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": 4.0296406745910645, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/full2/lstm/4/checkpoints/checkpoint-1068480", + "epoch": 1.0250006060157382, + "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": 10.8217, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 7.5568, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 7.0575, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 6.9931, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 6.9484, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 6.8791, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 6.7241, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 6.6207, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 6.5202, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 6.4443, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 6.3852, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 6.33, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 6.2719, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989098268236324e-05, + "loss": 6.2014, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988259673485272e-05, + "loss": 6.1552, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.98742107873422e-05, + "loss": 6.1015, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 6.0593, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 6.0156, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.9765, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.931, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.9008, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.982391148108281e-05, + "loss": 5.8631, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.981552553357229e-05, + "loss": 5.8367, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.980713958606178e-05, + "loss": 5.7946, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.979875363855125e-05, + "loss": 5.7844, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.979036769104073e-05, + "loss": 5.7509, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9781998122333946e-05, + "loss": 5.7237, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773612174823426e-05, + "loss": 5.6913, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.97652262273129e-05, + "loss": 5.6708, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.975684027980238e-05, + "loss": 5.6562, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.974845433229186e-05, + "loss": 5.6242, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.974008476358507e-05, + "loss": 5.6161, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.973169881607455e-05, + "loss": 5.5889, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.972331286856403e-05, + "loss": 5.5709, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.9714926921053515e-05, + "loss": 5.5674, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.9706557352346724e-05, + "loss": 5.5504, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.9698171404836204e-05, + "loss": 5.5262, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.9689785457325684e-05, + "loss": 5.4993, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.9681399509815164e-05, + "loss": 5.4884, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967302994110837e-05, + "loss": 5.4629, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966464399359785e-05, + "loss": 5.4628, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 5.4382, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 5.4321, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 5.4084, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.96311165823595e-05, + "loss": 5.4089, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962273063484898e-05, + "loss": 5.3942, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.961434468733847e-05, + "loss": 5.3942, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960595873982795e-05, + "loss": 5.3815, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959757279231743e-05, + "loss": 5.3523, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.958920322361064e-05, + "loss": 5.3439, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958081727610012e-05, + "loss": 5.3532, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.95724313285896e-05, + "loss": 5.3337, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956404538107908e-05, + "loss": 5.321, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.955567581237229e-05, + "loss": 5.3028, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.954728986486177e-05, + "loss": 5.3049, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.953890391735125e-05, + "loss": 5.2859, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530517969840727e-05, + "loss": 5.2957, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522132022330207e-05, + "loss": 5.2613, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.9513746074819686e-05, + "loss": 5.2641, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.95053765061129e-05, + "loss": 5.2597, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 5.2436, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948862098989559e-05, + "loss": 5.2499, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.948023504238507e-05, + "loss": 5.2204, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947184909487455e-05, + "loss": 5.2166, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946346314736403e-05, + "loss": 5.205, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945507719985351e-05, + "loss": 5.2255, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944669125234299e-05, + "loss": 5.1913, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.94383216836362e-05, + "loss": 5.1922, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942993573612568e-05, + "loss": 5.174, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.942154978861516e-05, + "loss": 5.1686, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.941318021990837e-05, + "loss": 5.1768, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404794272397856e-05, + "loss": 5.1702, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396408324887336e-05, + "loss": 5.1607, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388022377376816e-05, + "loss": 5.16, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379636429866296e-05, + "loss": 5.1609, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371250482355776e-05, + "loss": 5.13, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362864534845256e-05, + "loss": 5.1388, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.935447858733473e-05, + "loss": 5.1158, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.934609263982421e-05, + "loss": 5.1105, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.933770669231369e-05, + "loss": 5.1119, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.932932074480317e-05, + "loss": 5.111, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.932095117609638e-05, + "loss": 5.1003, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931256522858586e-05, + "loss": 5.1084, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930417928107534e-05, + "loss": 5.0886, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.9295793333564825e-05, + "loss": 5.0719, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.9287407386054305e-05, + "loss": 5.0666, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.9279021438543785e-05, + "loss": 5.0796, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.9270635491033264e-05, + "loss": 5.0609, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.9262249543522744e-05, + "loss": 5.0577, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.9253879974815954e-05, + "loss": 5.0546, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.9245494027305433e-05, + "loss": 5.0424, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.9237108079794913e-05, + "loss": 5.0434, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922872213228439e-05, + "loss": 5.037, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.922033618477387e-05, + "loss": 5.038, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921196661606708e-05, + "loss": 5.0346, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920358066855656e-05, + "loss": 5.0235, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919519472104604e-05, + "loss": 5.0081, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918680877353552e-05, + "loss": 5.0091, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.917843920482874e-05, + "loss": 4.998, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.917005325731822e-05, + "loss": 4.9966, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.91616673098077e-05, + "loss": 5.0055, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.915328136229718e-05, + "loss": 4.9836, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914489541478666e-05, + "loss": 4.9879, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.913650946727614e-05, + "loss": 4.9817, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.912812351976562e-05, + "loss": 4.9709, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.911973757225509e-05, + "loss": 4.9638, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.911136800354831e-05, + "loss": 4.9625, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910298205603779e-05, + "loss": 4.9471, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.909459610852727e-05, + "loss": 4.9482, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908621016101675e-05, + "loss": 4.9456, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907782421350623e-05, + "loss": 4.9452, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.906943826599571e-05, + "loss": 4.9374, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906105231848519e-05, + "loss": 4.9351, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.9052682749778396e-05, + "loss": 4.9261, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.9044296802267876e-05, + "loss": 4.9291, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.9035910854757356e-05, + "loss": 4.9311, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.9027524907246836e-05, + "loss": 4.9234, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.901917171734378e-05, + "loss": 4.9231, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.901078576983326e-05, + "loss": 4.9091, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.900239982232274e-05, + "loss": 4.9123, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8994013874812214e-05, + "loss": 4.9089, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.89856279273017e-05, + "loss": 4.8942, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.897724197979118e-05, + "loss": 4.892, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.896885603228066e-05, + "loss": 4.8888, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.896047008477014e-05, + "loss": 4.8899, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.895208413725962e-05, + "loss": 4.8772, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.89436981897491e-05, + "loss": 4.8822, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.893532862104231e-05, + "loss": 4.8761, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.892694267353179e-05, + "loss": 4.8678, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.891855672602127e-05, + "loss": 4.8608, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.891017077851075e-05, + "loss": 4.8783, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890178483100023e-05, + "loss": 4.8675, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889339888348971e-05, + "loss": 4.8598, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888501293597919e-05, + "loss": 4.8588, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.887662698846867e-05, + "loss": 4.8564, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886825741976188e-05, + "loss": 