diff --git "a/checkpoint-1068480/trainer_state.json" "b/checkpoint-1068480/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-1068480/trainer_state.json" @@ -0,0 +1,12653 @@ +{ + "best_metric": 4.028215408325195, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/binding-reconstruction/lstm/2/checkpoints/checkpoint-1068480", + "epoch": 0.025000606015738065, + "eval_steps": 10, + "global_step": 1068480, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 4.999998362119627e-05, + "loss": 10.8201, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 7.5498, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 7.0599, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 6.9942, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 6.9508, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 6.9339, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 6.7931, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 6.6876, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 6.5759, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 6.4872, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 6.4115, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 6.3432, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 6.2727, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989098268236324e-05, + "loss": 6.2001, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988259673485272e-05, + "loss": 6.1494, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.98742107873422e-05, + "loss": 6.088, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986582483983168e-05, + "loss": 6.0543, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985743889232116e-05, + "loss": 6.0135, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984905294481064e-05, + "loss": 5.964, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984066699730012e-05, + "loss": 5.9333, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.9832281049789595e-05, + "loss": 5.8943, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.982391148108281e-05, + "loss": 5.8629, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.981552553357229e-05, + "loss": 5.8341, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.980713958606178e-05, + "loss": 5.799, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.979875363855125e-05, + "loss": 5.7818, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790384069844466e-05, + "loss": 5.7427, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9781998122333946e-05, + "loss": 5.724, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 5.6992, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 5.6708, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756856658606115e-05, + "loss": 5.6427, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748470711095595e-05, + "loss": 5.628, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.974008476358507e-05, + "loss": 5.6165, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.973169881607455e-05, + "loss": 5.5902, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.972331286856403e-05, + "loss": 5.5703, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.9714943299857244e-05, + "loss": 5.5623, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.9706557352346724e-05, + "loss": 5.5499, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.9698171404836204e-05, + "loss": 5.5244, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.9689785457325684e-05, + "loss": 5.4912, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.96814158886189e-05, + "loss": 5.4869, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967302994110837e-05, + "loss": 5.4558, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966464399359785e-05, + "loss": 5.4597, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965625804608733e-05, + "loss": 5.4433, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964787209857681e-05, + "loss": 5.4402, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 5.4115, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.96311165823595e-05, + "loss": 5.4087, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962273063484898e-05, + "loss": 5.3948, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.961434468733847e-05, + "loss": 5.3876, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960595873982795e-05, + "loss": 5.3831, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959757279231743e-05, + "loss": 5.3484, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.958920322361064e-05, + "loss": 5.3462, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958081727610012e-05, + "loss": 5.3518, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.95724313285896e-05, + "loss": 5.342, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956404538107908e-05, + "loss": 5.316, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.955565943356856e-05, + "loss": 5.302, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.954727348605804e-05, + "loss": 5.295, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.953888753854752e-05, + "loss": 5.2869, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530501591037e-05, + "loss": 5.2978, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522132022330207e-05, + "loss": 5.2579, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.9513746074819686e-05, + "loss": 5.2679, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.9505360127309166e-05, + "loss": 5.2568, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.9496974179798646e-05, + "loss": 5.2416, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948860461109186e-05, + "loss": 5.2421, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.948021866358134e-05, + "loss": 5.2162, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947183271607082e-05, + "loss": 5.2111, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.94634467685603e-05, + "loss": 5.2091, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945506082104978e-05, + "loss": 5.2213, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.9446674873539255e-05, + "loss": 5.1899, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943830530483247e-05, + "loss": 5.1855, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942991935732195e-05, + "loss": 5.1659, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.942154978861516e-05, + "loss": 5.1728, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.941316384110464e-05, + "loss": 5.1737, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.940477789359412e-05, + "loss": 5.173, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.93963919460836e-05, + "loss": 5.1481, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.938800599857309e-05, + "loss": 5.1614, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.937962005106256e-05, + "loss": 5.1616, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.937123410355204e-05, + "loss": 5.137, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.936284815604152e-05, + "loss": 5.1237, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.9354462208531e-05, + "loss": 5.1148, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.934607626102048e-05, + "loss": 5.1051, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.933769031350996e-05, + "loss": 5.115, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.932932074480317e-05, + "loss": 5.094, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.932093479729265e-05, + "loss": 5.1093, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931254884978213e-05, + "loss": 5.1004, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930416290227161e-05, + "loss": 5.0834, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.9295793333564825e-05, + "loss": 5.0687, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.9287407386054305e-05, + "loss": 5.0701, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.9279021438543785e-05, + "loss": 5.0704, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.9270635491033264e-05, + "loss": 5.0734, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.9262265922326474e-05, + "loss": 5.0538, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.9253879974815954e-05, + "loss": 5.0525, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.9245494027305433e-05, + "loss": 5.0475, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.9237108079794913e-05, + "loss": 5.0327, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922872213228439e-05, + "loss": 5.0302, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.922033618477387e-05, + "loss": 5.0289, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921195023726335e-05, + "loss": 5.0215, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920358066855656e-05, + "loss": 5.0198, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919519472104604e-05, + "loss": 5.0081, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918680877353552e-05, + "loss": 5.0, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.917842282602501e-05, + "loss": 5.0063, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.917005325731822e-05, + "loss": 5.0027, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.91616673098077e-05, + "loss": 4.9949, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.915328136229718e-05, + "loss": 4.9887, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914489541478666e-05, + "loss": 4.9799, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.913650946727614e-05, + "loss": 4.9733, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.912812351976562e-05, + "loss": 4.9706, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.911973757225509e-05, + "loss": 4.9495, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.911136800354831e-05, + "loss": 4.956, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910298205603779e-05, + "loss": 4.9538, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.909459610852727e-05, + "loss": 4.9565, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908621016101675e-05, + "loss": 4.9432, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907784059230996e-05, + "loss": 4.9485, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.906945464479944e-05, + "loss": 4.9257, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906106869728892e-05, + "loss": 4.9447, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.9052682749778396e-05, + "loss": 4.9158, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.9044296802267876e-05, + "loss": 4.9247, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.9035910854757356e-05, + "loss": 4.9254, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.9027524907246836e-05, + "loss": 4.9212, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.9019155338540045e-05, + "loss": 4.9159, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.9010769391029525e-05, + "loss": 4.905, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.9002383443519005e-05, + "loss": 4.9099, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8993997496008485e-05, + "loss": 4.9127, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985611548497965e-05, + "loss": 4.8943, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977225600987445e-05, + "loss": 4.8905, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968839653476924e-05, + "loss": 4.8884, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.896045370596641e-05, + "loss": 4.8997, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.895206775845589e-05, + "loss": 4.8673, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.894368181094537e-05, + "loss": 4.8726, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.893529586343485e-05, + "loss": 4.8656, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.892690991592433e-05, + "loss": 4.8726, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.891854034721754e-05, + "loss": 4.8593, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.891015439970702e-05, + "loss": 4.8761, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890178483100023e-05, + "loss": 4.8647, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889339888348971e-05, + "loss": 4.8569, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888501293597919e-05, + "loss": 4.8479, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.887662698846867e-05, + "loss": 4.8545, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886824104095815e-05, + "loss": 4.8516, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885985509344763e-05, + "loss": 4.8519, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.8851485524740845e-05, + "loss": 4.8393, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.8843099577230325e-05, + "loss": 4.8479, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.8834713629719805e-05, + "loss": 4.8377, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882632768220928e-05, + "loss": 4.8364, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881794173469876e-05, + "loss": 4.8176, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.880955578718824e-05, + "loss": 4.8354, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880116983967772e-05, + "loss": 4.8176, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879280027097093e-05, + "loss": 4.801, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878441432346041e-05, + "loss": 4.825, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877602837594989e-05, + "loss": 4.813, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.87676588072431e-05, + "loss": 4.8115, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875927285973258e-05, + "loss": 4.8095, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875088691222206e-05, + "loss": 4.7955, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.762204647064209, + "eval_runtime": 290.7203, + "eval_samples_per_second": 1312.571, + "eval_steps_per_second": 41.019, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.874250096471154e-05, + "loss": 4.7789, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.873411501720102e-05, + "loss": 4.7873, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.87257290696905e-05, + "loss": 4.8041, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.871734312217998e-05, + "loss": 4.7882, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.870895717466946e-05, + "loss": 4.7936, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.870058760596267e-05, + "loss": 4.7799, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.869220165845215e-05, + "loss": 4.7821, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.868381571094163e-05, + "loss": 4.7677, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.867542976343111e-05, + "loss": 4.7698, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.866704381592059e-05, + "loss": 4.7708, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.865865786841007e-05, + "loss": 4.7822, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.865028829970329e-05, + "loss": 4.7764, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.864190235219277e-05, + "loss": 4.7596, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.863351640468225e-05, + "loss": 4.7535, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.862513045717173e-05, + "loss": 4.743, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.8616760888464936e-05, + "loss": 4.7467, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.8608374940954416e-05, + "loss": 4.7568, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.8599988993443896e-05, + "loss": 4.7435, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.8591603045933376e-05, + "loss": 4.7404, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.8583217098422856e-05, + "loss": 4.757, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.8574831150912336e-05, + "loss": 4.7429, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.8566461582205545e-05, + "loss": 4.7376, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.8558075634695025e-05, + "loss": 4.7371, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.8549689687184505e-05, + "loss": 4.7518, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.8541303739673985e-05, + "loss": 4.7228, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.8532917792163465e-05, + "loss": 4.7272, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.8524531844652945e-05, + "loss": 4.7331, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.8516145897142425e-05, + "loss": 4.7233, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.8507759949631905e-05, + "loss": 4.7088, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.8499390380925114e-05, + "loss": 4.7124, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.8491004433414594e-05, + "loss": 4.7238, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.8482618485904074e-05, + "loss": 4.7163, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.8474232538393554e-05, + "loss": 4.7129, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.8465846590883034e-05, + "loss": 4.717, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845747702217624e-05, + "loss": 4.7135, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844909107466572e-05, + "loss": 4.71, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.84407051271552e-05, + "loss": 4.692, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.843231917964469e-05, + "loss": 4.6978, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.842393323213417e-05, + "loss": 4.6808, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.841554728462365e-05, + "loss": 4.6953, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840717771591686e-05, + "loss": 4.6887, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.839879176840634e-05, + "loss": 4.698, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839040582089582e-05, + "loss": 4.6801, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.83820198733853e-05, + "loss": 4.6916, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.837363392587478e-05, + "loss": 4.6823, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.836524797836426e-05, + "loss": 4.6832, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.835686203085374e-05, + "loss": 4.6921, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.834847608334322e-05, + "loss": 4.6603, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.8340122893440156e-05, + "loss": 4.6659, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.833173694592964e-05, + "loss": 4.6829, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.832335099841912e-05, + "loss": 4.6755, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.83149650509086e-05, + "loss": 4.6639, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.830657910339808e-05, + "loss": 4.6569, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.829820953469129e-05, + "loss": 4.6573, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.828982358718077e-05, + "loss": 4.6465, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.828143763967025e-05, + "loss": 4.6736, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.827305169215973e-05, + "loss": 4.6417, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.826466574464921e-05, + "loss": 4.6604, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.825627979713869e-05, + "loss": 4.6507, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.824789384962817e-05, + "loss": 4.6432, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.823952428092138e-05, + "loss": 4.6477, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.823113833341086e-05, + "loss": 4.635, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.822275238590034e-05, + "loss": 4.6298, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.821436643838983e-05, + "loss": 4.6369, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.8205996869683037e-05, + "loss": 4.6537, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.8197610922172516e-05, + "loss": 4.6242, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.8189224974661996e-05, + "loss": 4.6295, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.8180839027151476e-05, + "loss": 4.6151, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.8172469458444685e-05, + "loss": 4.6282, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.8164083510934165e-05, + "loss": 4.6408, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.8155697563423645e-05, + "loss": 4.635, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.8147311615913125e-05, + "loss": 4.6213, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.81389256684026e-05, + "loss": 4.6345, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.813053972089208e-05, + "loss": 4.6419, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.8122153773381565e-05, + "loss": 4.6199, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.8113767825871045e-05, + "loss": 4.6143, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.8105381878360525e-05, + "loss": 4.6156, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.8096995930850005e-05, + "loss": 4.6072, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.8088609983339485e-05, + "loss": 4.6188, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.8080240414632694e-05, + "loss": 4.6049, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.8071854467122174e-05, + "loss": 4.6182, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.8063468519611654e-05, + "loss": 4.6161, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.8055082572101134e-05, + "loss": 4.6108, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.8046696624590614e-05, + "loss": 4.5932, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803832705588382e-05, + "loss": 4.6029, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.80299411083733e-05, + "loss": 4.606, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.802155516086278e-05, + "loss": 4.6114, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.801316921335226e-05, + "loss": 4.6022, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.800478326584174e-05, + "loss": 4.5989, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.799639731833123e-05, + "loss": 4.6009, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.798801137082071e-05, + "loss": 4.5894, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.797964180211392e-05, + "loss": 4.5868, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.79712558546034e-05, + "loss": 4.5955, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.796286990709288e-05, + "loss": 4.5863, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.795448395958236e-05, + "loss": 4.5887, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.794611439087557e-05, + "loss": 4.5888, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.793772844336505e-05, + "loss": 4.5762, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.792934249585453e-05, + "loss": 4.5873, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.792095654834401e-05, + "loss": 4.594, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.791257060083349e-05, + "loss": 4.5832, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.790418465332297e-05, + "loss": 4.5798, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.789579870581245e-05, + "loss": 4.5705, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.788741275830193e-05, + "loss": 4.5748, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.787902681079141e-05, + "loss": 4.5752, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.787064086328089e-05, + "loss": 4.5579, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.7862271294574096e-05, + "loss": 4.5631, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.7853885347063576e-05, + "loss": 4.5652, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.7845499399553056e-05, + "loss": 4.5749, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.7837113452042536e-05, + "loss": 4.5604, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.7828743883335745e-05, + "loss": 4.5676, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.7820357935825225e-05, + "loss": 4.5505, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.7811971988314705e-05, + "loss": 4.5719, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.7803586040804185e-05, + "loss": 4.5512, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.7795200093293665e-05, + "loss": 4.5554, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.778683052458688e-05, + "loss": 4.5651, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.777844457707636e-05, + "loss": 4.5596, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.777005862956584e-05, + "loss": 4.5583, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.776167268205532e-05, + "loss": 4.5471, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.77532867345448e-05, + "loss": 4.5556, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.774490078703428e-05, + "loss": 4.5627, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.773651483952376e-05, + "loss": 4.5435, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.772814527081697e-05, + "loss": 4.546, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.771975932330645e-05, + "loss": 4.5449, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.771137337579593e-05, + "loss": 4.5577, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.770298742828541e-05, + "loss": 