "epoch": 1.02, + "learning_rate": 2.5180134083438867e-05, + "loss": 3.4721, + "step": 1516032 + }, + { + "epoch": 1.02, + "learning_rate": 2.5171748135928347e-05, + "loss": 3.4865, + "step": 1516544 + }, + { + "epoch": 1.02, + "learning_rate": 2.5163378567221556e-05, + "loss": 3.4943, + "step": 1517056 + }, + { + "epoch": 1.02, + "learning_rate": 2.5154992619711036e-05, + "loss": 3.479, + "step": 1517568 + }, + { + "epoch": 1.02, + "learning_rate": 2.514660667220052e-05, + "loss": 3.4747, + "step": 1518080 + }, + { + "epoch": 1.02, + "learning_rate": 2.513822072469e-05, + "loss": 3.4781, + "step": 1518592 + }, + { + "epoch": 1.02, + "learning_rate": 2.512985115598321e-05, + "loss": 3.4747, + "step": 1519104 + }, + { + "epoch": 1.02, + "learning_rate": 2.512146520847269e-05, + "loss": 3.4908, + "step": 1519616 + }, + { + "epoch": 1.02, + "learning_rate": 2.511307926096217e-05, + "loss": 3.4752, + "step": 1520128 + }, + { + "epoch": 1.02, + "learning_rate": 2.5104693313451648e-05, + "loss": 3.4778, + "step": 1520640 + }, + { + "epoch": 1.02, + "learning_rate": 2.509632374474486e-05, + "loss": 3.4719, + "step": 1521152 + }, + { + "epoch": 1.02, + "learning_rate": 2.508793779723434e-05, + "loss": 3.4825, + "step": 1521664 + }, + { + "epoch": 1.02, + "learning_rate": 2.507955184972382e-05, + "loss": 3.4737, + "step": 1522176 + }, + { + "epoch": 1.02, + "learning_rate": 2.50711659022133e-05, + "loss": 3.4756, + "step": 1522688 + }, + { + "epoch": 1.02, + "learning_rate": 2.506279633350651e-05, + "loss": 3.4842, + "step": 1523200 + }, + { + "epoch": 1.02, + "learning_rate": 2.505441038599599e-05, + "loss": 3.4694, + "step": 1523712 + }, + { + "epoch": 1.02, + "learning_rate": 2.5046040817289206e-05, + "loss": 3.4834, + "step": 1524224 + }, + { + "epoch": 1.02, + "learning_rate": 2.5037654869778682e-05, + "loss": 3.4873, + "step": 1524736 + }, + { + "epoch": 1.02, + "learning_rate": 2.5029268922268162e-05, + "loss": 3.4762, + "step": 1525248 + }, + { + "epoch": 1.02, + "learning_rate": 2.5020882974757642e-05, + "loss": 3.4762, + "step": 1525760 + }, + { + "epoch": 1.02, + "learning_rate": 2.5012497027247122e-05, + "loss": 3.4681, + "step": 1526272 + }, + { + "epoch": 1.03, + "eval_loss": 3.8416829109191895, + "eval_runtime": 304.9118, + "eval_samples_per_second": 1251.48, + "eval_steps_per_second": 39.11, + "step": 1526391 + }, + { + "epoch": 0.0, + "learning_rate": 2.5004111079736602e-05, + "loss": 3.4679, + "step": 1526784 + }, + { + "epoch": 0.0, + "learning_rate": 2.4995725132226082e-05, + "loss": 3.4696, + "step": 1527296 + }, + { + "epoch": 0.0, + "learning_rate": 2.4987355563519298e-05, + "loss": 3.4877, + "step": 1527808 + }, + { + "epoch": 0.0, + "learning_rate": 2.4978969616008774e-05, + "loss": 3.4752, + "step": 1528320 + }, + { + "epoch": 0.0, + "learning_rate": 2.4970583668498254e-05, + "loss": 3.4892, + "step": 1528832 + }, + { + "epoch": 0.0, + "learning_rate": 2.4962197720987734e-05, + "loss": 3.4661, + "step": 1529344 + }, + { + "epoch": 0.0, + "learning_rate": 2.4953811773477214e-05, + "loss": 3.4792, + "step": 1529856 + }, + { + "epoch": 0.0, + "learning_rate": 2.4945425825966694e-05, + "loss": 3.4617, + "step": 1530368 + }, + { + "epoch": 0.0, + "learning_rate": 2.4937056257259907e-05, + "loss": 3.4779, + "step": 1530880 + }, + { + "epoch": 0.0, + "learning_rate": 2.4928670309749387e-05, + "loss": 3.4679, + "step": 1531392 + }, + { + "epoch": 0.0, + "learning_rate": 2.4920284362238867e-05, + "loss": 3.4857, + "step": 1531904 + }, + { + "epoch": 0.0, + "learning_rate": 2.4911898414728347e-05, + "loss": 3.4814, + "step": 1532416 + }, + { + "epoch": 0.0, + "learning_rate": 2.4903512467217826e-05, + "loss": 3.4603, + "step": 1532928 + }, + { + "epoch": 0.0, + "learning_rate": 2.4895126519707303e-05, + "loss": 3.4658, + "step": 1533440 + }, + { + "epoch": 0.0, + "learning_rate": 2.4886740572196783e-05, + "loss": 3.4745, + "step": 1533952 + }, + { + "epoch": 0.0, + "learning_rate": 2.4878354624686266e-05, + "loss": 3.4591, + "step": 1534464 + }, + { + "epoch": 0.0, + "learning_rate": 2.486998505597948e-05, + "loss": 3.4704, + "step": 1534976 + }, + { + "epoch": 0.0, + "learning_rate": 2.4861599108468955e-05, + "loss": 3.4724, + "step": 1535488 + }, + { + "epoch": 0.0, + "learning_rate": 2.4853213160958435e-05, + "loss": 3.4698, + "step": 1536000 + }, + { + "epoch": 0.0, + "learning_rate": 2.4844827213447915e-05, + "loss": 3.4898, + "step": 1536512 + }, + { + "epoch": 0.0, + "learning_rate": 2.4836457644741128e-05, + "loss": 3.4747, + "step": 1537024 + }, + { + "epoch": 0.0, + "learning_rate": 2.4828071697230608e-05, + "loss": 3.4708, + "step": 1537536 + }, + { + "epoch": 0.0, + "learning_rate": 2.4819685749720088e-05, + "loss": 3.4719, + "step": 1538048 + }, + { + "epoch": 0.0, + "learning_rate": 2.4811299802209568e-05, + "loss": 3.4793, + "step": 1538560 + }, + { + "epoch": 0.0, + "learning_rate": 2.4802930233502777e-05, + "loss": 3.4654, + "step": 1539072 + }, + { + "epoch": 0.0, + "learning_rate": 2.4794544285992257e-05, + "loss": 3.4764, + "step": 1539584 + }, + { + "epoch": 0.0, + "learning_rate": 2.4786158338481737e-05, + "loss": 3.4674, + "step": 1540096 + }, + { + "epoch": 0.0, + "learning_rate": 2.4777788769774953e-05, + "loss": 3.4696, + "step": 1540608 + }, + { + "epoch": 0.0, + "learning_rate": 2.476940282226443e-05, + "loss": 3.4658, + "step": 1541120 + }, + { + "epoch": 0.0, + "learning_rate": 2.476101687475391e-05, + "loss": 3.4687, + "step": 1541632 + }, + { + "epoch": 0.01, + "learning_rate": 2.475263092724339e-05, + "loss": 3.4706, + "step": 1542144 + }, + { + "epoch": 0.01, + "learning_rate": 2.474424497973287e-05, + "loss": 3.4758, + "step": 1542656 + }, + { + "epoch": 0.01, + "learning_rate": 2.473585903222235e-05, + "loss": 3.4739, + "step": 1543168 + }, + { + "epoch": 0.01, + "learning_rate": 2.472747308471183e-05, + "loss": 3.484, + "step": 1543680 + }, + { + "epoch": 0.01, + "learning_rate": 2.471908713720131e-05, + "loss": 3.4626, + "step": 1544192 + }, + { + "epoch": 0.01, + "learning_rate": 2.471071756849452e-05, + "loss": 3.4756, + "step": 1544704 + }, + { + "epoch": 0.01, + "learning_rate": 2.4702331620984e-05, + "loss": 3.4637, + "step": 1545216 + }, + { + "epoch": 0.01, + "learning_rate": 2.469394567347348e-05, + "loss": 3.4741, + "step": 1545728 + }, + { + "epoch": 0.01, + "learning_rate": 2.4685559725962958e-05, + "loss": 3.4604, + "step": 1546240 + }, + { + "epoch": 0.01, + "learning_rate": 2.4677206536059903e-05, + "loss": 3.4686, + "step": 1546752 + }, + { + "epoch": 0.01, + "learning_rate": 2.4668820588549383e-05, + "loss": 3.4663, + "step": 1547264 + }, + { + "epoch": 0.01, + "learning_rate": 2.4660434641038863e-05, + "loss": 3.478, + "step": 1547776 + }, + { + "epoch": 0.01, + "learning_rate": 2.4652048693528343e-05, + "loss": 3.4663, + "step": 1548288 + }, + { + "epoch": 0.01, + "learning_rate": 2.4643662746017823e-05, + "loss": 3.4675, + "step": 1548800 + }, + { + "epoch": 0.01, + "learning_rate": 2.4635276798507303e-05, + "loss": 3.4815, + "step": 1549312 + }, + { + "epoch": 0.01, + "learning_rate": 2.4626890850996783e-05, + "loss": 3.4741, + "step": 1549824 + }, + { + "epoch": 0.01, + "learning_rate": 2.4618504903486263e-05, + "loss": 3.4749, + "step": 1550336 + }, + { + "epoch": 0.01, + "learning_rate": 2.4610135334779475e-05, + "loss": 3.4631, + "step": 1550848 + }, + { + "epoch": 0.01, + "learning_rate": 2.4601749387268955e-05, + "loss": 3.4597, + "step": 1551360 + }, + { + "epoch": 0.01, + "learning_rate": 2.459336343975843e-05, + "loss": 3.4765, + "step": 1551872 + }, + { + "epoch": 0.01, + "learning_rate": 2.458497749224791e-05, + "loss": 3.4717, + "step": 1552384 + }, + { + "epoch": 0.01, + "learning_rate": 2.4576607923541124e-05, + "loss": 3.4616, + "step": 1552896 + }, + { + "epoch": 0.01, + "learning_rate": 2.4568221976030607e-05, + "loss": 3.4634, + "step": 1553408 + }, + { + "epoch": 0.01, + "learning_rate": 2.4559852407323816e-05, + "loss": 3.4691, + "step": 1553920 + }, + { + "epoch": 0.01, + "learning_rate": 2.4551466459813296e-05, + "loss": 3.4517, + "step": 1554432 + }, + { + "epoch": 0.01, + "learning_rate": 2.4543080512302776e-05, + "loss": 3.4715, + "step": 1554944 + }, + { + "epoch": 0.01, + "learning_rate": 2.4534694564792253e-05, + "loss": 3.4613, + "step": 1555456 + }, + { + "epoch": 0.01, + "learning_rate": 2.4526308617281736e-05, + "loss": 3.4673, + "step": 1555968 + }, + { + "epoch": 0.01, + "learning_rate": 2.4517922669771216e-05, + "loss": 3.4734, + "step": 1556480 + }, + { + "epoch": 0.01, + "learning_rate": 2.4509536722260696e-05, + "loss": 3.4601, + "step": 1556992 + }, + { + "epoch": 0.01, + "learning_rate": 2.4501150774750176e-05, + "loss": 3.4697, + "step": 1557504 + }, + { + "epoch": 0.01, + "learning_rate": 2.4492781206043385e-05, + "loss": 3.4676, + "step": 1558016 + }, + { + "epoch": 0.01, + "learning_rate": 2.4484395258532865e-05, + "loss": 3.461, + "step": 1558528 + }, + { + "epoch": 0.01, + "learning_rate": 2.4476009311022345e-05, + "loss": 3.4586, + "step": 1559040 + }, + { + "epoch": 0.01, + "learning_rate": 2.446762336351183e-05, + "loss": 3.4658, + "step": 1559552 + }, + { + "epoch": 0.01, + "learning_rate": 2.4459253794805038e-05, + "loss": 3.4623, + "step": 1560064 + }, + { + "epoch": 0.01, + "learning_rate": 2.445088422609825e-05, + "loss": 3.4622, + "step": 1560576 + }, + { + "epoch": 0.01, + "learning_rate": 2.4442498278587727e-05, + "loss": 3.4548, + "step": 1561088 + }, + { + "epoch": 0.01, + "learning_rate": 2.4434112331077207e-05, + "loss": 3.4564, + "step": 1561600 + }, + { + "epoch": 0.01, + "learning_rate": 2.442572638356669e-05, + "loss": 3.4654, + "step": 1562112 + }, + { + "epoch": 0.01, + "learning_rate": 2.441734043605617e-05, + "loss": 3.4763, + "step": 1562624 + }, + { + "epoch": 0.01, + "learning_rate": 2.440895448854565e-05, + "loss": 3.4648, + "step": 1563136 + }, + { + "epoch": 0.01, + "learning_rate": 2.440056854103513e-05, + "loss": 3.4765, + "step": 1563648 + }, + { + "epoch": 0.01, + "learning_rate": 2.439218259352461e-05, + "loss": 3.47, + "step": 1564160 + }, + { + "epoch": 0.01, + "learning_rate": 2.438381302481782e-05, + "loss": 3.4667, + "step": 1564672 + }, + { + "epoch": 0.01, + "learning_rate": 2.43754270773073e-05, + "loss": 3.4728, + "step": 1565184 + }, + { + "epoch": 0.01, + "learning_rate": 2.4367041129796782e-05, + "loss": 3.4761, + "step": 1565696 + }, + { + "epoch": 0.01, + "learning_rate": 2.4358655182286262e-05, + "loss": 3.4641, + "step": 1566208 + }, + { + "epoch": 0.01, + "learning_rate": 2.43503019923832e-05, + "loss": 3.4674, + "step": 1566720 + }, + { + "epoch": 0.01, + "learning_rate": 2.434191604487268e-05, + "loss": 3.4745, + "step": 1567232 + }, + { + "epoch": 0.01, + "learning_rate": 2.433353009736216e-05, + "loss": 3.4686, + "step": 1567744 + }, + { + "epoch": 0.01, + "learning_rate": 2.4325144149851644e-05, + "loss": 3.472, + "step": 1568256 + }, + { + "epoch": 0.01, + "learning_rate": 2.4316758202341124e-05, + "loss": 3.47, + "step": 1568768 + }, + { + "epoch": 0.01, + "learning_rate": 2.4308372254830603e-05, + "loss": 3.4499, + "step": 1569280 + }, + { + "epoch": 0.01, + "learning_rate": 2.4299986307320083e-05, + "loss": 3.4519, + "step": 1569792 + }, + { + "epoch": 0.01, + "learning_rate": 2.429160035980956e-05, + "loss": 3.4679, + "step": 1570304 + }, + { + "epoch": 0.01, + "learning_rate": 2.4283230791102772e-05, + "loss": 3.4675, + "step": 1570816 + }, + { + "epoch": 0.01, + "learning_rate": 2.4274844843592252e-05, + "loss": 3.4625, + "step": 1571328 + }, + { + "epoch": 0.01, + "learning_rate": 2.4266458896081732e-05, + "loss": 3.4685, + "step": 1571840 + }, + { + "epoch": 0.02, + "learning_rate": 2.4258072948571212e-05, + "loss": 3.4652, + "step": 1572352 + }, + { + "epoch": 0.02, + "learning_rate": 2.4249703379864425e-05, + "loss": 3.4565, + "step": 1572864 + }, + { + "epoch": 0.02, + "learning_rate": 2.4241317432353905e-05, + "loss": 3.4646, + "step": 1573376 + }, + { + "epoch": 0.02, + "learning_rate": 2.423293148484338e-05, + "loss": 3.4661, + "step": 1573888 + }, + { + "epoch": 0.02, + "learning_rate": 2.422454553733286e-05, + "loss": 3.4769, + "step": 1574400 + }, + { + "epoch": 0.02, + "learning_rate": 2.4216159589822345e-05, + "loss": 3.4734, + "step": 1574912 + }, + { + "epoch": 0.02, + "learning_rate": 2.4207773642311825e-05, + "loss": 3.4708, + "step": 1575424 + }, + { + "epoch": 0.02, + "learning_rate": 2.4199387694801305e-05, + "loss": 3.4594, + "step": 1575936 + }, + { + "epoch": 0.02, + "learning_rate": 2.4191001747290785e-05, + "loss": 3.4733, + "step": 1576448 + }, + { + "epoch": 0.02, + "learning_rate": 2.4182632178583994e-05, + "loss": 3.4689, + "step": 1576960 + }, + { + "epoch": 0.02, + "learning_rate": 2.4174246231073474e-05, + "loss": 3.4708, + "step": 1577472 + }, + { + "epoch": 0.02, + "learning_rate": 2.4165860283562954e-05, + "loss": 3.4643, + "step": 1577984 + }, + { + "epoch": 0.02, + "learning_rate": 2.4157474336052437e-05, + "loss": 3.4563, + "step": 1578496 + }, + { + "epoch": 0.02, + "learning_rate": 2.4149104767345646e-05, + "loss": 3.4691, + "step": 1579008 + }, + { + "epoch": 0.02, + "learning_rate": 2.4140718819835126e-05, + "loss": 3.4715, + "step": 1579520 + }, + { + "epoch": 0.02, + "learning_rate": 2.4132332872324606e-05, + "loss": 3.4609, + "step": 1580032 + }, + { + "epoch": 0.02, + "learning_rate": 2.4123946924814086e-05, + "loss": 3.4657, + "step": 1580544 + }, + { + "epoch": 0.02, + "learning_rate": 2.41155773561073e-05, + "loss": 3.4631, + "step": 1581056 + }, + { + "epoch": 0.02, + "learning_rate": 2.4107191408596778e-05, + "loss": 3.4554, + "step": 1581568 + }, + { + "epoch": 0.02, + "learning_rate": 2.4098805461086258e-05, + "loss": 3.453, + "step": 1582080 + }, + { + "epoch": 0.02, + "learning_rate": 2.4090419513575738e-05, + "loss": 3.4639, + "step": 1582592 + }, + { + "epoch": 0.02, + "learning_rate": 2.4082049944868947e-05, + "loss": 3.4606, + "step": 1583104 + }, + { + "epoch": 0.02, + "learning_rate": 2.4073663997358427e-05, + "loss": 3.4588, + "step": 1583616 + }, + { + "epoch": 0.02, + "learning_rate": 2.4065278049847907e-05, + "loss": 3.4619, + "step": 1584128 + }, + { + "epoch": 0.02, + "learning_rate": 2.4056892102337387e-05, + "loss": 3.4599, + "step": 1584640 + }, + { + "epoch": 0.02, + "learning_rate": 2.404853891243433e-05, + "loss": 3.4801, + "step": 1585152 + }, + { + "epoch": 0.02, + "learning_rate": 2.404015296492381e-05, + "loss": 3.4785, + "step": 1585664 + }, + { + "epoch": 0.02, + "learning_rate": 2.403176701741329e-05, + "loss": 3.4686, + "step": 1586176 + }, + { + "epoch": 0.02, + "learning_rate": 2.402338106990277e-05, + "loss": 3.4721, + "step": 1586688 + }, + { + "epoch": 0.02, + "learning_rate": 2.401501150119598e-05, + "loss": 3.4609, + "step": 1587200 + }, + { + "epoch": 0.02, + "learning_rate": 2.400662555368546e-05, + "loss": 3.4587, + "step": 1587712 + }, + { + "epoch": 0.02, + "learning_rate": 2.399823960617494e-05, + "loss": 3.456, + "step": 1588224 + }, + { + "epoch": 0.02, + "learning_rate": 2.398985365866442e-05, + "loss": 3.461, + "step": 1588736 + }, + { + "epoch": 0.02, + "learning_rate": 2.39814677111539e-05, + "loss": 3.4637, + "step": 1589248 + }, + { + "epoch": 0.02, + "learning_rate": 2.397308176364338e-05, + "loss": 3.468, + "step": 1589760 + }, + { + "epoch": 0.02, + "learning_rate": 2.396469581613286e-05, + "loss": 3.4623, + "step": 1590272 + }, + { + "epoch": 0.02, + "learning_rate": 2.395630986862234e-05, + "loss": 3.4678, + "step": 1590784 + }, + { + "epoch": 0.02, + "learning_rate": 2.3947940299915553e-05, + "loss": 3.4626, + "step": 1591296 + }, + { + "epoch": 0.02, + "learning_rate": 2.3939554352405033e-05, + "loss": 3.4593, + "step": 1591808 + }, + { + "epoch": 0.02, + "learning_rate": 2.393116840489451e-05, + "loss": 3.4602, + "step": 1592320 + }, + { + "epoch": 0.02, + "learning_rate": 2.392278245738399e-05, + "loss": 3.4747, + "step": 1592832 + }, + { + "epoch": 0.02, + "learning_rate": 2.3914412888677206e-05, + "loss": 3.4802, + "step": 1593344 + }, + { + "epoch": 0.02, + "learning_rate": 2.3906026941166686e-05, + "loss": 3.4706, + "step": 1593856 + }, + { + "epoch": 0.02, + "learning_rate": 2.3897640993656162e-05, + "loss": 3.4629, + "step": 1594368 + }, + { + "epoch": 0.02, + "learning_rate": 2.3889255046145642e-05, + "loss": 3.469, + "step": 1594880 + }, + { + "epoch": 0.02, + "learning_rate": 2.3880885477438855e-05, + "loss": 3.4642, + "step": 1595392 + }, + { + "epoch": 0.02, + "learning_rate": 2.387249952992833e-05, + "loss": 3.4764, + "step": 1595904 + }, + { + "epoch": 0.02, + "learning_rate": 2.3864113582417815e-05, + "loss": 3.4644, + "step": 1596416 + }, + { + "epoch": 0.02, + "learning_rate": 2.3855727634907294e-05, + "loss": 3.4641, + "step": 1596928 + }, + { + "epoch": 0.02, + "learning_rate": 2.3847358066200507e-05, + "loss": 3.4628, + "step": 1597440 + }, + { + "epoch": 0.02, + "learning_rate": 2.3838972118689984e-05, + "loss": 3.474, + "step": 1597952 + }, + { + "epoch": 0.02, + "learning_rate": 2.3830602549983196e-05, + "loss": 3.4606, + "step": 1598464 + }, + { + "epoch": 0.02, + "learning_rate": 2.3822216602472676e-05, + "loss": 3.4617, + "step": 1598976 + }, + { + "epoch": 0.02, + "learning_rate": 2.3813830654962156e-05, + "loss": 3.4706, + "step": 1599488 + }, + { + "epoch": 0.02, + "learning_rate": 2.3805444707451636e-05, + "loss": 3.4609, + "step": 1600000 + }, + { + "epoch": 0.02, + "learning_rate": 2.3797058759941116e-05, + "loss": 3.4705, + "step": 1600512 + }, + { + "epoch": 0.02, + "learning_rate": 2.3788672812430596e-05, + "loss": 3.4763, + "step": 1601024 + }, + { + "epoch": 0.02, + "learning_rate": 2.3780286864920076e-05, + "loss": 3.4654, + "step": 1601536 + }, + { + "epoch": 0.02, + "learning_rate": 2.3771900917409556e-05, + "loss": 3.4569, + "step": 1602048 + }, + { + "epoch": 0.02, + "learning_rate": 2.3763531348702768e-05, + "loss": 3.461, + "step": 1602560 + }, + { + "epoch": 0.03, + "eval_loss": 3.8433775901794434, + "eval_runtime": 303.7765, + "eval_samples_per_second": 1256.157, + "eval_steps_per_second": 39.256, + "step": 1602711 + }, + { + "epoch": 1.0, + "learning_rate": 2.3755145401192248e-05, + "loss": 3.465, + "step": 1603072 + }, + { + "epoch": 1.0, + "learning_rate": 2.3746759453681728e-05, + "loss": 3.4555, + "step": 1603584 + }, + { + "epoch": 1.0, + "learning_rate": 2.3738389884974937e-05, + "loss": 3.4764, + "step": 1604096 + }, + { + "epoch": 1.0, + "learning_rate": 2.3730003937464417e-05, + "loss": 3.4631, + "step": 1604608 + }, + { + "epoch": 1.0, + "learning_rate": 2.3721617989953897e-05, + "loss": 3.4754, + "step": 1605120 + }, + { + "epoch": 1.0, + "learning_rate": 2.3713232042443377e-05, + "loss": 3.4598, + "step": 1605632 + }, + { + "epoch": 1.0, + "learning_rate": 2.370484609493286e-05, + "loss": 3.4649, + "step": 1606144 + }, + { + "epoch": 1.0, + "learning_rate": 2.369646014742234e-05, + "loss": 3.4507, + "step": 1606656 + }, + { + "epoch": 1.0, + "learning_rate": 2.3688074199911817e-05, + "loss": 3.4638, + "step": 1607168 + }, + { + "epoch": 1.0, + "learning_rate": 2.3679688252401297e-05, + "loss": 3.4581, + "step": 1607680 + }, + { + "epoch": 1.0, + "learning_rate": 2.367131868369451e-05, + "loss": 3.469, + "step": 1608192 + }, + { + "epoch": 1.0, + "learning_rate": 2.3662932736183986e-05, + "loss": 3.4716, + "step": 1608704 + }, + { + "epoch": 1.0, + "learning_rate": 2.3654563167477202e-05, + "loss": 3.4492, + "step": 1609216 + }, + { + "epoch": 1.0, + "learning_rate": 2.3646177219966682e-05, + "loss": 3.4546, + "step": 1609728 + }, + { + "epoch": 1.0, + "learning_rate": 2.3637791272456162e-05, + "loss": 3.465, + "step": 1610240 + }, + { + "epoch": 1.0, + "learning_rate": 2.3629405324945638e-05, + "loss": 3.4499, + "step": 1610752 + }, + { + "epoch": 1.0, + "learning_rate": 2.3621019377435118e-05, + "loss": 3.4584, + "step": 1611264 + }, + { + "epoch": 1.0, + "learning_rate": 2.3612633429924598e-05, + "loss": 3.4616, + "step": 1611776 + }, + { + "epoch": 