diff --git "a/checkpoint-1831669/trainer_state.json" "b/checkpoint-1831669/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-1831669/trainer_state.json" @@ -0,0 +1,21679 @@ +{ + "best_metric": 3.8354902267456055, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/full/transformer/1/checkpoints/checkpoint-992149", + "epoch": 1.0250006060157382, + "eval_steps": 10, + "global_step": 1831669, + "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": 11.0634, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.8389, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.1855, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.9639, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.8109, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.6897, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.5891, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5257, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4716, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.3921, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3531, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.3124, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989938500867749e-05, + "loss": 5.269, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 5.2094, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 5.1808, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 5.1489, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.1096, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.076, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.0555, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0279, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 4.9988, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.9823927859886547e-05, + "loss": 4.9703, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.9581, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.9289, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.919, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790400448648195e-05, + "loss": 4.8917, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782014501137675e-05, + "loss": 4.8799, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.8626, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.828, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756873037409844e-05, + "loss": 4.831, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748487089899324e-05, + "loss": 4.8005, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 4.7908, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 4.7795, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.97233456261715e-05, + "loss": 4.7732, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.971495967866098e-05, + "loss": 4.7481, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.739, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 4.7382, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968981821493315e-05, + "loss": 4.7204, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.968143226742263e-05, + "loss": 4.7121, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967304631991211e-05, + "loss": 4.6943, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 4.6778, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.96562908036948e-05, + "loss": 4.6707, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964790485618428e-05, + "loss": 4.6477, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963951890867376e-05, + "loss": 4.6663, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.963113296116324e-05, + "loss": 4.6397, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.9622763392456454e-05, + "loss": 4.6409, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.9614377444945934e-05, + "loss": 4.63, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.9605991497435414e-05, + "loss": 4.6254, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.9597605549924894e-05, + "loss": 4.6178, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.95892359812181e-05, + "loss": 4.5949, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958086641251131e-05, + "loss": 4.5868, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957248046500079e-05, + "loss": 4.5768, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956409451749027e-05, + "loss": 4.5836, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.955570856997975e-05, + "loss": 4.5639, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.954732262246923e-05, + "loss": 4.5733, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.953893667495871e-05, + "loss": 4.5479, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.953055072744819e-05, + "loss": 4.5422, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.952216477993767e-05, + "loss": 4.5388, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951379521123089e-05, + "loss": 4.5331, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950540926372037e-05, + "loss": 4.5303, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949702331620985e-05, + "loss": 4.5119, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948863736869932e-05, + "loss": 4.5097, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.9480267799992536e-05, + "loss": 4.5168, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.9471881852482016e-05, + "loss": 4.4974, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946349590497149e-05, + "loss": 4.492, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945510995746097e-05, + "loss": 4.4907, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.9446740388754185e-05, + "loss": 4.4901, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.9438354441243665e-05, + "loss": 4.4692, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.9429968493733145e-05, + "loss": 4.4815, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.9421582546222625e-05, + "loss": 4.4701, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.941321297751584e-05, + "loss": 4.4594, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.940482703000532e-05, + "loss": 4.4649, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396441082494794e-05, + "loss": 4.4523, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.938807151378801e-05, + "loss": 4.4667, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.937968556627749e-05, + "loss": 4.4639, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.937129961876696e-05, + "loss": 4.455, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.936291367125644e-05, + "loss": 4.4379, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.935452772374592e-05, + "loss": 4.4281, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.934615815503914e-05, + "loss": 4.4183, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.933777220752861e-05, + "loss": 4.4319, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.93293862600181e-05, + "loss": 4.4329, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.932100031250758e-05, + "loss": 4.4279, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931261436499706e-05, + "loss": 4.4009, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930422841748654e-05, + "loss": 4.3998, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929584246997602e-05, + "loss": 4.4061, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.928747290126923e-05, + "loss": 4.3943, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927908695375871e-05, + "loss": 4.399, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927070100624819e-05, + "loss": 4.3958, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926231505873767e-05, + "loss": 4.3963, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925392911122715e-05, + "loss": 4.3862, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924554316371663e-05, + "loss": 4.3824, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923715721620611e-05, + "loss": 4.3703, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922877126869559e-05, + "loss": 4.3851, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.922041807879253e-05, + "loss": 4.3679, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921203213128201e-05, + "loss": 4.3549, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920364618377149e-05, + "loss": 4.3598, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919526023626097e-05, + "loss": 4.3723, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918687428875045e-05, + "loss": 4.3661, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.917848834123993e-05, + "loss": 4.3613, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.917010239372941e-05, + "loss": 4.3434, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.916171644621889e-05, + "loss": 4.3586, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.91533468775121e-05, + "loss": 4.3326, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914497730880531e-05, + "loss": 4.35, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.913659136129479e-05, + "loss": 4.3526, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.912820541378427e-05, + "loss": 4.3381, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.911981946627375e-05, + "loss": 4.3293, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.911143351876323e-05, + "loss": 4.3071, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910304757125272e-05, + "loss": 4.3225, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.9094678002545926e-05, + "loss": 4.32, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.9086292055035406e-05, + "loss": 4.3181, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.9077906107524886e-05, + "loss": 4.3234, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.9069520160014366e-05, + "loss": 4.3047, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.9061150591307575e-05, + "loss": 4.3082, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.9052764643797055e-05, + "loss": 4.3144, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.9044378696286535e-05, + "loss": 4.3171, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.9035992748776015e-05, + "loss": 4.3033, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.9027606801265495e-05, + "loss": 4.302, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.9019220853754975e-05, + "loss": 4.2961, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.9010851285048184e-05, + "loss": 4.2971, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.900246533753767e-05, + "loss": 4.3029, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.899409576883088e-05, + "loss": 4.2871, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.898570982132036e-05, + "loss": 4.2837, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.897732387380984e-05, + "loss": 4.2812, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.896893792629932e-05, + "loss": 4.2788, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.89605519787888e-05, + "loss": 4.2816, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.895216603127827e-05, + "loss": 4.2814, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.894378008376775e-05, + "loss": 4.2859, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.893539413625723e-05, + "loss": 4.2625, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.892702456755045e-05, + "loss": 4.2753, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.891863862003992e-05, + "loss": 4.277, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.891025267252941e-05, + "loss": 4.2661, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890186672501889e-05, + "loss": 4.2817, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889348077750837e-05, + "loss": 4.2644, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888511120880158e-05, + "loss": 4.2757, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.887672526129106e-05, + "loss": 4.2663, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886833931378054e-05, + "loss": 4.2452, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885995336627002e-05, + "loss": 4.2462, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.8851583797563226e-05, + "loss": 4.2491, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.8843197850052706e-05, + "loss": 4.2565, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.8834811902542186e-05, + "loss": 4.2572, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.8826425955031666e-05, + "loss": 4.2582, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.8818056386324875e-05, + "loss": 4.2472, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.880967043881436e-05, + "loss": 4.2416, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880128449130384e-05, + "loss": 4.2359, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879289854379332e-05, + "loss": 4.2309, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878452897508653e-05, + "loss": 4.2393, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877614302757601e-05, + "loss": 4.2494, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876775708006549e-05, + "loss": 4.2434, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875937113255497e-05, + "loss": 4.2233, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875098518504445e-05, + "loss": 4.2263, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.191549301147461, + "eval_runtime": 619.6834, + "eval_samples_per_second": 615.784, + "eval_steps_per_second": 19.244, + "step": 76319 + }, + { + "epoch": 0.0, + "learning_rate": 4.874261561633766e-05, + "loss": 4.2271, + "step": 76800 + }, + { + "epoch": 0.0, + "learning_rate": 4.873422966882714e-05, + "loss": 4.2236, + "step": 77312 + }, + { + "epoch": 0.0, + "learning_rate": 4.872584372131662e-05, + "loss": 4.2196, + "step": 77824 + }, + { + "epoch": 0.0, + "learning_rate": 4.87174577738061e-05, + "loss": 4.2196, + "step": 78336 + }, + { + "epoch": 0.0, + "learning_rate": 4.870907182629558e-05, + "loss": 4.2101, + "step": 78848 + }, + { + "epoch": 0.0, + "learning_rate": 4.870068587878506e-05, + "loss": 4.1946, + "step": 79360 + }, + { + "epoch": 0.0, + "learning_rate": 4.869229993127454e-05, + "loss": 4.2003, + "step": 79872 + }, + { + "epoch": 0.0, + "learning_rate": 4.8683913983764027e-05, + "loss": 4.2123, + "step": 80384 + }, + { + "epoch": 0.0, + "learning_rate": 4.8675528036253507e-05, + "loss": 4.2026, + "step": 80896 + }, + { + "epoch": 0.0, + "learning_rate": 4.8667142088742986e-05, + "loss": 4.2049, + "step": 81408 + }, + { + "epoch": 0.0, + "learning_rate": 4.865875614123246e-05, + "loss": 4.2058, + "step": 81920 + }, + { + "epoch": 0.0, + "learning_rate": 4.8650386572525676e-05, + "loss": 4.2061, + "step": 82432 + }, + { + "epoch": 0.0, + "learning_rate": 4.8642017003818885e-05, + "loss": 4.1969, + "step": 82944 + }, + { + "epoch": 0.0, + "learning_rate": 4.8633631056308365e-05, + "loss": 4.1974, + "step": 83456 + }, + { + "epoch": 0.0, + "learning_rate": 4.8625245108797845e-05, + "loss": 4.1931, + "step": 83968 + }, + { + "epoch": 0.0, + "learning_rate": 4.8616859161287324e-05, + "loss": 4.1777, + "step": 84480 + }, + { + "epoch": 0.0, + "learning_rate": 4.8608473213776804e-05, + "loss": 4.186, + "step": 84992 + }, + { + "epoch": 0.0, + "learning_rate": 4.860008726626628e-05, + "loss": 4.1901, + "step": 85504 + }, + { + "epoch": 0.0, + "learning_rate": 4.8591701318755764e-05, + "loss": 4.1885, + "step": 86016 + }, + { + "epoch": 0.0, + "learning_rate": 4.858333175004898e-05, + "loss": 4.1891, + "step": 86528 + }, + { + "epoch": 0.0, + "learning_rate": 4.857494580253846e-05, + "loss": 4.1768, + "step": 87040 + }, + { + "epoch": 0.0, + "learning_rate": 4.856655985502793e-05, + "loss": 4.1852, + "step": 87552 + }, + { + "epoch": 0.0, + "learning_rate": 4.855817390751741e-05, + "loss": 4.1732, + "step": 88064 + }, + { + "epoch": 0.0, + "learning_rate": 4.854980433881063e-05, + "loss": 4.1842, + "step": 88576 + }, + { + "epoch": 0.0, + "learning_rate": 4.854141839130011e-05, + "loss": 4.1749, + "step": 89088 + }, + { + "epoch": 0.0, + "learning_rate": 4.853303244378958e-05, + "loss": 4.1714, + "step": 89600 + }, + { + "epoch": 0.0, + "learning_rate": 4.852464649627906e-05, + "loss": 4.1768, + "step": 90112 + }, + { + "epoch": 0.0, + "learning_rate": 4.851627692757228e-05, + "loss": 4.1561, + "step": 90624 + }, + { + "epoch": 0.0, + "learning_rate": 4.850789098006175e-05, + "loss": 4.1743, + "step": 91136 + }, + { + "epoch": 0.01, + "learning_rate": 4.849950503255123e-05, + "loss": 4.1566, + "step": 91648 + }, + { + "epoch": 0.01, + "learning_rate": 4.849111908504072e-05, + "loss": 4.1625, + "step": 92160 + }, + { + "epoch": 0.01, + "learning_rate": 4.8482749516333934e-05, + "loss": 4.1607, + "step": 92672 + }, + { + "epoch": 0.01, + "learning_rate": 4.847436356882341e-05, + "loss": 4.1687, + "step": 93184 + }, + { + "epoch": 0.01, + "learning_rate": 4.846597762131289e-05, + "loss": 4.1562, + "step": 93696 + }, + { + "epoch": 0.01, + "learning_rate": 4.845759167380237e-05, + "loss": 4.1538, + "step": 94208 + }, + { + "epoch": 0.01, + "learning_rate": 4.844920572629185e-05, + "loss": 4.1638, + "step": 94720 + }, + { + "epoch": 0.01, + "learning_rate": 4.8440836157585056e-05, + "loss": 4.1531, + "step": 95232 + }, + { + "epoch": 0.01, + "learning_rate": 4.8432450210074536e-05, + "loss": 4.1605, + "step": 95744 + }, + { + "epoch": 0.01, + "learning_rate": 4.8424064262564016e-05, + "loss": 4.1453, + "step": 96256 + }, + { + "epoch": 0.01, + "learning_rate": 4.8415678315053496e-05, + "loss": 4.1368, + "step": 96768 + }, + { + "epoch": 0.01, + "learning_rate": 4.8407308746346705e-05, + "loss": 4.1395, + "step": 97280 + }, + { + "epoch": 0.01, + "learning_rate": 4.8398922798836185e-05, + "loss": 4.133, + "step": 97792 + }, + { + "epoch": 0.01, + "learning_rate": 4.839053685132567e-05, + "loss": 4.1497, + "step": 98304 + }, + { + "epoch": 0.01, + "learning_rate": 4.838215090381515e-05, + "loss": 4.137, + "step": 98816 + }, + { + "epoch": 0.01, + "learning_rate": 4.837378133510836e-05, + "loss": 4.1442, + "step": 99328 + }, + { + "epoch": 0.01, + "learning_rate": 4.836539538759784e-05, + "loss": 4.1377, + "step": 99840 + }, + { + "epoch": 0.01, + "learning_rate": 4.8357025818891057e-05, + "loss": 4.1415, + "step": 100352 + }, + { + "epoch": 0.01, + "learning_rate": 4.834863987138053e-05, + "loss": 4.1418, + "step": 100864 + }, + { + "epoch": 0.01, + "learning_rate": 4.834025392387001e-05, + "loss": 4.1192, + "step": 101376 + }, + { + "epoch": 0.01, + "learning_rate": 4.833186797635949e-05, + "loss": 4.1246, + "step": 101888 + }, + { + "epoch": 0.01, + "learning_rate": 4.83234984076527e-05, + "loss": 4.1197, + "step": 102400 + }, + { + "epoch": 0.01, + "learning_rate": 4.831511246014218e-05, + "loss": 4.1356, + "step": 102912 + }, + { + "epoch": 0.01, + "learning_rate": 4.830672651263166e-05, + "loss": 4.1125, + "step": 103424 + }, + { + "epoch": 0.01, + "learning_rate": 4.829834056512114e-05, + "loss": 4.1358, + "step": 103936 + }, + { + "epoch": 0.01, + "learning_rate": 4.8289954617610625e-05, + "loss": 4.1111, + "step": 104448 + }, + { + "epoch": 0.01, + "learning_rate": 4.8281568670100105e-05, + "loss": 4.1101, + "step": 104960 + }, + { + "epoch": 0.01, + "learning_rate": 4.8273182722589585e-05, + "loss": 4.1193, + "step": 105472 + }, + { + "epoch": 0.01, + "learning_rate": 4.8264796775079065e-05, + "loss": 4.1143, + "step": 105984 + }, + { + "epoch": 0.01, + "learning_rate": 4.8256427206372274e-05, + "loss": 4.1136, + "step": 106496 + }, + { + "epoch": 0.01, + "learning_rate": 4.8248041258861754e-05, + "loss": 4.1071, + "step": 107008 + }, + { + "epoch": 0.01, + "learning_rate": 4.8239655311351234e-05, + "loss": 4.1029, + "step": 107520 + }, + { + "epoch": 0.01, + "learning_rate": 4.8231269363840714e-05, + "loss": 4.1159, + "step": 108032 + }, + { + "epoch": 0.01, + "learning_rate": 4.822289979513392e-05, + "loss": 4.104, + "step": 108544 + }, + { + "epoch": 0.01, + "learning_rate": 4.82145138476234e-05, + "loss": 4.1047, + "step": 109056 + }, + { + "epoch": 0.01, + "learning_rate": 4.820612790011288e-05, + "loss": 4.1037, + "step": 109568 + }, + { + "epoch": 0.01, + "learning_rate": 4.819774195260236e-05, + "loss": 4.1075, + "step": 110080 + }, + { + "epoch": 0.01, + "learning_rate": 4.818937238389558e-05, + "loss": 4.0874, + "step": 110592 + }, + { + "epoch": 0.01, + "learning_rate": 4.818098643638506e-05, + "loss": 4.1088, + "step": 111104 + }, + { + "epoch": 0.01, + "learning_rate": 4.817260048887454e-05, + "loss": 4.0949, + "step": 111616 + }, + { + "epoch": 0.01, + "learning_rate": 4.816421454136402e-05, + "loss": 4.097, + "step": 112128 + }, + { + "epoch": 0.01, + "learning_rate": 4.815584497265723e-05, + "loss": 4.103, + "step": 112640 + }, + { + "epoch": 0.01, + "learning_rate": 4.814745902514671e-05, + "loss": 4.094, + "step": 113152 + }, + { + "epoch": 0.01, + "learning_rate": 4.813907307763619e-05, + "loss": 4.1096, + "step": 113664 + }, + { + "epoch": 0.01, + "learning_rate": 4.813068713012567e-05, + "loss": 4.1144, + "step": 114176 + }, + { + "epoch": 0.01, + "learning_rate": 4.812231756141888e-05, + "loss": 4.1067, + "step": 114688 + }, + { + "epoch": 0.01, + "learning_rate": 4.811393161390836e-05, + "loss": 4.092, + "step": 115200 + }, + { + "epoch": 0.01, + "learning_rate": 4.810554566639784e-05, + "loss": 4.0846, + "step": 115712 + }, + { + "epoch": 0.01, + "learning_rate": 4.8097176097691046e-05, + "loss": 4.0798, + "step": 116224 + }, + { + "epoch": 0.01, + "learning_rate": 4.808879015018053e-05, + "loss": 4.0936, + "step": 116736 + }, + { + "epoch": 0.01, + "learning_rate": 4.808040420267001e-05, + "loss": 4.1053, + "step": 117248 + }, + { + "epoch": 0.01, + "learning_rate": 4.807201825515949e-05, + "loss": 4.0948, + "step": 117760 + }, + { + "epoch": 0.01, + "learning_rate": 4.806363230764897e-05, + "loss": 4.0796, + "step": 118272 + }, + { + "epoch": 0.01, + "learning_rate": 4.805524636013845e-05, + "loss": 4.074, + "step": 118784 + }, + { + "epoch": 0.01, + "learning_rate": 4.804686041262793e-05, + "loss": 4.0859, + "step": 119296 + }, + { + "epoch": 0.01, + "learning_rate": 4.803849084392114e-05, + "loss": 4.0728, + "step": 119808 + }, + { + "epoch": 0.01, + "learning_rate": 4.803010489641062e-05, + "loss": 4.0812, + "step": 120320 + }, + { + "epoch": 0.01, + "learning_rate": 4.80217189489001e-05, + "loss": 4.0833, + "step": 120832 + }, + { + "epoch": 0.01, + "learning_rate": 4.801333300138958e-05, + "loss": 4.0882, + "step": 121344 + }, + { + "epoch": 0.01, + "learning_rate": 4.800494705387906e-05, + "loss": 4.0773, + "step": 121856 + }, + { + "epoch": 0.02, + "learning_rate": 4.7996561106368535e-05, + "loss": 4.0783, + "step": 122368 + }, + { + "epoch": 0.02, + "learning_rate": 4.7988175158858015e-05, + "loss": 4.0692, + "step": 122880 + }, + { + "epoch": 0.02, + "learning_rate": 4.797980559015123e-05, + "loss": 4.0806, + "step": 123392 + }, + { + "epoch": 0.02, + "learning_rate": 4.797141964264071e-05, + "loss": 4.0779, + "step": 123904 + }, + { + "epoch": 0.02, + "learning_rate": 4.796303369513019e-05, + "loss": 4.058, + "step": 124416 + }, + { + "epoch": 0.02, + "learning_rate": 4.795464774761967e-05, + "loss": 4.0683, + "step": 124928 + }, + { + "epoch": 0.02, + "learning_rate": 4.794626180010915e-05, + "loss": 4.0802, + "step": 125440 + }, + { + "epoch": 0.02, + "learning_rate": 4.793787585259863e-05, + "loss": 4.0854, + "step": 125952 + }, + { + "epoch": 0.02, + "learning_rate": 4.792948990508811e-05, + "loss": 4.07, + "step": 126464 + }, + { + "epoch": 0.02, + "learning_rate": 4.792110395757759e-05, + "loss": 4.0636, + "step": 126976 + }, + { + "epoch": 0.02, + "learning_rate": 4.79127343888708e-05, + "loss": 4.0766, + "step": 127488 + }, + { + "epoch": 0.02, + "learning_rate": 4.790434844136028e-05, + "loss": 4.0551, + "step": 128000 + }, + { + "epoch": 0.02, + "learning_rate": 4.789596249384976e-05, + "loss": 4.0702, + "step": 128512 + }, + { + "epoch": 0.02, + "learning_rate": 4.788757654633924e-05, + "loss": 4.0768, + "step": 129024 + }, + { + "epoch": 0.02, + "learning_rate": 4.787920697763245e-05, + "loss": 4.0672, + "step": 129536 + }, + { + "epoch": 0.02, + "learning_rate": 4.7870821030121935e-05, + "loss": 4.0648, + "step": 130048 + }, + { + "epoch": 0.02, + "learning_rate": 4.7862435082611415e-05, + "loss": 4.045, + "step": 130560 + }, + { + "epoch": 0.02, + "learning_rate": 4.7854049135100895e-05, + "loss": 4.0495, + "step": 131072 + }, + { + "epoch": 0.02, + "learning_rate": 4.7845679566394104e-05, + "loss": 4.0538, + "step": 131584 + }, + { + "epoch": 0.02, + "learning_rate": 4.7837293618883584e-05, + "loss": 4.055, + "step": 132096 + }, + { + "epoch": 0.02, + "learning_rate": 4.782892405017679e-05, + "loss": 4.0618, + "step": 132608 + }, + { + "epoch": 0.02, + "learning_rate": 4.782053810266627e-05, + "loss": 4.05, + "step": 133120 + }, + { + "epoch": 0.02, + "learning_rate": 4.781215215515575e-05, + "loss": 4.046, + "step": 133632 + }, + { + "epoch": 0.02, + "learning_rate": 4.780376620764523e-05, + "loss": 4.0582, + "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": 4.777860836511367e-05, + "loss": 4.0573, + "step": 135680 + }, + { + "epoch": 0.02, + "learning_rate": 4.777023879640689e-05, + "loss": 4.0472, + "step": 136192 + }, + { + "epoch": 0.02, + "learning_rate": 4.776185284889637e-05, + "loss": 4.0509, + "step": 136704 + }, + { + "epoch": 0.02, + "learning_rate": 4.775346690138585e-05, + "loss": 4.0575, + "step": 137216 + }, + { + "epoch": 0.02, + "learning_rate": 4.774509733267906e-05, + "loss": 4.0408, + "step": 137728 + }, + { + "epoch": 0.02, + "learning_rate": 4.773671138516854e-05, + "loss": 4.042, + "step": 138240 + }, + { + "epoch": 0.02, + "learning_rate": 4.772832543765802e-05, + "loss": 4.0411, + "step": 138752 + }, + { + "epoch": 0.02, + "learning_rate": 4.77199394901475e-05, + "loss": 4.0401, + "step": 139264 + }, + { + "epoch": 0.02, + "learning_rate": 4.771155354263698e-05, + "loss": 4.0433, + "step": 139776 + }, + { + "epoch": 0.02, + "learning_rate": 4.770316759512646e-05, + "loss": 4.0475, + "step": 140288 + }, + { + "epoch": 0.02, + "learning_rate": 4.769478164761594e-05, + "loss": 4.0522, + "step": 140800 + }, + { + "epoch": 0.02, + "learning_rate": 4.768639570010542e-05, + "loss": 4.0327, + "step": 141312 + }, + { + "epoch": 0.02, + "learning_rate": 4.7678042510202355e-05, + "loss": 4.0393, + "step": 141824 + }, + { + "epoch": 0.02, + "learning_rate": 4.766965656269184e-05, + "loss": 4.0527, + "step": 142336 + }, + { + "epoch": 0.02, + "learning_rate": 4.766127061518132e-05, + "loss": 4.0378, + "step": 142848 + }, + { + "epoch": 0.02, + "learning_rate": 4.76528846676708e-05, + "loss": 4.0508, + "step": 143360 + }, + { + "epoch": 0.02, + "learning_rate": 4.764449872016028e-05, + "loss": 4.0371, + "step": 143872 + }, + { + "epoch": 0.02, + "learning_rate": 4.763612915145349e-05, + "loss": 4.0521, + "step": 144384 + }, + { + "epoch": 0.02, + "learning_rate": 4.762774320394297e-05, + "loss": 4.0418, + "step": 144896 + }, + { + "epoch": 0.02, + "learning_rate": 4.761935725643245e-05, + "loss": 4.0255, + "step": 145408 + }, + { + "epoch": 0.02, + "learning_rate": 4.761097130892193e-05, + "loss": 4.026, + "step": 145920 + }, + { + "epoch": 0.02, + "learning_rate": 4.760258536141141e-05, + "loss": 4.0288, + "step": 146432 + }, + { + "epoch": 0.02, + "learning_rate": 4.759419941390089e-05, + "loss": 4.0412, + "step": 146944 + }, + { + "epoch": 0.02, + "learning_rate": 4.75858298451941e-05, + "loss": 4.0375, + "step": 147456 + }, + { + "epoch": 0.02, + "learning_rate": 4.757744389768358e-05, + "loss": 4.0413, + "step": 147968 + }, + { + "epoch": 0.02, + "learning_rate": 4.756905795017306e-05, + "loss": 4.0337, + "step": 148480 + }, + { + "epoch": 0.02, + "learning_rate": 4.756067200266254e-05, + "loss": 4.028, + "step": 148992 + }, + { + "epoch": 0.02, + "learning_rate": 4.755228605515202e-05, + "loss": 4.0258, + "step": 149504 + }, + { + "epoch": 0.02, + "learning_rate": 4.75439001076415e-05, + "loss": 4.0199, + "step": 150016 + }, + { + "epoch": 0.02, + "learning_rate": 4.753551416013098e-05, + "loss": 4.0291, + "step": 150528 + }, + { + "epoch": 0.02, + "learning_rate": 4.752712821262046e-05, + "loss": 4.0427, + "step": 151040 + }, + { + "epoch": 0.02, + "learning_rate": 4.751875864391367e-05, + "loss": 4.0292, + "step": 151552 + }, + { + "epoch": 0.02, + "learning_rate": 4.751037269640315e-05, + "loss": 4.0234, + "step": 152064 + }, + { + "epoch": 0.02, + "learning_rate": 4.750198674889263e-05, + "loss": 4.0206, + "step": 152576 + }, + { + "epoch": 0.03, + "eval_loss": 4.022192001342773, + "eval_runtime": 552.4226, + "eval_samples_per_second": 690.759, + "eval_steps_per_second": 21.587, + "step": 152638 + }, + { + "epoch": 0.0, + "learning_rate": 4.7493617180185845e-05, + "loss": 4.0278, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748523123267532e-05, + "loss": 4.0254, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.74768452851648e-05, + "loss": 4.0151, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.746845933765428e-05, + "loss": 4.0183, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.7460073390143764e-05, + "loss": 4.0168, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.7451687442633244e-05, + "loss": 3.998, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.7443301495122724e-05, + "loss": 4.0059, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.7434915547612204e-05, + "loss": 4.0226, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.7426529600101684e-05, + "loss": 4.0044, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.741816003139489e-05, + "loss": 4.0108, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740977408388437e-05, + "loss": 4.018, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.740138813637385e-05, + "loss": 4.0152, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739300218886333e-05, + "loss": 4.0054, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738461624135281e-05, + "loss": 4.0104, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.737624667264602e-05, + "loss": 4.0036, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.73678607251355e-05, + "loss": 3.9934, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735947477762498e-05, + "loss": 4.0003, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.735108883011446e-05, + "loss": 4.005, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734270288260394e-05, + "loss": 4.0065, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733431693509343e-05, + "loss": 4.0082, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732593098758291e-05, + "loss": 3.9975, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731754504007238e-05, + "loss": 4.0078, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.730919185016933e-05, + "loss": 3.9952, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730080590265881e-05, + "loss": 4.0054, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.729241995514829e-05, + "loss": 3.9987, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.728403400763777e-05, + "loss": 3.9974, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727564806012725e-05, + "loss": 4.0045, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.726726211261673e-05, + "loss": 3.9832, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.7258892543909936e-05, + "loss": 4.0004, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.7250506596399416e-05, + "loss": 3.9868, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.7242120648888896e-05, + "loss": 3.9908, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723373470137838e-05, + "loss": 3.9928, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.7225348753867856e-05, + "loss": 3.9964, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.7216962806357336e-05, + "loss": 3.9919, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.7208576858846816e-05, + "loss": 3.9846, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.720020729014003e-05, + "loss": 3.9965, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.7191821342629505e-05, + "loss": 3.9881, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.7183435395118985e-05, + "loss": 3.9991, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.7175049447608465e-05, + "loss": 3.9835, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.7166663500097945e-05, + "loss": 3.9723, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.7158277552587424e-05, + "loss": 3.9753, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.7149907983880634e-05, + "loss": 3.9753, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.714152203637012e-05, + "loss": 3.9939, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.71331360888596e-05, + "loss": 3.9725, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.712475014134908e-05, + "loss": 3.9874, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.711638057264229e-05, + "loss": 3.9817, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.710799462513177e-05, + "loss": 3.9793, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.709960867762125e-05, + "loss": 3.9862, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.709122273011073e-05, + "loss": 3.9636, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.708283678260021e-05, + "loss": 3.9688, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.707445083508969e-05, + "loss": 3.964, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.70660812663829e-05, + "loss": 3.9841, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705769531887238e-05, + "loss": 3.9628, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704930937136186e-05, + "loss": 3.9816, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.704092342385134e-05, + "loss": 3.9613, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.7032553855144554e-05, + "loss": 3.9605, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.7024167907634034e-05, + "loss": 3.9654, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.7015781960123514e-05, + "loss": 3.9631, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.7007396012612994e-05, + "loss": 3.9687, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.69990264439062e-05, + "loss": 3.9636, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699064049639568e-05, + "loss": 3.9515, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.698225454888516e-05, + "loss": 3.968, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.697386860137464e-05, + "loss": 3.9578, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696548265386412e-05, + "loss": 3.9631, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.69570967063536e-05, + "loss": 3.9569, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694871075884308e-05, + "loss": 3.9655, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694032481133256e-05, + "loss": 3.9433, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693195524262577e-05, + "loss": 3.9665, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692356929511526e-05, + "loss": 3.9502, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.691518334760474e-05, + "loss": 3.9581, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690679740009422e-05, + "loss": 3.9589, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.689842783138743e-05, + "loss": 3.9552, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.689004188387691e-05, + "loss": 3.9687, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.688165593636639e-05, + "loss": 3.9752, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.6873286367659596e-05, + "loss": 3.9698, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.6864900420149076e-05, + "loss": 3.9583, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.6856514472638556e-05, + "loss": 3.948, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.6848128525128036e-05, + "loss": 3.9396, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.6839758956421245e-05, + "loss": 3.9599, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.6831373008910725e-05, + "loss": 3.9666, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.6822987061400205e-05, + "loss": 3.9627, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.681460111388969e-05, + "loss": 3.9438, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.68062315451829e-05, + "loss": 3.9415, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679784559767238e-05, + "loss": 3.9496, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678945965016186e-05, + "loss": 3.9371, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678107370265134e-05, + "loss": 3.9458, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.6772687755140814e-05, + "loss": 3.9544, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.6764301807630294e-05, + "loss": 3.9516, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.6755915860119774e-05, + "loss": 3.9472, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674754629141298e-05, + "loss": 3.9509, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.673916034390246e-05, + "loss": 3.938, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.673077439639194e-05, + "loss": 3.9527, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.672238844888143e-05, + "loss": 3.9451, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.671400250137091e-05, + "loss": 3.9347, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.670563293266412e-05, + "loss": 3.9395, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.66972469851536e-05, + "loss": 3.9502, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.668886103764308e-05, + "loss": 3.9572, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668047509013256e-05, + "loss": 3.9419, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667210552142577e-05, + "loss": 3.9412, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.666371957391525e-05, + "loss": 3.9483, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665533362640473e-05, + "loss": 3.9304, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664694767889421e-05, + "loss": 3.9471, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663856173138369e-05, + "loss": 3.952, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.66301921626769e-05, + "loss": 3.9406, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.6621806215166383e-05, + "loss": 3.9465, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.6613420267655863e-05, + "loss": 3.9239, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660503432014534e-05, + "loss": 3.9229, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659666475143855e-05, + "loss": 3.9323, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.658827880392803e-05, + "loss": 3.9338, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.657989285641751e-05, + "loss": 3.9424, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657150690890699e-05, + "loss": 3.9292, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.656312096139647e-05, + "loss": 3.9248, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655475139268968e-05, + "loss": 3.9334, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.654636544517916e-05, + "loss": 3.9438, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.653797949766864e-05, + "loss": 3.936, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.652959355015812e-05, + "loss": 3.9417, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.65212076026476e-05, + "loss": 3.9267, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.651283803394082e-05, + "loss": 3.9295, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.65044520864303e-05, + "loss": 3.9427, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.649606613891978e-05, + "loss": 3.9235, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648768019140926e-05, + "loss": 3.9264, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.6479310622702466e-05, + "loss": 3.9256, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.6470924675191946e-05, + "loss": 3.9232, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.6462538727681426e-05, + "loss": 3.9271, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.6454152780170906e-05, + "loss": 3.9285, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.6445766832660386e-05, + "loss": 3.9394, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.6437397263953595e-05, + "loss": 3.9188, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.6429011316443075e-05, + "loss": 3.9221, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.6420625368932555e-05, + "loss": 3.9423, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.6412239421422035e-05, + "loss": 3.9231, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640385347391152e-05, + "loss": 3.9371, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.639548390520473e-05, + "loss": 3.9246, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.638709795769421e-05, + "loss": 3.9394, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.637871201018369e-05, + "loss": 3.9295, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.637032606267317e-05, + "loss": 3.9158, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.636195649396638e-05, + "loss": 3.9168, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.635357054645586e-05, + "loss": 3.9169, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.634518459894534e-05, + "loss": 3.9277, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.633679865143482e-05, + "loss": 3.932, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.632842908272803e-05, + "loss": 3.9291, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.632004313521751e-05, + "loss": 3.925, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.631165718770699e-05, + "loss": 3.918, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.6303271240196475e-05, + "loss": 3.9183, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.6294901671489684e-05, + "loss": 3.9094, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.6286515723979164e-05, + "loss": 3.9212, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.6278129776468644e-05, + "loss": 3.9325, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626974382895812e-05, + "loss": 3.9197, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.62613578814476e-05, + "loss": 3.9161, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625297193393708e-05, + "loss": 3.9134, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.9479596614837646, + "eval_runtime": 568.4433, + "eval_samples_per_second": 671.291, + "eval_steps_per_second": 20.978, + "step": 228957 + }, + { + "epoch": 0.0, + "learning_rate": 4.624460236523029e-05, + "loss": 3.9188, + "step": 229376 + }, + { + "epoch": 0.0, + "learning_rate": 4.6236216417719766e-05, + "loss": 3.9229, + "step": 229888 + }, + { + "epoch": 0.0, + "learning_rate": 4.6227830470209246e-05, + "loss": 3.9108, + "step": 230400 + }, + { + "epoch": 0.0, + "learning_rate": 4.6219444522698726e-05, + "loss": 3.9123, + "step": 230912 + }, + { + "epoch": 0.0, + "learning_rate": 4.621105857518821e-05, + "loss": 3.9146, + "step": 231424 + }, + { + "epoch": 0.0, + "learning_rate": 4.620267262767769e-05, + "loss": 3.8934, + "step": 231936 + }, + { + "epoch": 0.0, + "learning_rate": 4.619428668016717e-05, + "loss": 3.9017, + "step": 232448 + }, + { + "epoch": 0.0, + "learning_rate": 4.618590073265665e-05, + "loss": 3.9158, + "step": 232960 + }, + { + "epoch": 0.0, + "learning_rate": 4.617753116394986e-05, + "loss": 3.9039, + "step": 233472 + }, + { + "epoch": 0.0, + "learning_rate": 4.616916159524307e-05, + "loss": 3.91, + "step": 233984 + }, + { + "epoch": 0.0, + "learning_rate": 4.616077564773255e-05, + "loss": 3.912, + "step": 234496 + }, + { + "epoch": 0.0, + "learning_rate": 4.615238970022203e-05, + "loss": 3.9079, + "step": 235008 + }, + { + "epoch": 0.0, + "learning_rate": 4.614400375271151e-05, + "loss": 3.9048, + "step": 235520 + }, + { + "epoch": 0.0, + "learning_rate": 4.613561780520099e-05, + "loss": 3.9116, + "step": 236032 + }, + { + "epoch": 0.0, + "learning_rate": 4.612723185769047e-05, + "loss": 3.8999, + "step": 236544 + }, + { + "epoch": 0.0, + "learning_rate": 4.611884591017995e-05, + "loss": 3.8963, + "step": 237056 + }, + { + "epoch": 0.0, + "learning_rate": 4.611045996266943e-05, + "loss": 3.8958, + "step": 237568 + }, + { + "epoch": 0.0, + "learning_rate": 4.610209039396265e-05, + "loss": 3.9042, + "step": 238080 + }, + { + "epoch": 0.0, + "learning_rate": 4.609370444645213e-05, + "loss": 3.9053, + "step": 238592 + }, + { + "epoch": 0.0, + "learning_rate": 4.6085318498941607e-05, + "loss": 3.91, + "step": 239104 + }, + { + "epoch": 0.0, + "learning_rate": 4.6076932551431087e-05, + "loss": 3.8984, + "step": 239616 + }, + { + "epoch": 0.0, + "learning_rate": 4.6068546603920566e-05, + "loss": 3.9102, + "step": 240128 + }, + { + "epoch": 0.0, + "learning_rate": 4.6060177035213776e-05, + "loss": 3.8989, + "step": 240640 + }, + { + "epoch": 0.0, + "learning_rate": 4.6051791087703256e-05, + "loss": 3.9004, + "step": 241152 + }, + { + "epoch": 0.0, + "learning_rate": 4.6043405140192735e-05, + "loss": 3.9019, + "step": 241664 + }, + { + "epoch": 0.0, + "learning_rate": 4.6035019192682215e-05, + "loss": 3.8977, + "step": 242176 + }, + { + "epoch": 0.0, + "learning_rate": 4.6026649623975425e-05, + "loss": 3.9052, + "step": 242688 + }, + { + "epoch": 0.0, + "learning_rate": 4.6018263676464904e-05, + "loss": 3.8874, + "step": 243200 + }, + { + "epoch": 0.0, + "learning_rate": 4.6009894107758114e-05, + "loss": 3.9054, + "step": 243712 + }, + { + "epoch": 0.01, + "learning_rate": 4.60015081602476e-05, + "loss": 3.8897, + "step": 244224 + }, + { + "epoch": 0.01, + "learning_rate": 4.599312221273708e-05, + "loss": 3.8926, + "step": 244736 + }, + { + "epoch": 0.01, + "learning_rate": 4.598473626522656e-05, + "loss": 