4.5299, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.769460148077489e-05, + "loss": 4.539, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.768621553326437e-05, + "loss": 4.5302, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.7677845964557585e-05, + "loss": 4.542, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.7669460017047065e-05, + "loss": 4.5294, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.7661074069536545e-05, + "loss": 4.5503, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.7652688122026025e-05, + "loss": 4.5431, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.7644318553319234e-05, + "loss": 4.5345, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.7635932605808714e-05, + "loss": 4.527, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.7627546658298194e-05, + "loss": 4.5385, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.7619160710787674e-05, + "loss": 4.5365, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.761077476327715e-05, + "loss": 4.5431, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.760238881576663e-05, + "loss": 4.5214, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.759400286825611e-05, + "loss": 4.5397, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.758561692074559e-05, + "loss": 4.5312, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.7577230973235074e-05, + "loss": 4.5345, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.7568845025724554e-05, + "loss": 4.5183, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.7560459078214034e-05, + "loss": 4.5307, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.755208950950724e-05, + "loss": 4.5227, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.754371994080045e-05, + "loss": 4.5117, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.753535037209367e-05, + "loss": 4.5274, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.752696442458315e-05, + "loss": 4.5246, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.751857847707262e-05, + "loss": 4.5201, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.75101925295621e-05, + "loss": 4.5167, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.750180658205158e-05, + "loss": 4.5075, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.480353832244873, + "eval_runtime": 295.1459, + "eval_samples_per_second": 1292.89, + "eval_steps_per_second": 40.404, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.749342063454106e-05, + "loss": 4.4942, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748503468703054e-05, + "loss": 4.5013, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.747664873952003e-05, + "loss": 4.5218, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.746826279200951e-05, + "loss": 4.5105, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.745987684449899e-05, + "loss": 4.5152, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.745149089698847e-05, + "loss": 4.502, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.744310494947795e-05, + "loss": 4.5074, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.743471900196743e-05, + "loss": 4.4939, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.742633305445691e-05, + "loss": 4.4995, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.741794710694639e-05, + "loss": 4.5051, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.7409577538239597e-05, + "loss": 4.5102, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.7401191590729076e-05, + "loss": 4.5107, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.7392805643218556e-05, + "loss": 4.4927, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.7384419695708036e-05, + "loss": 4.4906, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.737603374819751e-05, + "loss": 4.4893, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736764780068699e-05, + "loss": 4.4797, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.7359261853176476e-05, + "loss": 4.4955, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.7350875905665956e-05, + "loss": 4.4841, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.7342489958155436e-05, + "loss": 4.4854, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.7334104010644916e-05, + "loss": 4.5049, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.7325718063134396e-05, + "loss": 4.4889, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.7317332115623876e-05, + "loss": 4.4866, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.7308962546917085e-05, + "loss": 4.4899, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.7300592978210294e-05, + "loss": 4.5031, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.7292207030699774e-05, + "loss": 4.4712, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.7283821083189254e-05, + "loss": 4.4814, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.7275435135678734e-05, + "loss": 4.4882, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.7267049188168214e-05, + "loss": 4.4829, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.7258663240657694e-05, + "loss": 4.4695, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.7250277293147174e-05, + "loss": 4.4662, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.724189134563666e-05, + "loss": 4.4869, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723350539812614e-05, + "loss": 4.4834, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.722511945061562e-05, + "loss": 4.4747, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.72167335031051e-05, + "loss": 4.4802, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720836393439831e-05, + "loss": 4.4767, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.719997798688779e-05, + "loss": 4.473, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.719159203937727e-05, + "loss": 4.4603, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.718320609186675e-05, + "loss": 4.4716, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.717482014435622e-05, + "loss": 4.4511, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.71664341968457e-05, + "loss": 4.47, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.715804824933518e-05, + "loss": 4.4646, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.714966230182466e-05, + "loss": 4.4703, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.714129273311788e-05, + "loss": 4.4591, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.713290678560736e-05, + "loss": 4.466, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.712452083809684e-05, + "loss": 4.4638, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.711613489058632e-05, + "loss": 4.4598, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.71077489430758e-05, + "loss": 4.4721, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.709936299556528e-05, + "loss": 4.4429, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.709097704805476e-05, + "loss": 4.453, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.708259110054424e-05, + "loss": 4.4655, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.707422153183745e-05, + "loss": 4.4616, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.706583558432693e-05, + "loss": 4.451, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705744963681641e-05, + "loss": 4.4428, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704906368930589e-05, + "loss": 4.4502, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.704071049940283e-05, + "loss": 4.4324, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703232455189231e-05, + "loss": 4.4643, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.702395498318552e-05, + "loss": 4.4384, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.7015569035675e-05, + "loss": 4.4467, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.700718308816448e-05, + "loss": 4.4463, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.699879714065396e-05, + "loss": 4.4374, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699041119314344e-05, + "loss": 4.4444, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.698202524563292e-05, + "loss": 4.4322, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.697365567692613e-05, + "loss": 4.4292, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696526972941561e-05, + "loss": 4.4315, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.695688378190509e-05, + "loss": 4.4511, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694849783439457e-05, + "loss": 4.4303, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694011188688405e-05, + "loss": 4.4302, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693172593937353e-05, + "loss": 4.4187, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.6923339991863017e-05, + "loss": 4.4306, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.6914954044352496e-05, + "loss": 4.4427, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.6906584475645706e-05, + "loss": 4.4426, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.6898198528135186e-05, + "loss": 4.4263, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.6889812580624665e-05, + "loss": 4.4433, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.6881426633114145e-05, + "loss": 4.4491, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.6873040685603625e-05, + "loss": 4.4276, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.6864671116896834e-05, + "loss": 4.4181, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.6856285169386314e-05, + "loss": 4.4305, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.6847899221875794e-05, + "loss": 4.422, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.6839513274365274e-05, + "loss": 4.4282, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.6831127326854754e-05, + "loss": 4.4167, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.682275775814797e-05, + "loss": 4.4296, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.681437181063745e-05, + "loss": 4.4333, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.680598586312693e-05, + "loss": 4.4254, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679759991561641e-05, + "loss": 4.4092, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678921396810588e-05, + "loss": 4.4193, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678082802059536e-05, + "loss": 4.4217, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.677244207308484e-05, + "loss": 4.4303, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.676405612557432e-05, + "loss": 4.4201, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.675568655686753e-05, + "loss": 4.4227, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674730060935701e-05, + "loss": 4.4177, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.673891466184649e-05, + "loss": 4.4119, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.673054509313971e-05, + "loss": 4.4099, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.672215914562919e-05, + "loss": 4.4123, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.671377319811867e-05, + "loss": 4.4119, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.6705403629411884e-05, + "loss": 4.4151, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.669701768190136e-05, + "loss": 4.4145, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.668863173439084e-05, + "loss": 4.4, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668024578688032e-05, + "loss": 4.4146, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.66718598393698e-05, + "loss": 4.4209, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.666347389185928e-05, + "loss": 4.409, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665508794434876e-05, + "loss": 4.4108, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664670199683824e-05, + "loss": 4.3989, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663831604932772e-05, + "loss": 4.405, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.6629930101817197e-05, + "loss": 4.4068, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.6621544154306677e-05, + "loss": 4.3857, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.661317458559989e-05, + "loss": 4.3964, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.66048050168931e-05, + "loss": 4.4028, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659641906938258e-05, + "loss": 4.4029, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.658803312187206e-05, + "loss": 4.3943, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.657964717436154e-05, + "loss": 4.4043, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657126122685102e-05, + "loss": 4.387, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.65628752793405e-05, + "loss": 4.4042, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655450571063371e-05, + "loss": 4.3891, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.654611976312319e-05, + "loss": 4.3897, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.653773381561267e-05, + "loss": 4.404, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.652934786810215e-05, + "loss": 4.4028, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.652097829939536e-05, + "loss": 4.3988, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.6512592351884846e-05, + "loss": 4.3907, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.6504206404374326e-05, + "loss": 4.393, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.6495820456863806e-05, + "loss": 4.398, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.6487434509353286e-05, + "loss": 4.3878, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.6479048561842766e-05, + "loss": 4.3921, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.6470662614332246e-05, + "loss": 4.3861, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.646227666682172e-05, + "loss": 4.3935, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.64538907193112e-05, + "loss": 4.3839, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.6445521150604415e-05, + "loss": 4.3835, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.643713520309389e-05, + "loss": 4.3704, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.642874925558337e-05, + "loss": 4.3913, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642036330807285e-05, + "loss": 4.3729, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.641197736056233e-05, + "loss": 4.3959, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640359141305181e-05, + "loss": 4.3915, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.6395205465541295e-05, + "loss": 4.3857, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.6386819518030775e-05, + "loss": 4.3721, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.6378449949323984e-05, + "loss": 4.3895, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.6370064001813464e-05, + "loss": 4.386, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.6361678054302944e-05, + "loss": 4.3898, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.6353292106792424e-05, + "loss": 4.3764, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.6344906159281903e-05, + "loss": 4.3861, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.6336520211771383e-05, + "loss": 4.3871, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.6328134264260863e-05, + "loss": 4.3878, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.631974831675034e-05, + "loss": 4.3735, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.631137874804355e-05, + "loss": 4.3815, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.630299280053303e-05, + "loss": 4.3774, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629462323182625e-05, + "loss": 4.3675, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.628623728431573e-05, + "loss": 4.3819, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.627785133680521e-05, + "loss": 4.3851, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626946538929469e-05, + "loss": 4.371, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626107944178417e-05, + "loss": 4.3753, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625269349427365e-05, + "loss": 4.365, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 4.343946933746338, + "eval_runtime": 305.8721, + "eval_samples_per_second": 1247.551, + "eval_steps_per_second": 38.987, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.624430754676313e-05, + "loss": 4.3602, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.623593797805634e-05, + "loss": 4.3555, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.622755203054582e-05, + "loss": 4.3809, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.62191660830353e-05, + "loss": 4.3664, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.621078013552478e-05, + "loss": 4.3776, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.6202410566817986e-05, + "loss": 4.362, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.6194024619307466e-05, + "loss": 4.3678, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.6185638671796946e-05, + "loss": 4.352, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.617725272428643e-05, + "loss": 4.3638, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.6168866776775906e-05, + "loss": 4.3648, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.6160480829265386e-05, + "loss": 4.374, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.61521112605586e-05, + "loss": 4.3725, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.614374169185181e-05, + "loss": 4.3557, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.613535574434129e-05, + "loss": 4.3551, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.612696979683077e-05, + "loss": 4.3534, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.611858384932025e-05, + "loss": 4.348, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.6110197901809724e-05, + "loss": 4.3564, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.6101811954299204e-05, + "loss": 4.3504, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.6093426006788684e-05, + "loss": 4.3501, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.608504005927817e-05, + "loss": 4.3768, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.607667049057138e-05, + "loss": 4.3545, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.606828454306086e-05, + "loss": 4.3524, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.605989859555034e-05, + "loss": 4.3605, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.605151264803982e-05, + "loss": 4.3662, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.60431267005293e-05, + "loss": 4.3428, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.603474075301878e-05, + "loss": 4.3488, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.602635480550826e-05, + "loss": 4.3576, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.601796885799774e-05, + "loss": 4.3548, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.600961566809468e-05, + "loss": 4.3373, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.600122972058416e-05, + "loss": 4.336, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.599286015187737e-05, + "loss": 4.3568, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.598447420436685e-05, + "loss": 4.3559, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.597608825685633e-05, + "loss": 4.3512, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.596770230934581e-05, + "loss": 4.3518, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.595933274063903e-05, + "loss": 4.3486, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.59509467931285e-05, + "loss": 4.348, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.594256084561798e-05, + "loss": 4.3315, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.593417489810746e-05, + "loss": 4.3493, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.592578895059694e-05, + "loss": 4.3259, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.591741938189015e-05, + "loss": 4.3437, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.590903343437963e-05, + "loss": 4.3379, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.590064748686911e-05, + "loss": 4.3505, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.589226153935859e-05, + "loss": 4.3395, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.588387559184808e-05, + "loss": 4.34, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.587550602314129e-05, + "loss": 4.3409, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.586712007563077e-05, + "loss": 4.3425, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.585873412812025e-05, + "loss": 4.3475, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.585034818060973e-05, + "loss": 4.3233, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.584196223309921e-05, + "loss": 4.3281, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.583357628558869e-05, + "loss": 4.346, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.582519033807817e-05, + "loss": 4.3403, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.581680439056765e-05, + "loss": 4.3307, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.5808418443057127e-05, + "loss": 4.3252, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.5800032495546607e-05, + "loss": 4.3315, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.5791646548036086e-05, + "loss": 4.317, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.578326060052556e-05, + "loss": 4.3425, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.5774891031818776e-05, + "loss": 4.3186, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.5766505084308255e-05, + "loss": 4.3292, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.575811913679774e-05, + "loss": 4.3307, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.574974956809095e-05, + "loss": 4.3222, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.574137999938416e-05, + "loss": 4.3243, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.573299405187364e-05, + "loss": 4.3195, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.572460810436312e-05, + "loss": 4.3121, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.57162221568526e-05, + "loss": 4.3222, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.570783620934208e-05, + "loss": 4.3331, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.569945026183156e-05, + "loss": 4.3171, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.569106431432103e-05, + "loss": 4.3159, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.568267836681051e-05, + "loss": 4.3068, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.567429241929999e-05, + "loss": 4.3151, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.566590647178948e-05, + "loss": 4.3261, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.565752052427896e-05, + "loss": 4.3336, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.564913457676844e-05, + "loss": 4.3143, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.564076500806165e-05, + "loss": 4.328, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.563237906055113e-05, + "loss": 4.3317, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.562399311304061e-05, + "loss": 4.3248, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.561562354433382e-05, + "loss": 4.3006, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.56072375968233e-05, + "loss": 4.3223, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.559885164931278e-05, + "loss": 4.3159, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.559046570180226e-05, + "loss": 4.3114, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.558207975429174e-05, + "loss": 4.3142, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.557371018558495e-05, + "loss": 4.3157, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.5565324238074434e-05, + "loss": 4.3248, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.5556938290563914e-05, + "loss": 4.3162, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.5548552343053394e-05, + "loss": 4.3023, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.5540166395542874e-05, + "loss": 4.3129, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.5531780448032354e-05, + "loss": 4.3078, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.552341087932556e-05, + "loss": 4.3215, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.551502493181504e-05, + "loss": 4.3185, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.550663898430452e-05, + "loss": 4.311, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.549826941559773e-05, + "loss": 4.3131, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.548988346808721e-05, + "loss": 4.3028, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.548149752057669e-05, + "loss": 4.3034, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.547311157306617e-05, + "loss": 4.3047, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.546472562555565e-05, + "loss": 4.3085, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.545633967804513e-05, + "loss": 4.3081, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.544795373053462e-05, + "loss": 4.3158, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.54395677830241e-05, + "loss": 4.2919, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.543118183551358e-05, + "loss": 4.3094, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.542281226680679e-05, + "loss": 