1.0, + "learning_rate": 2.3604247482414078e-05, + "loss": 3.4602, + "step": 1612288 + }, + { + "epoch": 1.0, + "learning_rate": 2.359586153490356e-05, + "loss": 3.4734, + "step": 1612800 + }, + { + "epoch": 1.0, + "learning_rate": 2.358749196619677e-05, + "loss": 3.4635, + "step": 1613312 + }, + { + "epoch": 1.0, + "learning_rate": 2.357910601868625e-05, + "loss": 3.463, + "step": 1613824 + }, + { + "epoch": 1.0, + "learning_rate": 2.357072007117573e-05, + "loss": 3.4626, + "step": 1614336 + }, + { + "epoch": 1.0, + "learning_rate": 2.356233412366521e-05, + "loss": 3.4633, + "step": 1614848 + }, + { + "epoch": 1.0, + "learning_rate": 2.3553964554958423e-05, + "loss": 3.4562, + "step": 1615360 + }, + { + "epoch": 1.0, + "learning_rate": 2.3545578607447903e-05, + "loss": 3.4653, + "step": 1615872 + }, + { + "epoch": 1.0, + "learning_rate": 2.3537192659937383e-05, + "loss": 3.4573, + "step": 1616384 + }, + { + "epoch": 1.0, + "learning_rate": 2.3528823091230592e-05, + "loss": 3.4572, + "step": 1616896 + }, + { + "epoch": 1.0, + "learning_rate": 2.3520437143720072e-05, + "loss": 3.4524, + "step": 1617408 + }, + { + "epoch": 1.0, + "learning_rate": 2.3512051196209552e-05, + "loss": 3.461, + "step": 1617920 + }, + { + "epoch": 1.01, + "learning_rate": 2.3503665248699032e-05, + "loss": 3.4569, + "step": 1618432 + }, + { + "epoch": 1.01, + "learning_rate": 2.3495295679992244e-05, + "loss": 3.4623, + "step": 1618944 + }, + { + "epoch": 1.01, + "learning_rate": 2.3486909732481724e-05, + "loss": 3.4629, + "step": 1619456 + }, + { + "epoch": 1.01, + "learning_rate": 2.3478523784971204e-05, + "loss": 3.4687, + "step": 1619968 + }, + { + "epoch": 1.01, + "learning_rate": 2.3470137837460684e-05, + "loss": 3.4551, + "step": 1620480 + }, + { + "epoch": 1.01, + "learning_rate": 2.3461768268753893e-05, + "loss": 3.4651, + "step": 1620992 + }, + { + "epoch": 1.01, + "learning_rate": 2.3453382321243377e-05, + "loss": 3.453, + "step": 1621504 + }, + { + "epoch": 1.01, + "learning_rate": 2.3444996373732857e-05, + "loss": 3.461, + "step": 1622016 + }, + { + "epoch": 1.01, + "learning_rate": 2.3436610426222337e-05, + "loss": 3.4483, + "step": 1622528 + }, + { + "epoch": 1.01, + "learning_rate": 2.3428257236319278e-05, + "loss": 3.4545, + "step": 1623040 + }, + { + "epoch": 1.01, + "learning_rate": 2.3419871288808755e-05, + "loss": 3.4574, + "step": 1623552 + }, + { + "epoch": 1.01, + "learning_rate": 2.3411485341298238e-05, + "loss": 3.4658, + "step": 1624064 + }, + { + "epoch": 1.01, + "learning_rate": 2.3403099393787718e-05, + "loss": 3.4561, + "step": 1624576 + }, + { + "epoch": 1.01, + "learning_rate": 2.3394713446277198e-05, + "loss": 3.4568, + "step": 1625088 + }, + { + "epoch": 1.01, + "learning_rate": 2.3386327498766678e-05, + "loss": 3.473, + "step": 1625600 + }, + { + "epoch": 1.01, + "learning_rate": 2.3377941551256158e-05, + "loss": 3.4611, + "step": 1626112 + }, + { + "epoch": 1.01, + "learning_rate": 2.3369555603745638e-05, + "loss": 3.4621, + "step": 1626624 + }, + { + "epoch": 1.01, + "learning_rate": 2.3361186035038847e-05, + "loss": 3.4545, + "step": 1627136 + }, + { + "epoch": 1.01, + "learning_rate": 2.335280008752833e-05, + "loss": 3.4404, + "step": 1627648 + }, + { + "epoch": 1.01, + "learning_rate": 2.334441414001781e-05, + "loss": 3.4674, + "step": 1628160 + }, + { + "epoch": 1.01, + "learning_rate": 2.333602819250729e-05, + "loss": 3.4579, + "step": 1628672 + }, + { + "epoch": 1.01, + "learning_rate": 2.33276586238005e-05, + "loss": 3.4526, + "step": 1629184 + }, + { + "epoch": 1.01, + "learning_rate": 2.331927267628998e-05, + "loss": 3.4549, + "step": 1629696 + }, + { + "epoch": 1.01, + "learning_rate": 2.3310903107583192e-05, + "loss": 3.4608, + "step": 1630208 + }, + { + "epoch": 1.01, + "learning_rate": 2.330251716007267e-05, + "loss": 3.4357, + "step": 1630720 + }, + { + "epoch": 1.01, + "learning_rate": 2.329413121256215e-05, + "loss": 3.4616, + "step": 1631232 + }, + { + "epoch": 1.01, + "learning_rate": 2.328574526505163e-05, + "loss": 3.4511, + "step": 1631744 + }, + { + "epoch": 1.01, + "learning_rate": 2.327735931754111e-05, + "loss": 3.4545, + "step": 1632256 + }, + { + "epoch": 1.01, + "learning_rate": 2.3268973370030588e-05, + "loss": 3.4622, + "step": 1632768 + }, + { + "epoch": 1.01, + "learning_rate": 2.3260587422520068e-05, + "loss": 3.4533, + "step": 1633280 + }, + { + "epoch": 1.01, + "learning_rate": 2.3252201475009548e-05, + "loss": 3.4521, + "step": 1633792 + }, + { + "epoch": 1.01, + "learning_rate": 2.3243831906302764e-05, + "loss": 3.4598, + "step": 1634304 + }, + { + "epoch": 1.01, + "learning_rate": 2.323544595879224e-05, + "loss": 3.4441, + "step": 1634816 + }, + { + "epoch": 1.01, + "learning_rate": 2.322706001128172e-05, + "loss": 3.4493, + "step": 1635328 + }, + { + "epoch": 1.01, + "learning_rate": 2.32186740637712e-05, + "loss": 3.4543, + "step": 1635840 + }, + { + "epoch": 1.01, + "learning_rate": 2.321030449506441e-05, + "loss": 3.4548, + "step": 1636352 + }, + { + "epoch": 1.01, + "learning_rate": 2.3201934926357625e-05, + "loss": 3.4498, + "step": 1636864 + }, + { + "epoch": 1.01, + "learning_rate": 2.3193548978847105e-05, + "loss": 3.4444, + "step": 1637376 + }, + { + "epoch": 1.01, + "learning_rate": 2.3185163031336585e-05, + "loss": 3.448, + "step": 1637888 + }, + { + "epoch": 1.01, + "learning_rate": 2.3176777083826062e-05, + "loss": 3.4519, + "step": 1638400 + }, + { + "epoch": 1.01, + "learning_rate": 2.3168391136315542e-05, + "loss": 3.4627, + "step": 1638912 + }, + { + "epoch": 1.01, + "learning_rate": 2.3160005188805022e-05, + "loss": 3.4514, + "step": 1639424 + }, + { + "epoch": 1.01, + "learning_rate": 2.3151619241294502e-05, + "loss": 3.4667, + "step": 1639936 + }, + { + "epoch": 1.01, + "learning_rate": 2.3143233293783985e-05, + "loss": 3.4604, + "step": 1640448 + }, + { + "epoch": 1.01, + "learning_rate": 2.3134863725077194e-05, + "loss": 3.4565, + "step": 1640960 + }, + { + "epoch": 1.01, + "learning_rate": 2.3126477777566674e-05, + "loss": 3.4569, + "step": 1641472 + }, + { + "epoch": 1.01, + "learning_rate": 2.3118091830056154e-05, + "loss": 3.464, + "step": 1641984 + }, + { + "epoch": 1.01, + "learning_rate": 2.3109705882545634e-05, + "loss": 3.4563, + "step": 1642496 + }, + { + "epoch": 1.01, + "learning_rate": 2.310135269264258e-05, + "loss": 3.454, + "step": 1643008 + }, + { + "epoch": 1.01, + "learning_rate": 2.309296674513206e-05, + "loss": 3.4626, + "step": 1643520 + }, + { + "epoch": 1.01, + "learning_rate": 2.3084580797621536e-05, + "loss": 3.4579, + "step": 1644032 + }, + { + "epoch": 1.01, + "learning_rate": 2.3076194850111016e-05, + "loss": 3.4604, + "step": 1644544 + }, + { + "epoch": 1.01, + "learning_rate": 2.3067808902600495e-05, + "loss": 3.4592, + "step": 1645056 + }, + { + "epoch": 1.01, + "learning_rate": 2.3059422955089975e-05, + "loss": 3.4375, + "step": 1645568 + }, + { + "epoch": 1.01, + "learning_rate": 2.3051037007579455e-05, + "loss": 3.4403, + "step": 1646080 + }, + { + "epoch": 1.01, + "learning_rate": 2.304265106006894e-05, + "loss": 3.4526, + "step": 1646592 + }, + { + "epoch": 1.01, + "learning_rate": 2.3034281491362148e-05, + "loss": 3.457, + "step": 1647104 + }, + { + "epoch": 1.01, + "learning_rate": 2.3025895543851628e-05, + "loss": 3.4512, + "step": 1647616 + }, + { + "epoch": 1.01, + "learning_rate": 2.3017509596341108e-05, + "loss": 3.4554, + "step": 1648128 + }, + { + "epoch": 1.02, + "learning_rate": 2.3009123648830588e-05, + "loss": 3.4525, + "step": 1648640 + }, + { + "epoch": 1.02, + "learning_rate": 2.30007540801238e-05, + "loss": 3.4458, + "step": 1649152 + }, + { + "epoch": 1.02, + "learning_rate": 2.299236813261328e-05, + "loss": 3.4548, + "step": 1649664 + }, + { + "epoch": 1.02, + "learning_rate": 2.298398218510276e-05, + "loss": 3.4505, + "step": 1650176 + }, + { + "epoch": 1.02, + "learning_rate": 2.297559623759224e-05, + "loss": 3.4644, + "step": 1650688 + }, + { + "epoch": 1.02, + "learning_rate": 2.296722666888545e-05, + "loss": 3.4657, + "step": 1651200 + }, + { + "epoch": 1.02, + "learning_rate": 2.295884072137493e-05, + "loss": 3.4598, + "step": 1651712 + }, + { + "epoch": 1.02, + "learning_rate": 2.295045477386441e-05, + "loss": 3.4514, + "step": 1652224 + }, + { + "epoch": 1.02, + "learning_rate": 2.2942068826353892e-05, + "loss": 3.4561, + "step": 1652736 + }, + { + "epoch": 1.02, + "learning_rate": 2.29336992576471e-05, + "loss": 3.4576, + "step": 1653248 + }, + { + "epoch": 1.02, + "learning_rate": 2.292531331013658e-05, + "loss": 3.4597, + "step": 1653760 + }, + { + "epoch": 1.02, + "learning_rate": 2.291692736262606e-05, + "loss": 3.4509, + "step": 1654272 + }, + { + "epoch": 1.02, + "learning_rate": 2.2908541415115538e-05, + "loss": 3.4463, + "step": 1654784 + }, + { + "epoch": 1.02, + "learning_rate": 2.2900171846408754e-05, + "loss": 3.4618, + "step": 1655296 + }, + { + "epoch": 1.02, + "learning_rate": 2.2891785898898234e-05, + "loss": 3.4547, + "step": 1655808 + }, + { + "epoch": 1.02, + "learning_rate": 2.2883399951387714e-05, + "loss": 3.4517, + "step": 1656320 + }, + { + "epoch": 1.02, + "learning_rate": 2.287501400387719e-05, + "loss": 3.4551, + "step": 1656832 + }, + { + "epoch": 1.02, + "learning_rate": 2.2866644435170403e-05, + "loss": 3.4519, + "step": 1657344 + }, + { + "epoch": 1.02, + "learning_rate": 2.2858258487659883e-05, + "loss": 3.4457, + "step": 1657856 + }, + { + "epoch": 1.02, + "learning_rate": 2.2849872540149363e-05, + "loss": 3.44, + "step": 1658368 + }, + { + "epoch": 1.02, + "learning_rate": 2.2841486592638843e-05, + "loss": 3.451, + "step": 1658880 + }, + { + "epoch": 1.02, + "learning_rate": 2.2833117023932055e-05, + "loss": 3.4548, + "step": 1659392 + }, + { + "epoch": 1.02, + "learning_rate": 2.2824731076421535e-05, + "loss": 3.4487, + "step": 1659904 + }, + { + "epoch": 1.02, + "learning_rate": 2.281634512891101e-05, + "loss": 3.4503, + "step": 1660416 + }, + { + "epoch": 1.02, + "learning_rate": 2.280795918140049e-05, + "loss": 3.4452, + "step": 1660928 + }, + { + "epoch": 1.02, + "learning_rate": 2.2799605991497437e-05, + "loss": 3.4685, + "step": 1661440 + }, + { + "epoch": 1.02, + "learning_rate": 2.2791220043986917e-05, + "loss": 3.4682, + "step": 1661952 + }, + { + "epoch": 1.02, + "learning_rate": 2.2782834096476397e-05, + "loss": 3.4593, + "step": 1662464 + }, + { + "epoch": 1.02, + "learning_rate": 2.2774448148965877e-05, + "loss": 3.461, + "step": 1662976 + }, + { + "epoch": 1.02, + "learning_rate": 2.2766062201455356e-05, + "loss": 3.4462, + "step": 1663488 + }, + { + "epoch": 1.02, + "learning_rate": 2.275769263274857e-05, + "loss": 3.4493, + "step": 1664000 + }, + { + "epoch": 1.02, + "learning_rate": 2.274930668523805e-05, + "loss": 3.4451, + "step": 1664512 + }, + { + "epoch": 1.02, + "learning_rate": 2.274092073772753e-05, + "loss": 3.4484, + "step": 1665024 + }, + { + "epoch": 1.02, + "learning_rate": 2.273253479021701e-05, + "loss": 3.4529, + "step": 1665536 + }, + { + "epoch": 1.02, + "learning_rate": 2.2724148842706485e-05, + "loss": 3.4507, + "step": 1666048 + }, + { + "epoch": 1.02, + "learning_rate": 2.2715762895195965e-05, + "loss": 3.4542, + "step": 1666560 + }, + { + "epoch": 1.02, + "learning_rate": 2.2707376947685445e-05, + "loss": 3.4539, + "step": 1667072 + }, + { + "epoch": 1.02, + "learning_rate": 2.269900737897866e-05, + "loss": 3.454, + "step": 1667584 + }, + { + "epoch": 1.02, + "learning_rate": 2.2690621431468138e-05, + "loss": 3.4496, + "step": 1668096 + }, + { + "epoch": 1.02, + "learning_rate": 2.268225186276135e-05, + "loss": 3.4537, + "step": 1668608 + }, + { + "epoch": 1.02, + "learning_rate": 2.267386591525083e-05, + "loss": 3.4566, + "step": 1669120 + }, + { + "epoch": 1.02, + "learning_rate": 2.2665479967740307e-05, + "loss": 3.467, + "step": 1669632 + }, + { + "epoch": 1.02, + "learning_rate": 2.2657094020229787e-05, + "loss": 3.4622, + "step": 1670144 + }, + { + "epoch": 1.02, + "learning_rate": 2.264870807271927e-05, + "loss": 3.4499, + "step": 1670656 + }, + { + "epoch": 1.02, + "learning_rate": 2.264032212520875e-05, + "loss": 3.4592, + "step": 1671168 + }, + { + "epoch": 1.02, + "learning_rate": 2.263193617769823e-05, + "loss": 3.4529, + "step": 1671680 + }, + { + "epoch": 1.02, + "learning_rate": 2.262356660899144e-05, + "loss": 3.4621, + "step": 1672192 + }, + { + "epoch": 1.02, + "learning_rate": 2.261518066148092e-05, + "loss": 3.4542, + "step": 1672704 + }, + { + "epoch": 1.02, + "learning_rate": 2.26067947139704e-05, + "loss": 3.4529, + "step": 1673216 + }, + { + "epoch": 1.02, + "learning_rate": 2.259840876645988e-05, + "loss": 3.4513, + "step": 1673728 + }, + { + "epoch": 1.02, + "learning_rate": 2.259003919775309e-05, + "loss": 3.4609, + "step": 1674240 + }, + { + "epoch": 1.02, + "learning_rate": 2.258165325024257e-05, + "loss": 3.4496, + "step": 1674752 + }, + { + "epoch": 1.02, + "learning_rate": 2.257326730273205e-05, + "loss": 3.4534, + "step": 1675264 + }, + { + "epoch": 1.02, + "learning_rate": 2.256488135522153e-05, + "loss": 3.4532, + "step": 1675776 + }, + { + "epoch": 1.02, + "learning_rate": 2.255651178651474e-05, + "loss": 3.4559, + "step": 1676288 + }, + { + "epoch": 1.02, + "learning_rate": 2.2548142217807956e-05, + "loss": 3.459, + "step": 1676800 + }, + { + "epoch": 1.02, + "learning_rate": 2.2539756270297433e-05, + "loss": 3.4579, + "step": 1677312 + }, + { + "epoch": 1.02, + "learning_rate": 2.2531370322786913e-05, + "loss": 3.4613, + "step": 1677824 + }, + { + "epoch": 1.02, + "learning_rate": 2.2522984375276393e-05, + "loss": 3.4429, + "step": 1678336 + }, + { + "epoch": 1.02, + "learning_rate": 2.2514598427765873e-05, + "loss": 3.4525, + "step": 1678848 + }, + { + "epoch": 1.03, + "eval_loss": 3.8458375930786133, + "eval_runtime": 303.9839, + "eval_samples_per_second": 1255.3, + "eval_steps_per_second": 39.229, + "step": 1679031 + }, + { + "epoch": 0.0, + "learning_rate": 2.2506212480255353e-05, + "loss": 3.4496, + "step": 1679360 + }, + { + "epoch": 0.0, + "learning_rate": 2.2497826532744833e-05, + "loss": 3.4449, + "step": 1679872 + }, + { + "epoch": 0.0, + "learning_rate": 2.2489456964038045e-05, + "loss": 3.4617, + "step": 1680384 + }, + { + "epoch": 0.0, + "learning_rate": 2.2481071016527525e-05, + "loss": 3.4536, + "step": 1680896 + }, + { + "epoch": 0.0, + "learning_rate": 2.2472685069017005e-05, + "loss": 3.465, + "step": 1681408 + }, + { + "epoch": 0.0, + "learning_rate": 2.2464299121506485e-05, + "loss": 3.4474, + "step": 1681920 + }, + { + "epoch": 0.0, + "learning_rate": 2.245591317399596e-05, + "loss": 3.4486, + "step": 1682432 + }, + { + "epoch": 0.0, + "learning_rate": 2.244752722648544e-05, + "loss": 3.4477, + "step": 1682944 + }, + { + "epoch": 0.0, + "learning_rate": 2.2439141278974925e-05, + "loss": 3.4491, + "step": 1683456 + }, + { + "epoch": 0.0, + "learning_rate": 2.2430755331464405e-05, + "loss": 3.4484, + "step": 1683968 + }, + { + "epoch": 0.0, + "learning_rate": 2.2422385762757614e-05, + "loss": 3.459, + "step": 1684480 + }, + { + "epoch": 0.0, + "learning_rate": 2.2413999815247094e-05, + "loss": 3.4612, + "step": 1684992 + }, + { + "epoch": 0.0, + "learning_rate": 2.2405630246540306e-05, + "loss": 3.4394, + "step": 1685504 + }, + { + "epoch": 0.0, + "learning_rate": 2.2397244299029786e-05, + "loss": 3.4414, + "step": 1686016 + }, + { + "epoch": 0.0, + "learning_rate": 2.2388858351519266e-05, + "loss": 3.4559, + "step": 1686528 + }, + { + "epoch": 0.0, + "learning_rate": 2.2380472404008746e-05, + "loss": 3.4354, + "step": 1687040 + }, + { + "epoch": 0.0, + "learning_rate": 2.2372086456498226e-05, + "loss": 3.448, + "step": 1687552 + }, + { + "epoch": 0.0, + "learning_rate": 2.2363700508987706e-05, + "loss": 3.4482, + "step": 1688064 + }, + { + "epoch": 0.0, + "learning_rate": 2.2355314561477186e-05, + "loss": 3.4468, + "step": 1688576 + }, + { + "epoch": 0.0, + "learning_rate": 2.2346928613966666e-05, + "loss": 3.4645, + "step": 1689088 + }, + { + "epoch": 0.0, + "learning_rate": 2.233855904525988e-05, + "loss": 3.4511, + "step": 1689600 + }, + { + "epoch": 0.0, + "learning_rate": 2.233017309774936e-05, + "loss": 3.4516, + "step": 1690112 + }, + { + "epoch": 0.0, + "learning_rate": 2.232178715023884e-05, + "loss": 3.4462, + "step": 1690624 + }, + { + "epoch": 0.0, + "learning_rate": 2.231340120272832e-05, + "loss": 3.4541, + "step": 1691136 + }, + { + "epoch": 0.0, + "learning_rate": 2.2305031634021527e-05, + "loss": 3.4467, + "step": 1691648 + }, + { + "epoch": 0.0, + "learning_rate": 2.2296645686511007e-05, + "loss": 3.4519, + "step": 1692160 + }, + { + "epoch": 0.0, + "learning_rate": 2.2288259739000487e-05, + "loss": 3.4468, + "step": 1692672 + }, + { + "epoch": 0.0, + "learning_rate": 2.227987379148997e-05, + "loss": 3.4418, + "step": 1693184 + }, + { + "epoch": 0.0, + "learning_rate": 2.227150422278318e-05, + "loss": 3.4466, + "step": 1693696 + }, + { + "epoch": 0.0, + "learning_rate": 2.226311827527266e-05, + "loss": 3.4458, + "step": 1694208 + }, + { + "epoch": 0.01, + "learning_rate": 2.225473232776214e-05, + "loss": 3.4537, + "step": 1694720 + }, + { + "epoch": 0.01, + "learning_rate": 2.2246346380251616e-05, + "loss": 3.4475, + "step": 1695232 + }, + { + "epoch": 0.01, + "learning_rate": 2.2237976811544832e-05, + "loss": 3.4549, + "step": 1695744 + }, + { + "epoch": 0.01, + "learning_rate": 2.2229590864034312e-05, + "loss": 3.4595, + "step": 1696256 + }, + { + "epoch": 0.01, + "learning_rate": 2.2221204916523792e-05, + "loss": 3.4428, + "step": 1696768 + }, + { + "epoch": 0.01, + "learning_rate": 2.221281896901327e-05, + "loss": 3.4511, + "step": 1697280 + }, + { + "epoch": 0.01, + "learning_rate": 2.220444940030648e-05, + "loss": 3.4458, + "step": 1697792 + }, + { + "epoch": 0.01, + "learning_rate": 2.219606345279596e-05, + "loss": 3.4466, + "step": 1698304 + }, + { + "epoch": 0.01, + "learning_rate": 2.218767750528544e-05, + "loss": 3.437, + "step": 1698816 + }, + { + "epoch": 0.01, + "learning_rate": 2.2179324315382383e-05, + "loss": 3.4445, + "step": 1699328 + }, + { + "epoch": 0.01, + "learning_rate": 2.2170938367871863e-05, + "loss": 3.4445, + "step": 1699840 + }, + { + "epoch": 0.01, + "learning_rate": 2.2162552420361343e-05, + "loss": 3.4528, + "step": 1700352 + }, + { + "epoch": 0.01, + "learning_rate": 2.2154166472850823e-05, + "loss": 3.445, + "step": 1700864 + }, + { + "epoch": 0.01, + "learning_rate": 2.2145780525340302e-05, + "loss": 3.4459, + "step": 1701376 + }, + { + "epoch": 0.01, + "learning_rate": 2.2137394577829786e-05, + "loss": 3.4644, + "step": 1701888 + }, + { + "epoch": 0.01, + "learning_rate": 2.2129008630319266e-05, + "loss": 3.4489, + "step": 1702400 + }, + { + "epoch": 0.01, + "learning_rate": 2.2120622682808742e-05, + "loss": 3.4498, + "step": 1702912 + }, + { + "epoch": 0.01, + "learning_rate": 2.2112253114101955e-05, + "loss": 3.4427, + "step": 1703424 + }, + { + "epoch": 0.01, + "learning_rate": 2.2103867166591435e-05, + "loss": 3.43, + "step": 1703936 + }, + { + "epoch": 0.01, + "learning_rate": 2.209548121908091e-05, + "loss": 3.459, + "step": 1704448 + }, + { + "epoch": 0.01, + "learning_rate": 2.2087095271570395e-05, + "loss": 3.4436, + "step": 1704960 + }, + { + "epoch": 0.01, + "learning_rate": 2.2078725702863607e-05, + "loss": 3.4417, + "step": 1705472 + }, + { + "epoch": 0.01, + "learning_rate": 2.2070339755353087e-05, + "loss": 3.4431, + "step": 1705984 + }, + { + "epoch": 0.01, + "learning_rate": 2.2061970186646296e-05, + "loss": 3.4482, + "step": 1706496 + }, + { + "epoch": 0.01, + "learning_rate": 2.2053584239135776e-05, + "loss": 3.4228, + "step": 1707008 + }, + { + "epoch": 0.01, + "learning_rate": 2.2045198291625256e-05, + "loss": 3.4425, + "step": 1707520 + }, + { + "epoch": 0.01, + "learning_rate": 2.203681234411474e-05, + "loss": 3.444, + "step": 1708032 + }, + { + "epoch": 0.01, + "learning_rate": 2.2028426396604216e-05, + "loss": 3.4386, + "step": 1708544 + }, + { + "epoch": 0.01, + "learning_rate": 2.2020040449093696e-05, + "loss": 3.4542, + "step": 1709056 + }, + { + "epoch": 0.01, + "learning_rate": 2.2011654501583176e-05, + "loss": 3.441, + "step": 1709568 + }, + { + "epoch": 0.01, + "learning_rate": 2.2003268554072656e-05, + "loss": 3.4395, + "step": 1710080 + }, + { + "epoch": 0.01, + "learning_rate": 2.1994898985365865e-05, + "loss": 3.4518, + "step": 1710592 + }, + { + "epoch": 0.01, + "learning_rate": 2.198651303785535e-05, + "loss": 3.4396, + "step": 1711104 + }, + { + "epoch": 0.01, + "learning_rate": 2.1978127090344828e-05, + "loss": 3.4344, + "step": 1711616 + }, + { + "epoch": 0.01, + "learning_rate": 2.1969741142834308e-05, + "loss": 3.442, + "step": 1712128 + }, + { + "epoch": 0.01, + "learning_rate": 2.1961371574127517e-05, + "loss": 3.4441, + "step": 1712640 + }, + { + "epoch": 0.01, + "learning_rate": 2.195300200542073e-05, + "loss": 3.4421, + "step": 1713152 + }, + { + "epoch": 0.01, + "learning_rate": 2.194461605791021e-05, + "loss": 3.4344, + "step": 1713664 + }, + { + "epoch": 0.01, + "learning_rate": 2.193623011039969e-05, + "loss": 3.4292, + "step": 1714176 + }, + { + "epoch": 0.01, + "learning_rate": 2.192784416288917e-05, + "loss": 3.4393, + "step": 1714688 + }, + { + "epoch": 0.01, + "learning_rate": 2.191945821537865e-05, + "loss": 3.4541, + "step": 1715200 + }, + { + "epoch": 0.01, + "learning_rate": 2.191107226786813e-05, + "loss": 3.4427, + "step": 1715712 + }, + { + "epoch": 0.01, + "learning_rate": 2.190268632035761e-05, + "loss": 3.4584, + "step": 1716224 + }, + { + "epoch": 0.01, + "learning_rate": 2.189430037284709e-05, + "loss": 3.4488, + "step": 1716736 + }, + { + "epoch": 0.01, + "learning_rate": 2.1885930804140302e-05, + "loss": 3.4465, + "step": 1717248 + }, + { + "epoch": 0.01, + "learning_rate": 2.1877544856629782e-05, + "loss": 3.4415, + "step": 1717760 + }, + { + "epoch": 0.01, + "learning_rate": 2.1869158909119262e-05, + "loss": 3.456, + "step": 1718272 + }, + { + "epoch": 0.01, + "learning_rate": 2.1860772961608742e-05, + "loss": 3.4434, + "step": 1718784 + }, + { + "epoch": 0.01, + "learning_rate": 2.1852419771705684e-05, + "loss": 3.44, + "step": 1719296 + }, + { + "epoch": 0.01, + "learning_rate": 2.1844033824195163e-05, + "loss": 3.4547, + "step": 1719808 + }, + { + "epoch": 0.01, + "learning_rate": 2.1835647876684643e-05, + "loss": 3.4472, + "step": 1720320 + }, + { + "epoch": 0.01, + "learning_rate": 2.1827261929174123e-05, + "loss": 3.4507, + "step": 1720832 + }, + { + "epoch": 0.01, + "learning_rate": 2.1818875981663603e-05, + "loss": 3.445, + "step": 1721344 + }, + { + "epoch": 0.01, + "learning_rate": 2.1810490034153083e-05, + "loss": 3.4281, + "step": 1721856 + }, + { + "epoch": 0.01, + "learning_rate": 2.1802104086642563e-05, + "loss": 3.4292, + "step": 1722368 + }, + { + "epoch": 0.01, + "learning_rate": 2.179371813913204e-05, + "loss": 3.4396, + "step": 1722880 + }, + { + "epoch": 0.01, + "learning_rate": 2.1785348570425256e-05, + "loss": 3.4461, + "step": 1723392 + }, + { + "epoch": 0.01, + "learning_rate": 2.1776962622914736e-05, + "loss": 3.4407, + "step": 1723904 + }, + { + "epoch": 0.01, + "learning_rate": 2.1768576675404216e-05, + "loss": 3.4385, + "step": 1724416 + }, + { + "epoch": 0.02, + "learning_rate": 2.1760190727893692e-05, + "loss": 3.4434, + "step": 1724928 + }, + { + "epoch": 0.02, + "learning_rate": 2.1751821159186905e-05, + "loss": 3.4346, + "step": 1725440 + }, + { + "epoch": 0.02, + "learning_rate": 2.1743435211676385e-05, + "loss": 3.4418, + "step": 1725952 + }, + { + "epoch": 0.02, + "learning_rate": 2.1735049264165865e-05, + "loss": 3.4381, + "step": 1726464 + }, + { + "epoch": 0.02, + "learning_rate": 2.1726679695459077e-05, + "loss": 3.459, + "step": 1726976 + }, + { + "epoch": 0.02, + "learning_rate": 2.1718293747948557e-05, + "loss": 3.4556, + "step": 1727488 + }, + { + "epoch": 0.02, + "learning_rate": 2.1709907800438037e-05, + "loss": 3.4465, + "step": 1728000 + }, + { + "epoch": 0.02, + "learning_rate": 2.1701521852927514e-05, + "loss": 3.4417, + "step": 1728512 + }, + { + "epoch": 0.02, + "learning_rate": 2.1693135905416993e-05, + "loss": 3.4485, + "step": 1729024 + }, + { + "epoch": 0.02, + "learning_rate": 2.1684749957906473e-05, + "loss": 3.4423, + "step": 1729536 + }, + { + "epoch": 0.02, + "learning_rate": 2.1676364010395957e-05, + "loss": 3.454, + "step": 1730048 + }, + { + "epoch": 0.02, + "learning_rate": 2.1667978062885437e-05, + "loss": 3.4389, + "step": 1730560 + }, + { + "epoch": 0.02, + "learning_rate": 2.1659608494178646e-05, + "loss": 3.4376, + "step": 1731072 + }, + { + "epoch": 0.02, + "learning_rate": 2.1651222546668126e-05, + "loss": 3.4463, + "step": 1731584 + }, + { + "epoch": 0.02, + "learning_rate": 2.1642836599157606e-05, + "loss": 3.4471, + "step": 1732096 + }, + { + "epoch": 0.02, + "learning_rate": 2.1634450651647086e-05, + "loss": 3.4356, + "step": 1732608 + }, + { + "epoch": 0.02, + "learning_rate": 2.1626081082940298e-05, + "loss": 3.445, + "step": 1733120 + }, + { + "epoch": 0.02, + "learning_rate": 2.1617695135429778e-05, + "loss": 3.4372, + "step": 1733632 + }, + { + "epoch": 0.02, + "learning_rate": 2.1609309187919258e-05, + "loss": 3.4368, + "step": 1734144 + }, + { + "epoch": 0.02, + "learning_rate": 2.1600923240408738e-05, + "loss": 3.4261, + "step": 1734656 + }, + { + "epoch": 0.02, + "learning_rate": 2.1592553671701947e-05, + "loss": 3.4451, + "step": 1735168 + }, + { + "epoch": 0.02, + "learning_rate": 2.1584167724191427e-05, + "loss": 3.4403, + "step": 1735680 + }, + { + "epoch": 0.02, + "learning_rate": 2.157578177668091e-05, + "loss": 3.4367, + "step": 1736192 + }, + { + "epoch": 0.02, + "learning_rate": 2.156741220797412e-05, + "loss": 3.4416, + "step": 1736704 + }, + { + "epoch": 0.02, + "learning_rate": 2.15590262604636e-05, + "loss": 3.435, + "step": 1737216 + }, + { + "epoch": 0.02, + "learning_rate": 2.155065669175681e-05, + "loss": 3.4536, + "step": 1737728 + }, + { + "epoch": 0.02, + "learning_rate": 2.154227074424629e-05, + "loss": 3.4582, + "step": 1738240 + }, + { + "epoch": 0.02, + "learning_rate": 2.1533884796735772e-05, + "loss": 3.4485, + "step": 1738752 + }, + { + "epoch": 0.02, + "learning_rate": 2.1525498849225252e-05, + "loss": 3.4485, + "step": 1739264 + }, + { + "epoch": 0.02, + "learning_rate": 2.1517112901714732e-05, + "loss": 3.4387, + "step": 1739776 + }, + { + "epoch": 0.02, + "learning_rate": 2.150874333300794e-05, + "loss": 3.437, + "step": 1740288 + }, + { + "epoch": 0.02, + "learning_rate": 2.150035738549742e-05, + "loss": 3.4306, + "step": 1740800 + }, + { + "epoch": 0.02, + "learning_rate": 2.14919714379869e-05, + "loss": 3.4386, + "step": 1741312 + }, + { + "epoch": 0.02, + "learning_rate": 2.148358549047638e-05, + "loss": 3.4417, + "step": 1741824 + }, + { + "epoch": 0.02, + "learning_rate": 2.1475199542965864e-05, + "loss": 3.4405, + "step": 1742336 + }, + { + "epoch": 0.02, + "learning_rate": 2.1466813595455344e-05, + "loss": 3.4431, + "step": 1742848 + }, + { + "epoch": 0.02, + "learning_rate": 2.145842764794482e-05, + "loss": 3.4387, + "step": 1743360 + }, + { + "epoch": 0.02, + "learning_rate": 2.1450058079238033e-05, + "loss": 3.447, + "step": 1743872 + }, + { + "epoch": 0.02, + "learning_rate": 2.1441672131727513e-05, + "loss": 3.4343, + "step": 1744384 + }, + { + "epoch": 0.02, + "learning_rate": 2.1433302563020726e-05, + "loss": 3.4451, + "step": 1744896 + }, + { + "epoch": 0.02, + "learning_rate": 2.1424916615510206e-05, + "loss": 3.4425, + "step": 1745408 + }, + { + "epoch": 0.02, + "learning_rate": 2.1416530667999685e-05, + "loss": 3.4545, + "step": 1745920 + }, + { + "epoch": 0.02, + "learning_rate": 2.1408144720489165e-05, + "loss": 3.451, + "step": 1746432 + }, + { + "epoch": 0.02, + "learning_rate": 2.1399758772978642e-05, + "loss": 3.4396, + "step": 1746944 + }, + { + "epoch": 0.02, + "learning_rate": 2.1391372825468122e-05, + "loss": 3.4507, + "step": 1747456 + }, + { + "epoch": 0.02, + "learning_rate": 2.1382986877957602e-05, + "loss": 3.4403, + "step": 1747968 + }, + { + "epoch": 0.02, + "learning_rate": 2.1374617309250818e-05, + "loss": 3.452, + "step": 1748480 + }, + { + "epoch": 0.02, + "learning_rate": 2.1366231361740294e-05, + "loss": 3.444, + "step": 1748992 + }, + { + "epoch": 0.02, + "learning_rate": 2.1357845414229774e-05, + "loss": 3.4472, + "step": 1749504 + }, + { + "epoch": 0.02, + "learning_rate": 2.1349459466719254e-05, + "loss": 3.4371, + "step": 1750016 + }, + { + "epoch": 0.02, + "learning_rate": 2.1341073519208734e-05, + "loss": 3.4478, + "step": 1750528 + }, + { + "epoch": 0.02, + "learning_rate": 2.1332703950501943e-05, + "loss": 3.4365, + "step": 1751040 + }, + { + "epoch": 0.02, + "learning_rate": 2.132433438179516e-05, + "loss": 3.4425, + "step": 1751552 + }, + { + "epoch": 0.02, + "learning_rate": 2.131594843428464e-05, + "loss": 3.4463, + "step": 1752064 + }, + { + "epoch": 0.02, + "learning_rate": 2.1307562486774116e-05, + "loss": 3.4447, + "step": 1752576 + }, + { + "epoch": 0.02, + "learning_rate": 2.1299176539263596e-05, + "loss": 3.4455, + "step": 1753088 + }, + { + "epoch": 0.02, + "learning_rate": 2.1290790591753076e-05, + "loss": 3.4456, + "step": 1753600 + }, + { + "epoch": 0.02, + "learning_rate": 2.1282421023046288e-05, + "loss": 3.4507, + "step": 1754112 + }, + { + "epoch": 0.02, + "learning_rate": 2.1274035075535768e-05, + "loss": 3.4321, + "step": 1754624 + }, + { + "epoch": 0.02, + "learning_rate": 2.1265649128025248e-05, + "loss": 3.4464, + "step": 1755136 + }, + { + "epoch": 0.03, + "eval_loss": 3.8472068309783936, + "eval_runtime": 304.174, + "eval_samples_per_second": 1254.515, + "eval_steps_per_second": 39.205, + "step": 1755351 + }, + { + "epoch": 1.0, + "learning_rate": 2.1257263180514728e-05, + "loss": 3.4396, + "step": 1755648 + }, + { + "epoch": 1.0, + "learning_rate": 2.1248877233004208e-05, + "loss": 3.4336, + "step": 1756160 + }, + { + "epoch": 1.0, + "learning_rate": 2.1240507664297417e-05, + "loss": 3.4509, + "step": 1756672 + }, + { + "epoch": 1.0, + "learning_rate": 2.1232121716786897e-05, + "loss": 3.444, + "step": 1757184 + }, + { + "epoch": 1.0, + "learning_rate": 2.122373576927638e-05, + "loss": 3.4504, + "step": 1757696 + }, + { + "epoch": 1.0, + "learning_rate": 2.121534982176586e-05, + "loss": 3.4385, + "step": 1758208 + }, + { + "epoch": 1.0, + "learning_rate": 2.120696387425534e-05, + "loss": 3.4368, + "step": 1758720 + }, + { + "epoch": 1.0, + "learning_rate": 2.119857792674482e-05, + "loss": 3.4387, + "step": 1759232 + }, + { + "epoch": 1.0, + "learning_rate": 2.1190191979234297e-05, + "loss": 3.4405, + "step": 1759744 + }, + { + "epoch": 1.0, + "learning_rate": 2.1181806031723777e-05, + "loss": 3.4327, + "step": 1760256 + }, + { + "epoch": 1.0, + "learning_rate": 2.117343646301699e-05, + "loss": 3.4505, + "step": 1760768 + }, + { + "epoch": 1.0, + "learning_rate": 2.1165050515506473e-05, + "loss": 3.4467, + "step": 1761280 + }, + { + "epoch": 1.0, + "learning_rate": 2.115668094679968e-05, + "loss": 3.4352, + "step": 1761792 + }, + { + "epoch": 1.0, + "learning_rate": 2.114829499928916e-05, + "loss": 3.427, + "step": 1762304 + }, + { + "epoch": 1.0, + "learning_rate": 2.113990905177864e-05, + "loss": 3.4416, + "step": 1762816 + }, + { + "epoch": 1.0, + "learning_rate": 2.1131523104268118e-05, + "loss": 3.4274, + "step": 1763328 + }, + { + "epoch": 1.0, + "learning_rate": 2.1123137156757598e-05, + "loss": 3.4367, + "step": 1763840 + }, + { + "epoch": 1.0, + "learning_rate": 2.111475120924708e-05, + "loss": 3.4352, + "step": 1764352 + }, + { + "epoch": 1.0, + "learning_rate": 2.110636526173656e-05, + "loss": 3.4399, + "step": 1764864 + }, + { + "epoch": 1.0, + "learning_rate": 2.109797931422604e-05, + "loss": 3.4503, + "step": 1765376 + }, + { + "epoch": 1.0, + "learning_rate": 2.108960974551925e-05, + "loss": 3.4459, + "step": 1765888 + }, + { + "epoch": 1.0, + "learning_rate": 2.108122379800873e-05, + "loss": 3.4382, + "step": 1766400 + }, + { + "epoch": 1.0, + "learning_rate": 2.107283785049821e-05, + "loss": 3.438, + "step": 1766912 + }, + { + "epoch": 1.0, + "learning_rate": 2.106445190298769e-05, + "loss": 3.4409, + "step": 1767424 + }, + { + "epoch": 1.0, + "learning_rate": 2.1056082334280903e-05, + "loss": 3.4341, + "step": 1767936 + }, + { + "epoch": 1.0, + "learning_rate": 2.1047696386770383e-05, + "loss": 3.4434, + "step": 1768448 + }, + { + "epoch": 1.0, + "learning_rate": 2.1039310439259863e-05, + "loss": 3.4369, + "step": 1768960 + }, + { + "epoch": 1.0, + "learning_rate": 2.1030924491749343e-05, + "loss": 3.4331, + "step": 1769472 + }, + { + "epoch": 1.0, + "learning_rate": 2.1022554923042552e-05, + "loss": 3.4311, + "step": 1769984 + }, + { + "epoch": 1.0, + "learning_rate": 2.1014168975532035e-05, + "loss": 3.439, + "step": 1770496 + }, + { + "epoch": 1.01, + "learning_rate": 2.1005783028021515e-05, + "loss": 3.4386, + "step": 1771008 + }, + { + "epoch": 1.01, + "learning_rate": 2.0997397080510995e-05, + "loss": 3.4395, + "step": 1771520 + }, + { + "epoch": 1.01, + "learning_rate": 2.0989027511804204e-05, + "loss": 3.4438, + "step": 1772032 + }, + { + "epoch": 1.01, + "learning_rate": 2.0980641564293684e-05, + "loss": 3.447, + "step": 1772544 + }, + { + "epoch": 1.01, + "learning_rate": 2.0972255616783164e-05, + "loss": 3.4293, + "step": 1773056 + }, + { + "epoch": 1.01, + "learning_rate": 2.0963886048076376e-05, + "loss": 3.4404, + "step": 1773568 + }, + { + "epoch": 1.01, + "learning_rate": 2.0955500100565856e-05, + "loss": 3.4403, + "step": 1774080 + }, + { + "epoch": 1.01, + "learning_rate": 2.0947114153055336e-05, + "loss": 3.4315, + "step": 1774592 + }, + { + "epoch": 1.01, + "learning_rate": 2.0938728205544816e-05, + "loss": 3.4274, + "step": 1775104 + }, + { + "epoch": 1.01, + "learning_rate": 2.0930358636838025e-05, + "loss": 3.4307, + "step": 1775616 + }, + { + "epoch": 1.01, + "learning_rate": 2.092198906813124e-05, + "loss": 3.4366, + "step": 1776128 + }, + { + "epoch": 1.01, + "learning_rate": 2.0913603120620718e-05, + "loss": 3.4436, + "step": 1776640 + }, + { + "epoch": 1.01, + "learning_rate": 2.0905217173110198e-05, + "loss": 3.4318, + "step": 1777152 + }, + { + "epoch": 1.01, + "learning_rate": 2.0896831225599678e-05, + "loss": 3.4317, + "step": 1777664 + }, + { + "epoch": 1.01, + "learning_rate": 2.0888445278089158e-05, + "loss": 3.4502, + "step": 1778176 + }, + { + "epoch": 1.01, + "learning_rate": 2.0880059330578638e-05, + "loss": 3.4385, + "step": 1778688 + }, + { + "epoch": 1.01, + "learning_rate": 2.0871673383068118e-05, + "loss": 3.4431, + "step": 1779200 + }, + { + "epoch": 1.01, + "learning_rate": 2.086330381436133e-05, + "loss": 3.4292, + "step": 1779712 + }, + { + "epoch": 1.01, + "learning_rate": 2.085491786685081e-05, + "loss": 3.4181, + "step": 1780224 + }, + { + "epoch": 1.01, + "learning_rate": 2.084654829814402e-05, + "loss": 3.4478, + "step": 1780736 + }, + { + "epoch": 1.01, + "learning_rate": 2.08381623506335e-05, + "loss": 3.4323, + "step": 1781248 + }, + { + "epoch": 1.01, + "learning_rate": 2.082977640312298e-05, + "loss": 3.4319, + "step": 1781760 + }, + { + "epoch": 1.01, + "learning_rate": 2.082139045561246e-05, + "loss": 3.4378, + "step": 1782272 + }, + { + "epoch": 1.01, + "learning_rate": 2.0813004508101942e-05, + "loss": 3.4331, + "step": 1782784 + }, + { + "epoch": 1.01, + "learning_rate": 2.0804618560591422e-05, + "loss": 3.4183, + "step": 1783296 + }, + { + "epoch": 1.01, + "learning_rate": 2.079624899188463e-05, + "loss": 3.4287, + "step": 1783808 + }, + { + "epoch": 1.01, + "learning_rate": 2.078786304437411e-05, + "loss": 3.4334, + "step": 1784320 + }, + { + "epoch": 1.01, + "learning_rate": 2.077947709686359e-05, + "loss": 3.4322, + "step": 1784832 + }, + { + "epoch": 1.01, + "learning_rate": 2.077109114935307e-05, + "loss": 3.4437, + "step": 1785344 + }, + { + "epoch": 1.01, + "learning_rate": 2.076270520184255e-05, + "loss": 3.4311, + "step": 1785856 + }, + { + "epoch": 1.01, + "learning_rate": 2.075431925433203e-05, + "loss": 3.4292, + "step": 1786368 + }, + { + "epoch": 1.01, + "learning_rate": 2.074593330682151e-05, + "loss": 3.4418, + "step": 1786880 + }, + { + "epoch": 1.01, + "learning_rate": 2.073754735931099e-05, + "loss": 3.4267, + "step": 1787392 + }, + { + "epoch": 1.01, + "learning_rate": 2.07291777906042e-05, + "loss": 3.4277, + "step": 1787904 + }, + { + "epoch": 1.01, + "learning_rate": 2.072079184309368e-05, + "loss": 3.4296, + "step": 1788416 + }, + { + "epoch": 1.01, + "learning_rate": 2.071240589558316e-05, + "loss": 3.4293, + "step": 1788928 + }, + { + "epoch": 1.01, + "learning_rate": 2.0704036326876373e-05, + "loss": 3.4275, + "step": 1789440 + }, + { + "epoch": 1.01, + "learning_rate": 2.0695650379365853e-05, + "loss": 3.4266, + "step": 1789952 + }, + { + "epoch": 1.01, + "learning_rate": 2.0687264431855333e-05, + "loss": 3.4185, + "step": 1790464 + }, + { + "epoch": 1.01, + "learning_rate": 2.0678878484344813e-05, + "loss": 3.4238, + "step": 1790976 + }, + { + "epoch": 1.01, + "learning_rate": 2.0670492536834292e-05, + "loss": 3.4457, + "step": 1791488 + }, + { + "epoch": 1.01, + "learning_rate": 2.0662106589323772e-05, + "loss": 3.4294, + "step": 1792000 + }, + { + "epoch": 1.01, + "learning_rate": 2.0653720641813252e-05, + "loss": 3.449, + "step": 1792512 + }, + { + "epoch": 1.01, + "learning_rate": 2.0645334694302732e-05, + "loss": 3.4352, + "step": 1793024 + }, + { + "epoch": 1.01, + "learning_rate": 2.0636965125595945e-05, + "loss": 3.4403, + "step": 1793536 + }, + { + "epoch": 1.01, + "learning_rate": 2.0628579178085425e-05, + "loss": 3.4279, + "step": 1794048 + }, + { + "epoch": 1.01, + "learning_rate": 2.06201932305749e-05, + "loss": 3.4443, + "step": 1794560 + }, + { + "epoch": 1.01, + "learning_rate": 2.061180728306438e-05, + "loss": 3.4352, + "step": 1795072 + }, + { + "epoch": 1.01, + "learning_rate": 2.0603454093161326e-05, + "loss": 3.4298, + "step": 1795584 + }, + { + "epoch": 1.01, + "learning_rate": 2.0595068145650806e-05, + "loss": 3.4459, + "step": 1796096 + }, + { + "epoch": 1.01, + "learning_rate": 2.0586682198140286e-05, + "loss": 3.4344, + "step": 1796608 + }, + { + "epoch": 1.01, + "learning_rate": 2.0578296250629766e-05, + "loss": 3.4389, + "step": 1797120 + }, + { + "epoch": 1.01, + "learning_rate": 2.0569910303119246e-05, + "loss": 3.4383, + "step": 1797632 + }, + { + "epoch": 1.01, + "learning_rate": 2.0561524355608726e-05, + "loss": 3.4146, + "step": 1798144 + }, + { + "epoch": 1.01, + "learning_rate": 2.0553138408098206e-05, + "loss": 3.4192, + "step": 1798656 + }, + { + "epoch": 1.01, + "learning_rate": 2.0544752460587686e-05, + "loss": 3.4254, + "step": 1799168 + }, + { + "epoch": 1.01, + "learning_rate": 2.05363828918809e-05, + "loss": 3.4364, + "step": 1799680 + }, + { + "epoch": 1.01, + "learning_rate": 2.0527996944370375e-05, + "loss": 3.4325, + "step": 1800192 + }, + { + "epoch": 1.01, + "learning_rate": 2.0519610996859855e-05, + "loss": 3.431, + "step": 1800704 + }, + { + "epoch": 1.02, + "learning_rate": 2.0511225049349335e-05, + "loss": 3.4302, + "step": 1801216 + }, + { + "epoch": 1.02, + "learning_rate": 2.050285548064255e-05, + "loss": 3.427, + "step": 1801728 + }, + { + "epoch": 1.02, + "learning_rate": 2.0494469533132027e-05, + "loss": 3.4288, + "step": 1802240 + }, + { + "epoch": 1.02, + "learning_rate": 2.0486083585621507e-05, + "loss": 3.4269, + "step": 1802752 + }, + { + "epoch": 1.02, + "learning_rate": 2.0477697638110987e-05, + "loss": 3.4469, + "step": 1803264 + }, + { + "epoch": 1.02, + "learning_rate": 2.0469311690600467e-05, + "loss": 3.45, + "step": 1803776 + }, + { + "epoch": 1.02, + "learning_rate": 2.0460925743089947e-05, + "loss": 3.4355, + "step": 1804288 + }, + { + "epoch": 1.02, + "learning_rate": 2.0452539795579427e-05, + "loss": 3.4296, + "step": 1804800 + }, + { + "epoch": 1.02, + "learning_rate": 2.0444153848068907e-05, + "loss": 3.4352, + "step": 1805312 + }, + { + "epoch": 1.02, + "learning_rate": 2.043578427936212e-05, + "loss": 3.4322, + "step": 1805824 + }, + { + "epoch": 1.02, + "learning_rate": 2.04273983318516e-05, + "loss": 