3.8971, + "step": 245248 + }, + { + "epoch": 0.01, + "learning_rate": 4.597635031771604e-05, + "loss": 3.906, + "step": 245760 + }, + { + "epoch": 0.01, + "learning_rate": 4.596796437020552e-05, + "loss": 3.891, + "step": 246272 + }, + { + "epoch": 0.01, + "learning_rate": 4.5959578422695e-05, + "loss": 3.8938, + "step": 246784 + }, + { + "epoch": 0.01, + "learning_rate": 4.595119247518448e-05, + "loss": 3.8965, + "step": 247296 + }, + { + "epoch": 0.01, + "learning_rate": 4.594282290647769e-05, + "loss": 3.8934, + "step": 247808 + }, + { + "epoch": 0.01, + "learning_rate": 4.593443695896717e-05, + "loss": 3.9068, + "step": 248320 + }, + { + "epoch": 0.01, + "learning_rate": 4.592605101145665e-05, + "loss": 3.8901, + "step": 248832 + }, + { + "epoch": 0.01, + "learning_rate": 4.591766506394613e-05, + "loss": 3.8786, + "step": 249344 + }, + { + "epoch": 0.01, + "learning_rate": 4.59092791164356e-05, + "loss": 3.885, + "step": 249856 + }, + { + "epoch": 0.01, + "learning_rate": 4.590090954772882e-05, + "loss": 3.8778, + "step": 250368 + }, + { + "epoch": 0.01, + "learning_rate": 4.58925236002183e-05, + "loss": 3.9011, + "step": 250880 + }, + { + "epoch": 0.01, + "learning_rate": 4.5884137652707785e-05, + "loss": 3.8845, + "step": 251392 + }, + { + "epoch": 0.01, + "learning_rate": 4.587575170519726e-05, + "loss": 3.8947, + "step": 251904 + }, + { + "epoch": 0.01, + "learning_rate": 4.5867382136490474e-05, + "loss": 3.8882, + "step": 252416 + }, + { + "epoch": 0.01, + "learning_rate": 4.5858996188979954e-05, + "loss": 3.8894, + "step": 252928 + }, + { + "epoch": 0.01, + "learning_rate": 4.585061024146943e-05, + "loss": 3.8943, + "step": 253440 + }, + { + "epoch": 0.01, + "learning_rate": 4.584222429395891e-05, + "loss": 3.8742, + "step": 253952 + }, + { + "epoch": 0.01, + "learning_rate": 4.583383834644839e-05, + "loss": 3.8744, + "step": 254464 + }, + { + "epoch": 0.01, + "learning_rate": 4.58254687777416e-05, + "loss": 3.8791, + "step": 254976 + }, + { + "epoch": 0.01, + "learning_rate": 4.5817082830231076e-05, + "loss": 3.8912, + "step": 255488 + }, + { + "epoch": 0.01, + "learning_rate": 4.5808696882720556e-05, + "loss": 3.8724, + "step": 256000 + }, + { + "epoch": 0.01, + "learning_rate": 4.5800310935210036e-05, + "loss": 3.8892, + "step": 256512 + }, + { + "epoch": 0.01, + "learning_rate": 4.579194136650325e-05, + "loss": 3.8728, + "step": 257024 + }, + { + "epoch": 0.01, + "learning_rate": 4.578355541899273e-05, + "loss": 3.8686, + "step": 257536 + }, + { + "epoch": 0.01, + "learning_rate": 4.577516947148221e-05, + "loss": 3.8823, + "step": 258048 + }, + { + "epoch": 0.01, + "learning_rate": 4.576678352397169e-05, + "loss": 3.8687, + "step": 258560 + }, + { + "epoch": 0.01, + "learning_rate": 4.57584139552649e-05, + "loss": 3.8855, + "step": 259072 + }, + { + "epoch": 0.01, + "learning_rate": 4.575002800775438e-05, + "loss": 3.8784, + "step": 259584 + }, + { + "epoch": 0.01, + "learning_rate": 4.574164206024386e-05, + "loss": 3.8631, + "step": 260096 + }, + { + "epoch": 0.01, + "learning_rate": 4.573325611273334e-05, + "loss": 3.8774, + "step": 260608 + }, + { + "epoch": 0.01, + "learning_rate": 4.572488654402655e-05, + "loss": 3.8699, + "step": 261120 + }, + { + "epoch": 0.01, + "learning_rate": 4.571650059651603e-05, + "loss": 3.8787, + "step": 261632 + }, + { + "epoch": 0.01, + "learning_rate": 4.570811464900551e-05, + "loss": 3.8667, + "step": 262144 + }, + { + "epoch": 0.01, + "learning_rate": 4.569972870149499e-05, + "loss": 3.8787, + "step": 262656 + }, + { + "epoch": 0.01, + "learning_rate": 4.5691342753984476e-05, + "loss": 3.8574, + "step": 263168 + }, + { + "epoch": 0.01, + "learning_rate": 4.5682973185277685e-05, + "loss": 3.8785, + "step": 263680 + }, + { + "epoch": 0.01, + "learning_rate": 4.5674587237767165e-05, + "loss": 3.8626, + "step": 264192 + }, + { + "epoch": 0.01, + "learning_rate": 4.5666201290256645e-05, + "loss": 3.8695, + "step": 264704 + }, + { + "epoch": 0.01, + "learning_rate": 4.5657815342746125e-05, + "loss": 3.8736, + "step": 265216 + }, + { + "epoch": 0.01, + "learning_rate": 4.5649445774039334e-05, + "loss": 3.8725, + "step": 265728 + }, + { + "epoch": 0.01, + "learning_rate": 4.5641059826528814e-05, + "loss": 3.8777, + "step": 266240 + }, + { + "epoch": 0.01, + "learning_rate": 4.5632673879018294e-05, + "loss": 3.8907, + "step": 266752 + }, + { + "epoch": 0.01, + "learning_rate": 4.5624287931507774e-05, + "loss": 3.884, + "step": 267264 + }, + { + "epoch": 0.01, + "learning_rate": 4.5615901983997254e-05, + "loss": 3.8704, + "step": 267776 + }, + { + "epoch": 0.01, + "learning_rate": 4.560753241529046e-05, + "loss": 3.8659, + "step": 268288 + }, + { + "epoch": 0.01, + "learning_rate": 4.559914646777994e-05, + "loss": 3.8593, + "step": 268800 + }, + { + "epoch": 0.01, + "learning_rate": 4.559076052026943e-05, + "loss": 3.874, + "step": 269312 + }, + { + "epoch": 0.01, + "learning_rate": 4.558237457275891e-05, + "loss": 3.8838, + "step": 269824 + }, + { + "epoch": 0.01, + "learning_rate": 4.557400500405212e-05, + "loss": 3.8786, + "step": 270336 + }, + { + "epoch": 0.01, + "learning_rate": 4.55656190565416e-05, + "loss": 3.8592, + "step": 270848 + }, + { + "epoch": 0.01, + "learning_rate": 4.555723310903108e-05, + "loss": 3.8583, + "step": 271360 + }, + { + "epoch": 0.01, + "learning_rate": 4.554884716152056e-05, + "loss": 3.8709, + "step": 271872 + }, + { + "epoch": 0.01, + "learning_rate": 4.554047759281377e-05, + "loss": 3.8495, + "step": 272384 + }, + { + "epoch": 0.01, + "learning_rate": 4.553209164530325e-05, + "loss": 3.865, + "step": 272896 + }, + { + "epoch": 0.01, + "learning_rate": 4.552370569779273e-05, + "loss": 3.8695, + "step": 273408 + }, + { + "epoch": 0.01, + "learning_rate": 4.551531975028221e-05, + "loss": 3.8695, + "step": 273920 + }, + { + "epoch": 0.01, + "learning_rate": 4.550693380277169e-05, + "loss": 3.8671, + "step": 274432 + }, + { + "epoch": 0.02, + "learning_rate": 4.54985642340649e-05, + "loss": 3.8718, + "step": 274944 + }, + { + "epoch": 0.02, + "learning_rate": 4.5490178286554384e-05, + "loss": 3.8547, + "step": 275456 + }, + { + "epoch": 0.02, + "learning_rate": 4.5481792339043864e-05, + "loss": 3.867, + "step": 275968 + }, + { + "epoch": 0.02, + "learning_rate": 4.5473406391533343e-05, + "loss": 3.8626, + "step": 276480 + }, + { + "epoch": 0.02, + "learning_rate": 4.5465020444022823e-05, + "loss": 3.8575, + "step": 276992 + }, + { + "epoch": 0.02, + "learning_rate": 4.545665087531603e-05, + "loss": 3.8564, + "step": 277504 + }, + { + "epoch": 0.02, + "learning_rate": 4.544826492780551e-05, + "loss": 3.8727, + "step": 278016 + }, + { + "epoch": 0.02, + "learning_rate": 4.543987898029499e-05, + "loss": 3.8723, + "step": 278528 + }, + { + "epoch": 0.02, + "learning_rate": 4.543149303278447e-05, + "loss": 3.8671, + "step": 279040 + }, + { + "epoch": 0.02, + "learning_rate": 4.542312346407768e-05, + "loss": 3.8592, + "step": 279552 + }, + { + "epoch": 0.02, + "learning_rate": 4.541473751656716e-05, + "loss": 3.8693, + "step": 280064 + }, + { + "epoch": 0.02, + "learning_rate": 4.540635156905664e-05, + "loss": 3.8535, + "step": 280576 + }, + { + "epoch": 0.02, + "learning_rate": 4.539796562154612e-05, + "loss": 3.8646, + "step": 281088 + }, + { + "epoch": 0.02, + "learning_rate": 4.538959605283933e-05, + "loss": 3.8725, + "step": 281600 + }, + { + "epoch": 0.02, + "learning_rate": 4.538121010532882e-05, + "loss": 3.859, + "step": 282112 + }, + { + "epoch": 0.02, + "learning_rate": 4.53728241578183e-05, + "loss": 3.8731, + "step": 282624 + }, + { + "epoch": 0.02, + "learning_rate": 4.536443821030778e-05, + "loss": 3.8412, + "step": 283136 + }, + { + "epoch": 0.02, + "learning_rate": 4.5356068641600986e-05, + "loss": 3.8454, + "step": 283648 + }, + { + "epoch": 0.02, + "learning_rate": 4.5347682694090466e-05, + "loss": 3.8549, + "step": 284160 + }, + { + "epoch": 0.02, + "learning_rate": 4.5339296746579946e-05, + "loss": 3.856, + "step": 284672 + }, + { + "epoch": 0.02, + "learning_rate": 4.5330910799069426e-05, + "loss": 3.8652, + "step": 285184 + }, + { + "epoch": 0.02, + "learning_rate": 4.5322541230362635e-05, + "loss": 3.8502, + "step": 285696 + }, + { + "epoch": 0.02, + "learning_rate": 4.5314155282852115e-05, + "loss": 3.8467, + "step": 286208 + }, + { + "epoch": 0.02, + "learning_rate": 4.5305769335341595e-05, + "loss": 3.856, + "step": 286720 + }, + { + "epoch": 0.02, + "learning_rate": 4.5297383387831075e-05, + "loss": 3.868, + "step": 287232 + }, + { + "epoch": 0.02, + "learning_rate": 4.5288997440320555e-05, + "loss": 3.8599, + "step": 287744 + }, + { + "epoch": 0.02, + "learning_rate": 4.528062787161377e-05, + "loss": 3.8654, + "step": 288256 + }, + { + "epoch": 0.02, + "learning_rate": 4.527224192410325e-05, + "loss": 3.849, + "step": 288768 + }, + { + "epoch": 0.02, + "learning_rate": 4.526385597659273e-05, + "loss": 3.8518, + "step": 289280 + }, + { + "epoch": 0.02, + "learning_rate": 4.525547002908221e-05, + "loss": 3.8684, + "step": 289792 + }, + { + "epoch": 0.02, + "learning_rate": 4.524710046037542e-05, + "loss": 3.8491, + "step": 290304 + }, + { + "epoch": 0.02, + "learning_rate": 4.52387145128649e-05, + "loss": 3.8464, + "step": 290816 + }, + { + "epoch": 0.02, + "learning_rate": 4.523032856535438e-05, + "loss": 3.8499, + "step": 291328 + }, + { + "epoch": 0.02, + "learning_rate": 4.522194261784386e-05, + "loss": 3.8455, + "step": 291840 + }, + { + "epoch": 0.02, + "learning_rate": 4.521357304913707e-05, + "loss": 3.8545, + "step": 292352 + }, + { + "epoch": 0.02, + "learning_rate": 4.520518710162655e-05, + "loss": 3.8536, + "step": 292864 + }, + { + "epoch": 0.02, + "learning_rate": 4.519680115411603e-05, + "loss": 3.8655, + "step": 293376 + }, + { + "epoch": 0.02, + "learning_rate": 4.518841520660551e-05, + "loss": 3.8454, + "step": 293888 + }, + { + "epoch": 0.02, + "learning_rate": 4.5180045637898725e-05, + "loss": 3.8429, + "step": 294400 + }, + { + "epoch": 0.02, + "learning_rate": 4.5171659690388204e-05, + "loss": 3.8703, + "step": 294912 + }, + { + "epoch": 0.02, + "learning_rate": 4.5163273742877684e-05, + "loss": 3.8464, + "step": 295424 + }, + { + "epoch": 0.02, + "learning_rate": 4.515488779536716e-05, + "loss": 3.8594, + "step": 295936 + }, + { + "epoch": 0.02, + "learning_rate": 4.5146518226660373e-05, + "loss": 3.8551, + "step": 296448 + }, + { + "epoch": 0.02, + "learning_rate": 4.5138132279149853e-05, + "loss": 3.8633, + "step": 296960 + }, + { + "epoch": 0.02, + "learning_rate": 4.5129746331639333e-05, + "loss": 3.8553, + "step": 297472 + }, + { + "epoch": 0.02, + "learning_rate": 4.5121360384128807e-05, + "loss": 3.846, + "step": 297984 + }, + { + "epoch": 0.02, + "learning_rate": 4.5112974436618287e-05, + "loss": 3.8403, + "step": 298496 + }, + { + "epoch": 0.02, + "learning_rate": 4.51046048679115e-05, + "loss": 3.8428, + "step": 299008 + }, + { + "epoch": 0.02, + "learning_rate": 4.5096218920400976e-05, + "loss": 3.853, + "step": 299520 + }, + { + "epoch": 0.02, + "learning_rate": 4.508783297289046e-05, + "loss": 3.8612, + "step": 300032 + }, + { + "epoch": 0.02, + "learning_rate": 4.507944702537994e-05, + "loss": 3.8532, + "step": 300544 + }, + { + "epoch": 0.02, + "learning_rate": 4.507107745667316e-05, + "loss": 3.8569, + "step": 301056 + }, + { + "epoch": 0.02, + "learning_rate": 4.506269150916263e-05, + "loss": 3.8424, + "step": 301568 + }, + { + "epoch": 0.02, + "learning_rate": 4.505430556165211e-05, + "loss": 3.8482, + "step": 302080 + }, + { + "epoch": 0.02, + "learning_rate": 4.504591961414159e-05, + "loss": 3.8351, + "step": 302592 + }, + { + "epoch": 0.02, + "learning_rate": 4.50375500454348e-05, + "loss": 3.8513, + "step": 303104 + }, + { + "epoch": 0.02, + "learning_rate": 4.502916409792428e-05, + "loss": 3.8542, + "step": 303616 + }, + { + "epoch": 0.02, + "learning_rate": 4.502077815041376e-05, + "loss": 3.855, + "step": 304128 + }, + { + "epoch": 0.02, + "learning_rate": 4.501239220290324e-05, + "loss": 3.8434, + "step": 304640 + }, + { + "epoch": 0.02, + "learning_rate": 4.500402263419645e-05, + "loss": 3.8415, + "step": 305152 + }, + { + "epoch": 0.03, + "eval_loss": 3.906484603881836, + "eval_runtime": 580.3968, + "eval_samples_per_second": 657.466, + "eval_steps_per_second": 20.546, + "step": 305276 + }, + { + "epoch": 0.0, + "learning_rate": 4.499563668668593e-05, + "loss": 3.8513, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.4987250739175416e-05, + "loss": 3.8466, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.4978864791664896e-05, + "loss": 3.8407, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.4970478844154376e-05, + "loss": 3.8396, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.4962092896643856e-05, + "loss": 3.842, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.4953706949133336e-05, + "loss": 3.827, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.4945321001622816e-05, + "loss": 3.8331, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.4936935054112296e-05, + "loss": 3.8396, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.4928565485405505e-05, + "loss": 3.8383, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.4920195916698714e-05, + "loss": 3.8418, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.4911809969188194e-05, + "loss": 3.8398, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.4903424021677674e-05, + "loss": 3.8354, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.4895038074167154e-05, + "loss": 3.8368, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.4886652126656634e-05, + "loss": 3.844, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.4878266179146114e-05, + "loss": 3.8334, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.48698802316356e-05, + "loss": 3.8262, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486149428412508e-05, + "loss": 3.8271, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.485312471541829e-05, + "loss": 3.8387, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.484473876790777e-05, + "loss": 3.8331, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.483635282039725e-05, + "loss": 3.845, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.482796687288673e-05, + "loss": 3.8312, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481959730417994e-05, + "loss": 3.8406, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481121135666942e-05, + "loss": 3.8334, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.48028254091589e-05, + "loss": 3.8357, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479443946164838e-05, + "loss": 3.832, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478605351413786e-05, + "loss": 3.8299, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477768394543107e-05, + "loss": 3.8374, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476929799792055e-05, + "loss": 3.8218, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.4760912050410034e-05, + "loss": 3.8356, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475254248170324e-05, + "loss": 3.8267, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474415653419272e-05, + "loss": 3.8221, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.47357705866822e-05, + "loss": 3.8326, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472738463917168e-05, + "loss": 3.8397, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.471899869166116e-05, + "loss": 3.8299, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.471062912295437e-05, + "loss": 3.8262, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.470224317544385e-05, + "loss": 3.8294, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469385722793333e-05, + "loss": 3.8309, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468547128042281e-05, + "loss": 3.8405, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.467710171171602e-05, + "loss": 3.8252, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.46687157642055e-05, + "loss": 3.8133, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.466032981669499e-05, + "loss": 3.8195, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.465194386918447e-05, + "loss": 3.8156, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464357430047768e-05, + "loss": 3.8316, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463518835296716e-05, + "loss": 3.8215, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.462680240545664e-05, + "loss": 3.8306, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461841645794611e-05, + "loss": 3.8242, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.4610046889239326e-05, + "loss": 3.8225, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.4601660941728806e-05, + "loss": 3.8323, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.4593274994218286e-05, + "loss": 3.8118, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.458488904670776e-05, + "loss": 3.8066, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.4576519478000975e-05, + "loss": 3.8183, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.4568133530490455e-05, + "loss": 3.8226, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.455974758297994e-05, + "loss": 3.809, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.4551361635469415e-05, + "loss": 3.8273, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.454299206676263e-05, + "loss": 3.8103, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.453460611925211e-05, + "loss": 3.8043, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.4526220171741584e-05, + "loss": 3.8176, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.4517834224231064e-05, + "loss": 3.8079, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.450946465552428e-05, + "loss": 3.825, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.450107870801376e-05, + "loss": 3.8196, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.449269276050323e-05, + "loss": 3.7992, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448430681299271e-05, + "loss": 3.8134, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.447593724428593e-05, + "loss": 3.8092, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446755129677541e-05, + "loss": 3.8222, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445916534926489e-05, + "loss": 3.8048, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445077940175437e-05, + "loss": 3.8139, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.4442409833047584e-05, + "loss": 3.7997, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.443402388553706e-05, + "loss": 3.8156, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.442563793802654e-05, + "loss": 3.8038, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441725199051602e-05, + "loss": 3.806, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.440888242180923e-05, + "loss": 3.8152, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.4400496474298706e-05, + "loss": 3.8107, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.4392110526788186e-05, + "loss": 3.8175, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.4383724579277666e-05, + "loss": 3.828, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437535501057088e-05, + "loss": 3.8242, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.436696906306036e-05, + "loss": 3.8119, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435858311554984e-05, + "loss": 3.8061, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.435019716803932e-05, + "loss": 3.8005, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.434182759933253e-05, + "loss": 3.81, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.433344165182201e-05, + "loss": 3.8251, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.432505570431149e-05, + "loss": 3.8157, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431666975680097e-05, + "loss": 3.8021, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.430830018809418e-05, + "loss": 3.7955, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.429991424058366e-05, + "loss": 3.8148, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.429152829307314e-05, + "loss": 3.7929, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.428314234556262e-05, + "loss": 3.8008, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.4274772776855836e-05, + "loss": 3.8063, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.4266386829345316e-05, + "loss": 3.8087, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.4258000881834796e-05, + "loss": 3.8116, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.4249614934324276e-05, + "loss": 3.8128, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.4241245365617485e-05, + "loss": 3.798, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.4232859418106965e-05, + "loss": 3.808, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.4224473470596445e-05, + "loss": 3.8045, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.4216087523085925e-05, + "loss": 3.7999, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.4207717954379134e-05, + "loss": 3.7959, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.4199332006868614e-05, + "loss": 3.8147, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.4190946059358094e-05, + "loss": 3.8137, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.4182560111847573e-05, + "loss": 3.8126, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.417419054314079e-05, + "loss": 3.802, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.416580459563027e-05, + "loss": 3.8084, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.415741864811975e-05, + "loss": 3.7958, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.414903270060923e-05, + "loss": 3.8097, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.414066313190244e-05, + "loss": 3.8119, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.413227718439192e-05, + "loss": 3.8029, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.41238912368814e-05, + "loss": 3.8164, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.411550528937088e-05, + "loss": 3.7855, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.410713572066409e-05, + "loss": 3.7895, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409874977315357e-05, + "loss": 3.7944, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.409036382564305e-05, + "loss": 3.7969, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.408197787813253e-05, + "loss": 3.8097, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407360830942574e-05, + "loss": 3.7984, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.406522236191522e-05, + "loss": 3.7855, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.40568364144047e-05, + "loss": 3.7974, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404845046689418e-05, + "loss": 3.8096, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.404008089818739e-05, + "loss": 3.8027, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.403169495067687e-05, + "loss": 3.8098, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402330900316635e-05, + "loss": 3.7949, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.401492305565583e-05, + "loss": 3.7938, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400655348694904e-05, + "loss": 3.8114, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399816753943852e-05, + "loss": 3.7962, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.3989781591928e-05, + "loss": 3.7916, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.398139564441748e-05, + "loss": 3.7918, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.39730260757107e-05, + "loss": 3.7904, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396464012820018e-05, + "loss": 3.7983, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.3956254180689657e-05, + "loss": 3.7987, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.3947868233179137e-05, + "loss": 3.8067, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.3939482285668617e-05, + "loss": 3.7878, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.3931112716961826e-05, + "loss": 3.7896, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.3922726769451306e-05, + "loss": 3.8128, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.3914340821940786e-05, + "loss": 3.7962, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.3905971253233995e-05, + "loss": 3.8028, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.3897585305723475e-05, + "loss": 3.8031, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.3889199358212955e-05, + "loss": 3.8037, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.3880813410702434e-05, + "loss": 3.8029, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.387244384199565e-05, + "loss": 3.7864, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.386405789448513e-05, + "loss": 3.7872, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.385567194697461e-05, + "loss": 3.7931, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.384728599946409e-05, + "loss": 3.7983, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.38389164307573e-05, + "loss": 3.8023, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.383053048324678e-05, + "loss": 3.8009, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.382214453573626e-05, + "loss": 3.8023, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.381375858822574e-05, + "loss": 3.7909, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.380538901951895e-05, + "loss": 3.793, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.379700307200843e-05, + "loss": 3.7798, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378861712449791e-05, + "loss": 3.7986, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.378023117698739e-05, + "loss": 3.8018, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.3771861608280604e-05, + "loss": 3.8012, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.3763475660770084e-05, + "loss": 3.7856, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.3755089713259564e-05, + "loss": 3.7892, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.882150411605835, + "eval_runtime": 556.9633, + "eval_samples_per_second": 685.128, + "eval_steps_per_second": 21.411, + "step": 381595 + }, + { + "epoch": 0.0, + "learning_rate": 4.3746703765749044e-05, + "loss": 3.8027, + "step": 381952 + }, + { + "epoch": 0.0, + "learning_rate": 4.3738317818238524e-05, + "loss": 3.7905, + "step": 382464 + }, + { + "epoch": 0.0, + "learning_rate": 4.3729931870728004e-05, + "loss": 3.7906, + "step": 382976 + }, + { + "epoch": 0.0, + "learning_rate": 4.3721545923217484e-05, + "loss": 3.7853, + "step": 383488 + }, + { + "epoch": 0.0, + "learning_rate": 4.371315997570696e-05, + "loss": 3.7872, + "step": 384000 + }, + { + "epoch": 0.0, + "learning_rate": 4.370477402819644e-05, + "loss": 3.7755, + "step": 384512 + }, + { + "epoch": 0.0, + "learning_rate": 4.369638808068592e-05, + "loss": 3.7822, + "step": 385024 + }, + { + "epoch": 0.0, + "learning_rate": 4.36880021331754e-05, + "loss": 3.7804, + "step": 385536 + }, + { + "epoch": 0.0, + "learning_rate": 4.3679632564468606e-05, + "loss": 3.7874, + "step": 386048 + }, + { + "epoch": 0.0, + "learning_rate": 4.367126299576182e-05, + "loss": 3.7934, + "step": 386560 + }, + { + "epoch": 0.0, + "learning_rate": 4.36628770482513e-05, + "loss": 3.7848, + "step": 387072 + }, + { + "epoch": 0.0, + "learning_rate": 4.365449110074079e-05, + "loss": 3.7816, + "step": 387584 + }, + { + "epoch": 0.0, + "learning_rate": 4.364610515323026e-05, + "loss": 3.7882, + "step": 388096 + }, + { + "epoch": 0.0, + "learning_rate": 4.363771920571974e-05, + "loss": 3.7894, + "step": 388608 + }, + { + "epoch": 0.0, + "learning_rate": 4.362933325820922e-05, + "loss": 3.7808, + "step": 389120 + }, + { + "epoch": 0.0, + "learning_rate": 4.36209473106987e-05, + "loss": 3.7744, + "step": 389632 + }, + { + "epoch": 0.0, + "learning_rate": 4.361256136318818e-05, + "loss": 3.7749, + "step": 390144 + }, + { + "epoch": 0.0, + "learning_rate": 4.360419179448139e-05, + "loss": 3.7837, + "step": 390656 + }, + { + "epoch": 0.0, + "learning_rate": 4.359580584697087e-05, + "loss": 3.7825, + "step": 391168 + }, + { + "epoch": 0.0, + "learning_rate": 4.358741989946035e-05, + "loss": 3.7945, + "step": 391680 + }, + { + "epoch": 0.0, + "learning_rate": 4.357903395194983e-05, + "loss": 3.7813, + "step": 392192 + }, + { + "epoch": 0.0, + "learning_rate": 4.357066438324304e-05, + "loss": 3.79, + "step": 392704 + }, + { + "epoch": 0.0, + "learning_rate": 4.3562278435732526e-05, + "loss": 3.785, + "step": 393216 + }, + { + "epoch": 0.0, + "learning_rate": 4.3553892488222006e-05, + "loss": 3.7825, + "step": 393728 + }, + { + "epoch": 0.0, + "learning_rate": 4.3545506540711486e-05, + "loss": 3.7793, + "step": 394240 + }, + { + "epoch": 0.0, + "learning_rate": 4.3537136972004695e-05, + "loss": 3.7807, + "step": 394752 + }, + { + "epoch": 0.0, + "learning_rate": 4.3528751024494175e-05, + "loss": 3.7883, + "step": 395264 + }, + { + "epoch": 0.0, + "learning_rate": 4.3520365076983655e-05, + "loss": 3.7694, + "step": 395776 + }, + { + "epoch": 0.0, + "learning_rate": 4.3511979129473135e-05, + "loss": 3.7873, + "step": 396288 + }, + { + "epoch": 0.0, + "learning_rate": 4.3503609560766344e-05, + "loss": 3.7759, + "step": 396800 + }, + { + "epoch": 0.01, + "learning_rate": 4.3495223613255824e-05, + "loss": 3.7676, + "step": 397312 + }, + { + "epoch": 0.01, + "learning_rate": 4.3486837665745304e-05, + "loss": 3.7836, + "step": 397824 + }, + { + "epoch": 0.01, + "learning_rate": 4.3478451718234784e-05, + "loss": 3.7849, + "step": 398336 + }, + { + "epoch": 0.01, + "learning_rate": 4.347008214952799e-05, + "loss": 3.7845, + "step": 398848 + }, + { + "epoch": 0.01, + "learning_rate": 4.346169620201748e-05, + "loss": 3.777, + "step": 399360 + }, + { + "epoch": 0.01, + "learning_rate": 4.345331025450696e-05, + "loss": 3.7759, + "step": 399872 + }, + { + "epoch": 0.01, + "learning_rate": 4.344492430699644e-05, + "loss": 3.7781, + "step": 400384 + }, + { + "epoch": 0.01, + "learning_rate": 4.343655473828965e-05, + "loss": 3.7933, + "step": 400896 + }, + { + "epoch": 0.01, + "learning_rate": 4.342816879077913e-05, + "loss": 3.7788, + "step": 401408 + }, + { + "epoch": 0.01, + "learning_rate": 4.341978284326861e-05, + "loss": 3.764, + "step": 401920 + }, + { + "epoch": 0.01, + "learning_rate": 4.341139689575809e-05, + "loss": 3.7701, + "step": 402432 + }, + { + "epoch": 0.01, + "learning_rate": 4.34030273270513e-05, + "loss": 3.763, + "step": 402944 + }, + { + "epoch": 0.01, + "learning_rate": 4.339464137954078e-05, + "loss": 3.7811, + "step": 403456 + }, + { + "epoch": 0.01, + "learning_rate": 4.338625543203026e-05, + "loss": 3.7742, + "step": 403968 + }, + { + "epoch": 0.01, + "learning_rate": 4.337786948451974e-05, + "loss": 3.7786, + "step": 404480 + }, + { + "epoch": 0.01, + "learning_rate": 4.336949991581295e-05, + "loss": 3.7772, + "step": 404992 + }, + { + "epoch": 0.01, + "learning_rate": 4.3361113968302434e-05, + "loss": 3.7743, + "step": 405504 + }, + { + "epoch": 0.01, + "learning_rate": 4.3352728020791914e-05, + "loss": 3.7847, + "step": 406016 + }, + { + "epoch": 0.01, + "learning_rate": 4.3344342073281393e-05, + "loss": 3.7632, + "step": 406528 + }, + { + "epoch": 0.01, + "learning_rate": 4.33359725045746e-05, + "loss": 3.7557, + "step": 407040 + }, + { + "epoch": 0.01, + "learning_rate": 4.332758655706408e-05, + "loss": 3.7741, + "step": 407552 + }, + { + "epoch": 0.01, + "learning_rate": 4.331920060955356e-05, + "loss": 3.7681, + "step": 408064 + }, + { + "epoch": 0.01, + "learning_rate": 4.331081466204304e-05, + "loss": 3.7646, + "step": 408576 + }, + { + "epoch": 0.01, + "learning_rate": 4.330244509333625e-05, + "loss": 3.7763, + "step": 409088 + }, + { + "epoch": 0.01, + "learning_rate": 4.329405914582573e-05, + "loss": 3.7602, + "step": 409600 + }, + { + "epoch": 0.01, + "learning_rate": 4.328567319831521e-05, + "loss": 3.7598, + "step": 410112 + }, + { + "epoch": 0.01, + "learning_rate": 4.327728725080469e-05, + "loss": 3.7666, + "step": 410624 + }, + { + "epoch": 0.01, + "learning_rate": 4.32689176820979e-05, + "loss": 3.7597, + "step": 411136 + }, + { + "epoch": 0.01, + "learning_rate": 4.326053173458739e-05, + "loss": 3.7748, + "step": 411648 + }, + { + "epoch": 0.01, + "learning_rate": 4.325214578707687e-05, + "loss": 3.7674, + "step": 412160 + }, + { + "epoch": 0.01, + "learning_rate": 4.324375983956635e-05, + "loss": 3.7592, + "step": 412672 + }, + { + "epoch": 0.01, + "learning_rate": 4.3235390270859556e-05, + "loss": 3.7619, + "step": 413184 + }, + { + "epoch": 0.01, + "learning_rate": 4.3227004323349036e-05, + "loss": 3.755, + "step": 413696 + }, + { + "epoch": 0.01, + "learning_rate": 4.3218618375838516e-05, + "loss": 3.7765, + "step": 414208 + }, + { + "epoch": 0.01, + "learning_rate": 4.3210232428327996e-05, + "loss": 3.7586, + "step": 414720 + }, + { + "epoch": 0.01, + "learning_rate": 4.3201862859621205e-05, + "loss": 3.772, + "step": 415232 + }, + { + "epoch": 0.01, + "learning_rate": 4.3193476912110685e-05, + "loss": 3.7494, + "step": 415744 + }, + { + "epoch": 0.01, + "learning_rate": 4.3185090964600165e-05, + "loss": 3.7657, + "step": 416256 + }, + { + "epoch": 0.01, + "learning_rate": 4.3176705017089645e-05, + "loss": 3.7566, + "step": 416768 + }, + { + "epoch": 0.01, + "learning_rate": 4.3168335448382854e-05, + "loss": 3.7575, + "step": 417280 + }, + { + "epoch": 0.01, + "learning_rate": 4.315994950087234e-05, + "loss": 3.7659, + "step": 417792 + }, + { + "epoch": 0.01, + "learning_rate": 4.315156355336182e-05, + "loss": 3.7646, + "step": 418304 + }, + { + "epoch": 0.01, + "learning_rate": 4.31431776058513e-05, + "loss": 3.7666, + "step": 418816 + }, + { + "epoch": 0.01, + "learning_rate": 4.313480803714451e-05, + "loss": 3.7795, + "step": 419328 + }, + { + "epoch": 0.01, + "learning_rate": 4.312642208963399e-05, + "loss": 3.7778, + "step": 419840 + }, + { + "epoch": 0.01, + "learning_rate": 4.311803614212347e-05, + "loss": 3.769, + "step": 420352 + }, + { + "epoch": 0.01, + "learning_rate": 4.310965019461295e-05, + "loss": 3.759, + "step": 420864 + }, + { + "epoch": 0.01, + "learning_rate": 4.310128062590616e-05, + "loss": 3.7557, + "step": 421376 + }, + { + "epoch": 0.01, + "learning_rate": 4.309289467839564e-05, + "loss": 3.76, + "step": 421888 + }, + { + "epoch": 0.01, + "learning_rate": 4.308450873088512e-05, + "loss": 3.7777, + "step": 422400 + }, + { + "epoch": 0.01, + "learning_rate": 4.30761227833746e-05, + "loss": 3.767, + "step": 422912 + }, + { + "epoch": 0.01, + "learning_rate": 4.306775321466781e-05, + "loss": 3.7578, + "step": 423424 + }, + { + "epoch": 0.01, + "learning_rate": 4.305936726715729e-05, + "loss": 3.7459, + "step": 423936 + }, + { + "epoch": 0.01, + "learning_rate": 4.3050981319646775e-05, + "loss": 3.7729, + "step": 424448 + }, + { + "epoch": 0.01, + "learning_rate": 4.3042595372136254e-05, + "loss": 3.7422, + "step": 424960 + }, + { + "epoch": 0.01, + "learning_rate": 4.3034225803429464e-05, + "loss": 3.7585, + "step": 425472 + }, + { + "epoch": 0.01, + "learning_rate": 4.3025839855918944e-05, + "loss": 3.7599, + "step": 425984 + }, + { + "epoch": 0.01, + "learning_rate": 4.3017453908408424e-05, + "loss": 3.7628, + "step": 426496 + }, + { + "epoch": 0.01, + "learning_rate": 4.3009067960897903e-05, + "loss": 3.7634, + "step": 427008 + }, + { + "epoch": 0.02, + "learning_rate": 4.300069839219111e-05, + "loss": 3.7708, + "step": 427520 + }, + { + "epoch": 0.02, + "learning_rate": 4.299231244468059e-05, + "loss": 3.7496, + "step": 428032 + }, + { + "epoch": 0.02, + "learning_rate": 4.298392649717007e-05, + "loss": 3.7594, + "step": 428544 + }, + { + "epoch": 0.02, + "learning_rate": 4.297554054965955e-05, + "loss": 3.7615, + "step": 429056 + }, + { + "epoch": 0.02, + "learning_rate": 4.296717098095276e-05, + "loss": 3.7544, + "step": 429568 + }, + { + "epoch": 0.02, + "learning_rate": 4.295878503344224e-05, + "loss": 3.752, + "step": 430080 + }, + { + "epoch": 0.02, + "learning_rate": 4.295039908593173e-05, + "loss": 3.769, + "step": 430592 + }, + { + "epoch": 0.02, + "learning_rate": 4.294201313842121e-05, + "loss": 3.7649, + "step": 431104 + }, + { + "epoch": 0.02, + "learning_rate": 4.293364356971442e-05, + "loss": 3.7723, + "step": 431616 + }, + { + "epoch": 0.02, + "learning_rate": 4.29252576222039e-05, + "loss": 3.7568, + "step": 432128 + }, + { + "epoch": 0.02, + "learning_rate": 4.291687167469338e-05, + "loss": 3.7609, + "step": 432640 + }, + { + "epoch": 0.02, + "learning_rate": 4.290848572718286e-05, + "loss": 3.7502, + "step": 433152 + }, + { + "epoch": 0.02, + "learning_rate": 4.2900116158476066e-05, + "loss": 3.7628, + "step": 433664 + }, + { + "epoch": 0.02, + "learning_rate": 4.2891730210965546e-05, + "loss": 3.7692, + "step": 434176 + }, + { + "epoch": 0.02, + "learning_rate": 4.2883344263455026e-05, + "loss": 3.7558, + "step": 434688 + }, + { + "epoch": 0.02, + "learning_rate": 4.2874958315944506e-05, + "loss": 3.7702, + "step": 435200 + }, + { + "epoch": 0.02, + "learning_rate": 4.2866588747237715e-05, + "loss": 3.7399, + "step": 435712 + }, + { + "epoch": 0.02, + "learning_rate": 4.2858202799727195e-05, + "loss": 3.7484, + "step": 436224 + }, + { + "epoch": 0.02, + "learning_rate": 4.284981685221668e-05, + "loss": 3.7464, + "step": 436736 + }, + { + "epoch": 0.02, + "learning_rate": 4.284143090470616e-05, + "loss": 3.7535, + "step": 437248 + }, + { + "epoch": 0.02, + "learning_rate": 4.283306133599937e-05, + "loss": 3.765, + "step": 437760 + }, + { + "epoch": 0.02, + "learning_rate": 4.282467538848885e-05, + "loss": 3.7597, + "step": 438272 + }, + { + "epoch": 0.02, + "learning_rate": 4.281628944097833e-05, + "loss": 3.7331, + "step": 438784 + }, + { + "epoch": 0.02, + "learning_rate": 4.280790349346781e-05, + "loss": 3.7576, + "step": 439296 + }, + { + "epoch": 0.02, + "learning_rate": 4.279953392476102e-05, + "loss": 3.7638, + "step": 439808 + }, + { + "epoch": 0.02, + "learning_rate": 4.27911479772505e-05, + "loss": 3.7599, + "step": 440320 + }, + { + "epoch": 0.02, + "learning_rate": 4.278276202973998e-05, + "loss": 3.7633, + "step": 440832 + }, + { + "epoch": 0.02, + "learning_rate": 4.277437608222945e-05, + "loss": 3.7498, + "step": 441344 + }, + { + "epoch": 0.02, + "learning_rate": 4.276600651352267e-05, + "loss": 3.7492, + "step": 441856 + }, + { + "epoch": 0.02, + "learning_rate": 4.275762056601215e-05, + "loss": 3.7681, + "step": 442368 + }, + { + "epoch": 0.02, + "learning_rate": 4.2749234618501636e-05, + "loss": 3.7506, + "step": 442880 + }, + { + "epoch": 0.02, + "learning_rate": 4.274084867099111e-05, + "loss": 3.7486, + "step": 443392 + }, + { + "epoch": 0.02, + "learning_rate": 4.2732479102284325e-05, + "loss": 3.7433, + "step": 443904 + }, + { + "epoch": 0.02, + "learning_rate": 4.2724093154773805e-05, + "loss": 3.7493, + "step": 444416 + }, + { + "epoch": 0.02, + "learning_rate": 4.2715707207263285e-05, + "loss": 3.7537, + "step": 444928 + }, + { + "epoch": 0.02, + "learning_rate": 4.270732125975276e-05, + "loss": 3.7549, + "step": 445440 + }, + { + "epoch": 0.02, + "learning_rate": 4.2698951691045974e-05, + "loss": 3.7627, + "step": 445952 + }, + { + "epoch": 0.02, + "learning_rate": 4.2690565743535454e-05, + "loss": 3.7479, + "step": 446464 + }, + { + "epoch": 0.02, + "learning_rate": 4.268217979602493e-05, + "loss": 3.7464, + "step": 446976 + }, + { + "epoch": 0.02, + "learning_rate": 4.267379384851441e-05, + "loss": 3.7666, + "step": 447488 + }, + { + "epoch": 0.02, + "learning_rate": 4.266542427980762e-05, + "loss": 3.7509, + "step": 448000 + }, + { + "epoch": 0.02, + "learning_rate": 4.26570383322971e-05, + "loss": 3.7554, + "step": 448512 + }, + { + "epoch": 0.02, + "learning_rate": 4.264865238478658e-05, + "loss": 3.7607, + "step": 449024 + }, + { + "epoch": 0.02, + "learning_rate": 4.264026643727606e-05, + "loss": 3.7619, + "step": 449536 + }, + { + "epoch": 0.02, + "learning_rate": 4.263189686856928e-05, + "loss": 3.7605, + "step": 450048 + }, + { + "epoch": 0.02, + "learning_rate": 4.262351092105876e-05, + "loss": 3.7477, + "step": 450560 + }, + { + "epoch": 0.02, + "learning_rate": 4.261512497354823e-05, + "loss": 3.7401, + "step": 451072 + }, + { + "epoch": 0.02, + "learning_rate": 4.260673902603771e-05, + "loss": 3.7472, + "step": 451584 + }, + { + "epoch": 0.02, + "learning_rate": 4.259836945733093e-05, + "loss": 3.7542, + "step": 452096 + }, + { + "epoch": 0.02, + "learning_rate": 4.25899835098204e-05, + "loss": 3.7619, + "step": 452608 + }, + { + "epoch": 0.02, + "learning_rate": 4.258159756230988e-05, + "loss": 3.7558, + "step": 453120 + }, + { + "epoch": 0.02, + "learning_rate": 4.2573227993603096e-05, + "loss": 3.7549, + "step": 453632 + }, + { + "epoch": 0.02, + "learning_rate": 4.2564842046092576e-05, + "loss": 3.7515, + "step": 454144 + }, + { + "epoch": 0.02, + "learning_rate": 4.2556456098582056e-05, + "loss": 3.7525, + "step": 454656 + }, + { + "epoch": 0.02, + "learning_rate": 4.2548070151071536e-05, + "loss": 3.7406, + "step": 455168 + }, + { + "epoch": 0.02, + "learning_rate": 4.253970058236475e-05, + "loss": 3.7489, + "step": 455680 + }, + { + "epoch": 0.02, + "learning_rate": 4.253131463485423e-05, + "loss": 3.7612, + "step": 456192 + }, + { + "epoch": 0.02, + "learning_rate": 4.2522928687343705e-05, + "loss": 3.7585, + "step": 456704 + }, + { + "epoch": 0.02, + "learning_rate": 4.2514542739833185e-05, + "loss": 3.7439, + "step": 457216 + }, + { + "epoch": 0.02, + "learning_rate": 4.25061731711264e-05, + "loss": 3.7441, + "step": 457728 + }, + { + "epoch": 0.03, + "eval_loss": 3.8657073974609375, + "eval_runtime": 571.2959, + "eval_samples_per_second": 667.939, + "eval_steps_per_second": 20.874, + "step": 457914 + }, + { + "epoch": 0.0, + "learning_rate": 4.2497787223615874e-05, + "loss": 3.7646, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.2489401276105354e-05, + "loss": 3.7485, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.2481015328594834e-05, + "loss": 3.7449, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.2472629381084314e-05, + "loss": 3.7467, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.2464243433573794e-05, + "loss": 3.7404, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.245585748606328e-05, + "loss": 3.7372, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.244747153855276e-05, + "loss": 3.7372, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.243908559104224e-05, + "loss": 3.7417, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.243071602233545e-05, + "loss": 3.7471, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.242233007482493e-05, + "loss": 3.7493, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.241396050611814e-05, + "loss": 3.7467, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.240557455860762e-05, + "loss": 3.7353, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.23971886110971e-05, + "loss": 3.7512, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.238880266358658e-05, + "loss": 3.7461, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.238041671607606e-05, + "loss": 3.7437, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.237203076856554e-05, + "loss": 3.7289, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.236364482105502e-05, + "loss": 3.7304, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.2355275252348234e-05, + "loss": 3.7458, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.2346889304837714e-05, + "loss": 3.7394, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.2338503357327194e-05, + "loss": 3.753, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.2330117409816674e-05, + "loss": 3.7397, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232174784110988e-05, + "loss": 3.7485, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.231336189359936e-05, + "loss": 3.7441, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.230497594608884e-05, + "loss": 3.7417, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.229660637738205e-05, + "loss": 3.7362, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.228822042987153e-05, + "loss": 3.7384, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.227983448236101e-05, + "loss": 3.7472, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.227144853485049e-05, + "loss": 3.7297, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.226306258733997e-05, + "loss": 3.7453, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.225467663982945e-05, + "loss": 3.7366, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.224629069231893e-05, + "loss": 3.7266, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.223790474480841e-05, + "loss": 3.7404, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.222953517610163e-05, + "loss": 3.7457, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.222114922859111e-05, + "loss": 3.747, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.221276328108059e-05, + "loss": 3.7356, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.220437733357006e-05, + "loss": 3.7391, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.219600776486328e-05, + "loss": 3.7379, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.218762181735276e-05, + "loss": 3.7472, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.217923586984224e-05, + "loss": 3.7408, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.217084992233171e-05, + "loss": 3.7225, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.2162480353624926e-05, + "loss": 3.7288, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.2154094406114406e-05, + "loss": 3.7236, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.2145708458603886e-05, + "loss": 3.7446, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.2137322511093366e-05, + "loss": 