4.318, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.541442631929627e-05, + "loss": 4.3063, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.540604037178575e-05, + "loss": 4.3059, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.539765442427522e-05, + "loss": 4.297, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.53892684767647e-05, + "loss": 4.3028, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.538088252925418e-05, + "loss": 4.3046, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.5372512960547396e-05, + "loss": 4.2841, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.536412701303687e-05, + "loss": 4.2963, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.5355741065526356e-05, + "loss": 4.2984, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.5347355118015836e-05, + "loss": 4.3038, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.5338969170505316e-05, + "loss": 4.2876, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.5330583222994796e-05, + "loss": 4.309, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.5322197275484276e-05, + "loss": 4.2816, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.5313811327973756e-05, + "loss": 4.305, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.5305441759266965e-05, + "loss": 4.2931, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.5297055811756445e-05, + "loss": 4.2867, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.5288669864245925e-05, + "loss": 4.3038, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.5280283916735405e-05, + "loss": 4.3038, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.5271897969224885e-05, + "loss": 4.2984, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.5263512021714365e-05, + "loss": 4.2935, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.5255142453007574e-05, + "loss": 4.2958, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.5246756505497054e-05, + "loss": 4.2982, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.5238370557986534e-05, + "loss": 4.2879, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.522998461047602e-05, + "loss": 4.2946, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.52215986629655e-05, + "loss": 4.2916, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.521322909425871e-05, + "loss": 4.2925, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.520484314674819e-05, + "loss": 4.2898, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.519645719923767e-05, + "loss": 4.2888, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.518807125172715e-05, + "loss": 4.2689, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.517970168302036e-05, + "loss": 4.2953, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.517131573550984e-05, + "loss": 4.2794, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.516292978799932e-05, + "loss": 4.2986, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.51545438404888e-05, + "loss": 4.2947, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.514615789297828e-05, + "loss": 4.2942, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.513777194546776e-05, + "loss": 4.2756, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.512938599795724e-05, + "loss": 4.2952, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.512100005044672e-05, + "loss": 4.2898, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.5112630481739934e-05, + "loss": 4.2969, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.510426091303314e-05, + "loss": 4.2785, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.509587496552262e-05, + "loss": 4.2979, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.50874890180121e-05, + "loss": 4.2939, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.507910307050158e-05, + "loss": 4.2961, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.5070717122991056e-05, + "loss": 4.2741, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.5062331175480536e-05, + "loss": 4.2887, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.5053945227970016e-05, + "loss": 4.2857, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.5045559280459496e-05, + "loss": 4.2769, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.5037173332948976e-05, + "loss": 4.2861, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.502880376424219e-05, + "loss": 4.2897, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.502041781673167e-05, + "loss": 4.2816, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.501204824802488e-05, + "loss": 4.2808, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.500366230051436e-05, + "loss": 4.279, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 4.259962558746338, + "eval_runtime": 307.8396, + "eval_samples_per_second": 1239.577, + "eval_steps_per_second": 38.738, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.499527635300384e-05, + "loss": 4.2634, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.498689040549332e-05, + "loss": 4.2678, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.49785044579828e-05, + "loss": 4.2862, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.497011851047228e-05, + "loss": 4.2767, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.496173256296176e-05, + "loss": 4.2886, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.495334661545124e-05, + "loss": 4.274, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.494496066794072e-05, + "loss": 4.2779, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.49365747204302e-05, + "loss": 4.2626, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.492818877291968e-05, + "loss": 4.2761, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.491980282540916e-05, + "loss": 4.2768, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.491141687789864e-05, + "loss": 4.2802, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.490303093038812e-05, + "loss": 4.2849, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.4894661361681336e-05, + "loss": 4.2659, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.4886275414170816e-05, + "loss": 4.2693, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.4877889466660296e-05, + "loss": 4.2656, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.486950351914977e-05, + "loss": 4.2592, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486111757163925e-05, + "loss": 4.2675, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.485273162412873e-05, + "loss": 4.2668, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.484434567661821e-05, + "loss": 4.2645, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.483595972910769e-05, + "loss": 4.2857, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.482757378159717e-05, + "loss": 4.2687, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481918783408665e-05, + "loss": 4.2655, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.4810818265379865e-05, + "loss": 4.2755, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.4802432317869345e-05, + "loss": 4.2794, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.4794046370358825e-05, + "loss": 4.2598, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.4785660422848305e-05, + "loss": 4.2663, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.4777274475337785e-05, + "loss": 4.2703, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.4768888527827265e-05, + "loss": 4.2678, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.4760502580316744e-05, + "loss": 4.2523, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.4752133011609954e-05, + "loss": 4.2538, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.4743747064099434e-05, + "loss": 4.2709, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.4735361116588914e-05, + "loss": 4.2711, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.4726975169078393e-05, + "loss": 4.2657, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.4718589221567873e-05, + "loss": 4.2702, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.471021965286108e-05, + "loss": 4.2631, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.470183370535056e-05, + "loss": 4.2675, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469344775784004e-05, + "loss": 4.2514, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468506181032953e-05, + "loss": 4.2608, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.467667586281901e-05, + "loss": 4.2457, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.466828991530848e-05, + "loss": 4.2583, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.46599203466017e-05, + "loss": 4.2546, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.465153439909118e-05, + "loss": 4.2693, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464314845158066e-05, + "loss": 4.2581, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463476250407013e-05, + "loss": 4.2584, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.462637655655961e-05, + "loss": 4.2579, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461799060904909e-05, + "loss": 4.2608, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.460960466153857e-05, + "loss": 4.2671, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.460121871402805e-05, + "loss": 4.2468, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.459284914532127e-05, + "loss": 4.2456, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.458447957661448e-05, + "loss": 4.2673, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.4576093629103956e-05, + "loss": 4.2592, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.4567707681593436e-05, + "loss": 4.2479, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.4559321734082916e-05, + "loss": 4.2458, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.4550935786572396e-05, + "loss": 4.2542, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.4542549839061876e-05, + "loss": 4.2377, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.4534163891551356e-05, + "loss": 4.2602, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.4525777944040836e-05, + "loss": 4.2397, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.4517391996530316e-05, + "loss": 4.2491, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.4509022427823525e-05, + "loss": 4.2506, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.4500636480313005e-05, + "loss": 4.2464, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.4492250532802485e-05, + "loss": 4.2406, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.4483864585291965e-05, + "loss": 4.2452, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.447549501658518e-05, + "loss": 4.2324, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446710906907466e-05, + "loss": 4.2447, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445873950036787e-05, + "loss": 4.2539, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445035355285735e-05, + "loss": 4.2388, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444196760534683e-05, + "loss": 4.2388, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.443358165783631e-05, + "loss": 4.2299, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.442519571032579e-05, + "loss": 4.2345, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441680976281527e-05, + "loss": 4.2526, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.440842381530475e-05, + "loss": 4.2542, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440003786779423e-05, + "loss": 4.2401, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.439166829908744e-05, + "loss": 4.2493, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438328235157692e-05, + "loss": 4.2591, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.4374896404066405e-05, + "loss": 4.2477, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.4366526835359614e-05, + "loss": 4.2277, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.4358140887849094e-05, + "loss": 4.2445, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.4349754940338574e-05, + "loss": 4.2427, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.4341368992828054e-05, + "loss": 4.2349, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.4332983045317534e-05, + "loss": 4.2377, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.4324597097807014e-05, + "loss": 4.2447, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.4316211150296494e-05, + "loss": 4.2519, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.430782520278597e-05, + "loss": 4.2414, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.429945563407918e-05, + "loss": 4.2244, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.429108606537239e-05, + "loss": 4.2394, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.428270011786187e-05, + "loss": 4.2379, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.427431417035135e-05, + "loss": 4.2412, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.426592822284084e-05, + "loss": 4.243, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.425754227533032e-05, + "loss": 4.2395, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.424917270662353e-05, + "loss": 4.2409, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.424078675911301e-05, + "loss": 4.2305, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.423240081160249e-05, + "loss": 4.2279, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422401486409197e-05, + "loss": 4.2298, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.421562891658144e-05, + "loss": 4.2393, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.420724296907092e-05, + "loss": 4.2357, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.4198873400364137e-05, + "loss": 4.2415, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.419048745285361e-05, + "loss": 4.2209, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.418210150534309e-05, + "loss": 4.2339, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.4173715557832576e-05, + "loss": 4.2442, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.4165329610322056e-05, + "loss": 4.2373, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.4156943662811536e-05, + "loss": 4.2326, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.4148557715301016e-05, + "loss": 4.2259, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.4140171767790496e-05, + "loss": 4.229, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.4131802199083705e-05, + "loss": 4.2358, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.4123416251573185e-05, + "loss": 4.2096, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.4115030304062665e-05, + "loss": 4.2274, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.4106660735355874e-05, + "loss": 4.2253, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.4098274787845354e-05, + "loss": 4.2332, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.4089888840334834e-05, + "loss": 4.2171, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.4081502892824314e-05, + "loss": 4.2365, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.4073116945313794e-05, + "loss": 4.2212, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.4064730997803274e-05, + "loss": 4.2295, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.405636142909649e-05, + "loss": 4.2255, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.40479918603897e-05, + "loss": 4.2147, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.403960591287918e-05, + "loss": 4.2329, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.403121996536866e-05, + "loss": 4.2365, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402283401785814e-05, + "loss": 4.231, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.401444807034762e-05, + "loss": 4.2206, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.40060621228371e-05, + "loss": 4.2249, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399767617532658e-05, + "loss": 4.2291, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398929022781606e-05, + "loss": 4.2176, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.398090428030554e-05, + "loss": 4.2256, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.397253471159875e-05, + "loss": 4.2228, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396414876408823e-05, + "loss": 4.2226, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.3955762816577715e-05, + "loss": 4.2231, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.3947376869067195e-05, + "loss": 4.2234, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.3938990921556674e-05, + "loss": 4.204, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.3930621352849884e-05, + "loss": 4.2237, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.3922235405339364e-05, + "loss": 4.2152, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.3913849457828843e-05, + "loss": 4.2324, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.3905463510318323e-05, + "loss": 4.2233, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.3897077562807803e-05, + "loss": 4.2283, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.3888691615297277e-05, + "loss": 4.209, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.3880305667786757e-05, + "loss": 4.2288, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.3871919720276236e-05, + "loss": 4.2255, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.386355015156945e-05, + "loss": 4.227, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.385516420405893e-05, + "loss": 4.2134, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.384677825654841e-05, + "loss": 4.2276, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.383839230903789e-05, + "loss": 4.2276, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.383000636152737e-05, + "loss": 4.2341, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.382162041401685e-05, + "loss": 4.2072, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.381325084531006e-05, + "loss": 4.2222, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.380486489779954e-05, + "loss": 4.2197, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.379647895028902e-05, + "loss": 4.2101, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.37880930027785e-05, + "loss": 4.2223, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.377970705526798e-05, + "loss": 4.2222, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.377132110775746e-05, + "loss": 4.2206, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.376293516024694e-05, + "loss": 4.2122, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.375456559154015e-05, + "loss": 4.2159, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 4.202970504760742, + "eval_runtime": 295.4183, + "eval_samples_per_second": 1291.697, + "eval_steps_per_second": 40.366, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.374617964402964e-05, + "loss": 4.2043, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.373779369651912e-05, + "loss": 4.2001, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.37294077490086e-05, + "loss": 4.222, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.3721038180301806e-05, + "loss": 4.2149, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.3712652232791286e-05, + "loss": 4.2209, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.3704266285280766e-05, + "loss": 4.2135, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.3695880337770246e-05, + "loss": 4.2108, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.3687510769063455e-05, + "loss": 4.2026, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.3679124821552935e-05, + "loss": 4.2093, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.3670738874042415e-05, + "loss": 4.2143, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.3662352926531895e-05, + "loss": 4.2172, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.3653966979021375e-05, + "loss": 4.2202, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.3645597410314584e-05, + "loss": 4.2044, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.363721146280407e-05, + "loss": 4.2071, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.362882551529355e-05, + "loss": 4.2059, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.362043956778303e-05, + "loss": 4.1918, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.361206999907624e-05, + "loss": 4.2068, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.360368405156572e-05, + "loss": 4.2039, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.359531448285893e-05, + "loss": 4.2002, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.358692853534841e-05, + "loss": 4.2193, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.357854258783789e-05, + "loss": 4.2129, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.357015664032737e-05, + "loss": 4.2076, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.356177069281685e-05, + "loss": 4.2129, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.355338474530633e-05, + "loss": 4.2189, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.354499879779581e-05, + "loss": 4.1948, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.353661285028529e-05, + "loss": 4.2037, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.352822690277477e-05, + "loss": 4.2124, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.351984095526425e-05, + "loss": 4.2004, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.3511471386557464e-05, + "loss": 4.1931, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.350308543904694e-05, + "loss": 4.1938, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.349469949153642e-05, + "loss": 4.2109, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.34863135440259e-05, + "loss": 4.2097, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.3477943975319106e-05, + "loss": 4.2062, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.3469558027808586e-05, + "loss": 4.2103, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.34611884591018e-05, + "loss": 4.2038, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.345280251159128e-05, + "loss": 4.203, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.344441656408076e-05, + "loss": 4.1944, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.343603061657024e-05, + "loss": 4.2003, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.342764466905972e-05, + "loss": 4.1862, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.34192587215492e-05, + "loss": 4.1957, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.341087277403868e-05, + "loss": 4.1978, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.340248682652816e-05, + "loss": 4.2094, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.339410087901764e-05, + "loss": 4.199, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.338571493150712e-05, + "loss": 4.1998, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.337734536280033e-05, + "loss": 4.2041, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.336895941528981e-05, + "loss": 4.1959, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.336057346777929e-05, + "loss": 4.2078, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.335218752026877e-05, + "loss": 4.1908, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.334380157275825e-05, + "loss": 4.1849, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.333541562524773e-05, + "loss": 4.2061, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.332702967773721e-05, + "loss": 4.2013, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.331864373022669e-05, + "loss": 4.1898, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.3310274161519906e-05, + "loss": 4.1918, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.3301904592813115e-05, + "loss": 4.1947, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.3293518645302595e-05, + "loss": 4.1779, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.3285132697792075e-05, + "loss": 4.2008, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.3276746750281555e-05, + "loss": 4.1844, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.3268360802771035e-05, + "loss": 4.1877, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.3259991234064244e-05, + "loss": 4.1963, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.3251605286553724e-05, + "loss": 4.1879, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.3243219339043204e-05, + "loss": 4.1879, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.3234833391532684e-05, + "loss": 4.186, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.3226447444022164e-05, + "loss": 4.1773, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.3218061496511644e-05, + "loss": 4.186, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.3209675549001124e-05, + "loss": 4.1964, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.3201289601490604e-05, + "loss": 4.1858, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.319292003278382e-05, + "loss": 4.1815, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.31845340852733e-05, + "loss": 4.1784, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.317614813776277e-05, + "loss": 4.1763, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.316776219025225e-05, + "loss": 4.1907, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.315937624274173e-05, + "loss": 4.1966, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.315100667403494e-05, + "loss": 