4.8544, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.8859871472251365e-05, + "loss": 4.8545, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.88515182823483e-05, + "loss": 4.8471, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884313233483778e-05, + "loss": 4.8406, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883474638732726e-05, + "loss": 4.8368, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882636043981674e-05, + "loss": 4.8251, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881797449230622e-05, + "loss": 4.8232, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.88095885447957e-05, + "loss": 4.8228, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880120259728518e-05, + "loss": 4.8266, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879283302857839e-05, + "loss": 4.8195, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878444708106787e-05, + "loss": 4.8184, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877606113355735e-05, + "loss": 4.8147, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876767518604683e-05, + "loss": 4.8142, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875928923853632e-05, + "loss": 4.8188, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.87509032910258e-05, + "loss": 4.7959, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.763843536376953, + "eval_runtime": 293.53, + "eval_samples_per_second": 1300.007, + "eval_steps_per_second": 40.626, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.874253372231901e-05, + "loss": 4.7882, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.873414777480849e-05, + "loss": 4.7878, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.872576182729797e-05, + "loss": 4.8056, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.871737587978745e-05, + "loss": 4.7883, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.870898993227693e-05, + "loss": 4.7936, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.87006039847664e-05, + "loss": 4.7843, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.8692234416059616e-05, + "loss": 4.7813, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.8683848468549096e-05, + "loss": 4.7668, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.8675462521038576e-05, + "loss": 4.7723, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.8667076573528056e-05, + "loss": 4.7691, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.8658690626017536e-05, + "loss": 4.7901, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.8650304678507016e-05, + "loss": 4.7725, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.8641935109800225e-05, + "loss": 4.7569, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.8633549162289705e-05, + "loss": 4.7583, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.8625163214779185e-05, + "loss": 4.7582, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.8616777267268665e-05, + "loss": 4.7493, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.8608391319758145e-05, + "loss": 4.7603, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.8600005372247625e-05, + "loss": 4.753, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.8591619424737105e-05, + "loss": 4.7439, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.8583233477226585e-05, + "loss": 4.7594, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.8574863908519794e-05, + "loss": 4.7437, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.8566477961009274e-05, + "loss": 4.7449, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.8558092013498754e-05, + "loss": 4.7302, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.854972244479197e-05, + "loss": 4.753, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.854133649728145e-05, + "loss": 4.7307, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.853295054977093e-05, + "loss": 4.7289, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.852456460226041e-05, + "loss": 4.7202, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.851617865474989e-05, + "loss": 4.7219, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.850779270723937e-05, + "loss": 4.7177, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.849940675972885e-05, + "loss": 4.7153, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.849102081221833e-05, + "loss": 4.7203, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.848263486470781e-05, + "loss": 4.7155, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847426529600102e-05, + "loss": 4.7124, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846589572729423e-05, + "loss": 4.7218, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845750977978371e-05, + "loss": 4.7131, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.8449123832273194e-05, + "loss": 4.7088, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.8440737884762674e-05, + "loss": 4.6957, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.8432351937252154e-05, + "loss": 4.698, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.8423965989741634e-05, + "loss": 4.6878, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.8415580042231114e-05, + "loss": 4.6965, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840721047352432e-05, + "loss": 4.6842, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.83988245260138e-05, + "loss": 4.6923, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839043857850328e-05, + "loss": 4.6752, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.838205263099276e-05, + "loss": 4.696, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.8373666683482236e-05, + "loss": 4.684, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.8365280735971716e-05, + "loss": 4.6872, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.8356894788461196e-05, + "loss": 4.6839, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.834852521975441e-05, + "loss": 4.6664, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834013927224389e-05, + "loss": 4.6658, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.833175332473337e-05, + "loss": 4.6821, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.832336737722285e-05, + "loss": 4.6681, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.831499780851606e-05, + "loss": 4.6667, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.830661186100554e-05, + "loss": 4.6558, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.829822591349502e-05, + "loss": 4.6659, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.828985634478824e-05, + "loss": 4.6483, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.828147039727771e-05, + "loss": 4.6735, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.827308444976719e-05, + "loss": 4.6365, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.826469850225667e-05, + "loss": 4.6577, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.825631255474615e-05, + "loss": 4.6543, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.824792660723563e-05, + "loss": 4.6445, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.823954065972511e-05, + "loss": 4.6531, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.82311547122146e-05, + "loss": 4.6415, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.8222768764704077e-05, + "loss": 4.6338, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.8214399195997286e-05, + "loss": 4.6316, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.8206013248486766e-05, + "loss": 4.6551, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.8197627300976246e-05, + "loss": 4.6243, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.8189241353465726e-05, + "loss": 4.6376, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.8180855405955206e-05, + "loss": 4.619, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.8172469458444685e-05, + "loss": 4.6274, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.8164083510934165e-05, + "loss": 4.6381, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.8155713942227375e-05, + "loss": 4.6361, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.8147344373520584e-05, + "loss": 4.6266, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.8138958426010064e-05, + "loss": 4.6338, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.813057247849955e-05, + "loss": 4.6363, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.812218653098903e-05, + "loss": 4.6206, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.811380058347851e-05, + "loss": 4.6279, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.810543101477172e-05, + "loss": 4.6148, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.80970450672612e-05, + "loss": 4.6141, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.808865911975068e-05, + "loss": 4.6088, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808027317224016e-05, + "loss": 4.6171, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.807188722472964e-05, + "loss": 4.6175, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.806350127721912e-05, + "loss": 4.6236, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.80551153297086e-05, + "loss": 4.6129, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804672938219807e-05, + "loss": 4.5931, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803834343468755e-05, + "loss": 4.5955, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.802995748717703e-05, + "loss": 4.6081, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.802157153966652e-05, + "loss": 4.6005, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.801320197095973e-05, + "loss": 4.5981, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.8004832402252944e-05, + "loss": 4.6041, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.7996446454742424e-05, + "loss": 4.5887, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.79880605072319e-05, + "loss": 4.5934, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.797969093852511e-05, + "loss": 4.5951, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.797130499101459e-05, + "loss": 4.5999, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.796291904350407e-05, + "loss": 4.5964, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.7954533095993546e-05, + "loss": 4.597, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.7946147148483026e-05, + "loss": 4.5791, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.7937761200972506e-05, + "loss": 4.5848, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.7929375253461986e-05, + "loss": 4.5823, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.792098930595147e-05, + "loss": 4.5795, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.791261973724468e-05, + "loss": 4.5954, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.79042501685379e-05, + "loss": 4.5717, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.789586422102737e-05, + "loss": 4.578, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.788747827351685e-05, + "loss": 4.5787, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.787909232600633e-05, + "loss": 4.5726, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.787070637849581e-05, + "loss": 4.5616, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.786232043098529e-05, + "loss": 4.5727, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.785393448347477e-05, + "loss": 4.5605, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.784554853596425e-05, + "loss": 4.5617, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.783716258845373e-05, + "loss": 4.5615, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.782877664094321e-05, + "loss": 4.5606, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.782040707223642e-05, + "loss": 4.5579, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.7812021124725906e-05, + "loss": 4.5656, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.7803635177215386e-05, + "loss": 4.5521, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.7795249229704866e-05, + "loss": 