3.7348, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.212895294238658e-05, + "loss": 3.7372, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.212056699487606e-05, + "loss": 3.7408, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.2112181047365535e-05, + "loss": 3.7335, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.210381147865875e-05, + "loss": 3.7441, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209542553114823e-05, + "loss": 3.7269, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208703958363771e-05, + "loss": 3.719, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.2078653636127184e-05, + "loss": 3.7334, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.2070267688616664e-05, + "loss": 3.7245, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.2061881741106144e-05, + "loss": 3.7301, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.2053495793595623e-05, + "loss": 3.7314, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.204512622488884e-05, + "loss": 3.7256, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.203674027737832e-05, + "loss": 3.7197, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.20283543298678e-05, + "loss": 3.7247, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.201996838235728e-05, + "loss": 3.7243, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.201158243484676e-05, + "loss": 3.7349, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.200319648733624e-05, + "loss": 3.7274, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.199482691862945e-05, + "loss": 3.7181, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.198644097111893e-05, + "loss": 3.7254, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.197805502360841e-05, + "loss": 3.711, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.196966907609789e-05, + "loss": 3.7409, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.196128312858737e-05, + "loss": 3.7218, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195289718107685e-05, + "loss": 3.7278, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.194451123356633e-05, + "loss": 3.7165, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.193612528605581e-05, + "loss": 3.7185, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.1927755717349024e-05, + "loss": 3.7212, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.1919369769838504e-05, + "loss": 3.7202, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.1910983822327984e-05, + "loss": 3.7287, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.1902597874817464e-05, + "loss": 3.7258, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.189422830611067e-05, + "loss": 3.729, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.188584235860015e-05, + "loss": 3.7405, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.187745641108963e-05, + "loss": 3.7364, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.186907046357911e-05, + "loss": 3.7321, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.186070089487232e-05, + "loss": 3.7229, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.18523149473618e-05, + "loss": 3.7172, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.184392899985128e-05, + "loss": 3.7224, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.183554305234076e-05, + "loss": 3.7382, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.182717348363398e-05, + "loss": 3.7308, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.181878753612346e-05, + "loss": 3.7208, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.181040158861294e-05, + "loss": 3.7068, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.180201564110242e-05, + "loss": 3.7362, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.1793646072395626e-05, + "loss": 3.7026, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.1785260124885106e-05, + "loss": 3.7205, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.1776874177374586e-05, + "loss": 3.7232, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.1768488229864066e-05, + "loss": 3.7226, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.1760118661157275e-05, + "loss": 3.727, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.1751732713646755e-05, + "loss": 3.7345, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.1743346766136235e-05, + "loss": 3.7084, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.1734960818625715e-05, + "loss": 3.7234, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.172659124991893e-05, + "loss": 3.7245, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.171820530240841e-05, + "loss": 3.7172, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170981935489789e-05, + "loss": 3.7134, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.17014497861911e-05, + "loss": 3.7311, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.169306383868058e-05, + "loss": 3.7289, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.168467789117006e-05, + "loss": 3.7373, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.167629194365954e-05, + "loss": 3.7173, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.166792237495275e-05, + "loss": 3.7251, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.165953642744223e-05, + "loss": 3.7125, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.165115047993171e-05, + "loss": 3.725, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.164276453242119e-05, + "loss": 3.7309, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.1634394963714405e-05, + "loss": 3.7247, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.1626009016203885e-05, + "loss": 3.7301, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.1617623068693365e-05, + "loss": 3.7071, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.1609237121182845e-05, + "loss": 3.7078, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.1600867552476054e-05, + "loss": 3.7066, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.1592481604965534e-05, + "loss": 3.717, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.1584095657455014e-05, + "loss": 3.7273, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.1575709709944494e-05, + "loss": 3.7255, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.15673401412377e-05, + "loss": 3.6943, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155895419372718e-05, + "loss": 3.7204, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.155056824621666e-05, + "loss": 3.7277, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154218229870614e-05, + "loss": 3.7246, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153381272999936e-05, + "loss": 3.7244, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152542678248884e-05, + "loss": 3.7144, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151704083497832e-05, + "loss": 3.7157, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.150865488746779e-05, + "loss": 3.7262, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.150028531876101e-05, + "loss": 3.7186, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.149189937125049e-05, + "loss": 3.7128, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.148351342373997e-05, + "loss": 3.7063, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.147512747622944e-05, + "loss": 3.7112, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.1466757907522656e-05, + "loss": 3.7211, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.1458371960012136e-05, + "loss": 3.7184, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.144998601250161e-05, + "loss": 3.7237, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.1441600064991096e-05, + "loss": 3.7122, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.1433230496284305e-05, + "loss": 3.711, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.142484454877379e-05, + "loss": 3.7306, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.1416458601263265e-05, + "loss": 3.7114, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.1408072653752745e-05, + "loss": 3.7238, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.139970308504596e-05, + "loss": 3.7277, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.139131713753544e-05, + "loss": 3.7223, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.1382931190024914e-05, + "loss": 3.7237, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.1374545242514394e-05, + "loss": 3.7154, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.136617567380761e-05, + "loss": 3.7032, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.135778972629708e-05, + "loss": 3.7109, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.134940377878656e-05, + "loss": 3.7166, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.134101783127604e-05, + "loss": 3.7288, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.133264826256926e-05, + "loss": 3.7169, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.132426231505874e-05, + "loss": 3.7248, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.131587636754822e-05, + "loss": 3.7123, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.13074904200377e-05, + "loss": 3.7166, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.1299120851330915e-05, + "loss": 3.7031, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.129073490382039e-05, + "loss": 3.7152, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128234895630987e-05, + "loss": 3.7269, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.127396300879935e-05, + "loss": 3.7251, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.126559344009256e-05, + "loss": 3.7066, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125720749258204e-05, + "loss": 3.7141, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 3.855856418609619, + "eval_runtime": 612.726, + "eval_samples_per_second": 622.776, + "eval_steps_per_second": 19.462, + "step": 534233 + }, + { + "epoch": 0.0, + "learning_rate": 4.124882154507152e-05, + "loss": 3.7314, + "step": 534528 + }, + { + "epoch": 0.0, + "learning_rate": 4.1240435597561e-05, + "loss": 3.7135, + "step": 535040 + }, + { + "epoch": 0.0, + "learning_rate": 4.1232049650050484e-05, + "loss": 3.7093, + "step": 535552 + }, + { + "epoch": 0.0, + "learning_rate": 4.1223663702539964e-05, + "loss": 3.7144, + "step": 536064 + }, + { + "epoch": 0.0, + "learning_rate": 4.1215277755029444e-05, + "loss": 3.7028, + "step": 536576 + }, + { + "epoch": 0.0, + "learning_rate": 4.1206891807518923e-05, + "loss": 3.7054, + "step": 537088 + }, + { + "epoch": 0.0, + "learning_rate": 4.1198505860008403e-05, + "loss": 3.6981, + "step": 537600 + }, + { + "epoch": 0.0, + "learning_rate": 4.119011991249788e-05, + "loss": 3.7097, + "step": 538112 + }, + { + "epoch": 0.0, + "learning_rate": 4.118175034379109e-05, + "loss": 3.7092, + "step": 538624 + }, + { + "epoch": 0.0, + "learning_rate": 4.117336439628057e-05, + "loss": 3.7139, + "step": 539136 + }, + { + "epoch": 0.0, + "learning_rate": 4.116499482757378e-05, + "loss": 3.7121, + "step": 539648 + }, + { + "epoch": 0.0, + "learning_rate": 4.115660888006326e-05, + "loss": 3.704, + "step": 540160 + }, + { + "epoch": 0.0, + "learning_rate": 4.114822293255274e-05, + "loss": 3.7168, + "step": 540672 + }, + { + "epoch": 0.0, + "learning_rate": 4.113983698504222e-05, + "loss": 3.7078, + "step": 541184 + }, + { + "epoch": 0.0, + "learning_rate": 4.11314510375317e-05, + "loss": 3.7148, + "step": 541696 + }, + { + "epoch": 0.0, + "learning_rate": 4.112306509002118e-05, + "loss": 3.6927, + "step": 542208 + }, + { + "epoch": 0.0, + "learning_rate": 4.111467914251067e-05, + "loss": 3.6981, + "step": 542720 + }, + { + "epoch": 0.0, + "learning_rate": 4.110630957380388e-05, + "loss": 3.71, + "step": 543232 + }, + { + "epoch": 0.0, + "learning_rate": 4.109792362629336e-05, + "loss": 3.7031, + "step": 543744 + }, + { + "epoch": 0.0, + "learning_rate": 4.108953767878284e-05, + "loss": 3.7181, + "step": 544256 + }, + { + "epoch": 0.0, + "learning_rate": 4.108115173127232e-05, + "loss": 3.7087, + "step": 544768 + }, + { + "epoch": 0.0, + "learning_rate": 4.1072782162565526e-05, + "loss": 3.7127, + "step": 545280 + }, + { + "epoch": 0.0, + "learning_rate": 4.1064396215055006e-05, + "loss": 3.7101, + "step": 545792 + }, + { + "epoch": 0.0, + "learning_rate": 4.1056026646348215e-05, + "loss": 3.7061, + "step": 546304 + }, + { + "epoch": 0.0, + "learning_rate": 4.1047640698837695e-05, + "loss": 3.7063, + "step": 546816 + }, + { + "epoch": 0.0, + "learning_rate": 4.1039254751327175e-05, + "loss": 3.7019, + "step": 547328 + }, + { + "epoch": 0.0, + "learning_rate": 4.1030868803816655e-05, + "loss": 3.7122, + "step": 547840 + }, + { + "epoch": 0.0, + "learning_rate": 4.1022482856306135e-05, + "loss": 3.702, + "step": 548352 + }, + { + "epoch": 0.0, + "learning_rate": 4.101409690879562e-05, + "loss": 3.7083, + "step": 548864 + }, + { + "epoch": 0.0, + "learning_rate": 4.10057109612851e-05, + "loss": 3.7017, + "step": 549376 + }, + { + "epoch": 0.01, + "learning_rate": 4.0997325013774575e-05, + "loss": 3.6953, + "step": 549888 + }, + { + "epoch": 0.01, + "learning_rate": 4.098895544506779e-05, + "loss": 3.7078, + "step": 550400 + }, + { + "epoch": 0.01, + "learning_rate": 4.0980585876361e-05, + "loss": 3.7102, + "step": 550912 + }, + { + "epoch": 0.01, + "learning_rate": 4.097219992885048e-05, + "loss": 3.7102, + "step": 551424 + }, + { + "epoch": 0.01, + "learning_rate": 4.096381398133996e-05, + "loss": 3.7071, + "step": 551936 + }, + { + "epoch": 0.01, + "learning_rate": 4.095542803382944e-05, + "loss": 3.7012, + "step": 552448 + }, + { + "epoch": 0.01, + "learning_rate": 4.094704208631892e-05, + "loss": 3.7064, + "step": 552960 + }, + { + "epoch": 0.01, + "learning_rate": 4.093865613880839e-05, + "loss": 3.7113, + "step": 553472 + }, + { + "epoch": 0.01, + "learning_rate": 4.093027019129787e-05, + "loss": 3.7079, + "step": 553984 + }, + { + "epoch": 0.01, + "learning_rate": 4.092188424378736e-05, + "loss": 3.6929, + "step": 554496 + }, + { + "epoch": 0.01, + "learning_rate": 4.0913514675080575e-05, + "loss": 3.6935, + "step": 555008 + }, + { + "epoch": 0.01, + "learning_rate": 4.090512872757005e-05, + "loss": 3.6912, + "step": 555520 + }, + { + "epoch": 0.01, + "learning_rate": 4.0896759158863264e-05, + "loss": 3.7108, + "step": 556032 + }, + { + "epoch": 0.01, + "learning_rate": 4.0888373211352744e-05, + "loss": 3.7025, + "step": 556544 + }, + { + "epoch": 0.01, + "learning_rate": 4.087998726384222e-05, + "loss": 3.7006, + "step": 557056 + }, + { + "epoch": 0.01, + "learning_rate": 4.08716013163317e-05, + "loss": 3.711, + "step": 557568 + }, + { + "epoch": 0.01, + "learning_rate": 4.086321536882118e-05, + "loss": 3.6971, + "step": 558080 + }, + { + "epoch": 0.01, + "learning_rate": 4.085484580011439e-05, + "loss": 3.7126, + "step": 558592 + }, + { + "epoch": 0.01, + "learning_rate": 4.0846459852603867e-05, + "loss": 3.6943, + "step": 559104 + }, + { + "epoch": 0.01, + "learning_rate": 4.0838073905093346e-05, + "loss": 3.6852, + "step": 559616 + }, + { + "epoch": 0.01, + "learning_rate": 4.0829687957582826e-05, + "loss": 3.698, + "step": 560128 + }, + { + "epoch": 0.01, + "learning_rate": 4.082130201007231e-05, + "loss": 3.6974, + "step": 560640 + }, + { + "epoch": 0.01, + "learning_rate": 4.081291606256179e-05, + "loss": 3.6914, + "step": 561152 + }, + { + "epoch": 0.01, + "learning_rate": 4.080453011505127e-05, + "loss": 3.7014, + "step": 561664 + }, + { + "epoch": 0.01, + "learning_rate": 4.079616054634448e-05, + "loss": 3.6958, + "step": 562176 + }, + { + "epoch": 0.01, + "learning_rate": 4.078777459883396e-05, + "loss": 3.6847, + "step": 562688 + }, + { + "epoch": 0.01, + "learning_rate": 4.077938865132344e-05, + "loss": 3.698, + "step": 563200 + }, + { + "epoch": 0.01, + "learning_rate": 4.077100270381292e-05, + "loss": 3.6837, + "step": 563712 + }, + { + "epoch": 0.01, + "learning_rate": 4.07626167563024e-05, + "loss": 3.7027, + "step": 564224 + }, + { + "epoch": 0.01, + "learning_rate": 4.075423080879188e-05, + "loss": 3.6943, + "step": 564736 + }, + { + "epoch": 0.01, + "learning_rate": 4.074586124008509e-05, + "loss": 3.6901, + "step": 565248 + }, + { + "epoch": 0.01, + "learning_rate": 4.073747529257457e-05, + "loss": 3.6908, + "step": 565760 + }, + { + "epoch": 0.01, + "learning_rate": 4.072908934506405e-05, + "loss": 3.6826, + "step": 566272 + }, + { + "epoch": 0.01, + "learning_rate": 4.072070339755353e-05, + "loss": 3.7064, + "step": 566784 + }, + { + "epoch": 0.01, + "learning_rate": 4.071231745004301e-05, + "loss": 3.6857, + "step": 567296 + }, + { + "epoch": 0.01, + "learning_rate": 4.070394788133623e-05, + "loss": 3.6975, + "step": 567808 + }, + { + "epoch": 0.01, + "learning_rate": 4.069556193382571e-05, + "loss": 3.6882, + "step": 568320 + }, + { + "epoch": 0.01, + "learning_rate": 4.068717598631519e-05, + "loss": 3.687, + "step": 568832 + }, + { + "epoch": 0.01, + "learning_rate": 4.0678790038804667e-05, + "loss": 3.6868, + "step": 569344 + }, + { + "epoch": 0.01, + "learning_rate": 4.0670404091294147e-05, + "loss": 3.6901, + "step": 569856 + }, + { + "epoch": 0.01, + "learning_rate": 4.0662018143783627e-05, + "loss": 3.6939, + "step": 570368 + }, + { + "epoch": 0.01, + "learning_rate": 4.0653632196273106e-05, + "loss": 3.6931, + "step": 570880 + }, + { + "epoch": 0.01, + "learning_rate": 4.064524624876258e-05, + "loss": 3.6987, + "step": 571392 + }, + { + "epoch": 0.01, + "learning_rate": 4.0636876680055796e-05, + "loss": 3.7079, + "step": 571904 + }, + { + "epoch": 0.01, + "learning_rate": 4.0628490732545275e-05, + "loss": 3.7055, + "step": 572416 + }, + { + "epoch": 0.01, + "learning_rate": 4.0620104785034755e-05, + "loss": 3.697, + "step": 572928 + }, + { + "epoch": 0.01, + "learning_rate": 4.061171883752423e-05, + "loss": 3.6966, + "step": 573440 + }, + { + "epoch": 0.01, + "learning_rate": 4.060336564762118e-05, + "loss": 3.6802, + "step": 573952 + }, + { + "epoch": 0.01, + "learning_rate": 4.059497970011066e-05, + "loss": 3.6912, + "step": 574464 + }, + { + "epoch": 0.01, + "learning_rate": 4.058659375260014e-05, + "loss": 3.7063, + "step": 574976 + }, + { + "epoch": 0.01, + "learning_rate": 4.057820780508962e-05, + "loss": 3.697, + "step": 575488 + }, + { + "epoch": 0.01, + "learning_rate": 4.05698218575791e-05, + "loss": 3.6946, + "step": 576000 + }, + { + "epoch": 0.01, + "learning_rate": 4.056143591006858e-05, + "loss": 3.6746, + "step": 576512 + }, + { + "epoch": 0.01, + "learning_rate": 4.055304996255805e-05, + "loss": 3.6991, + "step": 577024 + }, + { + "epoch": 0.01, + "learning_rate": 4.054466401504753e-05, + "loss": 3.6771, + "step": 577536 + }, + { + "epoch": 0.01, + "learning_rate": 4.053629444634075e-05, + "loss": 3.6867, + "step": 578048 + }, + { + "epoch": 0.01, + "learning_rate": 4.052790849883023e-05, + "loss": 3.6868, + "step": 578560 + }, + { + "epoch": 0.01, + "learning_rate": 4.05195225513197e-05, + "loss": 3.6932, + "step": 579072 + }, + { + "epoch": 0.01, + "learning_rate": 4.051113660380918e-05, + "loss": 3.6988, + "step": 579584 + }, + { + "epoch": 0.02, + "learning_rate": 4.05027670351024e-05, + "loss": 3.6979, + "step": 580096 + }, + { + "epoch": 0.02, + "learning_rate": 4.0494397466395614e-05, + "loss": 3.6799, + "step": 580608 + }, + { + "epoch": 0.02, + "learning_rate": 4.0486011518885094e-05, + "loss": 3.6957, + "step": 581120 + }, + { + "epoch": 0.02, + "learning_rate": 4.0477625571374574e-05, + "loss": 3.6888, + "step": 581632 + }, + { + "epoch": 0.02, + "learning_rate": 4.0469239623864054e-05, + "loss": 3.6873, + "step": 582144 + }, + { + "epoch": 0.02, + "learning_rate": 4.046085367635353e-05, + "loss": 3.6801, + "step": 582656 + }, + { + "epoch": 0.02, + "learning_rate": 4.045246772884301e-05, + "loss": 3.6966, + "step": 583168 + }, + { + "epoch": 0.02, + "learning_rate": 4.044408178133249e-05, + "loss": 3.6974, + "step": 583680 + }, + { + "epoch": 0.02, + "learning_rate": 4.043569583382197e-05, + "loss": 3.7054, + "step": 584192 + }, + { + "epoch": 0.02, + "learning_rate": 4.0427326265115176e-05, + "loss": 3.6884, + "step": 584704 + }, + { + "epoch": 0.02, + "learning_rate": 4.041895669640839e-05, + "loss": 3.6923, + "step": 585216 + }, + { + "epoch": 0.02, + "learning_rate": 4.041057074889787e-05, + "loss": 3.6813, + "step": 585728 + }, + { + "epoch": 0.02, + "learning_rate": 4.040218480138735e-05, + "loss": 3.6964, + "step": 586240 + }, + { + "epoch": 0.02, + "learning_rate": 4.039379885387683e-05, + "loss": 3.6984, + "step": 586752 + }, + { + "epoch": 0.02, + "learning_rate": 4.038541290636631e-05, + "loss": 3.694, + "step": 587264 + }, + { + "epoch": 0.02, + "learning_rate": 4.037702695885579e-05, + "loss": 3.6977, + "step": 587776 + }, + { + "epoch": 0.02, + "learning_rate": 4.036864101134527e-05, + "loss": 3.6795, + "step": 588288 + }, + { + "epoch": 0.02, + "learning_rate": 4.036025506383475e-05, + "loss": 3.6756, + "step": 588800 + }, + { + "epoch": 0.02, + "learning_rate": 4.035188549512796e-05, + "loss": 3.6774, + "step": 589312 + }, + { + "epoch": 0.02, + "learning_rate": 4.0343515926421177e-05, + "loss": 3.6834, + "step": 589824 + }, + { + "epoch": 0.02, + "learning_rate": 4.033512997891065e-05, + "loss": 3.6957, + "step": 590336 + }, + { + "epoch": 0.02, + "learning_rate": 4.032674403140013e-05, + "loss": 3.6958, + "step": 590848 + }, + { + "epoch": 0.02, + "learning_rate": 4.031835808388961e-05, + "loss": 3.6622, + "step": 591360 + }, + { + "epoch": 0.02, + "learning_rate": 4.030997213637909e-05, + "loss": 3.6928, + "step": 591872 + }, + { + "epoch": 0.02, + "learning_rate": 4.0301586188868576e-05, + "loss": 3.698, + "step": 592384 + }, + { + "epoch": 0.02, + "learning_rate": 4.0293200241358056e-05, + "loss": 3.6922, + "step": 592896 + }, + { + "epoch": 0.02, + "learning_rate": 4.0284814293847536e-05, + "loss": 3.6938, + "step": 593408 + }, + { + "epoch": 0.02, + "learning_rate": 4.0276444725140745e-05, + "loss": 3.6863, + "step": 593920 + }, + { + "epoch": 0.02, + "learning_rate": 4.0268058777630225e-05, + "loss": 3.6795, + "step": 594432 + }, + { + "epoch": 0.02, + "learning_rate": 4.0259672830119705e-05, + "loss": 3.6978, + "step": 594944 + }, + { + "epoch": 0.02, + "learning_rate": 4.0251286882609185e-05, + "loss": 3.6869, + "step": 595456 + }, + { + "epoch": 0.02, + "learning_rate": 4.0242917313902394e-05, + "loss": 3.6818, + "step": 595968 + }, + { + "epoch": 0.02, + "learning_rate": 4.0234531366391874e-05, + "loss": 3.6741, + "step": 596480 + }, + { + "epoch": 0.02, + "learning_rate": 4.0226145418881354e-05, + "loss": 3.6841, + "step": 596992 + }, + { + "epoch": 0.02, + "learning_rate": 4.021777585017456e-05, + "loss": 3.6885, + "step": 597504 + }, + { + "epoch": 0.02, + "learning_rate": 4.020938990266404e-05, + "loss": 3.6845, + "step": 598016 + }, + { + "epoch": 0.02, + "learning_rate": 4.020100395515353e-05, + "loss": 3.696, + "step": 598528 + }, + { + "epoch": 0.02, + "learning_rate": 4.019261800764301e-05, + "loss": 3.6828, + "step": 599040 + }, + { + "epoch": 0.02, + "learning_rate": 4.018423206013249e-05, + "loss": 3.6779, + "step": 599552 + }, + { + "epoch": 0.02, + "learning_rate": 4.017584611262197e-05, + "loss": 3.701, + "step": 600064 + }, + { + "epoch": 0.02, + "learning_rate": 4.016746016511145e-05, + "loss": 3.6788, + "step": 600576 + }, + { + "epoch": 0.02, + "learning_rate": 4.015907421760093e-05, + "loss": 3.694, + "step": 601088 + }, + { + "epoch": 0.02, + "learning_rate": 4.015070464889414e-05, + "loss": 3.6973, + "step": 601600 + }, + { + "epoch": 0.02, + "learning_rate": 4.014231870138362e-05, + "loss": 3.6888, + "step": 602112 + }, + { + "epoch": 0.02, + "learning_rate": 4.01339327538731e-05, + "loss": 3.6944, + "step": 602624 + }, + { + "epoch": 0.02, + "learning_rate": 4.012554680636258e-05, + "loss": 3.6856, + "step": 603136 + }, + { + "epoch": 0.02, + "learning_rate": 4.011717723765579e-05, + "loss": 3.6758, + "step": 603648 + }, + { + "epoch": 0.02, + "learning_rate": 4.010879129014527e-05, + "loss": 3.678, + "step": 604160 + }, + { + "epoch": 0.02, + "learning_rate": 4.010040534263475e-05, + "loss": 3.6888, + "step": 604672 + }, + { + "epoch": 0.02, + "learning_rate": 4.009201939512423e-05, + "loss": 3.6923, + "step": 605184 + }, + { + "epoch": 0.02, + "learning_rate": 4.0083649826417444e-05, + "loss": 3.6885, + "step": 605696 + }, + { + "epoch": 0.02, + "learning_rate": 4.0075263878906924e-05, + "loss": 3.6935, + "step": 606208 + }, + { + "epoch": 0.02, + "learning_rate": 4.0066877931396404e-05, + "loss": 3.6803, + "step": 606720 + }, + { + "epoch": 0.02, + "learning_rate": 4.0058491983885883e-05, + "loss": 3.6881, + "step": 607232 + }, + { + "epoch": 0.02, + "learning_rate": 4.005012241517909e-05, + "loss": 3.673, + "step": 607744 + }, + { + "epoch": 0.02, + "learning_rate": 4.004173646766857e-05, + "loss": 3.6851, + "step": 608256 + }, + { + "epoch": 0.02, + "learning_rate": 4.003335052015805e-05, + "loss": 3.6945, + "step": 608768 + }, + { + "epoch": 0.02, + "learning_rate": 4.002496457264753e-05, + "loss": 3.6951, + "step": 609280 + }, + { + "epoch": 0.02, + "learning_rate": 4.001659500394074e-05, + "loss": 3.6751, + "step": 609792 + }, + { + "epoch": 0.02, + "learning_rate": 4.000820905643022e-05, + "loss": 3.6863, + "step": 610304 + }, + { + "epoch": 0.03, + "eval_loss": 3.8489081859588623, + "eval_runtime": 574.9406, + "eval_samples_per_second": 663.705, + "eval_steps_per_second": 20.741, + "step": 610552 + }, + { + "epoch": 0.0, + "learning_rate": 3.99998231089197e-05, + "loss": 3.7011, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.999143716140918e-05, + "loss": 3.685, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.998305121389866e-05, + "loss": 3.6797, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.997466526638814e-05, + "loss": 3.6846, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.996627931887762e-05, + "loss": 3.672, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.99578933713671e-05, + "loss": 3.6743, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.994952380266031e-05, + "loss": 3.6734, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.994113785514979e-05, + "loss": 3.6744, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.993275190763927e-05, + "loss": 3.6777, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.992436596012875e-05, + "loss": 3.6851, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.991598001261823e-05, + "loss": 3.6809, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.990759406510771e-05, + "loss": 3.6778, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.989922449640092e-05, + "loss": 3.6877, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.98908385488904e-05, + "loss": 3.673, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.9882452601379886e-05, + "loss": 3.6871, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.9874066653869366e-05, + "loss": 3.6634, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.9865680706358846e-05, + "loss": 3.6699, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.9857294758848326e-05, + "loss": 3.6822, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.9848908811337806e-05, + "loss": 3.6728, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.9840522863827286e-05, + "loss": 3.6888, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.9832153295120495e-05, + "loss": 3.6801, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.9823767347609975e-05, + "loss": 3.68, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.9815381400099455e-05, + "loss": 3.6824, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.9806995452588935e-05, + "loss": 3.675, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.979864226268587e-05, + "loss": 3.6794, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.979025631517535e-05, + "loss": 3.6724, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.978187036766484e-05, + "loss": 3.6828, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.977348442015432e-05, + "loss": 3.6723, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.97650984726438e-05, + "loss": 3.6826, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.975672890393701e-05, + "loss": 3.6697, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.974834295642649e-05, + "loss": 3.6647, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.973995700891597e-05, + "loss": 3.6803, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.973157106140545e-05, + "loss": 3.682, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.972318511389493e-05, + "loss": 3.6796, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.971479916638441e-05, + "loss": 3.6771, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.970641321887389e-05, + "loss": 3.6769, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.969802727136337e-05, + "loss": 3.6729, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.968965770265658e-05, + "loss": 3.6836, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.968127175514606e-05, + "loss": 3.6807, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967288580763554e-05, + "loss": 3.6649, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.9664499860125024e-05, + "loss": 3.6654, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.965613029141823e-05, + "loss": 3.6612, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964776072271144e-05, + "loss": 3.6812, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.963937477520092e-05, + "loss": 3.6788, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.96309888276904e-05, + "loss": 3.6677, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.962260288017988e-05, + "loss": 3.6837, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.961421693266936e-05, + "loss": 3.6671, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.960584736396257e-05, + "loss": 3.6816, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.959746141645205e-05, + "loss": 3.6696, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958907546894153e-05, + "loss": 3.6602, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.958068952143101e-05, + "loss": 3.6672, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.957231995272423e-05, + "loss": 3.665, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.956393400521371e-05, + "loss": 3.6718, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.955554805770319e-05, + "loss": 3.6666, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.954716211019267e-05, + "loss": 3.6686, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.953877616268215e-05, + "loss": 3.6551, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.953039021517162e-05, + "loss": 3.6693, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.95220042676611e-05, + "loss": 3.6601, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.951361832015058e-05, + "loss": 3.6706, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.950524875144379e-05, + "loss": 3.6623, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.9496879182737005e-05, + "loss": 3.6672, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.9488493235226485e-05, + "loss": 3.6638, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.9480107287715965e-05, + "loss": 3.6547, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.9471721340205445e-05, + "loss": 3.6759, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.9463335392694925e-05, + "loss": 3.6588, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.945496582398814e-05, + "loss": 3.6696, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.944657987647762e-05, + "loss": 3.6618, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.9438193928967094e-05, + "loss": 3.656, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.9429807981456573e-05, + "loss": 3.6584, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.9421422033946053e-05, + "loss": 3.6629, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.9413036086435533e-05, + "loss": 3.6653, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.940465013892501e-05, + "loss": 3.6673, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.939626419141449e-05, + "loss": 3.667, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.938791100151144e-05, + "loss": 3.6857, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.937952505400092e-05, + "loss": 3.6773, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.93711391064904e-05, + "loss": 3.6665, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.936275315897988e-05, + "loss": 3.6682, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.935438359027309e-05, + "loss": 3.6544, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.934599764276257e-05, + "loss": 3.6617, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.933761169525205e-05, + "loss": 3.6757, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.932922574774153e-05, + "loss": 3.6735, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.932083980023101e-05, + "loss": 3.6626, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.931245385272049e-05, + "loss": 3.6503, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.9304084284013696e-05, + "loss": 3.6692, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.9295698336503176e-05, + "loss": 3.6456, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.9287312388992656e-05, + "loss": 3.6603, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.9278926441482136e-05, + "loss": 3.6622, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.9270540493971616e-05, + "loss": 3.6611, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.92621545464611e-05, + "loss": 3.6734, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925376859895058e-05, + "loss": 3.6699, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.924538265144006e-05, + "loss": 3.6556, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923701308273327e-05, + "loss": 3.6621, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.922862713522275e-05, + "loss": 3.6638, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.922024118771223e-05, + "loss": 3.6606, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.921187161900544e-05, + "loss": 3.6572, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.920348567149492e-05, + "loss": 3.6653, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.91950997239844e-05, + "loss": 3.6723, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.918671377647388e-05, + "loss": 3.6805, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.917832782896336e-05, + "loss": 3.6604, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.916994188145284e-05, + "loss": 3.6655, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.9161572312746056e-05, + "loss": 3.6571, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.9153186365235536e-05, + "loss": 3.6649, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.9144800417725016e-05, + "loss": 3.6728, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.9136414470214496e-05, + "loss": 3.6657, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.9128028522703976e-05, + "loss": 3.6712, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.9119658953997185e-05, + "loss": 3.649, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.9111273006486665e-05, + "loss": 3.6525, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.9102887058976145e-05, + "loss": 3.6517, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.9094501111465625e-05, + "loss": 3.6607, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.9086131542758834e-05, + "loss": 3.6626, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.9077745595248314e-05, + "loss": 3.6687, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.9069359647737794e-05, + "loss": 3.6347, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.9060973700227274e-05, + "loss": 3.667, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.9052587752716754e-05, + "loss": 3.6715, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.9044201805206234e-05, + "loss": 3.6633, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.9035815857695714e-05, + "loss": 3.6665, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.9027429910185194e-05, + "loss": 3.6636, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.901907672028214e-05, + "loss": 3.6507, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.901069077277162e-05, + "loss": 3.6693, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.90023048252611e-05, + "loss": 3.6686, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.899391887775057e-05, + "loss": 3.6516, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.898553293024005e-05, + "loss": 3.6509, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.897714698272953e-05, + "loss": 3.6567, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.896877741402275e-05, + "loss": 3.6595, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.896039146651223e-05, + "loss": 3.6581, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.895200551900171e-05, + "loss": 3.6677, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.894361957149119e-05, + "loss": 3.6603, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.893523362398067e-05, + "loss": 3.6508, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.892686405527388e-05, + "loss": 3.6748, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.891847810776336e-05, + "loss": 3.6515, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.891009216025284e-05, + "loss": 3.6669, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.890170621274232e-05, + "loss": 3.6731, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.8893336644035526e-05, + "loss": 3.6614, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.8884950696525006e-05, + "loss": 3.6686, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.8876564749014486e-05, + "loss": 3.6609, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.8868178801503966e-05, + "loss": 3.6476, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.8859792853993446e-05, + "loss": 3.6554, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.885140690648293e-05, + "loss": 3.6592, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.884302095897241e-05, + "loss": 3.6689, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.883463501146189e-05, + "loss": 3.664, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.88262654427551e-05, + "loss": 3.6649, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.881787949524458e-05, + "loss": 3.6583, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.880950992653779e-05, + "loss": 3.659, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.880112397902727e-05, + "loss": 3.6466, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.879273803151675e-05, + "loss": 3.6594, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.878435208400623e-05, + "loss": 3.6689, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.877596613649571e-05, + "loss": 3.6711, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.876758018898519e-05, + "loss": 3.651, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.875919424147467e-05, + "loss": 3.656, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 3.8443713188171387, + "eval_runtime": 599.4606, + "eval_samples_per_second": 636.557, + "eval_steps_per_second": 19.893, + "step": 686871 + }, + { + "epoch": 0.0, + "learning_rate": 3.875082467276788e-05, + "loss": 3.6755, + "step": 687104 + }, + { + "epoch": 0.0, + "learning_rate": 3.8742438725257366e-05, + "loss": 3.6587, + "step": 687616 + }, + { + "epoch": 0.0, + "learning_rate": 3.8734052777746846e-05, + "loss": 3.6582, + "step": 688128 + }, + { + "epoch": 0.0, + "learning_rate": 3.8725666830236326e-05, + "loss": 3.6566, + "step": 688640 + }, + { + "epoch": 0.0, + "learning_rate": 3.8717280882725806e-05, + "loss": 3.6495, + "step": 689152 + }, + { + "epoch": 0.0, + "learning_rate": 3.8708911314019015e-05, + "loss": 3.6468, + "step": 689664 + }, + { + "epoch": 0.0, + "learning_rate": 3.8700525366508495e-05, + "loss": 3.6483, + "step": 690176 + }, + { + "epoch": 0.0, + "learning_rate": 3.8692139418997975e-05, + "loss": 3.6497, + "step": 690688 + }, + { + "epoch": 0.0, + "learning_rate": 3.8683753471487455e-05, + "loss": 3.6512, + "step": 691200 + }, + { + "epoch": 0.0, + "learning_rate": 3.8675367523976935e-05, + "loss": 3.6611, + "step": 691712 + }, + { + "epoch": 0.0, + "learning_rate": 3.8666997955270144e-05, + "loss": 3.6522, + "step": 692224 + }, + { + "epoch": 0.0, + "learning_rate": 3.8658612007759624e-05, + "loss": 3.6505, + "step": 692736 + }, + { + "epoch": 0.0, + "learning_rate": 3.8650226060249104e-05, + "loss": 3.6609, + "step": 693248 + }, + { + "epoch": 0.0, + "learning_rate": 3.8641840112738584e-05, + "loss": 3.6497, + "step": 693760 + }, + { + "epoch": 0.0, + "learning_rate": 3.8633454165228064e-05, + "loss": 3.6576, + "step": 694272 + }, + { + "epoch": 0.0, + "learning_rate": 3.862508459652128e-05, + "loss": 3.6372, + "step": 694784 + }, + { + "epoch": 0.0, + "learning_rate": 3.861669864901076e-05, + "loss": 3.6417, + "step": 695296 + }, + { + "epoch": 0.0, + "learning_rate": 3.860831270150023e-05, + "loss": 3.6568, + "step": 695808 + }, + { + "epoch": 0.0, + "learning_rate": 3.859992675398971e-05, + "loss": 3.6476, + "step": 696320 + }, + { + "epoch": 0.0, + "learning_rate": 3.859154080647919e-05, + "loss": 3.6648, + "step": 696832 + }, + { + "epoch": 0.0, + "learning_rate": 3.858315485896867e-05, + "loss": 3.6497, + "step": 697344 + }, + { + "epoch": 0.0, + "learning_rate": 3.857476891145815e-05, + "loss": 3.6645, + "step": 697856 + }, + { + "epoch": 0.0, + "learning_rate": 3.856639934275136e-05, + "loss": 3.6494, + "step": 698368 + }, + { + "epoch": 0.0, + "learning_rate": 3.855802977404458e-05, + "loss": 3.6481, + "step": 698880 + }, + { + "epoch": 0.0, + "learning_rate": 3.854964382653406e-05, + "loss": 3.6539, + "step": 699392 + }, + { + "epoch": 0.0, + "learning_rate": 3.854125787902354e-05, + "loss": 3.6523, + "step": 699904 + }, + { + "epoch": 0.0, + "learning_rate": 3.853287193151302e-05, + "loss": 3.6559, + "step": 700416 + }, + { + "epoch": 0.0, + "learning_rate": 3.85244859840025e-05, + "loss": 3.6469, + "step": 700928 + }, + { + "epoch": 0.0, + "learning_rate": 3.851610003649198e-05, + "loss": 3.6575, + "step": 701440 + }, + { + "epoch": 0.0, + "learning_rate": 3.8507730467785186e-05, + "loss": 3.6484, + "step": 701952 + }, + { + "epoch": 0.01, + "learning_rate": 3.8499344520274666e-05, + "loss": 3.6342, + "step": 702464 + }, + { + "epoch": 0.01, + "learning_rate": 3.8490958572764146e-05, + "loss": 3.6568, + "step": 702976 + }, + { + "epoch": 0.01, + "learning_rate": 3.8482572625253626e-05, + "loss": 3.6563, + "step": 703488 + }, + { + "epoch": 0.01, + "learning_rate": 3.8474203056546835e-05, + "loss": 3.6529, + "step": 704000 + }, + { + "epoch": 0.01, + "learning_rate": 3.8465817109036315e-05, + "loss": 3.6534, + "step": 704512 + }, + { + "epoch": 0.01, + "learning_rate": 3.8457431161525795e-05, + "loss": 3.6495, + "step": 705024 + }, + { + "epoch": 0.01, + "learning_rate": 3.8449045214015275e-05, + "loss": 3.6489, + "step": 705536 + }, + { + "epoch": 0.01, + "learning_rate": 3.8440659266504755e-05, + "loss": 3.6546, + "step": 706048 + }, + { + "epoch": 0.01, + "learning_rate": 3.843227331899424e-05, + "loss": 3.6594, + "step": 706560 + }, + { + "epoch": 0.01, + "learning_rate": 3.842388737148372e-05, + "loss": 3.6365, + "step": 707072 + }, + { + "epoch": 0.01, + "learning_rate": 3.84155014239732e-05, + "loss": 3.644, + "step": 707584 + }, + { + "epoch": 0.01, + "learning_rate": 3.840713185526641e-05, + "loss": 3.639, + "step": 708096 + }, + { + "epoch": 0.01, + "learning_rate": 3.839876228655962e-05, + "loss": 3.6488, + "step": 708608 + }, + { + "epoch": 0.01, + "learning_rate": 3.83903763390491e-05, + "loss": 3.6556, + "step": 709120 + }, + { + "epoch": 0.01, + "learning_rate": 3.838199039153858e-05, + "loss": 3.6416, + "step": 709632 + }, + { + "epoch": 0.01, + "learning_rate": 3.837360444402806e-05, + "loss": 3.6578, + "step": 710144 + }, + { + "epoch": 0.01, + "learning_rate": 3.836521849651754e-05, + "loss": 3.6427, + "step": 710656 + }, + { + "epoch": 0.01, + "learning_rate": 3.835684892781075e-05, + "loss": 3.6576, + "step": 711168 + }, + { + "epoch": 0.01, + "learning_rate": 3.834846298030023e-05, + "loss": 3.6454, + "step": 711680 + }, + { + "epoch": 0.01, + "learning_rate": 3.834007703278971e-05, + "loss": 3.6367, + "step": 712192 + }, + { + "epoch": 0.01, + "learning_rate": 3.8331691085279195e-05, + "loss": 3.6444, + "step": 712704 + }, + { + "epoch": 0.01, + "learning_rate": 3.8323321516572405e-05, + "loss": 3.6355, + "step": 713216 + }, + { + "epoch": 0.01, + "learning_rate": 3.8314935569061885e-05, + "loss": 3.651, + "step": 713728 + }, + { + "epoch": 0.01, + "learning_rate": 3.8306549621551364e-05, + "loss": 3.6393, + "step": 714240 + }, + { + "epoch": 0.01, + "learning_rate": 3.8298163674040844e-05, + "loss": 3.645, + "step": 714752 + }, + { + "epoch": 0.01, + "learning_rate": 3.8289777726530324e-05, + "loss": 3.629, + "step": 715264 + }, + { + "epoch": 0.01, + "learning_rate": 3.8281391779019804e-05, + "loss": 3.6447, + "step": 715776 + }, + { + "epoch": 0.01, + "learning_rate": 3.8273022210313013e-05, + "loss": 3.6319, + "step": 716288 + }, + { + "epoch": 0.01, + "learning_rate": 3.8264636262802493e-05, + "loss": 3.6509, + "step": 716800 + }, + { + "epoch": 0.01, + "learning_rate": 3.825625031529197e-05, + "loss": 3.6366, + "step": 717312 + }, + { + "epoch": 0.01, + "learning_rate": 3.824786436778145e-05, + "loss": 3.6409, + "step": 717824 + }, + { + "epoch": 0.01, + "learning_rate": 3.823947842027093e-05, + "loss": 3.64, + "step": 718336 + }, + { + "epoch": 0.01, + "learning_rate": 3.823110885156415e-05, + "loss": 