3.4419, + "step": 1806336 + }, + { + "epoch": 1.02, + "learning_rate": 2.041901238434108e-05, + "loss": 3.4292, + "step": 1806848 + }, + { + "epoch": 1.02, + "learning_rate": 2.0410626436830556e-05, + "loss": 3.4276, + "step": 1807360 + }, + { + "epoch": 1.02, + "learning_rate": 2.040225686812377e-05, + "loss": 3.4376, + "step": 1807872 + }, + { + "epoch": 1.02, + "learning_rate": 2.0393870920613252e-05, + "loss": 3.437, + "step": 1808384 + }, + { + "epoch": 1.02, + "learning_rate": 2.0385484973102732e-05, + "loss": 3.4224, + "step": 1808896 + }, + { + "epoch": 1.02, + "learning_rate": 2.037709902559221e-05, + "loss": 3.4337, + "step": 1809408 + }, + { + "epoch": 1.02, + "learning_rate": 2.036872945688542e-05, + "loss": 3.4276, + "step": 1809920 + }, + { + "epoch": 1.02, + "learning_rate": 2.03603435093749e-05, + "loss": 3.4237, + "step": 1810432 + }, + { + "epoch": 1.02, + "learning_rate": 2.035195756186438e-05, + "loss": 3.4189, + "step": 1810944 + }, + { + "epoch": 1.02, + "learning_rate": 2.034357161435386e-05, + "loss": 3.4307, + "step": 1811456 + }, + { + "epoch": 1.02, + "learning_rate": 2.0335202045647073e-05, + "loss": 3.4326, + "step": 1811968 + }, + { + "epoch": 1.02, + "learning_rate": 2.0326816098136553e-05, + "loss": 3.4236, + "step": 1812480 + }, + { + "epoch": 1.02, + "learning_rate": 2.031843015062603e-05, + "loss": 3.433, + "step": 1812992 + }, + { + "epoch": 1.02, + "learning_rate": 2.031004420311551e-05, + "loss": 3.4267, + "step": 1813504 + }, + { + "epoch": 1.02, + "learning_rate": 2.0301691013212455e-05, + "loss": 3.4411, + "step": 1814016 + }, + { + "epoch": 1.02, + "learning_rate": 2.0293305065701935e-05, + "loss": 3.444, + "step": 1814528 + }, + { + "epoch": 1.02, + "learning_rate": 2.0284919118191415e-05, + "loss": 3.4384, + "step": 1815040 + }, + { + "epoch": 1.02, + "learning_rate": 2.0276533170680895e-05, + "loss": 3.4363, + "step": 1815552 + }, + { + "epoch": 1.02, + "learning_rate": 2.0268147223170375e-05, + "loss": 3.4243, + "step": 1816064 + }, + { + "epoch": 1.02, + "learning_rate": 2.0259777654463584e-05, + "loss": 3.4326, + "step": 1816576 + }, + { + "epoch": 1.02, + "learning_rate": 2.0251391706953067e-05, + "loss": 3.4196, + "step": 1817088 + }, + { + "epoch": 1.02, + "learning_rate": 2.0243005759442547e-05, + "loss": 3.4272, + "step": 1817600 + }, + { + "epoch": 1.02, + "learning_rate": 2.0234619811932027e-05, + "loss": 3.433, + "step": 1818112 + }, + { + "epoch": 1.02, + "learning_rate": 2.0226233864421504e-05, + "loss": 3.4283, + "step": 1818624 + }, + { + "epoch": 1.02, + "learning_rate": 2.0217847916910983e-05, + "loss": 3.4296, + "step": 1819136 + }, + { + "epoch": 1.02, + "learning_rate": 2.0209478348204196e-05, + "loss": 3.433, + "step": 1819648 + }, + { + "epoch": 1.02, + "learning_rate": 2.0201092400693676e-05, + "loss": 3.4377, + "step": 1820160 + }, + { + "epoch": 1.02, + "learning_rate": 2.0192706453183156e-05, + "loss": 3.428, + "step": 1820672 + }, + { + "epoch": 1.02, + "learning_rate": 2.0184320505672636e-05, + "loss": 3.4311, + "step": 1821184 + }, + { + "epoch": 1.02, + "learning_rate": 2.0175934558162116e-05, + "loss": 3.4329, + "step": 1821696 + }, + { + "epoch": 1.02, + "learning_rate": 2.0167548610651596e-05, + "loss": 3.4401, + "step": 1822208 + }, + { + "epoch": 1.02, + "learning_rate": 2.0159162663141076e-05, + "loss": 3.4425, + "step": 1822720 + }, + { + "epoch": 1.02, + "learning_rate": 2.0150776715630556e-05, + "loss": 3.4314, + "step": 1823232 + }, + { + "epoch": 1.02, + "learning_rate": 2.0142407146923768e-05, + "loss": 3.4385, + "step": 1823744 + }, + { + "epoch": 1.02, + "learning_rate": 2.0134021199413248e-05, + "loss": 3.4308, + "step": 1824256 + }, + { + "epoch": 1.02, + "learning_rate": 2.0125635251902728e-05, + "loss": 3.4384, + "step": 1824768 + }, + { + "epoch": 1.02, + "learning_rate": 2.0117249304392208e-05, + "loss": 3.4313, + "step": 1825280 + }, + { + "epoch": 1.02, + "learning_rate": 2.0108879735685417e-05, + "loss": 3.4351, + "step": 1825792 + }, + { + "epoch": 1.02, + "learning_rate": 2.0100493788174897e-05, + "loss": 3.428, + "step": 1826304 + }, + { + "epoch": 1.02, + "learning_rate": 2.0092107840664377e-05, + "loss": 3.4394, + "step": 1826816 + }, + { + "epoch": 1.02, + "learning_rate": 2.008373827195759e-05, + "loss": 3.4247, + "step": 1827328 + }, + { + "epoch": 1.02, + "learning_rate": 2.00753687032508e-05, + "loss": 3.4343, + "step": 1827840 + }, + { + "epoch": 1.02, + "learning_rate": 2.006698275574028e-05, + "loss": 3.4365, + "step": 1828352 + }, + { + "epoch": 1.02, + "learning_rate": 2.005859680822976e-05, + "loss": 3.4339, + "step": 1828864 + }, + { + "epoch": 1.02, + "learning_rate": 2.0050210860719242e-05, + "loss": 3.4332, + "step": 1829376 + }, + { + "epoch": 1.02, + "learning_rate": 2.0041824913208722e-05, + "loss": 3.4346, + "step": 1829888 + }, + { + "epoch": 1.02, + "learning_rate": 2.0033438965698202e-05, + "loss": 3.4403, + "step": 1830400 + }, + { + "epoch": 1.02, + "learning_rate": 2.0025053018187682e-05, + "loss": 3.4199, + "step": 1830912 + }, + { + "epoch": 1.02, + "learning_rate": 2.001668344948089e-05, + "loss": 3.4375, + "step": 1831424 + }, + { + "epoch": 1.03, + "eval_loss": 3.846804141998291, + "eval_runtime": 303.3771, + "eval_samples_per_second": 1257.811, + "eval_steps_per_second": 39.308, + "step": 1831671 + }, + { + "epoch": 0.0, + "learning_rate": 2.000829750197037e-05, + "loss": 3.4236, + "step": 1831936 + }, + { + "epoch": 0.0, + "learning_rate": 1.999991155445985e-05, + "loss": 3.4261, + "step": 1832448 + }, + { + "epoch": 0.0, + "learning_rate": 1.9991541985753063e-05, + "loss": 3.4339, + "step": 1832960 + }, + { + "epoch": 0.0, + "learning_rate": 1.9983156038242543e-05, + "loss": 3.4335, + "step": 1833472 + }, + { + "epoch": 0.0, + "learning_rate": 1.9974770090732023e-05, + "loss": 3.4398, + "step": 1833984 + }, + { + "epoch": 0.0, + "learning_rate": 1.9966384143221503e-05, + "loss": 3.4279, + "step": 1834496 + }, + { + "epoch": 0.0, + "learning_rate": 1.995799819571098e-05, + "loss": 3.43, + "step": 1835008 + }, + { + "epoch": 0.0, + "learning_rate": 1.994961224820046e-05, + "loss": 3.428, + "step": 1835520 + }, + { + "epoch": 0.0, + "learning_rate": 1.9941226300689943e-05, + "loss": 3.4256, + "step": 1836032 + }, + { + "epoch": 0.0, + "learning_rate": 1.9932840353179423e-05, + "loss": 3.4257, + "step": 1836544 + }, + { + "epoch": 0.0, + "learning_rate": 1.9924470784472632e-05, + "loss": 3.4377, + "step": 1837056 + }, + { + "epoch": 0.0, + "learning_rate": 1.9916084836962112e-05, + "loss": 3.4361, + "step": 1837568 + }, + { + "epoch": 0.0, + "learning_rate": 1.9907715268255324e-05, + "loss": 3.4252, + "step": 1838080 + }, + { + "epoch": 0.0, + "learning_rate": 1.9899329320744804e-05, + "loss": 3.4173, + "step": 1838592 + }, + { + "epoch": 0.0, + "learning_rate": 1.9890943373234284e-05, + "loss": 3.4314, + "step": 1839104 + }, + { + "epoch": 0.0, + "learning_rate": 1.9882557425723764e-05, + "loss": 3.4132, + "step": 1839616 + }, + { + "epoch": 0.0, + "learning_rate": 1.9874171478213244e-05, + "loss": 3.4255, + "step": 1840128 + }, + { + "epoch": 0.0, + "learning_rate": 1.9865785530702724e-05, + "loss": 3.4264, + "step": 1840640 + }, + { + "epoch": 0.0, + "learning_rate": 1.9857399583192204e-05, + "loss": 3.4292, + "step": 1841152 + }, + { + "epoch": 0.0, + "learning_rate": 1.9849013635681684e-05, + "loss": 3.4337, + "step": 1841664 + }, + { + "epoch": 0.0, + "learning_rate": 1.9840644066974897e-05, + "loss": 3.4394, + "step": 1842176 + }, + { + "epoch": 0.0, + "learning_rate": 1.9832258119464377e-05, + "loss": 3.4289, + "step": 1842688 + }, + { + "epoch": 0.0, + "learning_rate": 1.9823872171953857e-05, + "loss": 3.4245, + "step": 1843200 + }, + { + "epoch": 0.0, + "learning_rate": 1.9815486224443336e-05, + "loss": 3.4262, + "step": 1843712 + }, + { + "epoch": 0.0, + "learning_rate": 1.9807116655736546e-05, + "loss": 3.4262, + "step": 1844224 + }, + { + "epoch": 0.0, + "learning_rate": 1.9798730708226026e-05, + "loss": 3.4353, + "step": 1844736 + }, + { + "epoch": 0.0, + "learning_rate": 1.9790344760715505e-05, + "loss": 3.4218, + "step": 1845248 + }, + { + "epoch": 0.0, + "learning_rate": 1.9781958813204985e-05, + "loss": 3.4229, + "step": 1845760 + }, + { + "epoch": 0.0, + "learning_rate": 1.9773589244498198e-05, + "loss": 3.4263, + "step": 1846272 + }, + { + "epoch": 0.0, + "learning_rate": 1.9765203296987678e-05, + "loss": 3.4236, + "step": 1846784 + }, + { + "epoch": 0.01, + "learning_rate": 1.9756817349477158e-05, + "loss": 3.4258, + "step": 1847296 + }, + { + "epoch": 0.01, + "learning_rate": 1.9748431401966634e-05, + "loss": 3.4326, + "step": 1847808 + }, + { + "epoch": 0.01, + "learning_rate": 1.9740045454456114e-05, + "loss": 3.4351, + "step": 1848320 + }, + { + "epoch": 0.01, + "learning_rate": 1.9731659506945598e-05, + "loss": 3.4308, + "step": 1848832 + }, + { + "epoch": 0.01, + "learning_rate": 1.9723273559435078e-05, + "loss": 3.4193, + "step": 1849344 + }, + { + "epoch": 0.01, + "learning_rate": 1.9714903990728287e-05, + "loss": 3.4326, + "step": 1849856 + }, + { + "epoch": 0.01, + "learning_rate": 1.9706518043217767e-05, + "loss": 3.428, + "step": 1850368 + }, + { + "epoch": 0.01, + "learning_rate": 1.9698132095707247e-05, + "loss": 3.423, + "step": 1850880 + }, + { + "epoch": 0.01, + "learning_rate": 1.9689746148196727e-05, + "loss": 3.4156, + "step": 1851392 + }, + { + "epoch": 0.01, + "learning_rate": 1.968137657948994e-05, + "loss": 3.4197, + "step": 1851904 + }, + { + "epoch": 0.01, + "learning_rate": 1.967300701078315e-05, + "loss": 3.4225, + "step": 1852416 + }, + { + "epoch": 0.01, + "learning_rate": 1.966462106327263e-05, + "loss": 3.4346, + "step": 1852928 + }, + { + "epoch": 0.01, + "learning_rate": 1.9656235115762108e-05, + "loss": 3.422, + "step": 1853440 + }, + { + "epoch": 0.01, + "learning_rate": 1.9647849168251588e-05, + "loss": 3.4214, + "step": 1853952 + }, + { + "epoch": 0.01, + "learning_rate": 1.9639463220741068e-05, + "loss": 3.4362, + "step": 1854464 + }, + { + "epoch": 0.01, + "learning_rate": 1.963107727323055e-05, + "loss": 3.4277, + "step": 1854976 + }, + { + "epoch": 0.01, + "learning_rate": 1.962269132572003e-05, + "loss": 3.4356, + "step": 1855488 + }, + { + "epoch": 0.01, + "learning_rate": 1.961432175701324e-05, + "loss": 3.4199, + "step": 1856000 + }, + { + "epoch": 0.01, + "learning_rate": 1.960593580950272e-05, + "loss": 3.4026, + "step": 1856512 + }, + { + "epoch": 0.01, + "learning_rate": 1.95975498619922e-05, + "loss": 3.4403, + "step": 1857024 + }, + { + "epoch": 0.01, + "learning_rate": 1.958916391448168e-05, + "loss": 3.4254, + "step": 1857536 + }, + { + "epoch": 0.01, + "learning_rate": 1.9580794345774893e-05, + "loss": 3.4234, + "step": 1858048 + }, + { + "epoch": 0.01, + "learning_rate": 1.9572408398264373e-05, + "loss": 3.4252, + "step": 1858560 + }, + { + "epoch": 0.01, + "learning_rate": 1.9564038829557582e-05, + "loss": 3.422, + "step": 1859072 + }, + { + "epoch": 0.01, + "learning_rate": 1.9555652882047062e-05, + "loss": 3.4083, + "step": 1859584 + }, + { + "epoch": 0.01, + "learning_rate": 1.9547266934536542e-05, + "loss": 3.4177, + "step": 1860096 + }, + { + "epoch": 0.01, + "learning_rate": 1.953888098702602e-05, + "loss": 3.421, + "step": 1860608 + }, + { + "epoch": 0.01, + "learning_rate": 1.9530495039515505e-05, + "loss": 3.4201, + "step": 1861120 + }, + { + "epoch": 0.01, + "learning_rate": 1.9522109092004985e-05, + "loss": 3.4323, + "step": 1861632 + }, + { + "epoch": 0.01, + "learning_rate": 1.951372314449446e-05, + "loss": 3.4192, + "step": 1862144 + }, + { + "epoch": 0.01, + "learning_rate": 1.950533719698394e-05, + "loss": 3.4184, + "step": 1862656 + }, + { + "epoch": 0.01, + "learning_rate": 1.9496967628277154e-05, + "loss": 3.4326, + "step": 1863168 + }, + { + "epoch": 0.01, + "learning_rate": 1.9488581680766634e-05, + "loss": 3.4115, + "step": 1863680 + }, + { + "epoch": 0.01, + "learning_rate": 1.9480195733256114e-05, + "loss": 3.4153, + "step": 1864192 + }, + { + "epoch": 0.01, + "learning_rate": 1.9471809785745594e-05, + "loss": 3.417, + "step": 1864704 + }, + { + "epoch": 0.01, + "learning_rate": 1.9463440217038806e-05, + "loss": 3.4221, + "step": 1865216 + }, + { + "epoch": 0.01, + "learning_rate": 1.9455070648332015e-05, + "loss": 3.418, + "step": 1865728 + }, + { + "epoch": 0.01, + "learning_rate": 1.9446684700821495e-05, + "loss": 3.4199, + "step": 1866240 + }, + { + "epoch": 0.01, + "learning_rate": 1.9438298753310975e-05, + "loss": 3.4045, + "step": 1866752 + }, + { + "epoch": 0.01, + "learning_rate": 1.942991280580046e-05, + "loss": 3.4167, + "step": 1867264 + }, + { + "epoch": 0.01, + "learning_rate": 1.9421526858289935e-05, + "loss": 3.4297, + "step": 1867776 + }, + { + "epoch": 0.01, + "learning_rate": 1.9413140910779415e-05, + "loss": 3.42, + "step": 1868288 + }, + { + "epoch": 0.01, + "learning_rate": 1.9404754963268895e-05, + "loss": 3.4346, + "step": 1868800 + }, + { + "epoch": 0.01, + "learning_rate": 1.9396369015758375e-05, + "loss": 3.4253, + "step": 1869312 + }, + { + "epoch": 0.01, + "learning_rate": 1.9387999447051584e-05, + "loss": 3.435, + "step": 1869824 + }, + { + "epoch": 0.01, + "learning_rate": 1.9379613499541068e-05, + "loss": 3.417, + "step": 1870336 + }, + { + "epoch": 0.01, + "learning_rate": 1.9371227552030548e-05, + "loss": 3.4302, + "step": 1870848 + }, + { + "epoch": 0.01, + "learning_rate": 1.9362841604520027e-05, + "loss": 3.4252, + "step": 1871360 + }, + { + "epoch": 0.01, + "learning_rate": 1.9354472035813237e-05, + "loss": 3.4167, + "step": 1871872 + }, + { + "epoch": 0.01, + "learning_rate": 1.934610246710645e-05, + "loss": 3.4354, + "step": 1872384 + }, + { + "epoch": 0.01, + "learning_rate": 1.933771651959593e-05, + "loss": 3.4221, + "step": 1872896 + }, + { + "epoch": 0.01, + "learning_rate": 1.932933057208541e-05, + "loss": 3.4283, + "step": 1873408 + }, + { + "epoch": 0.01, + "learning_rate": 1.932094462457489e-05, + "loss": 3.4249, + "step": 1873920 + }, + { + "epoch": 0.01, + "learning_rate": 1.931255867706437e-05, + "loss": 3.4029, + "step": 1874432 + }, + { + "epoch": 0.01, + "learning_rate": 1.930417272955385e-05, + "loss": 3.4102, + "step": 1874944 + }, + { + "epoch": 0.01, + "learning_rate": 1.929578678204333e-05, + "loss": 3.4175, + "step": 1875456 + }, + { + "epoch": 0.01, + "learning_rate": 1.9287417213336538e-05, + "loss": 3.4257, + "step": 1875968 + }, + { + "epoch": 0.01, + "learning_rate": 1.927903126582602e-05, + "loss": 3.4212, + "step": 1876480 + }, + { + "epoch": 0.01, + "learning_rate": 1.92706453183155e-05, + "loss": 3.4159, + "step": 1876992 + }, + { + "epoch": 0.02, + "learning_rate": 1.926225937080498e-05, + "loss": 3.4195, + "step": 1877504 + }, + { + "epoch": 0.02, + "learning_rate": 1.925388980209819e-05, + "loss": 3.4199, + "step": 1878016 + }, + { + "epoch": 0.02, + "learning_rate": 1.924550385458767e-05, + "loss": 3.4188, + "step": 1878528 + }, + { + "epoch": 0.02, + "learning_rate": 1.923711790707715e-05, + "loss": 3.4147, + "step": 1879040 + }, + { + "epoch": 0.02, + "learning_rate": 1.922873195956663e-05, + "loss": 3.4377, + "step": 1879552 + }, + { + "epoch": 0.02, + "learning_rate": 1.9220346012056113e-05, + "loss": 3.4352, + "step": 1880064 + }, + { + "epoch": 0.02, + "learning_rate": 1.921196006454559e-05, + "loss": 3.4262, + "step": 1880576 + }, + { + "epoch": 0.02, + "learning_rate": 1.920357411703507e-05, + "loss": 3.4146, + "step": 1881088 + }, + { + "epoch": 0.02, + "learning_rate": 1.919518816952455e-05, + "loss": 3.425, + "step": 1881600 + }, + { + "epoch": 0.02, + "learning_rate": 1.9186818600817762e-05, + "loss": 3.4215, + "step": 1882112 + }, + { + "epoch": 0.02, + "learning_rate": 1.917843265330724e-05, + "loss": 3.4319, + "step": 1882624 + }, + { + "epoch": 0.02, + "learning_rate": 1.9170046705796722e-05, + "loss": 3.4206, + "step": 1883136 + }, + { + "epoch": 0.02, + "learning_rate": 1.9161660758286202e-05, + "loss": 3.4177, + "step": 1883648 + }, + { + "epoch": 0.02, + "learning_rate": 1.9153291189579415e-05, + "loss": 3.4247, + "step": 1884160 + }, + { + "epoch": 0.02, + "learning_rate": 1.914490524206889e-05, + "loss": 3.4278, + "step": 1884672 + }, + { + "epoch": 0.02, + "learning_rate": 1.913651929455837e-05, + "loss": 3.4144, + "step": 1885184 + }, + { + "epoch": 0.02, + "learning_rate": 1.912813334704785e-05, + "loss": 3.4218, + "step": 1885696 + }, + { + "epoch": 0.02, + "learning_rate": 1.9119763778341064e-05, + "loss": 3.4161, + "step": 1886208 + }, + { + "epoch": 0.02, + "learning_rate": 1.9111377830830544e-05, + "loss": 3.417, + "step": 1886720 + }, + { + "epoch": 0.02, + "learning_rate": 1.9103008262123756e-05, + "loss": 3.4095, + "step": 1887232 + }, + { + "epoch": 0.02, + "learning_rate": 1.9094622314613236e-05, + "loss": 3.4176, + "step": 1887744 + }, + { + "epoch": 0.02, + "learning_rate": 1.9086236367102713e-05, + "loss": 3.4209, + "step": 1888256 + }, + { + "epoch": 0.02, + "learning_rate": 1.9077850419592193e-05, + "loss": 3.419, + "step": 1888768 + }, + { + "epoch": 0.02, + "learning_rate": 1.9069464472081676e-05, + "loss": 3.423, + "step": 1889280 + }, + { + "epoch": 0.02, + "learning_rate": 1.9061078524571156e-05, + "loss": 3.414, + "step": 1889792 + }, + { + "epoch": 0.02, + "learning_rate": 1.9052708955864365e-05, + "loss": 3.4279, + "step": 1890304 + }, + { + "epoch": 0.02, + "learning_rate": 1.9044323008353845e-05, + "loss": 3.4369, + "step": 1890816 + }, + { + "epoch": 0.02, + "learning_rate": 1.9035937060843325e-05, + "loss": 3.428, + "step": 1891328 + }, + { + "epoch": 0.02, + "learning_rate": 1.9027551113332805e-05, + "loss": 3.4298, + "step": 1891840 + }, + { + "epoch": 0.02, + "learning_rate": 1.9019165165822285e-05, + "loss": 3.4113, + "step": 1892352 + }, + { + "epoch": 0.02, + "learning_rate": 1.9010795597115497e-05, + "loss": 3.4237, + "step": 1892864 + }, + { + "epoch": 0.02, + "learning_rate": 1.9002409649604977e-05, + "loss": 3.4148, + "step": 1893376 + }, + { + "epoch": 0.02, + "learning_rate": 1.8994023702094457e-05, + "loss": 3.415, + "step": 1893888 + }, + { + "epoch": 0.02, + "learning_rate": 1.8985637754583937e-05, + "loss": 3.4178, + "step": 1894400 + }, + { + "epoch": 0.02, + "learning_rate": 1.8977251807073417e-05, + "loss": 3.4166, + "step": 1894912 + }, + { + "epoch": 0.02, + "learning_rate": 1.8968865859562894e-05, + "loss": 3.4222, + "step": 1895424 + }, + { + "epoch": 0.02, + "learning_rate": 1.896049629085611e-05, + "loss": 3.4206, + "step": 1895936 + }, + { + "epoch": 0.02, + "learning_rate": 1.895211034334559e-05, + "loss": 3.4253, + "step": 1896448 + }, + { + "epoch": 0.02, + "learning_rate": 1.8943724395835066e-05, + "loss": 3.419, + "step": 1896960 + }, + { + "epoch": 0.02, + "learning_rate": 1.8935338448324546e-05, + "loss": 3.4178, + "step": 1897472 + }, + { + "epoch": 0.02, + "learning_rate": 1.8926952500814026e-05, + "loss": 3.4238, + "step": 1897984 + }, + { + "epoch": 0.02, + "learning_rate": 1.8918566553303506e-05, + "loss": 3.4265, + "step": 1898496 + }, + { + "epoch": 0.02, + "learning_rate": 1.8910180605792986e-05, + "loss": 3.4367, + "step": 1899008 + }, + { + "epoch": 0.02, + "learning_rate": 1.890179465828247e-05, + "loss": 3.4161, + "step": 1899520 + }, + { + "epoch": 0.02, + "learning_rate": 1.889342508957568e-05, + "loss": 3.431, + "step": 1900032 + }, + { + "epoch": 0.02, + "learning_rate": 1.888503914206516e-05, + "loss": 3.4206, + "step": 1900544 + }, + { + "epoch": 0.02, + "learning_rate": 1.887665319455464e-05, + "loss": 3.4269, + "step": 1901056 + }, + { + "epoch": 0.02, + "learning_rate": 1.8868267247044118e-05, + "loss": 3.4254, + "step": 1901568 + }, + { + "epoch": 0.02, + "learning_rate": 1.885989767833733e-05, + "loss": 3.423, + "step": 1902080 + }, + { + "epoch": 0.02, + "learning_rate": 1.885151173082681e-05, + "loss": 3.4133, + "step": 1902592 + }, + { + "epoch": 0.02, + "learning_rate": 1.884312578331629e-05, + "loss": 3.4327, + "step": 1903104 + }, + { + "epoch": 0.02, + "learning_rate": 