4.5611, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.7786863282194346e-05, + "loss": 4.5682, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.7778477334683826e-05, + "loss": 4.5593, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.7770107765977035e-05, + "loss": 4.5629, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.7761721818466515e-05, + "loss": 4.5548, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.7753335870955995e-05, + "loss": 4.5527, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.7744949923445475e-05, + "loss": 4.5549, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.7736563975934955e-05, + "loss": 4.5462, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.7728178028424435e-05, + "loss": 4.5421, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.771979208091391e-05, + "loss": 4.5442, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.771140613340339e-05, + "loss": 4.5486, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.770305294350034e-05, + "loss": 4.5417, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.769466699598982e-05, + "loss": 4.5413, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.76862810484793e-05, + "loss": 4.5419, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.767789510096878e-05, + "loss": 4.5331, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766952553226199e-05, + "loss": 4.5288, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766113958475147e-05, + "loss": 4.5518, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.765275363724095e-05, + "loss": 4.5435, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764436768973043e-05, + "loss": 4.5419, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.763599812102364e-05, + "loss": 4.5349, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762761217351312e-05, + "loss": 4.5367, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.76192262260026e-05, + "loss": 4.5341, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.761084027849208e-05, + "loss": 4.5445, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.760245433098156e-05, + "loss": 4.5347, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.759406838347104e-05, + "loss": 4.5275, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.758568243596052e-05, + "loss": 4.5285, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.757729648845e-05, + "loss": 4.5215, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.756891054093948e-05, + "loss": 4.5176, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.7560540972232686e-05, + "loss": 4.5242, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.7552155024722166e-05, + "loss": 4.5271, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.7543769077211646e-05, + "loss": 4.5173, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.7535383129701126e-05, + "loss": 4.5273, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.7526997182190606e-05, + "loss": 4.5233, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.7518611234680086e-05, + "loss": 4.5187, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.7510241665973295e-05, + "loss": 4.5223, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.750185571846278e-05, + "loss": 4.5079, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.4814772605896, + "eval_runtime": 293.6326, + "eval_samples_per_second": 1299.552, + "eval_steps_per_second": 40.612, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.749346977095226e-05, + "loss": 4.5001, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748508382344174e-05, + "loss": 4.5029, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.747669787593122e-05, + "loss": 4.5214, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.74683119284207e-05, + "loss": 4.508, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.745992598091018e-05, + "loss": 4.5179, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.745154003339966e-05, + "loss": 4.5036, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.744315408588914e-05, + "loss": 4.5076, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.743476813837862e-05, + "loss": 4.4926, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.7426382190868095e-05, + "loss": 4.502, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.7417996243357575e-05, + "loss": 4.498, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.7409610295847055e-05, + "loss": 4.5186, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.7401224348336535e-05, + "loss": 4.5092, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.7392838400826015e-05, + "loss": 4.4859, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.7384452453315495e-05, + "loss": 4.4937, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.737608288460871e-05, + "loss": 4.5003, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736769693709819e-05, + "loss": 4.4816, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735931098958767e-05, + "loss": 4.4982, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.735092504207715e-05, + "loss": 4.4932, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734255547337036e-05, + "loss": 4.4868, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733416952585984e-05, + "loss": 4.5083, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732578357834932e-05, + "loss": 4.4888, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.73173976308388e-05, + "loss": 4.4951, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.730901168332828e-05, + "loss": 4.4789, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730062573581776e-05, + "loss": 4.5053, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.729223978830724e-05, + "loss": 4.4784, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.728385384079672e-05, + "loss": 4.484, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.72754678932862e-05, + "loss": 4.4734, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.7267098324579415e-05, + "loss": 4.4823, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.7258728755872624e-05, + "loss": 4.473, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.7250342808362104e-05, + "loss": 4.4733, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.7241956860851584e-05, + "loss": 4.4826, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.7233570913341064e-05, + "loss": 4.4802, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.7225184965830544e-05, + "loss": 4.4728, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.7216799018320024e-05, + "loss": 4.488, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.7208413070809504e-05, + "loss": 4.474, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.7200027123298984e-05, + "loss": 4.4765, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.719164117578846e-05, + "loss": 4.4655, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.718327160708167e-05, + "loss": 4.4709, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.717488565957115e-05, + "loss": 4.4567, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.716649971206063e-05, + "loss": 4.4721, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.715811376455011e-05, + "loss": 4.4574, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.714972781703959e-05, + "loss": 4.4679, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.714135824833281e-05, + "loss": 4.4531, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.713297230082228e-05, + "loss": 4.4692, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.71246027321155e-05, + "loss": 4.4692, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.711621678460498e-05, + "loss": 4.4627, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.710783083709446e-05, + "loss": 4.4693, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.709944488958393e-05, + "loss": 4.4481, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.7091075320877147e-05, + "loss": 4.4475, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.7082689373366627e-05, + "loss": 4.4646, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.7074303425856106e-05, + "loss": 4.4519, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.7065917478345586e-05, + "loss": 4.4556, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.7057531530835066e-05, + "loss": 4.441, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.7049145583324546e-05, + "loss": 4.455, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.7040759635814026e-05, + "loss": 4.4343, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.7032373688303506e-05, + "loss": 4.4653, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.7023987740792986e-05, + "loss": 4.4274, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.7015601793282466e-05, + "loss": 4.4495, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.7007248603379404e-05, + "loss": 4.4496, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.6998862655868884e-05, + "loss": 4.4364, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.6990476708358364e-05, + "loss": 4.4518, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.6982090760847844e-05, + "loss": 4.4361, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.6973704813337324e-05, + "loss": 4.4306, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.6965318865826804e-05, + "loss": 4.4277, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.695693291831629e-05, + "loss": 4.4507, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694854697080577e-05, + "loss": 4.4278, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694016102329525e-05, + "loss": 4.4376, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693177507578473e-05, + "loss": 4.4245, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692338912827421e-05, + "loss": 4.4265, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.691500318076369e-05, + "loss": 4.441, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690664999086063e-05, + "loss": 4.4429, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.689826404335011e-05, + "loss": 4.427, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.688989447464332e-05, + "loss": 4.4454, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.68815085271328e-05, + "loss": 4.4415, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.687312257962228e-05, + "loss": 4.4317, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.686473663211176e-05, + "loss": 4.4303, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.6856350684601245e-05, + "loss": 4.4292, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.6847964737090725e-05, + "loss": 4.4231, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.6839578789580204e-05, + "loss": 4.422, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.6831192842069684e-05, + "loss": 4.4294, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.6822806894559164e-05, + "loss": 4.4325, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.6814420947048644e-05, + "loss": 4.4397, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.680603499953812e-05, + "loss": 4.4259, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.67976490520276e-05, + "loss": 4.4061, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678929586212454e-05, + "loss": 4.4102, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678092629341775e-05, + "loss": 4.4249, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.677254034590723e-05, + "loss": 4.4179, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.676415439839671e-05, + "loss": 4.4177, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.675576845088619e-05, + "loss": 4.4213, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674738250337568e-05, + "loss": 4.4127, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.673899655586516e-05, + "loss": 4.4071, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.673061060835464e-05, + "loss": 4.4182, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.672222466084412e-05, + "loss": 