3.6285, + "step": 718848 + }, + { + "epoch": 0.01, + "learning_rate": 3.822272290405363e-05, + "loss": 3.6502, + "step": 719360 + }, + { + "epoch": 0.01, + "learning_rate": 3.821433695654311e-05, + "loss": 3.6367, + "step": 719872 + }, + { + "epoch": 0.01, + "learning_rate": 3.820595100903259e-05, + "loss": 3.6457, + "step": 720384 + }, + { + "epoch": 0.01, + "learning_rate": 3.819756506152207e-05, + "loss": 3.6328, + "step": 720896 + }, + { + "epoch": 0.01, + "learning_rate": 3.818919549281528e-05, + "loss": 3.6319, + "step": 721408 + }, + { + "epoch": 0.01, + "learning_rate": 3.818080954530476e-05, + "loss": 3.6343, + "step": 721920 + }, + { + "epoch": 0.01, + "learning_rate": 3.817242359779424e-05, + "loss": 3.6387, + "step": 722432 + }, + { + "epoch": 0.01, + "learning_rate": 3.816403765028371e-05, + "loss": 3.6355, + "step": 722944 + }, + { + "epoch": 0.01, + "learning_rate": 3.815566808157693e-05, + "loss": 3.6438, + "step": 723456 + }, + { + "epoch": 0.01, + "learning_rate": 3.814728213406641e-05, + "loss": 3.6445, + "step": 723968 + }, + { + "epoch": 0.01, + "learning_rate": 3.813889618655589e-05, + "loss": 3.6605, + "step": 724480 + }, + { + "epoch": 0.01, + "learning_rate": 3.813051023904537e-05, + "loss": 3.6479, + "step": 724992 + }, + { + "epoch": 0.01, + "learning_rate": 3.812212429153485e-05, + "loss": 3.6442, + "step": 725504 + }, + { + "epoch": 0.01, + "learning_rate": 3.811375472282806e-05, + "loss": 3.6434, + "step": 726016 + }, + { + "epoch": 0.01, + "learning_rate": 3.810536877531754e-05, + "loss": 3.6339, + "step": 726528 + }, + { + "epoch": 0.01, + "learning_rate": 3.8096982827807016e-05, + "loss": 3.6361, + "step": 727040 + }, + { + "epoch": 0.01, + "learning_rate": 3.8088596880296496e-05, + "loss": 3.6496, + "step": 727552 + }, + { + "epoch": 0.01, + "learning_rate": 3.8080210932785976e-05, + "loss": 3.6509, + "step": 728064 + }, + { + "epoch": 0.01, + "learning_rate": 3.8071824985275456e-05, + "loss": 3.6426, + "step": 728576 + }, + { + "epoch": 0.01, + "learning_rate": 3.8063439037764936e-05, + "loss": 3.6272, + "step": 729088 + }, + { + "epoch": 0.01, + "learning_rate": 3.8055053090254416e-05, + "loss": 3.6407, + "step": 729600 + }, + { + "epoch": 0.01, + "learning_rate": 3.8046683521547625e-05, + "loss": 3.6238, + "step": 730112 + }, + { + "epoch": 0.01, + "learning_rate": 3.8038297574037105e-05, + "loss": 3.6358, + "step": 730624 + }, + { + "epoch": 0.01, + "learning_rate": 3.8029911626526585e-05, + "loss": 3.6369, + "step": 731136 + }, + { + "epoch": 0.01, + "learning_rate": 3.8021525679016065e-05, + "loss": 3.6378, + "step": 731648 + }, + { + "epoch": 0.01, + "learning_rate": 3.801313973150555e-05, + "loss": 3.6497, + "step": 732160 + }, + { + "epoch": 0.02, + "learning_rate": 3.800477016279876e-05, + "loss": 3.6437, + "step": 732672 + }, + { + "epoch": 0.02, + "learning_rate": 3.799638421528824e-05, + "loss": 3.6345, + "step": 733184 + }, + { + "epoch": 0.02, + "learning_rate": 3.798799826777772e-05, + "loss": 3.6368, + "step": 733696 + }, + { + "epoch": 0.02, + "learning_rate": 3.79796123202672e-05, + "loss": 3.6408, + "step": 734208 + }, + { + "epoch": 0.02, + "learning_rate": 3.797122637275668e-05, + "loss": 3.6337, + "step": 734720 + }, + { + "epoch": 0.02, + "learning_rate": 3.796285680404989e-05, + "loss": 3.6347, + "step": 735232 + }, + { + "epoch": 0.02, + "learning_rate": 3.795447085653937e-05, + "loss": 3.6398, + "step": 735744 + }, + { + "epoch": 0.02, + "learning_rate": 3.794608490902885e-05, + "loss": 3.6482, + "step": 736256 + }, + { + "epoch": 0.02, + "learning_rate": 3.793769896151833e-05, + "loss": 3.6542, + "step": 736768 + }, + { + "epoch": 0.02, + "learning_rate": 3.792931301400781e-05, + "loss": 3.6338, + "step": 737280 + }, + { + "epoch": 0.02, + "learning_rate": 3.792094344530102e-05, + "loss": 3.6441, + "step": 737792 + }, + { + "epoch": 0.02, + "learning_rate": 3.7912557497790505e-05, + "loss": 3.634, + "step": 738304 + }, + { + "epoch": 0.02, + "learning_rate": 3.7904171550279985e-05, + "loss": 3.6413, + "step": 738816 + }, + { + "epoch": 0.02, + "learning_rate": 3.7895785602769465e-05, + "loss": 3.6426, + "step": 739328 + }, + { + "epoch": 0.02, + "learning_rate": 3.7887416034062674e-05, + "loss": 3.646, + "step": 739840 + }, + { + "epoch": 0.02, + "learning_rate": 3.7879030086552154e-05, + "loss": 3.648, + "step": 740352 + }, + { + "epoch": 0.02, + "learning_rate": 3.7870644139041634e-05, + "loss": 3.6258, + "step": 740864 + }, + { + "epoch": 0.02, + "learning_rate": 3.7862258191531114e-05, + "loss": 3.6295, + "step": 741376 + }, + { + "epoch": 0.02, + "learning_rate": 3.7853872244020594e-05, + "loss": 3.6269, + "step": 741888 + }, + { + "epoch": 0.02, + "learning_rate": 3.78455026753138e-05, + "loss": 3.6314, + "step": 742400 + }, + { + "epoch": 0.02, + "learning_rate": 3.783711672780328e-05, + "loss": 3.6397, + "step": 742912 + }, + { + "epoch": 0.02, + "learning_rate": 3.782873078029276e-05, + "loss": 3.6431, + "step": 743424 + }, + { + "epoch": 0.02, + "learning_rate": 3.782034483278224e-05, + "loss": 3.6162, + "step": 743936 + }, + { + "epoch": 0.02, + "learning_rate": 3.781195888527172e-05, + "loss": 3.642, + "step": 744448 + }, + { + "epoch": 0.02, + "learning_rate": 3.78035729377612e-05, + "loss": 3.646, + "step": 744960 + }, + { + "epoch": 0.02, + "learning_rate": 3.779520336905442e-05, + "loss": 3.6399, + "step": 745472 + }, + { + "epoch": 0.02, + "learning_rate": 3.77868174215439e-05, + "loss": 3.644, + "step": 745984 + }, + { + "epoch": 0.02, + "learning_rate": 3.777843147403338e-05, + "loss": 3.6383, + "step": 746496 + }, + { + "epoch": 0.02, + "learning_rate": 3.777004552652285e-05, + "loss": 3.6287, + "step": 747008 + }, + { + "epoch": 0.02, + "learning_rate": 3.776165957901233e-05, + "loss": 3.643, + "step": 747520 + }, + { + "epoch": 0.02, + "learning_rate": 3.775327363150181e-05, + "loss": 3.6428, + "step": 748032 + }, + { + "epoch": 0.02, + "learning_rate": 3.774490406279502e-05, + "loss": 3.6347, + "step": 748544 + }, + { + "epoch": 0.02, + "learning_rate": 3.77365181152845e-05, + "loss": 3.6211, + "step": 749056 + }, + { + "epoch": 0.02, + "learning_rate": 3.772813216777398e-05, + "loss": 3.6348, + "step": 749568 + }, + { + "epoch": 0.02, + "learning_rate": 3.771974622026346e-05, + "loss": 3.6338, + "step": 750080 + }, + { + "epoch": 0.02, + "learning_rate": 3.771136027275294e-05, + "loss": 3.6378, + "step": 750592 + }, + { + "epoch": 0.02, + "learning_rate": 3.770297432524243e-05, + "loss": 3.6383, + "step": 751104 + }, + { + "epoch": 0.02, + "learning_rate": 3.769458837773191e-05, + "loss": 3.642, + "step": 751616 + }, + { + "epoch": 0.02, + "learning_rate": 3.768620243022139e-05, + "loss": 3.6285, + "step": 752128 + }, + { + "epoch": 0.02, + "learning_rate": 3.7677832861514596e-05, + "loss": 3.6506, + "step": 752640 + }, + { + "epoch": 0.02, + "learning_rate": 3.7669463292807805e-05, + "loss": 3.6292, + "step": 753152 + }, + { + "epoch": 0.02, + "learning_rate": 3.7661077345297285e-05, + "loss": 3.6418, + "step": 753664 + }, + { + "epoch": 0.02, + "learning_rate": 3.7652691397786765e-05, + "loss": 3.6493, + "step": 754176 + }, + { + "epoch": 0.02, + "learning_rate": 3.7644305450276245e-05, + "loss": 3.6388, + "step": 754688 + }, + { + "epoch": 0.02, + "learning_rate": 3.7635919502765725e-05, + "loss": 3.6429, + "step": 755200 + }, + { + "epoch": 0.02, + "learning_rate": 3.7627549934058934e-05, + "loss": 3.6388, + "step": 755712 + }, + { + "epoch": 0.02, + "learning_rate": 3.7619163986548414e-05, + "loss": 3.6249, + "step": 756224 + }, + { + "epoch": 0.02, + "learning_rate": 3.7610778039037894e-05, + "loss": 3.6318, + "step": 756736 + }, + { + "epoch": 0.02, + "learning_rate": 3.760239209152738e-05, + "loss": 3.6316, + "step": 757248 + }, + { + "epoch": 0.02, + "learning_rate": 3.759402252282059e-05, + "loss": 3.6443, + "step": 757760 + }, + { + "epoch": 0.02, + "learning_rate": 3.758563657531007e-05, + "loss": 3.641, + "step": 758272 + }, + { + "epoch": 0.02, + "learning_rate": 3.757725062779955e-05, + "loss": 3.6425, + "step": 758784 + }, + { + "epoch": 0.02, + "learning_rate": 3.756886468028903e-05, + "loss": 3.6396, + "step": 759296 + }, + { + "epoch": 0.02, + "learning_rate": 3.756047873277851e-05, + "loss": 3.6356, + "step": 759808 + }, + { + "epoch": 0.02, + "learning_rate": 3.755210916407172e-05, + "loss": 3.6222, + "step": 760320 + }, + { + "epoch": 0.02, + "learning_rate": 3.75437232165612e-05, + "loss": 3.6351, + "step": 760832 + }, + { + "epoch": 0.02, + "learning_rate": 3.753533726905068e-05, + "loss": 3.6471, + "step": 761344 + }, + { + "epoch": 0.02, + "learning_rate": 3.752695132154016e-05, + "loss": 3.6449, + "step": 761856 + }, + { + "epoch": 0.02, + "learning_rate": 3.751858175283337e-05, + "loss": 3.6277, + "step": 762368 + }, + { + "epoch": 0.02, + "learning_rate": 3.751019580532285e-05, + "loss": 3.6321, + "step": 762880 + }, + { + "epoch": 0.03, + "eval_loss": 3.8424477577209473, + "eval_runtime": 313.3643, + "eval_samples_per_second": 1217.723, + "eval_steps_per_second": 38.055, + "step": 763190 + }, + { + "epoch": 1.0, + "learning_rate": 3.750180985781233e-05, + "loss": 3.6475, + "step": 763392 + }, + { + "epoch": 1.0, + "learning_rate": 3.7493423910301815e-05, + "loss": 3.6314, + "step": 763904 + }, + { + "epoch": 1.0, + "learning_rate": 3.7485037962791294e-05, + "loss": 3.6371, + "step": 764416 + }, + { + "epoch": 1.0, + "learning_rate": 3.7476652015280774e-05, + "loss": 3.6296, + "step": 764928 + }, + { + "epoch": 1.0, + "learning_rate": 3.7468282446573984e-05, + "loss": 3.6338, + "step": 765440 + }, + { + "epoch": 1.0, + "learning_rate": 3.7459896499063463e-05, + "loss": 3.6203, + "step": 765952 + }, + { + "epoch": 1.0, + "learning_rate": 3.7451510551552943e-05, + "loss": 3.6263, + "step": 766464 + }, + { + "epoch": 1.0, + "learning_rate": 3.744312460404242e-05, + "loss": 3.622, + "step": 766976 + }, + { + "epoch": 1.0, + "learning_rate": 3.74347386565319e-05, + "loss": 3.6319, + "step": 767488 + }, + { + "epoch": 1.0, + "learning_rate": 3.742636908782511e-05, + "loss": 3.6364, + "step": 768000 + }, + { + "epoch": 1.0, + "learning_rate": 3.741798314031459e-05, + "loss": 3.6327, + "step": 768512 + }, + { + "epoch": 1.0, + "learning_rate": 3.740959719280407e-05, + "loss": 3.6273, + "step": 769024 + }, + { + "epoch": 1.0, + "learning_rate": 3.740121124529355e-05, + "loss": 3.6363, + "step": 769536 + }, + { + "epoch": 1.0, + "learning_rate": 3.739284167658677e-05, + "loss": 3.6287, + "step": 770048 + }, + { + "epoch": 1.0, + "learning_rate": 3.738445572907625e-05, + "loss": 3.6357, + "step": 770560 + }, + { + "epoch": 1.0, + "learning_rate": 3.737606978156573e-05, + "loss": 3.6133, + "step": 771072 + }, + { + "epoch": 1.0, + "learning_rate": 3.736768383405521e-05, + "loss": 3.6165, + "step": 771584 + }, + { + "epoch": 1.0, + "learning_rate": 3.735931426534842e-05, + "loss": 3.638, + "step": 772096 + }, + { + "epoch": 1.0, + "learning_rate": 3.73509283178379e-05, + "loss": 3.6248, + "step": 772608 + }, + { + "epoch": 1.0, + "learning_rate": 3.734254237032738e-05, + "loss": 3.641, + "step": 773120 + }, + { + "epoch": 1.0, + "learning_rate": 3.733415642281686e-05, + "loss": 3.623, + "step": 773632 + }, + { + "epoch": 1.0, + "learning_rate": 3.732577047530633e-05, + "loss": 3.6432, + "step": 774144 + }, + { + "epoch": 1.0, + "learning_rate": 3.7317400906599546e-05, + "loss": 3.6291, + "step": 774656 + }, + { + "epoch": 1.0, + "learning_rate": 3.7309014959089026e-05, + "loss": 3.6289, + "step": 775168 + }, + { + "epoch": 1.0, + "learning_rate": 3.7300629011578506e-05, + "loss": 3.6307, + "step": 775680 + }, + { + "epoch": 1.0, + "learning_rate": 3.7292243064067986e-05, + "loss": 3.6276, + "step": 776192 + }, + { + "epoch": 1.0, + "learning_rate": 3.7283857116557466e-05, + "loss": 3.6358, + "step": 776704 + }, + { + "epoch": 1.0, + "learning_rate": 3.727548754785068e-05, + "loss": 3.6218, + "step": 777216 + }, + { + "epoch": 1.0, + "learning_rate": 3.7267101600340155e-05, + "loss": 3.6314, + "step": 777728 + }, + { + "epoch": 1.0, + "learning_rate": 3.7258715652829635e-05, + "loss": 3.6312, + "step": 778240 + }, + { + "epoch": 1.01, + "learning_rate": 3.7250329705319115e-05, + "loss": 3.6114, + "step": 778752 + }, + { + "epoch": 1.01, + "learning_rate": 3.7241943757808595e-05, + "loss": 3.6325, + "step": 779264 + }, + { + "epoch": 1.01, + "learning_rate": 3.7233574189101804e-05, + "loss": 3.6366, + "step": 779776 + }, + { + "epoch": 1.01, + "learning_rate": 3.7225188241591284e-05, + "loss": 3.6299, + "step": 780288 + }, + { + "epoch": 1.01, + "learning_rate": 3.7216802294080764e-05, + "loss": 3.6293, + "step": 780800 + }, + { + "epoch": 1.01, + "learning_rate": 3.7208416346570244e-05, + "loss": 3.6316, + "step": 781312 + }, + { + "epoch": 1.01, + "learning_rate": 3.7200030399059724e-05, + "loss": 3.6312, + "step": 781824 + }, + { + "epoch": 1.01, + "learning_rate": 3.719166083035294e-05, + "loss": 3.6304, + "step": 782336 + }, + { + "epoch": 1.01, + "learning_rate": 3.718327488284242e-05, + "loss": 3.6376, + "step": 782848 + }, + { + "epoch": 1.01, + "learning_rate": 3.71748889353319e-05, + "loss": 3.6181, + "step": 783360 + }, + { + "epoch": 1.01, + "learning_rate": 3.716650298782138e-05, + "loss": 3.6214, + "step": 783872 + }, + { + "epoch": 1.01, + "learning_rate": 3.715811704031086e-05, + "loss": 3.6159, + "step": 784384 + }, + { + "epoch": 1.01, + "learning_rate": 3.714974747160407e-05, + "loss": 3.6286, + "step": 784896 + }, + { + "epoch": 1.01, + "learning_rate": 3.714136152409355e-05, + "loss": 3.6299, + "step": 785408 + }, + { + "epoch": 1.01, + "learning_rate": 3.713297557658303e-05, + "loss": 3.62, + "step": 785920 + }, + { + "epoch": 1.01, + "learning_rate": 3.712458962907251e-05, + "loss": 3.6353, + "step": 786432 + }, + { + "epoch": 1.01, + "learning_rate": 3.711620368156199e-05, + "loss": 3.6218, + "step": 786944 + }, + { + "epoch": 1.01, + "learning_rate": 3.71078341128552e-05, + "loss": 3.6346, + "step": 787456 + }, + { + "epoch": 1.01, + "learning_rate": 3.709944816534468e-05, + "loss": 3.6269, + "step": 787968 + }, + { + "epoch": 1.01, + "learning_rate": 3.709106221783416e-05, + "loss": 3.6105, + "step": 788480 + }, + { + "epoch": 1.01, + "learning_rate": 3.7082676270323644e-05, + "loss": 3.6204, + "step": 788992 + }, + { + "epoch": 1.01, + "learning_rate": 3.707430670161685e-05, + "loss": 3.6143, + "step": 789504 + }, + { + "epoch": 1.01, + "learning_rate": 3.706592075410633e-05, + "loss": 3.6301, + "step": 790016 + }, + { + "epoch": 1.01, + "learning_rate": 3.705753480659581e-05, + "loss": 3.6197, + "step": 790528 + }, + { + "epoch": 1.01, + "learning_rate": 3.704914885908529e-05, + "loss": 3.62, + "step": 791040 + }, + { + "epoch": 1.01, + "learning_rate": 3.704076291157477e-05, + "loss": 3.6044, + "step": 791552 + }, + { + "epoch": 1.01, + "learning_rate": 3.703237696406425e-05, + "loss": 3.6241, + "step": 792064 + }, + { + "epoch": 1.01, + "learning_rate": 3.702400739535746e-05, + "loss": 3.6127, + "step": 792576 + }, + { + "epoch": 1.01, + "learning_rate": 3.701562144784694e-05, + "loss": 3.6264, + "step": 793088 + }, + { + "epoch": 1.01, + "learning_rate": 3.700723550033642e-05, + "loss": 3.6155, + "step": 793600 + }, + { + "epoch": 1.01, + "learning_rate": 3.69988495528259e-05, + "loss": 3.6177, + "step": 794112 + }, + { + "epoch": 1.01, + "learning_rate": 3.699047998411911e-05, + "loss": 3.6178, + "step": 794624 + }, + { + "epoch": 1.01, + "learning_rate": 3.69820940366086e-05, + "loss": 3.6064, + "step": 795136 + }, + { + "epoch": 1.01, + "learning_rate": 3.697370808909808e-05, + "loss": 3.6262, + "step": 795648 + }, + { + "epoch": 1.01, + "learning_rate": 3.696532214158756e-05, + "loss": 3.6153, + "step": 796160 + }, + { + "epoch": 1.01, + "learning_rate": 3.695695257288077e-05, + "loss": 3.6256, + "step": 796672 + }, + { + "epoch": 1.01, + "learning_rate": 3.694856662537025e-05, + "loss": 3.6133, + "step": 797184 + }, + { + "epoch": 1.01, + "learning_rate": 3.694018067785973e-05, + "loss": 3.6103, + "step": 797696 + }, + { + "epoch": 1.01, + "learning_rate": 3.693179473034921e-05, + "loss": 3.613, + "step": 798208 + }, + { + "epoch": 1.01, + "learning_rate": 3.6923425161642416e-05, + "loss": 3.6177, + "step": 798720 + }, + { + "epoch": 1.01, + "learning_rate": 3.6915039214131896e-05, + "loss": 3.6142, + "step": 799232 + }, + { + "epoch": 1.01, + "learning_rate": 3.6906653266621376e-05, + "loss": 3.6233, + "step": 799744 + }, + { + "epoch": 1.01, + "learning_rate": 3.6898267319110856e-05, + "loss": 3.6181, + "step": 800256 + }, + { + "epoch": 1.01, + "learning_rate": 3.6889897750404065e-05, + "loss": 3.6394, + "step": 800768 + }, + { + "epoch": 1.01, + "learning_rate": 3.6881511802893545e-05, + "loss": 3.6309, + "step": 801280 + }, + { + "epoch": 1.01, + "learning_rate": 3.687312585538303e-05, + "loss": 3.6202, + "step": 801792 + }, + { + "epoch": 1.01, + "learning_rate": 3.686473990787251e-05, + "loss": 3.6217, + "step": 802304 + }, + { + "epoch": 1.01, + "learning_rate": 3.685637033916572e-05, + "loss": 3.6107, + "step": 802816 + }, + { + "epoch": 1.01, + "learning_rate": 3.68479843916552e-05, + "loss": 3.6181, + "step": 803328 + }, + { + "epoch": 1.01, + "learning_rate": 3.683959844414468e-05, + "loss": 3.621, + "step": 803840 + }, + { + "epoch": 1.01, + "learning_rate": 3.683121249663416e-05, + "loss": 3.6299, + "step": 804352 + }, + { + "epoch": 1.01, + "learning_rate": 3.682282654912364e-05, + "loss": 3.6229, + "step": 804864 + }, + { + "epoch": 1.01, + "learning_rate": 3.6814440601613113e-05, + "loss": 3.6059, + "step": 805376 + }, + { + "epoch": 1.01, + "learning_rate": 3.680605465410259e-05, + "loss": 3.6174, + "step": 805888 + }, + { + "epoch": 1.01, + "learning_rate": 3.679768508539581e-05, + "loss": 3.6045, + "step": 806400 + }, + { + "epoch": 1.01, + "learning_rate": 3.678929913788529e-05, + "loss": 3.6148, + "step": 806912 + }, + { + "epoch": 1.01, + "learning_rate": 3.678091319037477e-05, + "loss": 3.6113, + "step": 807424 + }, + { + "epoch": 1.01, + "learning_rate": 3.677252724286425e-05, + "loss": 3.6189, + "step": 807936 + }, + { + "epoch": 1.01, + "learning_rate": 3.6764157674157465e-05, + "loss": 3.6274, + "step": 808448 + }, + { + "epoch": 1.01, + "learning_rate": 3.675577172664694e-05, + "loss": 3.623, + "step": 808960 + }, + { + "epoch": 1.02, + "learning_rate": 3.674738577913642e-05, + "loss": 3.6107, + "step": 809472 + }, + { + "epoch": 1.02, + "learning_rate": 3.67389998316259e-05, + "loss": 3.6166, + "step": 809984 + }, + { + "epoch": 1.02, + "learning_rate": 3.6730630262919114e-05, + "loss": 3.6182, + "step": 810496 + }, + { + "epoch": 1.02, + "learning_rate": 3.672224431540859e-05, + "loss": 3.6117, + "step": 811008 + }, + { + "epoch": 1.02, + "learning_rate": 3.671385836789807e-05, + "loss": 3.6111, + "step": 811520 + }, + { + "epoch": 1.02, + "learning_rate": 3.670547242038755e-05, + "loss": 3.619, + "step": 812032 + }, + { + "epoch": 1.02, + "learning_rate": 3.669708647287703e-05, + "loss": 3.6288, + "step": 812544 + }, + { + "epoch": 1.02, + "learning_rate": 3.6688716904170236e-05, + "loss": 3.6338, + "step": 813056 + }, + { + "epoch": 1.02, + "learning_rate": 3.668033095665972e-05, + "loss": 3.6137, + "step": 813568 + }, + { + "epoch": 1.02, + "learning_rate": 3.66719450091492e-05, + "loss": 3.6257, + "step": 814080 + }, + { + "epoch": 1.02, + "learning_rate": 3.666355906163868e-05, + "loss": 3.614, + "step": 814592 + }, + { + "epoch": 1.02, + "learning_rate": 3.665517311412816e-05, + "loss": 3.6188, + "step": 815104 + }, + { + "epoch": 1.02, + "learning_rate": 3.664680354542137e-05, + "loss": 3.617, + "step": 815616 + }, + { + "epoch": 1.02, + "learning_rate": 3.663841759791085e-05, + "loss": 3.6312, + "step": 816128 + }, + { + "epoch": 1.02, + "learning_rate": 3.663003165040033e-05, + "loss": 3.6223, + "step": 816640 + }, + { + "epoch": 1.02, + "learning_rate": 3.662164570288981e-05, + "loss": 3.6041, + "step": 817152 + }, + { + "epoch": 1.02, + "learning_rate": 3.661327613418302e-05, + "loss": 3.6089, + "step": 817664 + }, + { + "epoch": 1.02, + "learning_rate": 3.66048901866725e-05, + "loss": 3.6064, + "step": 818176 + }, + { + "epoch": 1.02, + "learning_rate": 3.659650423916198e-05, + "loss": 3.6096, + "step": 818688 + }, + { + "epoch": 1.02, + "learning_rate": 3.658811829165146e-05, + "loss": 3.6172, + "step": 819200 + }, + { + "epoch": 1.02, + "learning_rate": 3.6579748722944676e-05, + "loss": 3.6263, + "step": 819712 + }, + { + "epoch": 1.02, + "learning_rate": 3.6571362775434156e-05, + "loss": 3.5978, + "step": 820224 + }, + { + "epoch": 1.02, + "learning_rate": 3.6562976827923636e-05, + "loss": 3.6148, + "step": 820736 + }, + { + "epoch": 1.02, + "learning_rate": 3.6554590880413116e-05, + "loss": 3.6259, + "step": 821248 + }, + { + "epoch": 1.02, + "learning_rate": 3.6546204932902596e-05, + "loss": 3.6178, + "step": 821760 + }, + { + "epoch": 1.02, + "learning_rate": 3.6537835364195805e-05, + "loss": 3.6224, + "step": 822272 + }, + { + "epoch": 1.02, + "learning_rate": 3.6529449416685285e-05, + "loss": 3.6205, + "step": 822784 + }, + { + "epoch": 1.02, + "learning_rate": 3.6521063469174765e-05, + "loss": 3.6011, + "step": 823296 + }, + { + "epoch": 1.02, + "learning_rate": 3.6512677521664245e-05, + "loss": 3.6203, + "step": 823808 + }, + { + "epoch": 1.02, + "learning_rate": 3.6504291574153725e-05, + "loss": 3.6253, + "step": 824320 + }, + { + "epoch": 1.02, + "learning_rate": 3.6495922005446934e-05, + "loss": 3.612, + "step": 824832 + }, + { + "epoch": 1.02, + "learning_rate": 3.6487536057936414e-05, + "loss": 3.5987, + "step": 825344 + }, + { + "epoch": 1.02, + "learning_rate": 3.6479150110425894e-05, + "loss": 3.6134, + "step": 825856 + }, + { + "epoch": 1.02, + "learning_rate": 3.6470764162915374e-05, + "loss": 3.6118, + "step": 826368 + }, + { + "epoch": 1.02, + "learning_rate": 3.646237821540486e-05, + "loss": 3.6189, + "step": 826880 + }, + { + "epoch": 1.02, + "learning_rate": 3.645400864669807e-05, + "loss": 3.6135, + "step": 827392 + }, + { + "epoch": 1.02, + "learning_rate": 3.644562269918755e-05, + "loss": 3.6236, + "step": 827904 + }, + { + "epoch": 1.02, + "learning_rate": 3.643723675167703e-05, + "loss": 3.6056, + "step": 828416 + }, + { + "epoch": 1.02, + "learning_rate": 3.642885080416651e-05, + "loss": 3.6277, + "step": 828928 + }, + { + "epoch": 1.02, + "learning_rate": 3.642048123545972e-05, + "loss": 3.6105, + "step": 829440 + }, + { + "epoch": 1.02, + "learning_rate": 3.64120952879492e-05, + "loss": 3.6225, + "step": 829952 + }, + { + "epoch": 1.02, + "learning_rate": 3.640370934043868e-05, + "loss": 3.6333, + "step": 830464 + }, + { + "epoch": 1.02, + "learning_rate": 3.639532339292816e-05, + "loss": 3.6125, + "step": 830976 + }, + { + "epoch": 1.02, + "learning_rate": 3.638693744541764e-05, + "loss": 3.619, + "step": 831488 + }, + { + "epoch": 1.02, + "learning_rate": 3.637856787671085e-05, + "loss": 3.6199, + "step": 832000 + }, + { + "epoch": 1.02, + "learning_rate": 3.637018192920033e-05, + "loss": 3.6044, + "step": 832512 + }, + { + "epoch": 1.02, + "learning_rate": 3.6361795981689815e-05, + "loss": 3.6081, + "step": 833024 + }, + { + "epoch": 1.02, + "learning_rate": 3.6353410034179295e-05, + "loss": 3.6114, + "step": 833536 + }, + { + "epoch": 1.02, + "learning_rate": 3.6345040465472504e-05, + "loss": 3.6202, + "step": 834048 + }, + { + "epoch": 1.02, + "learning_rate": 3.6336654517961984e-05, + "loss": 3.621, + "step": 834560 + }, + { + "epoch": 1.02, + "learning_rate": 3.6328268570451464e-05, + "loss": 3.6229, + "step": 835072 + }, + { + "epoch": 1.02, + "learning_rate": 3.6319882622940944e-05, + "loss": 3.6192, + "step": 835584 + }, + { + "epoch": 1.02, + "learning_rate": 3.631151305423415e-05, + "loss": 3.6123, + "step": 836096 + }, + { + "epoch": 1.02, + "learning_rate": 3.630312710672363e-05, + "loss": 3.602, + "step": 836608 + }, + { + "epoch": 1.02, + "learning_rate": 3.629474115921311e-05, + "loss": 3.6142, + "step": 837120 + }, + { + "epoch": 1.02, + "learning_rate": 3.628635521170259e-05, + "loss": 3.6244, + "step": 837632 + }, + { + "epoch": 1.02, + "learning_rate": 3.6277969264192066e-05, + "loss": 3.6237, + "step": 838144 + }, + { + "epoch": 1.02, + "learning_rate": 3.626959969548528e-05, + "loss": 3.6083, + "step": 838656 + }, + { + "epoch": 1.02, + "learning_rate": 3.626121374797477e-05, + "loss": 3.6117, + "step": 839168 + }, + { + "epoch": 1.03, + "eval_loss": 3.840956687927246, + "eval_runtime": 424.9722, + "eval_samples_per_second": 897.92, + "eval_steps_per_second": 28.061, + "step": 839509 + }, + { + "epoch": 0.0, + "learning_rate": 3.625282780046425e-05, + "loss": 3.5998, + "step": 839680 + }, + { + "epoch": 0.0, + "learning_rate": 3.624444185295372e-05, + "loss": 3.6135, + "step": 840192 + }, + { + "epoch": 0.0, + "learning_rate": 3.62360559054432e-05, + "loss": 3.6158, + "step": 840704 + }, + { + "epoch": 0.0, + "learning_rate": 3.622766995793268e-05, + "loss": 3.6179, + "step": 841216 + }, + { + "epoch": 0.0, + "learning_rate": 3.621928401042216e-05, + "loss": 3.6304, + "step": 841728 + }, + { + "epoch": 0.0, + "learning_rate": 3.621091444171537e-05, + "loss": 3.6131, + "step": 842240 + }, + { + "epoch": 0.0, + "learning_rate": 3.620252849420485e-05, + "loss": 3.6202, + "step": 842752 + }, + { + "epoch": 0.0, + "learning_rate": 3.619414254669433e-05, + "loss": 3.6161, + "step": 843264 + }, + { + "epoch": 0.0, + "learning_rate": 3.618575659918381e-05, + "loss": 3.6097, + "step": 843776 + }, + { + "epoch": 0.0, + "learning_rate": 3.617737065167329e-05, + "loss": 3.6101, + "step": 844288 + }, + { + "epoch": 0.0, + "learning_rate": 3.6169001082966506e-05, + "loss": 3.6223, + "step": 844800 + }, + { + "epoch": 0.0, + "learning_rate": 3.6160615135455986e-05, + "loss": 3.6266, + "step": 845312 + }, + { + "epoch": 0.0, + "learning_rate": 3.6152245566749195e-05, + "loss": 3.6196, + "step": 845824 + }, + { + "epoch": 0.0, + "learning_rate": 3.6143859619238675e-05, + "loss": 3.5968, + "step": 846336 + }, + { + "epoch": 0.0, + "learning_rate": 3.6135473671728155e-05, + "loss": 3.6197, + "step": 846848 + }, + { + "epoch": 0.0, + "learning_rate": 3.6127087724217635e-05, + "loss": 3.6017, + "step": 847360 + }, + { + "epoch": 0.0, + "learning_rate": 3.6118701776707115e-05, + "loss": 3.609, + "step": 847872 + }, + { + "epoch": 0.0, + "learning_rate": 3.6110315829196595e-05, + "loss": 3.6122, + "step": 848384 + }, + { + "epoch": 0.0, + "learning_rate": 3.6101929881686075e-05, + "loss": 3.6111, + "step": 848896 + }, + { + "epoch": 0.0, + "learning_rate": 3.6093543934175555e-05, + "loss": 3.6181, + "step": 849408 + }, + { + "epoch": 0.0, + "learning_rate": 3.6085157986665035e-05, + "loss": 3.6254, + "step": 849920 + }, + { + "epoch": 0.0, + "learning_rate": 3.6076788417958244e-05, + "loss": 3.6159, + "step": 850432 + }, + { + "epoch": 0.0, + "learning_rate": 3.6068402470447724e-05, + "loss": 3.6163, + "step": 850944 + }, + { + "epoch": 0.0, + "learning_rate": 3.6060016522937204e-05, + "loss": 3.6029, + "step": 851456 + }, + { + "epoch": 0.0, + "learning_rate": 3.6051630575426684e-05, + "loss": 3.6204, + "step": 851968 + }, + { + "epoch": 0.0, + "learning_rate": 3.60432610067199e-05, + "loss": 3.616, + "step": 852480 + }, + { + "epoch": 0.0, + "learning_rate": 3.603487505920938e-05, + "loss": 3.6087, + "step": 852992 + }, + { + "epoch": 0.0, + "learning_rate": 3.602648911169886e-05, + "loss": 3.6123, + "step": 853504 + }, + { + "epoch": 0.0, + "learning_rate": 3.601810316418834e-05, + "loss": 3.607, + "step": 854016 + }, + { + "epoch": 0.0, + "learning_rate": 3.600971721667782e-05, + "loss": 3.6146, + "step": 854528 + }, + { + "epoch": 0.01, + "learning_rate": 3.600134764797103e-05, + "loss": 3.6057, + "step": 855040 + }, + { + "epoch": 0.01, + "learning_rate": 3.599296170046051e-05, + "loss": 3.6153, + "step": 855552 + }, + { + "epoch": 0.01, + "learning_rate": 3.598457575294999e-05, + "loss": 3.6203, + "step": 856064 + }, + { + "epoch": 0.01, + "learning_rate": 3.597618980543947e-05, + "loss": 3.6192, + "step": 856576 + }, + { + "epoch": 0.01, + "learning_rate": 3.596782023673268e-05, + "loss": 3.6113, + "step": 857088 + }, + { + "epoch": 0.01, + "learning_rate": 3.595943428922216e-05, + "loss": 3.6102, + "step": 857600 + }, + { + "epoch": 0.01, + "learning_rate": 3.595104834171164e-05, + "loss": 3.6183, + "step": 858112 + }, + { + "epoch": 0.01, + "learning_rate": 3.594267877300485e-05, + "loss": 3.6085, + "step": 858624 + }, + { + "epoch": 0.01, + "learning_rate": 3.593429282549433e-05, + "loss": 3.6042, + "step": 859136 + }, + { + "epoch": 0.01, + "learning_rate": 3.592590687798381e-05, + "loss": 3.6088, + "step": 859648 + }, + { + "epoch": 0.01, + "learning_rate": 3.591752093047329e-05, + "loss": 3.6012, + "step": 860160 + }, + { + "epoch": 0.01, + "learning_rate": 3.59091513617665e-05, + "loss": 3.6086, + "step": 860672 + }, + { + "epoch": 0.01, + "learning_rate": 3.590076541425598e-05, + "loss": 3.6089, + "step": 861184 + }, + { + "epoch": 0.01, + "learning_rate": 3.589237946674546e-05, + "loss": 3.6124, + "step": 861696 + }, + { + "epoch": 0.01, + "learning_rate": 3.588399351923494e-05, + "loss": 3.6158, + "step": 862208 + }, + { + "epoch": 0.01, + "learning_rate": 3.587562395052815e-05, + "loss": 3.6136, + "step": 862720 + }, + { + "epoch": 0.01, + "learning_rate": 3.586723800301763e-05, + "loss": 3.613, + "step": 863232 + }, + { + "epoch": 0.01, + "learning_rate": 3.585885205550711e-05, + "loss": 3.6079, + "step": 863744 + }, + { + "epoch": 0.01, + "learning_rate": 3.585046610799659e-05, + "loss": 3.589, + "step": 864256 + }, + { + "epoch": 0.01, + "learning_rate": 3.584208016048608e-05, + "loss": 3.6199, + "step": 864768 + }, + { + "epoch": 0.01, + "learning_rate": 3.583371059177929e-05, + "loss": 3.6048, + "step": 865280 + }, + { + "epoch": 0.01, + "learning_rate": 3.582532464426877e-05, + "loss": 3.6096, + "step": 865792 + }, + { + "epoch": 0.01, + "learning_rate": 3.581693869675825e-05, + "loss": 3.6159, + "step": 866304 + }, + { + "epoch": 0.01, + "learning_rate": 3.580855274924773e-05, + "loss": 3.6035, + "step": 866816 + }, + { + "epoch": 0.01, + "learning_rate": 3.5800183180540936e-05, + "loss": 3.5893, + "step": 867328 + }, + { + "epoch": 0.01, + "learning_rate": 3.5791797233030416e-05, + "loss": 3.5975, + "step": 867840 + }, + { + "epoch": 0.01, + "learning_rate": 3.5783411285519896e-05, + "loss": 3.6056, + "step": 868352 + }, + { + "epoch": 0.01, + "learning_rate": 3.5775025338009376e-05, + "loss": 3.6014, + "step": 868864 + }, + { + "epoch": 0.01, + "learning_rate": 3.5766655769302585e-05, + "loss": 3.6189, + "step": 869376 + }, + { + "epoch": 0.01, + "learning_rate": 3.5758269821792065e-05, + "loss": 3.6025, + "step": 869888 + }, + { + "epoch": 0.01, + "learning_rate": 3.5749883874281545e-05, + "loss": 3.593, + "step": 870400 + }, + { + "epoch": 0.01, + "learning_rate": 3.574149792677103e-05, + "loss": 3.6239, + "step": 870912 + }, + { + "epoch": 0.01, + "learning_rate": 3.573312835806424e-05, + "loss": 3.5983, + "step": 871424 + }, + { + "epoch": 0.01, + "learning_rate": 3.572474241055372e-05, + "loss": 3.5922, + "step": 871936 + }, + { + "epoch": 0.01, + "learning_rate": 3.57163564630432e-05, + "loss": 3.6066, + "step": 872448 + }, + { + "epoch": 0.01, + "learning_rate": 3.5707970515532674e-05, + "loss": 3.6009, + "step": 872960 + }, + { + "epoch": 0.01, + "learning_rate": 3.569960094682589e-05, + "loss": 3.6003, + "step": 873472 + }, + { + "epoch": 0.01, + "learning_rate": 3.569121499931537e-05, + "loss": 3.6049, + "step": 873984 + }, + { + "epoch": 0.01, + "learning_rate": 3.568282905180485e-05, + "loss": 3.5872, + "step": 874496 + }, + { + "epoch": 0.01, + "learning_rate": 3.567444310429432e-05, + "loss": 3.5984, + "step": 875008 + }, + { + "epoch": 0.01, + "learning_rate": 3.566607353558754e-05, + "loss": 3.6126, + "step": 875520 + }, + { + "epoch": 0.01, + "learning_rate": 3.565768758807702e-05, + "loss": 3.6067, + "step": 876032 + }, + { + "epoch": 0.01, + "learning_rate": 3.56493016405665e-05, + "loss": 3.6142, + "step": 876544 + }, + { + "epoch": 0.01, + "learning_rate": 3.564091569305598e-05, + "loss": 3.6024, + "step": 877056 + }, + { + "epoch": 0.01, + "learning_rate": 3.5632546124349194e-05, + "loss": 3.6213, + "step": 877568 + }, + { + "epoch": 0.01, + "learning_rate": 3.5624160176838674e-05, + "loss": 3.5975, + "step": 878080 + }, + { + "epoch": 0.01, + "learning_rate": 3.561577422932815e-05, + "loss": 3.612, + "step": 878592 + }, + { + "epoch": 0.01, + "learning_rate": 3.560738828181763e-05, + "loss": 3.6069, + "step": 879104 + }, + { + "epoch": 0.01, + "learning_rate": 3.559900233430711e-05, + "loss": 3.5915, + "step": 879616 + }, + { + "epoch": 0.01, + "learning_rate": 3.559063276560032e-05, + "loss": 3.6118, + "step": 880128 + }, + { + "epoch": 0.01, + "learning_rate": 3.5582246818089796e-05, + "loss": 3.6116, + "step": 880640 + }, + { + "epoch": 0.01, + "learning_rate": 3.5573860870579276e-05, + "loss": 3.6075, + "step": 881152 + }, + { + "epoch": 0.01, + "learning_rate": 3.5565474923068756e-05, + "loss": 3.6081, + "step": 881664 + }, + { + "epoch": 0.01, + "learning_rate": 3.555710535436197e-05, + "loss": 3.5931, + "step": 882176 + }, + { + "epoch": 0.01, + "learning_rate": 3.554871940685145e-05, + "loss": 3.5859, + "step": 882688 + }, + { + "epoch": 0.01, + "learning_rate": 3.554033345934093e-05, + "loss": 3.5994, + "step": 883200 + }, + { + "epoch": 0.01, + "learning_rate": 3.553194751183041e-05, + "loss": 3.6084, + "step": 883712 + }, + { + "epoch": 0.01, + "learning_rate": 3.552357794312362e-05, + "loss": 3.5961, + "step": 884224 + }, + { + "epoch": 0.01, + "learning_rate": 3.55151919956131e-05, + "loss": 3.5965, + "step": 884736 + }, + { + "epoch": 0.01, + "learning_rate": 3.550680604810258e-05, + "loss": 3.5989, + "step": 885248 + }, + { + "epoch": 0.02, + "learning_rate": 3.549842010059206e-05, + "loss": 3.6046, + "step": 885760 + }, + { + "epoch": 0.02, + "learning_rate": 3.549003415308154e-05, + "loss": 3.599, + "step": 886272 + }, + { + "epoch": 0.02, + "learning_rate": 3.548166458437475e-05, + "loss": 3.5992, + "step": 886784 + }, + { + "epoch": 0.02, + "learning_rate": 3.547327863686423e-05, + "loss": 3.6113, + "step": 887296 + }, + { + "epoch": 0.02, + "learning_rate": 3.546489268935371e-05, + "loss": 3.6207, + "step": 887808 + }, + { + "epoch": 0.02, + "learning_rate": 3.545650674184319e-05, + "loss": 3.6085, + "step": 888320 + }, + { + "epoch": 0.02, + "learning_rate": 3.5448120794332677e-05, + "loss": 3.5959, + "step": 888832 + }, + { + "epoch": 0.02, + "learning_rate": 3.5439751225625886e-05, + "loss": 3.5982, + "step": 889344 + }, + { + "epoch": 0.02, + "learning_rate": 3.5431365278115366e-05, + "loss": 3.6003, + "step": 889856 + }, + { + "epoch": 0.02, + "learning_rate": 3.5422979330604846e-05, + "loss": 3.6117, + "step": 890368 + }, + { + "epoch": 0.02, + "learning_rate": 3.5414593383094326e-05, + "loss": 3.6021, + "step": 890880 + }, + { + "epoch": 0.02, + "learning_rate": 3.5406207435583805e-05, + "loss": 3.5995, + "step": 891392 + }, + { + "epoch": 0.02, + "learning_rate": 3.5397837866877015e-05, + "loss": 3.6002, + "step": 891904 + }, + { + "epoch": 0.02, + "learning_rate": 3.5389451919366495e-05, + "loss": 3.6077, + "step": 892416 + }, + { + "epoch": 0.02, + "learning_rate": 3.5381065971855975e-05, + "loss": 3.6037, + "step": 892928 + }, + { + "epoch": 0.02, + "learning_rate": 3.5372680024345454e-05, + "loss": 3.599, + "step": 893440 + }, + { + "epoch": 0.02, + "learning_rate": 3.5364310455638664e-05, + "loss": 3.5934, + "step": 893952 + }, + { + "epoch": 0.02, + "learning_rate": 3.5355924508128144e-05, + "loss": 3.5947, + "step": 894464 + }, + { + "epoch": 0.02, + "learning_rate": 3.5347538560617623e-05, + "loss": 3.5988, + "step": 894976 + }, + { + "epoch": 0.02, + "learning_rate": 3.533915261310711e-05, + "loss": 3.5921, + "step": 895488 + }, + { + "epoch": 0.02, + "learning_rate": 3.533076666559659e-05, + "loss": 3.5989, + "step": 896000 + }, + { + "epoch": 0.02, + "learning_rate": 3.53223970968898e-05, + "loss": 3.5949, + "step": 896512 + }, + { + "epoch": 0.02, + "learning_rate": 3.531401114937928e-05, + "loss": 3.6027, + "step": 897024 + }, + { + "epoch": 0.02, + "learning_rate": 3.530562520186876e-05, + "loss": 3.5949, + "step": 897536 + }, + { + "epoch": 0.02, + "learning_rate": 3.529723925435824e-05, + "loss": 3.6091, + "step": 898048 + }, + { + "epoch": 0.02, + "learning_rate": 3.528886968565145e-05, + "loss": 3.6122, + "step": 898560 + }, + { + "epoch": 0.02, + "learning_rate": 3.528048373814093e-05, + "loss": 3.5998, + "step": 899072 + }, + { + "epoch": 0.02, + "learning_rate": 3.527209779063041e-05, + "loss": 3.6115, + "step": 899584 + }, + { + "epoch": 0.02, + "learning_rate": 3.526371184311989e-05, + "loss": 3.5995, + "step": 900096 + }, + { + "epoch": 0.02, + "learning_rate": 3.525532589560937e-05, + "loss": 3.5982, + "step": 900608 + }, + { + "epoch": 0.02, + "learning_rate": 3.524695632690258e-05, + "loss": 3.5974, + "step": 901120 + }, + { + "epoch": 0.02, + "learning_rate": 3.5238570379392064e-05, + "loss": 3.5897, + "step": 901632 + }, + { + "epoch": 0.02, + "learning_rate": 3.5230184431881544e-05, + "loss": 3.6005, + "step": 902144 + }, + { + "epoch": 0.02, + "learning_rate": 3.5221798484371024e-05, + "loss": 3.6011, + "step": 902656 + }, + { + "epoch": 0.02, + "learning_rate": 3.521342891566423e-05, + "loss": 3.6042, + "step": 903168 + }, + { + "epoch": 0.02, + "learning_rate": 3.520504296815371e-05, + "loss": 3.5969, + "step": 903680 + }, + { + "epoch": 0.02, + "learning_rate": 3.519665702064319e-05, + "loss": 3.606, + "step": 904192 + }, + { + "epoch": 0.02, + "learning_rate": 3.518827107313267e-05, + "loss": 3.6005, + "step": 904704 + }, + { + "epoch": 0.02, + "learning_rate": 3.517990150442588e-05, + "loss": 3.5947, + "step": 905216 + }, + { + "epoch": 0.02, + "learning_rate": 3.517151555691536e-05, + "loss": 3.6006, + "step": 905728 + }, + { + "epoch": 0.02, + "learning_rate": 3.516312960940484e-05, + "loss": 3.6048, + "step": 906240 + }, + { + "epoch": 0.02, + "learning_rate": 3.515474366189432e-05, + "loss": 3.609, + "step": 906752 + }, + { + "epoch": 0.02, + "learning_rate": 3.514637409318753e-05, + "loss": 3.591, + "step": 907264 + }, + { + "epoch": 0.02, + "learning_rate": 3.513798814567702e-05, + "loss": 3.6147, + "step": 907776 + }, + { + "epoch": 0.02, + "learning_rate": 3.51296021981665e-05, + "loss": 3.5951, + "step": 908288 + }, + { + "epoch": 0.02, + "learning_rate": 3.512121625065598e-05, + "loss": 3.6076, + "step": 908800 + }, + { + "epoch": 0.02, + "learning_rate": 3.5112846681949187e-05, + "loss": 3.6031, + "step": 909312 + }, + { + "epoch": 0.02, + "learning_rate": 3.5104460734438666e-05, + "loss": 3.5968, + "step": 909824 + }, + { + "epoch": 0.02, + "learning_rate": 3.5096074786928146e-05, + "loss": 3.5904, + "step": 910336 + }, + { + "epoch": 0.02, + "learning_rate": 3.5087688839417626e-05, + "loss": 3.6171, + "step": 910848 + }, + { + "epoch": 0.02, + "learning_rate": 3.5079319270710836e-05, + "loss": 3.5871, + "step": 911360 + }, + { + "epoch": 0.02, + "learning_rate": 3.5070933323200315e-05, + "loss": 3.6064, + "step": 911872 + }, + { + "epoch": 0.02, + "learning_rate": 3.5062547375689795e-05, + "loss": 3.5999, + "step": 912384 + }, + { + "epoch": 0.02, + "learning_rate": 3.5054161428179275e-05, + "loss": 3.5992, + "step": 912896 + }, + { + "epoch": 0.02, + "learning_rate": 3.5045791859472484e-05, + "loss": 3.5941, + "step": 913408 + }, + { + "epoch": 0.02, + "learning_rate": 3.503740591196197e-05, + "loss": 3.6017, + "step": 913920 + }, + { + "epoch": 0.02, + "learning_rate": 3.502901996445145e-05, + "loss": 3.6011, + "step": 914432 + }, + { + "epoch": 0.02, + "learning_rate": 3.502063401694093e-05, + "loss": 3.6069, + "step": 914944 + }, + { + "epoch": 0.02, + "learning_rate": 3.5012248069430404e-05, + "loss": 3.5988, + "step": 915456 + }, + { + "epoch": 0.03, + "eval_loss": 3.8356547355651855, + "eval_runtime": 302.3937, + "eval_samples_per_second": 1261.901, + "eval_steps_per_second": 39.435, + "step": 915829 + }, + { + "epoch": 1.0, + "learning_rate": 3.500387850072362e-05, + "loss": 3.5923, + "step": 915968 + }, + { + "epoch": 1.0, + "learning_rate": 3.49954925532131e-05, + "loss": 3.5909, + "step": 916480 + }, + { + "epoch": 1.0, + "learning_rate": 3.498710660570257e-05, + "loss": 3.5945, + "step": 916992 + }, + { + "epoch": 1.0, + "learning_rate": 3.497872065819205e-05, + "loss": 3.5987, + "step": 917504 + }, + { + "epoch": 1.0, + "learning_rate": 3.497035108948527e-05, + "loss": 3.604, + "step": 918016 + }, + { + "epoch": 1.0, + "learning_rate": 3.496196514197475e-05, + "loss": 3.5924, + "step": 918528 + }, + { + "epoch": 1.0, + "learning_rate": 3.495357919446422e-05, + "loss": 3.6002, + "step": 919040 + }, + { + "epoch": 1.0, + "learning_rate": 3.494519324695371e-05, + "loss": 3.5959, + "step": 919552 + }, + { + "epoch": 1.0, + "learning_rate": 3.4936823678246925e-05, + "loss": 3.5876, + "step": 920064 + }, + { + "epoch": 1.0, + "learning_rate": 3.4928437730736405e-05, + "loss": 3.583, + "step": 920576 + }, + { + "epoch": 1.0, + "learning_rate": 3.492005178322588e-05, + "loss": 3.6059, + "step": 921088 + }, + { + "epoch": 1.0, + "learning_rate": 3.491166583571536e-05, + "loss": 3.603, + "step": 921600 + }, + { + "epoch": 1.0, + "learning_rate": 3.49033126458123e-05, + "loss": 3.5972, + "step": 922112 + }, + { + "epoch": 1.0, + "learning_rate": 3.489492669830178e-05, + "loss": 3.5757, + "step": 922624 + }, + { + "epoch": 1.0, + "learning_rate": 3.488654075079126e-05, + "loss": 3.5964, + "step": 923136 + }, + { + "epoch": 1.0, + "learning_rate": 3.487815480328074e-05, + "loss": 3.5801, + "step": 923648 + }, + { + "epoch": 1.0, + "learning_rate": 3.486976885577022e-05, + "loss": 3.5924, + "step": 924160 + }, + { + "epoch": 1.0, + "learning_rate": 3.4861382908259696e-05, + "loss": 3.59, + "step": 924672 + }, + { + "epoch": 1.0, + "learning_rate": 3.4852996960749176e-05, + "loss": 3.5886, + "step": 925184 + }, + { + "epoch": 1.0, + "learning_rate": 3.484461101323866e-05, + "loss": 3.597, + "step": 925696 + }, + { + "epoch": 1.0, + "learning_rate": 3.483624144453188e-05, + "loss": 3.6041, + "step": 926208 + }, + { + "epoch": 1.0, + "learning_rate": 3.482785549702135e-05, + "loss": 3.5939, + "step": 926720 + }, + { + "epoch": 1.0, + "learning_rate": 3.481946954951083e-05, + "loss": 3.5939, + "step": 927232 + }, + { + "epoch": 1.0, + "learning_rate": 3.481108360200031e-05, + "loss": 3.5871, + "step": 927744 + }, + { + "epoch": 1.0, + "learning_rate": 3.480269765448979e-05, + "loss": 3.5973, + "step": 928256 + }, + { + "epoch": 1.0, + "learning_rate": 3.4794328085783e-05, + "loss": 3.5975, + "step": 928768 + }, + { + "epoch": 1.0, + "learning_rate": 3.478594213827248e-05, + "loss": 3.5834, + "step": 929280 + }, + { + "epoch": 1.0, + "learning_rate": 3.477755619076196e-05, + "loss": 3.5907, + "step": 929792 + }, + { + "epoch": 1.0, + "learning_rate": 3.476917024325144e-05, + "loss": 3.5875, + "step": 930304 + }, + { + "epoch": 1.0, + "learning_rate": 3.476080067454465e-05, + "loss": 3.591, + "step": 930816 + }, + { + "epoch": 1.01, + "learning_rate": 3.475241472703413e-05, + "loss": 3.5882, + "step": 931328 + }, + { + "epoch": 1.01, + "learning_rate": 3.4744028779523616e-05, + "loss": 3.5949, + "step": 931840 + }, + { + "epoch": 1.01, + "learning_rate": 3.4735642832013096e-05, + "loss": 3.5926, + "step": 932352 + }, + { + "epoch": 1.01, + "learning_rate": 3.4727273263306305e-05, + "loss": 3.6009, + "step": 932864 + }, + { + "epoch": 1.01, + "learning_rate": 3.4718887315795785e-05, + "loss": 3.5888, + "step": 933376 + }, + { + "epoch": 1.01, + "learning_rate": 3.4710501368285265e-05, + "loss": 3.5891, + "step": 933888 + }, + { + "epoch": 1.01, + "learning_rate": 3.4702115420774745e-05, + "loss": 3.6008, + "step": 934400 + }, + { + "epoch": 1.01, + "learning_rate": 3.4693745852067954e-05, + "loss": 3.5824, + "step": 934912 + }, + { + "epoch": 1.01, + "learning_rate": 3.4685359904557434e-05, + "loss": 3.5834, + "step": 935424 + }, + { + "epoch": 1.01, + "learning_rate": 3.4676973957046914e-05, + "loss": 3.5874, + "step": 935936 + }, + { + "epoch": 1.01, + "learning_rate": 3.4668588009536394e-05, + "loss": 3.5828, + "step": 936448 + }, + { + "epoch": 1.01, + "learning_rate": 3.46602184408296e-05, + "loss": 3.5847, + "step": 936960 + }, + { + "epoch": 1.01, + "learning_rate": 3.465183249331908e-05, + "loss": 3.5893, + "step": 937472 + }, + { + "epoch": 1.01, + "learning_rate": 3.464344654580857e-05, + "loss": 3.5924, + "step": 937984 + }, + { + "epoch": 1.01, + "learning_rate": 3.463506059829805e-05, + "loss": 3.591, + "step": 938496 + }, + { + "epoch": 1.01, + "learning_rate": 3.462669102959126e-05, + "loss": 3.5947, + "step": 939008 + }, + { + "epoch": 1.01, + "learning_rate": 3.461830508208074e-05, + "loss": 3.5911, + "step": 939520 + }, + { + "epoch": 1.01, + "learning_rate": 3.460991913457022e-05, + "loss": 3.5909, + "step": 940032 + }, + { + "epoch": 1.01, + "learning_rate": 3.46015331870597e-05, + "loss": 3.5713, + "step": 940544 + }, + { + "epoch": 1.01, + "learning_rate": 3.459316361835291e-05, + "loss": 3.5993, + "step": 941056 + }, + { + "epoch": 1.01, + "learning_rate": 3.458477767084239e-05, + "loss": 3.5837, + "step": 941568 + }, + { + "epoch": 1.01, + "learning_rate": 3.457639172333187e-05, + "loss": 3.587, + "step": 942080 + }, + { + "epoch": 1.01, + "learning_rate": 3.456800577582135e-05, + "loss": 3.5908, + "step": 942592 + }, + { + "epoch": 1.01, + "learning_rate": 3.455963620711456e-05, + "loss": 3.5845, + "step": 943104 + }, + { + "epoch": 1.01, + "learning_rate": 3.455125025960404e-05, + "loss": 