1.883473983580577e-05, + "loss": 3.4156, + "step": 1903616 + }, + { + "epoch": 0.02, + "learning_rate": 1.8826386645902712e-05, + "loss": 3.4221, + "step": 1904128 + }, + { + "epoch": 0.02, + "learning_rate": 1.8818000698392192e-05, + "loss": 3.4266, + "step": 1904640 + }, + { + "epoch": 0.02, + "learning_rate": 1.8809614750881672e-05, + "loss": 3.4272, + "step": 1905152 + }, + { + "epoch": 0.02, + "learning_rate": 1.8801228803371152e-05, + "loss": 3.4179, + "step": 1905664 + }, + { + "epoch": 0.02, + "learning_rate": 1.8792842855860632e-05, + "loss": 3.4223, + "step": 1906176 + }, + { + "epoch": 0.02, + "learning_rate": 1.8784456908350112e-05, + "loss": 3.429, + "step": 1906688 + }, + { + "epoch": 0.02, + "learning_rate": 1.8776070960839592e-05, + "loss": 3.416, + "step": 1907200 + }, + { + "epoch": 0.02, + "learning_rate": 1.8767685013329072e-05, + "loss": 3.4228, + "step": 1907712 + }, + { + "epoch": 0.03, + "eval_loss": 3.8501827716827393, + "eval_runtime": 304.7949, + "eval_samples_per_second": 1251.96, + "eval_steps_per_second": 39.125, + "step": 1907991 + }, + { + "epoch": 1.0, + "learning_rate": 1.8759315444622284e-05, + "loss": 3.414, + "step": 1908224 + }, + { + "epoch": 1.0, + "learning_rate": 1.8750929497111764e-05, + "loss": 3.4179, + "step": 1908736 + }, + { + "epoch": 1.0, + "learning_rate": 1.8742543549601244e-05, + "loss": 3.4226, + "step": 1909248 + }, + { + "epoch": 1.0, + "learning_rate": 1.8734173980894453e-05, + "loss": 3.4234, + "step": 1909760 + }, + { + "epoch": 1.0, + "learning_rate": 1.8725788033383933e-05, + "loss": 3.4294, + "step": 1910272 + }, + { + "epoch": 1.0, + "learning_rate": 1.8717402085873413e-05, + "loss": 3.4149, + "step": 1910784 + }, + { + "epoch": 1.0, + "learning_rate": 1.8709016138362893e-05, + "loss": 3.4229, + "step": 1911296 + }, + { + "epoch": 1.0, + "learning_rate": 1.8700630190852373e-05, + "loss": 3.4176, + "step": 1911808 + }, + { + "epoch": 1.0, + "learning_rate": 1.8692244243341853e-05, + "loss": 3.4138, + "step": 1912320 + }, + { + "epoch": 1.0, + "learning_rate": 1.8683858295831333e-05, + "loss": 3.417, + "step": 1912832 + }, + { + "epoch": 1.0, + "learning_rate": 1.8675488727124546e-05, + "loss": 3.426, + "step": 1913344 + }, + { + "epoch": 1.0, + "learning_rate": 1.8667102779614022e-05, + "loss": 3.4212, + "step": 1913856 + }, + { + "epoch": 1.0, + "learning_rate": 1.8658733210907238e-05, + "loss": 3.4227, + "step": 1914368 + }, + { + "epoch": 1.0, + "learning_rate": 1.8650347263396718e-05, + "loss": 3.4016, + "step": 1914880 + }, + { + "epoch": 1.0, + "learning_rate": 1.8641961315886195e-05, + "loss": 3.4215, + "step": 1915392 + }, + { + "epoch": 1.0, + "learning_rate": 1.8633575368375675e-05, + "loss": 3.4057, + "step": 1915904 + }, + { + "epoch": 1.0, + "learning_rate": 1.8625189420865155e-05, + "loss": 3.4173, + "step": 1916416 + }, + { + "epoch": 1.0, + "learning_rate": 1.8616803473354634e-05, + "loss": 3.4174, + "step": 1916928 + }, + { + "epoch": 1.0, + "learning_rate": 1.8608417525844114e-05, + "loss": 3.4165, + "step": 1917440 + }, + { + "epoch": 1.0, + "learning_rate": 1.8600031578333594e-05, + "loss": 3.4243, + "step": 1917952 + }, + { + "epoch": 1.0, + "learning_rate": 1.8591662009626807e-05, + "loss": 3.43, + "step": 1918464 + }, + { + "epoch": 1.0, + "learning_rate": 1.8583276062116287e-05, + "loss": 3.4208, + "step": 1918976 + }, + { + "epoch": 1.0, + "learning_rate": 1.8574890114605767e-05, + "loss": 3.4142, + "step": 1919488 + }, + { + "epoch": 1.0, + "learning_rate": 1.8566504167095247e-05, + "loss": 3.4118, + "step": 1920000 + }, + { + "epoch": 1.0, + "learning_rate": 1.8558134598388456e-05, + "loss": 3.4212, + "step": 1920512 + }, + { + "epoch": 1.0, + "learning_rate": 1.854974865087794e-05, + "loss": 3.4198, + "step": 1921024 + }, + { + "epoch": 1.0, + "learning_rate": 1.854136270336742e-05, + "loss": 3.4156, + "step": 1921536 + }, + { + "epoch": 1.0, + "learning_rate": 1.85329767558569e-05, + "loss": 3.4153, + "step": 1922048 + }, + { + "epoch": 1.0, + "learning_rate": 1.8524607187150108e-05, + "loss": 3.4123, + "step": 1922560 + }, + { + "epoch": 1.0, + "learning_rate": 1.8516221239639588e-05, + "loss": 3.4168, + "step": 1923072 + }, + { + "epoch": 1.01, + "learning_rate": 1.8507835292129068e-05, + "loss": 3.4085, + "step": 1923584 + }, + { + "epoch": 1.01, + "learning_rate": 1.8499449344618548e-05, + "loss": 3.4243, + "step": 1924096 + }, + { + "epoch": 1.01, + "learning_rate": 1.8491063397108028e-05, + "loss": 3.4222, + "step": 1924608 + }, + { + "epoch": 1.01, + "learning_rate": 1.8482677449597508e-05, + "loss": 3.4217, + "step": 1925120 + }, + { + "epoch": 1.01, + "learning_rate": 1.8474291502086988e-05, + "loss": 3.4119, + "step": 1925632 + }, + { + "epoch": 1.01, + "learning_rate": 1.84659219333802e-05, + "loss": 3.4186, + "step": 1926144 + }, + { + "epoch": 1.01, + "learning_rate": 1.8457535985869677e-05, + "loss": 3.4192, + "step": 1926656 + }, + { + "epoch": 1.01, + "learning_rate": 1.844915003835916e-05, + "loss": 3.4125, + "step": 1927168 + }, + { + "epoch": 1.01, + "learning_rate": 1.844076409084864e-05, + "loss": 3.4093, + "step": 1927680 + }, + { + "epoch": 1.01, + "learning_rate": 1.843239452214185e-05, + "loss": 3.4079, + "step": 1928192 + }, + { + "epoch": 1.01, + "learning_rate": 1.8424024953435062e-05, + "loss": 3.4127, + "step": 1928704 + }, + { + "epoch": 1.01, + "learning_rate": 1.8415639005924542e-05, + "loss": 3.4201, + "step": 1929216 + }, + { + "epoch": 1.01, + "learning_rate": 1.8407253058414022e-05, + "loss": 3.4132, + "step": 1929728 + }, + { + "epoch": 1.01, + "learning_rate": 1.8398867110903502e-05, + "loss": 3.4144, + "step": 1930240 + }, + { + "epoch": 1.01, + "learning_rate": 1.839048116339298e-05, + "loss": 3.4266, + "step": 1930752 + }, + { + "epoch": 1.01, + "learning_rate": 1.838209521588246e-05, + "loss": 3.4167, + "step": 1931264 + }, + { + "epoch": 1.01, + "learning_rate": 1.837370926837194e-05, + "loss": 3.4242, + "step": 1931776 + }, + { + "epoch": 1.01, + "learning_rate": 1.836533969966515e-05, + "loss": 3.4116, + "step": 1932288 + }, + { + "epoch": 1.01, + "learning_rate": 1.835695375215463e-05, + "loss": 3.3927, + "step": 1932800 + }, + { + "epoch": 1.01, + "learning_rate": 1.834856780464411e-05, + "loss": 3.4283, + "step": 1933312 + }, + { + "epoch": 1.01, + "learning_rate": 1.8340181857133594e-05, + "loss": 3.4129, + "step": 1933824 + }, + { + "epoch": 1.01, + "learning_rate": 1.8331812288426803e-05, + "loss": 3.4155, + "step": 1934336 + }, + { + "epoch": 1.01, + "learning_rate": 1.8323426340916283e-05, + "loss": 3.4144, + "step": 1934848 + }, + { + "epoch": 1.01, + "learning_rate": 1.8315056772209495e-05, + "loss": 3.412, + "step": 1935360 + }, + { + "epoch": 1.01, + "learning_rate": 1.8306670824698975e-05, + "loss": 3.3991, + "step": 1935872 + }, + { + "epoch": 1.01, + "learning_rate": 1.8298284877188455e-05, + "loss": 3.4047, + "step": 1936384 + }, + { + "epoch": 1.01, + "learning_rate": 1.8289898929677935e-05, + "loss": 3.4109, + "step": 1936896 + }, + { + "epoch": 1.01, + "learning_rate": 1.8281512982167415e-05, + "loss": 3.4101, + "step": 1937408 + }, + { + "epoch": 1.01, + "learning_rate": 1.8273127034656895e-05, + "loss": 3.4235, + "step": 1937920 + }, + { + "epoch": 1.01, + "learning_rate": 1.8264741087146375e-05, + "loss": 3.4092, + "step": 1938432 + }, + { + "epoch": 1.01, + "learning_rate": 1.8256355139635852e-05, + "loss": 3.4074, + "step": 1938944 + }, + { + "epoch": 1.01, + "learning_rate": 1.8247985570929064e-05, + "loss": 3.4256, + "step": 1939456 + }, + { + "epoch": 1.01, + "learning_rate": 1.8239599623418548e-05, + "loss": 3.3998, + "step": 1939968 + }, + { + "epoch": 1.01, + "learning_rate": 1.8231213675908028e-05, + "loss": 3.3994, + "step": 1940480 + }, + { + "epoch": 1.01, + "learning_rate": 1.8222827728397504e-05, + "loss": 3.4131, + "step": 1940992 + }, + { + "epoch": 1.01, + "learning_rate": 1.8214458159690717e-05, + "loss": 3.4102, + "step": 1941504 + }, + { + "epoch": 1.01, + "learning_rate": 1.8206088590983926e-05, + "loss": 3.4075, + "step": 1942016 + }, + { + "epoch": 1.01, + "learning_rate": 1.819770264347341e-05, + "loss": 3.4082, + "step": 1942528 + }, + { + "epoch": 1.01, + "learning_rate": 1.818931669596289e-05, + "loss": 3.3976, + "step": 1943040 + }, + { + "epoch": 1.01, + "learning_rate": 1.818093074845237e-05, + "loss": 3.4009, + "step": 1943552 + }, + { + "epoch": 1.01, + "learning_rate": 1.817254480094185e-05, + "loss": 3.423, + "step": 1944064 + }, + { + "epoch": 1.01, + "learning_rate": 1.8164158853431325e-05, + "loss": 3.4081, + "step": 1944576 + }, + { + "epoch": 1.01, + "learning_rate": 1.8155772905920805e-05, + "loss": 3.4238, + "step": 1945088 + }, + { + "epoch": 1.01, + "learning_rate": 1.8147386958410285e-05, + "loss": 3.4158, + "step": 1945600 + }, + { + "epoch": 1.01, + "learning_rate": 1.81390173897035e-05, + "loss": 3.4254, + "step": 1946112 + }, + { + "epoch": 1.01, + "learning_rate": 1.8130631442192978e-05, + "loss": 3.4075, + "step": 1946624 + }, + { + "epoch": 1.01, + "learning_rate": 1.8122245494682458e-05, + "loss": 3.4199, + "step": 1947136 + }, + { + "epoch": 1.01, + "learning_rate": 1.8113859547171938e-05, + "loss": 3.4169, + "step": 1947648 + }, + { + "epoch": 1.01, + "learning_rate": 1.810548997846515e-05, + "loss": 3.4051, + "step": 1948160 + }, + { + "epoch": 1.01, + "learning_rate": 1.8097120409758363e-05, + "loss": 3.427, + "step": 1948672 + }, + { + "epoch": 1.01, + "learning_rate": 1.8088734462247843e-05, + "loss": 3.4123, + "step": 1949184 + }, + { + "epoch": 1.01, + "learning_rate": 1.8080348514737323e-05, + "loss": 3.4162, + "step": 1949696 + }, + { + "epoch": 1.01, + "learning_rate": 1.80719625672268e-05, + "loss": 3.4199, + "step": 1950208 + }, + { + "epoch": 1.01, + "learning_rate": 1.806357661971628e-05, + "loss": 3.3982, + "step": 1950720 + }, + { + "epoch": 1.01, + "learning_rate": 1.805519067220576e-05, + "loss": 3.3987, + "step": 1951232 + }, + { + "epoch": 1.01, + "learning_rate": 1.804680472469524e-05, + "loss": 3.4044, + "step": 1951744 + }, + { + "epoch": 1.01, + "learning_rate": 1.803843515598845e-05, + "loss": 3.4149, + "step": 1952256 + }, + { + "epoch": 1.01, + "learning_rate": 1.803004920847793e-05, + "loss": 3.4112, + "step": 1952768 + }, + { + "epoch": 1.01, + "learning_rate": 1.802166326096741e-05, + "loss": 3.4067, + "step": 1953280 + }, + { + "epoch": 1.02, + "learning_rate": 1.801327731345689e-05, + "loss": 3.4102, + "step": 1953792 + }, + { + "epoch": 1.02, + "learning_rate": 1.80049077447501e-05, + "loss": 3.4142, + "step": 1954304 + }, + { + "epoch": 1.02, + "learning_rate": 1.7996521797239584e-05, + "loss": 3.4039, + "step": 1954816 + }, + { + "epoch": 1.02, + "learning_rate": 1.7988135849729064e-05, + "loss": 3.4043, + "step": 1955328 + }, + { + "epoch": 1.02, + "learning_rate": 1.7979749902218544e-05, + "loss": 3.4265, + "step": 1955840 + }, + { + "epoch": 1.02, + "learning_rate": 1.7971363954708024e-05, + "loss": 3.4262, + "step": 1956352 + }, + { + "epoch": 1.02, + "learning_rate": 1.7962978007197504e-05, + "loss": 3.4184, + "step": 1956864 + }, + { + "epoch": 1.02, + "learning_rate": 1.795459205968698e-05, + "loss": 3.4043, + "step": 1957376 + }, + { + "epoch": 1.02, + "learning_rate": 1.794620611217646e-05, + "loss": 3.4173, + "step": 1957888 + }, + { + "epoch": 1.02, + "learning_rate": 1.7937836543469673e-05, + "loss": 3.409, + "step": 1958400 + }, + { + "epoch": 1.02, + "learning_rate": 1.7929450595959156e-05, + "loss": 3.4219, + "step": 1958912 + }, + { + "epoch": 1.02, + "learning_rate": 1.7921064648448633e-05, + "loss": 3.4112, + "step": 1959424 + }, + { + "epoch": 1.02, + "learning_rate": 1.7912678700938113e-05, + "loss": 3.4066, + "step": 1959936 + }, + { + "epoch": 1.02, + "learning_rate": 1.7904309132231325e-05, + "loss": 3.4123, + "step": 1960448 + }, + { + "epoch": 1.02, + "learning_rate": 1.7895923184720805e-05, + "loss": 3.4208, + "step": 1960960 + }, + { + "epoch": 1.02, + "learning_rate": 1.7887537237210285e-05, + "loss": 3.4023, + "step": 1961472 + }, + { + "epoch": 1.02, + "learning_rate": 1.7879151289699765e-05, + "loss": 3.4153, + "step": 1961984 + }, + { + "epoch": 1.02, + "learning_rate": 1.7870781720992977e-05, + "loss": 3.4034, + "step": 1962496 + }, + { + "epoch": 1.02, + "learning_rate": 1.7862395773482454e-05, + "loss": 3.4073, + "step": 1963008 + }, + { + "epoch": 1.02, + "learning_rate": 1.7854026204775666e-05, + "loss": 3.4024, + "step": 1963520 + }, + { + "epoch": 1.02, + "learning_rate": 1.7845640257265146e-05, + "loss": 3.4065, + "step": 1964032 + }, + { + "epoch": 1.02, + "learning_rate": 1.7837254309754626e-05, + "loss": 3.409, + "step": 1964544 + }, + { + "epoch": 1.02, + "learning_rate": 1.7828868362244106e-05, + "loss": 3.4108, + "step": 1965056 + }, + { + "epoch": 1.02, + "learning_rate": 1.7820482414733586e-05, + "loss": 3.4096, + "step": 1965568 + }, + { + "epoch": 1.02, + "learning_rate": 1.7812096467223066e-05, + "loss": 3.4044, + "step": 1966080 + }, + { + "epoch": 1.02, + "learning_rate": 1.7803726898516275e-05, + "loss": 3.4185, + "step": 1966592 + }, + { + "epoch": 1.02, + "learning_rate": 1.7795340951005755e-05, + "loss": 3.426, + "step": 1967104 + }, + { + "epoch": 1.02, + "learning_rate": 1.778695500349524e-05, + "loss": 3.4142, + "step": 1967616 + }, + { + "epoch": 1.02, + "learning_rate": 1.777856905598472e-05, + "loss": 3.421, + "step": 1968128 + }, + { + "epoch": 1.02, + "learning_rate": 1.77701831084742e-05, + "loss": 3.4028, + "step": 1968640 + }, + { + "epoch": 1.02, + "learning_rate": 1.7761813539767408e-05, + "loss": 3.4113, + "step": 1969152 + }, + { + "epoch": 1.02, + "learning_rate": 1.7753427592256888e-05, + "loss": 3.4051, + "step": 1969664 + }, + { + "epoch": 1.02, + "learning_rate": 1.7745041644746368e-05, + "loss": 3.4025, + "step": 1970176 + }, + { + "epoch": 1.02, + "learning_rate": 1.7736655697235847e-05, + "loss": 3.4078, + "step": 1970688 + }, + { + "epoch": 1.02, + "learning_rate": 1.772826974972533e-05, + "loss": 3.4087, + "step": 1971200 + }, + { + "epoch": 1.02, + "learning_rate": 1.771988380221481e-05, + "loss": 3.4083, + "step": 1971712 + }, + { + "epoch": 1.02, + "learning_rate": 1.771151423350802e-05, + "loss": 3.4111, + "step": 1972224 + }, + { + "epoch": 1.02, + "learning_rate": 1.77031282859975e-05, + "loss": 3.4141, + "step": 1972736 + }, + { + "epoch": 1.02, + "learning_rate": 1.769474233848698e-05, + "loss": 3.4103, + "step": 1973248 + }, + { + "epoch": 1.02, + "learning_rate": 1.7686356390976456e-05, + "loss": 3.4068, + "step": 1973760 + }, + { + "epoch": 1.02, + "learning_rate": 1.767797044346594e-05, + "loss": 3.4125, + "step": 1974272 + }, + { + "epoch": 1.02, + "learning_rate": 1.766958449595542e-05, + "loss": 3.4193, + "step": 1974784 + }, + { + "epoch": 1.02, + "learning_rate": 1.76611985484449e-05, + "loss": 3.4226, + "step": 1975296 + }, + { + "epoch": 1.02, + "learning_rate": 1.765281260093438e-05, + "loss": 3.4081, + "step": 1975808 + }, + { + "epoch": 1.02, + "learning_rate": 1.764444303222759e-05, + "loss": 3.4235, + "step": 1976320 + }, + { + "epoch": 1.02, + "learning_rate": 1.763605708471707e-05, + "loss": 3.4126, + "step": 1976832 + }, + { + "epoch": 1.02, + "learning_rate": 1.762767113720655e-05, + "loss": 3.4133, + "step": 1977344 + }, + { + "epoch": 1.02, + "learning_rate": 1.7619285189696032e-05, + "loss": 3.4131, + "step": 1977856 + }, + { + "epoch": 1.02, + "learning_rate": 1.761091562098924e-05, + "loss": 3.4116, + "step": 1978368 + }, + { + "epoch": 1.02, + "learning_rate": 1.760252967347872e-05, + "loss": 3.4059, + "step": 1978880 + }, + { + "epoch": 1.02, + "learning_rate": 1.75941437259682e-05, + "loss": 3.4197, + "step": 1979392 + }, + { + "epoch": 1.02, + "learning_rate": 1.758575777845768e-05, + "loss": 3.4022, + "step": 1979904 + }, + { + "epoch": 1.02, + "learning_rate": 1.7577388209750893e-05, + "loss": 3.4141, + "step": 1980416 + }, + { + "epoch": 1.02, + "learning_rate": 1.7569002262240373e-05, + "loss": 3.4183, + "step": 1980928 + }, + { + "epoch": 1.02, + "learning_rate": 1.7560616314729853e-05, + "loss": 3.4132, + "step": 1981440 + }, + { + "epoch": 1.02, + "learning_rate": 1.7552246746023062e-05, + "loss": 3.4092, + "step": 1981952 + }, + { + "epoch": 1.02, + "learning_rate": 1.7543860798512542e-05, + "loss": 3.4121, + "step": 1982464 + }, + { + "epoch": 1.02, + "learning_rate": 1.7535474851002022e-05, + "loss": 3.4194, + "step": 1982976 + }, + { + "epoch": 1.02, + "learning_rate": 1.7527088903491502e-05, + "loss": 3.4067, + "step": 1983488 + }, + { + "epoch": 1.02, + "learning_rate": 1.7518702955980986e-05, + "loss": 3.4133, + "step": 1984000 + }, + { + "epoch": 1.03, + "eval_loss": 3.8497278690338135, + "eval_runtime": 306.6962, + "eval_samples_per_second": 1244.199, + "eval_steps_per_second": 38.882, + "step": 1984311 + }, + { + "epoch": 0.0, + "learning_rate": 1.7510317008470466e-05, + "loss": 3.3957, + "step": 1984512 + }, + { + "epoch": 0.0, + "learning_rate": 1.7501931060959942e-05, + "loss": 3.4049, + "step": 1985024 + }, + { + "epoch": 0.0, + "learning_rate": 1.7493545113449422e-05, + "loss": 3.4128, + "step": 1985536 + }, + { + "epoch": 0.0, + "learning_rate": 1.7485175544742635e-05, + "loss": 3.4146, + "step": 1986048 + }, + { + "epoch": 0.0, + "learning_rate": 1.747678959723211e-05, + "loss": 3.4217, + "step": 1986560 + }, + { + "epoch": 0.0, + "learning_rate": 1.7468403649721594e-05, + "loss": 3.405, + "step": 1987072 + }, + { + "epoch": 0.0, + "learning_rate": 1.7460017702211074e-05, + "loss": 3.408, + "step": 1987584 + }, + { + "epoch": 0.0, + "learning_rate": 1.7451631754700554e-05, + "loss": 3.409, + "step": 1988096 + }, + { + "epoch": 0.0, + "learning_rate": 1.7443245807190034e-05, + "loss": 3.4041, + "step": 1988608 + }, + { + "epoch": 0.0, + "learning_rate": 1.7434859859679514e-05, + "loss": 3.4063, + "step": 1989120 + }, + { + "epoch": 0.0, + "learning_rate": 1.7426490290972723e-05, + "loss": 3.4144, + "step": 1989632 + }, + { + "epoch": 0.0, + "learning_rate": 1.7418104343462203e-05, + "loss": 3.4135, + "step": 1990144 + }, + { + "epoch": 0.0, + "learning_rate": 1.7409734774755416e-05, + "loss": 3.4164, + "step": 1990656 + }, + { + "epoch": 0.0, + "learning_rate": 1.7401348827244896e-05, + "loss": 3.389, + "step": 1991168 + }, + { + "epoch": 0.0, + "learning_rate": 1.7392962879734376e-05, + "loss": 3.4105, + "step": 1991680 + }, + { + "epoch": 0.0, + "learning_rate": 1.7384576932223856e-05, + "loss": 3.3925, + "step": 1992192 + }, + { + "epoch": 0.0, + "learning_rate": 1.7376190984713336e-05, + "loss": 3.4046, + "step": 1992704 + }, + { + "epoch": 0.0, + "learning_rate": 1.7367805037202816e-05, + "loss": 3.407, + "step": 1993216 + }, + { + "epoch": 0.0, + "learning_rate": 1.7359419089692296e-05, + "loss": 3.4066, + "step": 1993728 + }, + { + "epoch": 0.0, + "learning_rate": 1.7351033142181776e-05, + "loss": 3.4131, + "step": 1994240 + }, + { + "epoch": 0.0, + "learning_rate": 1.7342663573474988e-05, + "loss": 3.42, + "step": 1994752 + }, + { + "epoch": 0.0, + "learning_rate": 1.7334277625964468e-05, + "loss": 3.4126, + "step": 1995264 + }, + { + "epoch": 0.0, + "learning_rate": 1.7325891678453945e-05, + "loss": 3.402, + "step": 1995776 + }, + { + "epoch": 0.0, + "learning_rate": 1.7317505730943424e-05, + "loss": 3.3981, + "step": 1996288 + }, + { + "epoch": 0.0, + "learning_rate": 1.730913616223664e-05, + "loss": 3.4125, + "step": 1996800 + }, + { + "epoch": 0.0, + "learning_rate": 1.730075021472612e-05, + "loss": 3.4114, + "step": 1997312 + }, + { + "epoch": 0.0, + "learning_rate": 1.7292364267215597e-05, + "loss": 3.4088, + "step": 1997824 + }, + { + "epoch": 0.0, + "learning_rate": 1.7283978319705077e-05, + "loss": 3.4067, + "step": 1998336 + }, + { + "epoch": 0.0, + "learning_rate": 1.727560875099829e-05, + "loss": 3.3996, + "step": 1998848 + }, + { + "epoch": 0.0, + "learning_rate": 1.7267222803487766e-05, + "loss": 3.4057, + "step": 1999360 + }, + { + "epoch": 0.01, + "learning_rate": 