4.4214, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.671383871333359e-05, + "loss": 4.418, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.670545276582307e-05, + "loss": 4.4198, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.669706681831255e-05, + "loss": 4.407, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.668868087080203e-05, + "loss": 4.4096, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668029492329151e-05, + "loss": 4.4066, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667192535458472e-05, + "loss": 4.4104, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.66635394070742e-05, + "loss": 4.4221, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665515345956368e-05, + "loss": 4.4028, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664676751205316e-05, + "loss": 4.4045, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663838156454265e-05, + "loss": 4.4072, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.663002837463959e-05, + "loss": 4.4076, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.6621642427129065e-05, + "loss": 4.3928, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.6613256479618545e-05, + "loss": 4.3997, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.6604870532108025e-05, + "loss": 4.3975, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.6596484584597505e-05, + "loss": 4.3948, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.6588098637086985e-05, + "loss": 4.3943, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.6579712689576465e-05, + "loss": 4.3953, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.6571326742065945e-05, + "loss": 4.3956, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.6562940794555425e-05, + "loss": 4.3968, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.6554571225848634e-05, + "loss": 4.3871, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.6546185278338114e-05, + "loss": 4.3957, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.65377993308276e-05, + "loss": 4.4061, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.652941338331708e-05, + "loss": 4.4044, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.652102743580656e-05, + "loss": 4.3984, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.651264148829604e-05, + "loss": 4.3938, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650427191958925e-05, + "loss": 4.3929, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.649588597207873e-05, + "loss": 4.3976, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648750002456821e-05, + "loss": 4.3839, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.647911407705769e-05, + "loss": 4.3831, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.647072812954717e-05, + "loss": 4.388, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.646235856084038e-05, + "loss": 4.3943, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.645397261332986e-05, + "loss": 4.3857, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.644558666581934e-05, + "loss": 4.3882, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.643720071830882e-05, + "loss": 4.3851, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.6428831149602034e-05, + "loss": 4.3791, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.6420445202091514e-05, + "loss": 4.3742, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.6412059254580994e-05, + "loss": 4.3977, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.6403673307070474e-05, + "loss": 4.3951, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.639530373836368e-05, + "loss": 4.3857, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.638691779085316e-05, + "loss": 4.3831, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.637853184334264e-05, + "loss": 4.3841, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.637014589583212e-05, + "loss": 4.3849, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.6361759948321596e-05, + "loss": 4.3995, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.6353374000811076e-05, + "loss": 4.3817, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.634500443210429e-05, + "loss": 4.3773, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.633661848459377e-05, + "loss": 4.3782, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.632823253708325e-05, + "loss": 4.3755, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.631984658957273e-05, + "loss": 4.3738, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.631146064206221e-05, + "loss": 4.376, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.630307469455169e-05, + "loss": 4.3805, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629468874704117e-05, + "loss": 4.3743, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.628630279953065e-05, + "loss": 4.3792, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.627791685202013e-05, + "loss": 4.382, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626953090450961e-05, + "loss": 4.3725, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626116133580282e-05, + "loss": 4.3795, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.62527753882923e-05, + "loss": 4.3625, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 4.345034122467041, + "eval_runtime": 345.5584, + "eval_samples_per_second": 1104.274, + "eval_steps_per_second": 34.509, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.624438944078178e-05, + "loss": 4.3681, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.623601987207499e-05, + "loss": 4.3571, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.6227633924564476e-05, + "loss": 4.381, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.6219247977053956e-05, + "loss": 4.3638, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.6210862029543436e-05, + "loss": 4.3797, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.6202476082032916e-05, + "loss": 4.3622, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.6194090134522396e-05, + "loss": 4.3691, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.6185704187011876e-05, + "loss": 4.3517, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.6177318239501356e-05, + "loss": 4.3671, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.6168932291990836e-05, + "loss": 4.355, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.616054634448031e-05, + "loss": 4.3819, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.615216039696979e-05, + "loss": 4.372, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.6143790828263005e-05, + "loss": 4.3461, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.6135404880752485e-05, + "loss": 4.3579, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.612701893324196e-05, + "loss": 4.3646, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.611863298573144e-05, + "loss": 4.351, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.6110247038220925e-05, + "loss": 4.359, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.610187746951414e-05, + "loss": 4.3598, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.609350790080735e-05, + "loss": 4.3522, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.608512195329683e-05, + "loss": 4.3793, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.607673600578631e-05, + "loss": 4.3548, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.606835005827578e-05, + "loss": 4.359, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.605996411076526e-05, + "loss": 4.3512, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.605157816325474e-05, + "loss": 4.3678, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.604319221574422e-05, + "loss": 4.349, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.60348062682337e-05, + "loss": 4.352, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.602642032072318e-05, + "loss": 4.345, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.601803437321266e-05, + "loss": 4.3498, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.600964842570214e-05, + "loss": 4.3468, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.600126247819162e-05, + "loss": 4.3448, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.599289290948484e-05, + "loss": 4.349, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.598452334077805e-05, + "loss": 4.3542, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.597613739326753e-05, + "loss": 4.3521, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.5967767824560737e-05, + "loss": 4.3561, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.5959381877050217e-05, + "loss": 4.3487, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.5950995929539696e-05, + "loss": 4.3492, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.5942609982029176e-05, + "loss": 4.336, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.5934224034518656e-05, + "loss": 4.3494, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.5925838087008136e-05, + "loss": 4.3299, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.5917452139497616e-05, + "loss": 4.3437, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.5909066191987096e-05, + "loss": 4.3343, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.5900680244476576e-05, + "loss": 4.3476, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.589231067576979e-05, + "loss": 4.3308, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.588392472825927e-05, + "loss": 4.3406, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.587553878074875e-05, + "loss": 4.3486, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.586715283323823e-05, + "loss": 4.3415, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.585876688572771e-05, + "loss": 4.3489, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.585039731702092e-05, + "loss": 4.3278, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.58420113695104e-05, + "loss": 4.3258, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.583362542199988e-05, + "loss": 4.3412, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.582523947448936e-05, + "loss": 4.3339, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.581686990578257e-05, + "loss": 4.3332, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.580848395827205e-05, + "loss": 4.3254, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.580009801076153e-05, + "loss": 4.337, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.5791712063251017e-05, + "loss": 4.3194, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.5783342494544226e-05, + "loss": 4.3383, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.5774956547033706e-05, + "loss": 4.3151, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.5766570599523186e-05, + "loss": 4.3264, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.5758184652012666e-05, + "loss": 4.337, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.5749815083305875e-05, + "loss": 4.3185, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.5741429135795355e-05, + "loss": 4.3313, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.5733043188284835e-05, + "loss": 4.3234, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.5724657240774315e-05, + "loss": 4.3154, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.5716287672067524e-05, + "loss": 4.3168, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.5707901724557004e-05, + "loss": 4.3296, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.5699515777046484e-05, + "loss": 4.3146, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.5691129829535963e-05, + "loss": 4.3227, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.5682743882025443e-05, + "loss": 4.3114, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.5674357934514923e-05, + "loss": 4.3105, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.56659719870044e-05, + "loss": 4.3259, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.565758603949388e-05, + "loss": 4.3306, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.564923284959083e-05, + "loss": 