3.5719, + "step": 943616 + }, + { + "epoch": 1.01, + "learning_rate": 3.454286431209352e-05, + "loss": 3.5797, + "step": 944128 + }, + { + "epoch": 1.01, + "learning_rate": 3.4534478364583004e-05, + "loss": 3.5839, + "step": 944640 + }, + { + "epoch": 1.01, + "learning_rate": 3.452610879587621e-05, + "loss": 3.5782, + "step": 945152 + }, + { + "epoch": 1.01, + "learning_rate": 3.451772284836569e-05, + "loss": 3.5982, + "step": 945664 + }, + { + "epoch": 1.01, + "learning_rate": 3.450933690085517e-05, + "loss": 3.5854, + "step": 946176 + }, + { + "epoch": 1.01, + "learning_rate": 3.450095095334465e-05, + "loss": 3.5708, + "step": 946688 + }, + { + "epoch": 1.01, + "learning_rate": 3.449258138463786e-05, + "loss": 3.6022, + "step": 947200 + }, + { + "epoch": 1.01, + "learning_rate": 3.448419543712734e-05, + "loss": 3.5778, + "step": 947712 + }, + { + "epoch": 1.01, + "learning_rate": 3.447580948961682e-05, + "loss": 3.5724, + "step": 948224 + }, + { + "epoch": 1.01, + "learning_rate": 3.44674235421063e-05, + "loss": 3.5855, + "step": 948736 + }, + { + "epoch": 1.01, + "learning_rate": 3.445903759459578e-05, + "loss": 3.5811, + "step": 949248 + }, + { + "epoch": 1.01, + "learning_rate": 3.445066802588899e-05, + "loss": 3.5767, + "step": 949760 + }, + { + "epoch": 1.01, + "learning_rate": 3.444228207837847e-05, + "loss": 3.5841, + "step": 950272 + }, + { + "epoch": 1.01, + "learning_rate": 3.443389613086796e-05, + "loss": 3.5713, + "step": 950784 + }, + { + "epoch": 1.01, + "learning_rate": 3.442551018335744e-05, + "loss": 3.5731, + "step": 951296 + }, + { + "epoch": 1.01, + "learning_rate": 3.441712423584692e-05, + "loss": 3.5961, + "step": 951808 + }, + { + "epoch": 1.01, + "learning_rate": 3.4408754667140126e-05, + "loss": 3.5879, + "step": 952320 + }, + { + "epoch": 1.01, + "learning_rate": 3.4400368719629606e-05, + "loss": 3.5911, + "step": 952832 + }, + { + "epoch": 1.01, + "learning_rate": 3.4391982772119086e-05, + "loss": 3.5865, + "step": 953344 + }, + { + "epoch": 1.01, + "learning_rate": 3.4383613203412295e-05, + "loss": 3.598, + "step": 953856 + }, + { + "epoch": 1.01, + "learning_rate": 3.4375227255901775e-05, + "loss": 3.577, + "step": 954368 + }, + { + "epoch": 1.01, + "learning_rate": 3.4366841308391255e-05, + "loss": 3.5944, + "step": 954880 + }, + { + "epoch": 1.01, + "learning_rate": 3.4358455360880735e-05, + "loss": 3.5818, + "step": 955392 + }, + { + "epoch": 1.01, + "learning_rate": 3.4350069413370215e-05, + "loss": 3.576, + "step": 955904 + }, + { + "epoch": 1.01, + "learning_rate": 3.4341699844663424e-05, + "loss": 3.5887, + "step": 956416 + }, + { + "epoch": 1.01, + "learning_rate": 3.433331389715291e-05, + "loss": 3.595, + "step": 956928 + }, + { + "epoch": 1.01, + "learning_rate": 3.432492794964239e-05, + "loss": 3.5861, + "step": 957440 + }, + { + "epoch": 1.01, + "learning_rate": 3.431654200213187e-05, + "loss": 3.5931, + "step": 957952 + }, + { + "epoch": 1.01, + "learning_rate": 3.430817243342508e-05, + "loss": 3.5705, + "step": 958464 + }, + { + "epoch": 1.01, + "learning_rate": 3.429978648591456e-05, + "loss": 3.5664, + "step": 958976 + }, + { + "epoch": 1.01, + "learning_rate": 3.429140053840404e-05, + "loss": 3.5789, + "step": 959488 + }, + { + "epoch": 1.01, + "learning_rate": 3.428301459089352e-05, + "loss": 3.5871, + "step": 960000 + }, + { + "epoch": 1.01, + "learning_rate": 3.427464502218673e-05, + "loss": 3.5796, + "step": 960512 + }, + { + "epoch": 1.01, + "learning_rate": 3.426625907467621e-05, + "loss": 3.5783, + "step": 961024 + }, + { + "epoch": 1.01, + "learning_rate": 3.425787312716569e-05, + "loss": 3.5801, + "step": 961536 + }, + { + "epoch": 1.02, + "learning_rate": 3.424948717965517e-05, + "loss": 3.5858, + "step": 962048 + }, + { + "epoch": 1.02, + "learning_rate": 3.424111761094838e-05, + "loss": 3.5771, + "step": 962560 + }, + { + "epoch": 1.02, + "learning_rate": 3.4232731663437865e-05, + "loss": 3.5775, + "step": 963072 + }, + { + "epoch": 1.02, + "learning_rate": 3.4224345715927345e-05, + "loss": 3.5879, + "step": 963584 + }, + { + "epoch": 1.02, + "learning_rate": 3.4215959768416825e-05, + "loss": 3.6, + "step": 964096 + }, + { + "epoch": 1.02, + "learning_rate": 3.4207590199710034e-05, + "loss": 3.5901, + "step": 964608 + }, + { + "epoch": 1.02, + "learning_rate": 3.4199204252199514e-05, + "loss": 3.573, + "step": 965120 + }, + { + "epoch": 1.02, + "learning_rate": 3.4190818304688994e-05, + "loss": 3.5779, + "step": 965632 + }, + { + "epoch": 1.02, + "learning_rate": 3.4182432357178473e-05, + "loss": 3.5787, + "step": 966144 + }, + { + "epoch": 1.02, + "learning_rate": 3.417406278847168e-05, + "loss": 3.5913, + "step": 966656 + }, + { + "epoch": 1.02, + "learning_rate": 3.416567684096116e-05, + "loss": 3.5859, + "step": 967168 + }, + { + "epoch": 1.02, + "learning_rate": 3.415729089345064e-05, + "loss": 3.5789, + "step": 967680 + }, + { + "epoch": 1.02, + "learning_rate": 3.414890494594012e-05, + "loss": 3.5812, + "step": 968192 + }, + { + "epoch": 1.02, + "learning_rate": 3.414053537723333e-05, + "loss": 3.5844, + "step": 968704 + }, + { + "epoch": 1.02, + "learning_rate": 3.413214942972282e-05, + "loss": 3.588, + "step": 969216 + }, + { + "epoch": 1.02, + "learning_rate": 3.41237634822123e-05, + "loss": 3.5783, + "step": 969728 + }, + { + "epoch": 1.02, + "learning_rate": 3.411537753470178e-05, + "loss": 3.5776, + "step": 970240 + }, + { + "epoch": 1.02, + "learning_rate": 3.410700796599499e-05, + "loss": 3.5715, + "step": 970752 + }, + { + "epoch": 1.02, + "learning_rate": 3.409862201848447e-05, + "loss": 3.5792, + "step": 971264 + }, + { + "epoch": 1.02, + "learning_rate": 3.409023607097395e-05, + "loss": 3.5768, + "step": 971776 + }, + { + "epoch": 1.02, + "learning_rate": 3.408185012346343e-05, + "loss": 3.5745, + "step": 972288 + }, + { + "epoch": 1.02, + "learning_rate": 3.4073480554756636e-05, + "loss": 3.5753, + "step": 972800 + }, + { + "epoch": 1.02, + "learning_rate": 3.4065094607246116e-05, + "loss": 3.5836, + "step": 973312 + }, + { + "epoch": 1.02, + "learning_rate": 3.4056708659735596e-05, + "loss": 3.5734, + "step": 973824 + }, + { + "epoch": 1.02, + "learning_rate": 3.404832271222507e-05, + "loss": 3.5893, + "step": 974336 + }, + { + "epoch": 1.02, + "learning_rate": 3.4039953143518285e-05, + "loss": 3.5952, + "step": 974848 + }, + { + "epoch": 1.02, + "learning_rate": 3.403156719600777e-05, + "loss": 3.581, + "step": 975360 + }, + { + "epoch": 1.02, + "learning_rate": 3.402318124849725e-05, + "loss": 3.5884, + "step": 975872 + }, + { + "epoch": 1.02, + "learning_rate": 3.4014795300986725e-05, + "loss": 3.5821, + "step": 976384 + }, + { + "epoch": 1.02, + "learning_rate": 3.4006409353476205e-05, + "loss": 3.5785, + "step": 976896 + }, + { + "epoch": 1.02, + "learning_rate": 3.399803978476942e-05, + "loss": 3.5819, + "step": 977408 + }, + { + "epoch": 1.02, + "learning_rate": 3.39896538372589e-05, + "loss": 3.5641, + "step": 977920 + }, + { + "epoch": 1.02, + "learning_rate": 3.3981267889748374e-05, + "loss": 3.5831, + "step": 978432 + }, + { + "epoch": 1.02, + "learning_rate": 3.3972881942237854e-05, + "loss": 3.5804, + "step": 978944 + }, + { + "epoch": 1.02, + "learning_rate": 3.396451237353107e-05, + "loss": 3.584, + "step": 979456 + }, + { + "epoch": 1.02, + "learning_rate": 3.395612642602054e-05, + "loss": 3.5757, + "step": 979968 + }, + { + "epoch": 1.02, + "learning_rate": 3.394774047851002e-05, + "loss": 3.5885, + "step": 980480 + }, + { + "epoch": 1.02, + "learning_rate": 3.393935453099951e-05, + "loss": 3.5807, + "step": 980992 + }, + { + "epoch": 1.02, + "learning_rate": 3.3930984962292726e-05, + "loss": 3.5753, + "step": 981504 + }, + { + "epoch": 1.02, + "learning_rate": 3.39225990147822e-05, + "loss": 3.5818, + "step": 982016 + }, + { + "epoch": 1.02, + "learning_rate": 3.391421306727168e-05, + "loss": 3.5833, + "step": 982528 + }, + { + "epoch": 1.02, + "learning_rate": 3.390582711976116e-05, + "loss": 3.5896, + "step": 983040 + }, + { + "epoch": 1.02, + "learning_rate": 3.3897457551054375e-05, + "loss": 3.577, + "step": 983552 + }, + { + "epoch": 1.02, + "learning_rate": 3.388907160354385e-05, + "loss": 3.5912, + "step": 984064 + }, + { + "epoch": 1.02, + "learning_rate": 3.388068565603333e-05, + "loss": 3.5789, + "step": 984576 + }, + { + "epoch": 1.02, + "learning_rate": 3.387229970852281e-05, + "loss": 3.5849, + "step": 985088 + }, + { + "epoch": 1.02, + "learning_rate": 3.386393013981602e-05, + "loss": 3.5854, + "step": 985600 + }, + { + "epoch": 1.02, + "learning_rate": 3.38555441923055e-05, + "loss": 3.5747, + "step": 986112 + }, + { + "epoch": 1.02, + "learning_rate": 3.384715824479498e-05, + "loss": 3.5743, + "step": 986624 + }, + { + "epoch": 1.02, + "learning_rate": 3.3838772297284463e-05, + "loss": 3.5926, + "step": 987136 + }, + { + "epoch": 1.02, + "learning_rate": 3.383040272857767e-05, + "loss": 3.5723, + "step": 987648 + }, + { + "epoch": 1.02, + "learning_rate": 3.382201678106715e-05, + "loss": 3.5818, + "step": 988160 + }, + { + "epoch": 1.02, + "learning_rate": 3.381363083355663e-05, + "loss": 3.5837, + "step": 988672 + }, + { + "epoch": 1.02, + "learning_rate": 3.380524488604611e-05, + "loss": 3.5801, + "step": 989184 + }, + { + "epoch": 1.02, + "learning_rate": 3.379687531733932e-05, + "loss": 3.5768, + "step": 989696 + }, + { + "epoch": 1.02, + "learning_rate": 3.37884893698288e-05, + "loss": 3.58, + "step": 990208 + }, + { + "epoch": 1.02, + "learning_rate": 3.378010342231828e-05, + "loss": 3.582, + "step": 990720 + }, + { + "epoch": 1.02, + "learning_rate": 3.377171747480776e-05, + "loss": 3.5849, + "step": 991232 + }, + { + "epoch": 1.02, + "learning_rate": 3.376334790610097e-05, + "loss": 3.5827, + "step": 991744 + }, + { + "epoch": 1.03, + "eval_loss": 3.8354902267456055, + "eval_runtime": 301.9122, + "eval_samples_per_second": 1263.914, + "eval_steps_per_second": 39.498, + "step": 992149 + }, + { + "epoch": 0.0, + "learning_rate": 3.375496195859045e-05, + "loss": 3.5779, + "step": 992256 + }, + { + "epoch": 0.0, + "learning_rate": 3.374657601107993e-05, + "loss": 3.5681, + "step": 992768 + }, + { + "epoch": 0.0, + "learning_rate": 3.373819006356942e-05, + "loss": 3.5753, + "step": 993280 + }, + { + "epoch": 0.0, + "learning_rate": 3.37298041160589e-05, + "loss": 3.5856, + "step": 993792 + }, + { + "epoch": 0.0, + "learning_rate": 3.3721434547352106e-05, + "loss": 3.5795, + "step": 994304 + }, + { + "epoch": 0.0, + "learning_rate": 3.3713048599841586e-05, + "loss": 3.5782, + "step": 994816 + }, + { + "epoch": 0.0, + "learning_rate": 3.3704662652331066e-05, + "loss": 3.5826, + "step": 995328 + }, + { + "epoch": 0.0, + "learning_rate": 3.3696276704820546e-05, + "loss": 3.5763, + "step": 995840 + }, + { + "epoch": 0.0, + "learning_rate": 3.3687907136113755e-05, + "loss": 3.5686, + "step": 996352 + }, + { + "epoch": 0.0, + "learning_rate": 3.3679521188603235e-05, + "loss": 3.5699, + "step": 996864 + }, + { + "epoch": 0.0, + "learning_rate": 3.3671135241092715e-05, + "loss": 3.5852, + "step": 997376 + }, + { + "epoch": 0.0, + "learning_rate": 3.3662749293582195e-05, + "loss": 3.5833, + "step": 997888 + }, + { + "epoch": 0.0, + "learning_rate": 3.365439610367914e-05, + "loss": 3.5849, + "step": 998400 + }, + { + "epoch": 0.0, + "learning_rate": 3.364601015616862e-05, + "loss": 3.5515, + "step": 998912 + }, + { + "epoch": 0.0, + "learning_rate": 3.36376242086581e-05, + "loss": 3.576, + "step": 999424 + }, + { + "epoch": 0.0, + "learning_rate": 3.362923826114758e-05, + "loss": 3.5626, + "step": 999936 + }, + { + "epoch": 0.0, + "learning_rate": 3.362085231363706e-05, + "loss": 3.5742, + "step": 1000448 + }, + { + "epoch": 0.0, + "learning_rate": 3.361246636612654e-05, + "loss": 3.5714, + "step": 1000960 + }, + { + "epoch": 0.0, + "learning_rate": 3.360408041861602e-05, + "loss": 3.5693, + "step": 1001472 + }, + { + "epoch": 0.0, + "learning_rate": 3.35956944711055e-05, + "loss": 3.574, + "step": 1001984 + }, + { + "epoch": 0.0, + "learning_rate": 3.358732490239871e-05, + "loss": 3.5908, + "step": 1002496 + }, + { + "epoch": 0.0, + "learning_rate": 3.357893895488819e-05, + "loss": 3.5763, + "step": 1003008 + }, + { + "epoch": 0.0, + "learning_rate": 3.357055300737767e-05, + "loss": 3.5759, + "step": 1003520 + }, + { + "epoch": 0.0, + "learning_rate": 3.356216705986715e-05, + "loss": 3.569, + "step": 1004032 + }, + { + "epoch": 0.0, + "learning_rate": 3.355378111235663e-05, + "loss": 3.5807, + "step": 1004544 + }, + { + "epoch": 0.0, + "learning_rate": 3.354541154364984e-05, + "loss": 3.5779, + "step": 1005056 + }, + { + "epoch": 0.0, + "learning_rate": 3.353702559613932e-05, + "loss": 3.5648, + "step": 1005568 + }, + { + "epoch": 0.0, + "learning_rate": 3.3528639648628804e-05, + "loss": 3.5743, + "step": 1006080 + }, + { + "epoch": 0.0, + "learning_rate": 3.3520253701118284e-05, + "loss": 3.5668, + "step": 1006592 + }, + { + "epoch": 0.0, + "learning_rate": 3.3511884132411493e-05, + "loss": 3.5715, + "step": 1007104 + }, + { + "epoch": 0.01, + "learning_rate": 3.350349818490097e-05, + "loss": 3.5715, + "step": 1007616 + }, + { + "epoch": 0.01, + "learning_rate": 3.349511223739045e-05, + "loss": 3.5736, + "step": 1008128 + }, + { + "epoch": 0.01, + "learning_rate": 3.348672628987993e-05, + "loss": 3.5756, + "step": 1008640 + }, + { + "epoch": 0.01, + "learning_rate": 3.347835672117314e-05, + "loss": 3.5813, + "step": 1009152 + }, + { + "epoch": 0.01, + "learning_rate": 3.346997077366262e-05, + "loss": 3.5768, + "step": 1009664 + }, + { + "epoch": 0.01, + "learning_rate": 3.34615848261521e-05, + "loss": 3.5698, + "step": 1010176 + }, + { + "epoch": 0.01, + "learning_rate": 3.345319887864158e-05, + "loss": 3.5789, + "step": 1010688 + }, + { + "epoch": 0.01, + "learning_rate": 3.344482930993479e-05, + "loss": 3.5629, + "step": 1011200 + }, + { + "epoch": 0.01, + "learning_rate": 3.343644336242427e-05, + "loss": 3.5662, + "step": 1011712 + }, + { + "epoch": 0.01, + "learning_rate": 3.342805741491376e-05, + "loss": 3.5704, + "step": 1012224 + }, + { + "epoch": 0.01, + "learning_rate": 3.341967146740324e-05, + "loss": 3.5636, + "step": 1012736 + }, + { + "epoch": 0.01, + "learning_rate": 3.341130189869645e-05, + "loss": 3.5675, + "step": 1013248 + }, + { + "epoch": 0.01, + "learning_rate": 3.340291595118593e-05, + "loss": 3.5731, + "step": 1013760 + }, + { + "epoch": 0.01, + "learning_rate": 3.339453000367541e-05, + "loss": 3.5748, + "step": 1014272 + }, + { + "epoch": 0.01, + "learning_rate": 3.338614405616489e-05, + "loss": 3.572, + "step": 1014784 + }, + { + "epoch": 0.01, + "learning_rate": 3.3377774487458096e-05, + "loss": 3.5737, + "step": 1015296 + }, + { + "epoch": 0.01, + "learning_rate": 3.3369388539947576e-05, + "loss": 3.5736, + "step": 1015808 + }, + { + "epoch": 0.01, + "learning_rate": 3.3361002592437056e-05, + "loss": 3.5696, + "step": 1016320 + }, + { + "epoch": 0.01, + "learning_rate": 3.3352616644926536e-05, + "loss": 3.5552, + "step": 1016832 + }, + { + "epoch": 0.01, + "learning_rate": 3.3344247076219745e-05, + "loss": 3.5763, + "step": 1017344 + }, + { + "epoch": 0.01, + "learning_rate": 3.3335861128709225e-05, + "loss": 3.569, + "step": 1017856 + }, + { + "epoch": 0.01, + "learning_rate": 3.332747518119871e-05, + "loss": 3.5697, + "step": 1018368 + }, + { + "epoch": 0.01, + "learning_rate": 3.331908923368819e-05, + "loss": 3.5734, + "step": 1018880 + }, + { + "epoch": 0.01, + "learning_rate": 3.33107196649814e-05, + "loss": 3.5628, + "step": 1019392 + }, + { + "epoch": 0.01, + "learning_rate": 3.330233371747088e-05, + "loss": 3.5536, + "step": 1019904 + }, + { + "epoch": 0.01, + "learning_rate": 3.329394776996036e-05, + "loss": 3.5592, + "step": 1020416 + }, + { + "epoch": 0.01, + "learning_rate": 3.328556182244984e-05, + "loss": 3.5698, + "step": 1020928 + }, + { + "epoch": 0.01, + "learning_rate": 3.327719225374305e-05, + "loss": 3.5566, + "step": 1021440 + }, + { + "epoch": 0.01, + "learning_rate": 3.326880630623253e-05, + "loss": 3.5795, + "step": 1021952 + }, + { + "epoch": 0.01, + "learning_rate": 3.326042035872201e-05, + "loss": 3.5722, + "step": 1022464 + }, + { + "epoch": 0.01, + "learning_rate": 3.325203441121149e-05, + "loss": 3.5474, + "step": 1022976 + }, + { + "epoch": 0.01, + "learning_rate": 3.32436648425047e-05, + "loss": 3.5833, + "step": 1023488 + }, + { + "epoch": 0.01, + "learning_rate": 3.323527889499418e-05, + "loss": 3.5605, + "step": 1024000 + }, + { + "epoch": 0.01, + "learning_rate": 3.3226892947483665e-05, + "loss": 3.5561, + "step": 1024512 + }, + { + "epoch": 0.01, + "learning_rate": 3.3218506999973145e-05, + "loss": 3.5629, + "step": 1025024 + }, + { + "epoch": 0.01, + "learning_rate": 3.3210121052462625e-05, + "loss": 3.5659, + "step": 1025536 + }, + { + "epoch": 0.01, + "learning_rate": 3.3201751483755834e-05, + "loss": 3.5587, + "step": 1026048 + }, + { + "epoch": 0.01, + "learning_rate": 3.3193365536245314e-05, + "loss": 3.569, + "step": 1026560 + }, + { + "epoch": 0.01, + "learning_rate": 3.3184979588734794e-05, + "loss": 3.5499, + "step": 1027072 + }, + { + "epoch": 0.01, + "learning_rate": 3.3176593641224274e-05, + "loss": 3.5568, + "step": 1027584 + }, + { + "epoch": 0.01, + "learning_rate": 3.316822407251748e-05, + "loss": 3.5774, + "step": 1028096 + }, + { + "epoch": 0.01, + "learning_rate": 3.315983812500696e-05, + "loss": 3.5644, + "step": 1028608 + }, + { + "epoch": 0.01, + "learning_rate": 3.315145217749644e-05, + "loss": 3.5759, + "step": 1029120 + }, + { + "epoch": 0.01, + "learning_rate": 3.314306622998592e-05, + "loss": 3.5641, + "step": 1029632 + }, + { + "epoch": 0.01, + "learning_rate": 3.313469666127913e-05, + "loss": 3.5801, + "step": 1030144 + }, + { + "epoch": 0.01, + "learning_rate": 3.312631071376862e-05, + "loss": 3.5609, + "step": 1030656 + }, + { + "epoch": 0.01, + "learning_rate": 3.31179247662581e-05, + "loss": 3.5752, + "step": 1031168 + }, + { + "epoch": 0.01, + "learning_rate": 3.310953881874757e-05, + "loss": 3.5621, + "step": 1031680 + }, + { + "epoch": 0.01, + "learning_rate": 3.310116925004079e-05, + "loss": 3.5609, + "step": 1032192 + }, + { + "epoch": 0.01, + "learning_rate": 3.309278330253027e-05, + "loss": 3.5682, + "step": 1032704 + }, + { + "epoch": 0.01, + "learning_rate": 3.308439735501975e-05, + "loss": 3.5813, + "step": 1033216 + }, + { + "epoch": 0.01, + "learning_rate": 3.307601140750922e-05, + "loss": 3.5637, + "step": 1033728 + }, + { + "epoch": 0.01, + "learning_rate": 3.306764183880244e-05, + "loss": 3.5745, + "step": 1034240 + }, + { + "epoch": 0.01, + "learning_rate": 3.305925589129192e-05, + "loss": 3.5524, + "step": 1034752 + }, + { + "epoch": 0.01, + "learning_rate": 3.305086994378139e-05, + "loss": 3.5498, + "step": 1035264 + }, + { + "epoch": 0.01, + "learning_rate": 3.304248399627087e-05, + "loss": 3.5612, + "step": 1035776 + }, + { + "epoch": 0.01, + "learning_rate": 3.3034114427564086e-05, + "loss": 3.5651, + "step": 1036288 + }, + { + "epoch": 0.01, + "learning_rate": 3.302572848005357e-05, + "loss": 3.5627, + "step": 1036800 + }, + { + "epoch": 0.01, + "learning_rate": 3.3017342532543046e-05, + "loss": 3.5636, + "step": 1037312 + }, + { + "epoch": 0.01, + "learning_rate": 3.3008956585032526e-05, + "loss": 3.5606, + "step": 1037824 + }, + { + "epoch": 0.02, + "learning_rate": 3.3000570637522006e-05, + "loss": 3.5664, + "step": 1038336 + }, + { + "epoch": 0.02, + "learning_rate": 3.299220106881522e-05, + "loss": 3.5642, + "step": 1038848 + }, + { + "epoch": 0.02, + "learning_rate": 3.2983815121304695e-05, + "loss": 3.5584, + "step": 1039360 + }, + { + "epoch": 0.02, + "learning_rate": 3.2975429173794175e-05, + "loss": 3.5702, + "step": 1039872 + }, + { + "epoch": 0.02, + "learning_rate": 3.2967043226283655e-05, + "loss": 3.5796, + "step": 1040384 + }, + { + "epoch": 0.02, + "learning_rate": 3.2958673657576864e-05, + "loss": 3.5753, + "step": 1040896 + }, + { + "epoch": 0.02, + "learning_rate": 3.2950287710066344e-05, + "loss": 3.5538, + "step": 1041408 + }, + { + "epoch": 0.02, + "learning_rate": 3.2941901762555824e-05, + "loss": 3.5622, + "step": 1041920 + }, + { + "epoch": 0.02, + "learning_rate": 3.293351581504531e-05, + "loss": 3.5632, + "step": 1042432 + }, + { + "epoch": 0.02, + "learning_rate": 3.292514624633852e-05, + "loss": 3.5732, + "step": 1042944 + }, + { + "epoch": 0.02, + "learning_rate": 3.2916760298828e-05, + "loss": 3.5659, + "step": 1043456 + }, + { + "epoch": 0.02, + "learning_rate": 3.290837435131748e-05, + "loss": 3.5638, + "step": 1043968 + }, + { + "epoch": 0.02, + "learning_rate": 3.289998840380696e-05, + "loss": 3.5635, + "step": 1044480 + }, + { + "epoch": 0.02, + "learning_rate": 3.289161883510017e-05, + "loss": 3.5702, + "step": 1044992 + }, + { + "epoch": 0.02, + "learning_rate": 3.288323288758965e-05, + "loss": 3.5662, + "step": 1045504 + }, + { + "epoch": 0.02, + "learning_rate": 3.287484694007913e-05, + "loss": 3.5614, + "step": 1046016 + }, + { + "epoch": 0.02, + "learning_rate": 3.286646099256861e-05, + "loss": 3.5589, + "step": 1046528 + }, + { + "epoch": 0.02, + "learning_rate": 3.285809142386182e-05, + "loss": 3.554, + "step": 1047040 + }, + { + "epoch": 0.02, + "learning_rate": 3.28497054763513e-05, + "loss": 3.5655, + "step": 1047552 + }, + { + "epoch": 0.02, + "learning_rate": 3.284131952884078e-05, + "loss": 3.5583, + "step": 1048064 + }, + { + "epoch": 0.02, + "learning_rate": 3.283293358133026e-05, + "loss": 3.5558, + "step": 1048576 + }, + { + "epoch": 0.02, + "learning_rate": 3.282456401262347e-05, + "loss": 3.5596, + "step": 1049088 + }, + { + "epoch": 0.02, + "learning_rate": 3.281617806511295e-05, + "loss": 3.5659, + "step": 1049600 + }, + { + "epoch": 0.02, + "learning_rate": 3.280779211760243e-05, + "loss": 3.561, + "step": 1050112 + }, + { + "epoch": 0.02, + "learning_rate": 3.279940617009191e-05, + "loss": 3.5691, + "step": 1050624 + }, + { + "epoch": 0.02, + "learning_rate": 3.279103660138512e-05, + "loss": 3.5734, + "step": 1051136 + }, + { + "epoch": 0.02, + "learning_rate": 3.27826506538746e-05, + "loss": 3.5677, + "step": 1051648 + }, + { + "epoch": 0.02, + "learning_rate": 3.277426470636408e-05, + "loss": 3.5718, + "step": 1052160 + }, + { + "epoch": 0.02, + "learning_rate": 3.276587875885356e-05, + "loss": 3.5663, + "step": 1052672 + }, + { + "epoch": 0.02, + "learning_rate": 3.275750919014677e-05, + "loss": 3.559, + "step": 1053184 + }, + { + "epoch": 0.02, + "learning_rate": 3.274912324263625e-05, + "loss": 3.5651, + "step": 1053696 + }, + { + "epoch": 0.02, + "learning_rate": 3.274073729512573e-05, + "loss": 3.548, + "step": 1054208 + }, + { + "epoch": 0.02, + "learning_rate": 3.273235134761521e-05, + "loss": 3.5685, + "step": 1054720 + }, + { + "epoch": 0.02, + "learning_rate": 3.272398177890843e-05, + "loss": 3.5563, + "step": 1055232 + }, + { + "epoch": 0.02, + "learning_rate": 3.271559583139791e-05, + "loss": 3.5694, + "step": 1055744 + }, + { + "epoch": 0.02, + "learning_rate": 3.270720988388739e-05, + "loss": 3.5632, + "step": 1056256 + }, + { + "epoch": 0.02, + "learning_rate": 3.269882393637687e-05, + "loss": 3.5669, + "step": 1056768 + }, + { + "epoch": 0.02, + "learning_rate": 3.269043798886635e-05, + "loss": 3.5581, + "step": 1057280 + }, + { + "epoch": 0.02, + "learning_rate": 3.2682068420159556e-05, + "loss": 3.5579, + "step": 1057792 + }, + { + "epoch": 0.02, + "learning_rate": 3.2673682472649036e-05, + "loss": 3.563, + "step": 1058304 + }, + { + "epoch": 0.02, + "learning_rate": 3.2665296525138516e-05, + "loss": 3.5672, + "step": 1058816 + }, + { + "epoch": 0.02, + "learning_rate": 3.2656910577627996e-05, + "loss": 3.5713, + "step": 1059328 + }, + { + "epoch": 0.02, + "learning_rate": 3.2648541008921205e-05, + "loss": 3.5596, + "step": 1059840 + }, + { + "epoch": 0.02, + "learning_rate": 3.2640155061410685e-05, + "loss": 3.5723, + "step": 1060352 + }, + { + "epoch": 0.02, + "learning_rate": 3.2631769113900165e-05, + "loss": 3.5604, + "step": 1060864 + }, + { + "epoch": 0.02, + "learning_rate": 3.262338316638965e-05, + "loss": 3.5667, + "step": 1061376 + }, + { + "epoch": 0.02, + "learning_rate": 3.261501359768286e-05, + "loss": 3.5691, + "step": 1061888 + }, + { + "epoch": 0.02, + "learning_rate": 3.260662765017234e-05, + "loss": 3.5585, + "step": 1062400 + }, + { + "epoch": 0.02, + "learning_rate": 3.259824170266182e-05, + "loss": 3.5581, + "step": 1062912 + }, + { + "epoch": 0.02, + "learning_rate": 3.25898557551513e-05, + "loss": 3.5755, + "step": 1063424 + }, + { + "epoch": 0.02, + "learning_rate": 3.258148618644451e-05, + "loss": 3.5576, + "step": 1063936 + }, + { + "epoch": 0.02, + "learning_rate": 3.257310023893399e-05, + "loss": 3.5597, + "step": 1064448 + }, + { + "epoch": 0.02, + "learning_rate": 3.256471429142347e-05, + "loss": 3.5688, + "step": 1064960 + }, + { + "epoch": 0.02, + "learning_rate": 3.255632834391295e-05, + "loss": 3.5643, + "step": 1065472 + }, + { + "epoch": 0.02, + "learning_rate": 3.254795877520616e-05, + "loss": 3.5587, + "step": 1065984 + }, + { + "epoch": 0.02, + "learning_rate": 3.253957282769564e-05, + "loss": 3.5665, + "step": 1066496 + }, + { + "epoch": 0.02, + "learning_rate": 3.253118688018512e-05, + "loss": 3.5613, + "step": 1067008 + }, + { + "epoch": 0.02, + "learning_rate": 3.2522800932674605e-05, + "loss": 3.5709, + "step": 1067520 + }, + { + "epoch": 0.02, + "learning_rate": 3.2514431363967814e-05, + "loss": 3.5611, + "step": 1068032 + }, + { + "epoch": 0.03, + "eval_loss": 3.837040424346924, + "eval_runtime": 302.6819, + "eval_samples_per_second": 1260.7, + "eval_steps_per_second": 39.398, + "step": 1068469 + }, + { + "epoch": 1.0, + "learning_rate": 3.2506045416457294e-05, + "loss": 3.5592, + "step": 1068544 + }, + { + "epoch": 1.0, + "learning_rate": 3.2497659468946774e-05, + "loss": 3.5526, + "step": 1069056 + }, + { + "epoch": 1.0, + "learning_rate": 3.2489273521436254e-05, + "loss": 3.5599, + "step": 1069568 + }, + { + "epoch": 1.0, + "learning_rate": 3.248090395272946e-05, + "loss": 3.5713, + "step": 1070080 + }, + { + "epoch": 1.0, + "learning_rate": 3.247251800521894e-05, + "loss": 3.5648, + "step": 1070592 + }, + { + "epoch": 1.0, + "learning_rate": 3.246413205770842e-05, + "loss": 3.5614, + "step": 1071104 + }, + { + "epoch": 1.0, + "learning_rate": 3.24557461101979e-05, + "loss": 3.5579, + "step": 1071616 + }, + { + "epoch": 1.0, + "learning_rate": 3.244737654149111e-05, + "loss": 3.5616, + "step": 1072128 + }, + { + "epoch": 1.0, + "learning_rate": 3.243899059398059e-05, + "loss": 3.5492, + "step": 1072640 + }, + { + "epoch": 1.0, + "learning_rate": 3.243060464647007e-05, + "loss": 3.5587, + "step": 1073152 + }, + { + "epoch": 1.0, + "learning_rate": 3.242221869895956e-05, + "loss": 3.5611, + "step": 1073664 + }, + { + "epoch": 1.0, + "learning_rate": 3.241384913025277e-05, + "loss": 3.5709, + "step": 1074176 + }, + { + "epoch": 1.0, + "learning_rate": 3.240547956154598e-05, + "loss": 3.5684, + "step": 1074688 + }, + { + "epoch": 1.0, + "learning_rate": 3.239709361403546e-05, + "loss": 3.5355, + "step": 1075200 + }, + { + "epoch": 1.0, + "learning_rate": 3.238870766652494e-05, + "loss": 3.5582, + "step": 1075712 + }, + { + "epoch": 1.0, + "learning_rate": 3.238032171901442e-05, + "loss": 3.5438, + "step": 1076224 + }, + { + "epoch": 1.0, + "learning_rate": 3.23719357715039e-05, + "loss": 3.5593, + "step": 1076736 + }, + { + "epoch": 1.0, + "learning_rate": 3.236354982399338e-05, + "loss": 3.5516, + "step": 1077248 + }, + { + "epoch": 1.0, + "learning_rate": 3.235516387648286e-05, + "loss": 3.5558, + "step": 1077760 + }, + { + "epoch": 1.0, + "learning_rate": 3.234677792897234e-05, + "loss": 3.5518, + "step": 1078272 + }, + { + "epoch": 1.0, + "learning_rate": 3.2338408360265546e-05, + "loss": 3.5743, + "step": 1078784 + }, + { + "epoch": 1.0, + "learning_rate": 3.2330022412755026e-05, + "loss": 3.5574, + "step": 1079296 + }, + { + "epoch": 1.0, + "learning_rate": 3.232163646524451e-05, + "loss": 3.5621, + "step": 1079808 + }, + { + "epoch": 1.0, + "learning_rate": 3.231325051773399e-05, + "loss": 3.5517, + "step": 1080320 + }, + { + "epoch": 1.0, + "learning_rate": 3.23048809490272e-05, + "loss": 3.5713, + "step": 1080832 + }, + { + "epoch": 1.0, + "learning_rate": 3.229649500151668e-05, + "loss": 3.5582, + "step": 1081344 + }, + { + "epoch": 1.0, + "learning_rate": 3.228810905400616e-05, + "loss": 3.5486, + "step": 1081856 + }, + { + "epoch": 1.0, + "learning_rate": 3.227972310649564e-05, + "loss": 3.5585, + "step": 1082368 + }, + { + "epoch": 1.0, + "learning_rate": 3.227135353778885e-05, + "loss": 3.5541, + "step": 1082880 + }, + { + "epoch": 1.0, + "learning_rate": 3.226296759027833e-05, + "loss": 3.5532, + "step": 1083392 + }, + { + "epoch": 1.01, + "learning_rate": 3.225458164276781e-05, + "loss": 3.556, + "step": 1083904 + }, + { + "epoch": 1.01, + "learning_rate": 3.224619569525729e-05, + "loss": 3.5558, + "step": 1084416 + }, + { + "epoch": 1.01, + "learning_rate": 3.22378261265505e-05, + "loss": 3.5601, + "step": 1084928 + }, + { + "epoch": 1.01, + "learning_rate": 3.222944017903998e-05, + "loss": 3.5592, + "step": 1085440 + }, + { + "epoch": 1.01, + "learning_rate": 3.2221054231529466e-05, + "loss": 3.5611, + "step": 1085952 + }, + { + "epoch": 1.01, + "learning_rate": 3.2212668284018946e-05, + "loss": 3.5561, + "step": 1086464 + }, + { + "epoch": 1.01, + "learning_rate": 3.2204298715312155e-05, + "loss": 3.5654, + "step": 1086976 + }, + { + "epoch": 1.01, + "learning_rate": 3.2195912767801635e-05, + "loss": 3.542, + "step": 1087488 + }, + { + "epoch": 1.01, + "learning_rate": 3.2187526820291115e-05, + "loss": 3.5526, + "step": 1088000 + }, + { + "epoch": 1.01, + "learning_rate": 3.2179140872780595e-05, + "loss": 3.5534, + "step": 1088512 + }, + { + "epoch": 1.01, + "learning_rate": 3.217075492527007e-05, + "loss": 3.5411, + "step": 1089024 + }, + { + "epoch": 1.01, + "learning_rate": 3.2162385356563284e-05, + "loss": 3.551, + "step": 1089536 + }, + { + "epoch": 1.01, + "learning_rate": 3.2153999409052764e-05, + "loss": 3.558, + "step": 1090048 + }, + { + "epoch": 1.01, + "learning_rate": 3.2145613461542244e-05, + "loss": 3.5521, + "step": 1090560 + }, + { + "epoch": 1.01, + "learning_rate": 3.213722751403172e-05, + "loss": 3.5597, + "step": 1091072 + }, + { + "epoch": 1.01, + "learning_rate": 3.212885794532493e-05, + "loss": 3.5559, + "step": 1091584 + }, + { + "epoch": 1.01, + "learning_rate": 3.212047199781442e-05, + "loss": 3.5558, + "step": 1092096 + }, + { + "epoch": 1.01, + "learning_rate": 3.211208605030389e-05, + "loss": 3.5548, + "step": 1092608 + }, + { + "epoch": 1.01, + "learning_rate": 3.210370010279337e-05, + "loss": 3.5406, + "step": 1093120 + }, + { + "epoch": 1.01, + "learning_rate": 3.209533053408659e-05, + "loss": 3.5574, + "step": 1093632 + }, + { + "epoch": 1.01, + "learning_rate": 3.208694458657607e-05, + "loss": 3.553, + "step": 1094144 + }, + { + "epoch": 1.01, + "learning_rate": 3.207855863906554e-05, + "loss": 3.5589, + "step": 1094656 + }, + { + "epoch": 1.01, + "learning_rate": 3.207017269155502e-05, + "loss": 3.5511, + "step": 1095168 + }, + { + "epoch": 1.01, + "learning_rate": 3.206180312284824e-05, + "loss": 3.5468, + "step": 1095680 + }, + { + "epoch": 1.01, + "learning_rate": 3.205341717533772e-05, + "loss": 3.5401, + "step": 1096192 + }, + { + "epoch": 1.01, + "learning_rate": 3.204503122782719e-05, + "loss": 3.5441, + "step": 1096704 + }, + { + "epoch": 1.01, + "learning_rate": 3.203664528031667e-05, + "loss": 3.5533, + "step": 1097216 + }, + { + "epoch": 1.01, + "learning_rate": 3.202827571160989e-05, + "loss": 3.5383, + "step": 1097728 + }, + { + "epoch": 1.01, + "learning_rate": 3.201988976409937e-05, + "loss": 3.5637, + "step": 1098240 + }, + { + "epoch": 1.01, + "learning_rate": 3.201150381658885e-05, + "loss": 3.5562, + "step": 1098752 + }, + { + "epoch": 1.01, + "learning_rate": 3.2003117869078327e-05, + "loss": 3.5333, + "step": 1099264 + }, + { + "epoch": 1.01, + "learning_rate": 3.199474830037154e-05, + "loss": 3.5654, + "step": 1099776 + }, + { + "epoch": 1.01, + "learning_rate": 3.1986362352861016e-05, + "loss": 3.5417, + "step": 1100288 + }, + { + "epoch": 1.01, + "learning_rate": 3.1977976405350496e-05, + "loss": 3.5446, + "step": 1100800 + }, + { + "epoch": 1.01, + "learning_rate": 3.1969590457839976e-05, + "loss": 3.542, + "step": 1101312 + }, + { + "epoch": 1.01, + "learning_rate": 3.196122088913319e-05, + "loss": 3.5491, + "step": 1101824 + }, + { + "epoch": 1.01, + "learning_rate": 3.1952834941622665e-05, + "loss": 3.5422, + "step": 1102336 + }, + { + "epoch": 1.01, + "learning_rate": 3.1944448994112145e-05, + "loss": 3.5559, + "step": 1102848 + }, + { + "epoch": 1.01, + "learning_rate": 3.1936063046601625e-05, + "loss": 3.5293, + "step": 1103360 + }, + { + "epoch": 1.01, + "learning_rate": 3.192769347789484e-05, + "loss": 3.5409, + "step": 1103872 + }, + { + "epoch": 1.01, + "learning_rate": 3.191930753038432e-05, + "loss": 3.558, + "step": 1104384 + }, + { + "epoch": 1.01, + "learning_rate": 3.19109215828738e-05, + "loss": 3.5492, + "step": 1104896 + }, + { + "epoch": 1.01, + "learning_rate": 3.190253563536328e-05, + "loss": 3.5582, + "step": 1105408 + }, + { + "epoch": 1.01, + "learning_rate": 3.189416606665649e-05, + "loss": 3.5498, + "step": 1105920 + }, + { + "epoch": 1.01, + "learning_rate": 3.188578011914597e-05, + "loss": 3.5626, + "step": 1106432 + }, + { + "epoch": 1.01, + "learning_rate": 3.187739417163545e-05, + "loss": 3.5458, + "step": 1106944 + }, + { + "epoch": 1.01, + "learning_rate": 3.186900822412493e-05, + "loss": 3.5652, + "step": 1107456 + }, + { + "epoch": 1.01, + "learning_rate": 3.186063865541814e-05, + "loss": 3.5437, + "step": 1107968 + }, + { + "epoch": 1.01, + "learning_rate": 3.185225270790762e-05, + "loss": 3.5444, + "step": 1108480 + }, + { + "epoch": 1.01, + "learning_rate": 3.18438667603971e-05, + "loss": 3.5526, + "step": 1108992 + }, + { + "epoch": 1.01, + "learning_rate": 3.183548081288658e-05, + "loss": 3.5613, + "step": 1109504 + }, + { + "epoch": 1.01, + "learning_rate": 3.1827111244179794e-05, + "loss": 3.5516, + "step": 1110016 + }, + { + "epoch": 1.01, + "learning_rate": 3.1818725296669274e-05, + "loss": 3.5573, + "step": 1110528 + }, + { + "epoch": 1.01, + "learning_rate": 3.1810339349158754e-05, + "loss": 3.5383, + "step": 1111040 + }, + { + "epoch": 1.01, + "learning_rate": 3.1801953401648234e-05, + "loss": 3.5295, + "step": 1111552 + }, + { + "epoch": 1.01, + "learning_rate": 3.179358383294144e-05, + "loss": 3.5462, + "step": 1112064 + }, + { + "epoch": 1.01, + "learning_rate": 3.178519788543092e-05, + "loss": 3.55, + "step": 1112576 + }, + { + "epoch": 1.01, + "learning_rate": 3.17768119379204e-05, + "loss": 3.5433, + "step": 1113088 + }, + { + "epoch": 1.01, + "learning_rate": 3.176842599040988e-05, + "loss": 3.5453, + "step": 1113600 + }, + { + "epoch": 1.01, + "learning_rate": 3.176005642170309e-05, + "loss": 3.5482, + "step": 1114112 + }, + { + "epoch": 1.02, + "learning_rate": 3.175167047419257e-05, + "loss": 3.5478, + "step": 1114624 + }, + { + "epoch": 1.02, + "learning_rate": 3.174328452668205e-05, + "loss": 3.5457, + "step": 1115136 + }, + { + "epoch": 1.02, + "learning_rate": 3.173489857917153e-05, + "loss": 3.5425, + "step": 1115648 + }, + { + "epoch": 1.02, + "learning_rate": 3.172652901046475e-05, + "loss": 3.5557, + "step": 1116160 + }, + { + "epoch": 1.02, + "learning_rate": 3.171814306295423e-05, + "loss": 3.5651, + "step": 1116672 + }, + { + "epoch": 1.02, + "learning_rate": 3.170975711544371e-05, + "loss": 3.5585, + "step": 1117184 + }, + { + "epoch": 1.02, + "learning_rate": 3.170137116793319e-05, + "loss": 3.538, + "step": 1117696 + }, + { + "epoch": 1.02, + "learning_rate": 3.16930015992264e-05, + "loss": 3.5469, + "step": 1118208 + }, + { + "epoch": 1.02, + "learning_rate": 3.168461565171588e-05, + "loss": 3.5448, + "step": 1118720 + }, + { + "epoch": 1.02, + "learning_rate": 3.1676229704205357e-05, + "loss": 3.5564, + "step": 1119232 + }, + { + "epoch": 1.02, + "learning_rate": 3.1667843756694837e-05, + "loss": 3.5538, + "step": 1119744 + }, + { + "epoch": 1.02, + "learning_rate": 3.1659474187988046e-05, + "loss": 3.5439, + "step": 1120256 + }, + { + "epoch": 1.02, + "learning_rate": 3.1651088240477526e-05, + "loss": 3.5468, + "step": 1120768 + }, + { + "epoch": 1.02, + "learning_rate": 3.1642702292967006e-05, + "loss": 3.5513, + "step": 1121280 + }, + { + "epoch": 1.02, + "learning_rate": 3.1634316345456486e-05, + "loss": 3.55, + "step": 1121792 + }, + { + "epoch": 1.02, + "learning_rate": 3.16259467767497e-05, + "loss": 3.5443, + "step": 1122304 + }, + { + "epoch": 1.02, + "learning_rate": 3.161756082923918e-05, + "loss": 3.5464, + "step": 1122816 + }, + { + "epoch": 1.02, + "learning_rate": 3.160917488172866e-05, + "loss": 3.5355, + "step": 1123328 + }, + { + "epoch": 1.02, + "learning_rate": 3.160078893421814e-05, + "loss": 3.5483, + "step": 1123840 + }, + { + "epoch": 1.02, + "learning_rate": 3.159240298670762e-05, + "loss": 3.5373, + "step": 1124352 + }, + { + "epoch": 1.02, + "learning_rate": 3.158403341800083e-05, + "loss": 3.5411, + "step": 1124864 + }, + { + "epoch": 1.02, + "learning_rate": 3.157564747049031e-05, + "loss": 3.5411, + "step": 1125376 + }, + { + "epoch": 1.02, + "learning_rate": 3.156726152297979e-05, + "loss": 3.5488, + "step": 1125888 + }, + { + "epoch": 1.02, + "learning_rate": 3.155887557546927e-05, + "loss": 3.5454, + "step": 1126400 + }, + { + "epoch": 1.02, + "learning_rate": 3.155050600676248e-05, + "loss": 3.5476, + "step": 1126912 + }, + { + "epoch": 1.02, + "learning_rate": 3.154212005925196e-05, + "loss": 3.5566, + "step": 1127424 + }, + { + "epoch": 1.02, + "learning_rate": 3.153373411174144e-05, + "loss": 3.5564, + "step": 1127936 + }, + { + "epoch": 1.02, + "learning_rate": 3.152534816423092e-05, + "loss": 3.5555, + "step": 1128448 + }, + { + "epoch": 1.02, + "learning_rate": 3.1516978595524135e-05, + "loss": 3.5459, + "step": 1128960 + }, + { + "epoch": 1.02, + "learning_rate": 3.1508592648013615e-05, + "loss": 3.5461, + "step": 1129472 + }, + { + "epoch": 1.02, + "learning_rate": 3.1500206700503095e-05, + "loss": 3.5459, + "step": 1129984 + }, + { + "epoch": 1.02, + "learning_rate": 3.1491820752992575e-05, + "loss": 3.5288, + "step": 1130496 + }, + { + "epoch": 1.02, + "learning_rate": 3.1483451184285784e-05, + "loss": 3.5515, + "step": 1131008 + }, + { + "epoch": 1.02, + "learning_rate": 3.1475065236775264e-05, + "loss": 3.5439, + "step": 1131520 + }, + { + "epoch": 1.02, + "learning_rate": 3.1466679289264744e-05, + "loss": 3.5537, + "step": 1132032 + }, + { + "epoch": 1.02, + "learning_rate": 3.1458293341754224e-05, + "loss": 3.5419, + "step": 1132544 + }, + { + "epoch": 1.02, + "learning_rate": 3.144992377304743e-05, + "loss": 3.551, + "step": 1133056 + }, + { + "epoch": 1.02, + "learning_rate": 3.144153782553691e-05, + "loss": 3.5416, + "step": 1133568 + }, + { + "epoch": 1.02, + "learning_rate": 3.143315187802639e-05, + "loss": 3.5421, + "step": 1134080 + }, + { + "epoch": 1.02, + "learning_rate": 3.142476593051587e-05, + "loss": 3.5509, + "step": 1134592 + }, + { + "epoch": 1.02, + "learning_rate": 3.141639636180909e-05, + "loss": 3.5483, + "step": 1135104 + }, + { + "epoch": 1.02, + "learning_rate": 3.140801041429857e-05, + "loss": 3.5598, + "step": 1135616 + }, + { + "epoch": 1.02, + "learning_rate": 3.139962446678805e-05, + "loss": 3.5438, + "step": 1136128 + }, + { + "epoch": 1.02, + "learning_rate": 3.139123851927753e-05, + "loss": 3.5534, + "step": 1136640 + }, + { + "epoch": 1.02, + "learning_rate": 3.138286895057074e-05, + "loss": 3.5472, + "step": 1137152 + }, + { + "epoch": 1.02, + "learning_rate": 3.137448300306022e-05, + "loss": 3.5483, + "step": 1137664 + }, + { + "epoch": 1.02, + "learning_rate": 3.13660970555497e-05, + "loss": 3.5532, + "step": 1138176 + }, + { + "epoch": 1.02, + "learning_rate": 3.135771110803918e-05, + "loss": 3.542, + "step": 1138688 + }, + { + "epoch": 1.02, + "learning_rate": 3.1349341539332387e-05, + "loss": 3.5485, + "step": 1139200 + }, + { + "epoch": 1.02, + "learning_rate": 3.1340955591821867e-05, + "loss": 3.5581, + "step": 1139712 + }, + { + "epoch": 1.02, + "learning_rate": 3.1332569644311347e-05, + "loss": 3.5423, + "step": 1140224 + }, + { + "epoch": 1.02, + "learning_rate": 3.1324183696800826e-05, + "loss": 3.544, + "step": 1140736 + }, + { + "epoch": 1.02, + "learning_rate": 3.131581412809404e-05, + "loss": 3.5511, + "step": 1141248 + }, + { + "epoch": 1.02, + "learning_rate": 3.130742818058352e-05, + "loss": 3.5454, + "step": 1141760 + }, + { + "epoch": 1.02, + "learning_rate": 3.1299042233073e-05, + "loss": 3.5432, + "step": 1142272 + }, + { + "epoch": 1.02, + "learning_rate": 3.129065628556248e-05, + "loss": 3.5527, + "step": 1142784 + }, + { + "epoch": 1.02, + "learning_rate": 3.128228671685569e-05, + "loss": 3.5421, + "step": 1143296 + }, + { + "epoch": 1.02, + "learning_rate": 3.127390076934517e-05, + "loss": 3.5612, + "step": 1143808 + }, + { + "epoch": 1.02, + "learning_rate": 3.126551482183465e-05, + "loss": 3.5415, + "step": 1144320 + }, + { + "epoch": 1.03, + "eval_loss": 3.8377187252044678, + "eval_runtime": 303.3667, + "eval_samples_per_second": 1257.854, + "eval_steps_per_second": 39.309, + "step": 1144789 + }, + { + "epoch": 0.0, + "learning_rate": 3.125712887432413e-05, + "loss": 3.5201, + "step": 1144832 + }, + { + "epoch": 0.0, + "learning_rate": 3.124874292681361e-05, + "loss": 3.5433, + "step": 1145344 + }, + { + "epoch": 0.0, + "learning_rate": 3.124035697930309e-05, + "loss": 3.5355, + "step": 1145856 + }, + { + "epoch": 0.0, + "learning_rate": 3.1231971031792564e-05, + "loss": 3.5564, + "step": 1146368 + }, + { + "epoch": 0.0, + "learning_rate": 3.122358508428205e-05, + "loss": 3.547, + "step": 1146880 + }, + { + "epoch": 0.0, + "learning_rate": 3.121521551557526e-05, + "loss": 3.5493, + "step": 1147392 + }, + { + "epoch": 0.0, + "learning_rate": 3.120682956806475e-05, + "loss": 3.541, + "step": 1147904 + }, + { + "epoch": 0.0, + "learning_rate": 3.119844362055422e-05, + "loss": 3.5446, + "step": 1148416 + }, + { + "epoch": 0.0, + "learning_rate": 3.11900576730437e-05, + "loss": 3.5326, + "step": 1148928 + }, + { + "epoch": 0.0, + "learning_rate": 3.1181688104336916e-05, + "loss": 3.542, + "step": 1149440 + }, + { + "epoch": 0.0, + "learning_rate": 3.117330215682639e-05, + "loss": 3.5445, + "step": 1149952 + }, + { + "epoch": 0.0, + "learning_rate": 3.116491620931587e-05, + "loss": 3.5561, + "step": 1150464 + }, + { + "epoch": 0.0, + "learning_rate": 3.1156546640609085e-05, + "loss": 3.5515, + "step": 1150976 + }, + { + "epoch": 0.0, + "learning_rate": 3.1148160693098565e-05, + "loss": 3.5233, + "step": 1151488 + }, + { + "epoch": 0.0, + "learning_rate": 3.113977474558804e-05, + "loss": 3.5418, + "step": 1152000 + }, + { + "epoch": 0.0, + "learning_rate": 3.113138879807752e-05, + "loss": 3.5317, + "step": 1152512 + }, + { + "epoch": 0.0, + "learning_rate": 3.1123002850567e-05, + "loss": 3.5393, + "step": 1153024 + }, + { + "epoch": 0.0, + "learning_rate": 3.1114616903056485e-05, + "loss": 3.5367, + "step": 1153536 + }, + { + "epoch": 0.0, + "learning_rate": 3.1106230955545965e-05, + "loss": 3.5405, + "step": 1154048 + }, + { + "epoch": 0.0, + "learning_rate": 3.1097845008035445e-05, + "loss": 3.5377, + "step": 1154560 + }, + { + "epoch": 0.0, + "learning_rate": 3.1089475439328654e-05, + "loss": 3.5599, + "step": 1155072 + }, + { + "epoch": 0.0, + "learning_rate": 3.1081089491818134e-05, + "loss": 3.5447, + "step": 1155584 + }, + { + "epoch": 0.0, + "learning_rate": 3.1072703544307614e-05, + "loss": 3.5401, + "step": 1156096 + }, + { + "epoch": 0.0, + "learning_rate": 3.1064317596797093e-05, + "loss": 3.5355, + "step": 1156608 + }, + { + "epoch": 0.0, + "learning_rate": 3.10559480280903e-05, + "loss": 3.5552, + "step": 1157120 + }, + { + "epoch": 0.0, + "learning_rate": 3.104756208057978e-05, + "loss": 3.5391, + "step": 1157632 + }, + { + "epoch": 0.0, + "learning_rate": 3.103917613306926e-05, + "loss": 3.5319, + "step": 1158144 + }, + { + "epoch": 0.0, + "learning_rate": 3.103079018555874e-05, + "loss": 3.5429, + "step": 1158656 + }, + { + "epoch": 0.0, + "learning_rate": 3.102242061685195e-05, + "loss": 3.5353, + "step": 1159168 + }, + { + "epoch": 0.0, + "learning_rate": 3.101403466934144e-05, + "loss": 3.5364, + "step": 1159680 + }, + { + "epoch": 0.01, + "learning_rate": 3.100564872183092e-05, + "loss": 3.5404, + "step": 1160192 + }, + { + "epoch": 0.01, + "learning_rate": 3.09972627743204e-05, + "loss": 3.5369, + "step": 1160704 + }, + { + "epoch": 0.01, + "learning_rate": 3.098887682680988e-05, + "loss": 3.5441, + "step": 1161216 + }, + { + "epoch": 0.01, + "learning_rate": 3.098050725810309e-05, + "loss": 3.5473, + "step": 1161728 + }, + { + "epoch": 0.01, + "learning_rate": 3.097212131059257e-05, + "loss": 3.5451, + "step": 1162240 + }, + { + "epoch": 0.01, + "learning_rate": 3.096373536308205e-05, + "loss": 3.5409, + "step": 1162752 + }, + { + "epoch": 0.01, + "learning_rate": 3.095534941557153e-05, + "loss": 3.5463, + "step": 1163264 + }, + { + "epoch": 0.01, + "learning_rate": 3.0946979846864736e-05, + "loss": 3.5295, + "step": 1163776 + }, + { + "epoch": 0.01, + "learning_rate": 3.0938593899354216e-05, + "loss": 3.5357, + "step": 1164288 + }, + { + "epoch": 0.01, + "learning_rate": 3.0930207951843696e-05, + "loss": 3.5379, + "step": 1164800 + }, + { + "epoch": 0.01, + "learning_rate": 3.0921822004333176e-05, + "loss": 3.5291, + "step": 1165312 + }, + { + "epoch": 0.01, + "learning_rate": 3.091345243562639e-05, + "loss": 3.536, + "step": 1165824 + }, + { + "epoch": 0.01, + "learning_rate": 3.090506648811587e-05, + "loss": 3.5441, + "step": 1166336 + }, + { + "epoch": 0.01, + "learning_rate": 3.089668054060535e-05, + "loss": 