4.1887, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.314263710532816e-05, + "loss": 4.1933, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.313425115781764e-05, + "loss": 4.1978, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.3125881589110854e-05, + "loss": 4.1973, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.3117495641600334e-05, + "loss": 4.1715, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.3109109694089814e-05, + "loss": 4.1864, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.3100723746579294e-05, + "loss": 4.1892, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.3092337799068773e-05, + "loss": 4.1747, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.308395185155825e-05, + "loss": 4.1884, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.307556590404773e-05, + "loss": 4.183, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.3067179956537207e-05, + "loss": 4.1963, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.3058794009026687e-05, + "loss": 4.1878, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.3050408061516166e-05, + "loss": 4.1671, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.3042038492809376e-05, + "loss": 4.1849, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.3033652545298856e-05, + "loss": 4.1832, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.3025266597788335e-05, + "loss": 4.1898, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.3016880650277815e-05, + "loss": 4.1839, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.30084947027673e-05, + "loss": 4.1883, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.300010875525678e-05, + "loss": 4.1847, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.299172280774626e-05, + "loss": 4.1768, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.298333686023574e-05, + "loss": 4.1706, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.297496729152895e-05, + "loss": 4.1773, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.296658134401843e-05, + "loss": 4.1871, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.295819539650791e-05, + "loss": 4.1806, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.294980944899739e-05, + "loss": 4.1844, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.29414398802906e-05, + "loss": 4.1701, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.293308669038754e-05, + "loss": 4.1797, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.2924700742877025e-05, + "loss": 4.187, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.2916314795366505e-05, + "loss": 4.1851, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.2907928847855985e-05, + "loss": 4.1783, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.2899542900345465e-05, + "loss": 4.1739, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.2891156952834945e-05, + "loss": 4.1737, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.2882771005324425e-05, + "loss": 4.1843, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.2874385057813905e-05, + "loss": 4.1548, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.2865999110303385e-05, + "loss": 4.1762, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.2857629541596594e-05, + "loss": 4.168, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.2849243594086074e-05, + "loss": 4.1823, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.2840857646575554e-05, + "loss": 4.1631, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.2832471699065034e-05, + "loss": 4.188, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.2824085751554514e-05, + "loss": 4.168, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.2815699804043994e-05, + "loss": 4.177, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.2807313856533474e-05, + "loss": 4.1705, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.2798927909022954e-05, + "loss": 4.1651, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.279055834031617e-05, + "loss": 4.1786, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.278217239280565e-05, + "loss": 4.1854, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.277378644529513e-05, + "loss": 4.1788, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.27654004977846e-05, + "loss": 4.1663, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.275704730788155e-05, + "loss": 4.1724, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.274866136037103e-05, + "loss": 4.1783, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.274027541286051e-05, + "loss": 4.167, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.273188946534999e-05, + "loss": 4.1776, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.272350351783947e-05, + "loss": 4.1644, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.271511757032895e-05, + "loss": 4.171, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.270674800162216e-05, + "loss": 4.1726, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.269836205411164e-05, + "loss": 4.1732, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.268997610660112e-05, + "loss": 4.15, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.26815901590906e-05, + "loss": 4.1747, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.2673204211580076e-05, + "loss": 4.1624, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.2664818264069556e-05, + "loss": 4.1795, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.2656432316559036e-05, + "loss": 4.1734, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.2648046369048516e-05, + "loss": 4.177, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.2639676800341725e-05, + "loss": 4.158, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.2631290852831205e-05, + "loss": 4.1792, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.2622904905320685e-05, + "loss": 4.1762, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.2614518957810165e-05, + "loss": 4.1739, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.2606133010299645e-05, + "loss": 4.1671, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.259774706278913e-05, + "loss": 4.1759, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.258936111527861e-05, + "loss": 4.1781, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.258097516776809e-05, + "loss": 4.1818, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.25726055990613e-05, + "loss": 4.1597, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.256421965155078e-05, + "loss": 4.1726, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.255583370404026e-05, + "loss": 4.1696, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.254746413533347e-05, + "loss": 4.1591, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.253907818782295e-05, + "loss": 4.1744, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.253069224031243e-05, + "loss": 4.1679, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.252230629280191e-05, + "loss": 4.1745, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.251392034529139e-05, + "loss": 4.1621, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.250553439778087e-05, + "loss": 4.1659, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 4.16155481338501, + "eval_runtime": 312.5113, + "eval_samples_per_second": 1221.047, + "eval_steps_per_second": 38.159, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.249714845027035e-05, + "loss": 4.1565, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.248876250275983e-05, + "loss": 4.1465, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.248037655524931e-05, + "loss": 4.1708, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.2471990607738796e-05, + "loss": 4.168, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.246360466022827e-05, + "loss": 4.1727, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.245521871271775e-05, + "loss": 4.1647, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.244683276520723e-05, + "loss": 4.1571, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.243844681769671e-05, + "loss": 4.1572, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.243006087018619e-05, + "loss": 4.1605, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.242167492267567e-05, + "loss": 4.1636, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.241328897516515e-05, + "loss": 4.1706, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.240490302765463e-05, + "loss": 4.1719, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.239653345894784e-05, + "loss": 4.1574, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.238814751143732e-05, + "loss": 4.157, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.23797615639268e-05, + "loss": 4.1614, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.237137561641628e-05, + "loss": 4.1423, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.2362989668905765e-05, + "loss": 4.1574, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.2354603721395245e-05, + "loss": 4.1541, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.2346217773884725e-05, + "loss": 4.1539, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.2337831826374205e-05, + "loss": 4.1706, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.232944587886368e-05, + "loss": 4.1645, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232105993135316e-05, + "loss": 4.1618, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.231267398384264e-05, + "loss": 4.1613, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.230428803633212e-05, + "loss": 4.1708, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.229591846762533e-05, + "loss": 4.1491, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.228753252011481e-05, + "loss": 4.159, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.2279146572604287e-05, + "loss": 4.1582, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.2270760625093767e-05, + "loss": 4.1542, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.226239105638698e-05, + "loss": 4.1509, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.225400510887646e-05, + "loss": 4.1442, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.224561916136594e-05, + "loss": 4.1646, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.223723321385542e-05, + "loss": 4.1606, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.22288472663449e-05, + "loss": 4.1602, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.222047769763811e-05, + "loss": 4.1651, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.221210812893133e-05, + "loss": 4.1558, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.22037221814208e-05, + "loss": 4.1581, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.219533623391028e-05, + "loss": 4.1533, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.218695028639976e-05, + "loss": 4.1488, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.217856433888924e-05, + "loss": 4.1409, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.217017839137872e-05, + "loss": 4.1476, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.21617924438682e-05, + "loss": 4.1525, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.215340649635769e-05, + "loss": 4.1663, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.214502054884717e-05, + "loss": 4.1525, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.2136650980140376e-05, + "loss": 4.1516, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.2128265032629856e-05, + "loss": 4.1614, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.2119879085119336e-05, + "loss": 4.1523, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.2111493137608816e-05, + "loss": 4.1621, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.2103107190098296e-05, + "loss": 4.1456, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.2094737621391505e-05, + "loss": 4.1358, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.2086351673880985e-05, + "loss": 4.1612, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.2077982105174194e-05, + "loss": 4.1549, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.2069596157663674e-05, + "loss": 4.1487, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.2061210210153154e-05, + "loss": 4.1414, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.2052824262642634e-05, + "loss": 4.152, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.204443831513212e-05, + "loss": 4.1318, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.20360523676216e-05, + "loss": 4.1566, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.202766642011108e-05, + "loss": 4.1403, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.201928047260056e-05, + "loss": 4.1403, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.201091090389377e-05, + "loss": 4.1544, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.200252495638325e-05, + "loss": 4.1409, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.199413900887273e-05, + "loss": 4.1416, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.198575306136221e-05, + "loss": 4.1473, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.197736711385169e-05, + "loss": 4.1305, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.19689975451449e-05, + "loss": 4.1423, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.196061159763438e-05, + "loss": 4.1499, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195222565012386e-05, + "loss": 4.1441, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.194383970261334e-05, + "loss": 4.1374, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.193545375510282e-05, + "loss": 4.1348, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.1927084186396034e-05, + "loss": 4.1291, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.1918698238885514e-05, + "loss": 4.1428, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.191031229137499e-05, + "loss": 4.1534, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.190192634386447e-05, + "loss": 4.1433, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.189354039635395e-05, + "loss": 4.15, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.188515444884343e-05, + "loss": 4.1514, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.1876784880136636e-05, + "loss": 4.155, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.186841531142985e-05, + "loss": 4.1316, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.186002936391933e-05, + "loss": 4.1465, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.185164341640881e-05, + "loss": 4.1471, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.184325746889829e-05, + "loss": 4.1287, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.183487152138777e-05, + "loss": 4.1468, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.182648557387725e-05, + "loss": 4.1425, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.181809962636673e-05, + "loss": 4.1481, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.180971367885621e-05, + "loss": 4.1463, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.180132773134569e-05, + "loss": 4.1264, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.179294178383517e-05, + "loss": 4.1402, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.178458859393211e-05, + "loss": 4.1388, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.177620264642159e-05, + "loss": 4.1443, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.176781669891107e-05, + "loss": 4.1405, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.175943075140055e-05, + "loss": 4.1488, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.175104480389003e-05, + "loss": 4.1415, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.174265885637951e-05, + "loss": 4.1364, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.1734272908868996e-05, + "loss": 4.1303, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.1725886961358476e-05, + "loss": 4.133, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.1717501013847956e-05, + "loss": 4.1474, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.1709115066337436e-05, + "loss": 4.1413, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.1700729118826916e-05, + "loss": 4.1397, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.1692359550120125e-05, + "loss": 4.1296, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.1683973602609605e-05, + "loss": 4.1372, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.1675587655099085e-05, + "loss": 4.1468, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.1667201707588565e-05, + "loss": 4.142, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.1658815760078045e-05, + "loss": 4.1392, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.1650429812567525e-05, + "loss": 4.1326, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.1642043865057e-05, + "loss": 4.134, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.163365791754648e-05, + "loss": 4.1408, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.1625271970035965e-05, + "loss": 4.1167, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.1616902401329174e-05, + "loss": 4.1303, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.1608516453818654e-05, + "loss": 4.1272, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.1600130506308134e-05, + "loss": 4.1411, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.159176093760135e-05, + "loss": 4.1272, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.158337499009082e-05, + "loss": 4.1419, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.15749890425803e-05, + "loss": 4.1277, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.156660309506978e-05, + "loss": 4.1339, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155821714755926e-05, + "loss": 4.136, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.154984757885247e-05, + "loss": 4.1205, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154146163134195e-05, + "loss": 4.1367, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153307568383143e-05, + "loss": 4.1449, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152470611512465e-05, + "loss": 4.1361, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151632016761413e-05, + "loss": 4.1342, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.150793422010361e-05, + "loss": 4.1237, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.149954827259309e-05, + "loss": 4.1381, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.149116232508257e-05, + "loss": 4.1326, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.148279275637578e-05, + "loss": 4.1343, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.147440680886526e-05, + "loss": 4.1243, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.146602086135474e-05, + "loss": 4.1316, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.1457634913844217e-05, + "loss": 4.1362, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.1449248966333697e-05, + "loss": 4.1336, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.1440863018823177e-05, + "loss": 4.1112, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.1432477071312656e-05, + "loss": 4.1383, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.1424091123802136e-05, + "loss": 4.1213, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.1415705176291616e-05, + "loss": 4.1415, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.1407319228781096e-05, + "loss": 4.131, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.139893328127058e-05, + "loss": 4.1392, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.139054733376006e-05, + "loss": 4.1187, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.138217776505327e-05, + "loss": 4.1404, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.137379181754275e-05, + "loss": 4.1348, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.136540587003223e-05, + "loss": 4.1356, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.135701992252171e-05, + "loss": 4.1239, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.1348633975011185e-05, + "loss": 4.137, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.1340248027500665e-05, + "loss": 4.1376, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.1331862079990145e-05, + "loss": 4.1409, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.1323476132479625e-05, + "loss": 4.1232, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.1315106563772834e-05, + "loss": 4.1336, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.130672061626232e-05, + "loss": 4.1328, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.12983346687518e-05, + "loss": 4.1231, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.128996510004501e-05, + "loss": 4.1282, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128157915253449e-05, + "loss": 4.1316, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.127319320502397e-05, + "loss": 4.1338, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.126480725751345e-05, + "loss": 4.1268, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125642131000293e-05, + "loss": 4.129, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 4.130771636962891, + "eval_runtime": 293.0916, + "eval_samples_per_second": 1301.951, + "eval_steps_per_second": 40.687, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.124803536249241e-05, + "loss": 4.1219, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.123964941498189e-05, + "loss": 4.108, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.12312798462751e-05, + "loss": 4.1307, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.122289389876458e-05, + "loss": 4.1296, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.121450795125406e-05, + "loss": 4.1298, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.120612200374354e-05, + "loss": 4.1296, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.119773605623302e-05, + "loss": 4.1211, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.1189350108722505e-05, + "loss": 4.1183, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.1180964161211985e-05, + "loss": 4.1249, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.1172578213701465e-05, + "loss": 4.1239, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.1164192266190945e-05, + "loss": 4.1331, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.1155822697484154e-05, + "loss": 4.1335, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.114745312877736e-05, + "loss": 4.1216, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.113906718126684e-05, + "loss": 4.1193, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.113068123375632e-05, + "loss": 4.1198, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.11222952862458e-05, + "loss": 4.1026, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.111392571753901e-05, + "loss": 4.1223, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.110553977002849e-05, + "loss": 4.1152, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.109715382251797e-05, + "loss": 4.1207, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.108876787500746e-05, + "loss": 4.1283, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.108038192749694e-05, + "loss": 4.1314, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.107199597998642e-05, + "loss": 4.1232, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.10636100324759e-05, + "loss": 4.1233, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.105522408496537e-05, + "loss": 4.1307, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.104683813745485e-05, + "loss": 4.114, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.103845218994433e-05, + "loss": 4.121, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.103006624243381e-05, + "loss": 4.1245, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.102168029492329e-05, + "loss": 4.1173, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.10133107262165e-05, + "loss": 4.1115, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.100494115750972e-05, + "loss": 4.1113, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.09965552099992e-05, + "loss": 4.1233, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.098816926248868e-05, + "loss": 4.1256, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.097978331497816e-05, + "loss": 4.1217, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.097139736746764e-05, + "loss": 4.1261, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.0963027798760846e-05, + "loss": 4.1144, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.0954641851250326e-05, + "loss": 4.1218, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.0946255903739806e-05, + "loss": 4.1229, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.0937869956229286e-05, + "loss": 4.106, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.0929500387522495e-05, + "loss": 4.1086, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.0921114440011975e-05, + "loss": 4.1093, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.0912728492501455e-05, + "loss": 4.1144, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.0904342544990935e-05, + "loss": 4.1279, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.0895956597480414e-05, + "loss": 4.1145, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.0887570649969894e-05, + "loss": 4.1116, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.0879184702459374e-05, + "loss": 4.1265, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.087079875494886e-05, + "loss": 