4.3146, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.564084690208031e-05, + "loss": 4.3342, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.563246095456979e-05, + "loss": 4.3299, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.562407500705927e-05, + "loss": 4.318, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.561568905954874e-05, + "loss": 4.3209, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.560730311203822e-05, + "loss": 4.318, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.559891716452771e-05, + "loss": 4.314, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.559053121701719e-05, + "loss": 4.3134, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.558214526950667e-05, + "loss": 4.3176, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.557377570079988e-05, + "loss": 4.3252, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.556538975328936e-05, + "loss": 4.3216, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.55570365633863e-05, + "loss": 4.3219, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.554865061587578e-05, + "loss": 4.3004, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.554026466836526e-05, + "loss": 4.3022, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.553187872085474e-05, + "loss": 4.3161, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.5523492773344215e-05, + "loss": 4.313, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.5515106825833695e-05, + "loss": 4.3097, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.5506720878323175e-05, + "loss": 4.3134, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.5498334930812655e-05, + "loss": 4.3056, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.548994898330214e-05, + "loss": 4.3023, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.548156303579162e-05, + "loss": 4.3097, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.54731770882811e-05, + "loss": 4.3125, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.546479114077058e-05, + "loss": 4.3106, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.545640519326006e-05, + "loss": 4.3189, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.544801924574954e-05, + "loss": 4.3033, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.543963329823902e-05, + "loss": 4.3026, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.543126372953223e-05, + "loss": 4.3027, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.542287778202171e-05, + "loss": 4.306, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.541449183451119e-05, + "loss": 4.3172, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.540610588700067e-05, + "loss": 4.2968, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.539771993949015e-05, + "loss": 4.3035, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.538935037078336e-05, + "loss": 4.3045, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.5380980802076575e-05, + "loss": 4.3058, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.5372594854566055e-05, + "loss": 4.2932, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.5364208907055535e-05, + "loss": 4.2977, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.5355822959545015e-05, + "loss": 4.2976, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.5347437012034495e-05, + "loss": 4.2927, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.5339051064523975e-05, + "loss": 4.2896, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.5330665117013455e-05, + "loss": 4.2948, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.5322295548306664e-05, + "loss": 4.2986, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.5313909600796144e-05, + "loss": 4.2948, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.5305523653285624e-05, + "loss": 4.2887, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.5297137705775104e-05, + "loss": 4.2926, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.528875175826458e-05, + "loss": 4.3095, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.5280365810754064e-05, + "loss": 4.3046, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.5271979863243544e-05, + "loss": 4.301, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.5263593915733024e-05, + "loss": 4.297, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.5255207968222504e-05, + "loss": 4.2942, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.524683839951571e-05, + "loss": 4.2957, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.523845245200519e-05, + "loss": 4.2853, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.523006650449467e-05, + "loss": 4.2884, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.522169693578788e-05, + "loss": 4.2892, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.521331098827736e-05, + "loss": 4.298, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.520492504076684e-05, + "loss": 4.2872, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.519653909325632e-05, + "loss": 4.2941, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.51881531457458e-05, + "loss": 4.2833, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.517976719823528e-05, + "loss": 4.288, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.517138125072476e-05, + "loss": 4.2772, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.516299530321425e-05, + "loss": 4.3012, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.515462573450746e-05, + "loss": 4.3011, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.5146256165800667e-05, + "loss": 4.2924, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.5137870218290147e-05, + "loss": 4.2867, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.5129484270779626e-05, + "loss": 4.2912, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.5121098323269106e-05, + "loss": 4.2868, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.5112712375758586e-05, + "loss": 4.3029, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.5104326428248066e-05, + "loss": 4.2838, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.5095940480737546e-05, + "loss": 4.2881, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.5087554533227026e-05, + "loss": 4.2819, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.5079184964520235e-05, + "loss": 4.2892, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.5070799017009715e-05, + "loss": 4.2768, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.5062413069499195e-05, + "loss": 4.2808, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.505402712198868e-05, + "loss": 4.2885, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.504564117447816e-05, + "loss": 4.2842, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.503727160577137e-05, + "loss": 4.2862, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.502888565826085e-05, + "loss": 4.2907, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.502049971075033e-05, + "loss": 4.2805, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.501211376323981e-05, + "loss": 4.2855, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.500372781572929e-05, + "loss": 4.2769, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 4.261603832244873, + "eval_runtime": 348.871, + "eval_samples_per_second": 1093.788, + "eval_steps_per_second": 34.182, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.49953582470225e-05, + "loss": 4.2691, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.498697229951198e-05, + "loss": 4.265, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.497858635200146e-05, + "loss": 4.2884, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.497020040449093e-05, + "loss": 4.2764, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.496181445698042e-05, + "loss": 4.2907, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.49534285094699e-05, + "loss": 4.2728, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.494504256195938e-05, + "loss": 4.2805, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.493665661444886e-05, + "loss": 4.2609, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.492827066693834e-05, + "loss": 4.2814, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.491988471942782e-05, + "loss": 4.2645, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.49114987719173e-05, + "loss": 4.2876, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.490312920321051e-05, + "loss": 4.285, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.489474325569999e-05, + "loss": 4.2546, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.488635730818947e-05, + "loss": 4.2739, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.487797136067895e-05, + "loss": 4.2761, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.486958541316843e-05, + "loss": 4.2631, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486119946565791e-05, + "loss": 4.2702, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.485281351814739e-05, + "loss": 4.273, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.484442757063687e-05, + "loss": 4.2684, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.483604162312635e-05, + "loss": 4.2884, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.482765567561583e-05, + "loss": 4.266, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481926972810531e-05, + "loss": 4.2726, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481088378059479e-05, + "loss": 4.2683, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.4802514211888004e-05, + "loss": 4.2799, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479412826437748e-05, + "loss": 4.2622, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478574231686696e-05, + "loss": 4.2724, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477735636935644e-05, + "loss": 4.256, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476897042184592e-05, + "loss": 4.2643, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.4760600853139126e-05, + "loss": 4.2605, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.4752214905628606e-05, + "loss": 4.2621, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.4743828958118086e-05, + "loss": 4.2628, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473544301060757e-05, + "loss": 4.2721, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472708982070452e-05, + "loss": 4.2675, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.4718703873194e-05, + "loss": 4.2729, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.471031792568348e-05, + "loss": 4.2632, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.470193197817295e-05, + "loss": 4.2682, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469354603066243e-05, + "loss": 4.2596, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468516008315191e-05, + "loss": 4.2588, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.467679051444512e-05, + "loss": 4.2508, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.46684045669346e-05, + "loss": 4.2606, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.466001861942408e-05, + "loss": 4.2545, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.465163267191356e-05, + "loss": 4.2656, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464324672440304e-05, + "loss": 4.2489, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.4634860776892526e-05, + "loss": 4.2578, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.4626474829382006e-05, + "loss": 4.2723, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.4618088881871486e-05, + "loss": 4.2594, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.4609702934360966e-05, + "loss": 4.2649, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.4601333365654175e-05, + "loss": 4.2513, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.4592947418143655e-05, + "loss": 4.2415, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.4584561470633135e-05, + "loss": 4.2622, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.4576175523122615e-05, + "loss": 