3.5369, + "step": 1166848 + }, + { + "epoch": 0.01, + "learning_rate": 3.088829459309483e-05, + "loss": 3.5426, + "step": 1167360 + }, + { + "epoch": 0.01, + "learning_rate": 3.087992502438804e-05, + "loss": 3.5444, + "step": 1167872 + }, + { + "epoch": 0.01, + "learning_rate": 3.087153907687752e-05, + "loss": 3.5411, + "step": 1168384 + }, + { + "epoch": 0.01, + "learning_rate": 3.0863153129367e-05, + "loss": 3.538, + "step": 1168896 + }, + { + "epoch": 0.01, + "learning_rate": 3.085476718185648e-05, + "loss": 3.5242, + "step": 1169408 + }, + { + "epoch": 0.01, + "learning_rate": 3.084639761314969e-05, + "loss": 3.5395, + "step": 1169920 + }, + { + "epoch": 0.01, + "learning_rate": 3.083801166563917e-05, + "loss": 3.5426, + "step": 1170432 + }, + { + "epoch": 0.01, + "learning_rate": 3.082962571812865e-05, + "loss": 3.5387, + "step": 1170944 + }, + { + "epoch": 0.01, + "learning_rate": 3.082123977061813e-05, + "loss": 3.5377, + "step": 1171456 + }, + { + "epoch": 0.01, + "learning_rate": 3.081285382310761e-05, + "loss": 3.5316, + "step": 1171968 + }, + { + "epoch": 0.01, + "learning_rate": 3.0804484254400826e-05, + "loss": 3.5228, + "step": 1172480 + }, + { + "epoch": 0.01, + "learning_rate": 3.0796098306890306e-05, + "loss": 3.5265, + "step": 1172992 + }, + { + "epoch": 0.01, + "learning_rate": 3.0787712359379785e-05, + "loss": 3.5371, + "step": 1173504 + }, + { + "epoch": 0.01, + "learning_rate": 3.0779342790672995e-05, + "loss": 3.5303, + "step": 1174016 + }, + { + "epoch": 0.01, + "learning_rate": 3.0770956843162475e-05, + "loss": 3.5445, + "step": 1174528 + }, + { + "epoch": 0.01, + "learning_rate": 3.0762570895651954e-05, + "loss": 3.5394, + "step": 1175040 + }, + { + "epoch": 0.01, + "learning_rate": 3.0754184948141434e-05, + "loss": 3.5239, + "step": 1175552 + }, + { + "epoch": 0.01, + "learning_rate": 3.0745815379434644e-05, + "loss": 3.549, + "step": 1176064 + }, + { + "epoch": 0.01, + "learning_rate": 3.0737429431924124e-05, + "loss": 3.5261, + "step": 1176576 + }, + { + "epoch": 0.01, + "learning_rate": 3.0729043484413603e-05, + "loss": 3.5275, + "step": 1177088 + }, + { + "epoch": 0.01, + "learning_rate": 3.0720657536903083e-05, + "loss": 3.5267, + "step": 1177600 + }, + { + "epoch": 0.01, + "learning_rate": 3.071227158939256e-05, + "loss": 3.5393, + "step": 1178112 + }, + { + "epoch": 0.01, + "learning_rate": 3.070390202068578e-05, + "loss": 3.5239, + "step": 1178624 + }, + { + "epoch": 0.01, + "learning_rate": 3.069551607317526e-05, + "loss": 3.5371, + "step": 1179136 + }, + { + "epoch": 0.01, + "learning_rate": 3.068713012566474e-05, + "loss": 3.5142, + "step": 1179648 + }, + { + "epoch": 0.01, + "learning_rate": 3.067874417815422e-05, + "loss": 3.5258, + "step": 1180160 + }, + { + "epoch": 0.01, + "learning_rate": 3.067037460944743e-05, + "loss": 3.5429, + "step": 1180672 + }, + { + "epoch": 0.01, + "learning_rate": 3.066198866193691e-05, + "loss": 3.5364, + "step": 1181184 + }, + { + "epoch": 0.01, + "learning_rate": 3.065360271442639e-05, + "loss": 3.5376, + "step": 1181696 + }, + { + "epoch": 0.01, + "learning_rate": 3.064521676691587e-05, + "loss": 3.5385, + "step": 1182208 + }, + { + "epoch": 0.01, + "learning_rate": 3.063684719820908e-05, + "loss": 3.547, + "step": 1182720 + }, + { + "epoch": 0.01, + "learning_rate": 3.062846125069856e-05, + "loss": 3.5322, + "step": 1183232 + }, + { + "epoch": 0.01, + "learning_rate": 3.062007530318804e-05, + "loss": 3.5487, + "step": 1183744 + }, + { + "epoch": 0.01, + "learning_rate": 3.061168935567752e-05, + "loss": 3.5257, + "step": 1184256 + }, + { + "epoch": 0.01, + "learning_rate": 3.060331978697073e-05, + "loss": 3.5292, + "step": 1184768 + }, + { + "epoch": 0.01, + "learning_rate": 3.059493383946021e-05, + "loss": 3.5358, + "step": 1185280 + }, + { + "epoch": 0.01, + "learning_rate": 3.058654789194969e-05, + "loss": 3.5435, + "step": 1185792 + }, + { + "epoch": 0.01, + "learning_rate": 3.057816194443917e-05, + "loss": 3.5378, + "step": 1186304 + }, + { + "epoch": 0.01, + "learning_rate": 3.056979237573238e-05, + "loss": 3.5424, + "step": 1186816 + }, + { + "epoch": 0.01, + "learning_rate": 3.056140642822186e-05, + "loss": 3.5241, + "step": 1187328 + }, + { + "epoch": 0.01, + "learning_rate": 3.055302048071134e-05, + "loss": 3.5135, + "step": 1187840 + }, + { + "epoch": 0.01, + "learning_rate": 3.0544634533200815e-05, + "loss": 3.5296, + "step": 1188352 + }, + { + "epoch": 0.01, + "learning_rate": 3.053626496449403e-05, + "loss": 3.534, + "step": 1188864 + }, + { + "epoch": 0.01, + "learning_rate": 3.052787901698351e-05, + "loss": 3.5293, + "step": 1189376 + }, + { + "epoch": 0.01, + "learning_rate": 3.051949306947299e-05, + "loss": 3.5262, + "step": 1189888 + }, + { + "epoch": 0.01, + "learning_rate": 3.0511107121962467e-05, + "loss": 3.537, + "step": 1190400 + }, + { + "epoch": 0.02, + "learning_rate": 3.0502737553255683e-05, + "loss": 3.5298, + "step": 1190912 + }, + { + "epoch": 0.02, + "learning_rate": 3.0494351605745163e-05, + "loss": 3.5331, + "step": 1191424 + }, + { + "epoch": 0.02, + "learning_rate": 3.0485965658234643e-05, + "loss": 3.5272, + "step": 1191936 + }, + { + "epoch": 0.02, + "learning_rate": 3.047757971072412e-05, + "loss": 3.539, + "step": 1192448 + }, + { + "epoch": 0.02, + "learning_rate": 3.0469210142017336e-05, + "loss": 3.5499, + "step": 1192960 + }, + { + "epoch": 0.02, + "learning_rate": 3.0460824194506815e-05, + "loss": 3.5455, + "step": 1193472 + }, + { + "epoch": 0.02, + "learning_rate": 3.045243824699629e-05, + "loss": 3.5175, + "step": 1193984 + }, + { + "epoch": 0.02, + "learning_rate": 3.044405229948577e-05, + "loss": 3.5337, + "step": 1194496 + }, + { + "epoch": 0.02, + "learning_rate": 3.0435682730778985e-05, + "loss": 3.5298, + "step": 1195008 + }, + { + "epoch": 0.02, + "learning_rate": 3.0427296783268468e-05, + "loss": 3.5393, + "step": 1195520 + }, + { + "epoch": 0.02, + "learning_rate": 3.041891083575794e-05, + "loss": 3.5372, + "step": 1196032 + }, + { + "epoch": 0.02, + "learning_rate": 3.041052488824742e-05, + "loss": 3.5298, + "step": 1196544 + }, + { + "epoch": 0.02, + "learning_rate": 3.0402155319540637e-05, + "loss": 3.5318, + "step": 1197056 + }, + { + "epoch": 0.02, + "learning_rate": 3.0393769372030117e-05, + "loss": 3.5375, + "step": 1197568 + }, + { + "epoch": 0.02, + "learning_rate": 3.0385383424519593e-05, + "loss": 3.5358, + "step": 1198080 + }, + { + "epoch": 0.02, + "learning_rate": 3.0376997477009073e-05, + "loss": 3.5301, + "step": 1198592 + }, + { + "epoch": 0.02, + "learning_rate": 3.036862790830229e-05, + "loss": 3.5287, + "step": 1199104 + }, + { + "epoch": 0.02, + "learning_rate": 3.0360241960791762e-05, + "loss": 3.5208, + "step": 1199616 + }, + { + "epoch": 0.02, + "learning_rate": 3.0351856013281242e-05, + "loss": 3.5328, + "step": 1200128 + }, + { + "epoch": 0.02, + "learning_rate": 3.0343470065770722e-05, + "loss": 3.523, + "step": 1200640 + }, + { + "epoch": 0.02, + "learning_rate": 3.0335100497063938e-05, + "loss": 3.5231, + "step": 1201152 + }, + { + "epoch": 0.02, + "learning_rate": 3.0326714549553415e-05, + "loss": 3.5273, + "step": 1201664 + }, + { + "epoch": 0.02, + "learning_rate": 3.0318328602042895e-05, + "loss": 3.5388, + "step": 1202176 + }, + { + "epoch": 0.02, + "learning_rate": 3.0309942654532375e-05, + "loss": 3.5293, + "step": 1202688 + }, + { + "epoch": 0.02, + "learning_rate": 3.030157308582559e-05, + "loss": 3.5292, + "step": 1203200 + }, + { + "epoch": 0.02, + "learning_rate": 3.0293187138315067e-05, + "loss": 3.5459, + "step": 1203712 + }, + { + "epoch": 0.02, + "learning_rate": 3.0284801190804547e-05, + "loss": 3.5402, + "step": 1204224 + }, + { + "epoch": 0.02, + "learning_rate": 3.0276415243294027e-05, + "loss": 3.5405, + "step": 1204736 + }, + { + "epoch": 0.02, + "learning_rate": 3.0268045674587236e-05, + "loss": 3.5299, + "step": 1205248 + }, + { + "epoch": 0.02, + "learning_rate": 3.0259659727076716e-05, + "loss": 3.5319, + "step": 1205760 + }, + { + "epoch": 0.02, + "learning_rate": 3.0251273779566196e-05, + "loss": 3.5287, + "step": 1206272 + }, + { + "epoch": 0.02, + "learning_rate": 3.0242887832055676e-05, + "loss": 3.5184, + "step": 1206784 + }, + { + "epoch": 0.02, + "learning_rate": 3.023451826334889e-05, + "loss": 3.5339, + "step": 1207296 + }, + { + "epoch": 0.02, + "learning_rate": 3.022613231583837e-05, + "loss": 3.5276, + "step": 1207808 + }, + { + "epoch": 0.02, + "learning_rate": 3.021774636832785e-05, + "loss": 3.5355, + "step": 1208320 + }, + { + "epoch": 0.02, + "learning_rate": 3.020936042081733e-05, + "loss": 3.5286, + "step": 1208832 + }, + { + "epoch": 0.02, + "learning_rate": 3.0200990852110537e-05, + "loss": 3.5364, + "step": 1209344 + }, + { + "epoch": 0.02, + "learning_rate": 3.019260490460002e-05, + "loss": 3.5296, + "step": 1209856 + }, + { + "epoch": 0.02, + "learning_rate": 3.01842189570895e-05, + "loss": 3.5276, + "step": 1210368 + }, + { + "epoch": 0.02, + "learning_rate": 3.017583300957898e-05, + "loss": 3.5345, + "step": 1210880 + }, + { + "epoch": 0.02, + "learning_rate": 3.016746344087219e-05, + "loss": 3.532, + "step": 1211392 + }, + { + "epoch": 0.02, + "learning_rate": 3.015907749336167e-05, + "loss": 3.5427, + "step": 1211904 + }, + { + "epoch": 0.02, + "learning_rate": 3.015069154585115e-05, + "loss": 3.5316, + "step": 1212416 + }, + { + "epoch": 0.02, + "learning_rate": 3.014230559834063e-05, + "loss": 3.537, + "step": 1212928 + }, + { + "epoch": 0.02, + "learning_rate": 3.0133936029633842e-05, + "loss": 3.5343, + "step": 1213440 + }, + { + "epoch": 0.02, + "learning_rate": 3.0125550082123322e-05, + "loss": 3.5338, + "step": 1213952 + }, + { + "epoch": 0.02, + "learning_rate": 3.0117164134612802e-05, + "loss": 3.5334, + "step": 1214464 + }, + { + "epoch": 0.02, + "learning_rate": 3.0108778187102282e-05, + "loss": 3.5306, + "step": 1214976 + }, + { + "epoch": 0.02, + "learning_rate": 3.010040861839549e-05, + "loss": 3.5333, + "step": 1215488 + }, + { + "epoch": 0.02, + "learning_rate": 3.0092022670884974e-05, + "loss": 3.5403, + "step": 1216000 + }, + { + "epoch": 0.02, + "learning_rate": 3.0083636723374454e-05, + "loss": 3.5295, + "step": 1216512 + }, + { + "epoch": 0.02, + "learning_rate": 3.0075250775863934e-05, + "loss": 3.5282, + "step": 1217024 + }, + { + "epoch": 0.02, + "learning_rate": 3.0066881207157143e-05, + "loss": 3.5349, + "step": 1217536 + }, + { + "epoch": 0.02, + "learning_rate": 3.0058495259646623e-05, + "loss": 3.5304, + "step": 1218048 + }, + { + "epoch": 0.02, + "learning_rate": 3.0050109312136103e-05, + "loss": 3.5282, + "step": 1218560 + }, + { + "epoch": 0.02, + "learning_rate": 3.0041723364625583e-05, + "loss": 3.5386, + "step": 1219072 + }, + { + "epoch": 0.02, + "learning_rate": 3.0033353795918796e-05, + "loss": 3.5281, + "step": 1219584 + }, + { + "epoch": 0.02, + "learning_rate": 3.0024967848408276e-05, + "loss": 3.541, + "step": 1220096 + }, + { + "epoch": 0.02, + "learning_rate": 3.0016581900897756e-05, + "loss": 3.5289, + "step": 1220608 + }, + { + "epoch": 0.03, + "eval_loss": 3.8382747173309326, + "eval_runtime": 303.9381, + "eval_samples_per_second": 1255.489, + "eval_steps_per_second": 39.235, + "step": 1221109 + }, + { + "epoch": 1.0, + "learning_rate": 3.0008195953387236e-05, + "loss": 3.5297, + "step": 1221120 + }, + { + "epoch": 1.0, + "learning_rate": 2.9999826384680445e-05, + "loss": 3.5242, + "step": 1221632 + }, + { + "epoch": 1.0, + "learning_rate": 2.9991440437169928e-05, + "loss": 3.5213, + "step": 1222144 + }, + { + "epoch": 1.0, + "learning_rate": 2.9983054489659408e-05, + "loss": 3.5385, + "step": 1222656 + }, + { + "epoch": 1.0, + "learning_rate": 2.9974668542148888e-05, + "loss": 3.5347, + "step": 1223168 + }, + { + "epoch": 1.0, + "learning_rate": 2.9966298973442097e-05, + "loss": 3.5346, + "step": 1223680 + }, + { + "epoch": 1.0, + "learning_rate": 2.9957913025931577e-05, + "loss": 3.5259, + "step": 1224192 + }, + { + "epoch": 1.0, + "learning_rate": 2.9949527078421057e-05, + "loss": 3.5282, + "step": 1224704 + }, + { + "epoch": 1.0, + "learning_rate": 2.9941141130910537e-05, + "loss": 3.516, + "step": 1225216 + }, + { + "epoch": 1.0, + "learning_rate": 2.993277156220375e-05, + "loss": 3.5334, + "step": 1225728 + }, + { + "epoch": 1.0, + "learning_rate": 2.992438561469323e-05, + "loss": 3.5277, + "step": 1226240 + }, + { + "epoch": 1.0, + "learning_rate": 2.991599966718271e-05, + "loss": 3.5418, + "step": 1226752 + }, + { + "epoch": 1.0, + "learning_rate": 2.990763009847592e-05, + "loss": 3.5384, + "step": 1227264 + }, + { + "epoch": 1.0, + "learning_rate": 2.98992441509654e-05, + "loss": 3.5084, + "step": 1227776 + }, + { + "epoch": 1.0, + "learning_rate": 2.9890858203454882e-05, + "loss": 3.5223, + "step": 1228288 + }, + { + "epoch": 1.0, + "learning_rate": 2.9882472255944362e-05, + "loss": 3.5196, + "step": 1228800 + }, + { + "epoch": 1.0, + "learning_rate": 2.987408630843384e-05, + "loss": 3.52, + "step": 1229312 + }, + { + "epoch": 1.0, + "learning_rate": 2.986570036092332e-05, + "loss": 3.5258, + "step": 1229824 + }, + { + "epoch": 1.0, + "learning_rate": 2.98573144134128e-05, + "loss": 3.5281, + "step": 1230336 + }, + { + "epoch": 1.0, + "learning_rate": 2.984892846590228e-05, + "loss": 3.5194, + "step": 1230848 + }, + { + "epoch": 1.0, + "learning_rate": 2.984055889719549e-05, + "loss": 3.5438, + "step": 1231360 + }, + { + "epoch": 1.0, + "learning_rate": 2.983217294968497e-05, + "loss": 3.5329, + "step": 1231872 + }, + { + "epoch": 1.0, + "learning_rate": 2.9823787002174454e-05, + "loss": 3.5255, + "step": 1232384 + }, + { + "epoch": 1.0, + "learning_rate": 2.9815401054663934e-05, + "loss": 3.5203, + "step": 1232896 + }, + { + "epoch": 1.0, + "learning_rate": 2.9807031485957143e-05, + "loss": 3.5405, + "step": 1233408 + }, + { + "epoch": 1.0, + "learning_rate": 2.9798645538446623e-05, + "loss": 3.5258, + "step": 1233920 + }, + { + "epoch": 1.0, + "learning_rate": 2.9790259590936103e-05, + "loss": 3.5193, + "step": 1234432 + }, + { + "epoch": 1.0, + "learning_rate": 2.9781873643425583e-05, + "loss": 3.5277, + "step": 1234944 + }, + { + "epoch": 1.0, + "learning_rate": 2.9773504074718795e-05, + "loss": 3.518, + "step": 1235456 + }, + { + "epoch": 1.0, + "learning_rate": 2.9765118127208275e-05, + "loss": 3.524, + "step": 1235968 + }, + { + "epoch": 1.01, + "learning_rate": 2.9756732179697755e-05, + "loss": 3.5253, + "step": 1236480 + }, + { + "epoch": 1.01, + "learning_rate": 2.9748346232187235e-05, + "loss": 3.5237, + "step": 1236992 + }, + { + "epoch": 1.01, + "learning_rate": 2.9739960284676715e-05, + "loss": 3.5288, + "step": 1237504 + }, + { + "epoch": 1.01, + "learning_rate": 2.9731590715969924e-05, + "loss": 3.53, + "step": 1238016 + }, + { + "epoch": 1.01, + "learning_rate": 2.9723204768459408e-05, + "loss": 3.5332, + "step": 1238528 + }, + { + "epoch": 1.01, + "learning_rate": 2.9714818820948888e-05, + "loss": 3.5257, + "step": 1239040 + }, + { + "epoch": 1.01, + "learning_rate": 2.9706449252242097e-05, + "loss": 3.5329, + "step": 1239552 + }, + { + "epoch": 1.01, + "learning_rate": 2.9698063304731577e-05, + "loss": 3.518, + "step": 1240064 + }, + { + "epoch": 1.01, + "learning_rate": 2.9689677357221057e-05, + "loss": 3.5234, + "step": 1240576 + }, + { + "epoch": 1.01, + "learning_rate": 2.9681291409710537e-05, + "loss": 3.5168, + "step": 1241088 + }, + { + "epoch": 1.01, + "learning_rate": 2.9672905462200016e-05, + "loss": 3.521, + "step": 1241600 + }, + { + "epoch": 1.01, + "learning_rate": 2.966453589349323e-05, + "loss": 3.5173, + "step": 1242112 + }, + { + "epoch": 1.01, + "learning_rate": 2.965614994598271e-05, + "loss": 3.5292, + "step": 1242624 + }, + { + "epoch": 1.01, + "learning_rate": 2.964776399847219e-05, + "loss": 3.5217, + "step": 1243136 + }, + { + "epoch": 1.01, + "learning_rate": 2.963937805096167e-05, + "loss": 3.5283, + "step": 1243648 + }, + { + "epoch": 1.01, + "learning_rate": 2.9631008482254878e-05, + "loss": 3.527, + "step": 1244160 + }, + { + "epoch": 1.01, + "learning_rate": 2.962262253474436e-05, + "loss": 3.5305, + "step": 1244672 + }, + { + "epoch": 1.01, + "learning_rate": 2.961423658723384e-05, + "loss": 3.5212, + "step": 1245184 + }, + { + "epoch": 1.01, + "learning_rate": 2.9605850639723314e-05, + "loss": 3.5073, + "step": 1245696 + }, + { + "epoch": 1.01, + "learning_rate": 2.959748107101653e-05, + "loss": 3.5234, + "step": 1246208 + }, + { + "epoch": 1.01, + "learning_rate": 2.958909512350601e-05, + "loss": 3.5333, + "step": 1246720 + }, + { + "epoch": 1.01, + "learning_rate": 2.958070917599549e-05, + "loss": 3.5247, + "step": 1247232 + }, + { + "epoch": 1.01, + "learning_rate": 2.9572323228484967e-05, + "loss": 3.5186, + "step": 1247744 + }, + { + "epoch": 1.01, + "learning_rate": 2.9563953659778183e-05, + "loss": 3.5184, + "step": 1248256 + }, + { + "epoch": 1.01, + "learning_rate": 2.9555567712267663e-05, + "loss": 3.5113, + "step": 1248768 + }, + { + "epoch": 1.01, + "learning_rate": 2.9547181764757143e-05, + "loss": 3.5075, + "step": 1249280 + }, + { + "epoch": 1.01, + "learning_rate": 2.9538795817246616e-05, + "loss": 3.5277, + "step": 1249792 + }, + { + "epoch": 1.01, + "learning_rate": 2.953042624853983e-05, + "loss": 3.5111, + "step": 1250304 + }, + { + "epoch": 1.01, + "learning_rate": 2.9522040301029315e-05, + "loss": 3.5271, + "step": 1250816 + }, + { + "epoch": 1.01, + "learning_rate": 2.9513654353518788e-05, + "loss": 3.5242, + "step": 1251328 + }, + { + "epoch": 1.01, + "learning_rate": 2.9505268406008268e-05, + "loss": 3.5081, + "step": 1251840 + }, + { + "epoch": 1.01, + "learning_rate": 2.9496898837301484e-05, + "loss": 3.5338, + "step": 1252352 + }, + { + "epoch": 1.01, + "learning_rate": 2.9488512889790964e-05, + "loss": 3.5131, + "step": 1252864 + }, + { + "epoch": 1.01, + "learning_rate": 2.948012694228044e-05, + "loss": 3.5164, + "step": 1253376 + }, + { + "epoch": 1.01, + "learning_rate": 2.947174099476992e-05, + "loss": 3.5092, + "step": 1253888 + }, + { + "epoch": 1.01, + "learning_rate": 2.9463371426063136e-05, + "loss": 3.5243, + "step": 1254400 + }, + { + "epoch": 1.01, + "learning_rate": 2.9454985478552616e-05, + "loss": 3.5122, + "step": 1254912 + }, + { + "epoch": 1.01, + "learning_rate": 2.944659953104209e-05, + "loss": 3.5179, + "step": 1255424 + }, + { + "epoch": 1.01, + "learning_rate": 2.943821358353157e-05, + "loss": 3.5039, + "step": 1255936 + }, + { + "epoch": 1.01, + "learning_rate": 2.9429844014824785e-05, + "loss": 3.5112, + "step": 1256448 + }, + { + "epoch": 1.01, + "learning_rate": 2.9421458067314262e-05, + "loss": 3.5235, + "step": 1256960 + }, + { + "epoch": 1.01, + "learning_rate": 2.9413072119803742e-05, + "loss": 3.5283, + "step": 1257472 + }, + { + "epoch": 1.01, + "learning_rate": 2.9404686172293222e-05, + "loss": 3.5219, + "step": 1257984 + }, + { + "epoch": 1.01, + "learning_rate": 2.9396316603586438e-05, + "loss": 3.5224, + "step": 1258496 + }, + { + "epoch": 1.01, + "learning_rate": 2.9387930656075914e-05, + "loss": 3.5314, + "step": 1259008 + }, + { + "epoch": 1.01, + "learning_rate": 2.9379544708565394e-05, + "loss": 3.5183, + "step": 1259520 + }, + { + "epoch": 1.01, + "learning_rate": 2.9371158761054874e-05, + "loss": 3.5347, + "step": 1260032 + }, + { + "epoch": 1.01, + "learning_rate": 2.936278919234809e-05, + "loss": 3.5114, + "step": 1260544 + }, + { + "epoch": 1.01, + "learning_rate": 2.9354403244837563e-05, + "loss": 3.5156, + "step": 1261056 + }, + { + "epoch": 1.01, + "learning_rate": 2.9346017297327043e-05, + "loss": 3.5205, + "step": 1261568 + }, + { + "epoch": 1.01, + "learning_rate": 2.9337631349816523e-05, + "loss": 3.5276, + "step": 1262080 + }, + { + "epoch": 1.01, + "learning_rate": 2.9329261781109736e-05, + "loss": 3.522, + "step": 1262592 + }, + { + "epoch": 1.01, + "learning_rate": 2.9320875833599215e-05, + "loss": 3.5287, + "step": 1263104 + }, + { + "epoch": 1.01, + "learning_rate": 2.9312489886088695e-05, + "loss": 3.514, + "step": 1263616 + }, + { + "epoch": 1.01, + "learning_rate": 2.9304103938578175e-05, + "loss": 3.4972, + "step": 1264128 + }, + { + "epoch": 1.01, + "learning_rate": 2.9295734369871385e-05, + "loss": 3.5155, + "step": 1264640 + }, + { + "epoch": 1.01, + "learning_rate": 2.9287348422360868e-05, + "loss": 3.52, + "step": 1265152 + }, + { + "epoch": 1.01, + "learning_rate": 2.9278962474850348e-05, + "loss": 3.5145, + "step": 1265664 + }, + { + "epoch": 1.01, + "learning_rate": 2.9270576527339828e-05, + "loss": 3.5126, + "step": 1266176 + }, + { + "epoch": 1.01, + "learning_rate": 2.9262206958633037e-05, + "loss": 3.5238, + "step": 1266688 + }, + { + "epoch": 1.02, + "learning_rate": 2.9253821011122517e-05, + "loss": 3.514, + "step": 1267200 + }, + { + "epoch": 1.02, + "learning_rate": 2.9245435063611997e-05, + "loss": 3.5194, + "step": 1267712 + }, + { + "epoch": 1.02, + "learning_rate": 2.9237049116101477e-05, + "loss": 3.5135, + "step": 1268224 + }, + { + "epoch": 1.02, + "learning_rate": 2.922867954739469e-05, + "loss": 3.5241, + "step": 1268736 + }, + { + "epoch": 1.02, + "learning_rate": 2.922029359988417e-05, + "loss": 3.5347, + "step": 1269248 + }, + { + "epoch": 1.02, + "learning_rate": 2.921190765237365e-05, + "loss": 3.5315, + "step": 1269760 + }, + { + "epoch": 1.02, + "learning_rate": 2.920352170486313e-05, + "loss": 3.5056, + "step": 1270272 + }, + { + "epoch": 1.02, + "learning_rate": 2.9195152136156338e-05, + "loss": 3.5169, + "step": 1270784 + }, + { + "epoch": 1.02, + "learning_rate": 2.918676618864582e-05, + "loss": 3.5194, + "step": 1271296 + }, + { + "epoch": 1.02, + "learning_rate": 2.91783802411353e-05, + "loss": 3.5218, + "step": 1271808 + }, + { + "epoch": 1.02, + "learning_rate": 2.916999429362478e-05, + "loss": 3.5235, + "step": 1272320 + }, + { + "epoch": 1.02, + "learning_rate": 2.916162472491799e-05, + "loss": 3.5168, + "step": 1272832 + }, + { + "epoch": 1.02, + "learning_rate": 2.915323877740747e-05, + "loss": 3.5144, + "step": 1273344 + }, + { + "epoch": 1.02, + "learning_rate": 2.914485282989695e-05, + "loss": 3.5236, + "step": 1273856 + }, + { + "epoch": 1.02, + "learning_rate": 2.913646688238643e-05, + "loss": 3.5237, + "step": 1274368 + }, + { + "epoch": 1.02, + "learning_rate": 2.9128097313679643e-05, + "loss": 3.5112, + "step": 1274880 + }, + { + "epoch": 1.02, + "learning_rate": 2.9119711366169123e-05, + "loss": 3.5198, + "step": 1275392 + }, + { + "epoch": 1.02, + "learning_rate": 2.9111325418658603e-05, + "loss": 3.5096, + "step": 1275904 + }, + { + "epoch": 1.02, + "learning_rate": 2.9102939471148083e-05, + "loss": 3.5145, + "step": 1276416 + }, + { + "epoch": 1.02, + "learning_rate": 2.9094569902441292e-05, + "loss": 3.511, + "step": 1276928 + }, + { + "epoch": 1.02, + "learning_rate": 2.9086183954930775e-05, + "loss": 3.509, + "step": 1277440 + }, + { + "epoch": 1.02, + "learning_rate": 2.9077798007420255e-05, + "loss": 3.5075, + "step": 1277952 + }, + { + "epoch": 1.02, + "learning_rate": 2.9069412059909735e-05, + "loss": 3.5235, + "step": 1278464 + }, + { + "epoch": 1.02, + "learning_rate": 2.9061042491202944e-05, + "loss": 3.5179, + "step": 1278976 + }, + { + "epoch": 1.02, + "learning_rate": 2.9052656543692424e-05, + "loss": 3.5151, + "step": 1279488 + }, + { + "epoch": 1.02, + "learning_rate": 2.9044270596181904e-05, + "loss": 3.53, + "step": 1280000 + }, + { + "epoch": 1.02, + "learning_rate": 2.9035884648671384e-05, + "loss": 3.5285, + "step": 1280512 + }, + { + "epoch": 1.02, + "learning_rate": 2.9027515079964597e-05, + "loss": 3.5248, + "step": 1281024 + }, + { + "epoch": 1.02, + "learning_rate": 2.9019129132454076e-05, + "loss": 3.5206, + "step": 1281536 + }, + { + "epoch": 1.02, + "learning_rate": 2.9010743184943556e-05, + "loss": 3.5154, + "step": 1282048 + }, + { + "epoch": 1.02, + "learning_rate": 2.9002357237433036e-05, + "loss": 3.5132, + "step": 1282560 + }, + { + "epoch": 1.02, + "learning_rate": 2.8993987668726246e-05, + "loss": 3.5091, + "step": 1283072 + }, + { + "epoch": 1.02, + "learning_rate": 2.8985601721215725e-05, + "loss": 3.5147, + "step": 1283584 + }, + { + "epoch": 1.02, + "learning_rate": 2.897721577370521e-05, + "loss": 3.5151, + "step": 1284096 + }, + { + "epoch": 1.02, + "learning_rate": 2.896882982619469e-05, + "loss": 3.5195, + "step": 1284608 + }, + { + "epoch": 1.02, + "learning_rate": 2.8960460257487898e-05, + "loss": 3.5138, + "step": 1285120 + }, + { + "epoch": 1.02, + "learning_rate": 2.8952074309977378e-05, + "loss": 3.5203, + "step": 1285632 + }, + { + "epoch": 1.02, + "learning_rate": 2.8943688362466858e-05, + "loss": 3.5211, + "step": 1286144 + }, + { + "epoch": 1.02, + "learning_rate": 2.8935302414956338e-05, + "loss": 3.5142, + "step": 1286656 + }, + { + "epoch": 1.02, + "learning_rate": 2.892693284624955e-05, + "loss": 3.5118, + "step": 1287168 + }, + { + "epoch": 1.02, + "learning_rate": 2.891854689873903e-05, + "loss": 3.5269, + "step": 1287680 + }, + { + "epoch": 1.02, + "learning_rate": 2.891016095122851e-05, + "loss": 3.5247, + "step": 1288192 + }, + { + "epoch": 1.02, + "learning_rate": 2.890177500371799e-05, + "loss": 3.5178, + "step": 1288704 + }, + { + "epoch": 1.02, + "learning_rate": 2.88934054350112e-05, + "loss": 3.5181, + "step": 1289216 + }, + { + "epoch": 1.02, + "learning_rate": 2.888501948750068e-05, + "loss": 3.5231, + "step": 1289728 + }, + { + "epoch": 1.02, + "learning_rate": 2.8876633539990162e-05, + "loss": 3.5216, + "step": 1290240 + }, + { + "epoch": 1.02, + "learning_rate": 2.8868247592479642e-05, + "loss": 3.5201, + "step": 1290752 + }, + { + "epoch": 1.02, + "learning_rate": 2.885987802377285e-05, + "loss": 3.514, + "step": 1291264 + }, + { + "epoch": 1.02, + "learning_rate": 2.885149207626233e-05, + "loss": 3.521, + "step": 1291776 + }, + { + "epoch": 1.02, + "learning_rate": 2.884310612875181e-05, + "loss": 3.5263, + "step": 1292288 + }, + { + "epoch": 1.02, + "learning_rate": 2.883472018124129e-05, + "loss": 3.5151, + "step": 1292800 + }, + { + "epoch": 1.02, + "learning_rate": 2.8826350612534504e-05, + "loss": 3.514, + "step": 1293312 + }, + { + "epoch": 1.02, + "learning_rate": 2.8817964665023984e-05, + "loss": 3.5196, + "step": 1293824 + }, + { + "epoch": 1.02, + "learning_rate": 2.8809578717513464e-05, + "loss": 3.5203, + "step": 1294336 + }, + { + "epoch": 1.02, + "learning_rate": 2.8801192770002944e-05, + "loss": 3.5081, + "step": 1294848 + }, + { + "epoch": 1.02, + "learning_rate": 2.8792823201296153e-05, + "loss": 3.5269, + "step": 1295360 + }, + { + "epoch": 1.02, + "learning_rate": 2.8784437253785633e-05, + "loss": 3.516, + "step": 1295872 + }, + { + "epoch": 1.02, + "learning_rate": 2.8776051306275116e-05, + "loss": 3.5243, + "step": 1296384 + }, + { + "epoch": 1.02, + "learning_rate": 2.8767665358764596e-05, + "loss": 3.5183, + "step": 1296896 + }, + { + "epoch": 1.02, + "learning_rate": 2.8759295790057805e-05, + "loss": 3.5099, + "step": 1297408 + }, + { + "epoch": 1.03, + "eval_loss": 3.8403775691986084, + "eval_runtime": 303.0962, + "eval_samples_per_second": 1258.976, + "eval_steps_per_second": 39.344, + "step": 1297429 + }, + { + "epoch": 0.0, + "learning_rate": 2.8750909842547285e-05, + "loss": 3.51, + "step": 1297920 + }, + { + "epoch": 0.0, + "learning_rate": 2.8742523895036765e-05, + "loss": 3.5082, + "step": 1298432 + }, + { + "epoch": 0.0, + "learning_rate": 2.8734137947526245e-05, + "loss": 3.5261, + "step": 1298944 + }, + { + "epoch": 0.0, + "learning_rate": 2.8725768378819458e-05, + "loss": 3.5144, + "step": 1299456 + }, + { + "epoch": 0.0, + "learning_rate": 2.8717382431308937e-05, + "loss": 3.5224, + "step": 1299968 + }, + { + "epoch": 0.0, + "learning_rate": 2.8708996483798417e-05, + "loss": 3.5153, + "step": 1300480 + }, + { + "epoch": 0.0, + "learning_rate": 2.8700610536287897e-05, + "loss": 3.5117, + "step": 1300992 + }, + { + "epoch": 0.0, + "learning_rate": 2.8692240967581107e-05, + "loss": 3.5031, + "step": 1301504 + }, + { + "epoch": 0.0, + "learning_rate": 2.8683855020070586e-05, + "loss": 3.5209, + "step": 1302016 + }, + { + "epoch": 0.0, + "learning_rate": 2.867546907256007e-05, + "loss": 3.5105, + "step": 1302528 + }, + { + "epoch": 0.0, + "learning_rate": 2.866708312504955e-05, + "loss": 3.5308, + "step": 1303040 + }, + { + "epoch": 0.0, + "learning_rate": 2.865869717753903e-05, + "loss": 3.5193, + "step": 1303552 + }, + { + "epoch": 0.0, + "learning_rate": 2.8650343987635968e-05, + "loss": 3.504, + "step": 1304064 + }, + { + "epoch": 0.0, + "learning_rate": 2.8641958040125448e-05, + "loss": 3.5055, + "step": 1304576 + }, + { + "epoch": 0.0, + "learning_rate": 2.863357209261493e-05, + "loss": 3.5094, + "step": 1305088 + }, + { + "epoch": 0.0, + "learning_rate": 2.862518614510441e-05, + "loss": 3.5021, + "step": 1305600 + }, + { + "epoch": 0.0, + "learning_rate": 2.861680019759389e-05, + "loss": 3.5137, + "step": 1306112 + }, + { + "epoch": 0.0, + "learning_rate": 2.860841425008337e-05, + "loss": 3.5157, + "step": 1306624 + }, + { + "epoch": 0.0, + "learning_rate": 2.860002830257285e-05, + "loss": 3.5041, + "step": 1307136 + }, + { + "epoch": 0.0, + "learning_rate": 2.859165873386606e-05, + "loss": 3.5339, + "step": 1307648 + }, + { + "epoch": 0.0, + "learning_rate": 2.858327278635554e-05, + "loss": 3.5135, + "step": 1308160 + }, + { + "epoch": 0.0, + "learning_rate": 2.8574886838845023e-05, + "loss": 3.5164, + "step": 1308672 + }, + { + "epoch": 0.0, + "learning_rate": 2.8566500891334503e-05, + "loss": 3.5073, + "step": 1309184 + }, + { + "epoch": 0.0, + "learning_rate": 2.8558131322627713e-05, + "loss": 3.5266, + "step": 1309696 + }, + { + "epoch": 0.0, + "learning_rate": 2.8549745375117192e-05, + "loss": 3.5099, + "step": 1310208 + }, + { + "epoch": 0.0, + "learning_rate": 2.8541359427606672e-05, + "loss": 3.5106, + "step": 1310720 + }, + { + "epoch": 0.0, + "learning_rate": 2.8532973480096152e-05, + "loss": 3.5091, + "step": 1311232 + }, + { + "epoch": 0.0, + "learning_rate": 2.8524587532585632e-05, + "loss": 3.5072, + "step": 1311744 + }, + { + "epoch": 0.0, + "learning_rate": 2.8516217963878845e-05, + "loss": 3.505, + "step": 1312256 + }, + { + "epoch": 0.01, + "learning_rate": 2.8507832016368325e-05, + "loss": 3.5124, + "step": 1312768 + }, + { + "epoch": 0.01, + "learning_rate": 2.8499446068857805e-05, + "loss": 3.5129, + "step": 1313280 + }, + { + "epoch": 0.01, + "learning_rate": 2.8491060121347285e-05, + "loss": 3.5114, + "step": 1313792 + }, + { + "epoch": 0.01, + "learning_rate": 2.8482690552640494e-05, + "loss": 3.5147, + "step": 1314304 + }, + { + "epoch": 0.01, + "learning_rate": 2.8474304605129977e-05, + "loss": 3.5199, + "step": 1314816 + }, + { + "epoch": 0.01, + "learning_rate": 2.8465918657619457e-05, + "loss": 3.5114, + "step": 1315328 + }, + { + "epoch": 0.01, + "learning_rate": 2.8457532710108937e-05, + "loss": 3.5174, + "step": 1315840 + }, + { + "epoch": 0.01, + "learning_rate": 2.8449163141402146e-05, + "loss": 3.5046, + "step": 1316352 + }, + { + "epoch": 0.01, + "learning_rate": 2.8440777193891626e-05, + "loss": 3.5109, + "step": 1316864 + }, + { + "epoch": 0.01, + "learning_rate": 2.8432391246381106e-05, + "loss": 3.5013, + "step": 1317376 + }, + { + "epoch": 0.01, + "learning_rate": 2.8424005298870583e-05, + "loss": 3.5112, + "step": 1317888 + }, + { + "epoch": 0.01, + "learning_rate": 2.84156357301638e-05, + "loss": 3.5043, + "step": 1318400 + }, + { + "epoch": 0.01, + "learning_rate": 2.840724978265328e-05, + "loss": 3.5158, + "step": 1318912 + }, + { + "epoch": 0.01, + "learning_rate": 2.839886383514276e-05, + "loss": 3.5077, + "step": 1319424 + }, + { + "epoch": 0.01, + "learning_rate": 2.839047788763223e-05, + "loss": 3.5152, + "step": 1319936 + }, + { + "epoch": 0.01, + "learning_rate": 2.8382108318925447e-05, + "loss": 3.512, + "step": 1320448 + }, + { + "epoch": 0.01, + "learning_rate": 2.837372237141493e-05, + "loss": 3.5161, + "step": 1320960 + }, + { + "epoch": 0.01, + "learning_rate": 2.836533642390441e-05, + "loss": 3.5096, + "step": 1321472 + }, + { + "epoch": 0.01, + "learning_rate": 2.8356950476393884e-05, + "loss": 3.4991, + "step": 1321984 + }, + { + "epoch": 0.01, + "learning_rate": 2.83485809076871e-05, + "loss": 3.5042, + "step": 1322496 + }, + { + "epoch": 0.01, + "learning_rate": 2.834019496017658e-05, + "loss": 3.5212, + "step": 1323008 + }, + { + "epoch": 0.01, + "learning_rate": 2.8331809012666056e-05, + "loss": 3.5061, + "step": 1323520 + }, + { + "epoch": 0.01, + "learning_rate": 2.8323423065155536e-05, + "loss": 3.5068, + "step": 1324032 + }, + { + "epoch": 0.01, + "learning_rate": 2.8315037117645016e-05, + "loss": 3.5015, + "step": 1324544 + }, + { + "epoch": 0.01, + "learning_rate": 2.8306667548938232e-05, + "loss": 3.5036, + "step": 1325056 + }, + { + "epoch": 0.01, + "learning_rate": 2.8298281601427705e-05, + "loss": 3.4892, + "step": 1325568 + }, + { + "epoch": 0.01, + "learning_rate": 2.8289895653917185e-05, + "loss": 3.5184, + "step": 1326080 + }, + { + "epoch": 0.01, + "learning_rate": 2.828150970640667e-05, + "loss": 3.4954, + "step": 1326592 + }, + { + "epoch": 0.01, + "learning_rate": 2.8273140137699884e-05, + "loss": 3.5133, + "step": 1327104 + }, + { + "epoch": 0.01, + "learning_rate": 2.8264754190189358e-05, + "loss": 3.5108, + "step": 1327616 + }, + { + "epoch": 0.01, + "learning_rate": 2.8256368242678838e-05, + "loss": 3.4952, + "step": 1328128 + }, + { + "epoch": 0.01, + "learning_rate": 2.8247982295168318e-05, + "loss": 3.5158, + "step": 1328640 + }, + { + "epoch": 0.01, + "learning_rate": 2.823961272646153e-05, + "loss": 3.5024, + "step": 1329152 + }, + { + "epoch": 0.01, + "learning_rate": 2.823122677895101e-05, + "loss": 3.5059, + "step": 1329664 + }, + { + "epoch": 0.01, + "learning_rate": 2.822284083144049e-05, + "loss": 3.4924, + "step": 1330176 + }, + { + "epoch": 0.01, + "learning_rate": 2.821445488392997e-05, + "loss": 3.5106, + "step": 1330688 + }, + { + "epoch": 0.01, + "learning_rate": 2.820608531522318e-05, + "loss": 3.5005, + "step": 1331200 + }, + { + "epoch": 0.01, + "learning_rate": 2.819769936771266e-05, + "loss": 3.5068, + "step": 1331712 + }, + { + "epoch": 0.01, + "learning_rate": 2.818931342020214e-05, + "loss": 3.4885, + "step": 1332224 + }, + { + "epoch": 0.01, + "learning_rate": 2.8180943851495355e-05, + "loss": 3.4982, + "step": 1332736 + }, + { + "epoch": 0.01, + "learning_rate": 2.817255790398483e-05, + "loss": 3.5087, + "step": 1333248 + }, + { + "epoch": 0.01, + "learning_rate": 2.816417195647431e-05, + "loss": 3.5132, + "step": 1333760 + }, + { + "epoch": 0.01, + "learning_rate": 2.815578600896379e-05, + "loss": 3.5105, + "step": 1334272 + }, + { + "epoch": 0.01, + "learning_rate": 2.8147416440257e-05, + "loss": 3.5086, + "step": 1334784 + }, + { + "epoch": 0.01, + "learning_rate": 2.8139030492746484e-05, + "loss": 3.5154, + "step": 1335296 + }, + { + "epoch": 0.01, + "learning_rate": 2.8130644545235964e-05, + "loss": 3.5055, + "step": 1335808 + }, + { + "epoch": 0.01, + "learning_rate": 2.8122258597725444e-05, + "loss": 3.5175, + "step": 1336320 + }, + { + "epoch": 0.01, + "learning_rate": 2.8113889029018653e-05, + "loss": 3.5019, + "step": 1336832 + }, + { + "epoch": 0.01, + "learning_rate": 2.8105503081508133e-05, + "loss": 3.5027, + "step": 1337344 + }, + { + "epoch": 0.01, + "learning_rate": 2.8097117133997613e-05, + "loss": 3.5036, + "step": 1337856 + }, + { + "epoch": 0.01, + "learning_rate": 2.8088731186487093e-05, + "loss": 3.5145, + "step": 1338368 + }, + { + "epoch": 0.01, + "learning_rate": 2.8080361617780305e-05, + "loss": 3.5093, + "step": 1338880 + }, + { + "epoch": 0.01, + "learning_rate": 2.8071975670269785e-05, + "loss": 3.514, + "step": 1339392 + }, + { + "epoch": 0.01, + "learning_rate": 2.8063589722759265e-05, + "loss": 3.5065, + "step": 1339904 + }, + { + "epoch": 0.01, + "learning_rate": 2.8055203775248745e-05, + "loss": 3.4825, + "step": 1340416 + }, + { + "epoch": 0.01, + "learning_rate": 2.8046834206541954e-05, + "loss": 3.4985, + "step": 1340928 + }, + { + "epoch": 0.01, + "learning_rate": 2.8038448259031434e-05, + "loss": 3.5049, + "step": 1341440 + }, + { + "epoch": 0.01, + "learning_rate": 2.8030062311520917e-05, + "loss": 3.5012, + "step": 1341952 + }, + { + "epoch": 0.01, + "learning_rate": 2.8021676364010397e-05, + "loss": 3.4981, + "step": 1342464 + }, + { + "epoch": 0.01, + "learning_rate": 2.8013306795303606e-05, + "loss": 3.5102, + "step": 1342976 + }, + { + "epoch": 0.02, + "learning_rate": 2.8004920847793086e-05, + "loss": 3.4994, + "step": 1343488 + }, + { + "epoch": 0.02, + "learning_rate": 2.7996534900282566e-05, + "loss": 3.5028, + "step": 1344000 + }, + { + "epoch": 0.02, + "learning_rate": 2.7988148952772046e-05, + "loss": 3.5053, + "step": 1344512 + }, + { + "epoch": 0.02, + "learning_rate": 2.797977938406526e-05, + "loss": 3.5099, + "step": 1345024 + }, + { + "epoch": 0.02, + "learning_rate": 2.797139343655474e-05, + "loss": 3.5167, + "step": 1345536 + }, + { + "epoch": 0.02, + "learning_rate": 2.796300748904422e-05, + "loss": 3.5205, + "step": 1346048 + }, + { + "epoch": 0.02, + "learning_rate": 2.79546215415337e-05, + "loss": 3.4883, + "step": 1346560 + }, + { + "epoch": 0.02, + "learning_rate": 2.7946251972826908e-05, + "loss": 3.5074, + "step": 1347072 + }, + { + "epoch": 0.02, + "learning_rate": 2.7937866025316388e-05, + "loss": 3.5042, + "step": 1347584 + }, + { + "epoch": 0.02, + "learning_rate": 2.792948007780587e-05, + "loss": 3.5084, + "step": 1348096 + }, + { + "epoch": 0.02, + "learning_rate": 2.792109413029535e-05, + "loss": 3.5157, + "step": 1348608 + }, + { + "epoch": 0.02, + "learning_rate": 2.791272456158856e-05, + "loss": 3.4983, + "step": 1349120 + }, + { + "epoch": 0.02, + "learning_rate": 2.790433861407804e-05, + "loss": 3.5012, + "step": 1349632 + }, + { + "epoch": 0.02, + "learning_rate": 2.789595266656752e-05, + "loss": 3.5127, + "step": 1350144 + }, + { + "epoch": 0.02, + "learning_rate": 2.7887566719057e-05, + "loss": 3.5123, + "step": 1350656 + }, + { + "epoch": 0.02, + "learning_rate": 2.7879197150350212e-05, + "loss": 3.4957, + "step": 1351168 + }, + { + "epoch": 0.02, + "learning_rate": 2.7870811202839692e-05, + "loss": 3.5086, + "step": 1351680 + }, + { + "epoch": 0.02, + "learning_rate": 2.7862425255329172e-05, + "loss": 3.4983, + "step": 1352192 + }, + { + "epoch": 0.02, + "learning_rate": 2.7854039307818652e-05, + "loss": 3.4995, + "step": 1352704 + }, + { + "epoch": 0.02, + "learning_rate": 2.784566973911186e-05, + "loss": 3.4971, + "step": 1353216 + }, + { + "epoch": 0.02, + "learning_rate": 2.783728379160134e-05, + "loss": 3.4993, + "step": 1353728 + }, + { + "epoch": 0.02, + "learning_rate": 2.7828897844090825e-05, + "loss": 3.4963, + "step": 1354240 + }, + { + "epoch": 0.02, + "learning_rate": 2.7820511896580305e-05, + "loss": 3.5075, + "step": 1354752 + }, + { + "epoch": 0.02, + "learning_rate": 2.7812142327873514e-05, + "loss": 3.5034, + "step": 1355264 + }, + { + "epoch": 0.02, + "learning_rate": 2.7803756380362994e-05, + "loss": 3.5027, + "step": 1355776 + }, + { + "epoch": 0.02, + "learning_rate": 2.7795370432852474e-05, + "loss": 3.5185, + "step": 1356288 + }, + { + "epoch": 0.02, + "learning_rate": 2.7786984485341954e-05, + "loss": 3.5149, + "step": 1356800 + }, + { + "epoch": 0.02, + "learning_rate": 2.7778614916635166e-05, + "loss": 3.5059, + "step": 1357312 + }, + { + "epoch": 0.02, + "learning_rate": 2.7770228969124646e-05, + "loss": 3.5077, + "step": 1357824 + }, + { + "epoch": 0.02, + "learning_rate": 2.7761843021614126e-05, + "loss": 3.5033, + "step": 1358336 + }, + { + "epoch": 0.02, + "learning_rate": 2.7753457074103606e-05, + "loss": 3.4998, + "step": 1358848 + }, + { + "epoch": 0.02, + "learning_rate": 2.7745087505396815e-05, + "loss": 3.4932, + "step": 1359360 + }, + { + "epoch": 0.02, + "learning_rate": 2.7736701557886295e-05, + "loss": 3.5021, + "step": 1359872 + }, + { + "epoch": 0.02, + "learning_rate": 2.772831561037578e-05, + "loss": 3.5047, + "step": 1360384 + }, + { + "epoch": 0.02, + "learning_rate": 2.7719929662865258e-05, + "loss": 3.5057, + "step": 1360896 + }, + { + "epoch": 0.02, + "learning_rate": 2.7711560094158467e-05, + "loss": 3.5028, + "step": 1361408 + }, + { + "epoch": 0.02, + "learning_rate": 2.7703174146647947e-05, + "loss": 3.5034, + "step": 1361920 + }, + { + "epoch": 0.02, + "learning_rate": 2.7694788199137427e-05, + "loss": 3.5063, + "step": 1362432 + }, + { + "epoch": 0.02, + "learning_rate": 2.7686402251626907e-05, + "loss": 3.4993, + "step": 1362944 + }, + { + "epoch": 0.02, + "learning_rate": 2.767803268292012e-05, + "loss": 3.4983, + "step": 1363456 + }, + { + "epoch": 0.02, + "learning_rate": 2.76696467354096e-05, + "loss": 3.5131, + "step": 1363968 + }, + { + "epoch": 0.02, + "learning_rate": 2.766126078789908e-05, + "loss": 3.5122, + "step": 1364480 + }, + { + "epoch": 0.02, + "learning_rate": 2.765287484038856e-05, + "loss": 3.5046, + "step": 1364992 + }, + { + "epoch": 0.02, + "learning_rate": 2.764450527168177e-05, + "loss": 3.5021, + "step": 1365504 + }, + { + "epoch": 0.02, + "learning_rate": 2.763611932417125e-05, + "loss": 3.5074, + "step": 1366016 + }, + { + "epoch": 0.02, + "learning_rate": 2.7627733376660732e-05, + "loss": 3.5063, + "step": 1366528 + }, + { + "epoch": 0.02, + "learning_rate": 2.7619347429150212e-05, + "loss": 3.5128, + "step": 1367040 + }, + { + "epoch": 0.02, + "learning_rate": 2.761097786044342e-05, + "loss": 3.5024, + "step": 1367552 + }, + { + "epoch": 0.02, + "learning_rate": 2.76025919129329e-05, + "loss": 3.5081, + "step": 1368064 + }, + { + "epoch": 0.02, + "learning_rate": 2.759420596542238e-05, + "loss": 3.5059, + "step": 1368576 + }, + { + "epoch": 0.02, + "learning_rate": 2.758582001791186e-05, + "loss": 3.5051, + "step": 1369088 + }, + { + "epoch": 0.02, + "learning_rate": 2.7577450449205073e-05, + "loss": 3.5037, + "step": 1369600 + }, + { + "epoch": 0.02, + "learning_rate": 2.7569064501694553e-05, + "loss": 3.5063, + "step": 1370112 + }, + { + "epoch": 0.02, + "learning_rate": 2.7560678554184033e-05, + "loss": 3.5049, + "step": 1370624 + }, + { + "epoch": 0.02, + "learning_rate": 2.7552292606673513e-05, + "loss": 3.4948, + "step": 1371136 + }, + { + "epoch": 0.02, + "learning_rate": 2.7543923037966722e-05, + "loss": 3.5142, + "step": 1371648 + }, + { + "epoch": 0.02, + "learning_rate": 2.7535537090456202e-05, + "loss": 3.5047, + "step": 1372160 + }, + { + "epoch": 0.02, + "learning_rate": 2.7527151142945686e-05, + "loss": 3.5061, + "step": 1372672 + }, + { + "epoch": 0.02, + "learning_rate": 2.7518765195435166e-05, + "loss": 3.5062, + "step": 1373184 + }, + { + "epoch": 0.02, + "learning_rate": 2.7510395626728375e-05, + "loss": 3.4976, + "step": 1373696 + }, + { + "epoch": 0.03, + "eval_loss": 3.8414766788482666, + "eval_runtime": 315.2482, + "eval_samples_per_second": 1210.446, + "eval_steps_per_second": 37.827, + "step": 1373749 + }, + { + "epoch": 0.0, + "learning_rate": 2.7502009679217855e-05, + "loss": 3.4971, + "step": 1374208 + }, + { + "epoch": 0.0, + "learning_rate": 2.7493623731707335e-05, + "loss": 3.4956, + "step": 1374720 + }, + { + "epoch": 0.0, + "learning_rate": 2.7485237784196815e-05, + "loss": 3.5136, + "step": 1375232 + }, + { + "epoch": 0.0, + "learning_rate": 2.7476851836686295e-05, + "loss": 3.5001, + "step": 1375744 + }, + { + "epoch": 0.0, + "learning_rate": 2.7468482267979507e-05, + "loss": 3.513, + "step": 1376256 + }, + { + "epoch": 0.0, + "learning_rate": 2.7460096320468987e-05, + "loss": 3.4975, + "step": 1376768 + }, + { + "epoch": 0.0, + "learning_rate": 2.7451710372958467e-05, + "loss": 3.5022, + "step": 1377280 + }, + { + "epoch": 0.0, + "learning_rate": 2.7443340804251676e-05, + "loss": 3.4876, + "step": 1377792 + }, + { + "epoch": 0.0, + "learning_rate": 2.7434954856741156e-05, + "loss": 3.5069, + "step": 1378304 + }, + { + "epoch": 0.0, + "learning_rate": 2.742656890923064e-05, + "loss": 3.5022, + "step": 1378816 + }, + { + "epoch": 0.0, + "learning_rate": 2.741818296172012e-05, + "loss": 3.5138, + "step": 1379328 + }, + { + "epoch": 0.0, + "learning_rate": 2.740981339301333e-05, + "loss": 3.5055, + "step": 1379840 + }, + { + "epoch": 0.0, + "learning_rate": 2.740142744550281e-05, + "loss": 3.4889, + "step": 1380352 + }, + { + "epoch": 0.0, + "learning_rate": 2.7393041497992288e-05, + "loss": 3.4922, + "step": 1380864 + }, + { + "epoch": 0.0, + "learning_rate": 2.7384655550481768e-05, + "loss": 3.5, + "step": 1381376 + }, + { + "epoch": 0.0, + "learning_rate": 2.737628598177498e-05, + "loss": 3.4791, + "step": 1381888 + }, + { + "epoch": 0.0, + "learning_rate": 2.736790003426446e-05, + "loss": 3.5014, + "step": 1382400 + }, + { + "epoch": 0.0, + "learning_rate": 2.735951408675394e-05, + "loss": 3.5017, + "step": 1382912 + }, + { + "epoch": 0.0, + "learning_rate": 2.735112813924342e-05, + "loss": 3.4931, + "step": 1383424 + }, + { + "epoch": 0.0, + "learning_rate": 2.734275857053663e-05, + "loss": 3.5229, + "step": 1383936 + }, + { + "epoch": 0.0, + "learning_rate": 2.733437262302611e-05, + "loss": 3.4988, + "step": 1384448 + }, + { + "epoch": 0.0, + "learning_rate": 2.7325986675515593e-05, + "loss": 3.5049, + "step": 1384960 + }, + { + "epoch": 0.0, + "learning_rate": 2.7317600728005073e-05, + "loss": 3.495, + "step": 1385472 + }, + { + "epoch": 0.0, + "learning_rate": 2.7309231159298282e-05, + "loss": 3.5151, + "step": 1385984 + }, + { + "epoch": 0.0, + "learning_rate": 2.7300845211787762e-05, + "loss": 3.4891, + "step": 1386496 + }, + { + "epoch": 0.0, + "learning_rate": 2.7292459264277242e-05, + "loss": 3.5, + "step": 1387008 + }, + { + "epoch": 0.0, + "learning_rate": 2.7284073316766722e-05, + "loss": 3.4914, + "step": 1387520 + }, + { + "epoch": 0.0, + "learning_rate": 2.7275703748059934e-05, + "loss": 3.4978, + "step": 1388032 + }, + { + "epoch": 0.0, + "learning_rate": 2.7267317800549414e-05, + "loss": 3.5, + "step": 1388544 + }, + { + "epoch": 