4.115, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.086241280743834e-05, + "loss": 4.1249, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.085402685992782e-05, + "loss": 4.1109, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.08456409124173e-05, + "loss": 4.0996, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.083725496490678e-05, + "loss": 4.13, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.082888539619999e-05, + "loss": 4.1142, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.082049944868947e-05, + "loss": 4.1135, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.081211350117895e-05, + "loss": 4.109, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.080372755366843e-05, + "loss": 4.1077, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.079535798496164e-05, + "loss": 4.1011, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.078698841625485e-05, + "loss": 4.1126, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.077860246874433e-05, + "loss": 4.105, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.0770216521233815e-05, + "loss": 4.106, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.0761830573723295e-05, + "loss": 4.1172, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.0753444626212775e-05, + "loss": 4.1065, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.0745058678702255e-05, + "loss": 4.1018, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.0736672731191735e-05, + "loss": 4.1149, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.072828678368121e-05, + "loss": 4.0952, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.0719917214974424e-05, + "loss": 4.1077, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.0711531267463904e-05, + "loss": 4.11, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.070316169875711e-05, + "loss": 4.109, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.069477575124659e-05, + "loss": 4.101, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.068638980373607e-05, + "loss": 4.1014, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.067800385622555e-05, + "loss": 4.0919, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.066961790871503e-05, + "loss": 4.1095, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.066123196120451e-05, + "loss": 4.1174, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.065284601369399e-05, + "loss": 4.1105, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.064446006618347e-05, + "loss": 4.1102, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.063607411867295e-05, + "loss": 4.1176, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.06277209287699e-05, + "loss": 4.1228, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.0619351360063106e-05, + "loss": 4.0926, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.0610965412552586e-05, + "loss": 4.1113, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.0602579465042066e-05, + "loss": 4.1135, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.0594193517531546e-05, + "loss": 4.0898, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.0585807570021026e-05, + "loss": 4.1152, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.0577421622510506e-05, + "loss": 4.1029, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.0569035674999986e-05, + "loss": 4.1157, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.0560649727489466e-05, + "loss": 4.1136, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.0552263779978946e-05, + "loss": 4.0915, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.0543877832468426e-05, + "loss": 4.1002, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.0535491884957906e-05, + "loss": 4.1093, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.0527122316251115e-05, + "loss": 4.1092, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.0518736368740595e-05, + "loss": 4.1049, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.0510350421230075e-05, + "loss": 4.1112, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.0501964473719555e-05, + "loss": 4.1047, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.0493578526209035e-05, + "loss": 4.1009, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.0485208957502244e-05, + "loss": 4.1008, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.0476823009991724e-05, + "loss": 4.097, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.0468437062481204e-05, + "loss": 4.1118, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.046005111497069e-05, + "loss": 4.1069, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.045166516746017e-05, + "loss": 4.112, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.044331197755711e-05, + "loss": 4.0912, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.043492603004659e-05, + "loss": 4.1028, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.042654008253607e-05, + "loss": 4.1125, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.041815413502555e-05, + "loss": 4.1112, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.040976818751503e-05, + "loss": 4.104, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.040138224000451e-05, + "loss": 4.0975, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.039299629249399e-05, + "loss": 4.1016, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.038461034498347e-05, + "loss": 4.1068, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.037624077627668e-05, + "loss": 4.0818, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.036785482876616e-05, + "loss": 4.1002, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.035946888125564e-05, + "loss": 4.0904, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.0351082933745124e-05, + "loss": 4.108, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.0342696986234604e-05, + "loss": 4.0943, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.0334311038724084e-05, + "loss": 4.1025, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.032594147001729e-05, + "loss": 4.0965, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.031755552250677e-05, + "loss": 4.104, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.030916957499625e-05, + "loss": 4.0991, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.030078362748573e-05, + "loss": 4.0872, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.029239767997521e-05, + "loss": 4.104, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.028402811126842e-05, + "loss": 4.1092, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.02756421637579e-05, + "loss": 4.1025, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.026725621624738e-05, + "loss": 4.1038, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.025887026873686e-05, + "loss": 4.0873, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.025048432122634e-05, + "loss": 4.1025, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.024211475251956e-05, + "loss": 4.1035, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.023372880500904e-05, + "loss": 4.0935, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.022534285749852e-05, + "loss": 4.0956, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.021695690998799e-05, + "loss": 4.0972, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.020857096247747e-05, + "loss": 4.1036, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.020018501496695e-05, + "loss": 4.0985, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.019181544626016e-05, + "loss": 4.0785, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.018342949874964e-05, + "loss": 4.1044, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.017504355123912e-05, + "loss": 4.0853, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.01666576037286e-05, + "loss": 4.1079, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.015827165621808e-05, + "loss": 4.1007, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.014988570870756e-05, + "loss": 4.1033, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.0141499761197047e-05, + "loss": 4.0856, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.0133113813686527e-05, + "loss": 4.1116, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.0124744244979736e-05, + "loss": 4.1029, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.0116358297469216e-05, + "loss": 4.1, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.0107988728762425e-05, + "loss": 4.0964, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.0099602781251905e-05, + "loss": 4.0995, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.0091216833741385e-05, + "loss": 4.103, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.0082830886230865e-05, + "loss": 4.1126, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.0074444938720344e-05, + "loss": 4.0895, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.0066058991209824e-05, + "loss": 4.0997, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.0057673043699304e-05, + "loss": 4.1036, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.0049287096188784e-05, + "loss": 4.0924, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.0040901148678264e-05, + "loss": 4.0915, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.0032515201167744e-05, + "loss": 4.0985, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.002412925365723e-05, + "loss": 4.1009, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.001575968495044e-05, + "loss": 4.0938, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.000737373743992e-05, + "loss": 4.097, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 4.105889797210693, + "eval_runtime": 294.2794, + "eval_samples_per_second": 1296.696, + "eval_steps_per_second": 40.523, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.99989877899294e-05, + "loss": 4.0823, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.999060184241887e-05, + "loss": 4.0816, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.998221589490835e-05, + "loss": 4.094, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.997382994739783e-05, + "loss": 4.0961, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.996544399988731e-05, + "loss": 4.1028, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.995705805237679e-05, + "loss": 4.0933, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.994867210486627e-05, + "loss": 4.0912, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.994028615735575e-05, + "loss": 4.0903, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.993190020984523e-05, + "loss": 4.0882, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.992351426233471e-05, + "loss": 4.0933, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.991512831482419e-05, + "loss": 4.0988, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.990674236731368e-05, + "loss": 4.0991, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.989837279860689e-05, + "loss": 4.0896, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.988998685109637e-05, + "loss": 4.0896, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.988160090358585e-05, + "loss": 4.091, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.987321495607533e-05, + "loss": 4.074, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.986482900856481e-05, + "loss": 4.0873, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.985644306105429e-05, + "loss": 4.0835, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.984805711354376e-05, + "loss": 4.0896, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.983967116603324e-05, + "loss": 4.093, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.983128521852272e-05, + "loss": 4.1003, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.98228992710122e-05, + "loss": 4.0923, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.981452970230542e-05, + "loss": 4.0916, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.98061437547949e-05, + "loss": 4.0968, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.979775780728438e-05, + "loss": 4.0868, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.978937185977386e-05, + "loss": 4.0889, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.978098591226334e-05, + "loss": 4.0929, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.977259996475282e-05, + "loss": 4.0866, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.97642140172423e-05, + "loss": 4.0864, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.975582806973178e-05, + "loss": 4.0775, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.9747458501024986e-05, + "loss": 4.0898, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.9739072553514466e-05, + "loss": 4.097, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.9730686606003946e-05, + "loss": 4.0909, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.9722317037297155e-05, + "loss": 4.091, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.9713931089786635e-05, + "loss": 4.082, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.970556152107985e-05, + "loss": 4.097, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.969717557356933e-05, + "loss": 4.09, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.968878962605881e-05, + "loss": 4.0777, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.968040367854829e-05, + "loss": 4.08, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967201773103777e-05, + "loss": 4.0759, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.966363178352725e-05, + "loss": 4.0818, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.965524583601673e-05, + "loss": 4.097, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964685988850621e-05, + "loss": 4.0841, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.963847394099569e-05, + "loss": 4.0823, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.963008799348517e-05, + "loss": 4.0937, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.962171842477838e-05, + "loss": 4.0839, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.961333247726786e-05, + "loss": 4.0966, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.960494652975734e-05, + "loss": 4.084, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.959656058224682e-05, + "loss": 4.0621, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.9588191013540035e-05, + "loss": 4.1013, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.9579805066029515e-05, + "loss": 4.0847, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.9571419118518995e-05, + "loss": 4.0854, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.9563033171008475e-05, + "loss": 4.0788, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.9554647223497955e-05, + "loss": 4.0759, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.954626127598743e-05, + "loss": 4.0746, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.953787532847691e-05, + "loss": 4.0828, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.952948938096639e-05, + "loss": 4.0754, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.95211198122596e-05, + "loss": 4.0757, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.951273386474908e-05, + "loss": 4.0897, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.950438067484602e-05, + "loss": 4.0756, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.949599472733551e-05, + "loss": 4.068, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.948760877982499e-05, + "loss": 4.0894, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.947922283231447e-05, + "loss": 4.0639, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.947083688480395e-05, + "loss": 4.0723, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.946245093729342e-05, + "loss": 4.0865, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.94540649897829e-05, + "loss": 4.0808, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.944567904227238e-05, + "loss": 4.0688, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.943729309476186e-05, + "loss": 4.0753, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.942890714725134e-05, + "loss": 4.0636, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.942052119974082e-05, + "loss": 4.0806, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.94121352522303e-05, + "loss": 4.0853, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.940376568352351e-05, + "loss": 4.0781, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.939537973601299e-05, + "loss": 4.0793, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.938699378850247e-05, + "loss": 4.0904, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.937860784099196e-05, + "loss": 4.0918, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.9370254651088896e-05, + "loss": 4.0647, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.9361868703578376e-05, + "loss": 4.0842, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.9353482756067856e-05, + "loss": 4.0788, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.9345096808557336e-05, + "loss": 4.063, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.9336710861046816e-05, + "loss": 4.0831, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.9328324913536296e-05, + "loss": 4.0773, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.9319938966025776e-05, + "loss": 4.0881, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.9311553018515256e-05, + "loss": 4.0821, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.9303167071004735e-05, + "loss": 4.0655, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.9294781123494215e-05, + "loss": 4.0701, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.9286395175983695e-05, + "loss": 4.0831, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.9278009228473175e-05, + "loss": 4.0756, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.926963965976639e-05, + "loss": 4.0798, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.92612700910596e-05, + "loss": 4.0799, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925288414354908e-05, + "loss": 4.0732, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.924449819603856e-05, + "loss": 4.0733, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923611224852804e-05, + "loss": 4.0724, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.922772630101752e-05, + "loss": 4.0686, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.9219340353507e-05, + "loss": 4.0829, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.921097078480021e-05, + "loss": 4.0766, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.920258483728969e-05, + "loss": 4.0823, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.919419888977917e-05, + "loss": 4.0641, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.918581294226865e-05, + "loss": 4.0739, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.9177443373561865e-05, + "loss": 4.0817, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.9169057426051345e-05, + "loss": 4.0782, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.9160671478540825e-05, + "loss": 4.076, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.9152285531030305e-05, + "loss": 4.071, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.9143899583519785e-05, + "loss": 4.0763, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.913551363600926e-05, + "loss": 4.075, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.912712768849874e-05, + "loss": 4.0622, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.911874174098822e-05, + "loss": 4.0685, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.9110372172281434e-05, + "loss": 4.0623, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.910198622477091e-05, + "loss": 4.0825, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.909360027726039e-05, + "loss": 4.0664, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.908521432974987e-05, + "loss": 4.072, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.907684476104308e-05, + "loss": 4.0651, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.906845881353256e-05, + "loss": 4.081, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.906007286602204e-05, + "loss": 4.0693, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.905168691851152e-05, + "loss": 4.0602, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.9043300971001e-05, + "loss": 4.0781, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.903493140229421e-05, + "loss": 4.0817, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.902654545478369e-05, + "loss": 4.0749, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.901815950727317e-05, + "loss": 4.0756, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.900977355976265e-05, + "loss": 4.0628, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.900138761225213e-05, + "loss": 4.0736, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.899300166474161e-05, + "loss": 4.0752, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.898461571723109e-05, + "loss": 4.0666, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.897622976972057e-05, + "loss": 4.0656, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.896786020101379e-05, + "loss": 4.0725, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.8959490632306996e-05, + "loss": 4.0766, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.8951104684796476e-05, + "loss": 4.0725, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.8942718737285956e-05, + "loss": 4.0507, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.8934332789775436e-05, + "loss": 4.0753, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.8925946842264916e-05, + "loss": 4.0609, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.8917560894754396e-05, + "loss": 4.0783, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.8909191326047605e-05, + "loss": 4.0746, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.8900805378537085e-05, + "loss": 4.0751, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.8892419431026565e-05, + "loss": 4.0574, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.8884033483516045e-05, + "loss": 4.0836, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.8875647536005525e-05, + "loss": 4.074, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.8867261588495005e-05, + "loss": 4.0775, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.885889201978822e-05, + "loss": 4.0703, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.885052245108143e-05, + "loss": 4.0667, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.884213650357091e-05, + "loss": 4.0751, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.883375055606039e-05, + "loss": 4.0889, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.882536460854987e-05, + "loss": 4.0626, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.881697866103935e-05, + "loss": 4.0733, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.880859271352883e-05, + "loss": 4.0765, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.880020676601831e-05, + "loss": 4.0634, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.879182081850779e-05, + "loss": 4.0661, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.878343487099727e-05, + "loss": 4.0716, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.877504892348674e-05, + "loss": 4.0753, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.876666297597622e-05, + "loss": 4.0713, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.87582770284657e-05, + "loss": 4.0694, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 4.0864973068237305, + "eval_runtime": 292.5469, + "eval_samples_per_second": 1304.375, + "eval_steps_per_second": 40.763, + "step": 686880 + }, + { + "epoch": 0.0, + "learning_rate": 3.874990745975892e-05, + "loss": 4.0546, + "step": 687104 + }, + { + "epoch": 0.0, + "learning_rate": 3.87415215122484e-05, + "loss": 4.0535, + "step": 687616 + }, + { + "epoch": 0.0, + "learning_rate": 3.873313556473788e-05, + "loss": 4.0692, + "step": 688128 + }, + { + "epoch": 0.0, + "learning_rate": 3.872474961722736e-05, + "loss": 4.0717, + "step": 688640 + }, + { + "epoch": 0.0, + "learning_rate": 3.871636366971684e-05, + "loss": 4.0743, + "step": 689152 + }, + { + "epoch": 0.0, + "learning_rate": 3.870797772220632e-05, + "loss": 4.0649, + "step": 689664 + }, + { + "epoch": 0.0, + "learning_rate": 3.86995917746958e-05, + "loss": 4.0692, + "step": 690176 + }, + { + "epoch": 0.0, + "learning_rate": 3.869120582718528e-05, + "loss": 4.0616, + "step": 690688 + }, + { + "epoch": 0.0, + "learning_rate": 3.868281987967476e-05, + "loss": 4.0594, + "step": 691200 + }, + { + "epoch": 0.0, + "learning_rate": 3.867443393216424e-05, + "loss": 4.0697, + "step": 691712 + }, + { + "epoch": 0.0, + "learning_rate": 3.866604798465372e-05, + "loss": 4.0732, + "step": 692224 + }, + { + "epoch": 0.0, + "learning_rate": 3.86576620371432e-05, + "loss": 4.0702, + "step": 692736 + }, + { + "epoch": 0.0, + "learning_rate": 3.864927608963268e-05, + "loss": 4.072, + "step": 693248 + }, + { + "epoch": 0.0, + "learning_rate": 3.864089014212216e-05, + "loss": 4.0567, + "step": 693760 + }, + { + "epoch": 0.0, + "learning_rate": 3.863250419461164e-05, + "loss": 4.0621, + "step": 694272 + }, + { + "epoch": 0.0, + "learning_rate": 3.862411824710112e-05, + "loss": 4.0483, + "step": 694784 + }, + { + "epoch": 0.0, + "learning_rate": 3.86157322995906e-05, + "loss": 4.0597, + "step": 695296 + }, + { + "epoch": 