1.725883685597725e-05, + "loss": 3.3947, + "step": 1999872 + }, + { + "epoch": 0.01, + "learning_rate": 1.725045090846673e-05, + "loss": 3.4185, + "step": 2000384 + }, + { + "epoch": 0.01, + "learning_rate": 1.724206496095621e-05, + "loss": 3.4155, + "step": 2000896 + }, + { + "epoch": 0.01, + "learning_rate": 1.723367901344569e-05, + "loss": 3.4102, + "step": 2001408 + }, + { + "epoch": 0.01, + "learning_rate": 1.722529306593517e-05, + "loss": 3.4043, + "step": 2001920 + }, + { + "epoch": 0.01, + "learning_rate": 1.7216923497228378e-05, + "loss": 3.4001, + "step": 2002432 + }, + { + "epoch": 0.01, + "learning_rate": 1.7208537549717858e-05, + "loss": 3.4132, + "step": 2002944 + }, + { + "epoch": 0.01, + "learning_rate": 1.720015160220734e-05, + "loss": 3.406, + "step": 2003456 + }, + { + "epoch": 0.01, + "learning_rate": 1.719176565469682e-05, + "loss": 3.3964, + "step": 2003968 + }, + { + "epoch": 0.01, + "learning_rate": 1.718339608599003e-05, + "loss": 3.3997, + "step": 2004480 + }, + { + "epoch": 0.01, + "learning_rate": 1.717502651728324e-05, + "loss": 3.4038, + "step": 2004992 + }, + { + "epoch": 0.01, + "learning_rate": 1.716664056977272e-05, + "loss": 3.4065, + "step": 2005504 + }, + { + "epoch": 0.01, + "learning_rate": 1.7158254622262203e-05, + "loss": 3.4041, + "step": 2006016 + }, + { + "epoch": 0.01, + "learning_rate": 1.7149868674751683e-05, + "loss": 3.406, + "step": 2006528 + }, + { + "epoch": 0.01, + "learning_rate": 1.7141482727241163e-05, + "loss": 3.4149, + "step": 2007040 + }, + { + "epoch": 0.01, + "learning_rate": 1.7133096779730643e-05, + "loss": 3.4056, + "step": 2007552 + }, + { + "epoch": 0.01, + "learning_rate": 1.7124710832220123e-05, + "loss": 3.4115, + "step": 2008064 + }, + { + "epoch": 0.01, + "learning_rate": 1.71163248847096e-05, + "loss": 3.4072, + "step": 2008576 + }, + { + "epoch": 0.01, + "learning_rate": 1.7107955316002812e-05, + "loss": 3.3807, + "step": 2009088 + }, + { + "epoch": 0.01, + "learning_rate": 1.7099569368492295e-05, + "loss": 3.4172, + "step": 2009600 + }, + { + "epoch": 0.01, + "learning_rate": 1.709118342098177e-05, + "loss": 3.4015, + "step": 2010112 + }, + { + "epoch": 0.01, + "learning_rate": 1.7082813852274984e-05, + "loss": 3.4035, + "step": 2010624 + }, + { + "epoch": 0.01, + "learning_rate": 1.7074427904764464e-05, + "loss": 3.4083, + "step": 2011136 + }, + { + "epoch": 0.01, + "learning_rate": 1.7066058336057673e-05, + "loss": 3.4004, + "step": 2011648 + }, + { + "epoch": 0.01, + "learning_rate": 1.7057672388547157e-05, + "loss": 3.3875, + "step": 2012160 + }, + { + "epoch": 0.01, + "learning_rate": 1.7049286441036637e-05, + "loss": 3.3963, + "step": 2012672 + }, + { + "epoch": 0.01, + "learning_rate": 1.7040900493526116e-05, + "loss": 3.3987, + "step": 2013184 + }, + { + "epoch": 0.01, + "learning_rate": 1.7032514546015596e-05, + "loss": 3.3994, + "step": 2013696 + }, + { + "epoch": 0.01, + "learning_rate": 1.7024128598505073e-05, + "loss": 3.4119, + "step": 2014208 + }, + { + "epoch": 0.01, + "learning_rate": 1.7015742650994553e-05, + "loss": 3.4009, + "step": 2014720 + }, + { + "epoch": 0.01, + "learning_rate": 1.7007356703484033e-05, + "loss": 3.3959, + "step": 2015232 + }, + { + "epoch": 0.01, + "learning_rate": 1.6998987134777245e-05, + "loss": 3.4176, + "step": 2015744 + }, + { + "epoch": 0.01, + "learning_rate": 1.6990601187266725e-05, + "loss": 3.3904, + "step": 2016256 + }, + { + "epoch": 0.01, + "learning_rate": 1.6982215239756205e-05, + "loss": 3.3909, + "step": 2016768 + }, + { + "epoch": 0.01, + "learning_rate": 1.6973829292245685e-05, + "loss": 3.4055, + "step": 2017280 + }, + { + "epoch": 0.01, + "learning_rate": 1.6965459723538894e-05, + "loss": 3.399, + "step": 2017792 + }, + { + "epoch": 0.01, + "learning_rate": 1.695709015483211e-05, + "loss": 3.394, + "step": 2018304 + }, + { + "epoch": 0.01, + "learning_rate": 1.694870420732159e-05, + "loss": 3.3993, + "step": 2018816 + }, + { + "epoch": 0.01, + "learning_rate": 1.694031825981107e-05, + "loss": 3.391, + "step": 2019328 + }, + { + "epoch": 0.01, + "learning_rate": 1.6931932312300547e-05, + "loss": 3.3914, + "step": 2019840 + }, + { + "epoch": 0.01, + "learning_rate": 1.6923546364790027e-05, + "loss": 3.4119, + "step": 2020352 + }, + { + "epoch": 0.01, + "learning_rate": 1.6915160417279507e-05, + "loss": 3.4002, + "step": 2020864 + }, + { + "epoch": 0.01, + "learning_rate": 1.6906774469768987e-05, + "loss": 3.4094, + "step": 2021376 + }, + { + "epoch": 0.01, + "learning_rate": 1.6898388522258467e-05, + "loss": 3.4022, + "step": 2021888 + }, + { + "epoch": 0.01, + "learning_rate": 1.689001895355168e-05, + "loss": 3.4185, + "step": 2022400 + }, + { + "epoch": 0.01, + "learning_rate": 1.688163300604116e-05, + "loss": 3.3953, + "step": 2022912 + }, + { + "epoch": 0.01, + "learning_rate": 1.6873263437334368e-05, + "loss": 3.4113, + "step": 2023424 + }, + { + "epoch": 0.01, + "learning_rate": 1.6864877489823848e-05, + "loss": 3.4087, + "step": 2023936 + }, + { + "epoch": 0.01, + "learning_rate": 1.6856491542313328e-05, + "loss": 3.3894, + "step": 2024448 + }, + { + "epoch": 0.01, + "learning_rate": 1.684810559480281e-05, + "loss": 3.4167, + "step": 2024960 + }, + { + "epoch": 0.01, + "learning_rate": 1.683971964729229e-05, + "loss": 3.4038, + "step": 2025472 + }, + { + "epoch": 0.01, + "learning_rate": 1.68313500785855e-05, + "loss": 3.4053, + "step": 2025984 + }, + { + "epoch": 0.01, + "learning_rate": 1.682296413107498e-05, + "loss": 3.4107, + "step": 2026496 + }, + { + "epoch": 0.01, + "learning_rate": 1.681457818356446e-05, + "loss": 3.3872, + "step": 2027008 + }, + { + "epoch": 0.01, + "learning_rate": 1.680619223605394e-05, + "loss": 3.3848, + "step": 2027520 + }, + { + "epoch": 0.01, + "learning_rate": 1.679780628854342e-05, + "loss": 3.3946, + "step": 2028032 + }, + { + "epoch": 0.01, + "learning_rate": 1.6789436719836633e-05, + "loss": 3.4063, + "step": 2028544 + }, + { + "epoch": 0.01, + "learning_rate": 1.6781050772326113e-05, + "loss": 3.3969, + "step": 2029056 + }, + { + "epoch": 0.01, + "learning_rate": 1.6772664824815593e-05, + "loss": 3.3961, + "step": 2029568 + }, + { + "epoch": 0.01, + "learning_rate": 1.6764278877305073e-05, + "loss": 3.3973, + "step": 2030080 + }, + { + "epoch": 0.02, + "learning_rate": 1.675590930859828e-05, + "loss": 3.4058, + "step": 2030592 + }, + { + "epoch": 0.02, + "learning_rate": 1.6747523361087765e-05, + "loss": 3.3954, + "step": 2031104 + }, + { + "epoch": 0.02, + "learning_rate": 1.6739137413577245e-05, + "loss": 3.3953, + "step": 2031616 + }, + { + "epoch": 0.02, + "learning_rate": 1.6730751466066725e-05, + "loss": 3.4142, + "step": 2032128 + }, + { + "epoch": 0.02, + "learning_rate": 1.67223655185562e-05, + "loss": 3.4164, + "step": 2032640 + }, + { + "epoch": 0.02, + "learning_rate": 1.671397957104568e-05, + "loss": 3.411, + "step": 2033152 + }, + { + "epoch": 0.02, + "learning_rate": 1.670559362353516e-05, + "loss": 3.3924, + "step": 2033664 + }, + { + "epoch": 0.02, + "learning_rate": 1.669720767602464e-05, + "loss": 3.4043, + "step": 2034176 + }, + { + "epoch": 0.02, + "learning_rate": 1.6688838107317854e-05, + "loss": 3.3972, + "step": 2034688 + }, + { + "epoch": 0.02, + "learning_rate": 1.6680452159807334e-05, + "loss": 3.4114, + "step": 2035200 + }, + { + "epoch": 0.02, + "learning_rate": 1.6672066212296814e-05, + "loss": 3.4004, + "step": 2035712 + }, + { + "epoch": 0.02, + "learning_rate": 1.6663680264786294e-05, + "loss": 3.402, + "step": 2036224 + }, + { + "epoch": 0.02, + "learning_rate": 1.6655310696079503e-05, + "loss": 3.4001, + "step": 2036736 + }, + { + "epoch": 0.02, + "learning_rate": 1.6646924748568983e-05, + "loss": 3.4072, + "step": 2037248 + }, + { + "epoch": 0.02, + "learning_rate": 1.6638538801058466e-05, + "loss": 3.4004, + "step": 2037760 + }, + { + "epoch": 0.02, + "learning_rate": 1.6630152853547946e-05, + "loss": 3.4025, + "step": 2038272 + }, + { + "epoch": 0.02, + "learning_rate": 1.6621783284841155e-05, + "loss": 3.3937, + "step": 2038784 + }, + { + "epoch": 0.02, + "learning_rate": 1.6613397337330635e-05, + "loss": 3.3974, + "step": 2039296 + }, + { + "epoch": 0.02, + "learning_rate": 1.6605011389820115e-05, + "loss": 3.3942, + "step": 2039808 + }, + { + "epoch": 0.02, + "learning_rate": 1.6596625442309595e-05, + "loss": 3.3919, + "step": 2040320 + }, + { + "epoch": 0.02, + "learning_rate": 1.6588255873602807e-05, + "loss": 3.3975, + "step": 2040832 + }, + { + "epoch": 0.02, + "learning_rate": 1.6579869926092287e-05, + "loss": 3.3979, + "step": 2041344 + }, + { + "epoch": 0.02, + "learning_rate": 1.6571483978581767e-05, + "loss": 3.402, + "step": 2041856 + }, + { + "epoch": 0.02, + "learning_rate": 1.6563098031071247e-05, + "loss": 3.393, + "step": 2042368 + }, + { + "epoch": 0.02, + "learning_rate": 1.655474484116819e-05, + "loss": 3.408, + "step": 2042880 + }, + { + "epoch": 0.02, + "learning_rate": 1.654635889365767e-05, + "loss": 3.4147, + "step": 2043392 + }, + { + "epoch": 0.02, + "learning_rate": 1.653797294614715e-05, + "loss": 3.4043, + "step": 2043904 + }, + { + "epoch": 0.02, + "learning_rate": 1.652958699863663e-05, + "loss": 3.4111, + "step": 2044416 + }, + { + "epoch": 0.02, + "learning_rate": 1.652120105112611e-05, + "loss": 3.3926, + "step": 2044928 + }, + { + "epoch": 0.02, + "learning_rate": 1.6512831482419318e-05, + "loss": 3.401, + "step": 2045440 + }, + { + "epoch": 0.02, + "learning_rate": 1.6504445534908798e-05, + "loss": 3.3956, + "step": 2045952 + }, + { + "epoch": 0.02, + "learning_rate": 1.649605958739828e-05, + "loss": 3.388, + "step": 2046464 + }, + { + "epoch": 0.02, + "learning_rate": 1.648767363988776e-05, + "loss": 3.402, + "step": 2046976 + }, + { + "epoch": 0.02, + "learning_rate": 1.647928769237724e-05, + "loss": 3.397, + "step": 2047488 + }, + { + "epoch": 0.02, + "learning_rate": 1.647090174486672e-05, + "loss": 3.4013, + "step": 2048000 + }, + { + "epoch": 0.02, + "learning_rate": 1.646253217615993e-05, + "loss": 3.3998, + "step": 2048512 + }, + { + "epoch": 0.02, + "learning_rate": 1.645414622864941e-05, + "loss": 3.4056, + "step": 2049024 + }, + { + "epoch": 0.02, + "learning_rate": 1.644576028113889e-05, + "loss": 3.3968, + "step": 2049536 + }, + { + "epoch": 0.02, + "learning_rate": 1.6437374333628373e-05, + "loss": 3.3974, + "step": 2050048 + }, + { + "epoch": 0.02, + "learning_rate": 1.642898838611785e-05, + "loss": 3.404, + "step": 2050560 + }, + { + "epoch": 0.02, + "learning_rate": 1.642060243860733e-05, + "loss": 3.4104, + "step": 2051072 + }, + { + "epoch": 0.02, + "learning_rate": 1.641221649109681e-05, + "loss": 3.4113, + "step": 2051584 + }, + { + "epoch": 0.02, + "learning_rate": 1.640383054358629e-05, + "loss": 3.3969, + "step": 2052096 + }, + { + "epoch": 0.02, + "learning_rate": 1.6395460974879502e-05, + "loss": 3.414, + "step": 2052608 + }, + { + "epoch": 0.02, + "learning_rate": 1.6387075027368982e-05, + "loss": 3.4016, + "step": 2053120 + }, + { + "epoch": 0.02, + "learning_rate": 1.6378689079858462e-05, + "loss": 3.4053, + "step": 2053632 + }, + { + "epoch": 0.02, + "learning_rate": 1.6370303132347942e-05, + "loss": 3.4059, + "step": 2054144 + }, + { + "epoch": 0.02, + "learning_rate": 1.636193356364115e-05, + "loss": 3.3948, + "step": 2054656 + }, + { + "epoch": 0.02, + "learning_rate": 1.635354761613063e-05, + "loss": 3.3952, + "step": 2055168 + }, + { + "epoch": 0.02, + "learning_rate": 1.634516166862011e-05, + "loss": 3.4131, + "step": 2055680 + }, + { + "epoch": 0.02, + "learning_rate": 1.6336775721109595e-05, + "loss": 3.3923, + "step": 2056192 + }, + { + "epoch": 0.02, + "learning_rate": 1.6328422531206536e-05, + "loss": 3.405, + "step": 2056704 + }, + { + "epoch": 0.02, + "learning_rate": 1.6320036583696016e-05, + "loss": 3.406, + "step": 2057216 + }, + { + "epoch": 0.02, + "learning_rate": 1.6311650636185496e-05, + "loss": 3.4048, + "step": 2057728 + }, + { + "epoch": 0.02, + "learning_rate": 1.6303264688674973e-05, + "loss": 3.3988, + "step": 2058240 + }, + { + "epoch": 0.02, + "learning_rate": 1.6294878741164456e-05, + "loss": 3.4039, + "step": 2058752 + }, + { + "epoch": 0.02, + "learning_rate": 1.6286492793653936e-05, + "loss": 3.4047, + "step": 2059264 + }, + { + "epoch": 0.02, + "learning_rate": 1.6278106846143416e-05, + "loss": 3.4036, + "step": 2059776 + }, + { + "epoch": 0.02, + "learning_rate": 1.6269720898632896e-05, + "loss": 3.4024, + "step": 2060288 + }, + { + "epoch": 0.03, + "eval_loss": 3.8521807193756104, + "eval_runtime": 305.27, + "eval_samples_per_second": 1250.011, + "eval_steps_per_second": 39.064, + "step": 2060631 + }, + { + "epoch": 1.0, + "learning_rate": 1.6261351329926105e-05, + "loss": 3.3886, + "step": 2060800 + }, + { + "epoch": 1.0, + "learning_rate": 1.6252965382415585e-05, + "loss": 3.3963, + "step": 2061312 + }, + { + "epoch": 1.0, + "learning_rate": 1.6244579434905065e-05, + "loss": 3.4025, + "step": 2061824 + }, + { + "epoch": 1.0, + "learning_rate": 1.6236209866198277e-05, + "loss": 3.4039, + "step": 2062336 + }, + { + "epoch": 1.0, + "learning_rate": 1.6227823918687757e-05, + "loss": 3.4149, + "step": 2062848 + }, + { + "epoch": 1.0, + "learning_rate": 1.6219437971177237e-05, + "loss": 3.3931, + "step": 2063360 + }, + { + "epoch": 1.0, + "learning_rate": 1.6211052023666717e-05, + "loss": 3.4008, + "step": 2063872 + }, + { + "epoch": 1.0, + "learning_rate": 1.6202666076156197e-05, + "loss": 3.3992, + "step": 2064384 + }, + { + "epoch": 1.0, + "learning_rate": 1.6194280128645677e-05, + "loss": 3.3936, + "step": 2064896 + }, + { + "epoch": 1.0, + "learning_rate": 1.618591055993889e-05, + "loss": 3.3918, + "step": 2065408 + }, + { + "epoch": 1.0, + "learning_rate": 1.617752461242837e-05, + "loss": 3.4026, + "step": 2065920 + }, + { + "epoch": 1.0, + "learning_rate": 1.616913866491785e-05, + "loss": 3.4103, + "step": 2066432 + }, + { + "epoch": 1.0, + "learning_rate": 1.616075271740733e-05, + "loss": 3.4059, + "step": 2066944 + }, + { + "epoch": 1.0, + "learning_rate": 1.6152366769896806e-05, + "loss": 3.38, + "step": 2067456 + }, + { + "epoch": 1.0, + "learning_rate": 1.6143980822386286e-05, + "loss": 3.4011, + "step": 2067968 + }, + { + "epoch": 1.0, + "learning_rate": 1.6135594874875766e-05, + "loss": 3.3821, + "step": 2068480 + }, + { + "epoch": 1.0, + "learning_rate": 1.612722530616898e-05, + "loss": 3.3967, + "step": 2068992 + }, + { + "epoch": 1.0, + "learning_rate": 1.611883935865846e-05, + "loss": 3.3973, + "step": 2069504 + }, + { + "epoch": 1.0, + "learning_rate": 1.611045341114794e-05, + "loss": 3.3961, + "step": 2070016 + }, + { + "epoch": 1.0, + "learning_rate": 1.610206746363742e-05, + "loss": 3.3997, + "step": 2070528 + }, + { + "epoch": 1.0, + "learning_rate": 1.6093697894930627e-05, + "loss": 3.409, + "step": 2071040 + }, + { + "epoch": 1.0, + "learning_rate": 1.608531194742011e-05, + "loss": 3.3993, + "step": 2071552 + }, + { + "epoch": 1.0, + "learning_rate": 1.607692599990959e-05, + "loss": 3.3952, + "step": 2072064 + }, + { + "epoch": 1.0, + "learning_rate": 1.606854005239907e-05, + "loss": 3.3888, + "step": 2072576 + }, + { + "epoch": 1.0, + "learning_rate": 1.606017048369228e-05, + "loss": 3.4027, + "step": 2073088 + }, + { + "epoch": 1.0, + "learning_rate": 1.605178453618176e-05, + "loss": 3.3998, + "step": 2073600 + }, + { + "epoch": 1.0, + "learning_rate": 1.604339858867124e-05, + "loss": 3.3967, + "step": 2074112 + }, + { + "epoch": 1.0, + "learning_rate": 1.603501264116072e-05, + "loss": 3.3984, + "step": 2074624 + }, + { + "epoch": 1.0, + "learning_rate": 1.6026643072453932e-05, + "loss": 3.3883, + "step": 2075136 + }, + { + "epoch": 1.0, + "learning_rate": 1.6018257124943412e-05, + "loss": 3.3954, + "step": 2075648 + }, + { + "epoch": 1.01, + "learning_rate": 1.6009871177432892e-05, + "loss": 3.3906, + "step": 2076160 + }, + { + "epoch": 1.01, + "learning_rate": 1.6001485229922372e-05, + "loss": 3.4027, + "step": 2076672 + }, + { + "epoch": 1.01, + "learning_rate": 1.5993099282411852e-05, + "loss": 3.4022, + "step": 2077184 + }, + { + "epoch": 1.01, + "learning_rate": 1.5984713334901332e-05, + "loss": 3.4018, + "step": 2077696 + }, + { + "epoch": 1.01, + "learning_rate": 1.5976327387390812e-05, + "loss": 3.3939, + "step": 2078208 + }, + { + "epoch": 1.01, + "learning_rate": 1.5967941439880292e-05, + "loss": 3.3939, + "step": 2078720 + }, + { + "epoch": 1.01, + "learning_rate": 1.5959571871173504e-05, + "loss": 3.4029, + "step": 2079232 + }, + { + "epoch": 1.01, + "learning_rate": 1.595118592366298e-05, + "loss": 3.3909, + "step": 2079744 + }, + { + "epoch": 1.01, + "learning_rate": 1.594279997615246e-05, + "loss": 3.3892, + "step": 2080256 + }, + { + "epoch": 1.01, + "learning_rate": 1.5934430407445673e-05, + "loss": 3.3959, + "step": 2080768 + }, + { + "epoch": 1.01, + "learning_rate": 1.5926060838738886e-05, + "loss": 3.3876, + "step": 2081280 + }, + { + "epoch": 1.01, + "learning_rate": 1.5917674891228366e-05, + "loss": 3.3949, + "step": 2081792 + }, + { + "epoch": 1.01, + "learning_rate": 1.5909288943717846e-05, + "loss": 3.3919, + "step": 2082304 + }, + { + "epoch": 1.01, + "learning_rate": 1.5900902996207326e-05, + "loss": 3.3965, + "step": 2082816 + }, + { + "epoch": 1.01, + "learning_rate": 1.5892517048696806e-05, + "loss": 3.4023, + "step": 2083328 + }, + { + "epoch": 1.01, + "learning_rate": 1.5884131101186282e-05, + "loss": 3.4034, + "step": 2083840 + }, + { + "epoch": 1.01, + "learning_rate": 1.5875745153675766e-05, + "loss": 3.4001, + "step": 2084352 + }, + { + "epoch": 1.01, + "learning_rate": 1.5867359206165245e-05, + "loss": 3.3962, + "step": 2084864 + }, + { + "epoch": 1.01, + "learning_rate": 1.5858989637458455e-05, + "loss": 3.373, + "step": 2085376 + }, + { + "epoch": 1.01, + "learning_rate": 1.5850603689947935e-05, + "loss": 3.4044, + "step": 2085888 + }, + { + "epoch": 1.01, + "learning_rate": 1.5842217742437414e-05, + "loss": 3.3925, + "step": 2086400 + }, + { + "epoch": 1.01, + "learning_rate": 1.5833831794926894e-05, + "loss": 3.3956, + "step": 2086912 + }, + { + "epoch": 1.01, + "learning_rate": 1.5825462226220107e-05, + "loss": 3.3971, + "step": 2087424 + }, + { + "epoch": 1.01, + "learning_rate": 1.581709265751332e-05, + "loss": 3.3903, + "step": 2087936 + }, + { + "epoch": 1.01, + "learning_rate": 1.58087067100028e-05, + "loss": 3.3751, + "step": 2088448 + }, + { + "epoch": 1.01, + "learning_rate": 1.580032076249228e-05, + "loss": 3.3842, + "step": 2088960 + }, + { + "epoch": 1.01, + "learning_rate": 1.5791934814981756e-05, + "loss": 3.3931, + "step": 2089472 + }, + { + "epoch": 1.01, + "learning_rate": 1.5783548867471236e-05, + "loss": 3.3854, + "step": 2089984 + }, + { + "epoch": 1.01, + "learning_rate": 1.577516291996072e-05, + "loss": 3.4055, + "step": 2090496 + }, + { + "epoch": 1.01, + "learning_rate": 1.57667769724502e-05, + "loss": 3.3922, + "step": 2091008 + }, + { + "epoch": 1.01, + "learning_rate": 1.575839102493968e-05, + "loss": 3.3826, + "step": 2091520 + }, + { + "epoch": 1.01, + "learning_rate": 1.5750021456232888e-05, + "loss": 3.407, + "step": 2092032 + }, + { + "epoch": 1.01, + "learning_rate": 1.5741635508722368e-05, + "loss": 3.3842, + "step": 2092544 + }, + { + "epoch": 1.01, + "learning_rate": 1.5733249561211848e-05, + "loss": 3.3784, + "step": 2093056 + }, + { + "epoch": 1.01, + "learning_rate": 1.5724863613701328e-05, + "loss": 3.3937, + "step": 2093568 + }, + { + "epoch": 1.01, + "learning_rate": 1.571649404499454e-05, + "loss": 3.3905, + "step": 2094080 + }, + { + "epoch": 1.01, + "learning_rate": 1.5708124476287753e-05, + "loss": 3.385, + "step": 2094592 + }, + { + "epoch": 1.01, + "learning_rate": 1.569973852877723e-05, + "loss": 3.3884, + "step": 2095104 + }, + { + "epoch": 1.01, + "learning_rate": 1.569135258126671e-05, + "loss": 3.3798, + "step": 2095616 + }, + { + "epoch": 1.01, + "learning_rate": 1.568296663375619e-05, + "loss": 3.385, + "step": 2096128 + }, + { + "epoch": 1.01, + "learning_rate": 1.5674580686245673e-05, + "loss": 3.3984, + "step": 2096640 + }, + { + "epoch": 