0.01, + "learning_rate": 2.7258931853038894e-05, + "loss": 3.496, + "step": 1389056 + }, + { + "epoch": 0.01, + "learning_rate": 2.7250545905528374e-05, + "loss": 3.4992, + "step": 1389568 + }, + { + "epoch": 0.01, + "learning_rate": 2.7242159958017847e-05, + "loss": 3.5019, + "step": 1390080 + }, + { + "epoch": 0.01, + "learning_rate": 2.7233790389311063e-05, + "loss": 3.4962, + "step": 1390592 + }, + { + "epoch": 0.01, + "learning_rate": 2.7225404441800543e-05, + "loss": 3.5117, + "step": 1391104 + }, + { + "epoch": 0.01, + "learning_rate": 2.7217018494290027e-05, + "loss": 3.4961, + "step": 1391616 + }, + { + "epoch": 0.01, + "learning_rate": 2.72086325467795e-05, + "loss": 3.5032, + "step": 1392128 + }, + { + "epoch": 0.01, + "learning_rate": 2.7200262978072716e-05, + "loss": 3.4932, + "step": 1392640 + }, + { + "epoch": 0.01, + "learning_rate": 2.7191877030562196e-05, + "loss": 3.4973, + "step": 1393152 + }, + { + "epoch": 0.01, + "learning_rate": 2.7183491083051676e-05, + "loss": 3.4877, + "step": 1393664 + }, + { + "epoch": 0.01, + "learning_rate": 2.7175105135541152e-05, + "loss": 3.4962, + "step": 1394176 + }, + { + "epoch": 0.01, + "learning_rate": 2.7166735566834368e-05, + "loss": 3.4916, + "step": 1394688 + }, + { + "epoch": 0.01, + "learning_rate": 2.7158349619323848e-05, + "loss": 3.5066, + "step": 1395200 + }, + { + "epoch": 0.01, + "learning_rate": 2.714996367181332e-05, + "loss": 3.4928, + "step": 1395712 + }, + { + "epoch": 0.01, + "learning_rate": 2.71415777243028e-05, + "loss": 3.5007, + "step": 1396224 + }, + { + "epoch": 0.01, + "learning_rate": 2.7133208155596017e-05, + "loss": 3.5046, + "step": 1396736 + }, + { + "epoch": 0.01, + "learning_rate": 2.7124822208085497e-05, + "loss": 3.5003, + "step": 1397248 + }, + { + "epoch": 0.01, + "learning_rate": 2.7116436260574974e-05, + "loss": 3.4959, + "step": 1397760 + }, + { + "epoch": 0.01, + "learning_rate": 2.7108050313064453e-05, + "loss": 3.4844, + "step": 1398272 + }, + { + "epoch": 0.01, + "learning_rate": 2.709968074435767e-05, + "loss": 3.4926, + "step": 1398784 + }, + { + "epoch": 0.01, + "learning_rate": 2.709129479684715e-05, + "loss": 3.5042, + "step": 1399296 + }, + { + "epoch": 0.01, + "learning_rate": 2.7082908849336626e-05, + "loss": 3.4927, + "step": 1399808 + }, + { + "epoch": 0.01, + "learning_rate": 2.7074522901826106e-05, + "loss": 3.497, + "step": 1400320 + }, + { + "epoch": 0.01, + "learning_rate": 2.7066153333119322e-05, + "loss": 3.484, + "step": 1400832 + }, + { + "epoch": 0.01, + "learning_rate": 2.7057767385608795e-05, + "loss": 3.4941, + "step": 1401344 + }, + { + "epoch": 0.01, + "learning_rate": 2.7049381438098275e-05, + "loss": 3.4751, + "step": 1401856 + }, + { + "epoch": 0.01, + "learning_rate": 2.7040995490587755e-05, + "loss": 3.5053, + "step": 1402368 + }, + { + "epoch": 0.01, + "learning_rate": 2.703262592188097e-05, + "loss": 3.4819, + "step": 1402880 + }, + { + "epoch": 0.01, + "learning_rate": 2.7024239974370447e-05, + "loss": 3.5055, + "step": 1403392 + }, + { + "epoch": 0.01, + "learning_rate": 2.7015854026859927e-05, + "loss": 3.4937, + "step": 1403904 + }, + { + "epoch": 0.01, + "learning_rate": 2.7007468079349407e-05, + "loss": 3.4814, + "step": 1404416 + }, + { + "epoch": 0.01, + "learning_rate": 2.6999098510642623e-05, + "loss": 3.5045, + "step": 1404928 + }, + { + "epoch": 0.01, + "learning_rate": 2.6990712563132096e-05, + "loss": 3.4911, + "step": 1405440 + }, + { + "epoch": 0.01, + "learning_rate": 2.698232661562158e-05, + "loss": 3.4893, + "step": 1405952 + }, + { + "epoch": 0.01, + "learning_rate": 2.697394066811106e-05, + "loss": 3.4788, + "step": 1406464 + }, + { + "epoch": 0.01, + "learning_rate": 2.696557109940427e-05, + "loss": 3.4997, + "step": 1406976 + }, + { + "epoch": 0.01, + "learning_rate": 2.695718515189375e-05, + "loss": 3.4869, + "step": 1407488 + }, + { + "epoch": 0.01, + "learning_rate": 2.694879920438323e-05, + "loss": 3.4899, + "step": 1408000 + }, + { + "epoch": 0.01, + "learning_rate": 2.694041325687271e-05, + "loss": 3.4764, + "step": 1408512 + }, + { + "epoch": 0.01, + "learning_rate": 2.693204368816592e-05, + "loss": 3.486, + "step": 1409024 + }, + { + "epoch": 0.01, + "learning_rate": 2.69236577406554e-05, + "loss": 3.4934, + "step": 1409536 + }, + { + "epoch": 0.01, + "learning_rate": 2.691527179314488e-05, + "loss": 3.5021, + "step": 1410048 + }, + { + "epoch": 0.01, + "learning_rate": 2.690688584563436e-05, + "loss": 3.4952, + "step": 1410560 + }, + { + "epoch": 0.01, + "learning_rate": 2.689851627692757e-05, + "loss": 3.5, + "step": 1411072 + }, + { + "epoch": 0.01, + "learning_rate": 2.689013032941705e-05, + "loss": 3.4997, + "step": 1411584 + }, + { + "epoch": 0.01, + "learning_rate": 2.6881744381906533e-05, + "loss": 3.4938, + "step": 1412096 + }, + { + "epoch": 0.01, + "learning_rate": 2.6873358434396013e-05, + "loss": 3.5014, + "step": 1412608 + }, + { + "epoch": 0.01, + "learning_rate": 2.6864988865689222e-05, + "loss": 3.4936, + "step": 1413120 + }, + { + "epoch": 0.01, + "learning_rate": 2.6856602918178702e-05, + "loss": 3.4902, + "step": 1413632 + }, + { + "epoch": 0.01, + "learning_rate": 2.6848216970668182e-05, + "loss": 3.4922, + "step": 1414144 + }, + { + "epoch": 0.01, + "learning_rate": 2.6839831023157662e-05, + "loss": 3.4993, + "step": 1414656 + }, + { + "epoch": 0.01, + "learning_rate": 2.6831461454450875e-05, + "loss": 3.4996, + "step": 1415168 + }, + { + "epoch": 0.01, + "learning_rate": 2.6823075506940355e-05, + "loss": 3.5027, + "step": 1415680 + }, + { + "epoch": 0.01, + "learning_rate": 2.6814689559429835e-05, + "loss": 3.4928, + "step": 1416192 + }, + { + "epoch": 0.01, + "learning_rate": 2.6806303611919314e-05, + "loss": 3.4682, + "step": 1416704 + }, + { + "epoch": 0.01, + "learning_rate": 2.6797934043212524e-05, + "loss": 3.4864, + "step": 1417216 + }, + { + "epoch": 0.01, + "learning_rate": 2.6789548095702004e-05, + "loss": 3.4923, + "step": 1417728 + }, + { + "epoch": 0.01, + "learning_rate": 2.6781162148191487e-05, + "loss": 3.4881, + "step": 1418240 + }, + { + "epoch": 0.01, + "learning_rate": 2.6772776200680967e-05, + "loss": 3.4823, + "step": 1418752 + }, + { + "epoch": 0.01, + "learning_rate": 2.6764406631974176e-05, + "loss": 3.4979, + "step": 1419264 + }, + { + "epoch": 0.02, + "learning_rate": 2.6756020684463656e-05, + "loss": 3.4898, + "step": 1419776 + }, + { + "epoch": 0.02, + "learning_rate": 2.6747634736953136e-05, + "loss": 3.4856, + "step": 1420288 + }, + { + "epoch": 0.02, + "learning_rate": 2.6739248789442616e-05, + "loss": 3.4898, + "step": 1420800 + }, + { + "epoch": 0.02, + "learning_rate": 2.6730879220735828e-05, + "loss": 3.502, + "step": 1421312 + }, + { + "epoch": 0.02, + "learning_rate": 2.6722493273225308e-05, + "loss": 3.5002, + "step": 1421824 + }, + { + "epoch": 0.02, + "learning_rate": 2.6714107325714788e-05, + "loss": 3.5054, + "step": 1422336 + }, + { + "epoch": 0.02, + "learning_rate": 2.6705721378204268e-05, + "loss": 3.4832, + "step": 1422848 + }, + { + "epoch": 0.02, + "learning_rate": 2.6697351809497477e-05, + "loss": 3.493, + "step": 1423360 + }, + { + "epoch": 0.02, + "learning_rate": 2.6688965861986957e-05, + "loss": 3.4913, + "step": 1423872 + }, + { + "epoch": 0.02, + "learning_rate": 2.668057991447644e-05, + "loss": 3.4958, + "step": 1424384 + }, + { + "epoch": 0.02, + "learning_rate": 2.667219396696592e-05, + "loss": 3.5005, + "step": 1424896 + }, + { + "epoch": 0.02, + "learning_rate": 2.666382439825913e-05, + "loss": 3.4877, + "step": 1425408 + }, + { + "epoch": 0.02, + "learning_rate": 2.665543845074861e-05, + "loss": 3.4878, + "step": 1425920 + }, + { + "epoch": 0.02, + "learning_rate": 2.664705250323809e-05, + "loss": 3.4968, + "step": 1426432 + }, + { + "epoch": 0.02, + "learning_rate": 2.663866655572757e-05, + "loss": 3.5018, + "step": 1426944 + }, + { + "epoch": 0.02, + "learning_rate": 2.6630296987020782e-05, + "loss": 3.4822, + "step": 1427456 + }, + { + "epoch": 0.02, + "learning_rate": 2.6621911039510262e-05, + "loss": 3.49, + "step": 1427968 + }, + { + "epoch": 0.02, + "learning_rate": 2.6613525091999742e-05, + "loss": 3.4899, + "step": 1428480 + }, + { + "epoch": 0.02, + "learning_rate": 2.6605139144489222e-05, + "loss": 3.4892, + "step": 1428992 + }, + { + "epoch": 0.02, + "learning_rate": 2.659676957578243e-05, + "loss": 3.4806, + "step": 1429504 + }, + { + "epoch": 0.02, + "learning_rate": 2.658838362827191e-05, + "loss": 3.4838, + "step": 1430016 + }, + { + "epoch": 0.02, + "learning_rate": 2.6579997680761394e-05, + "loss": 3.4856, + "step": 1430528 + }, + { + "epoch": 0.02, + "learning_rate": 2.6571611733250874e-05, + "loss": 3.4939, + "step": 1431040 + }, + { + "epoch": 0.02, + "learning_rate": 2.6563225785740354e-05, + "loss": 3.4866, + "step": 1431552 + }, + { + "epoch": 0.02, + "learning_rate": 2.6554856217033563e-05, + "loss": 3.4895, + "step": 1432064 + }, + { + "epoch": 0.02, + "learning_rate": 2.6546470269523043e-05, + "loss": 3.5053, + "step": 1432576 + }, + { + "epoch": 0.02, + "learning_rate": 2.6538084322012523e-05, + "loss": 3.5014, + "step": 1433088 + }, + { + "epoch": 0.02, + "learning_rate": 2.6529698374502003e-05, + "loss": 3.4943, + "step": 1433600 + }, + { + "epoch": 0.02, + "learning_rate": 2.6521328805795216e-05, + "loss": 3.4982, + "step": 1434112 + }, + { + "epoch": 0.02, + "learning_rate": 2.6512942858284696e-05, + "loss": 3.4904, + "step": 1434624 + }, + { + "epoch": 0.02, + "learning_rate": 2.6504556910774175e-05, + "loss": 3.4845, + "step": 1435136 + }, + { + "epoch": 0.02, + "learning_rate": 2.6496170963263655e-05, + "loss": 3.4813, + "step": 1435648 + }, + { + "epoch": 0.02, + "learning_rate": 2.6487801394556865e-05, + "loss": 3.4853, + "step": 1436160 + }, + { + "epoch": 0.02, + "learning_rate": 2.6479415447046348e-05, + "loss": 3.4904, + "step": 1436672 + }, + { + "epoch": 0.02, + "learning_rate": 2.6471029499535828e-05, + "loss": 3.4974, + "step": 1437184 + }, + { + "epoch": 0.02, + "learning_rate": 2.6462643552025308e-05, + "loss": 3.489, + "step": 1437696 + }, + { + "epoch": 0.02, + "learning_rate": 2.6454273983318517e-05, + "loss": 3.4905, + "step": 1438208 + }, + { + "epoch": 0.02, + "learning_rate": 2.6445888035807997e-05, + "loss": 3.492, + "step": 1438720 + }, + { + "epoch": 0.02, + "learning_rate": 2.6437502088297477e-05, + "loss": 3.4853, + "step": 1439232 + }, + { + "epoch": 0.02, + "learning_rate": 2.6429116140786957e-05, + "loss": 3.4856, + "step": 1439744 + }, + { + "epoch": 0.02, + "learning_rate": 2.642074657208017e-05, + "loss": 3.4999, + "step": 1440256 + }, + { + "epoch": 0.02, + "learning_rate": 2.641236062456965e-05, + "loss": 3.5024, + "step": 1440768 + }, + { + "epoch": 0.02, + "learning_rate": 2.640397467705913e-05, + "loss": 3.4955, + "step": 1441280 + }, + { + "epoch": 0.02, + "learning_rate": 2.6395605108352338e-05, + "loss": 3.4892, + "step": 1441792 + }, + { + "epoch": 0.02, + "learning_rate": 2.6387219160841818e-05, + "loss": 3.4891, + "step": 1442304 + }, + { + "epoch": 0.02, + "learning_rate": 2.63788332133313e-05, + "loss": 3.4921, + "step": 1442816 + }, + { + "epoch": 0.02, + "learning_rate": 2.637044726582078e-05, + "loss": 3.5055, + "step": 1443328 + }, + { + "epoch": 0.02, + "learning_rate": 2.636207769711399e-05, + "loss": 3.4891, + "step": 1443840 + }, + { + "epoch": 0.02, + "learning_rate": 2.635369174960347e-05, + "loss": 3.4917, + "step": 1444352 + }, + { + "epoch": 0.02, + "learning_rate": 2.634530580209295e-05, + "loss": 3.4918, + "step": 1444864 + }, + { + "epoch": 0.02, + "learning_rate": 2.633691985458243e-05, + "loss": 3.4928, + "step": 1445376 + }, + { + "epoch": 0.02, + "learning_rate": 2.6328550285875643e-05, + "loss": 3.4875, + "step": 1445888 + }, + { + "epoch": 0.02, + "learning_rate": 2.6320164338365123e-05, + "loss": 3.4936, + "step": 1446400 + }, + { + "epoch": 0.02, + "learning_rate": 2.6311778390854603e-05, + "loss": 3.4948, + "step": 1446912 + }, + { + "epoch": 0.02, + "learning_rate": 2.6303392443344083e-05, + "loss": 3.4806, + "step": 1447424 + }, + { + "epoch": 0.02, + "learning_rate": 2.6295022874637292e-05, + "loss": 3.5007, + "step": 1447936 + }, + { + "epoch": 0.02, + "learning_rate": 2.6286636927126772e-05, + "loss": 3.4974, + "step": 1448448 + }, + { + "epoch": 0.02, + "learning_rate": 2.6278250979616252e-05, + "loss": 3.4913, + "step": 1448960 + }, + { + "epoch": 0.02, + "learning_rate": 2.6269865032105735e-05, + "loss": 3.4925, + "step": 1449472 + }, + { + "epoch": 0.02, + "learning_rate": 2.6261495463398944e-05, + "loss": 3.484, + "step": 1449984 + }, + { + "epoch": 0.03, + "eval_loss": 3.843531608581543, + "eval_runtime": 325.9777, + "eval_samples_per_second": 1170.604, + "eval_steps_per_second": 36.582, + "step": 1450069 + }, + { + "epoch": 1.0, + "learning_rate": 2.6253109515888424e-05, + "loss": 3.4899, + "step": 1450496 + }, + { + "epoch": 1.0, + "learning_rate": 2.6244723568377904e-05, + "loss": 3.4839, + "step": 1451008 + }, + { + "epoch": 1.0, + "learning_rate": 2.6236337620867384e-05, + "loss": 3.5017, + "step": 1451520 + }, + { + "epoch": 1.0, + "learning_rate": 2.6227968052160597e-05, + "loss": 3.4845, + "step": 1452032 + }, + { + "epoch": 1.0, + "learning_rate": 2.6219582104650077e-05, + "loss": 3.5013, + "step": 1452544 + }, + { + "epoch": 1.0, + "learning_rate": 2.6211196157139557e-05, + "loss": 3.4835, + "step": 1453056 + }, + { + "epoch": 1.0, + "learning_rate": 2.6202810209629036e-05, + "loss": 3.4929, + "step": 1453568 + }, + { + "epoch": 1.0, + "learning_rate": 2.6194440640922246e-05, + "loss": 3.4757, + "step": 1454080 + }, + { + "epoch": 1.0, + "learning_rate": 2.6186054693411726e-05, + "loss": 3.4956, + "step": 1454592 + }, + { + "epoch": 1.0, + "learning_rate": 2.6177668745901205e-05, + "loss": 3.4851, + "step": 1455104 + }, + { + "epoch": 1.0, + "learning_rate": 2.616928279839069e-05, + "loss": 3.5015, + "step": 1455616 + }, + { + "epoch": 1.0, + "learning_rate": 2.6160913229683898e-05, + "loss": 3.491, + "step": 1456128 + }, + { + "epoch": 1.0, + "learning_rate": 2.6152543660977107e-05, + "loss": 3.4763, + "step": 1456640 + }, + { + "epoch": 1.0, + "learning_rate": 2.6144157713466587e-05, + "loss": 3.4812, + "step": 1457152 + }, + { + "epoch": 1.0, + "learning_rate": 2.6135771765956067e-05, + "loss": 3.4874, + "step": 1457664 + }, + { + "epoch": 1.0, + "learning_rate": 2.612738581844555e-05, + "loss": 3.4722, + "step": 1458176 + }, + { + "epoch": 1.0, + "learning_rate": 2.611899987093503e-05, + "loss": 3.4842, + "step": 1458688 + }, + { + "epoch": 1.0, + "learning_rate": 2.611061392342451e-05, + "loss": 3.4853, + "step": 1459200 + }, + { + "epoch": 1.0, + "learning_rate": 2.610222797591399e-05, + "loss": 3.4783, + "step": 1459712 + }, + { + "epoch": 1.0, + "learning_rate": 2.60938584072072e-05, + "loss": 3.5086, + "step": 1460224 + }, + { + "epoch": 1.0, + "learning_rate": 2.608547245969668e-05, + "loss": 3.4908, + "step": 1460736 + }, + { + "epoch": 1.0, + "learning_rate": 2.607708651218616e-05, + "loss": 3.4877, + "step": 1461248 + }, + { + "epoch": 1.0, + "learning_rate": 2.6068700564675642e-05, + "loss": 3.4839, + "step": 1461760 + }, + { + "epoch": 1.0, + "learning_rate": 2.606033099596885e-05, + "loss": 3.4996, + "step": 1462272 + }, + { + "epoch": 1.0, + "learning_rate": 2.605194504845833e-05, + "loss": 3.4805, + "step": 1462784 + }, + { + "epoch": 1.0, + "learning_rate": 2.604355910094781e-05, + "loss": 3.4851, + "step": 1463296 + }, + { + "epoch": 1.0, + "learning_rate": 2.603517315343729e-05, + "loss": 3.4816, + "step": 1463808 + }, + { + "epoch": 1.0, + "learning_rate": 2.6026803584730504e-05, + "loss": 3.4851, + "step": 1464320 + }, + { + "epoch": 1.0, + "learning_rate": 2.6018417637219984e-05, + "loss": 3.4829, + "step": 1464832 + }, + { + "epoch": 1.01, + "learning_rate": 2.6010031689709464e-05, + "loss": 3.4821, + "step": 1465344 + }, + { + "epoch": 1.01, + "learning_rate": 2.6001645742198944e-05, + "loss": 3.4887, + "step": 1465856 + }, + { + "epoch": 1.01, + "learning_rate": 2.5993276173492153e-05, + "loss": 3.487, + "step": 1466368 + }, + { + "epoch": 1.01, + "learning_rate": 2.5984890225981633e-05, + "loss": 3.4866, + "step": 1466880 + }, + { + "epoch": 1.01, + "learning_rate": 2.5976504278471113e-05, + "loss": 3.493, + "step": 1467392 + }, + { + "epoch": 1.01, + "learning_rate": 2.596811833096059e-05, + "loss": 3.4825, + "step": 1467904 + }, + { + "epoch": 1.01, + "learning_rate": 2.5959748762253805e-05, + "loss": 3.4911, + "step": 1468416 + }, + { + "epoch": 1.01, + "learning_rate": 2.5951362814743285e-05, + "loss": 3.4772, + "step": 1468928 + }, + { + "epoch": 1.01, + "learning_rate": 2.5942976867232765e-05, + "loss": 3.4888, + "step": 1469440 + }, + { + "epoch": 1.01, + "learning_rate": 2.5934590919722242e-05, + "loss": 3.4741, + "step": 1469952 + }, + { + "epoch": 1.01, + "learning_rate": 2.5926221351015458e-05, + "loss": 3.4819, + "step": 1470464 + }, + { + "epoch": 1.01, + "learning_rate": 2.5917835403504938e-05, + "loss": 3.48, + "step": 1470976 + }, + { + "epoch": 1.01, + "learning_rate": 2.5909449455994418e-05, + "loss": 3.4913, + "step": 1471488 + }, + { + "epoch": 1.01, + "learning_rate": 2.590106350848389e-05, + "loss": 3.4803, + "step": 1472000 + }, + { + "epoch": 1.01, + "learning_rate": 2.5892693939777107e-05, + "loss": 3.4853, + "step": 1472512 + }, + { + "epoch": 1.01, + "learning_rate": 2.5884307992266587e-05, + "loss": 3.4935, + "step": 1473024 + }, + { + "epoch": 1.01, + "learning_rate": 2.5875922044756063e-05, + "loss": 3.4876, + "step": 1473536 + }, + { + "epoch": 1.01, + "learning_rate": 2.5867536097245543e-05, + "loss": 3.4889, + "step": 1474048 + }, + { + "epoch": 1.01, + "learning_rate": 2.585916652853876e-05, + "loss": 3.471, + "step": 1474560 + }, + { + "epoch": 1.01, + "learning_rate": 2.585078058102824e-05, + "loss": 3.4781, + "step": 1475072 + }, + { + "epoch": 1.01, + "learning_rate": 2.5842394633517712e-05, + "loss": 3.4888, + "step": 1475584 + }, + { + "epoch": 1.01, + "learning_rate": 2.5834008686007195e-05, + "loss": 3.4809, + "step": 1476096 + }, + { + "epoch": 1.01, + "learning_rate": 2.582563911730041e-05, + "loss": 3.4827, + "step": 1476608 + }, + { + "epoch": 1.01, + "learning_rate": 2.581725316978989e-05, + "loss": 3.4755, + "step": 1477120 + }, + { + "epoch": 1.01, + "learning_rate": 2.5808867222279364e-05, + "loss": 3.4802, + "step": 1477632 + }, + { + "epoch": 1.01, + "learning_rate": 2.5800481274768844e-05, + "loss": 3.4649, + "step": 1478144 + }, + { + "epoch": 1.01, + "learning_rate": 2.579211170606206e-05, + "loss": 3.4871, + "step": 1478656 + }, + { + "epoch": 1.01, + "learning_rate": 2.5783725758551537e-05, + "loss": 3.4738, + "step": 1479168 + }, + { + "epoch": 1.01, + "learning_rate": 2.5775339811041017e-05, + "loss": 3.487, + "step": 1479680 + }, + { + "epoch": 1.01, + "learning_rate": 2.5766953863530497e-05, + "loss": 3.4854, + "step": 1480192 + }, + { + "epoch": 1.01, + "learning_rate": 2.5758584294823713e-05, + "loss": 3.4684, + "step": 1480704 + }, + { + "epoch": 1.01, + "learning_rate": 2.5750198347313186e-05, + "loss": 3.4905, + "step": 1481216 + }, + { + "epoch": 1.01, + "learning_rate": 2.5741812399802666e-05, + "loss": 3.4805, + "step": 1481728 + }, + { + "epoch": 1.01, + "learning_rate": 2.573342645229215e-05, + "loss": 3.4769, + "step": 1482240 + }, + { + "epoch": 1.01, + "learning_rate": 2.5725056883585365e-05, + "loss": 3.4669, + "step": 1482752 + }, + { + "epoch": 1.01, + "learning_rate": 2.5716670936074838e-05, + "loss": 3.4839, + "step": 1483264 + }, + { + "epoch": 1.01, + "learning_rate": 2.5708284988564318e-05, + "loss": 3.4758, + "step": 1483776 + }, + { + "epoch": 1.01, + "learning_rate": 2.5699899041053798e-05, + "loss": 3.4782, + "step": 1484288 + }, + { + "epoch": 1.01, + "learning_rate": 2.569152947234701e-05, + "loss": 3.4658, + "step": 1484800 + }, + { + "epoch": 1.01, + "learning_rate": 2.568314352483649e-05, + "loss": 3.4727, + "step": 1485312 + }, + { + "epoch": 1.01, + "learning_rate": 2.567475757732597e-05, + "loss": 3.4796, + "step": 1485824 + }, + { + "epoch": 1.01, + "learning_rate": 2.566637162981545e-05, + "loss": 3.4913, + "step": 1486336 + }, + { + "epoch": 1.01, + "learning_rate": 2.565800206110866e-05, + "loss": 3.4785, + "step": 1486848 + }, + { + "epoch": 1.01, + "learning_rate": 2.564961611359814e-05, + "loss": 3.4893, + "step": 1487360 + }, + { + "epoch": 1.01, + "learning_rate": 2.564123016608762e-05, + "loss": 3.4878, + "step": 1487872 + }, + { + "epoch": 1.01, + "learning_rate": 2.5632844218577103e-05, + "loss": 3.4798, + "step": 1488384 + }, + { + "epoch": 1.01, + "learning_rate": 2.5624474649870312e-05, + "loss": 3.4864, + "step": 1488896 + }, + { + "epoch": 1.01, + "learning_rate": 2.5616088702359792e-05, + "loss": 3.4823, + "step": 1489408 + }, + { + "epoch": 1.01, + "learning_rate": 2.5607702754849272e-05, + "loss": 3.4781, + "step": 1489920 + }, + { + "epoch": 1.01, + "learning_rate": 2.5599316807338752e-05, + "loss": 3.4798, + "step": 1490432 + }, + { + "epoch": 1.01, + "learning_rate": 2.5590947238631964e-05, + "loss": 3.4849, + "step": 1490944 + }, + { + "epoch": 1.01, + "learning_rate": 2.5582561291121444e-05, + "loss": 3.4899, + "step": 1491456 + }, + { + "epoch": 1.01, + "learning_rate": 2.5574175343610924e-05, + "loss": 3.4892, + "step": 1491968 + }, + { + "epoch": 1.01, + "learning_rate": 2.5565789396100404e-05, + "loss": 3.4785, + "step": 1492480 + }, + { + "epoch": 1.01, + "learning_rate": 2.5557419827393613e-05, + "loss": 3.4586, + "step": 1492992 + }, + { + "epoch": 1.01, + "learning_rate": 2.5549033879883093e-05, + "loss": 3.4749, + "step": 1493504 + }, + { + "epoch": 1.01, + "learning_rate": 2.5540647932372573e-05, + "loss": 3.4767, + "step": 1494016 + }, + { + "epoch": 1.01, + "learning_rate": 2.5532261984862056e-05, + "loss": 3.481, + "step": 1494528 + }, + { + "epoch": 1.01, + "learning_rate": 2.5523892416155266e-05, + "loss": 3.4708, + "step": 1495040 + }, + { + "epoch": 1.01, + "learning_rate": 2.5515506468644745e-05, + "loss": 3.4845, + "step": 1495552 + }, + { + "epoch": 1.02, + "learning_rate": 2.5507120521134225e-05, + "loss": 3.4784, + "step": 1496064 + }, + { + "epoch": 1.02, + "learning_rate": 2.5498734573623705e-05, + "loss": 3.4726, + "step": 1496576 + }, + { + "epoch": 1.02, + "learning_rate": 2.5490365004916918e-05, + "loss": 3.4804, + "step": 1497088 + }, + { + "epoch": 1.02, + "learning_rate": 2.5481979057406398e-05, + "loss": 3.4851, + "step": 1497600 + }, + { + "epoch": 1.02, + "learning_rate": 2.5473593109895878e-05, + "loss": 3.4854, + "step": 1498112 + }, + { + "epoch": 1.02, + "learning_rate": 2.5465207162385358e-05, + "loss": 3.4948, + "step": 1498624 + }, + { + "epoch": 1.02, + "learning_rate": 2.5456837593678567e-05, + "loss": 3.474, + "step": 1499136 + }, + { + "epoch": 1.02, + "learning_rate": 2.5448451646168047e-05, + "loss": 3.4789, + "step": 1499648 + }, + { + "epoch": 1.02, + "learning_rate": 2.5440065698657527e-05, + "loss": 3.4781, + "step": 1500160 + }, + { + "epoch": 1.02, + "learning_rate": 2.543167975114701e-05, + "loss": 3.4825, + "step": 1500672 + }, + { + "epoch": 1.02, + "learning_rate": 2.542331018244022e-05, + "loss": 3.4869, + "step": 1501184 + }, + { + "epoch": 1.02, + "learning_rate": 2.54149242349297e-05, + "loss": 3.475, + "step": 1501696 + }, + { + "epoch": 1.02, + "learning_rate": 2.540653828741918e-05, + "loss": 3.4771, + "step": 1502208 + }, + { + "epoch": 1.02, + "learning_rate": 2.539815233990866e-05, + "loss": 3.4819, + "step": 1502720 + }, + { + "epoch": 1.02, + "learning_rate": 2.538978277120187e-05, + "loss": 3.4877, + "step": 1503232 + }, + { + "epoch": 1.02, + "learning_rate": 2.538139682369135e-05, + "loss": 3.4687, + "step": 1503744 + }, + { + "epoch": 1.02, + "learning_rate": 2.537301087618083e-05, + "loss": 3.4824, + "step": 1504256 + }, + { + "epoch": 1.02, + "learning_rate": 2.536462492867031e-05, + "loss": 3.4752, + "step": 1504768 + }, + { + "epoch": 1.02, + "learning_rate": 2.535625535996352e-05, + "loss": 3.4755, + "step": 1505280 + }, + { + "epoch": 1.02, + "learning_rate": 2.5347869412453e-05, + "loss": 3.4673, + "step": 1505792 + }, + { + "epoch": 1.02, + "learning_rate": 2.533948346494248e-05, + "loss": 3.4728, + "step": 1506304 + }, + { + "epoch": 1.02, + "learning_rate": 2.533109751743196e-05, + "loss": 3.477, + "step": 1506816 + }, + { + "epoch": 1.02, + "learning_rate": 2.5322727948725173e-05, + "loss": 3.4761, + "step": 1507328 + }, + { + "epoch": 1.02, + "learning_rate": 2.5314342001214653e-05, + "loss": 3.4781, + "step": 1507840 + }, + { + "epoch": 1.02, + "learning_rate": 2.5305956053704133e-05, + "loss": 3.4781, + "step": 1508352 + }, + { + "epoch": 1.02, + "learning_rate": 2.5297570106193613e-05, + "loss": 3.4929, + "step": 1508864 + }, + { + "epoch": 1.02, + "learning_rate": 2.5289200537486825e-05, + "loss": 3.4904, + "step": 1509376 + }, + { + "epoch": 1.02, + "learning_rate": 2.5280814589976305e-05, + "loss": 3.4828, + "step": 1509888 + }, + { + "epoch": 1.02, + "learning_rate": 2.5272428642465785e-05, + "loss": 3.4826, + "step": 1510400 + }, + { + "epoch": 1.02, + "learning_rate": 2.5264042694955265e-05, + "loss": 3.4805, + "step": 1510912 + }, + { + "epoch": 1.02, + "learning_rate": 2.5255673126248474e-05, + "loss": 3.4747, + "step": 1511424 + }, + { + "epoch": 1.02, + "learning_rate": 2.5247287178737954e-05, + "loss": 3.4709, + "step": 1511936 + }, + { + "epoch": 1.02, + "learning_rate": 2.5238901231227434e-05, + "loss": 3.4725, + "step": 1512448 + }, + { + "epoch": 1.02, + "learning_rate": 2.5230515283716914e-05, + "loss": 3.4784, + "step": 1512960 + }, + { + "epoch": 1.02, + "learning_rate": 2.5222145715010127e-05, + "loss": 3.4853, + "step": 1513472 + }, + { + "epoch": 1.02, + "learning_rate": 2.5213759767499606e-05, + "loss": 3.4781, + "step": 1513984 + }, + { + "epoch": 1.02, + "learning_rate": 2.5205373819989086e-05, + "loss": 3.4792, + "step": 1514496 + }, + { + "epoch": 1.02, + "learning_rate": 2.5196987872478566e-05, + "loss": 3.4784, + "step": 1515008 + }, + { + "epoch": 1.02, + "learning_rate": 2.5188618303771775e-05, + "loss": 3.4721, + "step": 1515520 + }, + { + "epoch": 1.02, + "learning_rate": 2.518023235626126e-05, + "loss": 3.4751, + "step": 1516032 + }, + { + "epoch": 1.02, + "learning_rate": 2.517184640875074e-05, + "loss": 3.4897, + "step": 1516544 + }, + { + "epoch": 1.02, + "learning_rate": 2.516346046124022e-05, + "loss": 3.4914, + "step": 1517056 + }, + { + "epoch": 1.02, + "learning_rate": 2.5155090892533428e-05, + "loss": 3.4784, + "step": 1517568 + }, + { + "epoch": 1.02, + "learning_rate": 2.5146704945022908e-05, + "loss": 3.4771, + "step": 1518080 + }, + { + "epoch": 1.02, + "learning_rate": 2.5138318997512388e-05, + "loss": 3.4811, + "step": 1518592 + }, + { + "epoch": 1.02, + "learning_rate": 2.5129933050001868e-05, + "loss": 3.4772, + "step": 1519104 + }, + { + "epoch": 1.02, + "learning_rate": 2.512156348129508e-05, + "loss": 3.4936, + "step": 1519616 + }, + { + "epoch": 1.02, + "learning_rate": 2.511317753378456e-05, + "loss": 3.4765, + "step": 1520128 + }, + { + "epoch": 1.02, + "learning_rate": 2.510479158627404e-05, + "loss": 3.4814, + "step": 1520640 + }, + { + "epoch": 1.02, + "learning_rate": 2.509640563876352e-05, + "loss": 3.4754, + "step": 1521152 + }, + { + "epoch": 1.02, + "learning_rate": 2.508803607005673e-05, + "loss": 3.4841, + "step": 1521664 + }, + { + "epoch": 1.02, + "learning_rate": 2.5079650122546212e-05, + "loss": 3.4757, + "step": 1522176 + }, + { + "epoch": 1.02, + "learning_rate": 2.5071264175035692e-05, + "loss": 3.4796, + "step": 1522688 + }, + { + "epoch": 1.02, + "learning_rate": 2.5062878227525172e-05, + "loss": 3.4819, + "step": 1523200 + }, + { + "epoch": 1.02, + "learning_rate": 2.505450865881838e-05, + "loss": 3.4716, + "step": 1523712 + }, + { + "epoch": 1.02, + "learning_rate": 2.504612271130786e-05, + "loss": 3.4853, + "step": 1524224 + }, + { + "epoch": 1.02, + "learning_rate": 2.503773676379734e-05, + "loss": 3.488, + "step": 1524736 + }, + { + "epoch": 1.02, + "learning_rate": 2.502935081628682e-05, + "loss": 3.4781, + "step": 1525248 + }, + { + "epoch": 1.02, + "learning_rate": 2.5020981247580034e-05, + "loss": 3.48, + "step": 1525760 + }, + { + "epoch": 1.02, + "learning_rate": 2.5012595300069514e-05, + "loss": 3.4693, + "step": 1526272 + }, + { + "epoch": 1.03, + "eval_loss": 3.844906806945801, + "eval_runtime": 308.106, + "eval_samples_per_second": 1238.505, + "eval_steps_per_second": 38.704, + "step": 1526389 + }, + { + "epoch": 0.0, + "learning_rate": 2.5004209352558994e-05, + "loss": 3.4704, + "step": 1526784 + }, + { + "epoch": 0.0, + "learning_rate": 2.499582340504847e-05, + "loss": 3.4712, + "step": 1527296 + }, + { + "epoch": 0.0, + "learning_rate": 2.498743745753795e-05, + "loss": 3.4872, + "step": 1527808 + }, + { + "epoch": 0.0, + "learning_rate": 2.4979051510027434e-05, + "loss": 3.4759, + "step": 1528320 + }, + { + "epoch": 0.0, + "learning_rate": 2.4970681941320646e-05, + "loss": 3.4905, + "step": 1528832 + }, + { + "epoch": 0.0, + "learning_rate": 2.4962295993810123e-05, + "loss": 3.4693, + "step": 1529344 + }, + { + "epoch": 0.0, + "learning_rate": 2.4953910046299603e-05, + "loss": 3.4816, + "step": 1529856 + }, + { + "epoch": 0.0, + "learning_rate": 2.4945524098789083e-05, + "loss": 3.4604, + "step": 1530368 + }, + { + "epoch": 0.0, + "learning_rate": 2.4937154530082295e-05, + "loss": 3.4843, + "step": 1530880 + }, + { + "epoch": 0.0, + "learning_rate": 2.4928768582571775e-05, + "loss": 3.4691, + "step": 1531392 + }, + { + "epoch": 0.0, + "learning_rate": 2.4920382635061255e-05, + "loss": 3.4881, + "step": 1531904 + }, + { + "epoch": 0.0, + "learning_rate": 2.4911996687550735e-05, + "loss": 3.4825, + "step": 1532416 + }, + { + "epoch": 0.0, + "learning_rate": 2.4903643497647677e-05, + "loss": 3.4617, + "step": 1532928 + }, + { + "epoch": 0.0, + "learning_rate": 2.4895257550137157e-05, + "loss": 3.4722, + "step": 1533440 + }, + { + "epoch": 0.0, + "learning_rate": 2.4886871602626636e-05, + "loss": 3.4749, + "step": 1533952 + }, + { + "epoch": 0.0, + "learning_rate": 2.487848565511612e-05, + "loss": 3.4634, + "step": 1534464 + }, + { + "epoch": 0.0, + "learning_rate": 2.4870099707605596e-05, + "loss": 3.4706, + "step": 1534976 + }, + { + "epoch": 0.0, + "learning_rate": 2.4861713760095076e-05, + "loss": 3.4737, + "step": 1535488 + }, + { + "epoch": 0.0, + "learning_rate": 2.4853327812584556e-05, + "loss": 3.4712, + "step": 1536000 + }, + { + "epoch": 0.0, + "learning_rate": 2.4844941865074036e-05, + "loss": 3.4944, + "step": 1536512 + }, + { + "epoch": 0.0, + "learning_rate": 2.4836572296367245e-05, + "loss": 3.4766, + "step": 1537024 + }, + { + "epoch": 0.0, + "learning_rate": 2.482818634885673e-05, + "loss": 3.4747, + "step": 1537536 + }, + { + "epoch": 0.0, + "learning_rate": 2.481980040134621e-05, + "loss": 3.4761, + "step": 1538048 + }, + { + "epoch": 0.0, + "learning_rate": 2.4811430832639418e-05, + "loss": 3.4829, + "step": 1538560 + }, + { + "epoch": 0.0, + "learning_rate": 2.4803044885128898e-05, + "loss": 3.4709, + "step": 1539072 + }, + { + "epoch": 0.0, + "learning_rate": 2.4794658937618378e-05, + "loss": 3.4779, + "step": 1539584 + }, + { + "epoch": 0.0, + "learning_rate": 2.4786272990107858e-05, + "loss": 3.4682, + "step": 1540096 + }, + { + "epoch": 0.0, + "learning_rate": 2.477790342140107e-05, + "loss": 3.4707, + "step": 1540608 + }, + { + "epoch": 0.0, + "learning_rate": 2.476951747389055e-05, + "loss": 3.4708, + "step": 1541120 + }, + { + "epoch": 0.0, + "learning_rate": 2.476113152638003e-05, + "loss": 3.4743, + "step": 1541632 + }, + { + "epoch": 0.01, + "learning_rate": 2.475274557886951e-05, + "loss": 3.471, + "step": 1542144 + }, + { + "epoch": 0.01, + "learning_rate": 2.474437601016272e-05, + "loss": 3.479, + "step": 1542656 + }, + { + "epoch": 0.01, + "learning_rate": 2.47359900626522e-05, + "loss": 3.4763, + "step": 1543168 + }, + { + "epoch": 0.01, + "learning_rate": 2.4727604115141682e-05, + "loss": 3.4854, + "step": 1543680 + }, + { + "epoch": 0.01, + "learning_rate": 2.4719218167631162e-05, + "loss": 3.4669, + "step": 1544192 + }, + { + "epoch": 0.01, + "learning_rate": 2.471084859892437e-05, + "loss": 3.4809, + "step": 1544704 + }, + { + "epoch": 0.01, + "learning_rate": 2.470246265141385e-05, + "loss": 3.4653, + "step": 1545216 + }, + { + "epoch": 0.01, + "learning_rate": 2.469407670390333e-05, + "loss": 3.4759, + "step": 1545728 + }, + { + "epoch": 0.01, + "learning_rate": 2.468569075639281e-05, + "loss": 3.4611, + "step": 1546240 + }, + { + "epoch": 0.01, + "learning_rate": 2.4677321187686024e-05, + "loss": 3.4708, + "step": 1546752 + }, + { + "epoch": 0.01, + "learning_rate": 2.4668935240175504e-05, + "loss": 3.4658, + "step": 1547264 + }, + { + "epoch": 0.01, + "learning_rate": 2.4660549292664984e-05, + "loss": 3.4812, + "step": 1547776 + }, + { + "epoch": 0.01, + "learning_rate": 2.4652163345154464e-05, + "loss": 3.4716, + "step": 1548288 + }, + { + "epoch": 0.01, + "learning_rate": 2.4643793776447673e-05, + "loss": 3.47, + "step": 1548800 + }, + { + "epoch": 0.01, + "learning_rate": 2.4635407828937153e-05, + "loss": 3.4855, + "step": 1549312 + }, + { + "epoch": 0.01, + "learning_rate": 2.4627021881426636e-05, + "loss": 3.4764, + "step": 1549824 + }, + { + "epoch": 0.01, + "learning_rate": 2.4618635933916116e-05, + "loss": 3.4771, + "step": 1550336 + }, + { + "epoch": 0.01, + "learning_rate": 2.4610266365209325e-05, + "loss": 3.4639, + "step": 1550848 + }, + { + "epoch": 0.01, + "learning_rate": 2.4601880417698805e-05, + "loss": 3.4611, + "step": 1551360 + }, + { + "epoch": 0.01, + "learning_rate": 2.4593494470188285e-05, + "loss": 3.4779, + "step": 1551872 + }, + { + "epoch": 0.01, + "learning_rate": 2.4585108522677765e-05, + "loss": 3.4712, + "step": 1552384 + }, + { + "epoch": 0.01, + "learning_rate": 2.4576738953970977e-05, + "loss": 3.4673, + "step": 1552896 + }, + { + "epoch": 0.01, + "learning_rate": 2.4568353006460457e-05, + "loss": 3.4655, + "step": 1553408 + }, + { + "epoch": 0.01, + "learning_rate": 2.4559967058949937e-05, + "loss": 3.4724, + "step": 1553920 + }, + { + "epoch": 0.01, + "learning_rate": 2.4551581111439417e-05, + "loss": 3.4512, + "step": 1554432 + }, + { + "epoch": 0.01, + "learning_rate": 2.4543211542732626e-05, + "loss": 3.4729, + "step": 1554944 + }, + { + "epoch": 0.01, + "learning_rate": 2.4534825595222106e-05, + "loss": 3.4618, + "step": 1555456 + }, + { + "epoch": 0.01, + "learning_rate": 2.452643964771159e-05, + "loss": 3.4706, + "step": 1555968 + }, + { + "epoch": 0.01, + "learning_rate": 2.451805370020107e-05, + "loss": 3.4772, + "step": 1556480 + }, + { + "epoch": 0.01, + "learning_rate": 2.450968413149428e-05, + "loss": 3.4599, + "step": 1556992 + }, + { + "epoch": 0.01, + "learning_rate": 2.450129818398376e-05, + "loss": 3.4729, + "step": 1557504 + }, + { + "epoch": 0.01, + "learning_rate": 2.449291223647324e-05, + "loss": 3.4703, + "step": 1558016 + }, + { + "epoch": 0.01, + "learning_rate": 2.448452628896272e-05, + "loss": 3.4635, + "step": 1558528 + }, + { + "epoch": 0.01, + "learning_rate": 2.447615672025593e-05, + "loss": 3.4631, + "step": 1559040 + }, + { + "epoch": 0.01, + "learning_rate": 2.446777077274541e-05, + "loss": 3.4685, + "step": 1559552 + }, + { + "epoch": 0.01, + "learning_rate": 2.445938482523489e-05, + "loss": 3.4656, + "step": 1560064 + }, + { + "epoch": 0.01, + "learning_rate": 2.4450998877724368e-05, + "loss": 3.4634, + "step": 1560576 + }, + { + "epoch": 0.01, + "learning_rate": 2.444262930901758e-05, + "loss": 3.4584, + "step": 1561088 + }, + { + "epoch": 0.01, + "learning_rate": 2.443424336150706e-05, + "loss": 3.4584, + "step": 1561600 + }, + { + "epoch": 0.01, + "learning_rate": 2.4425857413996543e-05, + "loss": 3.4671, + "step": 1562112 + }, + { + "epoch": 0.01, + "learning_rate": 2.441747146648602e-05, + "loss": 3.4798, + "step": 1562624 + }, + { + "epoch": 0.01, + "learning_rate": 2.4409101897779232e-05, + "loss": 3.4675, + "step": 1563136 + }, + { + "epoch": 0.01, + "learning_rate": 2.4400715950268712e-05, + "loss": 3.476, + "step": 1563648 + }, + { + "epoch": 0.01, + "learning_rate": 2.4392330002758192e-05, + "loss": 3.4737, + "step": 1564160 + }, + { + "epoch": 0.01, + "learning_rate": 2.438394405524767e-05, + "loss": 3.4678, + "step": 1564672 + }, + { + "epoch": 0.01, + "learning_rate": 2.4375574486540885e-05, + "loss": 3.4728, + "step": 1565184 + }, + { + "epoch": 0.01, + "learning_rate": 2.4367188539030365e-05, + "loss": 3.4758, + "step": 1565696 + }, + { + "epoch": 0.01, + "learning_rate": 2.435880259151984e-05, + "loss": 3.4652, + "step": 1566208 + }, + { + "epoch": 0.01, + "learning_rate": 2.435041664400932e-05, + "loss": 3.4671, + "step": 1566720 + }, + { + "epoch": 0.01, + "learning_rate": 2.4342047075302534e-05, + "loss": 3.475, + "step": 1567232 + }, + { + "epoch": 0.01, + "learning_rate": 2.4333661127792014e-05, + "loss": 3.4737, + "step": 1567744 + }, + { + "epoch": 0.01, + "learning_rate": 2.4325275180281494e-05, + "loss": 3.4723, + "step": 1568256 + }, + { + "epoch": 0.01, + "learning_rate": 2.4316889232770974e-05, + "loss": 3.4709, + "step": 1568768 + }, + { + "epoch": 0.01, + "learning_rate": 2.4308519664064186e-05, + "loss": 3.4511, + "step": 1569280 + }, + { + "epoch": 0.01, + "learning_rate": 2.4300133716553666e-05, + "loss": 3.4571, + "step": 1569792 + }, + { + "epoch": 0.01, + "learning_rate": 2.4291747769043143e-05, + "loss": 3.4696, + "step": 1570304 + }, + { + "epoch": 0.01, + "learning_rate": 2.4283361821532623e-05, + "loss": 3.4686, + "step": 1570816 + }, + { + "epoch": 0.01, + "learning_rate": 2.427499225282584e-05, + "loss": 3.4623, + "step": 1571328 + }, + { + "epoch": 0.01, + "learning_rate": 2.4266606305315315e-05, + "loss": 3.4717, + "step": 1571840 + }, + { + "epoch": 0.02, + "learning_rate": 2.4258220357804795e-05, + "loss": 3.4656, + "step": 1572352 + }, + { + "epoch": 0.02, + "learning_rate": 2.4249834410294275e-05, + "loss": 3.4619, + "step": 1572864 + }, + { + "epoch": 0.02, + "learning_rate": 2.4241464841587487e-05, + "loss": 3.4667, + "step": 1573376 + }, + { + "epoch": 0.02, + "learning_rate": 2.4233078894076967e-05, + "loss": 3.4679, + "step": 1573888 + }, + { + "epoch": 0.02, + "learning_rate": 2.4224692946566447e-05, + "loss": 3.4782, + "step": 1574400 + }, + { + "epoch": 0.02, + "learning_rate": 2.4216306999055927e-05, + "loss": 3.4763, + "step": 1574912 + }, + { + "epoch": 0.02, + "learning_rate": 2.420793743034914e-05, + "loss": 3.472, + "step": 1575424 + }, + { + "epoch": 0.02, + "learning_rate": 2.4199551482838616e-05, + "loss": 3.4592, + "step": 1575936 + }, + { + "epoch": 0.02, + "learning_rate": 2.4191165535328096e-05, + "loss": 3.472, + "step": 1576448 + }, + { + "epoch": 0.02, + "learning_rate": 2.4182779587817576e-05, + "loss": 3.4671, + "step": 1576960 + }, + { + "epoch": 0.02, + "learning_rate": 2.417441001911079e-05, + "loss": 3.477, + "step": 1577472 + }, + { + "epoch": 0.02, + "learning_rate": 2.416602407160027e-05, + "loss": 3.4668, + "step": 1577984 + }, + { + "epoch": 0.02, + "learning_rate": 2.415763812408975e-05, + "loss": 3.4607, + "step": 1578496 + }, + { + "epoch": 0.02, + "learning_rate": 2.414925217657923e-05, + "loss": 3.4711, + "step": 1579008 + }, + { + "epoch": 0.02, + "learning_rate": 2.4140882607872438e-05, + "loss": 3.4759, + "step": 1579520 + }, + { + "epoch": 0.02, + "learning_rate": 2.413249666036192e-05, + "loss": 3.4619, + "step": 1580032 + }, + { + "epoch": 0.02, + "learning_rate": 2.41241107128514e-05, + "loss": 3.4699, + "step": 1580544 + }, + { + "epoch": 0.02, + "learning_rate": 2.411572476534088e-05, + "loss": 3.4668, + "step": 1581056 + }, + { + "epoch": 0.02, + "learning_rate": 2.410735519663409e-05, + "loss": 3.4572, + "step": 1581568 + }, + { + "epoch": 0.02, + "learning_rate": 2.409896924912357e-05, + "loss": 3.4545, + "step": 1582080 + }, + { + "epoch": 0.02, + "learning_rate": 2.409058330161305e-05, + "loss": 3.464, + "step": 1582592 + }, + { + "epoch": 0.02, + "learning_rate": 2.408219735410253e-05, + "loss": 3.4637, + "step": 1583104 + }, + { + "epoch": 0.02, + "learning_rate": 2.4073827785395742e-05, + "loss": 3.4656, + "step": 1583616 + }, + { + "epoch": 0.02, + "learning_rate": 2.4065441837885222e-05, + "loss": 3.4636, + "step": 1584128 + }, + { + "epoch": 0.02, + "learning_rate": 2.4057055890374702e-05, + "loss": 3.4647, + "step": 1584640 + }, + { + "epoch": 0.02, + "learning_rate": 2.4048669942864182e-05, + "loss": 3.4802, + "step": 1585152 + }, + { + "epoch": 0.02, + "learning_rate": 2.404030037415739e-05, + "loss": 3.4808, + "step": 1585664 + }, + { + "epoch": 0.02, + "learning_rate": 2.4031914426646875e-05, + "loss": 3.4679, + "step": 1586176 + }, + { + "epoch": 0.02, + "learning_rate": 2.4023528479136355e-05, + "loss": 3.4726, + "step": 1586688 + }, + { + "epoch": 0.02, + "learning_rate": 2.4015142531625835e-05, + "loss": 3.4638, + "step": 1587200 + }, + { + "epoch": 0.02, + "learning_rate": 2.4006772962919044e-05, + "loss": 3.464, + "step": 1587712 + }, + { + "epoch": 0.02, + "learning_rate": 2.3998387015408524e-05, + "loss": 3.461, + "step": 1588224 + }, + { + "epoch": 0.02, + "learning_rate": 2.3990001067898004e-05, + "loss": 3.4626, + "step": 1588736 + }, + { + "epoch": 0.02, + "learning_rate": 2.3981615120387484e-05, + "loss": 3.4667, + "step": 1589248 + }, + { + "epoch": 0.02, + "learning_rate": 2.3973245551680696e-05, + "loss": 3.4695, + "step": 1589760 + }, + { + "epoch": 0.02, + "learning_rate": 2.3964859604170176e-05, + "loss": 3.4661, + "step": 1590272 + }, + { + "epoch": 0.02, + "learning_rate": 2.3956473656659656e-05, + "loss": 3.4681, + "step": 1590784 + }, + { + "epoch": 0.02, + "learning_rate": 2.3948087709149136e-05, + "loss": 3.4659, + "step": 1591296 + }, + { + "epoch": 0.02, + "learning_rate": 2.3939718140442345e-05, + "loss": 3.4611, + "step": 1591808 + }, + { + "epoch": 0.02, + "learning_rate": 2.393133219293183e-05, + "loss": 3.4623, + "step": 1592320 + }, + { + "epoch": 0.02, + "learning_rate": 2.3922946245421308e-05, + "loss": 3.4772, + "step": 1592832 + }, + { + "epoch": 0.02, + "learning_rate": 2.3914560297910788e-05, + "loss": 3.4791, + "step": 1593344 + }, + { + "epoch": 0.02, + "learning_rate": 2.3906190729203997e-05, + "loss": 3.4714, + "step": 1593856 + }, + { + "epoch": 0.02, + "learning_rate": 2.3897804781693477e-05, + "loss": 3.4625, + "step": 1594368 + }, + { + "epoch": 0.02, + "learning_rate": 2.3889418834182957e-05, + "loss": 3.4682, + "step": 1594880 + }, + { + "epoch": 0.02, + "learning_rate": 2.3881032886672437e-05, + "loss": 3.4667, + "step": 1595392 + }, + { + "epoch": 0.02, + "learning_rate": 2.387266331796565e-05, + "loss": 3.4775, + "step": 1595904 + }, + { + "epoch": 0.02, + "learning_rate": 2.386427737045513e-05, + "loss": 3.4633, + "step": 1596416 + }, + { + "epoch": 0.02, + "learning_rate": 2.385589142294461e-05, + "loss": 3.468, + "step": 1596928 + }, + { + "epoch": 0.02, + "learning_rate": 2.384750547543409e-05, + "loss": 3.4666, + "step": 1597440 + }, + { + "epoch": 0.02, + "learning_rate": 2.38391359067273e-05, + "loss": 3.4762, + "step": 1597952 + }, + { + "epoch": 0.02, + "learning_rate": 2.3830749959216782e-05, + "loss": 3.4623, + "step": 1598464 + }, + { + "epoch": 0.02, + "learning_rate": 2.3822364011706262e-05, + "loss": 3.4671, + "step": 1598976 + }, + { + "epoch": 0.02, + "learning_rate": 2.381397806419574e-05, + "loss": 3.4701, + "step": 1599488 + }, + { + "epoch": 0.02, + "learning_rate": 2.380560849548895e-05, + "loss": 3.4613, + "step": 1600000 + }, + { + "epoch": 0.02, + "learning_rate": 2.379722254797843e-05, + "loss": 3.4714, + "step": 1600512 + }, + { + "epoch": 0.02, + "learning_rate": 2.378883660046791e-05, + "loss": 3.4774, + "step": 1601024 + }, + { + "epoch": 0.02, + "learning_rate": 2.378045065295739e-05, + "loss": 3.4659, + "step": 1601536 + }, + { + "epoch": 0.02, + "learning_rate": 2.3772081084250603e-05, + "loss": 3.4632, + "step": 1602048 + }, + { + "epoch": 0.02, + "learning_rate": 2.3763695136740083e-05, + "loss": 3.4647, + "step": 1602560 + }, + { + "epoch": 0.03, + "eval_loss": 3.8460073471069336, + "eval_runtime": 303.0242, + "eval_samples_per_second": 1259.276, + "eval_steps_per_second": 39.353, + "step": 1602709 + }, + { + "epoch": 1.0, + "learning_rate": 2.3755309189229563e-05, + "loss": 3.4648, + "step": 1603072 + }, + { + "epoch": 1.0, + "learning_rate": 2.374692324171904e-05, + "loss": 3.4566, + "step": 1603584 + }, + { + "epoch": 1.0, + "learning_rate": 2.3738553673012252e-05, + "loss": 3.4741, + "step": 1604096 + }, + { + "epoch": 1.0, + "learning_rate": 2.3730167725501736e-05, + "loss": 3.4671, + "step": 1604608 + }, + { + "epoch": 1.0, + "learning_rate": 2.3721781777991212e-05, + "loss": 3.4763, + "step": 1605120 + }, + { + "epoch": 1.0, + "learning_rate": 2.3713395830480692e-05, + "loss": 3.4626, + "step": 1605632 + }, + { + "epoch": 1.0, + "learning_rate": 2.3705026261773905e-05, + "loss": 3.4696, + "step": 1606144 + }, + { + "epoch": 1.0, + "learning_rate": 2.3696640314263385e-05, + "loss": 3.4513, + "step": 1606656 + }, + { + "epoch": 1.0, + "learning_rate": 2.368825436675286e-05, + "loss": 3.4701, + "step": 1607168 + }, + { + "epoch": 1.0, + "learning_rate": 2.3679868419242345e-05, + "loss": 3.4635, + "step": 1607680 + }, + { + "epoch": 1.0, + "learning_rate": 2.3671498850535557e-05, + "loss": 3.4677, + "step": 1608192 + }, + { + "epoch": 1.0, + "learning_rate": 2.3663112903025037e-05, + "loss": 3.472, + "step": 1608704 + }, + { + "epoch": 1.0, + "learning_rate": 2.3654743334318246e-05, + "loss": 3.4495, + "step": 1609216 + }, + { + "epoch": 1.0, + "learning_rate": 2.3646357386807726e-05, + "loss": 3.4582, + "step": 1609728 + }, + { + "epoch": 1.0, + "learning_rate": 2.3637971439297206e-05, + "loss": 3.4647, + "step": 1610240 + }, + { + "epoch": 