4.2553, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.4567789575612095e-05, + "loss": 4.2518, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.4559403628101575e-05, + "loss": 4.2479, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.4551017680591055e-05, + "loss": 4.2586, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.4542648111884264e-05, + "loss": 4.2371, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.4534262164373744e-05, + "loss": 4.2603, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.4525876216863224e-05, + "loss": 4.2341, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.4517490269352704e-05, + "loss": 4.2486, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.450910432184219e-05, + "loss": 4.2534, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.45007347531354e-05, + "loss": 4.2438, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.449234880562488e-05, + "loss": 4.2485, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448396285811436e-05, + "loss": 4.246, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.447557691060384e-05, + "loss": 4.2365, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446720734189705e-05, + "loss": 4.2443, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445882139438653e-05, + "loss": 4.2488, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445043544687601e-05, + "loss": 4.2404, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444204949936548e-05, + "loss": 4.2459, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.443366355185496e-05, + "loss": 4.2347, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.442527760434444e-05, + "loss": 4.232, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441690803563766e-05, + "loss": 4.2479, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.440852208812714e-05, + "loss": 4.2558, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440013614061662e-05, + "loss": 4.2374, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.43917501931061e-05, + "loss": 4.2581, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438336424559558e-05, + "loss": 4.2517, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437497829808506e-05, + "loss": 4.2393, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.436659235057454e-05, + "loss": 4.2411, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435820640306402e-05, + "loss": 4.251, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.43498204555535e-05, + "loss": 4.2368, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.4341450886846707e-05, + "loss": 4.239, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.4333064939336186e-05, + "loss": 4.2437, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.4324678991825666e-05, + "loss": 4.2462, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.4316293044315146e-05, + "loss": 4.249, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.4307907096804626e-05, + "loss": 4.244, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.429953752809784e-05, + "loss": 4.2289, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.429115158058732e-05, + "loss": 4.2283, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.42827656330768e-05, + "loss": 4.2383, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.427437968556628e-05, + "loss": 4.2421, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.426601011685949e-05, + "loss": 4.2371, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.42576405481527e-05, + "loss": 4.239, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.424925460064218e-05, + "loss": 4.2317, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.424086865313166e-05, + "loss": 4.2316, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.423248270562114e-05, + "loss": 4.238, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422409675811062e-05, + "loss": 4.2349, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.42157108106001e-05, + "loss": 4.242, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.4207341241893316e-05, + "loss": 4.2395, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.4198971673186525e-05, + "loss": 4.2378, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.4190585725676005e-05, + "loss": 4.2276, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.4182199778165485e-05, + "loss": 4.2359, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.4173813830654965e-05, + "loss": 4.2326, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.4165427883144445e-05, + "loss": 4.2451, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.4157041935633925e-05, + "loss": 4.2284, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.4148655988123405e-05, + "loss": 4.225, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.4140270040612885e-05, + "loss": 4.2402, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.4131884093102365e-05, + "loss": 4.2317, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.4123498145591845e-05, + "loss": 4.2257, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.4115128576885054e-05, + "loss": 4.2291, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.4106742629374534e-05, + "loss": 4.2285, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409835668186402e-05, + "loss": 4.2148, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.40899707343535e-05, + "loss": 4.2209, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.4081584786842974e-05, + "loss": 4.2322, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.4073198839332453e-05, + "loss": 4.2249, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.4064812891821933e-05, + "loss": 4.2245, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.4056426944311413e-05, + "loss": 4.2188, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404805737560462e-05, + "loss": 4.22, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.40396714280941e-05, + "loss": 4.241, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.403128548058358e-05, + "loss": 4.2377, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402291591187679e-05, + "loss": 4.2327, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.401452996436627e-05, + "loss": 4.2278, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400614401685576e-05, + "loss": 4.2234, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399775806934524e-05, + "loss": 4.227, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398937212183472e-05, + "loss": 4.2179, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.39809861743242e-05, + "loss": 4.2238, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.397260022681368e-05, + "loss": 4.2203, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396421427930316e-05, + "loss": 4.2287, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.395584471059637e-05, + "loss": 4.2202, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394745876308585e-05, + "loss": 4.2239, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.3939089194379056e-05, + "loss": 4.2166, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.3930703246868536e-05, + "loss": 4.2196, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.3922317299358016e-05, + "loss": 4.2147, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.3913931351847496e-05, + "loss": 4.2281, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.3905545404336976e-05, + "loss": 4.2347, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.3897159456826456e-05, + "loss": 4.2285, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.3888773509315936e-05, + "loss": 4.2171, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.388038756180542e-05, + "loss": 4.2267, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.387201799309863e-05, + "loss": 4.2184, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.386363204558811e-05, + "loss": 4.235, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.385524609807759e-05, + "loss": 4.2188, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.384686015056707e-05, + "loss": 4.2221, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.383849058186028e-05, + "loss": 4.2165, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.383010463434976e-05, + "loss": 4.2254, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.382171868683924e-05, + "loss": 4.2091, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.381333273932872e-05, + "loss": 4.2151, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.38049467918182e-05, + "loss": 4.2215, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.379657722311141e-05, + "loss": 4.2174, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.3788207654404625e-05, + "loss": 4.222, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.3779821706894105e-05, + "loss": 4.2236, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.3771435759383585e-05, + "loss": 4.2162, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.3763049811873065e-05, + "loss": 4.2163, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.3754663864362545e-05, + "loss": 4.2133, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 4.204583168029785, + "eval_runtime": 288.7537, + "eval_samples_per_second": 1321.51, + "eval_steps_per_second": 41.298, + "step": 381600 + }, + { + "epoch": 0.0, + "learning_rate": 4.3746277916852025e-05, + "loss": 4.2082, + "step": 381952 + }, + { + "epoch": 0.0, + "learning_rate": 4.3737891969341505e-05, + "loss": 4.1981, + "step": 382464 + }, + { + "epoch": 0.0, + "learning_rate": 4.372950602183098e-05, + "loss": 4.2241, + "step": 382976 + }, + { + "epoch": 0.0, + "learning_rate": 4.372112007432046e-05, + "loss": 4.2143, + "step": 383488 + }, + { + "epoch": 0.0, + "learning_rate": 4.371273412680994e-05, + "loss": 4.2228, + "step": 384000 + }, + { + "epoch": 0.0, + "learning_rate": 4.370434817929942e-05, + "loss": 4.2131, + "step": 384512 + }, + { + "epoch": 0.0, + "learning_rate": 4.36959622317889e-05, + "loss": 4.2109, + "step": 385024 + }, + { + "epoch": 0.0, + "learning_rate": 4.368757628427838e-05, + "loss": 4.2024, + "step": 385536 + }, + { + "epoch": 0.0, + "learning_rate": 4.367919033676786e-05, + "loss": 4.2103, + "step": 386048 + }, + { + "epoch": 0.0, + "learning_rate": 4.3670804389257345e-05, + "loss": 4.2076, + "step": 386560 + }, + { + "epoch": 0.0, + "learning_rate": 4.3662418441746825e-05, + "loss": 4.2229, + "step": 387072 + }, + { + "epoch": 0.0, + "learning_rate": 4.3654032494236305e-05, + "loss": 4.2203, + "step": 387584 + }, + { + "epoch": 0.0, + "learning_rate": 4.3645646546725785e-05, + "loss": 4.1926, + "step": 388096 + }, + { + "epoch": 0.0, + "learning_rate": 4.3637260599215265e-05, + "loss": 4.2103, + "step": 388608 + }, + { + "epoch": 0.0, + "learning_rate": 4.3628874651704745e-05, + "loss": 4.2157, + "step": 389120 + }, + { + "epoch": 0.0, + "learning_rate": 4.3620505082997954e-05, + "loss": 4.1984, + "step": 389632 + }, + { + "epoch": 0.0, + "learning_rate": 4.3612119135487434e-05, + "loss": 4.2074, + "step": 390144 + }, + { + "epoch": 0.0, + "learning_rate": 4.3603733187976914e-05, + "loss": 4.21, + "step": 390656 + }, + { + "epoch": 0.0, + "learning_rate": 4.3595347240466394e-05, + "loss": 4.2056, + "step": 391168 + }, + { + "epoch": 0.0, + "learning_rate": 4.358696129295587e-05, + "loss": 4.222, + "step": 391680 + }, + { + "epoch": 0.0, + "learning_rate": 4.357857534544535e-05, + "loss": 4.2075, + "step": 392192 + }, + { + "epoch": 0.0, + "learning_rate": 4.357018939793483e-05, + "loss": 4.2133, + "step": 392704 + }, + { + "epoch": 0.0, + "learning_rate": 4.356180345042431e-05, + "loss": 4.2061, + "step": 393216 + }, + { + "epoch": 0.0, + "learning_rate": 4.355341750291379e-05, + "loss": 4.2169, + "step": 393728 + }, + { + "epoch": 0.0, + "learning_rate": 4.354503155540327e-05, + "loss": 4.201, + "step": 394240 + }, + { + "epoch": 0.0, + "learning_rate": 4.353664560789275e-05, + "loss": 4.2089, + "step": 394752 + }, + { + "epoch": 0.0, + "learning_rate": 