1.01, + "learning_rate": 1.5666194738735153e-05, + "loss": 3.3905, + "step": 2097152 + }, + { + "epoch": 1.01, + "learning_rate": 1.5657808791224633e-05, + "loss": 3.4014, + "step": 2097664 + }, + { + "epoch": 1.01, + "learning_rate": 1.564942284371411e-05, + "loss": 3.3911, + "step": 2098176 + }, + { + "epoch": 1.01, + "learning_rate": 1.5641053275007322e-05, + "loss": 3.4078, + "step": 2098688 + }, + { + "epoch": 1.01, + "learning_rate": 1.5632667327496802e-05, + "loss": 3.3871, + "step": 2099200 + }, + { + "epoch": 1.01, + "learning_rate": 1.5624281379986282e-05, + "loss": 3.4017, + "step": 2099712 + }, + { + "epoch": 1.01, + "learning_rate": 1.561589543247576e-05, + "loss": 3.3955, + "step": 2100224 + }, + { + "epoch": 1.01, + "learning_rate": 1.5607525863768974e-05, + "loss": 3.3816, + "step": 2100736 + }, + { + "epoch": 1.01, + "learning_rate": 1.5599156295062183e-05, + "loss": 3.4022, + "step": 2101248 + }, + { + "epoch": 1.01, + "learning_rate": 1.5590770347551663e-05, + "loss": 3.3994, + "step": 2101760 + }, + { + "epoch": 1.01, + "learning_rate": 1.5582384400041143e-05, + "loss": 3.3952, + "step": 2102272 + }, + { + "epoch": 1.01, + "learning_rate": 1.5573998452530627e-05, + "loss": 3.4012, + "step": 2102784 + }, + { + "epoch": 1.01, + "learning_rate": 1.5565612505020106e-05, + "loss": 3.3786, + "step": 2103296 + }, + { + "epoch": 1.01, + "learning_rate": 1.5557226557509583e-05, + "loss": 3.3735, + "step": 2103808 + }, + { + "epoch": 1.01, + "learning_rate": 1.5548840609999063e-05, + "loss": 3.3832, + "step": 2104320 + }, + { + "epoch": 1.01, + "learning_rate": 1.5540471041292275e-05, + "loss": 3.3983, + "step": 2104832 + }, + { + "epoch": 1.01, + "learning_rate": 1.5532085093781755e-05, + "loss": 3.3905, + "step": 2105344 + }, + { + "epoch": 1.01, + "learning_rate": 1.5523699146271235e-05, + "loss": 3.3852, + "step": 2105856 + }, + { + "epoch": 1.01, + "learning_rate": 1.5515313198760715e-05, + "loss": 3.3863, + "step": 2106368 + }, + { + "epoch": 1.02, + "learning_rate": 1.5506927251250195e-05, + "loss": 3.392, + "step": 2106880 + }, + { + "epoch": 1.02, + "learning_rate": 1.5498557682543408e-05, + "loss": 3.3892, + "step": 2107392 + }, + { + "epoch": 1.02, + "learning_rate": 1.5490171735032884e-05, + "loss": 3.389, + "step": 2107904 + }, + { + "epoch": 1.02, + "learning_rate": 1.5481785787522364e-05, + "loss": 3.401, + "step": 2108416 + }, + { + "epoch": 1.02, + "learning_rate": 1.5473399840011844e-05, + "loss": 3.4072, + "step": 2108928 + }, + { + "epoch": 1.02, + "learning_rate": 1.5465013892501328e-05, + "loss": 3.3995, + "step": 2109440 + }, + { + "epoch": 1.02, + "learning_rate": 1.5456627944990808e-05, + "loss": 3.3886, + "step": 2109952 + }, + { + "epoch": 1.02, + "learning_rate": 1.5448241997480288e-05, + "loss": 3.3893, + "step": 2110464 + }, + { + "epoch": 1.02, + "learning_rate": 1.5439872428773497e-05, + "loss": 3.3889, + "step": 2110976 + }, + { + "epoch": 1.02, + "learning_rate": 1.5431486481262977e-05, + "loss": 3.3994, + "step": 2111488 + }, + { + "epoch": 1.02, + "learning_rate": 1.5423100533752457e-05, + "loss": 3.391, + "step": 2112000 + }, + { + "epoch": 1.02, + "learning_rate": 1.5414714586241936e-05, + "loss": 3.3897, + "step": 2112512 + }, + { + "epoch": 1.02, + "learning_rate": 1.5406328638731416e-05, + "loss": 3.3906, + "step": 2113024 + }, + { + "epoch": 1.02, + "learning_rate": 1.5397942691220896e-05, + "loss": 3.391, + "step": 2113536 + }, + { + "epoch": 1.02, + "learning_rate": 1.5389556743710376e-05, + "loss": 3.3967, + "step": 2114048 + }, + { + "epoch": 1.02, + "learning_rate": 1.5381170796199856e-05, + "loss": 3.3876, + "step": 2114560 + }, + { + "epoch": 1.02, + "learning_rate": 1.5372801227493065e-05, + "loss": 3.3844, + "step": 2115072 + }, + { + "epoch": 1.02, + "learning_rate": 1.5364415279982545e-05, + "loss": 3.3859, + "step": 2115584 + }, + { + "epoch": 1.02, + "learning_rate": 1.535602933247203e-05, + "loss": 3.389, + "step": 2116096 + }, + { + "epoch": 1.02, + "learning_rate": 1.5347659763765238e-05, + "loss": 3.3832, + "step": 2116608 + }, + { + "epoch": 1.02, + "learning_rate": 1.5339273816254718e-05, + "loss": 3.388, + "step": 2117120 + }, + { + "epoch": 1.02, + "learning_rate": 1.5330887868744198e-05, + "loss": 3.3861, + "step": 2117632 + }, + { + "epoch": 1.02, + "learning_rate": 1.5322501921233678e-05, + "loss": 3.3914, + "step": 2118144 + }, + { + "epoch": 1.02, + "learning_rate": 1.5314115973723158e-05, + "loss": 3.3824, + "step": 2118656 + }, + { + "epoch": 1.02, + "learning_rate": 1.530574640501637e-05, + "loss": 3.4, + "step": 2119168 + }, + { + "epoch": 1.02, + "learning_rate": 1.529736045750585e-05, + "loss": 3.4055, + "step": 2119680 + }, + { + "epoch": 1.02, + "learning_rate": 1.528897450999533e-05, + "loss": 3.3921, + "step": 2120192 + }, + { + "epoch": 1.02, + "learning_rate": 1.528058856248481e-05, + "loss": 3.4002, + "step": 2120704 + }, + { + "epoch": 1.02, + "learning_rate": 1.527220261497429e-05, + "loss": 3.3903, + "step": 2121216 + }, + { + "epoch": 1.02, + "learning_rate": 1.52638330462675e-05, + "loss": 3.3896, + "step": 2121728 + }, + { + "epoch": 1.02, + "learning_rate": 1.525544709875698e-05, + "loss": 3.3849, + "step": 2122240 + }, + { + "epoch": 1.02, + "learning_rate": 1.524706115124646e-05, + "loss": 3.3767, + "step": 2122752 + }, + { + "epoch": 1.02, + "learning_rate": 1.5238675203735942e-05, + "loss": 3.3906, + "step": 2123264 + }, + { + "epoch": 1.02, + "learning_rate": 1.5230289256225419e-05, + "loss": 3.3902, + "step": 2123776 + }, + { + "epoch": 1.02, + "learning_rate": 1.5221903308714899e-05, + "loss": 3.3939, + "step": 2124288 + }, + { + "epoch": 1.02, + "learning_rate": 1.5213533740008113e-05, + "loss": 3.3864, + "step": 2124800 + }, + { + "epoch": 1.02, + "learning_rate": 1.5205147792497593e-05, + "loss": 3.3926, + "step": 2125312 + }, + { + "epoch": 1.02, + "learning_rate": 1.519676184498707e-05, + "loss": 3.3886, + "step": 2125824 + }, + { + "epoch": 1.02, + "learning_rate": 1.5188375897476551e-05, + "loss": 3.3874, + "step": 2126336 + }, + { + "epoch": 1.02, + "learning_rate": 1.5180006328769764e-05, + "loss": 3.3941, + "step": 2126848 + }, + { + "epoch": 1.02, + "learning_rate": 1.5171620381259242e-05, + "loss": 3.3989, + "step": 2127360 + }, + { + "epoch": 1.02, + "learning_rate": 1.5163234433748722e-05, + "loss": 3.4024, + "step": 2127872 + }, + { + "epoch": 1.02, + "learning_rate": 1.5154848486238202e-05, + "loss": 3.3862, + "step": 2128384 + }, + { + "epoch": 1.02, + "learning_rate": 1.5146462538727682e-05, + "loss": 3.4069, + "step": 2128896 + }, + { + "epoch": 1.02, + "learning_rate": 1.5138076591217162e-05, + "loss": 3.3889, + "step": 2129408 + }, + { + "epoch": 1.02, + "learning_rate": 1.5129690643706643e-05, + "loss": 3.3978, + "step": 2129920 + }, + { + "epoch": 1.02, + "learning_rate": 1.5121304696196123e-05, + "loss": 3.3963, + "step": 2130432 + }, + { + "epoch": 1.02, + "learning_rate": 1.5112935127489332e-05, + "loss": 3.3897, + "step": 2130944 + }, + { + "epoch": 1.02, + "learning_rate": 1.5104549179978814e-05, + "loss": 3.3831, + "step": 2131456 + }, + { + "epoch": 1.02, + "learning_rate": 1.5096163232468294e-05, + "loss": 3.4053, + "step": 2131968 + }, + { + "epoch": 1.02, + "learning_rate": 1.5087777284957774e-05, + "loss": 3.3807, + "step": 2132480 + }, + { + "epoch": 1.02, + "learning_rate": 1.5079407716250985e-05, + "loss": 3.3965, + "step": 2132992 + }, + { + "epoch": 1.02, + "learning_rate": 1.5071021768740465e-05, + "loss": 3.393, + "step": 2133504 + }, + { + "epoch": 1.02, + "learning_rate": 1.5062635821229945e-05, + "loss": 3.3934, + "step": 2134016 + }, + { + "epoch": 1.02, + "learning_rate": 1.5054249873719423e-05, + "loss": 3.3902, + "step": 2134528 + }, + { + "epoch": 1.02, + "learning_rate": 1.5045863926208903e-05, + "loss": 3.3926, + "step": 2135040 + }, + { + "epoch": 1.02, + "learning_rate": 1.5037477978698383e-05, + "loss": 3.392, + "step": 2135552 + }, + { + "epoch": 1.02, + "learning_rate": 1.5029092031187863e-05, + "loss": 3.399, + "step": 2136064 + }, + { + "epoch": 1.02, + "learning_rate": 1.5020706083677344e-05, + "loss": 3.3884, + "step": 2136576 + }, + { + "epoch": 1.03, + "eval_loss": 3.8521366119384766, + "eval_runtime": 305.5138, + "eval_samples_per_second": 1249.014, + "eval_steps_per_second": 39.033, + "step": 2136951 + }, + { + "epoch": 0.0, + "learning_rate": 1.5012336514970554e-05, + "loss": 3.3817, + "step": 2137088 + }, + { + "epoch": 0.0, + "learning_rate": 1.5003950567460035e-05, + "loss": 3.3825, + "step": 2137600 + }, + { + "epoch": 0.0, + "learning_rate": 1.4995564619949515e-05, + "loss": 3.3924, + "step": 2138112 + }, + { + "epoch": 0.0, + "learning_rate": 1.4987195051242724e-05, + "loss": 3.3964, + "step": 2138624 + }, + { + "epoch": 0.0, + "learning_rate": 1.4978809103732206e-05, + "loss": 3.3988, + "step": 2139136 + }, + { + "epoch": 0.0, + "learning_rate": 1.4970423156221686e-05, + "loss": 3.3849, + "step": 2139648 + }, + { + "epoch": 0.0, + "learning_rate": 1.4962037208711166e-05, + "loss": 3.3921, + "step": 2140160 + }, + { + "epoch": 0.0, + "learning_rate": 1.4953651261200646e-05, + "loss": 3.3899, + "step": 2140672 + }, + { + "epoch": 0.0, + "learning_rate": 1.4945265313690127e-05, + "loss": 3.3844, + "step": 2141184 + }, + { + "epoch": 0.0, + "learning_rate": 1.4936879366179604e-05, + "loss": 3.3768, + "step": 2141696 + }, + { + "epoch": 0.0, + "learning_rate": 1.4928493418669084e-05, + "loss": 3.3982, + "step": 2142208 + }, + { + "epoch": 0.0, + "learning_rate": 1.4920123849962298e-05, + "loss": 3.4009, + "step": 2142720 + }, + { + "epoch": 0.0, + "learning_rate": 1.4911754281255507e-05, + "loss": 3.3959, + "step": 2143232 + }, + { + "epoch": 0.0, + "learning_rate": 1.4903368333744989e-05, + "loss": 3.3712, + "step": 2143744 + }, + { + "epoch": 0.0, + "learning_rate": 1.4894982386234469e-05, + "loss": 3.3898, + "step": 2144256 + }, + { + "epoch": 0.0, + "learning_rate": 1.4886596438723949e-05, + "loss": 3.3734, + "step": 2144768 + }, + { + "epoch": 0.0, + "learning_rate": 1.4878210491213429e-05, + "loss": 3.3878, + "step": 2145280 + }, + { + "epoch": 0.0, + "learning_rate": 1.4869824543702907e-05, + "loss": 3.3866, + "step": 2145792 + }, + { + "epoch": 0.0, + "learning_rate": 1.4861438596192387e-05, + "loss": 3.3834, + "step": 2146304 + }, + { + "epoch": 0.0, + "learning_rate": 1.4853052648681867e-05, + "loss": 3.3908, + "step": 2146816 + }, + { + "epoch": 0.0, + "learning_rate": 1.4844683079975078e-05, + "loss": 3.3979, + "step": 2147328 + }, + { + "epoch": 0.0, + "learning_rate": 1.4836297132464558e-05, + "loss": 3.3874, + "step": 2147840 + }, + { + "epoch": 0.0, + "learning_rate": 1.4827911184954038e-05, + "loss": 3.3871, + "step": 2148352 + }, + { + "epoch": 0.0, + "learning_rate": 1.4819525237443518e-05, + "loss": 3.383, + "step": 2148864 + }, + { + "epoch": 0.0, + "learning_rate": 1.4811155668736728e-05, + "loss": 3.3927, + "step": 2149376 + }, + { + "epoch": 0.0, + "learning_rate": 1.4802769721226208e-05, + "loss": 3.3902, + "step": 2149888 + }, + { + "epoch": 0.0, + "learning_rate": 1.479438377371569e-05, + "loss": 3.3819, + "step": 2150400 + }, + { + "epoch": 0.0, + "learning_rate": 1.478599782620517e-05, + "loss": 3.3884, + "step": 2150912 + }, + { + "epoch": 0.0, + "learning_rate": 1.4777628257498379e-05, + "loss": 3.3848, + "step": 2151424 + }, + { + "epoch": 0.0, + "learning_rate": 1.476924230998786e-05, + "loss": 3.3832, + "step": 2151936 + }, + { + "epoch": 0.01, + "learning_rate": 1.476085636247734e-05, + "loss": 3.3849, + "step": 2152448 + }, + { + "epoch": 0.01, + "learning_rate": 1.475247041496682e-05, + "loss": 3.3918, + "step": 2152960 + }, + { + "epoch": 0.01, + "learning_rate": 1.47440844674563e-05, + "loss": 3.3863, + "step": 2153472 + }, + { + "epoch": 0.01, + "learning_rate": 1.4735698519945782e-05, + "loss": 3.396, + "step": 2153984 + }, + { + "epoch": 0.01, + "learning_rate": 1.4727312572435259e-05, + "loss": 3.3844, + "step": 2154496 + }, + { + "epoch": 0.01, + "learning_rate": 1.4718926624924739e-05, + "loss": 3.3825, + "step": 2155008 + }, + { + "epoch": 0.01, + "learning_rate": 1.4710557056217953e-05, + "loss": 3.3958, + "step": 2155520 + }, + { + "epoch": 0.01, + "learning_rate": 1.4702171108707433e-05, + "loss": 3.3783, + "step": 2156032 + }, + { + "epoch": 0.01, + "learning_rate": 1.469378516119691e-05, + "loss": 3.3812, + "step": 2156544 + }, + { + "epoch": 0.01, + "learning_rate": 1.4685399213686391e-05, + "loss": 3.3833, + "step": 2157056 + }, + { + "epoch": 0.01, + "learning_rate": 1.4677046023783333e-05, + "loss": 3.3848, + "step": 2157568 + }, + { + "epoch": 0.01, + "learning_rate": 1.4668660076272814e-05, + "loss": 3.3831, + "step": 2158080 + }, + { + "epoch": 0.01, + "learning_rate": 1.4660274128762294e-05, + "loss": 3.3831, + "step": 2158592 + }, + { + "epoch": 0.01, + "learning_rate": 1.4651888181251774e-05, + "loss": 3.3858, + "step": 2159104 + }, + { + "epoch": 0.01, + "learning_rate": 1.4643502233741254e-05, + "loss": 3.3889, + "step": 2159616 + }, + { + "epoch": 0.01, + "learning_rate": 1.4635116286230732e-05, + "loss": 3.3926, + "step": 2160128 + }, + { + "epoch": 0.01, + "learning_rate": 1.4626730338720212e-05, + "loss": 3.3896, + "step": 2160640 + }, + { + "epoch": 0.01, + "learning_rate": 1.4618344391209692e-05, + "loss": 3.3868, + "step": 2161152 + }, + { + "epoch": 0.01, + "learning_rate": 1.4609974822502907e-05, + "loss": 3.366, + "step": 2161664 + }, + { + "epoch": 0.01, + "learning_rate": 1.4601588874992383e-05, + "loss": 3.3929, + "step": 2162176 + }, + { + "epoch": 0.01, + "learning_rate": 1.4593202927481863e-05, + "loss": 3.3827, + "step": 2162688 + }, + { + "epoch": 0.01, + "learning_rate": 1.4584816979971345e-05, + "loss": 3.3832, + "step": 2163200 + }, + { + "epoch": 0.01, + "learning_rate": 1.4576447411264554e-05, + "loss": 3.3853, + "step": 2163712 + }, + { + "epoch": 0.01, + "learning_rate": 1.4568077842557768e-05, + "loss": 3.3811, + "step": 2164224 + }, + { + "epoch": 0.01, + "learning_rate": 1.4559691895047248e-05, + "loss": 3.3676, + "step": 2164736 + }, + { + "epoch": 0.01, + "learning_rate": 1.4551305947536728e-05, + "loss": 3.3757, + "step": 2165248 + }, + { + "epoch": 0.01, + "learning_rate": 1.4542920000026206e-05, + "loss": 3.3834, + "step": 2165760 + }, + { + "epoch": 0.01, + "learning_rate": 1.4534534052515686e-05, + "loss": 3.3749, + "step": 2166272 + }, + { + "epoch": 0.01, + "learning_rate": 1.4526148105005166e-05, + "loss": 3.3934, + "step": 2166784 + }, + { + "epoch": 0.01, + "learning_rate": 1.4517762157494646e-05, + "loss": 3.3841, + "step": 2167296 + }, + { + "epoch": 0.01, + "learning_rate": 1.4509376209984126e-05, + "loss": 3.37, + "step": 2167808 + }, + { + "epoch": 0.01, + "learning_rate": 1.4501006641277337e-05, + "loss": 3.397, + "step": 2168320 + }, + { + "epoch": 0.01, + "learning_rate": 1.4492620693766817e-05, + "loss": 3.3731, + "step": 2168832 + }, + { + "epoch": 0.01, + "learning_rate": 1.4484234746256298e-05, + "loss": 3.3694, + "step": 2169344 + }, + { + "epoch": 0.01, + "learning_rate": 1.4475848798745778e-05, + "loss": 3.3838, + "step": 2169856 + }, + { + "epoch": 0.01, + "learning_rate": 1.446747923003899e-05, + "loss": 3.3801, + "step": 2170368 + }, + { + "epoch": 0.01, + "learning_rate": 1.4459109661332202e-05, + "loss": 3.3727, + "step": 2170880 + }, + { + "epoch": 0.01, + "learning_rate": 1.4450723713821678e-05, + "loss": 3.3797, + "step": 2171392 + }, + { + "epoch": 0.01, + "learning_rate": 1.444233776631116e-05, + "loss": 3.3713, + "step": 2171904 + }, + { + "epoch": 0.01, + "learning_rate": 1.443395181880064e-05, + "loss": 3.3707, + "step": 2172416 + }, + { + "epoch": 0.01, + "learning_rate": 1.442556587129012e-05, + "loss": 3.3913, + "step": 2172928 + }, + { + "epoch": 0.01, + "learning_rate": 1.44171799237796e-05, + "loss": 3.3816, + "step": 2173440 + }, + { + "epoch": 0.01, + "learning_rate": 1.440879397626908e-05, + "loss": 3.3911, + "step": 2173952 + }, + { + "epoch": 0.01, + "learning_rate": 1.4400408028758561e-05, + "loss": 3.3832, + "step": 2174464 + }, + { + "epoch": 0.01, + "learning_rate": 1.439203846005177e-05, + "loss": 3.3961, + "step": 2174976 + }, + { + "epoch": 0.01, + "learning_rate": 1.4383652512541252e-05, + "loss": 3.3751, + "step": 2175488 + }, + { + "epoch": 0.01, + "learning_rate": 1.4375266565030732e-05, + "loss": 3.3964, + "step": 2176000 + }, + { + "epoch": 0.01, + "learning_rate": 1.4366880617520209e-05, + "loss": 3.3805, + "step": 2176512 + }, + { + "epoch": 0.01, + "learning_rate": 1.4358511048813423e-05, + "loss": 3.3748, + "step": 2177024 + }, + { + "epoch": 0.01, + "learning_rate": 1.4350141480106632e-05, + "loss": 3.3886, + "step": 2177536 + }, + { + "epoch": 0.01, + "learning_rate": 1.4341755532596114e-05, + "loss": 3.3932, + "step": 2178048 + }, + { + "epoch": 0.01, + "learning_rate": 1.4333369585085593e-05, + "loss": 3.3846, + "step": 2178560 + }, + { + "epoch": 0.01, + "learning_rate": 1.4324983637575073e-05, + "loss": 3.3925, + "step": 2179072 + }, + { + "epoch": 0.01, + "learning_rate": 1.4316597690064553e-05, + "loss": 3.3684, + "step": 2179584 + }, + { + "epoch": 0.01, + "learning_rate": 1.4308211742554033e-05, + "loss": 3.3627, + "step": 2180096 + }, + { + "epoch": 0.01, + "learning_rate": 1.4299825795043512e-05, + "loss": 3.3759, + "step": 2180608 + }, + { + "epoch": 0.01, + "learning_rate": 1.4291456226336724e-05, + "loss": 3.3863, + "step": 2181120 + }, + { + "epoch": 0.01, + "learning_rate": 1.4283070278826206e-05, + "loss": 3.3824, + "step": 2181632 + }, + { + "epoch": 0.01, + "learning_rate": 1.4274684331315682e-05, + "loss": 3.3763, + "step": 2182144 + }, + { + "epoch": 0.01, + "learning_rate": 1.4266298383805162e-05, + "loss": 3.3782, + "step": 2182656 + }, + { + "epoch": 0.02, + "learning_rate": 1.4257912436294644e-05, + "loss": 3.381, + "step": 2183168 + }, + { + "epoch": 0.02, + "learning_rate": 1.4249542867587856e-05, + "loss": 3.3761, + "step": 2183680 + }, + { + "epoch": 0.02, + "learning_rate": 1.4241156920077333e-05, + "loss": 3.3781, + "step": 2184192 + }, + { + "epoch": 0.02, + "learning_rate": 1.4232770972566815e-05, + "loss": 3.3899, + "step": 2184704 + }, + { + "epoch": 0.02, + "learning_rate": 1.4224385025056295e-05, + "loss": 3.3947, + "step": 2185216 + }, + { + "epoch": 0.02, + "learning_rate": 1.4215999077545775e-05, + "loss": 3.3906, + "step": 2185728 + }, + { + "epoch": 0.02, + "learning_rate": 1.4207613130035254e-05, + "loss": 3.3763, + "step": 2186240 + }, + { + "epoch": 0.02, + "learning_rate": 1.4199227182524734e-05, + "loss": 3.3834, + "step": 2186752 + }, + { + "epoch": 0.02, + "learning_rate": 1.4190857613817945e-05, + "loss": 3.3801, + "step": 2187264 + }, + { + "epoch": 0.02, + "learning_rate": 1.4182471666307425e-05, + "loss": 3.3888, + "step": 2187776 + }, + { + "epoch": 0.02, + "learning_rate": 1.4174085718796907e-05, + "loss": 3.383, + "step": 2188288 + }, + { + "epoch": 0.02, + "learning_rate": 1.4165699771286387e-05, + "loss": 3.3802, + "step": 2188800 + }, + { + "epoch": 0.02, + "learning_rate": 1.4157330202579598e-05, + "loss": 3.3807, + "step": 2189312 + }, + { + "epoch": 0.02, + "learning_rate": 1.4148944255069078e-05, + "loss": 3.3822, + "step": 2189824 + }, + { + "epoch": 0.02, + "learning_rate": 1.4140558307558557e-05, + "loss": 3.3849, + "step": 2190336 + }, + { + "epoch": 0.02, + "learning_rate": 1.4132172360048037e-05, + "loss": 3.3801, + "step": 2190848 + }, + { + "epoch": 0.02, + "learning_rate": 1.4123802791341248e-05, + "loss": 3.3771, + "step": 2191360 + }, + { + "epoch": 0.02, + "learning_rate": 1.4115416843830728e-05, + "loss": 3.3732, + "step": 2191872 + }, + { + "epoch": 0.02, + "learning_rate": 1.4107030896320208e-05, + "loss": 3.379, + "step": 2192384 + }, + { + "epoch": 0.02, + "learning_rate": 1.4098644948809686e-05, + "loss": 3.3749, + "step": 2192896 + }, + { + "epoch": 0.02, + "learning_rate": 1.4090275380102899e-05, + "loss": 3.3728, + "step": 2193408 + }, + { + "epoch": 0.02, + "learning_rate": 