0.0, + "learning_rate": 3.860734635208008e-05, + "loss": 4.0607, + "step": 695808 + }, + { + "epoch": 0.0, + "learning_rate": 3.859896040456956e-05, + "loss": 4.0609, + "step": 696320 + }, + { + "epoch": 0.0, + "learning_rate": 3.859057445705904e-05, + "loss": 4.0647, + "step": 696832 + }, + { + "epoch": 0.0, + "learning_rate": 3.858220488835225e-05, + "loss": 4.0758, + "step": 697344 + }, + { + "epoch": 0.0, + "learning_rate": 3.857381894084173e-05, + "loss": 4.0677, + "step": 697856 + }, + { + "epoch": 0.0, + "learning_rate": 3.856543299333121e-05, + "loss": 4.068, + "step": 698368 + }, + { + "epoch": 0.0, + "learning_rate": 3.8557047045820687e-05, + "loss": 4.0673, + "step": 698880 + }, + { + "epoch": 0.0, + "learning_rate": 3.8548677477113896e-05, + "loss": 4.0616, + "step": 699392 + }, + { + "epoch": 0.0, + "learning_rate": 3.8540291529603376e-05, + "loss": 4.0628, + "step": 699904 + }, + { + "epoch": 0.0, + "learning_rate": 3.8531905582092856e-05, + "loss": 4.0666, + "step": 700416 + }, + { + "epoch": 0.0, + "learning_rate": 3.852351963458234e-05, + "loss": 4.0631, + "step": 700928 + }, + { + "epoch": 0.0, + "learning_rate": 3.851513368707182e-05, + "loss": 4.0571, + "step": 701440 + }, + { + "epoch": 0.0, + "learning_rate": 3.850676411836503e-05, + "loss": 4.0556, + "step": 701952 + }, + { + "epoch": 0.01, + "learning_rate": 3.849839454965824e-05, + "loss": 4.0587, + "step": 702464 + }, + { + "epoch": 0.01, + "learning_rate": 3.849000860214772e-05, + "loss": 4.068, + "step": 702976 + }, + { + "epoch": 0.01, + "learning_rate": 3.84816226546372e-05, + "loss": 4.0685, + "step": 703488 + }, + { + "epoch": 0.01, + "learning_rate": 3.847323670712668e-05, + "loss": 4.0654, + "step": 704000 + }, + { + "epoch": 0.01, + "learning_rate": 3.846485075961616e-05, + "loss": 4.0569, + "step": 704512 + }, + { + "epoch": 0.01, + "learning_rate": 3.845648119090937e-05, + "loss": 4.0659, + "step": 705024 + }, + { + "epoch": 0.01, + "learning_rate": 3.844809524339885e-05, + "loss": 4.0689, + "step": 705536 + }, + { + "epoch": 0.01, + "learning_rate": 3.843970929588833e-05, + "loss": 4.0502, + "step": 706048 + }, + { + "epoch": 0.01, + "learning_rate": 3.843132334837781e-05, + "loss": 4.0545, + "step": 706560 + }, + { + "epoch": 0.01, + "learning_rate": 3.8422953779671025e-05, + "loss": 4.0486, + "step": 707072 + }, + { + "epoch": 0.01, + "learning_rate": 3.8414567832160505e-05, + "loss": 4.0577, + "step": 707584 + }, + { + "epoch": 0.01, + "learning_rate": 3.8406181884649985e-05, + "loss": 4.0684, + "step": 708096 + }, + { + "epoch": 0.01, + "learning_rate": 3.8397795937139465e-05, + "loss": 4.0629, + "step": 708608 + }, + { + "epoch": 0.01, + "learning_rate": 3.8389409989628945e-05, + "loss": 4.0575, + "step": 709120 + }, + { + "epoch": 0.01, + "learning_rate": 3.8381040420922154e-05, + "loss": 4.0683, + "step": 709632 + }, + { + "epoch": 0.01, + "learning_rate": 3.8372654473411634e-05, + "loss": 4.0586, + "step": 710144 + }, + { + "epoch": 0.01, + "learning_rate": 3.8364268525901114e-05, + "loss": 4.0668, + "step": 710656 + }, + { + "epoch": 0.01, + "learning_rate": 3.8355882578390594e-05, + "loss": 4.0647, + "step": 711168 + }, + { + "epoch": 0.01, + "learning_rate": 3.8347496630880074e-05, + "loss": 4.0315, + "step": 711680 + }, + { + "epoch": 0.01, + "learning_rate": 3.833912706217328e-05, + "loss": 4.0795, + "step": 712192 + }, + { + "epoch": 0.01, + "learning_rate": 3.83307574934665e-05, + "loss": 4.0557, + "step": 712704 + }, + { + "epoch": 0.01, + "learning_rate": 3.832237154595598e-05, + "loss": 4.068, + "step": 713216 + }, + { + "epoch": 0.01, + "learning_rate": 3.831398559844546e-05, + "loss": 4.0475, + "step": 713728 + }, + { + "epoch": 0.01, + "learning_rate": 3.830559965093494e-05, + "loss": 4.0552, + "step": 714240 + }, + { + "epoch": 0.01, + "learning_rate": 3.829721370342442e-05, + "loss": 4.0482, + "step": 714752 + }, + { + "epoch": 0.01, + "learning_rate": 3.82888277559139e-05, + "loss": 4.0539, + "step": 715264 + }, + { + "epoch": 0.01, + "learning_rate": 3.828044180840338e-05, + "loss": 4.0518, + "step": 715776 + }, + { + "epoch": 0.01, + "learning_rate": 3.827205586089286e-05, + "loss": 4.0491, + "step": 716288 + }, + { + "epoch": 0.01, + "learning_rate": 3.826366991338234e-05, + "loss": 4.0696, + "step": 716800 + }, + { + "epoch": 0.01, + "learning_rate": 3.825528396587182e-05, + "loss": 4.0508, + "step": 717312 + }, + { + "epoch": 0.01, + "learning_rate": 3.824689801836129e-05, + "loss": 4.0432, + "step": 717824 + }, + { + "epoch": 0.01, + "learning_rate": 3.823852844965451e-05, + "loss": 4.0636, + "step": 718336 + }, + { + "epoch": 0.01, + "learning_rate": 3.823014250214399e-05, + "loss": 4.0411, + "step": 718848 + }, + { + "epoch": 0.01, + "learning_rate": 3.822175655463347e-05, + "loss": 4.0445, + "step": 719360 + }, + { + "epoch": 0.01, + "learning_rate": 3.821337060712295e-05, + "loss": 4.0602, + "step": 719872 + }, + { + "epoch": 0.01, + "learning_rate": 3.820498465961243e-05, + "loss": 4.0537, + "step": 720384 + }, + { + "epoch": 0.01, + "learning_rate": 3.819659871210191e-05, + "loss": 4.0454, + "step": 720896 + }, + { + "epoch": 0.01, + "learning_rate": 3.8188229143395116e-05, + "loss": 4.0458, + "step": 721408 + }, + { + "epoch": 0.01, + "learning_rate": 3.8179843195884596e-05, + "loss": 4.0425, + "step": 721920 + }, + { + "epoch": 0.01, + "learning_rate": 3.8171457248374076e-05, + "loss": 4.0539, + "step": 722432 + }, + { + "epoch": 0.01, + "learning_rate": 3.8163071300863556e-05, + "loss": 4.0633, + "step": 722944 + }, + { + "epoch": 0.01, + "learning_rate": 3.8154685353353036e-05, + "loss": 4.0514, + "step": 723456 + }, + { + "epoch": 0.01, + "learning_rate": 3.8146315784646245e-05, + "loss": 4.0565, + "step": 723968 + }, + { + "epoch": 0.01, + "learning_rate": 3.8137929837135725e-05, + "loss": 4.0614, + "step": 724480 + }, + { + "epoch": 0.01, + "learning_rate": 3.8129543889625205e-05, + "loss": 4.0689, + "step": 724992 + }, + { + "epoch": 0.01, + "learning_rate": 3.8121157942114685e-05, + "loss": 4.0395, + "step": 725504 + }, + { + "epoch": 0.01, + "learning_rate": 3.8112771994604165e-05, + "loss": 4.0609, + "step": 726016 + }, + { + "epoch": 0.01, + "learning_rate": 3.810438604709365e-05, + "loss": 4.0521, + "step": 726528 + }, + { + "epoch": 0.01, + "learning_rate": 3.809600009958313e-05, + "loss": 4.0401, + "step": 727040 + }, + { + "epoch": 0.01, + "learning_rate": 3.808761415207261e-05, + "loss": 4.0558, + "step": 727552 + }, + { + "epoch": 0.01, + "learning_rate": 3.807922820456209e-05, + "loss": 4.0607, + "step": 728064 + }, + { + "epoch": 0.01, + "learning_rate": 3.80708586358553e-05, + "loss": 4.0609, + "step": 728576 + }, + { + "epoch": 0.01, + "learning_rate": 3.806247268834478e-05, + "loss": 4.0626, + "step": 729088 + }, + { + "epoch": 0.01, + "learning_rate": 3.805408674083426e-05, + "loss": 4.0388, + "step": 729600 + }, + { + "epoch": 0.01, + "learning_rate": 3.804570079332374e-05, + "loss": 4.0436, + "step": 730112 + }, + { + "epoch": 0.01, + "learning_rate": 3.803733122461695e-05, + "loss": 4.059, + "step": 730624 + }, + { + "epoch": 0.01, + "learning_rate": 3.802894527710643e-05, + "loss": 4.0489, + "step": 731136 + }, + { + "epoch": 0.01, + "learning_rate": 3.802055932959591e-05, + "loss": 4.0536, + "step": 731648 + }, + { + "epoch": 0.01, + "learning_rate": 3.801217338208539e-05, + "loss": 4.0577, + "step": 732160 + }, + { + "epoch": 0.02, + "learning_rate": 3.800378743457487e-05, + "loss": 4.0489, + "step": 732672 + }, + { + "epoch": 0.02, + "learning_rate": 3.7995417865868085e-05, + "loss": 4.0489, + "step": 733184 + }, + { + "epoch": 0.02, + "learning_rate": 3.7987031918357565e-05, + "loss": 4.0489, + "step": 733696 + }, + { + "epoch": 0.02, + "learning_rate": 3.7978645970847045e-05, + "loss": 4.0448, + "step": 734208 + }, + { + "epoch": 0.02, + "learning_rate": 3.7970276402140254e-05, + "loss": 4.0571, + "step": 734720 + }, + { + "epoch": 0.02, + "learning_rate": 3.7961890454629734e-05, + "loss": 4.0539, + "step": 735232 + }, + { + "epoch": 0.02, + "learning_rate": 3.7953504507119214e-05, + "loss": 4.0558, + "step": 735744 + }, + { + "epoch": 0.02, + "learning_rate": 3.7945134938412423e-05, + "loss": 4.0444, + "step": 736256 + }, + { + "epoch": 0.02, + "learning_rate": 3.7936748990901903e-05, + "loss": 4.0436, + "step": 736768 + }, + { + "epoch": 0.02, + "learning_rate": 3.7928363043391383e-05, + "loss": 4.0591, + "step": 737280 + }, + { + "epoch": 0.02, + "learning_rate": 3.791997709588086e-05, + "loss": 4.0554, + "step": 737792 + }, + { + "epoch": 0.02, + "learning_rate": 3.791159114837034e-05, + "loss": 4.0525, + "step": 738304 + }, + { + "epoch": 0.02, + "learning_rate": 3.790320520085982e-05, + "loss": 4.0501, + "step": 738816 + }, + { + "epoch": 0.02, + "learning_rate": 3.78948192533493e-05, + "loss": 4.05, + "step": 739328 + }, + { + "epoch": 0.02, + "learning_rate": 3.788643330583878e-05, + "loss": 4.0445, + "step": 739840 + }, + { + "epoch": 0.02, + "learning_rate": 3.787804735832826e-05, + "loss": 4.0457, + "step": 740352 + }, + { + "epoch": 0.02, + "learning_rate": 3.786966141081774e-05, + "loss": 4.0417, + "step": 740864 + }, + { + "epoch": 0.02, + "learning_rate": 3.786129184211095e-05, + "loss": 4.0381, + "step": 741376 + }, + { + "epoch": 0.02, + "learning_rate": 3.785290589460043e-05, + "loss": 4.0593, + "step": 741888 + }, + { + "epoch": 0.02, + "learning_rate": 3.784451994708991e-05, + "loss": 4.0453, + "step": 742400 + }, + { + "epoch": 0.02, + "learning_rate": 3.783613399957939e-05, + "loss": 4.0475, + "step": 742912 + }, + { + "epoch": 0.02, + "learning_rate": 3.78277644308726e-05, + "loss": 4.0382, + "step": 743424 + }, + { + "epoch": 0.02, + "learning_rate": 3.781937848336208e-05, + "loss": 4.0547, + "step": 743936 + }, + { + "epoch": 0.02, + "learning_rate": 3.781099253585156e-05, + "loss": 4.0481, + "step": 744448 + }, + { + "epoch": 0.02, + "learning_rate": 3.780260658834104e-05, + "loss": 4.0367, + "step": 744960 + }, + { + "epoch": 0.02, + "learning_rate": 3.779422064083053e-05, + "loss": 4.0581, + "step": 745472 + }, + { + "epoch": 0.02, + "learning_rate": 3.778583469332001e-05, + "loss": 4.0553, + "step": 745984 + }, + { + "epoch": 0.02, + "learning_rate": 3.777744874580949e-05, + "loss": 4.0504, + "step": 746496 + }, + { + "epoch": 0.02, + "learning_rate": 3.776906279829897e-05, + "loss": 4.0481, + "step": 747008 + }, + { + "epoch": 0.02, + "learning_rate": 3.776069322959218e-05, + "loss": 4.0415, + "step": 747520 + }, + { + "epoch": 0.02, + "learning_rate": 3.775230728208166e-05, + "loss": 4.0462, + "step": 748032 + }, + { + "epoch": 0.02, + "learning_rate": 3.7743937713374866e-05, + "loss": 4.054, + "step": 748544 + }, + { + "epoch": 0.02, + "learning_rate": 3.7735551765864346e-05, + "loss": 4.0408, + "step": 749056 + }, + { + "epoch": 0.02, + "learning_rate": 3.7727165818353826e-05, + "loss": 4.0449, + "step": 749568 + }, + { + "epoch": 0.02, + "learning_rate": 3.7718779870843306e-05, + "loss": 4.0484, + "step": 750080 + }, + { + "epoch": 0.02, + "learning_rate": 3.7710393923332786e-05, + "loss": 4.052, + "step": 750592 + }, + { + "epoch": 0.02, + "learning_rate": 3.7702007975822266e-05, + "loss": 4.0481, + "step": 751104 + }, + { + "epoch": 0.02, + "learning_rate": 3.7693638407115475e-05, + "loss": 4.0315, + "step": 751616 + }, + { + "epoch": 0.02, + "learning_rate": 3.768525245960496e-05, + "loss": 4.0534, + "step": 752128 + }, + { + "epoch": 0.02, + "learning_rate": 3.767686651209444e-05, + "loss": 4.0359, + "step": 752640 + }, + { + "epoch": 0.02, + "learning_rate": 3.766848056458392e-05, + "loss": 4.0553, + "step": 753152 + }, + { + "epoch": 0.02, + "learning_rate": 3.76600946170734e-05, + "loss": 4.048, + "step": 753664 + }, + { + "epoch": 0.02, + "learning_rate": 3.765170866956288e-05, + "loss": 4.0558, + "step": 754176 + }, + { + "epoch": 0.02, + "learning_rate": 3.764332272205236e-05, + "loss": 4.0298, + "step": 754688 + }, + { + "epoch": 0.02, + "learning_rate": 3.763493677454184e-05, + "loss": 4.0605, + "step": 755200 + }, + { + "epoch": 0.02, + "learning_rate": 3.762658358463878e-05, + "loss": 4.0468, + "step": 755712 + }, + { + "epoch": 0.02, + "learning_rate": 3.761819763712826e-05, + "loss": 4.0548, + "step": 756224 + }, + { + "epoch": 0.02, + "learning_rate": 3.760981168961774e-05, + "loss": 4.0496, + "step": 756736 + }, + { + "epoch": 0.02, + "learning_rate": 3.760142574210722e-05, + "loss": 4.0391, + "step": 757248 + }, + { + "epoch": 0.02, + "learning_rate": 3.75930397945967e-05, + "loss": 4.0562, + "step": 757760 + }, + { + "epoch": 0.02, + "learning_rate": 3.7584670225889915e-05, + "loss": 4.064, + "step": 758272 + }, + { + "epoch": 0.02, + "learning_rate": 3.7576284278379395e-05, + "loss": 4.0432, + "step": 758784 + }, + { + "epoch": 0.02, + "learning_rate": 3.7567898330868875e-05, + "loss": 4.0472, + "step": 759296 + }, + { + "epoch": 0.02, + "learning_rate": 3.7559512383358355e-05, + "loss": 4.052, + "step": 759808 + }, + { + "epoch": 0.02, + "learning_rate": 3.7551126435847835e-05, + "loss": 4.0401, + "step": 760320 + }, + { + "epoch": 0.02, + "learning_rate": 3.7542740488337315e-05, + "loss": 4.0421, + "step": 760832 + }, + { + "epoch": 0.02, + "learning_rate": 3.753435454082679e-05, + "loss": 4.0522, + "step": 761344 + }, + { + "epoch": 0.02, + "learning_rate": 3.752596859331627e-05, + "loss": 4.0496, + "step": 761856 + }, + { + "epoch": 0.02, + "learning_rate": 3.7517599024609484e-05, + "loss": 4.0504, + "step": 762368 + }, + { + "epoch": 0.02, + "learning_rate": 3.750921307709896e-05, + "loss": 4.043, + "step": 762880 + }, + { + "epoch": 0.03, + "eval_loss": 4.0705389976501465, + "eval_runtime": 294.3964, + "eval_samples_per_second": 1296.181, + "eval_steps_per_second": 40.507, + "step": 763200 + }, + { + "epoch": 1.0, + "learning_rate": 3.750082712958844e-05, + "loss": 4.0342, + "step": 763392 + }, + { + "epoch": 1.0, + "learning_rate": 3.749244118207792e-05, + "loss": 4.0299, + "step": 763904 + }, + { + "epoch": 1.0, + "learning_rate": 3.74840552345674e-05, + "loss": 4.0438, + "step": 764416 + }, + { + "epoch": 1.0, + "learning_rate": 3.747568566586061e-05, + "loss": 4.0498, + "step": 764928 + }, + { + "epoch": 1.0, + "learning_rate": 3.746729971835009e-05, + "loss": 4.0511, + "step": 765440 + }, + { + "epoch": 1.0, + "learning_rate": 3.745891377083957e-05, + "loss": 4.0453, + "step": 765952 + }, + { + "epoch": 1.0, + "learning_rate": 3.745054420213279e-05, + "loss": 4.0451, + "step": 766464 + }, + { + "epoch": 1.0, + "learning_rate": 3.744215825462226e-05, + "loss": 4.0378, + "step": 766976 + }, + { + "epoch": 1.0, + "learning_rate": 3.743377230711174e-05, + "loss": 4.0401, + "step": 767488 + }, + { + "epoch": 1.0, + "learning_rate": 3.742538635960122e-05, + "loss": 4.044, + "step": 768000 + }, + { + "epoch": 1.0, + "learning_rate": 3.74170004120907e-05, + "loss": 4.0484, + "step": 768512 + }, + { + "epoch": 1.0, + "learning_rate": 3.740861446458018e-05, + "loss": 4.0488, + "step": 769024 + }, + { + "epoch": 1.0, + "learning_rate": 3.740024489587339e-05, + "loss": 4.0519, + "step": 769536 + }, + { + "epoch": 1.0, + "learning_rate": 3.739185894836287e-05, + "loss": 4.0325, + "step": 770048 + }, + { + "epoch": 1.0, + "learning_rate": 3.738347300085235e-05, + "loss": 4.0417, + "step": 770560 + }, + { + "epoch": 1.0, + "learning_rate": 3.737508705334184e-05, + "loss": 4.0221, + "step": 771072 + }, + { + "epoch": 1.0, + "learning_rate": 3.736670110583132e-05, + "loss": 4.038, + "step": 771584 + }, + { + "epoch": 1.0, + "learning_rate": 3.73583151583208e-05, + "loss": 4.0374, + "step": 772096 + }, + { + "epoch": 1.0, + "learning_rate": 3.734992921081028e-05, + "loss": 4.0371, + "step": 772608 + }, + { + "epoch": 1.0, + "learning_rate": 3.734154326329976e-05, + "loss": 4.0427, + "step": 773120 + }, + { + "epoch": 1.0, + "learning_rate": 3.7333173694592966e-05, + "loss": 4.0518, + "step": 773632 + }, + { + "epoch": 1.0, + "learning_rate": 3.7324787747082446e-05, + "loss": 4.0471, + "step": 774144 + }, + { + "epoch": 1.0, + "learning_rate": 3.7316401799571926e-05, + "loss": 4.0464, + "step": 774656 + }, + { + "epoch": 1.0, + "learning_rate": 3.7308015852061406e-05, + "loss": 4.0402, + "step": 775168 + }, + { + "epoch": 1.0, + "learning_rate": 3.7299629904550886e-05, + "loss": 4.0431, + "step": 775680 + }, + { + "epoch": 1.0, + "learning_rate": 3.7291243957040366e-05, + "loss": 4.0397, + "step": 776192 + }, + { + "epoch": 1.0, + "learning_rate": 3.7282858009529846e-05, + "loss": 4.0427, + "step": 776704 + }, + { + "epoch": 1.0, + "learning_rate": 3.727447206201932e-05, + "loss": 4.0418, + "step": 777216 + }, + { + "epoch": 1.0, + "learning_rate": 3.7266102493312535e-05, + "loss": 4.0333, + "step": 777728 + }, + { + "epoch": 1.0, + "learning_rate": 3.7257716545802015e-05, + "loss": 4.0333, + "step": 778240 + }, + { + "epoch": 1.01, + "learning_rate": 3.72493305982915e-05, + "loss": 4.0331, + "step": 778752 + }, + { + "epoch": 1.01, + "learning_rate": 3.7240944650780975e-05, + "loss": 4.0483, + "step": 779264 + }, + { + "epoch": 1.01, + "learning_rate": 3.723257508207419e-05, + "loss": 4.0489, + "step": 779776 + }, + { + "epoch": 1.01, + "learning_rate": 3.722418913456367e-05, + "loss": 4.039, + "step": 780288 + }, + { + "epoch": 1.01, + "learning_rate": 3.721580318705315e-05, + "loss": 4.0382, + "step": 780800 + }, + { + "epoch": 1.01, + "learning_rate": 3.720743361834636e-05, + "loss": 4.0367, + "step": 781312 + }, + { + "epoch": 1.01, + "learning_rate": 3.719904767083584e-05, + "loss": 4.0494, + "step": 781824 + }, + { + "epoch": 1.01, + "learning_rate": 3.719067810212905e-05, + "loss": 4.0312, + "step": 782336 + }, + { + "epoch": 1.01, + "learning_rate": 3.718229215461853e-05, + "loss": 4.0313, + "step": 782848 + }, + { + "epoch": 1.01, + "learning_rate": 3.717390620710801e-05, + "loss": 4.0265, + "step": 783360 + }, + { + "epoch": 1.01, + "learning_rate": 3.716552025959749e-05, + "loss": 4.0374, + "step": 783872 + }, + { + "epoch": 1.01, + "learning_rate": 3.715713431208697e-05, + "loss": 4.0433, + "step": 784384 + }, + { + "epoch": 1.01, + "learning_rate": 3.714874836457645e-05, + "loss": 4.0396, + "step": 784896 + }, + { + "epoch": 1.01, + "learning_rate": 3.714036241706593e-05, + "loss": 4.037, + "step": 785408 + }, + { + "epoch": 1.01, + "learning_rate": 3.713197646955541e-05, + "loss": 4.0447, + "step": 785920 + }, + { + "epoch": 1.01, + "learning_rate": 3.712360690084862e-05, + "loss": 4.0341, + "step": 786432 + }, + { + "epoch": 1.01, + "learning_rate": 3.71152209533381e-05, + "loss": 4.0462, + "step": 786944 + }, + { + "epoch": 1.01, + "learning_rate": 3.710683500582758e-05, + "loss": 4.0404, + "step": 787456 + }, + { + "epoch": 1.01, + "learning_rate": 3.709844905831706e-05, + "loss": 4.0114, + "step": 787968 + }, + { + "epoch": 1.01, + "learning_rate": 3.709006311080654e-05, + "loss": 4.0524, + "step": 788480 + }, + { + "epoch": 1.01, + "learning_rate": 3.7081693542099746e-05, + "loss": 4.0335, + "step": 788992 + }, + { + "epoch": 1.01, + "learning_rate": 3.7073307594589226e-05, + "loss": 4.0471, + "step": 789504 + }, + { + "epoch": 1.01, + "learning_rate": 3.7064921647078706e-05, + "loss": 4.0289, + "step": 790016 + }, + { + "epoch": 1.01, + "learning_rate": 3.705653569956819e-05, + "loss": 4.0317, + "step": 790528 + }, + { + "epoch": 1.01, + "learning_rate": 3.704814975205767e-05, + "loss": 4.0238, + "step": 791040 + }, + { + "epoch": 1.01, + "learning_rate": 3.703976380454715e-05, + "loss": 4.0333, + "step": 791552 + }, + { + "epoch": 1.01, + "learning_rate": 3.703137785703663e-05, + "loss": 4.0309, + "step": 792064 + }, + { + "epoch": 1.01, + "learning_rate": 3.702300828832984e-05, + "loss": 4.0248, + "step": 792576 + }, + { + "epoch": 1.01, + "learning_rate": 3.701462234081932e-05, + "loss": 4.0465, + "step": 793088 + }, + { + "epoch": 1.01, + "learning_rate": 3.70062363933088e-05, + "loss": 4.0348, + "step": 793600 + }, + { + "epoch": 1.01, + "learning_rate": 3.699785044579828e-05, + "loss": 4.0133, + "step": 794112 + }, + { + "epoch": 1.01, + "learning_rate": 3.698946449828776e-05, + "loss": 4.0438, + "step": 794624 + }, + { + "epoch": 1.01, + "learning_rate": 3.698107855077724e-05, + "loss": 4.0209, + "step": 795136 + }, + { + "epoch": 1.01, + "learning_rate": 3.697269260326672e-05, + "loss": 4.0229, + "step": 795648 + }, + { + "epoch": 1.01, + "learning_rate": 3.69643066557562e-05, + "loss": 4.039, + "step": 796160 + }, + { + "epoch": 1.01, + "learning_rate": 3.695593708704941e-05, + "loss": 4.0314, + "step": 796672 + }, + { + "epoch": 1.01, + "learning_rate": 3.694755113953889e-05, + "loss": 4.024, + "step": 797184 + }, + { + "epoch": 1.01, + "learning_rate": 3.693916519202838e-05, + "loss": 4.0235, + "step": 797696 + }, + { + "epoch": 1.01, + "learning_rate": 3.693077924451786e-05, + "loss": 4.0223, + "step": 798208 + }, + { + "epoch": 1.01, + "learning_rate": 3.692239329700734e-05, + "loss": 4.0305, + "step": 798720 + }, + { + "epoch": 1.01, + "learning_rate": 3.6914023728300547e-05, + "loss": 4.0405, + "step": 799232 + }, + { + "epoch": 1.01, + "learning_rate": 3.6905637780790027e-05, + "loss": 4.0306, + "step": 799744 + }, + { + "epoch": 1.01, + "learning_rate": 3.6897251833279506e-05, + "loss": 4.0374, + "step": 800256 + }, + { + "epoch": 1.01, + "learning_rate": 3.688886588576898e-05, + "loss": 4.0375, + "step": 800768 + }, + { + "epoch": 1.01, + "learning_rate": 3.6880512695865925e-05, + "loss": 4.0459, + "step": 801280 + }, + { + "epoch": 1.01, + "learning_rate": 3.6872126748355405e-05, + "loss": 4.0258, + "step": 801792 + }, + { + "epoch": 1.01, + "learning_rate": 3.6863740800844885e-05, + "loss": 4.0347, + "step": 802304 + }, + { + "epoch": 1.01, + "learning_rate": 3.6855354853334365e-05, + "loss": 4.0295, + "step": 802816 + }, + { + "epoch": 1.01, + "learning_rate": 3.684698528462758e-05, + "loss": 4.0206, + "step": 803328 + }, + { + "epoch": 1.01, + "learning_rate": 3.683859933711706e-05, + "loss": 4.033, + "step": 803840 + }, + { + "epoch": 1.01, + "learning_rate": 3.683021338960654e-05, + "loss": 4.0387, + "step": 804352 + }, + { + "epoch": 1.01, + "learning_rate": 3.682182744209602e-05, + "loss": 4.035, + "step": 804864 + }, + { + "epoch": 1.01, + "learning_rate": 3.68134414945855e-05, + "loss": 4.0451, + "step": 805376 + }, + { + "epoch": 1.01, + "learning_rate": 3.680505554707498e-05, + "loss": 4.0114, + "step": 805888 + }, + { + "epoch": 1.01, + "learning_rate": 3.679666959956445e-05, + "loss": 4.0257, + "step": 806400 + }, + { + "epoch": 1.01, + "learning_rate": 3.678828365205393e-05, + "loss": 4.034, + "step": 806912 + }, + { + "epoch": 1.01, + "learning_rate": 3.677989770454341e-05, + "loss": 4.0312, + "step": 807424 + }, + { + "epoch": 1.01, + "learning_rate": 3.677152813583663e-05, + "loss": 4.027, + "step": 807936 + }, + { + "epoch": 1.01, + "learning_rate": 3.67631421883261e-05, + "loss": 4.0382, + "step": 808448 + }, + { + "epoch": 1.01, + "learning_rate": 3.675475624081558e-05, + "loss": 4.0304, + "step": 808960 + }, + { + "epoch": 1.02, + "learning_rate": 3.674637029330507e-05, + "loss": 4.0309, + "step": 809472 + }, + { + "epoch": 1.02, + "learning_rate": 3.673798434579455e-05, + "loss": 4.021, + "step": 809984 + }, + { + "epoch": 1.02, + "learning_rate": 3.672961477708776e-05, + "loss": 4.023, + "step": 810496 + }, + { + "epoch": 1.02, + "learning_rate": 3.672122882957724e-05, + "loss": 4.0385, + "step": 811008 + }, + { + "epoch": 1.02, + "learning_rate": 3.671284288206672e-05, + "loss": 4.0321, + "step": 811520 + }, + { + "epoch": 1.02, + "learning_rate": 3.67044569345562e-05, + "loss": 4.0344, + "step": 812032 + }, + { + "epoch": 1.02, + "learning_rate": 3.669608736584941e-05, + "loss": 4.0255, + "step": 812544 + }, + { + "epoch": 1.02, + "learning_rate": 3.668770141833889e-05, + "loss": 4.0186, + "step": 813056 + }, + { + "epoch": 1.02, + "learning_rate": 3.667931547082837e-05, + "loss": 4.0352, + "step": 813568 + }, + { + "epoch": 1.02, + "learning_rate": 3.667092952331785e-05, + "loss": 4.0363, + "step": 814080 + }, + { + "epoch": 1.02, + "learning_rate": 3.666254357580733e-05, + "loss": 4.0322, + "step": 814592 + }, + { + "epoch": 1.02, + "learning_rate": 3.665415762829681e-05, + "loss": 4.0276, + "step": 815104 + }, + { + "epoch": 1.02, + "learning_rate": 3.664577168078629e-05, + "loss": 4.0266, + "step": 815616 + }, + { + "epoch": 1.02, + "learning_rate": 3.66374021120795e-05, + "loss": 4.0242, + "step": 816128 + }, + { + "epoch": 1.02, + "learning_rate": 3.662901616456898e-05, + "loss": 4.0264, + "step": 816640 + }, + { + "epoch": 1.02, + "learning_rate": 3.662063021705846e-05, + "loss": 4.0175, + "step": 817152 + }, + { + "epoch": 1.02, + "learning_rate": 3.661224426954794e-05, + "loss": 4.0194, + "step": 817664 + }, + { + "epoch": 1.02, + "learning_rate": 3.660385832203742e-05, + "loss": 4.0299, + "step": 818176 + }, + { + "epoch": 1.02, + "learning_rate": 3.65954723745269e-05, + "loss": 4.0304, + "step": 818688 + }, + { + "epoch": 1.02, + "learning_rate": 3.658708642701638e-05, + "loss": 4.0199, + "step": 819200 + }, + { + "epoch": 1.02, + "learning_rate": 3.657870047950586e-05, + "loss": 4.0228, + "step": 819712 + }, + { + "epoch": 1.02, + "learning_rate": 3.657031453199534e-05, + "loss": 4.0282, + "step": 820224 + }, + { + "epoch": 1.02, + "learning_rate": 3.656194496328855e-05, + "loss": 