1.0, + "learning_rate": 2.3629585491786686e-05, + "loss": 3.451, + "step": 1610752 + }, + { + "epoch": 1.0, + "learning_rate": 2.3621199544276166e-05, + "loss": 3.4591, + "step": 1611264 + }, + { + "epoch": 1.0, + "learning_rate": 2.3612813596765646e-05, + "loss": 3.4618, + "step": 1611776 + }, + { + "epoch": 1.0, + "learning_rate": 2.3604427649255126e-05, + "loss": 3.4584, + "step": 1612288 + }, + { + "epoch": 1.0, + "learning_rate": 2.3596041701744606e-05, + "loss": 3.4803, + "step": 1612800 + }, + { + "epoch": 1.0, + "learning_rate": 2.3587672133037815e-05, + "loss": 3.4653, + "step": 1613312 + }, + { + "epoch": 1.0, + "learning_rate": 2.3579286185527298e-05, + "loss": 3.4647, + "step": 1613824 + }, + { + "epoch": 1.0, + "learning_rate": 2.3570900238016778e-05, + "loss": 3.4664, + "step": 1614336 + }, + { + "epoch": 1.0, + "learning_rate": 2.3562514290506258e-05, + "loss": 3.4674, + "step": 1614848 + }, + { + "epoch": 1.0, + "learning_rate": 2.3554144721799467e-05, + "loss": 3.4591, + "step": 1615360 + }, + { + "epoch": 1.0, + "learning_rate": 2.3545758774288947e-05, + "loss": 3.4675, + "step": 1615872 + }, + { + "epoch": 1.0, + "learning_rate": 2.3537372826778427e-05, + "loss": 3.4576, + "step": 1616384 + }, + { + "epoch": 1.0, + "learning_rate": 2.3528986879267907e-05, + "loss": 3.4581, + "step": 1616896 + }, + { + "epoch": 1.0, + "learning_rate": 2.352061731056112e-05, + "loss": 3.4583, + "step": 1617408 + }, + { + "epoch": 1.0, + "learning_rate": 2.35122313630506e-05, + "loss": 3.4662, + "step": 1617920 + }, + { + "epoch": 1.01, + "learning_rate": 2.350384541554008e-05, + "loss": 3.4601, + "step": 1618432 + }, + { + "epoch": 1.01, + "learning_rate": 2.349547584683329e-05, + "loss": 3.4643, + "step": 1618944 + }, + { + "epoch": 1.01, + "learning_rate": 2.348708989932277e-05, + "loss": 3.4646, + "step": 1619456 + }, + { + "epoch": 1.01, + "learning_rate": 2.3478703951812252e-05, + "loss": 3.469, + "step": 1619968 + }, + { + "epoch": 1.01, + "learning_rate": 2.3470318004301732e-05, + "loss": 3.4581, + "step": 1620480 + }, + { + "epoch": 1.01, + "learning_rate": 2.3461932056791212e-05, + "loss": 3.4688, + "step": 1620992 + }, + { + "epoch": 1.01, + "learning_rate": 2.345356248808442e-05, + "loss": 3.4582, + "step": 1621504 + }, + { + "epoch": 1.01, + "learning_rate": 2.34451765405739e-05, + "loss": 3.4622, + "step": 1622016 + }, + { + "epoch": 1.01, + "learning_rate": 2.343679059306338e-05, + "loss": 3.4505, + "step": 1622528 + }, + { + "epoch": 1.01, + "learning_rate": 2.3428421024356593e-05, + "loss": 3.4559, + "step": 1623040 + }, + { + "epoch": 1.01, + "learning_rate": 2.3420035076846073e-05, + "loss": 3.4586, + "step": 1623552 + }, + { + "epoch": 1.01, + "learning_rate": 2.3411649129335553e-05, + "loss": 3.4674, + "step": 1624064 + }, + { + "epoch": 1.01, + "learning_rate": 2.3403263181825033e-05, + "loss": 3.4591, + "step": 1624576 + }, + { + "epoch": 1.01, + "learning_rate": 2.3394893613118242e-05, + "loss": 3.4606, + "step": 1625088 + }, + { + "epoch": 1.01, + "learning_rate": 2.3386507665607722e-05, + "loss": 3.4738, + "step": 1625600 + }, + { + "epoch": 1.01, + "learning_rate": 2.3378121718097206e-05, + "loss": 3.4638, + "step": 1626112 + }, + { + "epoch": 1.01, + "learning_rate": 2.3369735770586686e-05, + "loss": 3.4656, + "step": 1626624 + }, + { + "epoch": 1.01, + "learning_rate": 2.3361366201879895e-05, + "loss": 3.4534, + "step": 1627136 + }, + { + "epoch": 1.01, + "learning_rate": 2.3352980254369375e-05, + "loss": 3.4448, + "step": 1627648 + }, + { + "epoch": 1.01, + "learning_rate": 2.3344594306858855e-05, + "loss": 3.4698, + "step": 1628160 + }, + { + "epoch": 1.01, + "learning_rate": 2.3336208359348334e-05, + "loss": 3.4569, + "step": 1628672 + }, + { + "epoch": 1.01, + "learning_rate": 2.3327838790641547e-05, + "loss": 3.4564, + "step": 1629184 + }, + { + "epoch": 1.01, + "learning_rate": 2.3319452843131027e-05, + "loss": 3.456, + "step": 1629696 + }, + { + "epoch": 1.01, + "learning_rate": 2.3311066895620507e-05, + "loss": 3.4604, + "step": 1630208 + }, + { + "epoch": 1.01, + "learning_rate": 2.3302680948109987e-05, + "loss": 3.436, + "step": 1630720 + }, + { + "epoch": 1.01, + "learning_rate": 2.3294311379403196e-05, + "loss": 3.4625, + "step": 1631232 + }, + { + "epoch": 1.01, + "learning_rate": 2.3285925431892676e-05, + "loss": 3.4487, + "step": 1631744 + }, + { + "epoch": 1.01, + "learning_rate": 2.327753948438216e-05, + "loss": 3.4605, + "step": 1632256 + }, + { + "epoch": 1.01, + "learning_rate": 2.3269153536871636e-05, + "loss": 3.461, + "step": 1632768 + }, + { + "epoch": 1.01, + "learning_rate": 2.3260783968164848e-05, + "loss": 3.4551, + "step": 1633280 + }, + { + "epoch": 1.01, + "learning_rate": 2.3252398020654328e-05, + "loss": 3.4567, + "step": 1633792 + }, + { + "epoch": 1.01, + "learning_rate": 2.3244012073143808e-05, + "loss": 3.4621, + "step": 1634304 + }, + { + "epoch": 1.01, + "learning_rate": 2.3235626125633285e-05, + "loss": 3.4477, + "step": 1634816 + }, + { + "epoch": 1.01, + "learning_rate": 2.32272565569265e-05, + "loss": 3.4526, + "step": 1635328 + }, + { + "epoch": 1.01, + "learning_rate": 2.321887060941598e-05, + "loss": 3.4547, + "step": 1635840 + }, + { + "epoch": 1.01, + "learning_rate": 2.321048466190546e-05, + "loss": 3.4572, + "step": 1636352 + }, + { + "epoch": 1.01, + "learning_rate": 2.3202098714394937e-05, + "loss": 3.4517, + "step": 1636864 + }, + { + "epoch": 1.01, + "learning_rate": 2.319372914568815e-05, + "loss": 3.446, + "step": 1637376 + }, + { + "epoch": 1.01, + "learning_rate": 2.318534319817763e-05, + "loss": 3.4469, + "step": 1637888 + }, + { + "epoch": 1.01, + "learning_rate": 2.317695725066711e-05, + "loss": 3.4544, + "step": 1638400 + }, + { + "epoch": 1.01, + "learning_rate": 2.316857130315659e-05, + "loss": 3.4662, + "step": 1638912 + }, + { + "epoch": 1.01, + "learning_rate": 2.3160201734449802e-05, + "loss": 3.4553, + "step": 1639424 + }, + { + "epoch": 1.01, + "learning_rate": 2.3151815786939282e-05, + "loss": 3.4668, + "step": 1639936 + }, + { + "epoch": 1.01, + "learning_rate": 2.314342983942876e-05, + "loss": 3.4661, + "step": 1640448 + }, + { + "epoch": 1.01, + "learning_rate": 2.313504389191824e-05, + "loss": 3.4587, + "step": 1640960 + }, + { + "epoch": 1.01, + "learning_rate": 2.3126674323211454e-05, + "loss": 3.4574, + "step": 1641472 + }, + { + "epoch": 1.01, + "learning_rate": 2.3118288375700934e-05, + "loss": 3.4618, + "step": 1641984 + }, + { + "epoch": 1.01, + "learning_rate": 2.310990242819041e-05, + "loss": 3.4582, + "step": 1642496 + }, + { + "epoch": 1.01, + "learning_rate": 2.310151648067989e-05, + "loss": 3.4543, + "step": 1643008 + }, + { + "epoch": 1.01, + "learning_rate": 2.3093146911973103e-05, + "loss": 3.4669, + "step": 1643520 + }, + { + "epoch": 1.01, + "learning_rate": 2.3084760964462583e-05, + "loss": 3.4598, + "step": 1644032 + }, + { + "epoch": 1.01, + "learning_rate": 2.3076375016952063e-05, + "loss": 3.4631, + "step": 1644544 + }, + { + "epoch": 1.01, + "learning_rate": 2.3067989069441543e-05, + "loss": 3.4597, + "step": 1645056 + }, + { + "epoch": 1.01, + "learning_rate": 2.3059619500734756e-05, + "loss": 3.4381, + "step": 1645568 + }, + { + "epoch": 1.01, + "learning_rate": 2.3051233553224232e-05, + "loss": 3.4456, + "step": 1646080 + }, + { + "epoch": 1.01, + "learning_rate": 2.3042847605713712e-05, + "loss": 3.453, + "step": 1646592 + }, + { + "epoch": 1.01, + "learning_rate": 2.3034461658203192e-05, + "loss": 3.4579, + "step": 1647104 + }, + { + "epoch": 1.01, + "learning_rate": 2.3026092089496408e-05, + "loss": 3.4514, + "step": 1647616 + }, + { + "epoch": 1.01, + "learning_rate": 2.3017706141985885e-05, + "loss": 3.458, + "step": 1648128 + }, + { + "epoch": 1.02, + "learning_rate": 2.3009320194475364e-05, + "loss": 3.4564, + "step": 1648640 + }, + { + "epoch": 1.02, + "learning_rate": 2.3000934246964844e-05, + "loss": 3.4499, + "step": 1649152 + }, + { + "epoch": 1.02, + "learning_rate": 2.2992564678258054e-05, + "loss": 3.4576, + "step": 1649664 + }, + { + "epoch": 1.02, + "learning_rate": 2.2984178730747537e-05, + "loss": 3.4521, + "step": 1650176 + }, + { + "epoch": 1.02, + "learning_rate": 2.2975792783237017e-05, + "loss": 3.4664, + "step": 1650688 + }, + { + "epoch": 1.02, + "learning_rate": 2.2967406835726497e-05, + "loss": 3.4654, + "step": 1651200 + }, + { + "epoch": 1.02, + "learning_rate": 2.2959037267019706e-05, + "loss": 3.4615, + "step": 1651712 + }, + { + "epoch": 1.02, + "learning_rate": 2.2950651319509186e-05, + "loss": 3.4471, + "step": 1652224 + }, + { + "epoch": 1.02, + "learning_rate": 2.2942265371998666e-05, + "loss": 3.4579, + "step": 1652736 + }, + { + "epoch": 1.02, + "learning_rate": 2.2933879424488146e-05, + "loss": 3.4551, + "step": 1653248 + }, + { + "epoch": 1.02, + "learning_rate": 2.2925509855781358e-05, + "loss": 3.466, + "step": 1653760 + }, + { + "epoch": 1.02, + "learning_rate": 2.2917123908270838e-05, + "loss": 3.4548, + "step": 1654272 + }, + { + "epoch": 1.02, + "learning_rate": 2.2908737960760318e-05, + "loss": 3.4488, + "step": 1654784 + }, + { + "epoch": 1.02, + "learning_rate": 2.2900352013249798e-05, + "loss": 3.4642, + "step": 1655296 + }, + { + "epoch": 1.02, + "learning_rate": 2.2891982444543007e-05, + "loss": 3.4591, + "step": 1655808 + }, + { + "epoch": 1.02, + "learning_rate": 2.288359649703249e-05, + "loss": 3.4539, + "step": 1656320 + }, + { + "epoch": 1.02, + "learning_rate": 2.287521054952197e-05, + "loss": 3.4598, + "step": 1656832 + }, + { + "epoch": 1.02, + "learning_rate": 2.286682460201145e-05, + "loss": 3.4531, + "step": 1657344 + }, + { + "epoch": 1.02, + "learning_rate": 2.285845503330466e-05, + "loss": 3.4469, + "step": 1657856 + }, + { + "epoch": 1.02, + "learning_rate": 2.285006908579414e-05, + "loss": 3.442, + "step": 1658368 + }, + { + "epoch": 1.02, + "learning_rate": 2.284168313828362e-05, + "loss": 3.453, + "step": 1658880 + }, + { + "epoch": 1.02, + "learning_rate": 2.28332971907731e-05, + "loss": 3.4556, + "step": 1659392 + }, + { + "epoch": 1.02, + "learning_rate": 2.2824927622066312e-05, + "loss": 3.4532, + "step": 1659904 + }, + { + "epoch": 1.02, + "learning_rate": 2.2816541674555792e-05, + "loss": 3.4527, + "step": 1660416 + }, + { + "epoch": 1.02, + "learning_rate": 2.2808155727045272e-05, + "loss": 3.4504, + "step": 1660928 + }, + { + "epoch": 1.02, + "learning_rate": 2.2799769779534752e-05, + "loss": 3.4702, + "step": 1661440 + }, + { + "epoch": 1.02, + "learning_rate": 2.279140021082796e-05, + "loss": 3.469, + "step": 1661952 + }, + { + "epoch": 1.02, + "learning_rate": 2.2783014263317444e-05, + "loss": 3.4621, + "step": 1662464 + }, + { + "epoch": 1.02, + "learning_rate": 2.2774628315806924e-05, + "loss": 3.4602, + "step": 1662976 + }, + { + "epoch": 1.02, + "learning_rate": 2.2766242368296404e-05, + "loss": 3.4515, + "step": 1663488 + }, + { + "epoch": 1.02, + "learning_rate": 2.2757872799589613e-05, + "loss": 3.4531, + "step": 1664000 + }, + { + "epoch": 1.02, + "learning_rate": 2.2749486852079093e-05, + "loss": 3.45, + "step": 1664512 + }, + { + "epoch": 1.02, + "learning_rate": 2.2741100904568573e-05, + "loss": 3.4519, + "step": 1665024 + }, + { + "epoch": 1.02, + "learning_rate": 2.2732714957058053e-05, + "loss": 3.4549, + "step": 1665536 + }, + { + "epoch": 1.02, + "learning_rate": 2.2724345388351266e-05, + "loss": 3.4572, + "step": 1666048 + }, + { + "epoch": 1.02, + "learning_rate": 2.2715959440840746e-05, + "loss": 3.4546, + "step": 1666560 + }, + { + "epoch": 1.02, + "learning_rate": 2.2707573493330225e-05, + "loss": 3.4528, + "step": 1667072 + }, + { + "epoch": 1.02, + "learning_rate": 2.2699187545819705e-05, + "loss": 3.4553, + "step": 1667584 + }, + { + "epoch": 1.02, + "learning_rate": 2.2690817977112915e-05, + "loss": 3.4522, + "step": 1668096 + }, + { + "epoch": 1.02, + "learning_rate": 2.2682432029602398e-05, + "loss": 3.4538, + "step": 1668608 + }, + { + "epoch": 1.02, + "learning_rate": 2.2674046082091878e-05, + "loss": 3.4582, + "step": 1669120 + }, + { + "epoch": 1.02, + "learning_rate": 2.2665660134581358e-05, + "loss": 3.4662, + "step": 1669632 + }, + { + "epoch": 1.02, + "learning_rate": 2.2657290565874567e-05, + "loss": 3.4619, + "step": 1670144 + }, + { + "epoch": 1.02, + "learning_rate": 2.2648904618364047e-05, + "loss": 3.4524, + "step": 1670656 + }, + { + "epoch": 1.02, + "learning_rate": 2.2640518670853527e-05, + "loss": 3.4604, + "step": 1671168 + }, + { + "epoch": 1.02, + "learning_rate": 2.2632132723343007e-05, + "loss": 3.4534, + "step": 1671680 + }, + { + "epoch": 1.02, + "learning_rate": 2.262376315463622e-05, + "loss": 3.4655, + "step": 1672192 + }, + { + "epoch": 1.02, + "learning_rate": 2.26153772071257e-05, + "loss": 3.4549, + "step": 1672704 + }, + { + "epoch": 1.02, + "learning_rate": 2.260699125961518e-05, + "loss": 3.4574, + "step": 1673216 + }, + { + "epoch": 1.02, + "learning_rate": 2.2598605312104656e-05, + "loss": 3.453, + "step": 1673728 + }, + { + "epoch": 1.02, + "learning_rate": 2.2590235743397868e-05, + "loss": 3.4641, + "step": 1674240 + }, + { + "epoch": 1.02, + "learning_rate": 2.2581849795887348e-05, + "loss": 3.4517, + "step": 1674752 + }, + { + "epoch": 1.02, + "learning_rate": 2.257346384837683e-05, + "loss": 3.4573, + "step": 1675264 + }, + { + "epoch": 1.02, + "learning_rate": 2.2565077900866308e-05, + "loss": 3.4526, + "step": 1675776 + }, + { + "epoch": 1.02, + "learning_rate": 2.255670833215952e-05, + "loss": 3.454, + "step": 1676288 + }, + { + "epoch": 1.02, + "learning_rate": 2.2548322384649e-05, + "loss": 3.4598, + "step": 1676800 + }, + { + "epoch": 1.02, + "learning_rate": 2.2539936437138477e-05, + "loss": 3.4591, + "step": 1677312 + }, + { + "epoch": 1.02, + "learning_rate": 2.253155048962796e-05, + "loss": 3.4632, + "step": 1677824 + }, + { + "epoch": 1.02, + "learning_rate": 2.2523180920921173e-05, + "loss": 3.449, + "step": 1678336 + }, + { + "epoch": 1.02, + "learning_rate": 2.2514794973410653e-05, + "loss": 3.4563, + "step": 1678848 + }, + { + "epoch": 1.03, + "eval_loss": 3.848487377166748, + "eval_runtime": 308.1513, + "eval_samples_per_second": 1238.324, + "eval_steps_per_second": 38.699, + "step": 1679029 + }, + { + "epoch": 0.0, + "learning_rate": 2.250640902590013e-05, + "loss": 3.4524, + "step": 1679360 + }, + { + "epoch": 0.0, + "learning_rate": 2.249802307838961e-05, + "loss": 3.4452, + "step": 1679872 + }, + { + "epoch": 0.0, + "learning_rate": 2.248963713087909e-05, + "loss": 3.4609, + "step": 1680384 + }, + { + "epoch": 0.0, + "learning_rate": 2.248125118336857e-05, + "loss": 3.455, + "step": 1680896 + }, + { + "epoch": 0.0, + "learning_rate": 2.2472881614661782e-05, + "loss": 3.4639, + "step": 1681408 + }, + { + "epoch": 0.0, + "learning_rate": 2.2464495667151262e-05, + "loss": 3.4504, + "step": 1681920 + }, + { + "epoch": 0.0, + "learning_rate": 2.2456109719640742e-05, + "loss": 3.4499, + "step": 1682432 + }, + { + "epoch": 0.0, + "learning_rate": 2.244772377213022e-05, + "loss": 3.4481, + "step": 1682944 + }, + { + "epoch": 0.0, + "learning_rate": 2.243935420342343e-05, + "loss": 3.4544, + "step": 1683456 + }, + { + "epoch": 0.0, + "learning_rate": 2.2430968255912914e-05, + "loss": 3.4529, + "step": 1683968 + }, + { + "epoch": 0.0, + "learning_rate": 2.2422582308402394e-05, + "loss": 3.4559, + "step": 1684480 + }, + { + "epoch": 0.0, + "learning_rate": 2.2414196360891874e-05, + "loss": 3.4627, + "step": 1684992 + }, + { + "epoch": 0.0, + "learning_rate": 2.2405843170988816e-05, + "loss": 3.4401, + "step": 1685504 + }, + { + "epoch": 0.0, + "learning_rate": 2.2397457223478296e-05, + "loss": 3.4487, + "step": 1686016 + }, + { + "epoch": 0.0, + "learning_rate": 2.2389071275967776e-05, + "loss": 3.4545, + "step": 1686528 + }, + { + "epoch": 0.0, + "learning_rate": 2.2380685328457255e-05, + "loss": 3.4376, + "step": 1687040 + }, + { + "epoch": 0.0, + "learning_rate": 2.2372299380946735e-05, + "loss": 3.4479, + "step": 1687552 + }, + { + "epoch": 0.0, + "learning_rate": 2.2363913433436215e-05, + "loss": 3.4508, + "step": 1688064 + }, + { + "epoch": 0.0, + "learning_rate": 2.2355527485925695e-05, + "loss": 3.4453, + "step": 1688576 + }, + { + "epoch": 0.0, + "learning_rate": 2.2347141538415175e-05, + "loss": 3.4693, + "step": 1689088 + }, + { + "epoch": 0.0, + "learning_rate": 2.2338771969708384e-05, + "loss": 3.4551, + "step": 1689600 + }, + { + "epoch": 0.0, + "learning_rate": 2.2330386022197868e-05, + "loss": 3.4539, + "step": 1690112 + }, + { + "epoch": 0.0, + "learning_rate": 2.2322000074687348e-05, + "loss": 3.4541, + "step": 1690624 + }, + { + "epoch": 0.0, + "learning_rate": 2.2313614127176828e-05, + "loss": 3.456, + "step": 1691136 + }, + { + "epoch": 0.0, + "learning_rate": 2.2305244558470037e-05, + "loss": 3.4505, + "step": 1691648 + }, + { + "epoch": 0.0, + "learning_rate": 2.2296858610959517e-05, + "loss": 3.4544, + "step": 1692160 + }, + { + "epoch": 0.0, + "learning_rate": 2.2288472663448997e-05, + "loss": 3.4479, + "step": 1692672 + }, + { + "epoch": 0.0, + "learning_rate": 2.2280086715938477e-05, + "loss": 3.4425, + "step": 1693184 + }, + { + "epoch": 0.0, + "learning_rate": 2.227171714723169e-05, + "loss": 3.4464, + "step": 1693696 + }, + { + "epoch": 0.0, + "learning_rate": 2.226333119972117e-05, + "loss": 3.4494, + "step": 1694208 + }, + { + "epoch": 0.01, + "learning_rate": 2.225494525221065e-05, + "loss": 3.4543, + "step": 1694720 + }, + { + "epoch": 0.01, + "learning_rate": 2.224655930470013e-05, + "loss": 3.4514, + "step": 1695232 + }, + { + "epoch": 0.01, + "learning_rate": 2.2238189735993338e-05, + "loss": 3.455, + "step": 1695744 + }, + { + "epoch": 0.01, + "learning_rate": 2.222980378848282e-05, + "loss": 3.4618, + "step": 1696256 + }, + { + "epoch": 0.01, + "learning_rate": 2.22214178409723e-05, + "loss": 3.4453, + "step": 1696768 + }, + { + "epoch": 0.01, + "learning_rate": 2.221304827226551e-05, + "loss": 3.4531, + "step": 1697280 + }, + { + "epoch": 0.01, + "learning_rate": 2.220466232475499e-05, + "loss": 3.4513, + "step": 1697792 + }, + { + "epoch": 0.01, + "learning_rate": 2.219627637724447e-05, + "loss": 3.4481, + "step": 1698304 + }, + { + "epoch": 0.01, + "learning_rate": 2.218789042973395e-05, + "loss": 3.4387, + "step": 1698816 + }, + { + "epoch": 0.01, + "learning_rate": 2.2179520861027163e-05, + "loss": 3.4462, + "step": 1699328 + }, + { + "epoch": 0.01, + "learning_rate": 2.2171134913516643e-05, + "loss": 3.4472, + "step": 1699840 + }, + { + "epoch": 0.01, + "learning_rate": 2.2162748966006123e-05, + "loss": 3.4525, + "step": 1700352 + }, + { + "epoch": 0.01, + "learning_rate": 2.2154363018495603e-05, + "loss": 3.4496, + "step": 1700864 + }, + { + "epoch": 0.01, + "learning_rate": 2.2145993449788812e-05, + "loss": 3.4467, + "step": 1701376 + }, + { + "epoch": 0.01, + "learning_rate": 2.2137607502278292e-05, + "loss": 3.4661, + "step": 1701888 + }, + { + "epoch": 0.01, + "learning_rate": 2.2129221554767772e-05, + "loss": 3.4509, + "step": 1702400 + }, + { + "epoch": 0.01, + "learning_rate": 2.2120835607257255e-05, + "loss": 3.4522, + "step": 1702912 + }, + { + "epoch": 0.01, + "learning_rate": 2.2112466038550464e-05, + "loss": 3.4421, + "step": 1703424 + }, + { + "epoch": 0.01, + "learning_rate": 2.2104080091039944e-05, + "loss": 3.4346, + "step": 1703936 + }, + { + "epoch": 0.01, + "learning_rate": 2.2095694143529424e-05, + "loss": 3.46, + "step": 1704448 + }, + { + "epoch": 0.01, + "learning_rate": 2.2087308196018904e-05, + "loss": 3.4471, + "step": 1704960 + }, + { + "epoch": 0.01, + "learning_rate": 2.2078938627312116e-05, + "loss": 3.4458, + "step": 1705472 + }, + { + "epoch": 0.01, + "learning_rate": 2.2070552679801596e-05, + "loss": 3.4478, + "step": 1705984 + }, + { + "epoch": 0.01, + "learning_rate": 2.2062166732291076e-05, + "loss": 3.4511, + "step": 1706496 + }, + { + "epoch": 0.01, + "learning_rate": 2.2053780784780553e-05, + "loss": 3.4243, + "step": 1707008 + }, + { + "epoch": 0.01, + "learning_rate": 2.2045411216073765e-05, + "loss": 3.4462, + "step": 1707520 + }, + { + "epoch": 0.01, + "learning_rate": 2.2037025268563245e-05, + "loss": 3.4436, + "step": 1708032 + }, + { + "epoch": 0.01, + "learning_rate": 2.2028639321052725e-05, + "loss": 3.4426, + "step": 1708544 + }, + { + "epoch": 0.01, + "learning_rate": 2.2020253373542205e-05, + "loss": 3.4561, + "step": 1709056 + }, + { + "epoch": 0.01, + "learning_rate": 2.2011883804835418e-05, + "loss": 3.441, + "step": 1709568 + }, + { + "epoch": 0.01, + "learning_rate": 2.2003497857324898e-05, + "loss": 3.4439, + "step": 1710080 + }, + { + "epoch": 0.01, + "learning_rate": 2.1995111909814374e-05, + "loss": 3.4533, + "step": 1710592 + }, + { + "epoch": 0.01, + "learning_rate": 2.1986725962303854e-05, + "loss": 3.4401, + "step": 1711104 + }, + { + "epoch": 0.01, + "learning_rate": 2.197835639359707e-05, + "loss": 3.4365, + "step": 1711616 + }, + { + "epoch": 0.01, + "learning_rate": 2.196997044608655e-05, + "loss": 3.4433, + "step": 1712128 + }, + { + "epoch": 0.01, + "learning_rate": 2.1961584498576027e-05, + "loss": 3.4451, + "step": 1712640 + }, + { + "epoch": 0.01, + "learning_rate": 2.1953198551065507e-05, + "loss": 3.4408, + "step": 1713152 + }, + { + "epoch": 0.01, + "learning_rate": 2.194482898235872e-05, + "loss": 3.4393, + "step": 1713664 + }, + { + "epoch": 0.01, + "learning_rate": 2.19364430348482e-05, + "loss": 3.4297, + "step": 1714176 + }, + { + "epoch": 0.01, + "learning_rate": 2.192805708733768e-05, + "loss": 3.4403, + "step": 1714688 + }, + { + "epoch": 0.01, + "learning_rate": 2.191967113982716e-05, + "loss": 3.4565, + "step": 1715200 + }, + { + "epoch": 0.01, + "learning_rate": 2.191130157112037e-05, + "loss": 3.4437, + "step": 1715712 + }, + { + "epoch": 0.01, + "learning_rate": 2.1902915623609848e-05, + "loss": 3.4572, + "step": 1716224 + }, + { + "epoch": 0.01, + "learning_rate": 2.1894529676099328e-05, + "loss": 3.453, + "step": 1716736 + }, + { + "epoch": 0.01, + "learning_rate": 2.1886143728588808e-05, + "loss": 3.4485, + "step": 1717248 + }, + { + "epoch": 0.01, + "learning_rate": 2.1877774159882024e-05, + "loss": 3.4429, + "step": 1717760 + }, + { + "epoch": 0.01, + "learning_rate": 2.18693882123715e-05, + "loss": 3.4556, + "step": 1718272 + }, + { + "epoch": 0.01, + "learning_rate": 2.186100226486098e-05, + "loss": 3.4426, + "step": 1718784 + }, + { + "epoch": 0.01, + "learning_rate": 2.185261631735046e-05, + "loss": 3.4445, + "step": 1719296 + }, + { + "epoch": 0.01, + "learning_rate": 2.1844246748643673e-05, + "loss": 3.4558, + "step": 1719808 + }, + { + "epoch": 0.01, + "learning_rate": 2.1835860801133153e-05, + "loss": 3.4474, + "step": 1720320 + }, + { + "epoch": 0.01, + "learning_rate": 2.1827474853622633e-05, + "loss": 3.4532, + "step": 1720832 + }, + { + "epoch": 0.01, + "learning_rate": 2.1819088906112113e-05, + "loss": 3.4468, + "step": 1721344 + }, + { + "epoch": 0.01, + "learning_rate": 2.1810719337405322e-05, + "loss": 3.4282, + "step": 1721856 + }, + { + "epoch": 0.01, + "learning_rate": 2.1802333389894802e-05, + "loss": 3.4325, + "step": 1722368 + }, + { + "epoch": 0.01, + "learning_rate": 2.179394744238428e-05, + "loss": 3.4446, + "step": 1722880 + }, + { + "epoch": 0.01, + "learning_rate": 2.178556149487376e-05, + "loss": 3.4468, + "step": 1723392 + }, + { + "epoch": 0.01, + "learning_rate": 2.1777191926166974e-05, + "loss": 3.441, + "step": 1723904 + }, + { + "epoch": 0.01, + "learning_rate": 2.1768805978656454e-05, + "loss": 3.4425, + "step": 1724416 + }, + { + "epoch": 0.02, + "learning_rate": 2.1760420031145934e-05, + "loss": 3.4468, + "step": 1724928 + }, + { + "epoch": 0.02, + "learning_rate": 2.1752034083635414e-05, + "loss": 3.4368, + "step": 1725440 + }, + { + "epoch": 0.02, + "learning_rate": 2.1743664514928623e-05, + "loss": 3.4432, + "step": 1725952 + }, + { + "epoch": 0.02, + "learning_rate": 2.1735278567418106e-05, + "loss": 3.4415, + "step": 1726464 + }, + { + "epoch": 0.02, + "learning_rate": 2.1726892619907586e-05, + "loss": 3.4608, + "step": 1726976 + }, + { + "epoch": 0.02, + "learning_rate": 2.1718506672397066e-05, + "loss": 3.4571, + "step": 1727488 + }, + { + "epoch": 0.02, + "learning_rate": 2.1710137103690275e-05, + "loss": 3.4498, + "step": 1728000 + }, + { + "epoch": 0.02, + "learning_rate": 2.1701751156179755e-05, + "loss": 3.4402, + "step": 1728512 + }, + { + "epoch": 0.02, + "learning_rate": 2.1693365208669235e-05, + "loss": 3.4459, + "step": 1729024 + }, + { + "epoch": 0.02, + "learning_rate": 2.1684979261158715e-05, + "loss": 3.4431, + "step": 1729536 + }, + { + "epoch": 0.02, + "learning_rate": 2.1676609692451928e-05, + "loss": 3.4563, + "step": 1730048 + }, + { + "epoch": 0.02, + "learning_rate": 2.1668223744941408e-05, + "loss": 3.4426, + "step": 1730560 + }, + { + "epoch": 0.02, + "learning_rate": 2.1659837797430888e-05, + "loss": 3.4412, + "step": 1731072 + }, + { + "epoch": 0.02, + "learning_rate": 2.1651451849920368e-05, + "loss": 3.4499, + "step": 1731584 + }, + { + "epoch": 0.02, + "learning_rate": 2.1643082281213577e-05, + "loss": 3.4519, + "step": 1732096 + }, + { + "epoch": 0.02, + "learning_rate": 2.1634696333703057e-05, + "loss": 3.4395, + "step": 1732608 + }, + { + "epoch": 0.02, + "learning_rate": 2.162631038619254e-05, + "loss": 3.4474, + "step": 1733120 + }, + { + "epoch": 0.02, + "learning_rate": 2.161792443868202e-05, + "loss": 3.4383, + "step": 1733632 + }, + { + "epoch": 0.02, + "learning_rate": 2.160955486997523e-05, + "loss": 3.4375, + "step": 1734144 + }, + { + "epoch": 0.02, + "learning_rate": 2.160116892246471e-05, + "loss": 3.4267, + "step": 1734656 + }, + { + "epoch": 0.02, + "learning_rate": 2.159278297495419e-05, + "loss": 3.4458, + "step": 1735168 + }, + { + "epoch": 0.02, + "learning_rate": 2.158439702744367e-05, + "loss": 3.443, + "step": 1735680 + }, + { + "epoch": 0.02, + "learning_rate": 2.157602745873688e-05, + "loss": 3.4418, + "step": 1736192 + }, + { + "epoch": 0.02, + "learning_rate": 2.156764151122636e-05, + "loss": 3.4417, + "step": 1736704 + }, + { + "epoch": 0.02, + "learning_rate": 2.155925556371584e-05, + "loss": 3.4389, + "step": 1737216 + }, + { + "epoch": 0.02, + "learning_rate": 2.155086961620532e-05, + "loss": 3.4545, + "step": 1737728 + }, + { + "epoch": 0.02, + "learning_rate": 2.154250004749853e-05, + "loss": 3.4609, + "step": 1738240 + }, + { + "epoch": 0.02, + "learning_rate": 2.153411409998801e-05, + "loss": 3.451, + "step": 1738752 + }, + { + "epoch": 0.02, + "learning_rate": 2.1525728152477494e-05, + "loss": 3.448, + "step": 1739264 + }, + { + "epoch": 0.02, + "learning_rate": 2.1517342204966974e-05, + "loss": 3.4423, + "step": 1739776 + }, + { + "epoch": 0.02, + "learning_rate": 2.1508972636260183e-05, + "loss": 3.4405, + "step": 1740288 + }, + { + "epoch": 0.02, + "learning_rate": 2.1500586688749663e-05, + "loss": 3.4347, + "step": 1740800 + }, + { + "epoch": 0.02, + "learning_rate": 2.1492200741239143e-05, + "loss": 3.4433, + "step": 1741312 + }, + { + "epoch": 0.02, + "learning_rate": 2.1483814793728623e-05, + "loss": 3.443, + "step": 1741824 + }, + { + "epoch": 0.02, + "learning_rate": 2.1475445225021835e-05, + "loss": 3.4432, + "step": 1742336 + }, + { + "epoch": 0.02, + "learning_rate": 2.1467059277511315e-05, + "loss": 3.4496, + "step": 1742848 + }, + { + "epoch": 0.02, + "learning_rate": 2.1458673330000795e-05, + "loss": 3.4377, + "step": 1743360 + }, + { + "epoch": 0.02, + "learning_rate": 2.1450287382490275e-05, + "loss": 3.451, + "step": 1743872 + }, + { + "epoch": 0.02, + "learning_rate": 2.1441917813783484e-05, + "loss": 3.4372, + "step": 1744384 + }, + { + "epoch": 0.02, + "learning_rate": 2.1433531866272964e-05, + "loss": 3.4467, + "step": 1744896 + }, + { + "epoch": 0.02, + "learning_rate": 2.1425145918762447e-05, + "loss": 3.4433, + "step": 1745408 + }, + { + "epoch": 0.02, + "learning_rate": 2.1416759971251924e-05, + "loss": 3.4543, + "step": 1745920 + }, + { + "epoch": 0.02, + "learning_rate": 2.1408390402545136e-05, + "loss": 3.45, + "step": 1746432 + }, + { + "epoch": 0.02, + "learning_rate": 2.1400004455034616e-05, + "loss": 3.4422, + "step": 1746944 + }, + { + "epoch": 0.02, + "learning_rate": 2.1391618507524096e-05, + "loss": 3.4498, + "step": 1747456 + }, + { + "epoch": 0.02, + "learning_rate": 2.1383232560013576e-05, + "loss": 3.4449, + "step": 1747968 + }, + { + "epoch": 0.02, + "learning_rate": 2.137486299130679e-05, + "loss": 3.4506, + "step": 1748480 + }, + { + "epoch": 0.02, + "learning_rate": 2.136647704379627e-05, + "loss": 3.4424, + "step": 1748992 + }, + { + "epoch": 0.02, + "learning_rate": 2.1358091096285745e-05, + "loss": 3.4504, + "step": 1749504 + }, + { + "epoch": 0.02, + "learning_rate": 2.1349705148775225e-05, + "loss": 3.4415, + "step": 1750016 + }, + { + "epoch": 0.02, + "learning_rate": 2.1341335580068438e-05, + "loss": 3.4514, + "step": 1750528 + }, + { + "epoch": 0.02, + "learning_rate": 2.1332949632557918e-05, + "loss": 3.4397, + "step": 1751040 + }, + { + "epoch": 0.02, + "learning_rate": 2.1324563685047398e-05, + "loss": 3.4466, + "step": 1751552 + }, + { + "epoch": 0.02, + "learning_rate": 2.1316177737536878e-05, + "loss": 3.447, + "step": 1752064 + }, + { + "epoch": 0.02, + "learning_rate": 2.130780816883009e-05, + "loss": 3.4445, + "step": 1752576 + }, + { + "epoch": 0.02, + "learning_rate": 2.129942222131957e-05, + "loss": 3.4454, + "step": 1753088 + }, + { + "epoch": 0.02, + "learning_rate": 2.1291036273809047e-05, + "loss": 3.4455, + "step": 1753600 + }, + { + "epoch": 0.02, + "learning_rate": 2.128265032629853e-05, + "loss": 3.4524, + "step": 1754112 + }, + { + "epoch": 0.02, + "learning_rate": 2.1274280757591742e-05, + "loss": 3.4342, + "step": 1754624 + }, + { + "epoch": 0.02, + "learning_rate": 2.126589481008122e-05, + "loss": 3.4495, + "step": 1755136 + }, + { + "epoch": 0.03, + "eval_loss": 3.8494338989257812, + "eval_runtime": 305.6096, + "eval_samples_per_second": 1248.623, + "eval_steps_per_second": 39.02, + "step": 1755349 + }, + { + "epoch": 1.0, + "learning_rate": 2.12575088625707e-05, + "loss": 3.4426, + "step": 1755648 + }, + { + "epoch": 1.0, + "learning_rate": 2.124912291506018e-05, + "loss": 3.4359, + "step": 1756160 + }, + { + "epoch": 1.0, + "learning_rate": 2.124075334635339e-05, + "loss": 3.4488, + "step": 1756672 + }, + { + "epoch": 1.0, + "learning_rate": 2.123236739884287e-05, + "loss": 3.4442, + "step": 1757184 + }, + { + "epoch": 1.0, + "learning_rate": 2.122398145133235e-05, + "loss": 3.4533, + "step": 1757696 + }, + { + "epoch": 1.0, + "learning_rate": 2.121559550382183e-05, + "loss": 3.4402, + "step": 1758208 + }, + { + "epoch": 1.0, + "learning_rate": 2.1207225935115044e-05, + "loss": 3.4407, + "step": 1758720 + }, + { + "epoch": 1.0, + "learning_rate": 2.119883998760452e-05, + "loss": 3.4391, + "step": 1759232 + }, + { + "epoch": 1.0, + "learning_rate": 2.1190454040094e-05, + "loss": 3.4454, + "step": 1759744 + }, + { + "epoch": 1.0, + "learning_rate": 2.118206809258348e-05, + "loss": 3.4378, + "step": 1760256 + }, + { + "epoch": 1.0, + "learning_rate": 2.1173698523876693e-05, + "loss": 3.4498, + "step": 1760768 + }, + { + "epoch": 1.0, + "learning_rate": 2.1165312576366173e-05, + "loss": 3.4476, + "step": 1761280 + }, + { + "epoch": 1.0, + "learning_rate": 2.1156943007659385e-05, + "loss": 3.4339, + "step": 1761792 + }, + { + "epoch": 1.0, + "learning_rate": 2.1148557060148865e-05, + "loss": 3.4311, + "step": 1762304 + }, + { + "epoch": 1.0, + "learning_rate": 2.114017111263834e-05, + "loss": 3.443, + "step": 1762816 + }, + { + "epoch": 1.0, + "learning_rate": 2.1131785165127825e-05, + "loss": 3.43, + "step": 1763328 + }, + { + "epoch": 1.0, + "learning_rate": 2.1123399217617305e-05, + "loss": 3.4358, + "step": 1763840 + }, + { + "epoch": 1.0, + "learning_rate": 2.1115013270106785e-05, + "loss": 3.4349, + "step": 1764352 + }, + { + "epoch": 1.0, + "learning_rate": 2.1106627322596265e-05, + "loss": 3.4382, + "step": 1764864 + }, + { + "epoch": 1.0, + "learning_rate": 2.1098241375085745e-05, + "loss": 3.453, + "step": 1765376 + }, + { + "epoch": 1.0, + "learning_rate": 2.1089871806378954e-05, + "loss": 3.4484, + "step": 1765888 + }, + { + "epoch": 1.0, + "learning_rate": 2.1081485858868434e-05, + "loss": 3.4412, + "step": 1766400 + }, + { + "epoch": 1.0, + "learning_rate": 2.1073099911357917e-05, + "loss": 3.4419, + "step": 1766912 + }, + { + "epoch": 1.0, + "learning_rate": 2.1064713963847397e-05, + "loss": 3.4421, + "step": 1767424 + }, + { + "epoch": 1.0, + "learning_rate": 2.1056344395140606e-05, + "loss": 3.4352, + "step": 1767936 + }, + { + "epoch": 1.0, + "learning_rate": 2.1047958447630086e-05, + "loss": 3.4462, + "step": 1768448 + }, + { + "epoch": 1.0, + "learning_rate": 2.1039572500119566e-05, + "loss": 3.437, + "step": 1768960 + }, + { + "epoch": 1.0, + "learning_rate": 2.1031186552609046e-05, + "loss": 3.4317, + "step": 1769472 + }, + { + "epoch": 1.0, + "learning_rate": 2.102281698390226e-05, + "loss": 3.4359, + "step": 1769984 + }, + { + "epoch": 1.0, + "learning_rate": 2.101443103639174e-05, + "loss": 3.4425, + "step": 1770496 + }, + { + "epoch": 1.01, + "learning_rate": 2.100604508888122e-05, + "loss": 3.4399, + "step": 1771008 + }, + { + "epoch": 1.01, + "learning_rate": 2.09976591413707e-05, + "loss": 3.4416, + "step": 1771520 + }, + { + "epoch": 1.01, + "learning_rate": 2.0989289572663908e-05, + "loss": 3.4471, + "step": 1772032 + }, + { + "epoch": 1.01, + "learning_rate": 2.0980903625153388e-05, + "loss": 3.4485, + "step": 1772544 + }, + { + "epoch": 1.01, + "learning_rate": 2.097251767764287e-05, + "loss": 3.4312, + "step": 1773056 + }, + { + "epoch": 1.01, + "learning_rate": 2.0964131730132347e-05, + "loss": 3.4434, + "step": 1773568 + }, + { + "epoch": 1.01, + "learning_rate": 2.095576216142556e-05, + "loss": 3.4417, + "step": 1774080 + }, + { + "epoch": 1.01, + "learning_rate": 2.094737621391504e-05, + "loss": 3.4363, + "step": 1774592 + }, + { + "epoch": 1.01, + "learning_rate": 2.093899026640452e-05, + "loss": 3.4281, + "step": 1775104 + }, + { + "epoch": 1.01, + "learning_rate": 2.0930604318894e-05, + "loss": 3.4336, + "step": 1775616 + }, + { + "epoch": 1.01, + "learning_rate": 2.0922234750187212e-05, + "loss": 3.4368, + "step": 1776128 + }, + { + "epoch": 1.01, + "learning_rate": 2.0913848802676692e-05, + "loss": 3.4407, + "step": 1776640 + }, + { + "epoch": 1.01, + "learning_rate": 2.0905462855166172e-05, + "loss": 3.4381, + "step": 1777152 + }, + { + "epoch": 1.01, + "learning_rate": 2.089707690765565e-05, + "loss": 3.4354, + "step": 1777664 + }, + { + "epoch": 1.01, + "learning_rate": 2.088870733894886e-05, + "loss": 3.4535, + "step": 1778176 + }, + { + "epoch": 1.01, + "learning_rate": 2.088032139143834e-05, + "loss": 3.4442, + "step": 1778688 + }, + { + "epoch": 1.01, + "learning_rate": 2.087193544392782e-05, + "loss": 3.4448, + "step": 1779200 + }, + { + "epoch": 1.01, + "learning_rate": 2.08635494964173e-05, + "loss": 3.4302, + "step": 1779712 + }, + { + "epoch": 1.01, + "learning_rate": 2.0855179927710514e-05, + "loss": 3.4213, + "step": 1780224 + }, + { + "epoch": 1.01, + "learning_rate": 2.0846793980199994e-05, + "loss": 3.4497, + "step": 1780736 + }, + { + "epoch": 1.01, + "learning_rate": 2.083840803268947e-05, + "loss": 3.4336, + "step": 1781248 + }, + { + "epoch": 1.01, + "learning_rate": 2.0830022085178954e-05, + "loss": 3.4349, + "step": 1781760 + }, + { + "epoch": 1.01, + "learning_rate": 2.0821652516472166e-05, + "loss": 3.4403, + "step": 1782272 + }, + { + "epoch": 1.01, + "learning_rate": 2.0813266568961646e-05, + "loss": 3.4349, + "step": 1782784 + }, + { + "epoch": 1.01, + "learning_rate": 2.0804880621451123e-05, + "loss": 3.4195, + "step": 1783296 + }, + { + "epoch": 1.01, + "learning_rate": 2.0796494673940602e-05, + "loss": 3.4299, + "step": 1783808 + }, + { + "epoch": 1.01, + "learning_rate": 2.0788125105233815e-05, + "loss": 3.4342, + "step": 1784320 + }, + { + "epoch": 1.01, + "learning_rate": 2.0779739157723295e-05, + "loss": 3.434, + "step": 1784832 + }, + { + "epoch": 1.01, + "learning_rate": 2.0771353210212775e-05, + "loss": 3.4417, + "step": 1785344 + }, + { + "epoch": 1.01, + "learning_rate": 2.0762967262702255e-05, + "loss": 3.432, + "step": 1785856 + }, + { + "epoch": 1.01, + "learning_rate": 2.0754597693995467e-05, + "loss": 3.4333, + "step": 1786368 + }, + { + "epoch": 1.01, + "learning_rate": 2.0746211746484944e-05, + "loss": 3.4443, + "step": 1786880 + }, + { + "epoch": 1.01, + "learning_rate": 2.0737825798974424e-05, + "loss": 3.4266, + "step": 1787392 + }, + { + "epoch": 1.01, + "learning_rate": 2.0729439851463904e-05, + "loss": 3.4313, + "step": 1787904 + }, + { + "epoch": 1.01, + "learning_rate": 2.0721070282757116e-05, + "loss": 3.4327, + "step": 1788416 + }, + { + "epoch": 1.01, + "learning_rate": 2.0712684335246596e-05, + "loss": 3.4317, + "step": 1788928 + }, + { + "epoch": 1.01, + "learning_rate": 2.0704298387736076e-05, + "loss": 3.429, + "step": 1789440 + }, + { + "epoch": 1.01, + "learning_rate": 2.0695912440225556e-05, + "loss": 3.4323, + "step": 1789952 + }, + { + "epoch": 1.01, + "learning_rate": 2.0687542871518765e-05, + "loss": 3.4169, + "step": 1790464 + }, + { + "epoch": 1.01, + "learning_rate": 2.067915692400825e-05, + "loss": 3.4285, + "step": 1790976 + }, + { + "epoch": 1.01, + "learning_rate": 2.067077097649773e-05, + "loss": 3.4484, + "step": 1791488 + }, + { + "epoch": 1.01, + "learning_rate": 2.066238502898721e-05, + "loss": 3.4291, + "step": 1792000 + }, + { + "epoch": 1.01, + "learning_rate": 2.0654015460280418e-05, + "loss": 3.4516, + "step": 1792512 + }, + { + "epoch": 1.01, + "learning_rate": 2.0645629512769898e-05, + "loss": 3.4386, + "step": 1793024 + }, + { + "epoch": 1.01, + "learning_rate": 2.0637243565259377e-05, + "loss": 3.443, + "step": 1793536 + }, + { + "epoch": 1.01, + "learning_rate": 2.062887399655259e-05, + "loss": 3.431, + "step": 1794048 + }, + { + "epoch": 1.01, + "learning_rate": 2.062048804904207e-05, + "loss": 3.4413, + "step": 1794560 + }, + { + "epoch": 1.01, + "learning_rate": 2.061210210153155e-05, + "loss": 3.436, + "step": 1795072 + }, + { + "epoch": 1.01, + "learning_rate": 2.060371615402103e-05, + "loss": 3.4303, + "step": 1795584 + }, + { + "epoch": 1.01, + "learning_rate": 2.059534658531424e-05, + "loss": 3.4502, + "step": 1796096 + }, + { + "epoch": 1.01, + "learning_rate": 2.058696063780372e-05, + "loss": 3.4345, + "step": 1796608 + }, + { + "epoch": 1.01, + "learning_rate": 2.0578574690293202e-05, + "loss": 3.4396, + "step": 1797120 + }, + { + "epoch": 1.01, + "learning_rate": 2.0570188742782682e-05, + "loss": 3.4393, + "step": 1797632 + }, + { + "epoch": 1.01, + "learning_rate": 2.056181917407589e-05, + "loss": 3.4174, + "step": 1798144 + }, + { + "epoch": 1.01, + "learning_rate": 2.055343322656537e-05, + "loss": 3.4201, + "step": 1798656 + }, + { + "epoch": 1.01, + "learning_rate": 2.054504727905485e-05, + "loss": 3.4298, + "step": 1799168 + }, + { + "epoch": 1.01, + "learning_rate": 2.053666133154433e-05, + "loss": 3.4371, + "step": 1799680 + }, + { + "epoch": 1.01, + "learning_rate": 2.0528291762837544e-05, + "loss": 3.4314, + "step": 1800192 + }, + { + "epoch": 1.01, + "learning_rate": 2.0519905815327024e-05, + "loss": 3.4331, + "step": 1800704 + }, + { + "epoch": 1.02, + "learning_rate": 2.0511519867816504e-05, + "loss": 3.4337, + "step": 1801216 + }, + { + "epoch": 1.02, + "learning_rate": 2.0503133920305984e-05, + "loss": 3.4283, + "step": 1801728 + }, + { + "epoch": 1.02, + "learning_rate": 2.0494764351599193e-05, + "loss": 3.4314, + "step": 1802240 + }, + { + "epoch": 1.02, + "learning_rate": 2.0486378404088673e-05, + "loss": 3.4282, + "step": 1802752 + }, + { + "epoch": 1.02, + "learning_rate": 2.0477992456578156e-05, + "loss": 3.4494, + "step": 1803264 + }, + { + "epoch": 1.02, + "learning_rate": 2.0469606509067636e-05, + "loss": 3.4525, + "step": 1803776 + }, + { + "epoch": 1.02, + "learning_rate": 2.0461236940360845e-05, + "loss": 3.436, + "step": 1804288 + }, + { + "epoch": 1.02, + "learning_rate": 2.0452850992850325e-05, + "loss": 3.426, + "step": 1804800 + }, + { + "epoch": 1.02, + "learning_rate": 2.0444465045339805e-05, + "loss": 3.4364, + "step": 1805312 + }, + { + "epoch": 1.02, + "learning_rate": 2.0436079097829285e-05, + "loss": 3.4313, + "step": 1805824 + }, + { + "epoch": 1.02, + "learning_rate": 2.0427709529122497e-05, + "loss": 3.4433, + "step": 1806336 + }, + { + "epoch": 1.02, + "learning_rate": 2.0419323581611977e-05, + "loss": 3.4323, + "step": 1806848 + }, + { + "epoch": 1.02, + "learning_rate": 2.0410937634101457e-05, + "loss": 3.4314, + "step": 1807360 + }, + { + "epoch": 1.02, + "learning_rate": 2.0402551686590937e-05, + "loss": 3.438, + "step": 1807872 + }, + { + "epoch": 1.02, + "learning_rate": 2.0394182117884146e-05, + "loss": 3.4415, + "step": 1808384 + }, + { + "epoch": 1.02, + "learning_rate": 2.0385796170373626e-05, + "loss": 3.4266, + "step": 1808896 + }, + { + "epoch": 1.02, + "learning_rate": 2.037741022286311e-05, + "loss": 3.4359, + "step": 1809408 + }, + { + "epoch": 1.02, + "learning_rate": 2.036902427535259e-05, + "loss": 3.4295, + "step": 1809920 + }, + { + "epoch": 1.02, + "learning_rate": 2.03606547066458e-05, + "loss": 3.4269, + "step": 1810432 + }, + { + "epoch": 1.02, + "learning_rate": 2.035226875913528e-05, + "loss": 3.4234, + "step": 1810944 + }, + { + "epoch": 1.02, + "learning_rate": 2.034388281162476e-05, + "loss": 3.4307, + "step": 1811456 + }, + { + "epoch": 1.02, + "learning_rate": 2.033549686411424e-05, + "loss": 3.4356, + "step": 1811968 + }, + { + "epoch": 1.02, + "learning_rate": 2.032712729540745e-05, + "loss": 3.4271, + "step": 1812480 + }, + { + "epoch": 1.02, + "learning_rate": 2.031874134789693e-05, + "loss": 3.4341, + "step": 1812992 + }, + { + "epoch": 1.02, + "learning_rate": 2.031035540038641e-05, + "loss": 3.4321, + "step": 1813504 + }, + { + "epoch": 1.02, + "learning_rate": 2.030196945287589e-05, + "loss": 3.4414, + "step": 1814016 + }, + { + "epoch": 1.02, + "learning_rate": 2.02935998841691e-05, + "loss": 3.4484, + "step": 1814528 + }, + { + "epoch": 1.02, + "learning_rate": 2.028521393665858e-05, + "loss": 3.4413, + "step": 1815040 + }, + { + "epoch": 1.02, + "learning_rate": 2.0276827989148063e-05, + "loss": 3.4364, + "step": 1815552 + }, + { + "epoch": 1.02, + "learning_rate": 2.0268442041637543e-05, + "loss": 3.4282, + "step": 1816064 + }, + { + "epoch": 1.02, + "learning_rate": 2.0260072472930752e-05, + "loss": 3.4326, + "step": 1816576 + }, + { + "epoch": 1.02, + "learning_rate": 2.0251686525420232e-05, + "loss": 3.4236, + "step": 1817088 + }, + { + "epoch": 1.02, + "learning_rate": 2.0243300577909712e-05, + "loss": 3.4304, + "step": 1817600 + }, + { + "epoch": 1.02, + "learning_rate": 2.023491463039919e-05, + "loss": 3.4347, + "step": 1818112 + }, + { + "epoch": 1.02, + "learning_rate": 2.0226545061692405e-05, + "loss": 3.432, + "step": 1818624 + }, + { + "epoch": 1.02, + "learning_rate": 2.0218159114181885e-05, + "loss": 3.4334, + "step": 1819136 + }, + { + "epoch": 1.02, + "learning_rate": 2.0209773166671365e-05, + "loss": 3.4287, + "step": 1819648 + }, + { + "epoch": 1.02, + "learning_rate": 2.020138721916084e-05, + "loss": 3.4443, + "step": 1820160 + }, + { + "epoch": 1.02, + "learning_rate": 2.0193017650454054e-05, + "loss": 3.4294, + "step": 1820672 + }, + { + "epoch": 1.02, + "learning_rate": 2.0184631702943534e-05, + "loss": 3.432, + "step": 1821184 + }, + { + "epoch": 1.02, + "learning_rate": 2.0176245755433017e-05, + "loss": 3.4332, + "step": 1821696 + }, + { + "epoch": 1.02, + "learning_rate": 2.0167859807922493e-05, + "loss": 3.4376, + "step": 1822208 + }, + { + "epoch": 1.02, + "learning_rate": 2.0159490239215706e-05, + "loss": 3.4425, + "step": 1822720 + }, + { + "epoch": 1.02, + "learning_rate": 2.0151104291705186e-05, + "loss": 3.4318, + "step": 1823232 + }, + { + "epoch": 1.02, + "learning_rate": 2.0142718344194662e-05, + "loss": 3.4396, + "step": 1823744 + }, + { + "epoch": 1.02, + "learning_rate": 2.0134332396684142e-05, + "loss": 3.4345, + "step": 1824256 + }, + { + "epoch": 1.02, + "learning_rate": 2.012596282797736e-05, + "loss": 3.4417, + "step": 1824768 + }, + { + "epoch": 1.02, + "learning_rate": 2.0117576880466838e-05, + "loss": 3.4295, + "step": 1825280 + }, + { + "epoch": 1.02, + "learning_rate": 2.0109190932956315e-05, + "loss": 3.4399, + "step": 1825792 + }, + { + "epoch": 1.02, + "learning_rate": 2.0100804985445795e-05, + "loss": 3.4304, + "step": 1826304 + }, + { + "epoch": 1.02, + "learning_rate": 2.0092435416739007e-05, + "loss": 3.4427, + "step": 1826816 + }, + { + "epoch": 1.02, + "learning_rate": 2.0084049469228487e-05, + "loss": 3.425, + "step": 1827328 + }, + { + "epoch": 1.02, + "learning_rate": 2.0075663521717967e-05, + "loss": 3.4378, + "step": 1827840 + }, + { + "epoch": 1.02, + "learning_rate": 2.0067277574207447e-05, + "loss": 3.4356, + "step": 1828352 + }, + { + "epoch": 1.02, + "learning_rate": 2.005890800550066e-05, + "loss": 3.4323, + "step": 1828864 + }, + { + "epoch": 1.02, + "learning_rate": 2.0050522057990136e-05, + "loss": 3.4325, + "step": 1829376 + }, + { + "epoch": 1.02, + "learning_rate": 2.0042136110479616e-05, + "loss": 3.4362, + "step": 1829888 + }, + { + "epoch": 1.02, + "learning_rate": 2.0033750162969096e-05, + "loss": 3.4431, + "step": 1830400 + }, + { + "epoch": 1.02, + "learning_rate": 2.0025380594262312e-05, + "loss": 3.4254, + "step": 1830912 + }, + { + "epoch": 1.02, + "learning_rate": 2.001699464675179e-05, + "loss": 3.4402, + "step": 1831424 + }, + { + "epoch": 1.03, + "eval_loss": 3.8512802124023438, + "eval_runtime": 305.509, + "eval_samples_per_second": 1249.034, + "eval_steps_per_second": 39.033, + "step": 1831669 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.274182763417561e+18, + "trial_name": null, + "trial_params": null +}