1.4081889432592379e-05, + "loss": 3.3757, + "step": 2193920 + }, + { + "epoch": 0.02, + "learning_rate": 1.407350348508186e-05, + "loss": 3.3819, + "step": 2194432 + }, + { + "epoch": 0.02, + "learning_rate": 1.4065117537571337e-05, + "loss": 3.3694, + "step": 2194944 + }, + { + "epoch": 0.02, + "learning_rate": 1.405674796886455e-05, + "loss": 3.3889, + "step": 2195456 + }, + { + "epoch": 0.02, + "learning_rate": 1.404837840015776e-05, + "loss": 3.3994, + "step": 2195968 + }, + { + "epoch": 0.02, + "learning_rate": 1.403999245264724e-05, + "loss": 3.3857, + "step": 2196480 + }, + { + "epoch": 0.02, + "learning_rate": 1.4031606505136722e-05, + "loss": 3.3882, + "step": 2196992 + }, + { + "epoch": 0.02, + "learning_rate": 1.4023220557626202e-05, + "loss": 3.3808, + "step": 2197504 + }, + { + "epoch": 0.02, + "learning_rate": 1.4014850988919411e-05, + "loss": 3.3798, + "step": 2198016 + }, + { + "epoch": 0.02, + "learning_rate": 1.4006465041408893e-05, + "loss": 3.3804, + "step": 2198528 + }, + { + "epoch": 0.02, + "learning_rate": 1.3998079093898373e-05, + "loss": 3.3617, + "step": 2199040 + }, + { + "epoch": 0.02, + "learning_rate": 1.3989693146387853e-05, + "loss": 3.3836, + "step": 2199552 + }, + { + "epoch": 0.02, + "learning_rate": 1.3981307198877333e-05, + "loss": 3.3801, + "step": 2200064 + }, + { + "epoch": 0.02, + "learning_rate": 1.397292125136681e-05, + "loss": 3.3831, + "step": 2200576 + }, + { + "epoch": 0.02, + "learning_rate": 1.3964551682660023e-05, + "loss": 3.3773, + "step": 2201088 + }, + { + "epoch": 0.02, + "learning_rate": 1.3956165735149503e-05, + "loss": 3.3862, + "step": 2201600 + }, + { + "epoch": 0.02, + "learning_rate": 1.3947779787638985e-05, + "loss": 3.3766, + "step": 2202112 + }, + { + "epoch": 0.02, + "learning_rate": 1.3939393840128461e-05, + "loss": 3.3762, + "step": 2202624 + }, + { + "epoch": 0.02, + "learning_rate": 1.3931007892617941e-05, + "loss": 3.3875, + "step": 2203136 + }, + { + "epoch": 0.02, + "learning_rate": 1.3922621945107423e-05, + "loss": 3.3855, + "step": 2203648 + }, + { + "epoch": 0.02, + "learning_rate": 1.3914235997596903e-05, + "loss": 3.394, + "step": 2204160 + }, + { + "epoch": 0.02, + "learning_rate": 1.3905850050086383e-05, + "loss": 3.3778, + "step": 2204672 + }, + { + "epoch": 0.02, + "learning_rate": 1.3897480481379594e-05, + "loss": 3.393, + "step": 2205184 + }, + { + "epoch": 0.02, + "learning_rate": 1.3889094533869074e-05, + "loss": 3.3816, + "step": 2205696 + }, + { + "epoch": 0.02, + "learning_rate": 1.3880708586358554e-05, + "loss": 3.3852, + "step": 2206208 + }, + { + "epoch": 0.02, + "learning_rate": 1.3872322638848034e-05, + "loss": 3.3873, + "step": 2206720 + }, + { + "epoch": 0.02, + "learning_rate": 1.3863953070141244e-05, + "loss": 3.3769, + "step": 2207232 + }, + { + "epoch": 0.02, + "learning_rate": 1.3855567122630724e-05, + "loss": 3.3738, + "step": 2207744 + }, + { + "epoch": 0.02, + "learning_rate": 1.3847181175120206e-05, + "loss": 3.3939, + "step": 2208256 + }, + { + "epoch": 0.02, + "learning_rate": 1.3838795227609686e-05, + "loss": 3.3733, + "step": 2208768 + }, + { + "epoch": 0.02, + "learning_rate": 1.3830425658902895e-05, + "loss": 3.3833, + "step": 2209280 + }, + { + "epoch": 0.02, + "learning_rate": 1.3822039711392377e-05, + "loss": 3.3846, + "step": 2209792 + }, + { + "epoch": 0.02, + "learning_rate": 1.3813653763881857e-05, + "loss": 3.3849, + "step": 2210304 + }, + { + "epoch": 0.02, + "learning_rate": 1.3805284195175067e-05, + "loss": 3.3837, + "step": 2210816 + }, + { + "epoch": 0.02, + "learning_rate": 1.3796898247664547e-05, + "loss": 3.3796, + "step": 2211328 + }, + { + "epoch": 0.02, + "learning_rate": 1.3788512300154027e-05, + "loss": 3.3845, + "step": 2211840 + }, + { + "epoch": 0.02, + "learning_rate": 1.3780126352643507e-05, + "loss": 3.3838, + "step": 2212352 + }, + { + "epoch": 0.02, + "learning_rate": 1.3771740405132987e-05, + "loss": 3.3802, + "step": 2212864 + }, + { + "epoch": 0.03, + "eval_loss": 3.8546574115753174, + "eval_runtime": 305.7532, + "eval_samples_per_second": 1248.036, + "eval_steps_per_second": 39.002, + "step": 2213271 + }, + { + "epoch": 1.0, + "learning_rate": 1.3763354457622466e-05, + "loss": 3.3764, + "step": 2213376 + }, + { + "epoch": 1.0, + "learning_rate": 1.3754968510111945e-05, + "loss": 3.369, + "step": 2213888 + }, + { + "epoch": 1.0, + "learning_rate": 1.3746582562601425e-05, + "loss": 3.3807, + "step": 2214400 + }, + { + "epoch": 1.0, + "learning_rate": 1.373821299389464e-05, + "loss": 3.3914, + "step": 2214912 + }, + { + "epoch": 1.0, + "learning_rate": 1.3729827046384116e-05, + "loss": 3.383, + "step": 2215424 + }, + { + "epoch": 1.0, + "learning_rate": 1.3721441098873596e-05, + "loss": 3.3807, + "step": 2215936 + }, + { + "epoch": 1.0, + "learning_rate": 1.3713055151363078e-05, + "loss": 3.3812, + "step": 2216448 + }, + { + "epoch": 1.0, + "learning_rate": 1.3704669203852558e-05, + "loss": 3.3798, + "step": 2216960 + }, + { + "epoch": 1.0, + "learning_rate": 1.3696283256342038e-05, + "loss": 3.3701, + "step": 2217472 + }, + { + "epoch": 1.0, + "learning_rate": 1.3687897308831518e-05, + "loss": 3.3729, + "step": 2217984 + }, + { + "epoch": 1.0, + "learning_rate": 1.3679511361320996e-05, + "loss": 3.3861, + "step": 2218496 + }, + { + "epoch": 1.0, + "learning_rate": 1.3671141792614208e-05, + "loss": 3.3894, + "step": 2219008 + }, + { + "epoch": 1.0, + "learning_rate": 1.366277222390742e-05, + "loss": 3.3906, + "step": 2219520 + }, + { + "epoch": 1.0, + "learning_rate": 1.36543862763969e-05, + "loss": 3.3583, + "step": 2220032 + }, + { + "epoch": 1.0, + "learning_rate": 1.3646000328886379e-05, + "loss": 3.3787, + "step": 2220544 + }, + { + "epoch": 1.0, + "learning_rate": 1.363761438137586e-05, + "loss": 3.3653, + "step": 2221056 + }, + { + "epoch": 1.0, + "learning_rate": 1.362922843386534e-05, + "loss": 3.3785, + "step": 2221568 + }, + { + "epoch": 1.0, + "learning_rate": 1.362084248635482e-05, + "loss": 3.3769, + "step": 2222080 + }, + { + "epoch": 1.0, + "learning_rate": 1.3612456538844299e-05, + "loss": 3.3724, + "step": 2222592 + }, + { + "epoch": 1.0, + "learning_rate": 1.3604070591333779e-05, + "loss": 3.3791, + "step": 2223104 + }, + { + "epoch": 1.0, + "learning_rate": 1.3595701022626991e-05, + "loss": 3.3926, + "step": 2223616 + }, + { + "epoch": 1.0, + "learning_rate": 1.358731507511647e-05, + "loss": 3.3782, + "step": 2224128 + }, + { + "epoch": 1.0, + "learning_rate": 1.357892912760595e-05, + "loss": 3.3733, + "step": 2224640 + }, + { + "epoch": 1.0, + "learning_rate": 1.357054318009543e-05, + "loss": 3.3753, + "step": 2225152 + }, + { + "epoch": 1.0, + "learning_rate": 1.3562173611388642e-05, + "loss": 3.3851, + "step": 2225664 + }, + { + "epoch": 1.0, + "learning_rate": 1.355378766387812e-05, + "loss": 3.3795, + "step": 2226176 + }, + { + "epoch": 1.0, + "learning_rate": 1.35454017163676e-05, + "loss": 3.3722, + "step": 2226688 + }, + { + "epoch": 1.0, + "learning_rate": 1.353701576885708e-05, + "loss": 3.38, + "step": 2227200 + }, + { + "epoch": 1.0, + "learning_rate": 1.3528646200150294e-05, + "loss": 3.3719, + "step": 2227712 + }, + { + "epoch": 1.0, + "learning_rate": 1.3520260252639771e-05, + "loss": 3.3711, + "step": 2228224 + }, + { + "epoch": 1.01, + "learning_rate": 1.3511874305129253e-05, + "loss": 3.3777, + "step": 2228736 + }, + { + "epoch": 1.01, + "learning_rate": 1.3503488357618733e-05, + "loss": 3.3795, + "step": 2229248 + }, + { + "epoch": 1.01, + "learning_rate": 1.3495102410108213e-05, + "loss": 3.3759, + "step": 2229760 + }, + { + "epoch": 1.01, + "learning_rate": 1.3486716462597692e-05, + "loss": 3.3844, + "step": 2230272 + }, + { + "epoch": 1.01, + "learning_rate": 1.3478330515087172e-05, + "loss": 3.3773, + "step": 2230784 + }, + { + "epoch": 1.01, + "learning_rate": 1.346994456757665e-05, + "loss": 3.3737, + "step": 2231296 + }, + { + "epoch": 1.01, + "learning_rate": 1.3461574998869863e-05, + "loss": 3.3856, + "step": 2231808 + }, + { + "epoch": 1.01, + "learning_rate": 1.3453189051359343e-05, + "loss": 3.3655, + "step": 2232320 + }, + { + "epoch": 1.01, + "learning_rate": 1.3444803103848825e-05, + "loss": 3.3711, + "step": 2232832 + }, + { + "epoch": 1.01, + "learning_rate": 1.3436417156338301e-05, + "loss": 3.375, + "step": 2233344 + }, + { + "epoch": 1.01, + "learning_rate": 1.3428063966435245e-05, + "loss": 3.3719, + "step": 2233856 + }, + { + "epoch": 1.01, + "learning_rate": 1.3419678018924725e-05, + "loss": 3.3729, + "step": 2234368 + }, + { + "epoch": 1.01, + "learning_rate": 1.3411292071414205e-05, + "loss": 3.3782, + "step": 2234880 + }, + { + "epoch": 1.01, + "learning_rate": 1.3402906123903686e-05, + "loss": 3.3794, + "step": 2235392 + }, + { + "epoch": 1.01, + "learning_rate": 1.3394520176393166e-05, + "loss": 3.3791, + "step": 2235904 + }, + { + "epoch": 1.01, + "learning_rate": 1.3386134228882646e-05, + "loss": 3.3806, + "step": 2236416 + }, + { + "epoch": 1.01, + "learning_rate": 1.3377748281372124e-05, + "loss": 3.3807, + "step": 2236928 + }, + { + "epoch": 1.01, + "learning_rate": 1.3369362333861604e-05, + "loss": 3.3765, + "step": 2237440 + }, + { + "epoch": 1.01, + "learning_rate": 1.3360992765154817e-05, + "loss": 3.3586, + "step": 2237952 + }, + { + "epoch": 1.01, + "learning_rate": 1.3352606817644297e-05, + "loss": 3.381, + "step": 2238464 + }, + { + "epoch": 1.01, + "learning_rate": 1.3344237248937508e-05, + "loss": 3.3773, + "step": 2238976 + }, + { + "epoch": 1.01, + "learning_rate": 1.3335851301426988e-05, + "loss": 3.3763, + "step": 2239488 + }, + { + "epoch": 1.01, + "learning_rate": 1.332746535391647e-05, + "loss": 3.3739, + "step": 2240000 + }, + { + "epoch": 1.01, + "learning_rate": 1.3319079406405946e-05, + "loss": 3.3659, + "step": 2240512 + }, + { + "epoch": 1.01, + "learning_rate": 1.3310693458895426e-05, + "loss": 3.3607, + "step": 2241024 + }, + { + "epoch": 1.01, + "learning_rate": 1.3302307511384907e-05, + "loss": 3.3657, + "step": 2241536 + }, + { + "epoch": 1.01, + "learning_rate": 1.329393794267812e-05, + "loss": 3.3758, + "step": 2242048 + }, + { + "epoch": 1.01, + "learning_rate": 1.3285551995167596e-05, + "loss": 3.3615, + "step": 2242560 + }, + { + "epoch": 1.01, + "learning_rate": 1.3277166047657078e-05, + "loss": 3.3849, + "step": 2243072 + }, + { + "epoch": 1.01, + "learning_rate": 1.3268780100146558e-05, + "loss": 3.378, + "step": 2243584 + }, + { + "epoch": 1.01, + "learning_rate": 1.3260394152636038e-05, + "loss": 3.3564, + "step": 2244096 + }, + { + "epoch": 1.01, + "learning_rate": 1.3252008205125518e-05, + "loss": 3.3857, + "step": 2244608 + }, + { + "epoch": 1.01, + "learning_rate": 1.3243622257615e-05, + "loss": 3.365, + "step": 2245120 + }, + { + "epoch": 1.01, + "learning_rate": 1.3235252688908209e-05, + "loss": 3.364, + "step": 2245632 + }, + { + "epoch": 1.01, + "learning_rate": 1.3226866741397689e-05, + "loss": 3.3699, + "step": 2246144 + }, + { + "epoch": 1.01, + "learning_rate": 1.321848079388717e-05, + "loss": 3.3756, + "step": 2246656 + }, + { + "epoch": 1.01, + "learning_rate": 1.321009484637665e-05, + "loss": 3.3608, + "step": 2247168 + }, + { + "epoch": 1.01, + "learning_rate": 1.3201708898866127e-05, + "loss": 3.3726, + "step": 2247680 + }, + { + "epoch": 1.01, + "learning_rate": 1.3193322951355608e-05, + "loss": 3.3585, + "step": 2248192 + }, + { + "epoch": 1.01, + "learning_rate": 1.3184937003845088e-05, + "loss": 3.3632, + "step": 2248704 + }, + { + "epoch": 1.01, + "learning_rate": 1.3176551056334568e-05, + "loss": 3.382, + "step": 2249216 + }, + { + "epoch": 1.01, + "learning_rate": 1.316818148762778e-05, + "loss": 3.3698, + "step": 2249728 + }, + { + "epoch": 1.01, + "learning_rate": 1.3159795540117259e-05, + "loss": 3.3797, + "step": 2250240 + }, + { + "epoch": 1.01, + "learning_rate": 1.3151409592606739e-05, + "loss": 3.3706, + "step": 2250752 + }, + { + "epoch": 1.01, + "learning_rate": 1.3143023645096219e-05, + "loss": 3.3878, + "step": 2251264 + }, + { + "epoch": 1.01, + "learning_rate": 1.313465407638943e-05, + "loss": 3.3636, + "step": 2251776 + }, + { + "epoch": 1.01, + "learning_rate": 1.3126284507682642e-05, + "loss": 3.3861, + "step": 2252288 + }, + { + "epoch": 1.01, + "learning_rate": 1.3117898560172124e-05, + "loss": 3.3705, + "step": 2252800 + }, + { + "epoch": 1.01, + "learning_rate": 1.31095126126616e-05, + "loss": 3.3684, + "step": 2253312 + }, + { + "epoch": 1.01, + "learning_rate": 1.310112666515108e-05, + "loss": 3.3779, + "step": 2253824 + }, + { + "epoch": 1.01, + "learning_rate": 1.3092740717640562e-05, + "loss": 3.3849, + "step": 2254336 + }, + { + "epoch": 1.01, + "learning_rate": 1.3084371148933775e-05, + "loss": 3.3691, + "step": 2254848 + }, + { + "epoch": 1.01, + "learning_rate": 1.3075985201423251e-05, + "loss": 3.3841, + "step": 2255360 + }, + { + "epoch": 1.01, + "learning_rate": 1.3067599253912733e-05, + "loss": 3.3574, + "step": 2255872 + }, + { + "epoch": 1.01, + "learning_rate": 1.3059213306402213e-05, + "loss": 3.3566, + "step": 2256384 + }, + { + "epoch": 1.01, + "learning_rate": 1.3050827358891693e-05, + "loss": 3.3661, + "step": 2256896 + }, + { + "epoch": 1.01, + "learning_rate": 1.3042457790184904e-05, + "loss": 3.3736, + "step": 2257408 + }, + { + "epoch": 1.01, + "learning_rate": 1.3034071842674383e-05, + "loss": 3.3701, + "step": 2257920 + }, + { + "epoch": 1.01, + "learning_rate": 1.3025685895163863e-05, + "loss": 3.3701, + "step": 2258432 + }, + { + "epoch": 1.01, + "learning_rate": 1.3017299947653343e-05, + "loss": 3.3684, + "step": 2258944 + }, + { + "epoch": 1.02, + "learning_rate": 1.3008914000142825e-05, + "loss": 3.3695, + "step": 2259456 + }, + { + "epoch": 1.02, + "learning_rate": 1.3000544431436034e-05, + "loss": 3.3708, + "step": 2259968 + }, + { + "epoch": 1.02, + "learning_rate": 1.2992158483925516e-05, + "loss": 3.3667, + "step": 2260480 + }, + { + "epoch": 1.02, + "learning_rate": 1.2983772536414996e-05, + "loss": 3.3757, + "step": 2260992 + }, + { + "epoch": 1.02, + "learning_rate": 1.2975386588904476e-05, + "loss": 3.3869, + "step": 2261504 + }, + { + "epoch": 1.02, + "learning_rate": 1.2967000641393956e-05, + "loss": 3.383, + "step": 2262016 + }, + { + "epoch": 1.02, + "learning_rate": 1.2958614693883434e-05, + "loss": 3.3636, + "step": 2262528 + }, + { + "epoch": 1.02, + "learning_rate": 1.2950228746372914e-05, + "loss": 3.3728, + "step": 2263040 + }, + { + "epoch": 1.02, + "learning_rate": 1.2941842798862394e-05, + "loss": 3.3718, + "step": 2263552 + }, + { + "epoch": 1.02, + "learning_rate": 1.2933473230155608e-05, + "loss": 3.3796, + "step": 2264064 + }, + { + "epoch": 1.02, + "learning_rate": 1.2925087282645085e-05, + "loss": 3.371, + "step": 2264576 + }, + { + "epoch": 1.02, + "learning_rate": 1.2916701335134565e-05, + "loss": 3.3713, + "step": 2265088 + }, + { + "epoch": 1.02, + "learning_rate": 1.2908331766427779e-05, + "loss": 3.3732, + "step": 2265600 + }, + { + "epoch": 1.02, + "learning_rate": 1.2899945818917255e-05, + "loss": 3.3754, + "step": 2266112 + }, + { + "epoch": 1.02, + "learning_rate": 1.2891559871406735e-05, + "loss": 3.3712, + "step": 2266624 + }, + { + "epoch": 1.02, + "learning_rate": 1.2883173923896217e-05, + "loss": 3.3706, + "step": 2267136 + }, + { + "epoch": 1.02, + "learning_rate": 1.287480435518943e-05, + "loss": 3.3682, + "step": 2267648 + }, + { + "epoch": 1.02, + "learning_rate": 1.2866418407678908e-05, + "loss": 3.3623, + "step": 2268160 + }, + { + "epoch": 1.02, + "learning_rate": 1.2858032460168388e-05, + "loss": 3.369, + "step": 2268672 + }, + { + "epoch": 1.02, + "learning_rate": 1.2849646512657868e-05, + "loss": 3.3654, + "step": 2269184 + }, + { + "epoch": 1.02, + "learning_rate": 1.2841276943951078e-05, + "loss": 3.3658, + "step": 2269696 + }, + { + "epoch": 1.02, + "learning_rate": 1.2832890996440558e-05, + "loss": 3.3663, + "step": 2270208 + }, + { + "epoch": 1.02, + "learning_rate": 1.2824505048930038e-05, + "loss": 3.3738, + "step": 2270720 + }, + { + "epoch": 1.02, + "learning_rate": 1.2816119101419518e-05, + "loss": 3.3646, + "step": 2271232 + }, + { + "epoch": 1.02, + "learning_rate": 1.2807749532712729e-05, + "loss": 3.3767, + "step": 2271744 + }, + { + "epoch": 1.02, + "learning_rate": 1.2799379964005941e-05, + "loss": 3.3857, + "step": 2272256 + }, + { + "epoch": 1.02, + "learning_rate": 1.2790994016495423e-05, + "loss": 3.3772, + "step": 2272768 + }, + { + "epoch": 1.02, + "learning_rate": 1.2782608068984903e-05, + "loss": 3.3784, + "step": 2273280 + }, + { + "epoch": 1.02, + "learning_rate": 1.277422212147438e-05, + "loss": 3.3739, + "step": 2273792 + }, + { + "epoch": 1.02, + "learning_rate": 1.2765852552767594e-05, + "loss": 3.369, + "step": 2274304 + }, + { + "epoch": 1.02, + "learning_rate": 1.2757466605257074e-05, + "loss": 3.3723, + "step": 2274816 + }, + { + "epoch": 1.02, + "learning_rate": 1.274908065774655e-05, + "loss": 3.3569, + "step": 2275328 + }, + { + "epoch": 1.02, + "learning_rate": 1.2740694710236032e-05, + "loss": 3.3719, + "step": 2275840 + }, + { + "epoch": 1.02, + "learning_rate": 1.2732308762725512e-05, + "loss": 3.3653, + "step": 2276352 + }, + { + "epoch": 1.02, + "learning_rate": 1.2723922815214992e-05, + "loss": 3.3762, + "step": 2276864 + }, + { + "epoch": 1.02, + "learning_rate": 1.2715553246508203e-05, + "loss": 3.3735, + "step": 2277376 + }, + { + "epoch": 1.02, + "learning_rate": 1.2707167298997683e-05, + "loss": 3.3715, + "step": 2277888 + }, + { + "epoch": 1.02, + "learning_rate": 1.2698781351487163e-05, + "loss": 3.3642, + "step": 2278400 + }, + { + "epoch": 1.02, + "learning_rate": 1.2690395403976643e-05, + "loss": 3.3668, + "step": 2278912 + }, + { + "epoch": 1.02, + "learning_rate": 1.2682009456466124e-05, + "loss": 3.375, + "step": 2279424 + }, + { + "epoch": 1.02, + "learning_rate": 1.2673623508955604e-05, + "loss": 3.3776, + "step": 2279936 + }, + { + "epoch": 1.02, + "learning_rate": 1.2665237561445084e-05, + "loss": 3.3849, + "step": 2280448 + }, + { + "epoch": 1.02, + "learning_rate": 1.2656851613934562e-05, + "loss": 3.3672, + "step": 2280960 + }, + { + "epoch": 1.02, + "learning_rate": 1.2648482045227775e-05, + "loss": 3.3829, + "step": 2281472 + }, + { + "epoch": 1.02, + "learning_rate": 1.2640096097717255e-05, + "loss": 3.3697, + "step": 2281984 + }, + { + "epoch": 1.02, + "learning_rate": 1.2631710150206733e-05, + "loss": 3.3745, + "step": 2282496 + }, + { + "epoch": 1.02, + "learning_rate": 1.2623324202696213e-05, + "loss": 3.377, + "step": 2283008 + }, + { + "epoch": 1.02, + "learning_rate": 1.2614954633989426e-05, + "loss": 3.3693, + "step": 2283520 + }, + { + "epoch": 1.02, + "learning_rate": 1.2606568686478905e-05, + "loss": 3.3672, + "step": 2284032 + }, + { + "epoch": 1.02, + "learning_rate": 1.2598182738968384e-05, + "loss": 3.3819, + "step": 2284544 + }, + { + "epoch": 1.02, + "learning_rate": 1.2589796791457864e-05, + "loss": 3.3676, + "step": 2285056 + }, + { + "epoch": 1.02, + "learning_rate": 1.2581443601554807e-05, + "loss": 3.3675, + "step": 2285568 + }, + { + "epoch": 1.02, + "learning_rate": 1.2573057654044287e-05, + "loss": 3.3761, + "step": 2286080 + }, + { + "epoch": 1.02, + "learning_rate": 1.2564671706533767e-05, + "loss": 3.3773, + "step": 2286592 + }, + { + "epoch": 1.02, + "learning_rate": 1.2556285759023249e-05, + "loss": 3.372, + "step": 2287104 + }, + { + "epoch": 1.02, + "learning_rate": 1.2547899811512729e-05, + "loss": 3.3753, + "step": 2287616 + }, + { + "epoch": 1.02, + "learning_rate": 1.253953024280594e-05, + "loss": 3.3703, + "step": 2288128 + }, + { + "epoch": 1.02, + "learning_rate": 1.253114429529542e-05, + "loss": 3.3785, + "step": 2288640 + }, + { + "epoch": 1.02, + "learning_rate": 1.25227583477849e-05, + "loss": 3.3687, + "step": 2289152 + }, + { + "epoch": 1.03, + "eval_loss": 3.8550589084625244, + "eval_runtime": 304.3525, + "eval_samples_per_second": 1253.78, + "eval_steps_per_second": 39.182, + "step": 2289591 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.5930038031034982e+18, + "trial_name": null, + "trial_params": null +}