4.0257, + "step": 820736 + }, + { + "epoch": 1.02, + "learning_rate": 3.655355901577803e-05, + "loss": 4.0165, + "step": 821248 + }, + { + "epoch": 1.02, + "learning_rate": 3.654517306826751e-05, + "loss": 4.0358, + "step": 821760 + }, + { + "epoch": 1.02, + "learning_rate": 3.653678712075699e-05, + "loss": 4.0345, + "step": 822272 + }, + { + "epoch": 1.02, + "learning_rate": 3.65284175520502e-05, + "loss": 4.032, + "step": 822784 + }, + { + "epoch": 1.02, + "learning_rate": 3.6520047983343416e-05, + "loss": 4.0259, + "step": 823296 + }, + { + "epoch": 1.02, + "learning_rate": 3.6511662035832896e-05, + "loss": 4.021, + "step": 823808 + }, + { + "epoch": 1.02, + "learning_rate": 3.6503276088322376e-05, + "loss": 4.0272, + "step": 824320 + }, + { + "epoch": 1.02, + "learning_rate": 3.6494890140811856e-05, + "loss": 4.0361, + "step": 824832 + }, + { + "epoch": 1.02, + "learning_rate": 3.6486504193301336e-05, + "loss": 4.0219, + "step": 825344 + }, + { + "epoch": 1.02, + "learning_rate": 3.6478118245790816e-05, + "loss": 4.0228, + "step": 825856 + }, + { + "epoch": 1.02, + "learning_rate": 3.646973229828029e-05, + "loss": 4.0228, + "step": 826368 + }, + { + "epoch": 1.02, + "learning_rate": 3.6461362729573505e-05, + "loss": 4.0343, + "step": 826880 + }, + { + "epoch": 1.02, + "learning_rate": 3.6452976782062985e-05, + "loss": 4.0256, + "step": 827392 + }, + { + "epoch": 1.02, + "learning_rate": 3.6444590834552465e-05, + "loss": 4.0087, + "step": 827904 + }, + { + "epoch": 1.02, + "learning_rate": 3.643620488704194e-05, + "loss": 4.0309, + "step": 828416 + }, + { + "epoch": 1.02, + "learning_rate": 3.6427818939531425e-05, + "loss": 4.0158, + "step": 828928 + }, + { + "epoch": 1.02, + "learning_rate": 3.6419432992020905e-05, + "loss": 4.0356, + "step": 829440 + }, + { + "epoch": 1.02, + "learning_rate": 3.6411047044510385e-05, + "loss": 4.0276, + "step": 829952 + }, + { + "epoch": 1.02, + "learning_rate": 3.6402661096999865e-05, + "loss": 4.0333, + "step": 830464 + }, + { + "epoch": 1.02, + "learning_rate": 3.6394291528293074e-05, + "loss": 4.0127, + "step": 830976 + }, + { + "epoch": 1.02, + "learning_rate": 3.638592195958629e-05, + "loss": 4.0365, + "step": 831488 + }, + { + "epoch": 1.02, + "learning_rate": 3.637753601207576e-05, + "loss": 4.0304, + "step": 832000 + }, + { + "epoch": 1.02, + "learning_rate": 3.636916644336898e-05, + "loss": 4.0294, + "step": 832512 + }, + { + "epoch": 1.02, + "learning_rate": 3.636078049585846e-05, + "loss": 4.0312, + "step": 833024 + }, + { + "epoch": 1.02, + "learning_rate": 3.635241092715167e-05, + "loss": 4.0179, + "step": 833536 + }, + { + "epoch": 1.02, + "learning_rate": 3.634402497964115e-05, + "loss": 4.0373, + "step": 834048 + }, + { + "epoch": 1.02, + "learning_rate": 3.633563903213063e-05, + "loss": 4.0364, + "step": 834560 + }, + { + "epoch": 1.02, + "learning_rate": 3.632725308462011e-05, + "loss": 4.0269, + "step": 835072 + }, + { + "epoch": 1.02, + "learning_rate": 3.631886713710959e-05, + "loss": 4.0265, + "step": 835584 + }, + { + "epoch": 1.02, + "learning_rate": 3.631048118959907e-05, + "loss": 4.0311, + "step": 836096 + }, + { + "epoch": 1.02, + "learning_rate": 3.630209524208855e-05, + "loss": 4.0261, + "step": 836608 + }, + { + "epoch": 1.02, + "learning_rate": 3.629370929457803e-05, + "loss": 4.0173, + "step": 837120 + }, + { + "epoch": 1.02, + "learning_rate": 3.628532334706751e-05, + "loss": 4.0313, + "step": 837632 + }, + { + "epoch": 1.02, + "learning_rate": 3.627693739955699e-05, + "loss": 4.0288, + "step": 838144 + }, + { + "epoch": 1.02, + "learning_rate": 3.626855145204647e-05, + "loss": 4.0341, + "step": 838656 + }, + { + "epoch": 1.02, + "learning_rate": 3.626016550453595e-05, + "loss": 4.0225, + "step": 839168 + }, + { + "epoch": 1.03, + "eval_loss": 4.056351661682129, + "eval_runtime": 295.807, + "eval_samples_per_second": 1290.0, + "eval_steps_per_second": 40.313, + "step": 839520 + }, + { + "epoch": 0.0, + "learning_rate": 3.625177955702543e-05, + "loss": 4.0092, + "step": 839680 + }, + { + "epoch": 0.0, + "learning_rate": 3.624339360951491e-05, + "loss": 4.0097, + "step": 840192 + }, + { + "epoch": 0.0, + "learning_rate": 3.623500766200439e-05, + "loss": 4.024, + "step": 840704 + }, + { + "epoch": 0.0, + "learning_rate": 3.622662171449387e-05, + "loss": 4.0283, + "step": 841216 + }, + { + "epoch": 0.0, + "learning_rate": 3.621823576698335e-05, + "loss": 4.0321, + "step": 841728 + }, + { + "epoch": 0.0, + "learning_rate": 3.620984981947283e-05, + "loss": 4.0238, + "step": 842240 + }, + { + "epoch": 0.0, + "learning_rate": 3.620146387196231e-05, + "loss": 4.0246, + "step": 842752 + }, + { + "epoch": 0.0, + "learning_rate": 3.619307792445179e-05, + "loss": 4.0225, + "step": 843264 + }, + { + "epoch": 0.0, + "learning_rate": 3.618469197694127e-05, + "loss": 4.0174, + "step": 843776 + }, + { + "epoch": 0.0, + "learning_rate": 3.617630602943075e-05, + "loss": 4.0192, + "step": 844288 + }, + { + "epoch": 0.0, + "learning_rate": 3.616792008192023e-05, + "loss": 4.0301, + "step": 844800 + }, + { + "epoch": 0.0, + "learning_rate": 3.615953413440971e-05, + "loss": 4.0304, + "step": 845312 + }, + { + "epoch": 0.0, + "learning_rate": 3.615114818689919e-05, + "loss": 4.03, + "step": 845824 + }, + { + "epoch": 0.0, + "learning_rate": 3.614276223938867e-05, + "loss": 4.0122, + "step": 846336 + }, + { + "epoch": 0.0, + "learning_rate": 3.613437629187815e-05, + "loss": 4.021, + "step": 846848 + }, + { + "epoch": 0.0, + "learning_rate": 3.612599034436763e-05, + "loss": 4.0004, + "step": 847360 + }, + { + "epoch": 0.0, + "learning_rate": 3.6117604396857107e-05, + "loss": 4.0206, + "step": 847872 + }, + { + "epoch": 0.0, + "learning_rate": 3.6109218449346587e-05, + "loss": 4.0204, + "step": 848384 + }, + { + "epoch": 0.0, + "learning_rate": 3.6100832501836066e-05, + "loss": 4.0156, + "step": 848896 + }, + { + "epoch": 0.0, + "learning_rate": 3.609244655432554e-05, + "loss": 4.0207, + "step": 849408 + }, + { + "epoch": 0.0, + "learning_rate": 3.6084076985618756e-05, + "loss": 4.03, + "step": 849920 + }, + { + "epoch": 0.0, + "learning_rate": 3.607569103810824e-05, + "loss": 4.0256, + "step": 850432 + }, + { + "epoch": 0.0, + "learning_rate": 3.606732146940145e-05, + "loss": 4.0315, + "step": 850944 + }, + { + "epoch": 0.0, + "learning_rate": 3.605893552189093e-05, + "loss": 4.0213, + "step": 851456 + }, + { + "epoch": 0.0, + "learning_rate": 3.605054957438041e-05, + "loss": 4.0213, + "step": 851968 + }, + { + "epoch": 0.0, + "learning_rate": 3.604216362686989e-05, + "loss": 4.0165, + "step": 852480 + }, + { + "epoch": 0.0, + "learning_rate": 3.6033777679359364e-05, + "loss": 4.0188, + "step": 852992 + }, + { + "epoch": 0.0, + "learning_rate": 3.6025391731848844e-05, + "loss": 4.0242, + "step": 853504 + }, + { + "epoch": 0.0, + "learning_rate": 3.6017005784338324e-05, + "loss": 4.0182, + "step": 854016 + }, + { + "epoch": 0.0, + "learning_rate": 3.6008619836827804e-05, + "loss": 4.0122, + "step": 854528 + }, + { + "epoch": 0.01, + "learning_rate": 3.6000233889317284e-05, + "loss": 4.014, + "step": 855040 + }, + { + "epoch": 0.01, + "learning_rate": 3.5991897078217965e-05, + "loss": 4.0249, + "step": 855552 + }, + { + "epoch": 0.01, + "learning_rate": 3.5983543888314903e-05, + "loss": 4.0268, + "step": 856064 + }, + { + "epoch": 0.01, + "learning_rate": 3.597515794080438e-05, + "loss": 4.0231, + "step": 856576 + }, + { + "epoch": 0.01, + "learning_rate": 3.596677199329386e-05, + "loss": 4.0191, + "step": 857088 + }, + { + "epoch": 0.01, + "learning_rate": 3.595838604578334e-05, + "loss": 4.0223, + "step": 857600 + }, + { + "epoch": 0.01, + "learning_rate": 3.595000009827282e-05, + "loss": 4.0285, + "step": 858112 + }, + { + "epoch": 0.01, + "learning_rate": 3.59416141507623e-05, + "loss": 4.0078, + "step": 858624 + }, + { + "epoch": 0.01, + "learning_rate": 3.593322820325178e-05, + "loss": 4.0132, + "step": 859136 + }, + { + "epoch": 0.01, + "learning_rate": 3.592484225574126e-05, + "loss": 4.0112, + "step": 859648 + }, + { + "epoch": 0.01, + "learning_rate": 3.591645630823074e-05, + "loss": 4.016, + "step": 860160 + }, + { + "epoch": 0.01, + "learning_rate": 3.590807036072022e-05, + "loss": 4.0244, + "step": 860672 + }, + { + "epoch": 0.01, + "learning_rate": 3.58996844132097e-05, + "loss": 4.0148, + "step": 861184 + }, + { + "epoch": 0.01, + "learning_rate": 3.589129846569918e-05, + "loss": 4.0243, + "step": 861696 + }, + { + "epoch": 0.01, + "learning_rate": 3.588291251818866e-05, + "loss": 4.0228, + "step": 862208 + }, + { + "epoch": 0.01, + "learning_rate": 3.587452657067814e-05, + "loss": 4.0201, + "step": 862720 + }, + { + "epoch": 0.01, + "learning_rate": 3.586614062316762e-05, + "loss": 4.0233, + "step": 863232 + }, + { + "epoch": 0.01, + "learning_rate": 3.58577546756571e-05, + "loss": 4.0257, + "step": 863744 + }, + { + "epoch": 0.01, + "learning_rate": 3.584936872814658e-05, + "loss": 3.9924, + "step": 864256 + }, + { + "epoch": 0.01, + "learning_rate": 3.584099915943979e-05, + "loss": 4.0316, + "step": 864768 + }, + { + "epoch": 0.01, + "learning_rate": 3.583261321192927e-05, + "loss": 4.0153, + "step": 865280 + }, + { + "epoch": 0.01, + "learning_rate": 3.582422726441875e-05, + "loss": 4.0283, + "step": 865792 + }, + { + "epoch": 0.01, + "learning_rate": 3.581584131690823e-05, + "loss": 4.01, + "step": 866304 + }, + { + "epoch": 0.01, + "learning_rate": 3.580747174820144e-05, + "loss": 4.0138, + "step": 866816 + }, + { + "epoch": 0.01, + "learning_rate": 3.579908580069092e-05, + "loss": 4.0014, + "step": 867328 + }, + { + "epoch": 0.01, + "learning_rate": 3.5790716231984137e-05, + "loss": 4.0132, + "step": 867840 + }, + { + "epoch": 0.01, + "learning_rate": 3.5782330284473617e-05, + "loss": 4.0172, + "step": 868352 + }, + { + "epoch": 0.01, + "learning_rate": 3.5773944336963096e-05, + "loss": 3.9989, + "step": 868864 + }, + { + "epoch": 0.01, + "learning_rate": 3.5765558389452576e-05, + "loss": 4.0282, + "step": 869376 + }, + { + "epoch": 0.01, + "learning_rate": 3.5757172441942056e-05, + "loss": 4.0164, + "step": 869888 + }, + { + "epoch": 0.01, + "learning_rate": 3.5748786494431536e-05, + "loss": 3.9961, + "step": 870400 + }, + { + "epoch": 0.01, + "learning_rate": 3.5740400546921016e-05, + "loss": 4.0224, + "step": 870912 + }, + { + "epoch": 0.01, + "learning_rate": 3.5732014599410496e-05, + "loss": 4.0046, + "step": 871424 + }, + { + "epoch": 0.01, + "learning_rate": 3.5723628651899976e-05, + "loss": 4.0025, + "step": 871936 + }, + { + "epoch": 0.01, + "learning_rate": 3.5715242704389456e-05, + "loss": 4.0183, + "step": 872448 + }, + { + "epoch": 0.01, + "learning_rate": 3.5706856756878936e-05, + "loss": 4.0133, + "step": 872960 + }, + { + "epoch": 0.01, + "learning_rate": 3.5698470809368416e-05, + "loss": 4.0046, + "step": 873472 + }, + { + "epoch": 0.01, + "learning_rate": 3.5690084861857896e-05, + "loss": 4.0063, + "step": 873984 + }, + { + "epoch": 0.01, + "learning_rate": 3.5681698914347376e-05, + "loss": 4.0029, + "step": 874496 + }, + { + "epoch": 0.01, + "learning_rate": 3.5673312966836856e-05, + "loss": 4.0133, + "step": 875008 + }, + { + "epoch": 0.01, + "learning_rate": 3.5664927019326336e-05, + "loss": 4.0183, + "step": 875520 + }, + { + "epoch": 0.01, + "learning_rate": 3.5656541071815816e-05, + "loss": 4.0143, + "step": 876032 + }, + { + "epoch": 0.01, + "learning_rate": 3.5648171503109025e-05, + "loss": 4.0177, + "step": 876544 + }, + { + "epoch": 0.01, + "learning_rate": 3.5639785555598505e-05, + "loss": 4.0188, + "step": 877056 + }, + { + "epoch": 0.01, + "learning_rate": 3.5631399608087985e-05, + "loss": 4.026, + "step": 877568 + }, + { + "epoch": 0.01, + "learning_rate": 3.562304641818493e-05, + "loss": 4.0068, + "step": 878080 + }, + { + "epoch": 0.01, + "learning_rate": 3.561466047067441e-05, + "loss": 4.0194, + "step": 878592 + }, + { + "epoch": 0.01, + "learning_rate": 3.560627452316389e-05, + "loss": 4.0063, + "step": 879104 + }, + { + "epoch": 0.01, + "learning_rate": 3.559788857565337e-05, + "loss": 4.0032, + "step": 879616 + }, + { + "epoch": 0.01, + "learning_rate": 3.558950262814285e-05, + "loss": 4.0155, + "step": 880128 + }, + { + "epoch": 0.01, + "learning_rate": 3.558113305943606e-05, + "loss": 4.0166, + "step": 880640 + }, + { + "epoch": 0.01, + "learning_rate": 3.557274711192554e-05, + "loss": 4.0202, + "step": 881152 + }, + { + "epoch": 0.01, + "learning_rate": 3.556436116441502e-05, + "loss": 4.0262, + "step": 881664 + }, + { + "epoch": 0.01, + "learning_rate": 3.55559752169045e-05, + "loss": 3.9916, + "step": 882176 + }, + { + "epoch": 0.01, + "learning_rate": 3.554758926939398e-05, + "loss": 4.0093, + "step": 882688 + }, + { + "epoch": 0.01, + "learning_rate": 3.553920332188346e-05, + "loss": 4.0155, + "step": 883200 + }, + { + "epoch": 0.01, + "learning_rate": 3.553081737437294e-05, + "loss": 4.0154, + "step": 883712 + }, + { + "epoch": 0.01, + "learning_rate": 3.552243142686242e-05, + "loss": 4.008, + "step": 884224 + }, + { + "epoch": 0.01, + "learning_rate": 3.5514078236959364e-05, + "loss": 4.0187, + "step": 884736 + }, + { + "epoch": 0.01, + "learning_rate": 3.550570866825257e-05, + "loss": 4.0124, + "step": 885248 + }, + { + "epoch": 0.02, + "learning_rate": 3.549732272074205e-05, + "loss": 4.0113, + "step": 885760 + }, + { + "epoch": 0.02, + "learning_rate": 3.548893677323153e-05, + "loss": 4.0056, + "step": 886272 + }, + { + "epoch": 0.02, + "learning_rate": 3.548055082572101e-05, + "loss": 4.0049, + "step": 886784 + }, + { + "epoch": 0.02, + "learning_rate": 3.547216487821049e-05, + "loss": 4.0196, + "step": 887296 + }, + { + "epoch": 0.02, + "learning_rate": 3.546377893069997e-05, + "loss": 4.015, + "step": 887808 + }, + { + "epoch": 0.02, + "learning_rate": 3.545539298318945e-05, + "loss": 4.0127, + "step": 888320 + }, + { + "epoch": 0.02, + "learning_rate": 3.544700703567893e-05, + "loss": 4.0097, + "step": 888832 + }, + { + "epoch": 0.02, + "learning_rate": 3.543862108816841e-05, + "loss": 4.005, + "step": 889344 + }, + { + "epoch": 0.02, + "learning_rate": 3.543023514065789e-05, + "loss": 4.0171, + "step": 889856 + }, + { + "epoch": 0.02, + "learning_rate": 3.542184919314737e-05, + "loss": 4.018, + "step": 890368 + }, + { + "epoch": 0.02, + "learning_rate": 3.541346324563685e-05, + "loss": 4.0104, + "step": 890880 + }, + { + "epoch": 0.02, + "learning_rate": 3.540509367693006e-05, + "loss": 4.0097, + "step": 891392 + }, + { + "epoch": 0.02, + "learning_rate": 3.539670772941954e-05, + "loss": 4.0101, + "step": 891904 + }, + { + "epoch": 0.02, + "learning_rate": 3.538832178190902e-05, + "loss": 4.0097, + "step": 892416 + }, + { + "epoch": 0.02, + "learning_rate": 3.53799358343985e-05, + "loss": 4.0016, + "step": 892928 + }, + { + "epoch": 0.02, + "learning_rate": 3.537154988688798e-05, + "loss": 4.0029, + "step": 893440 + }, + { + "epoch": 0.02, + "learning_rate": 3.5363196696984926e-05, + "loss": 4.0042, + "step": 893952 + }, + { + "epoch": 0.02, + "learning_rate": 3.5354810749474406e-05, + "loss": 4.0149, + "step": 894464 + }, + { + "epoch": 0.02, + "learning_rate": 3.5346424801963886e-05, + "loss": 4.0092, + "step": 894976 + }, + { + "epoch": 0.02, + "learning_rate": 3.5338038854453366e-05, + "loss": 4.0079, + "step": 895488 + }, + { + "epoch": 0.02, + "learning_rate": 3.5329652906942846e-05, + "loss": 3.9995, + "step": 896000 + }, + { + "epoch": 0.02, + "learning_rate": 3.5321266959432326e-05, + "loss": 4.0098, + "step": 896512 + }, + { + "epoch": 0.02, + "learning_rate": 3.5312881011921806e-05, + "loss": 4.0139, + "step": 897024 + }, + { + "epoch": 0.02, + "learning_rate": 3.5304495064411286e-05, + "loss": 4.0037, + "step": 897536 + }, + { + "epoch": 0.02, + "learning_rate": 3.5296125495704495e-05, + "loss": 4.0117, + "step": 898048 + }, + { + "epoch": 0.02, + "learning_rate": 3.5287739548193975e-05, + "loss": 4.0153, + "step": 898560 + }, + { + "epoch": 0.02, + "learning_rate": 3.5279353600683455e-05, + "loss": 4.0159, + "step": 899072 + }, + { + "epoch": 0.02, + "learning_rate": 3.5270984031976664e-05, + "loss": 4.0092, + "step": 899584 + }, + { + "epoch": 0.02, + "learning_rate": 3.526259808446615e-05, + "loss": 4.0066, + "step": 900096 + }, + { + "epoch": 0.02, + "learning_rate": 3.525421213695563e-05, + "loss": 4.0064, + "step": 900608 + }, + { + "epoch": 0.02, + "learning_rate": 3.524582618944511e-05, + "loss": 4.0202, + "step": 901120 + }, + { + "epoch": 0.02, + "learning_rate": 3.523744024193459e-05, + "loss": 4.003, + "step": 901632 + }, + { + "epoch": 0.02, + "learning_rate": 3.522905429442407e-05, + "loss": 4.0047, + "step": 902144 + }, + { + "epoch": 0.02, + "learning_rate": 3.522066834691355e-05, + "loss": 4.0056, + "step": 902656 + }, + { + "epoch": 0.02, + "learning_rate": 3.521228239940303e-05, + "loss": 4.014, + "step": 903168 + }, + { + "epoch": 0.02, + "learning_rate": 3.520391283069624e-05, + "loss": 4.0113, + "step": 903680 + }, + { + "epoch": 0.02, + "learning_rate": 3.519552688318572e-05, + "loss": 3.9948, + "step": 904192 + }, + { + "epoch": 0.02, + "learning_rate": 3.51871409356752e-05, + "loss": 4.0083, + "step": 904704 + }, + { + "epoch": 0.02, + "learning_rate": 3.517875498816468e-05, + "loss": 3.997, + "step": 905216 + }, + { + "epoch": 0.02, + "learning_rate": 3.517038541945789e-05, + "loss": 4.0178, + "step": 905728 + }, + { + "epoch": 0.02, + "learning_rate": 3.516199947194737e-05, + "loss": 4.0138, + "step": 906240 + }, + { + "epoch": 0.02, + "learning_rate": 3.515361352443685e-05, + "loss": 4.0122, + "step": 906752 + }, + { + "epoch": 0.02, + "learning_rate": 3.5145243955730064e-05, + "loss": 3.9998, + "step": 907264 + }, + { + "epoch": 0.02, + "learning_rate": 3.5136858008219544e-05, + "loss": 4.0138, + "step": 907776 + }, + { + "epoch": 0.02, + "learning_rate": 3.5128472060709024e-05, + "loss": 4.0171, + "step": 908288 + }, + { + "epoch": 0.02, + "learning_rate": 3.5120086113198504e-05, + "loss": 4.009, + "step": 908800 + }, + { + "epoch": 0.02, + "learning_rate": 3.511171654449171e-05, + "loss": 4.0127, + "step": 909312 + }, + { + "epoch": 0.02, + "learning_rate": 3.510333059698119e-05, + "loss": 4.0009, + "step": 909824 + }, + { + "epoch": 0.02, + "learning_rate": 3.509494464947067e-05, + "loss": 4.0226, + "step": 910336 + }, + { + "epoch": 0.02, + "learning_rate": 3.508655870196015e-05, + "loss": 4.0201, + "step": 910848 + }, + { + "epoch": 0.02, + "learning_rate": 3.5078172754449626e-05, + "loss": 4.0119, + "step": 911360 + }, + { + "epoch": 0.02, + "learning_rate": 3.506980318574284e-05, + "loss": 4.0069, + "step": 911872 + }, + { + "epoch": 0.02, + "learning_rate": 3.506141723823232e-05, + "loss": 4.0137, + "step": 912384 + }, + { + "epoch": 0.02, + "learning_rate": 3.50530312907218e-05, + "loss": 4.0046, + "step": 912896 + }, + { + "epoch": 0.02, + "learning_rate": 3.504464534321128e-05, + "loss": 4.0002, + "step": 913408 + }, + { + "epoch": 0.02, + "learning_rate": 3.503625939570076e-05, + "loss": 4.0144, + "step": 913920 + }, + { + "epoch": 0.02, + "learning_rate": 3.502787344819024e-05, + "loss": 4.0115, + "step": 914432 + }, + { + "epoch": 0.02, + "learning_rate": 3.501948750067972e-05, + "loss": 4.0163, + "step": 914944 + }, + { + "epoch": 0.02, + "learning_rate": 3.501111793197293e-05, + "loss": 4.0072, + "step": 915456 + }, + { + "epoch": 0.03, + "eval_loss": 4.045725345611572, + "eval_runtime": 297.0182, + "eval_samples_per_second": 1284.74, + "eval_steps_per_second": 40.149, + "step": 915840 + }, + { + "epoch": 1.0, + "learning_rate": 3.500273198446241e-05, + "loss": 4.0012, + "step": 915968 + }, + { + "epoch": 1.0, + "learning_rate": 3.499434603695189e-05, + "loss": 3.9889, + "step": 916480 + }, + { + "epoch": 1.0, + "learning_rate": 3.498596008944137e-05, + "loss": 4.006, + "step": 916992 + }, + { + "epoch": 1.0, + "learning_rate": 3.497759052073458e-05, + "loss": 4.0116, + "step": 917504 + }, + { + "epoch": 1.0, + "learning_rate": 3.496920457322406e-05, + "loss": 4.0107, + "step": 918016 + }, + { + "epoch": 1.0, + "learning_rate": 3.496081862571354e-05, + "loss": 4.008, + "step": 918528 + }, + { + "epoch": 1.0, + "learning_rate": 3.4952432678203026e-05, + "loss": 4.0138, + "step": 919040 + }, + { + "epoch": 1.0, + "learning_rate": 3.4944046730692506e-05, + "loss": 4.0022, + "step": 919552 + }, + { + "epoch": 1.0, + "learning_rate": 3.4935660783181986e-05, + "loss": 4.0, + "step": 920064 + }, + { + "epoch": 1.0, + "learning_rate": 3.4927274835671466e-05, + "loss": 4.0011, + "step": 920576 + }, + { + "epoch": 1.0, + "learning_rate": 3.4918888888160946e-05, + "loss": 4.0178, + "step": 921088 + }, + { + "epoch": 1.0, + "learning_rate": 3.4910519319454155e-05, + "loss": 4.0123, + "step": 921600 + }, + { + "epoch": 1.0, + "learning_rate": 3.4902149750747364e-05, + "loss": 4.0135, + "step": 922112 + }, + { + "epoch": 1.0, + "learning_rate": 3.4893763803236844e-05, + "loss": 3.9962, + "step": 922624 + }, + { + "epoch": 1.0, + "learning_rate": 3.4885377855726324e-05, + "loss": 4.0064, + "step": 923136 + }, + { + "epoch": 1.0, + "learning_rate": 3.4876991908215804e-05, + "loss": 3.9817, + "step": 923648 + }, + { + "epoch": 1.0, + "learning_rate": 3.4868605960705284e-05, + "loss": 4.0044, + "step": 924160 + }, + { + "epoch": 1.0, + "learning_rate": 3.4860220013194764e-05, + "loss": 4.0028, + "step": 924672 + }, + { + "epoch": 1.0, + "learning_rate": 3.485185044448798e-05, + "loss": 3.9953, + "step": 925184 + }, + { + "epoch": 1.0, + "learning_rate": 3.484346449697746e-05, + "loss": 4.007, + "step": 925696 + }, + { + "epoch": 1.0, + "learning_rate": 3.483507854946694e-05, + "loss": 4.0098, + "step": 926208 + }, + { + "epoch": 1.0, + "learning_rate": 3.482669260195642e-05, + "loss": 4.0093, + "step": 926720 + }, + { + "epoch": 1.0, + "learning_rate": 3.48183066544459e-05, + "loss": 4.0142, + "step": 927232 + }, + { + "epoch": 1.0, + "learning_rate": 3.480992070693538e-05, + "loss": 4.0046, + "step": 927744 + }, + { + "epoch": 1.0, + "learning_rate": 3.480153475942486e-05, + "loss": 4.0071, + "step": 928256 + }, + { + "epoch": 1.0, + "learning_rate": 3.479314881191434e-05, + "loss": 4.0013, + "step": 928768 + }, + { + "epoch": 1.0, + "learning_rate": 3.478477924320755e-05, + "loss": 4.0, + "step": 929280 + }, + { + "epoch": 1.0, + "learning_rate": 3.477639329569703e-05, + "loss": 4.0069, + "step": 929792 + }, + { + "epoch": 1.0, + "learning_rate": 3.476800734818651e-05, + "loss": 4.0016, + "step": 930304 + }, + { + "epoch": 1.0, + "learning_rate": 3.475963777947972e-05, + "loss": 3.9931, + "step": 930816 + }, + { + "epoch": 1.01, + "learning_rate": 3.47512518319692e-05, + "loss": 3.9996, + "step": 931328 + }, + { + "epoch": 1.01, + "learning_rate": 3.474286588445868e-05, + "loss": 4.0069, + "step": 931840 + }, + { + "epoch": 1.01, + "learning_rate": 3.473447993694816e-05, + "loss": 4.0077, + "step": 932352 + }, + { + "epoch": 1.01, + "learning_rate": 3.4726093989437645e-05, + "loss": 4.0082, + "step": 932864 + }, + { + "epoch": 1.01, + "learning_rate": 3.471770804192712e-05, + "loss": 4.0037, + "step": 933376 + }, + { + "epoch": 1.01, + "learning_rate": 3.470935485202406e-05, + "loss": 4.0051, + "step": 933888 + }, + { + "epoch": 1.01, + "learning_rate": 3.470096890451354e-05, + "loss": 4.0108, + "step": 934400 + }, + { + "epoch": 1.01, + "learning_rate": 3.469258295700302e-05, + "loss": 3.9906, + "step": 934912 + }, + { + "epoch": 1.01, + "learning_rate": 3.46841970094925e-05, + "loss": 3.9953, + "step": 935424 + }, + { + "epoch": 1.01, + "learning_rate": 3.467581106198198e-05, + "loss": 3.9958, + "step": 935936 + }, + { + "epoch": 1.01, + "learning_rate": 3.466742511447146e-05, + "loss": 3.9983, + "step": 936448 + }, + { + "epoch": 1.01, + "learning_rate": 3.4659039166960936e-05, + "loss": 4.0034, + "step": 936960 + }, + { + "epoch": 1.01, + "learning_rate": 3.4650653219450416e-05, + "loss": 4.0031, + "step": 937472 + }, + { + "epoch": 1.01, + "learning_rate": 3.4642267271939896e-05, + "loss": 4.006, + "step": 937984 + }, + { + "epoch": 1.01, + "learning_rate": 3.463388132442938e-05, + "loss": 4.0038, + "step": 938496 + }, + { + "epoch": 1.01, + "learning_rate": 3.462549537691886e-05, + "loss": 4.0032, + "step": 939008 + }, + { + "epoch": 1.01, + "learning_rate": 3.461712580821207e-05, + "loss": 4.0054, + "step": 939520 + }, + { + "epoch": 1.01, + "learning_rate": 3.460873986070155e-05, + "loss": 4.0147, + "step": 940032 + }, + { + "epoch": 1.01, + "learning_rate": 3.460035391319103e-05, + "loss": 3.9752, + "step": 940544 + }, + { + "epoch": 1.01, + "learning_rate": 3.459196796568051e-05, + "loss": 4.0122, + "step": 941056 + }, + { + "epoch": 1.01, + "learning_rate": 3.458358201816999e-05, + "loss": 3.998, + "step": 941568 + }, + { + "epoch": 1.01, + "learning_rate": 3.457519607065947e-05, + "loss": 4.0076, + "step": 942080 + }, + { + "epoch": 1.01, + "learning_rate": 3.456681012314895e-05, + "loss": 3.9941, + "step": 942592 + }, + { + "epoch": 1.01, + "learning_rate": 3.455842417563843e-05, + "loss": 3.9973, + "step": 943104 + }, + { + "epoch": 1.01, + "learning_rate": 3.455005460693164e-05, + "loss": 3.989, + "step": 943616 + }, + { + "epoch": 1.01, + "learning_rate": 3.454168503822485e-05, + "loss": 3.9944, + "step": 944128 + }, + { + "epoch": 1.01, + "learning_rate": 3.4533299090714336e-05, + "loss": 4.0008, + "step": 944640 + }, + { + "epoch": 1.01, + "learning_rate": 3.4524913143203816e-05, + "loss": 