4.352825966038223e-05, + "loss": 4.1994, + "step": 395264 + }, + { + "epoch": 0.0, + "learning_rate": 4.351990647047917e-05, + "loss": 4.1997, + "step": 395776 + }, + { + "epoch": 0.0, + "learning_rate": 4.351152052296865e-05, + "loss": 4.1993, + "step": 396288 + }, + { + "epoch": 0.0, + "learning_rate": 4.350313457545813e-05, + "loss": 4.203, + "step": 396800 + }, + { + "epoch": 0.01, + "learning_rate": 4.349474862794761e-05, + "loss": 4.2021, + "step": 397312 + }, + { + "epoch": 0.01, + "learning_rate": 4.348637905924082e-05, + "loss": 4.2092, + "step": 397824 + }, + { + "epoch": 0.01, + "learning_rate": 4.34779931117303e-05, + "loss": 4.2115, + "step": 398336 + }, + { + "epoch": 0.01, + "learning_rate": 4.346960716421978e-05, + "loss": 4.2109, + "step": 398848 + }, + { + "epoch": 0.01, + "learning_rate": 4.346122121670926e-05, + "loss": 4.2018, + "step": 399360 + }, + { + "epoch": 0.01, + "learning_rate": 4.345283526919875e-05, + "loss": 4.2054, + "step": 399872 + }, + { + "epoch": 0.01, + "learning_rate": 4.344444932168823e-05, + "loss": 4.2002, + "step": 400384 + }, + { + "epoch": 0.01, + "learning_rate": 4.343606337417771e-05, + "loss": 4.2014, + "step": 400896 + }, + { + "epoch": 0.01, + "learning_rate": 4.342767742666719e-05, + "loss": 4.1894, + "step": 401408 + }, + { + "epoch": 0.01, + "learning_rate": 4.341929147915667e-05, + "loss": 4.1969, + "step": 401920 + }, + { + "epoch": 0.01, + "learning_rate": 4.3410921910449876e-05, + "loss": 4.1983, + "step": 402432 + }, + { + "epoch": 0.01, + "learning_rate": 4.3402535962939356e-05, + "loss": 4.2034, + "step": 402944 + }, + { + "epoch": 0.01, + "learning_rate": 4.3394150015428836e-05, + "loss": 4.1908, + "step": 403456 + }, + { + "epoch": 0.01, + "learning_rate": 4.3385764067918316e-05, + "loss": 4.198, + "step": 403968 + }, + { + "epoch": 0.01, + "learning_rate": 4.3377378120407796e-05, + "loss": 4.2131, + "step": 404480 + }, + { + "epoch": 0.01, + "learning_rate": 4.3368992172897276e-05, + "loss": 4.2005, + "step": 404992 + }, + { + "epoch": 0.01, + "learning_rate": 4.3360606225386756e-05, + "loss": 4.2054, + "step": 405504 + }, + { + "epoch": 0.01, + "learning_rate": 4.3352236656679965e-05, + "loss": 4.1936, + "step": 406016 + }, + { + "epoch": 0.01, + "learning_rate": 4.3343850709169445e-05, + "loss": 4.1801, + "step": 406528 + }, + { + "epoch": 0.01, + "learning_rate": 4.333546476165893e-05, + "loss": 4.2018, + "step": 407040 + }, + { + "epoch": 0.01, + "learning_rate": 4.332707881414841e-05, + "loss": 4.1985, + "step": 407552 + }, + { + "epoch": 0.01, + "learning_rate": 4.331870924544162e-05, + "loss": 4.191, + "step": 408064 + }, + { + "epoch": 0.01, + "learning_rate": 4.33103232979311e-05, + "loss": 4.1923, + "step": 408576 + }, + { + "epoch": 0.01, + "learning_rate": 4.330193735042058e-05, + "loss": 4.2013, + "step": 409088 + }, + { + "epoch": 0.01, + "learning_rate": 4.3293551402910054e-05, + "loss": 4.1758, + "step": 409600 + }, + { + "epoch": 0.01, + "learning_rate": 4.3285165455399534e-05, + "loss": 4.202, + "step": 410112 + }, + { + "epoch": 0.01, + "learning_rate": 4.3276779507889013e-05, + "loss": 4.1802, + "step": 410624 + }, + { + "epoch": 0.01, + "learning_rate": 4.3268393560378493e-05, + "loss": 4.1882, + "step": 411136 + }, + { + "epoch": 0.01, + "learning_rate": 4.3260007612867973e-05, + "loss": 4.1991, + "step": 411648 + }, + { + "epoch": 0.01, + "learning_rate": 4.325163804416118e-05, + "loss": 4.1896, + "step": 412160 + }, + { + "epoch": 0.01, + "learning_rate": 4.32432684754544e-05, + "loss": 4.1878, + "step": 412672 + }, + { + "epoch": 0.01, + "learning_rate": 4.3234882527943885e-05, + "loss": 4.1946, + "step": 413184 + }, + { + "epoch": 0.01, + "learning_rate": 4.322649658043336e-05, + "loss": 4.1792, + "step": 413696 + }, + { + "epoch": 0.01, + "learning_rate": 4.321811063292284e-05, + "loss": 4.1824, + "step": 414208 + }, + { + "epoch": 0.01, + "learning_rate": 4.3209741064216054e-05, + "loss": 4.1923, + "step": 414720 + }, + { + "epoch": 0.01, + "learning_rate": 4.320135511670553e-05, + "loss": 4.1875, + "step": 415232 + }, + { + "epoch": 0.01, + "learning_rate": 4.319296916919501e-05, + "loss": 4.1864, + "step": 415744 + }, + { + "epoch": 0.01, + "learning_rate": 4.318458322168449e-05, + "loss": 4.18, + "step": 416256 + }, + { + "epoch": 0.01, + "learning_rate": 4.317619727417397e-05, + "loss": 4.1765, + "step": 416768 + }, + { + "epoch": 0.01, + "learning_rate": 4.3167827705467176e-05, + "loss": 4.1874, + "step": 417280 + }, + { + "epoch": 0.01, + "learning_rate": 4.3159441757956656e-05, + "loss": 4.1984, + "step": 417792 + }, + { + "epoch": 0.01, + "learning_rate": 4.3151055810446136e-05, + "loss": 4.1836, + "step": 418304 + }, + { + "epoch": 0.01, + "learning_rate": 4.314266986293562e-05, + "loss": 4.2006, + "step": 418816 + }, + { + "epoch": 0.01, + "learning_rate": 4.31342839154251e-05, + "loss": 4.1977, + "step": 419328 + }, + { + "epoch": 0.01, + "learning_rate": 4.312589796791458e-05, + "loss": 4.1888, + "step": 419840 + }, + { + "epoch": 0.01, + "learning_rate": 4.311751202040406e-05, + "loss": 4.1811, + "step": 420352 + }, + { + "epoch": 0.01, + "learning_rate": 4.310912607289354e-05, + "loss": 4.1962, + "step": 420864 + }, + { + "epoch": 0.01, + "learning_rate": 4.310074012538302e-05, + "loss": 4.1847, + "step": 421376 + }, + { + "epoch": 0.01, + "learning_rate": 4.309237055667623e-05, + "loss": 4.18, + "step": 421888 + }, + { + "epoch": 0.01, + "learning_rate": 4.308398460916571e-05, + "loss": 4.1924, + "step": 422400 + }, + { + "epoch": 0.01, + "learning_rate": 4.307561504045892e-05, + "loss": 4.1901, + "step": 422912 + }, + { + "epoch": 0.01, + "learning_rate": 4.30672290929484e-05, + "loss": 4.1948, + "step": 423424 + }, + { + "epoch": 0.01, + "learning_rate": 4.305884314543788e-05, + "loss": 4.1898, + "step": 423936 + }, + { + "epoch": 0.01, + "learning_rate": 4.305047357673109e-05, + "loss": 4.1756, + "step": 424448 + }, + { + "epoch": 0.01, + "learning_rate": 4.3042087629220577e-05, + "loss": 4.1705, + "step": 424960 + }, + { + "epoch": 0.01, + "learning_rate": 4.3033701681710057e-05, + "loss": 4.1835, + "step": 425472 + }, + { + "epoch": 0.01, + "learning_rate": 4.3025315734199536e-05, + "loss": 4.1883, + "step": 425984 + }, + { + "epoch": 0.01, + "learning_rate": 4.3016929786689016e-05, + "loss": 4.1818, + "step": 426496 + }, + { + "epoch": 0.01, + "learning_rate": 4.3008560217982226e-05, + "loss": 4.1822, + "step": 427008 + }, + { + "epoch": 0.02, + "learning_rate": 4.3000174270471705e-05, + "loss": 4.1802, + "step": 427520 + }, + { + "epoch": 0.02, + "learning_rate": 4.2991804701764915e-05, + "loss": 4.1745, + "step": 428032 + }, + { + "epoch": 0.02, + "learning_rate": 4.2983418754254395e-05, + "loss": 4.1861, + "step": 428544 + }, + { + "epoch": 0.02, + "learning_rate": 4.2975032806743874e-05, + "loss": 4.1769, + "step": 429056 + }, + { + "epoch": 0.02, + "learning_rate": 4.2966646859233354e-05, + "loss": 4.1885, + "step": 429568 + }, + { + "epoch": 0.02, + "learning_rate": 4.2958260911722834e-05, + "loss": 4.1906, + "step": 430080 + }, + { + "epoch": 0.02, + "learning_rate": 4.2949891343016043e-05, + "loss": 4.1844, + "step": 430592 + }, + { + "epoch": 0.02, + "learning_rate": 4.294150539550553e-05, + "loss": 4.1743, + "step": 431104 + }, + { + "epoch": 0.02, + "learning_rate": 4.293311944799501e-05, + "loss": 4.1778, + "step": 431616 + }, + { + "epoch": 0.02, + "learning_rate": 4.292473350048449e-05, + "loss": 4.1796, + "step": 432128 + }, + { + "epoch": 0.02, + "learning_rate": 4.291634755297397e-05, + "loss": 4.1936, + "step": 432640 + }, + { + "epoch": 0.02, + "learning_rate": 4.290796160546345e-05, + "loss": 4.1741, + "step": 433152 + }, + { + "epoch": 0.02, + "learning_rate": 4.289957565795293e-05, + "loss": 4.175, + "step": 433664 + }, + { + "epoch": 0.02, + "learning_rate": 4.289118971044241e-05, + "loss": 4.1859, + "step": 434176 + }, + { + "epoch": 0.02, + "learning_rate": 4.288280376293189e-05, + "loss": 4.1775, + "step": 434688 + }, + { + "epoch": 0.02, + "learning_rate": 4.287441781542136e-05, + "loss": 4.1748, + "step": 435200 + }, + { + "epoch": 0.02, + "learning_rate": 4.286603186791084e-05, + "loss": 4.176, + "step": 435712 + }, + { + "epoch": 0.02, + "learning_rate": 4.285764592040032e-05, + "loss": 4.1742, + "step": 436224 + }, + { + "epoch": 0.02, + "learning_rate": 4.284927635169354e-05, + "loss": 4.1692, + "step": 436736 + }, + { + "epoch": 0.02, + "learning_rate": 4.284089040418301e-05, + "loss": 4.1631, + "step": 437248 + }, + { + "epoch": 0.02, + "learning_rate": 4.283250445667249e-05, + "loss": 4.1796, + "step": 437760 + }, + { + "epoch": 0.02, + "learning_rate": 4.282411850916198e-05, + "loss": 4.1767, + "step": 438272 + }, + { + "epoch": 0.02, + "learning_rate": 4.281573256165146e-05, + "loss": 4.1714, + "step": 438784 + }, + { + "epoch": 0.02, + "learning_rate": 4.280734661414094e-05, + "loss": 4.169, + "step": 439296 + }, + { + "epoch": 0.02, + "learning_rate": 4.279897704543415e-05, + "loss": 4.1642, + "step": 439808 + }, + { + "epoch": 0.02, + "learning_rate": 4.279059109792363e-05, + "loss": 4.1894, + "step": 440320 + }, + { + "epoch": 0.02, + "learning_rate": 4.278220515041311e-05, + "loss": 4.1858, + "step": 440832 + }, + { + "epoch": 0.02, + "learning_rate": 4.277381920290259e-05, + "loss": 4.1829, + "step": 441344 + }, + { + "epoch": 0.02, + "learning_rate": 4.276543325539207e-05, + "loss": 4.1777, + "step": 441856 + }, + { + "epoch": 0.02, + "learning_rate": 4.275704730788155e-05, + "loss": 4.1707, + "step": 442368 + }, + { + "epoch": 0.02, + "learning_rate": 4.274866136037103e-05, + "loss": 4.1756, + "step": 442880 + }, + { + "epoch": 0.02, + "learning_rate": 4.274027541286051e-05, + "loss": 4.167, + "step": 443392 + }, + { + "epoch": 0.02, + "learning_rate": 4.2731905844153717e-05, + "loss": 4.173, + "step": 443904 + }, + { + "epoch": 0.02, + "learning_rate": 4.2723519896643196e-05, + "loss": 4.1728, + "step": 444416 + }, + { + "epoch": 0.02, + "learning_rate": 4.2715133949132676e-05, + "loss": 4.1737, + "step": 444928 + }, + { + "epoch": 0.02, + "learning_rate": 4.270674800162216e-05, + "loss": 4.1756, + "step": 445440 + }, + { + "epoch": 0.02, + "learning_rate": 4.269836205411164e-05, + "loss": 4.1688, + "step": 445952 + }, + { + "epoch": 0.02, + "learning_rate": 4.268997610660112e-05, + "loss": 4.1681, + "step": 446464 + }, + { + "epoch": 0.02, + "learning_rate": 4.26815901590906e-05, + "loss": 4.1706, + "step": 446976 + }, + { + "epoch": 0.02, + "learning_rate": 4.2673204211580076e-05, + "loss": 4.1654, + "step": 447488 + }, + { + "epoch": 0.02, + "learning_rate": 4.266483464287329e-05, + "loss": 4.1714, + "step": 448000 + }, + { + "epoch": 0.02, + "learning_rate": 4.26564650741665e-05, + "loss": 4.182, + "step": 448512 + }, + { + "epoch": 0.02, + "learning_rate": 4.264807912665598e-05, + "loss": 4.1828, + "step": 449024 + }, + { + "epoch": 0.02, + "learning_rate": 4.263969317914546e-05, + "loss": 4.1647, + "step": 449536 + }, + { + "epoch": 0.02, + "learning_rate": 4.263130723163494e-05, + "loss": 4.1779, + "step": 450048 + }, + { + "epoch": 0.02, + "learning_rate": 4.262292128412442e-05, + "loss": 4.1706, + "step": 450560 + }, + { + "epoch": 0.02, + "learning_rate": 4.26145353366139e-05, + "loss": 4.1803, + "step": 451072 + }, + { + "epoch": 0.02, + "learning_rate": 4.260614938910338e-05, + "loss": 4.1719, + "step": 451584 + }, + { + "epoch": 0.02, + "learning_rate": 4.25977798203966e-05, + "loss": 4.1767, + "step": 452096 + }, + { + "epoch": 0.02, + "learning_rate": 4.258939387288608e-05, + "loss": 4.1656, + "step": 452608 + }, + { + "epoch": 0.02, + "learning_rate": 4.258100792537555e-05, + "loss": 4.1737, + "step": 453120 + }, + { + "epoch": 0.02, + "learning_rate": 4.257262197786503e-05, + "loss": 4.1613, + "step": 453632 + }, + { + "epoch": 0.02, + "learning_rate": 4.2564252409158246e-05, + "loss": 4.167, + "step": 454144 + }, + { + "epoch": 0.02, + "learning_rate": 