3.9842, + "step": 945152 + }, + { + "epoch": 1.01, + "learning_rate": 3.4516527195693296e-05, + "loss": 4.014, + "step": 945664 + }, + { + "epoch": 1.01, + "learning_rate": 3.4508141248182776e-05, + "loss": 3.9975, + "step": 946176 + }, + { + "epoch": 1.01, + "learning_rate": 3.4499755300672256e-05, + "loss": 3.9784, + "step": 946688 + }, + { + "epoch": 1.01, + "learning_rate": 3.4491369353161736e-05, + "loss": 4.0081, + "step": 947200 + }, + { + "epoch": 1.01, + "learning_rate": 3.4482983405651216e-05, + "loss": 3.9852, + "step": 947712 + }, + { + "epoch": 1.01, + "learning_rate": 3.4474597458140696e-05, + "loss": 3.9873, + "step": 948224 + }, + { + "epoch": 1.01, + "learning_rate": 3.4466227889433905e-05, + "loss": 4.0005, + "step": 948736 + }, + { + "epoch": 1.01, + "learning_rate": 3.4457841941923385e-05, + "loss": 3.9971, + "step": 949248 + }, + { + "epoch": 1.01, + "learning_rate": 3.4449455994412865e-05, + "loss": 3.9876, + "step": 949760 + }, + { + "epoch": 1.01, + "learning_rate": 3.4441070046902345e-05, + "loss": 3.9945, + "step": 950272 + }, + { + "epoch": 1.01, + "learning_rate": 3.4432700478195554e-05, + "loss": 3.9841, + "step": 950784 + }, + { + "epoch": 1.01, + "learning_rate": 3.4424314530685034e-05, + "loss": 3.9929, + "step": 951296 + }, + { + "epoch": 1.01, + "learning_rate": 3.441592858317452e-05, + "loss": 4.0021, + "step": 951808 + }, + { + "epoch": 1.01, + "learning_rate": 3.4407542635664e-05, + "loss": 3.9985, + "step": 952320 + }, + { + "epoch": 1.01, + "learning_rate": 3.439917306695721e-05, + "loss": 4.0023, + "step": 952832 + }, + { + "epoch": 1.01, + "learning_rate": 3.439078711944669e-05, + "loss": 4.0007, + "step": 953344 + }, + { + "epoch": 1.01, + "learning_rate": 3.438240117193617e-05, + "loss": 4.0101, + "step": 953856 + }, + { + "epoch": 1.01, + "learning_rate": 3.437403160322938e-05, + "loss": 3.9918, + "step": 954368 + }, + { + "epoch": 1.01, + "learning_rate": 3.436564565571886e-05, + "loss": 4.005, + "step": 954880 + }, + { + "epoch": 1.01, + "learning_rate": 3.435725970820834e-05, + "loss": 3.9873, + "step": 955392 + }, + { + "epoch": 1.01, + "learning_rate": 3.434887376069782e-05, + "loss": 3.9867, + "step": 955904 + }, + { + "epoch": 1.01, + "learning_rate": 3.43404878131873e-05, + "loss": 3.9994, + "step": 956416 + }, + { + "epoch": 1.01, + "learning_rate": 3.433210186567677e-05, + "loss": 3.998, + "step": 956928 + }, + { + "epoch": 1.01, + "learning_rate": 3.432371591816626e-05, + "loss": 4.0059, + "step": 957440 + }, + { + "epoch": 1.01, + "learning_rate": 3.431532997065574e-05, + "loss": 4.0066, + "step": 957952 + }, + { + "epoch": 1.01, + "learning_rate": 3.430694402314522e-05, + "loss": 3.9825, + "step": 958464 + }, + { + "epoch": 1.01, + "learning_rate": 3.429857445443843e-05, + "loss": 3.9892, + "step": 958976 + }, + { + "epoch": 1.01, + "learning_rate": 3.429018850692791e-05, + "loss": 3.9958, + "step": 959488 + }, + { + "epoch": 1.01, + "learning_rate": 3.428180255941739e-05, + "loss": 4.0003, + "step": 960000 + }, + { + "epoch": 1.01, + "learning_rate": 3.4273432990710596e-05, + "loss": 3.9916, + "step": 960512 + }, + { + "epoch": 1.01, + "learning_rate": 3.426506342200381e-05, + "loss": 4.0019, + "step": 961024 + }, + { + "epoch": 1.01, + "learning_rate": 3.425667747449329e-05, + "loss": 4.0022, + "step": 961536 + }, + { + "epoch": 1.02, + "learning_rate": 3.424829152698277e-05, + "loss": 3.9892, + "step": 962048 + }, + { + "epoch": 1.02, + "learning_rate": 3.4239905579472245e-05, + "loss": 3.9888, + "step": 962560 + }, + { + "epoch": 1.02, + "learning_rate": 3.4231519631961725e-05, + "loss": 3.9907, + "step": 963072 + }, + { + "epoch": 1.02, + "learning_rate": 3.4223133684451205e-05, + "loss": 3.9976, + "step": 963584 + }, + { + "epoch": 1.02, + "learning_rate": 3.421474773694069e-05, + "loss": 4.0004, + "step": 964096 + }, + { + "epoch": 1.02, + "learning_rate": 3.420636178943017e-05, + "loss": 3.9965, + "step": 964608 + }, + { + "epoch": 1.02, + "learning_rate": 3.419797584191965e-05, + "loss": 3.9928, + "step": 965120 + }, + { + "epoch": 1.02, + "learning_rate": 3.418958989440913e-05, + "loss": 3.9853, + "step": 965632 + }, + { + "epoch": 1.02, + "learning_rate": 3.418120394689861e-05, + "loss": 4.0058, + "step": 966144 + }, + { + "epoch": 1.02, + "learning_rate": 3.417281799938809e-05, + "loss": 4.0002, + "step": 966656 + }, + { + "epoch": 1.02, + "learning_rate": 3.41644484306813e-05, + "loss": 3.998, + "step": 967168 + }, + { + "epoch": 1.02, + "learning_rate": 3.415607886197451e-05, + "loss": 3.9911, + "step": 967680 + }, + { + "epoch": 1.02, + "learning_rate": 3.414769291446399e-05, + "loss": 3.9938, + "step": 968192 + }, + { + "epoch": 1.02, + "learning_rate": 3.413930696695347e-05, + "loss": 3.9912, + "step": 968704 + }, + { + "epoch": 1.02, + "learning_rate": 3.413092101944295e-05, + "loss": 3.9879, + "step": 969216 + }, + { + "epoch": 1.02, + "learning_rate": 3.412253507193243e-05, + "loss": 3.9891, + "step": 969728 + }, + { + "epoch": 1.02, + "learning_rate": 3.411414912442191e-05, + "loss": 3.9873, + "step": 970240 + }, + { + "epoch": 1.02, + "learning_rate": 3.4105779555715125e-05, + "loss": 3.9957, + "step": 970752 + }, + { + "epoch": 1.02, + "learning_rate": 3.4097393608204605e-05, + "loss": 4.0003, + "step": 971264 + }, + { + "epoch": 1.02, + "learning_rate": 3.4089007660694085e-05, + "loss": 3.9845, + "step": 971776 + }, + { + "epoch": 1.02, + "learning_rate": 3.4080621713183565e-05, + "loss": 3.9863, + "step": 972288 + }, + { + "epoch": 1.02, + "learning_rate": 3.4072235765673045e-05, + "loss": 3.9913, + "step": 972800 + }, + { + "epoch": 1.02, + "learning_rate": 3.4063849818162525e-05, + "loss": 3.997, + "step": 973312 + }, + { + "epoch": 1.02, + "learning_rate": 3.4055463870652005e-05, + "loss": 3.9845, + "step": 973824 + }, + { + "epoch": 1.02, + "learning_rate": 3.4047077923141485e-05, + "loss": 3.9995, + "step": 974336 + }, + { + "epoch": 1.02, + "learning_rate": 3.4038724733238423e-05, + "loss": 3.9924, + "step": 974848 + }, + { + "epoch": 1.02, + "learning_rate": 3.40303387857279e-05, + "loss": 4.0034, + "step": 975360 + }, + { + "epoch": 1.02, + "learning_rate": 3.402195283821738e-05, + "loss": 3.9948, + "step": 975872 + }, + { + "epoch": 1.02, + "learning_rate": 3.401356689070686e-05, + "loss": 3.9907, + "step": 976384 + }, + { + "epoch": 1.02, + "learning_rate": 3.400518094319634e-05, + "loss": 3.9929, + "step": 976896 + }, + { + "epoch": 1.02, + "learning_rate": 3.399679499568583e-05, + "loss": 4.0033, + "step": 977408 + }, + { + "epoch": 1.02, + "learning_rate": 3.398840904817531e-05, + "loss": 3.9848, + "step": 977920 + }, + { + "epoch": 1.02, + "learning_rate": 3.398002310066478e-05, + "loss": 3.9909, + "step": 978432 + }, + { + "epoch": 1.02, + "learning_rate": 3.3971653531958e-05, + "loss": 3.9912, + "step": 978944 + }, + { + "epoch": 1.02, + "learning_rate": 3.396326758444748e-05, + "loss": 3.9958, + "step": 979456 + }, + { + "epoch": 1.02, + "learning_rate": 3.395488163693696e-05, + "loss": 3.9926, + "step": 979968 + }, + { + "epoch": 1.02, + "learning_rate": 3.394651206823017e-05, + "loss": 3.9832, + "step": 980480 + }, + { + "epoch": 1.02, + "learning_rate": 3.393812612071965e-05, + "loss": 3.9908, + "step": 980992 + }, + { + "epoch": 1.02, + "learning_rate": 3.392974017320913e-05, + "loss": 3.9851, + "step": 981504 + }, + { + "epoch": 1.02, + "learning_rate": 3.392135422569861e-05, + "loss": 4.0035, + "step": 982016 + }, + { + "epoch": 1.02, + "learning_rate": 3.391296827818808e-05, + "loss": 3.9939, + "step": 982528 + }, + { + "epoch": 1.02, + "learning_rate": 3.390458233067757e-05, + "loss": 3.9987, + "step": 983040 + }, + { + "epoch": 1.02, + "learning_rate": 3.389619638316705e-05, + "loss": 3.9826, + "step": 983552 + }, + { + "epoch": 1.02, + "learning_rate": 3.388781043565653e-05, + "loss": 3.999, + "step": 984064 + }, + { + "epoch": 1.02, + "learning_rate": 3.387942448814601e-05, + "loss": 4.0021, + "step": 984576 + }, + { + "epoch": 1.02, + "learning_rate": 3.387105491943922e-05, + "loss": 3.9954, + "step": 985088 + }, + { + "epoch": 1.02, + "learning_rate": 3.386268535073243e-05, + "loss": 3.9926, + "step": 985600 + }, + { + "epoch": 1.02, + "learning_rate": 3.3854299403221906e-05, + "loss": 3.9841, + "step": 986112 + }, + { + "epoch": 1.02, + "learning_rate": 3.3845913455711386e-05, + "loss": 4.0088, + "step": 986624 + }, + { + "epoch": 1.02, + "learning_rate": 3.3837527508200866e-05, + "loss": 4.0027, + "step": 987136 + }, + { + "epoch": 1.02, + "learning_rate": 3.3829141560690346e-05, + "loss": 3.9948, + "step": 987648 + }, + { + "epoch": 1.02, + "learning_rate": 3.3820755613179826e-05, + "loss": 3.9895, + "step": 988160 + }, + { + "epoch": 1.02, + "learning_rate": 3.3812386044473035e-05, + "loss": 4.0001, + "step": 988672 + }, + { + "epoch": 1.02, + "learning_rate": 3.380400009696252e-05, + "loss": 3.9924, + "step": 989184 + }, + { + "epoch": 1.02, + "learning_rate": 3.379563052825573e-05, + "loss": 3.9824, + "step": 989696 + }, + { + "epoch": 1.02, + "learning_rate": 3.378724458074521e-05, + "loss": 4.0032, + "step": 990208 + }, + { + "epoch": 1.02, + "learning_rate": 3.377885863323469e-05, + "loss": 3.9903, + "step": 990720 + }, + { + "epoch": 1.02, + "learning_rate": 3.377047268572417e-05, + "loss": 4.0034, + "step": 991232 + }, + { + "epoch": 1.02, + "learning_rate": 3.376208673821365e-05, + "loss": 3.9891, + "step": 991744 + }, + { + "epoch": 1.03, + "eval_loss": 4.036824703216553, + "eval_runtime": 301.8829, + "eval_samples_per_second": 1264.036, + "eval_steps_per_second": 39.502, + "step": 992160 + }, + { + "epoch": 0.0, + "learning_rate": 3.375370079070313e-05, + "loss": 4.0072, + "step": 992256 + }, + { + "epoch": 0.0, + "learning_rate": 3.374531484319261e-05, + "loss": 3.9706, + "step": 992768 + }, + { + "epoch": 0.0, + "learning_rate": 3.373692889568209e-05, + "loss": 3.9872, + "step": 993280 + }, + { + "epoch": 0.0, + "learning_rate": 3.372854294817157e-05, + "loss": 4.0024, + "step": 993792 + }, + { + "epoch": 0.0, + "learning_rate": 3.372015700066105e-05, + "loss": 3.9934, + "step": 994304 + }, + { + "epoch": 0.0, + "learning_rate": 3.371177105315053e-05, + "loss": 3.9941, + "step": 994816 + }, + { + "epoch": 0.0, + "learning_rate": 3.370338510564001e-05, + "loss": 3.9949, + "step": 995328 + }, + { + "epoch": 0.0, + "learning_rate": 3.369499915812949e-05, + "loss": 3.9889, + "step": 995840 + }, + { + "epoch": 0.0, + "learning_rate": 3.368661321061897e-05, + "loss": 3.9814, + "step": 996352 + }, + { + "epoch": 0.0, + "learning_rate": 3.367822726310845e-05, + "loss": 3.9879, + "step": 996864 + }, + { + "epoch": 0.0, + "learning_rate": 3.366984131559793e-05, + "loss": 3.9988, + "step": 997376 + }, + { + "epoch": 0.0, + "learning_rate": 3.366145536808741e-05, + "loss": 3.9938, + "step": 997888 + }, + { + "epoch": 0.0, + "learning_rate": 3.365306942057689e-05, + "loss": 4.0066, + "step": 998400 + }, + { + "epoch": 0.0, + "learning_rate": 3.364468347306637e-05, + "loss": 3.9779, + "step": 998912 + }, + { + "epoch": 0.0, + "learning_rate": 3.363629752555585e-05, + "loss": 3.9858, + "step": 999424 + }, + { + "epoch": 0.0, + "learning_rate": 3.362791157804533e-05, + "loss": 3.9728, + "step": 999936 + }, + { + "epoch": 0.0, + "learning_rate": 3.361952563053481e-05, + "loss": 3.9846, + "step": 1000448 + }, + { + "epoch": 0.0, + "learning_rate": 3.361115606182802e-05, + "loss": 3.9891, + "step": 1000960 + }, + { + "epoch": 0.0, + "learning_rate": 3.36027701143175e-05, + "loss": 3.9841, + "step": 1001472 + }, + { + "epoch": 0.0, + "learning_rate": 3.359438416680698e-05, + "loss": 3.9841, + "step": 1001984 + }, + { + "epoch": 0.0, + "learning_rate": 3.358599821929646e-05, + "loss": 4.0026, + "step": 1002496 + }, + { + "epoch": 0.0, + "learning_rate": 3.357761227178594e-05, + "loss": 3.9903, + "step": 1003008 + }, + { + "epoch": 0.0, + "learning_rate": 3.356922632427542e-05, + "loss": 3.9971, + "step": 1003520 + }, + { + "epoch": 0.0, + "learning_rate": 3.35608403767649e-05, + "loss": 3.992, + "step": 1004032 + }, + { + "epoch": 0.0, + "learning_rate": 3.3552470808058114e-05, + "loss": 3.9936, + "step": 1004544 + }, + { + "epoch": 0.0, + "learning_rate": 3.3544084860547594e-05, + "loss": 3.9845, + "step": 1005056 + }, + { + "epoch": 0.0, + "learning_rate": 3.3535698913037074e-05, + "loss": 3.9854, + "step": 1005568 + }, + { + "epoch": 0.0, + "learning_rate": 3.352732934433028e-05, + "loss": 3.9934, + "step": 1006080 + }, + { + "epoch": 0.0, + "learning_rate": 3.351894339681976e-05, + "loss": 3.9879, + "step": 1006592 + }, + { + "epoch": 0.0, + "learning_rate": 3.351055744930924e-05, + "loss": 3.974, + "step": 1007104 + }, + { + "epoch": 0.01, + "learning_rate": 3.350217150179872e-05, + "loss": 3.987, + "step": 1007616 + }, + { + "epoch": 0.01, + "learning_rate": 3.34937855542882e-05, + "loss": 3.9903, + "step": 1008128 + }, + { + "epoch": 0.01, + "learning_rate": 3.348539960677768e-05, + "loss": 3.9931, + "step": 1008640 + }, + { + "epoch": 0.01, + "learning_rate": 3.3477013659267156e-05, + "loss": 3.9894, + "step": 1009152 + }, + { + "epoch": 0.01, + "learning_rate": 3.3468627711756636e-05, + "loss": 3.989, + "step": 1009664 + }, + { + "epoch": 0.01, + "learning_rate": 3.346025814304985e-05, + "loss": 3.9933, + "step": 1010176 + }, + { + "epoch": 0.01, + "learning_rate": 3.345187219553933e-05, + "loss": 3.9963, + "step": 1010688 + }, + { + "epoch": 0.01, + "learning_rate": 3.344348624802881e-05, + "loss": 3.9696, + "step": 1011200 + }, + { + "epoch": 0.01, + "learning_rate": 3.343510030051829e-05, + "loss": 3.9827, + "step": 1011712 + }, + { + "epoch": 0.01, + "learning_rate": 3.342671435300777e-05, + "loss": 3.9784, + "step": 1012224 + }, + { + "epoch": 0.01, + "learning_rate": 3.341834478430098e-05, + "loss": 3.9823, + "step": 1012736 + }, + { + "epoch": 0.01, + "learning_rate": 3.340995883679046e-05, + "loss": 3.9944, + "step": 1013248 + }, + { + "epoch": 0.01, + "learning_rate": 3.340157288927994e-05, + "loss": 3.9912, + "step": 1013760 + }, + { + "epoch": 0.01, + "learning_rate": 3.339318694176942e-05, + "loss": 3.9891, + "step": 1014272 + }, + { + "epoch": 0.01, + "learning_rate": 3.33848009942589e-05, + "loss": 3.9888, + "step": 1014784 + }, + { + "epoch": 0.01, + "learning_rate": 3.337641504674838e-05, + "loss": 3.985, + "step": 1015296 + }, + { + "epoch": 0.01, + "learning_rate": 3.336802909923786e-05, + "loss": 3.9904, + "step": 1015808 + }, + { + "epoch": 0.01, + "learning_rate": 3.335964315172734e-05, + "loss": 3.9957, + "step": 1016320 + }, + { + "epoch": 0.01, + "learning_rate": 3.3351289961824286e-05, + "loss": 3.9619, + "step": 1016832 + }, + { + "epoch": 0.01, + "learning_rate": 3.3342904014313766e-05, + "loss": 3.9963, + "step": 1017344 + }, + { + "epoch": 0.01, + "learning_rate": 3.3334518066803246e-05, + "loss": 3.9852, + "step": 1017856 + }, + { + "epoch": 0.01, + "learning_rate": 3.3326132119292726e-05, + "loss": 3.9924, + "step": 1018368 + }, + { + "epoch": 0.01, + "learning_rate": 3.3317746171782206e-05, + "loss": 3.9784, + "step": 1018880 + }, + { + "epoch": 0.01, + "learning_rate": 3.3309360224271685e-05, + "loss": 3.9799, + "step": 1019392 + }, + { + "epoch": 0.01, + "learning_rate": 3.3300990655564895e-05, + "loss": 3.9754, + "step": 1019904 + }, + { + "epoch": 0.01, + "learning_rate": 3.3292604708054375e-05, + "loss": 3.9765, + "step": 1020416 + }, + { + "epoch": 0.01, + "learning_rate": 3.3284218760543854e-05, + "loss": 3.9883, + "step": 1020928 + }, + { + "epoch": 0.01, + "learning_rate": 3.3275832813033334e-05, + "loss": 3.9686, + "step": 1021440 + }, + { + "epoch": 0.01, + "learning_rate": 3.3267446865522814e-05, + "loss": 3.9976, + "step": 1021952 + }, + { + "epoch": 0.01, + "learning_rate": 3.3259060918012294e-05, + "loss": 3.9838, + "step": 1022464 + }, + { + "epoch": 0.01, + "learning_rate": 3.3250674970501774e-05, + "loss": 3.9647, + "step": 1022976 + }, + { + "epoch": 0.01, + "learning_rate": 3.324230540179499e-05, + "loss": 3.9921, + "step": 1023488 + }, + { + "epoch": 0.01, + "learning_rate": 3.323391945428447e-05, + "loss": 3.9685, + "step": 1024000 + }, + { + "epoch": 0.01, + "learning_rate": 3.322553350677395e-05, + "loss": 3.9763, + "step": 1024512 + }, + { + "epoch": 0.01, + "learning_rate": 3.321714755926343e-05, + "loss": 3.9819, + "step": 1025024 + }, + { + "epoch": 0.01, + "learning_rate": 3.320876161175291e-05, + "loss": 3.9867, + "step": 1025536 + }, + { + "epoch": 0.01, + "learning_rate": 3.320037566424239e-05, + "loss": 3.9694, + "step": 1026048 + }, + { + "epoch": 0.01, + "learning_rate": 3.319198971673187e-05, + "loss": 3.9827, + "step": 1026560 + }, + { + "epoch": 0.01, + "learning_rate": 3.318360376922134e-05, + "loss": 3.9665, + "step": 1027072 + }, + { + "epoch": 0.01, + "learning_rate": 3.317521782171082e-05, + "loss": 3.9778, + "step": 1027584 + }, + { + "epoch": 0.01, + "learning_rate": 3.316684825300404e-05, + "loss": 3.9914, + "step": 1028096 + }, + { + "epoch": 0.01, + "learning_rate": 3.315846230549352e-05, + "loss": 3.9801, + "step": 1028608 + }, + { + "epoch": 0.01, + "learning_rate": 3.315007635798299e-05, + "loss": 3.9884, + "step": 1029120 + }, + { + "epoch": 0.01, + "learning_rate": 3.314169041047248e-05, + "loss": 3.9837, + "step": 1029632 + }, + { + "epoch": 0.01, + "learning_rate": 3.3133320841765695e-05, + "loss": 3.998, + "step": 1030144 + }, + { + "epoch": 0.01, + "learning_rate": 3.3124951273058904e-05, + "loss": 3.9765, + "step": 1030656 + }, + { + "epoch": 0.01, + "learning_rate": 3.3116565325548384e-05, + "loss": 3.9869, + "step": 1031168 + }, + { + "epoch": 0.01, + "learning_rate": 3.310819575684159e-05, + "loss": 3.976, + "step": 1031680 + }, + { + "epoch": 0.01, + "learning_rate": 3.309980980933107e-05, + "loss": 3.972, + "step": 1032192 + }, + { + "epoch": 0.01, + "learning_rate": 3.309142386182055e-05, + "loss": 3.9862, + "step": 1032704 + }, + { + "epoch": 0.01, + "learning_rate": 3.308303791431003e-05, + "loss": 3.9799, + "step": 1033216 + }, + { + "epoch": 0.01, + "learning_rate": 3.307465196679951e-05, + "loss": 3.9885, + "step": 1033728 + }, + { + "epoch": 0.01, + "learning_rate": 3.306626601928899e-05, + "loss": 3.9945, + "step": 1034240 + }, + { + "epoch": 0.01, + "learning_rate": 3.3057880071778466e-05, + "loss": 3.9733, + "step": 1034752 + }, + { + "epoch": 0.01, + "learning_rate": 3.3049494124267946e-05, + "loss": 3.9703, + "step": 1035264 + }, + { + "epoch": 0.01, + "learning_rate": 3.304110817675743e-05, + "loss": 3.9792, + "step": 1035776 + }, + { + "epoch": 0.01, + "learning_rate": 3.303273860805064e-05, + "loss": 3.987, + "step": 1036288 + }, + { + "epoch": 0.01, + "learning_rate": 3.302435266054012e-05, + "loss": 3.9781, + "step": 1036800 + }, + { + "epoch": 0.01, + "learning_rate": 3.301598309183334e-05, + "loss": 3.9833, + "step": 1037312 + }, + { + "epoch": 0.01, + "learning_rate": 3.300759714432282e-05, + "loss": 3.9859, + "step": 1037824 + }, + { + "epoch": 0.02, + "learning_rate": 3.299921119681229e-05, + "loss": 3.9773, + "step": 1038336 + }, + { + "epoch": 0.02, + "learning_rate": 3.299082524930177e-05, + "loss": 3.978, + "step": 1038848 + }, + { + "epoch": 0.02, + "learning_rate": 3.298243930179125e-05, + "loss": 3.9684, + "step": 1039360 + }, + { + "epoch": 0.02, + "learning_rate": 3.297405335428073e-05, + "loss": 3.9886, + "step": 1039872 + }, + { + "epoch": 0.02, + "learning_rate": 3.296566740677021e-05, + "loss": 3.9856, + "step": 1040384 + }, + { + "epoch": 0.02, + "learning_rate": 3.295728145925969e-05, + "loss": 3.9837, + "step": 1040896 + }, + { + "epoch": 0.02, + "learning_rate": 3.294889551174917e-05, + "loss": 3.977, + "step": 1041408 + }, + { + "epoch": 0.02, + "learning_rate": 3.2940525943042386e-05, + "loss": 3.9706, + "step": 1041920 + }, + { + "epoch": 0.02, + "learning_rate": 3.2932139995531866e-05, + "loss": 3.9891, + "step": 1042432 + }, + { + "epoch": 0.02, + "learning_rate": 3.2923754048021346e-05, + "loss": 3.9877, + "step": 1042944 + }, + { + "epoch": 0.02, + "learning_rate": 3.2915368100510826e-05, + "loss": 3.9811, + "step": 1043456 + }, + { + "epoch": 0.02, + "learning_rate": 3.2906998531804035e-05, + "loss": 3.9798, + "step": 1043968 + }, + { + "epoch": 0.02, + "learning_rate": 3.2898612584293515e-05, + "loss": 3.9758, + "step": 1044480 + }, + { + "epoch": 0.02, + "learning_rate": 3.2890226636782995e-05, + "loss": 3.9812, + "step": 1044992 + }, + { + "epoch": 0.02, + "learning_rate": 3.2881840689272475e-05, + "loss": 3.9743, + "step": 1045504 + }, + { + "epoch": 0.02, + "learning_rate": 3.2873454741761955e-05, + "loss": 3.968, + "step": 1046016 + }, + { + "epoch": 0.02, + "learning_rate": 3.2865068794251435e-05, + "loss": 3.9746, + "step": 1046528 + }, + { + "epoch": 0.02, + "learning_rate": 3.2856682846740915e-05, + "loss": 3.9787, + "step": 1047040 + }, + { + "epoch": 0.02, + "learning_rate": 3.2848296899230395e-05, + "loss": 3.9868, + "step": 1047552 + }, + { + "epoch": 0.02, + "learning_rate": 3.2839927330523604e-05, + "loss": 3.9685, + "step": 1048064 + }, + { + "epoch": 0.02, + "learning_rate": 3.283155776181682e-05, + "loss": 3.9754, + "step": 1048576 + }, + { + "epoch": 0.02, + "learning_rate": 3.28231718143063e-05, + "loss": 3.971, + "step": 1049088 + }, + { + "epoch": 0.02, + "learning_rate": 3.281478586679578e-05, + "loss": 3.9854, + "step": 1049600 + }, + { + "epoch": 0.02, + "learning_rate": 3.280639991928526e-05, + "loss": 3.9728, + "step": 1050112 + }, + { + "epoch": 0.02, + "learning_rate": 3.279801397177474e-05, + "loss": 3.9764, + "step": 1050624 + }, + { + "epoch": 0.02, + "learning_rate": 3.278962802426422e-05, + "loss": 3.9829, + "step": 1051136 + }, + { + "epoch": 0.02, + "learning_rate": 3.27812420767537e-05, + "loss": 3.9898, + "step": 1051648 + }, + { + "epoch": 0.02, + "learning_rate": 3.277287250804691e-05, + "loss": 3.9767, + "step": 1052160 + }, + { + "epoch": 0.02, + "learning_rate": 3.276448656053639e-05, + "loss": 3.9763, + "step": 1052672 + }, + { + "epoch": 0.02, + "learning_rate": 3.275610061302587e-05, + "loss": 3.9794, + "step": 1053184 + }, + { + "epoch": 0.02, + "learning_rate": 3.274771466551535e-05, + "loss": 3.9854, + "step": 1053696 + }, + { + "epoch": 0.02, + "learning_rate": 3.273932871800482e-05, + "loss": 3.9715, + "step": 1054208 + }, + { + "epoch": 0.02, + "learning_rate": 3.273095914929804e-05, + "loss": 3.9773, + "step": 1054720 + }, + { + "epoch": 0.02, + "learning_rate": 3.2722573201787524e-05, + "loss": 3.9751, + "step": 1055232 + }, + { + "epoch": 0.02, + "learning_rate": 3.2714187254277004e-05, + "loss": 3.9826, + "step": 1055744 + }, + { + "epoch": 0.02, + "learning_rate": 3.270580130676648e-05, + "loss": 3.9781, + "step": 1056256 + }, + { + "epoch": 0.02, + "learning_rate": 3.269743173805969e-05, + "loss": 3.9704, + "step": 1056768 + }, + { + "epoch": 0.02, + "learning_rate": 3.268904579054917e-05, + "loss": 3.9767, + "step": 1057280 + }, + { + "epoch": 0.02, + "learning_rate": 3.268065984303865e-05, + "loss": 3.9714, + "step": 1057792 + }, + { + "epoch": 0.02, + "learning_rate": 3.2672273895528126e-05, + "loss": 3.9855, + "step": 1058304 + }, + { + "epoch": 0.02, + "learning_rate": 3.2663887948017606e-05, + "loss": 3.9807, + "step": 1058816 + }, + { + "epoch": 0.02, + "learning_rate": 3.2655502000507086e-05, + "loss": 3.9851, + "step": 1059328 + }, + { + "epoch": 0.02, + "learning_rate": 3.2647116052996566e-05, + "loss": 3.9715, + "step": 1059840 + }, + { + "epoch": 0.02, + "learning_rate": 3.2638746484289775e-05, + "loss": 3.9843, + "step": 1060352 + }, + { + "epoch": 0.02, + "learning_rate": 3.263036053677926e-05, + "loss": 3.9872, + "step": 1060864 + }, + { + "epoch": 0.02, + "learning_rate": 3.262197458926874e-05, + "loss": 3.9778, + "step": 1061376 + }, + { + "epoch": 0.02, + "learning_rate": 3.261358864175822e-05, + "loss": 3.9802, + "step": 1061888 + }, + { + "epoch": 0.02, + "learning_rate": 3.26052026942477e-05, + "loss": 3.9742, + "step": 1062400 + }, + { + "epoch": 0.02, + "learning_rate": 3.259681674673718e-05, + "loss": 3.992, + "step": 1062912 + }, + { + "epoch": 0.02, + "learning_rate": 3.258843079922666e-05, + "loss": 3.9898, + "step": 1063424 + }, + { + "epoch": 0.02, + "learning_rate": 3.258006123051987e-05, + "loss": 3.982, + "step": 1063936 + }, + { + "epoch": 0.02, + "learning_rate": 3.257167528300935e-05, + "loss": 3.9758, + "step": 1064448 + }, + { + "epoch": 0.02, + "learning_rate": 3.256328933549883e-05, + "loss": 3.9888, + "step": 1064960 + }, + { + "epoch": 0.02, + "learning_rate": 3.255490338798831e-05, + "loss": 3.9767, + "step": 1065472 + }, + { + "epoch": 0.02, + "learning_rate": 3.254653381928152e-05, + "loss": 3.9679, + "step": 1065984 + }, + { + "epoch": 0.02, + "learning_rate": 3.2538147871771e-05, + "loss": 3.9897, + "step": 1066496 + }, + { + "epoch": 0.02, + "learning_rate": 3.252976192426048e-05, + "loss": 3.9765, + "step": 1067008 + }, + { + "epoch": 0.02, + "learning_rate": 3.252137597674996e-05, + "loss": 3.9925, + "step": 1067520 + }, + { + "epoch": 0.02, + "learning_rate": 3.251299002923944e-05, + "loss": 3.9735, + "step": 1068032 + }, + { + "epoch": 0.03, + "eval_loss": 4.028215408325195, + "eval_runtime": 295.3074, + "eval_samples_per_second": 1292.182, + "eval_steps_per_second": 40.382, + "step": 1068480 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 4.403068497643776e+17, + "trial_name": null, + "trial_params": null +}