4.2555866461647726e-05, + "loss": 4.1689, + "step": 454656 + }, + { + "epoch": 0.02, + "learning_rate": 4.25474805141372e-05, + "loss": 4.1723, + "step": 455168 + }, + { + "epoch": 0.02, + "learning_rate": 4.253909456662668e-05, + "loss": 4.1712, + "step": 455680 + }, + { + "epoch": 0.02, + "learning_rate": 4.253070861911616e-05, + "loss": 4.1683, + "step": 456192 + }, + { + "epoch": 0.02, + "learning_rate": 4.2522339050409375e-05, + "loss": 4.1764, + "step": 456704 + }, + { + "epoch": 0.02, + "learning_rate": 4.2513953102898855e-05, + "loss": 4.1633, + "step": 457216 + }, + { + "epoch": 0.02, + "learning_rate": 4.250558353419207e-05, + "loss": 4.167, + "step": 457728 + }, + { + "epoch": 0.03, + "eval_loss": 4.163780689239502, + "eval_runtime": 291.3236, + "eval_samples_per_second": 1309.853, + "eval_steps_per_second": 40.934, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.249719758668155e-05, + "loss": 4.1611, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.2488811639171024e-05, + "loss": 4.1494, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.2480425691660504e-05, + "loss": 4.1747, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.2472039744149984e-05, + "loss": 4.165, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.2463653796639464e-05, + "loss": 4.1734, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.2455267849128943e-05, + "loss": 4.1627, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.2446881901618423e-05, + "loss": 4.1585, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.24384959541079e-05, + "loss": 4.1582, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.243011000659738e-05, + "loss": 4.1615, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.242172405908686e-05, + "loss": 4.1584, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.241333811157634e-05, + "loss": 4.1737, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.240495216406582e-05, + "loss": 4.1742, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.23965662165553e-05, + "loss": 4.1493, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.238818026904478e-05, + "loss": 4.1587, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.237979432153426e-05, + "loss": 4.169, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.237140837402374e-05, + "loss": 4.1524, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.236302242651322e-05, + "loss": 4.159, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.23546364790027e-05, + "loss": 4.1604, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.234625053149218e-05, + "loss": 4.1599, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233786458398166e-05, + "loss": 4.1735, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.232949501527487e-05, + "loss": 4.163, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232112544656809e-05, + "loss": 4.1637, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.231273949905756e-05, + "loss": 4.1565, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.230435355154704e-05, + "loss": 4.1668, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.229596760403652e-05, + "loss": 4.1581, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.2287581656526e-05, + "loss": 4.1617, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.227919570901549e-05, + "loss": 4.1481, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.227080976150497e-05, + "loss": 4.1511, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.226242381399445e-05, + "loss": 4.1551, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.2254054245287657e-05, + "loss": 4.156, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.2245684676580866e-05, + "loss": 4.1562, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.2237298729070346e-05, + "loss": 4.1613, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.2228912781559826e-05, + "loss": 4.1633, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.2220526834049306e-05, + "loss": 4.1661, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.2212157265342515e-05, + "loss": 4.1552, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.2203771317831995e-05, + "loss": 4.1584, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.219540174912521e-05, + "loss": 4.1582, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.218701580161469e-05, + "loss": 4.1516, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.217862985410417e-05, + "loss": 4.1417, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.217024390659365e-05, + "loss": 4.1499, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.216185795908313e-05, + "loss": 4.1525, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.215347201157261e-05, + "loss": 4.1581, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.214508606406209e-05, + "loss": 4.145, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.213670011655157e-05, + "loss": 4.1518, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.212831416904105e-05, + "loss": 4.1713, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.211992822153053e-05, + "loss": 4.1544, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.211155865282374e-05, + "loss": 4.1602, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.210317270531322e-05, + "loss": 4.1443, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209480313660643e-05, + "loss": 4.1347, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208641718909591e-05, + "loss": 4.1614, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.2078031241585395e-05, + "loss": 4.1469, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.2069645294074875e-05, + "loss": 4.1473, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.2061259346564355e-05, + "loss": 4.1482, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.2052873399053835e-05, + "loss": 4.1534, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.2044487451543315e-05, + "loss": 4.1329, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.2036117882836524e-05, + "loss": 4.1515, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.2027731935326004e-05, + "loss": 4.1397, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.2019345987815484e-05, + "loss": 4.1373, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.2010960040304964e-05, + "loss": 4.1586, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.2002574092794444e-05, + "loss": 4.1436, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.199420452408765e-05, + "loss": 4.1413, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.198581857657713e-05, + "loss": 4.1529, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.197743262906661e-05, + "loss": 4.1349, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.196904668155609e-05, + "loss": 4.141, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.196066073404557e-05, + "loss": 4.1424, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195227478653505e-05, + "loss": 4.1415, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.194388883902453e-05, + "loss": 4.1459, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.193550289151401e-05, + "loss": 4.1396, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.192711694400349e-05, + "loss": 4.1264, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.191873099649297e-05, + "loss": 4.1411, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.191034504898245e-05, + "loss": 4.1552, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.190197548027566e-05, + "loss": 4.1402, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.189358953276514e-05, + "loss": 4.1595, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.188520358525462e-05, + "loss": 4.1538, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.18768176377441e-05, + "loss": 4.1493, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.186844806903731e-05, + "loss": 4.1335, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.18600621215268e-05, + "loss": 4.153, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.185167617401628e-05, + "loss": 4.143, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.184329022650576e-05, + "loss": 4.1343, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.1834920657798966e-05, + "loss": 4.1507, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.1826534710288446e-05, + "loss": 4.1461, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.1818148762777926e-05, + "loss": 4.1509, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.1809762815267406e-05, + "loss": 4.1466, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.1801376867756886e-05, + "loss": 4.1295, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.1792990920246366e-05, + "loss": 4.1279, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.1784604972735846e-05, + "loss": 4.135, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.1776219025225326e-05, + "loss": 4.1458, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.1767849456518535e-05, + "loss": 4.1404, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.175949626661548e-05, + "loss": 4.1356, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.175111031910496e-05, + "loss": 4.1393, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.174272437159444e-05, + "loss": 4.1329, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.173433842408392e-05, + "loss": 4.1392, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.17259524765734e-05, + "loss": 4.1324, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.171756652906288e-05, + "loss": 4.1508, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170918058155236e-05, + "loss": 4.1475, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.170079463404184e-05, + "loss": 4.139, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.169240868653132e-05, + "loss": 4.1347, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.16840227390208e-05, + "loss": 4.138, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.167563679151028e-05, + "loss": 4.1323, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.166725084399975e-05, + "loss": 4.1534, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.165886489648923e-05, + "loss": 4.1335, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.1650511706586184e-05, + "loss": 4.1343, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.1642142137879393e-05, + "loss": 4.1386, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.1633756190368873e-05, + "loss": 4.1402, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.1625370242858353e-05, + "loss": 4.1279, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.161698429534783e-05, + "loss": 4.1364, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.160859834783731e-05, + "loss": 4.1305, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160021240032679e-05, + "loss": 4.1239, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.159182645281627e-05, + "loss": 4.1241, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.158344050530575e-05, + "loss": 4.1375, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.1575054557795226e-05, + "loss": 4.1369, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.156668498908844e-05, + "loss": 4.1264, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155829904157792e-05, + "loss": 4.1275, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.15499130940674e-05, + "loss": 4.1251, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154152714655688e-05, + "loss": 4.1437, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153314119904636e-05, + "loss": 4.1473, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152475525153584e-05, + "loss": 4.1429, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151636930402532e-05, + "loss": 4.1355, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.150799973531853e-05, + "loss": 4.1276, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.149961378780801e-05, + "loss": 4.1356, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.149122784029749e-05, + "loss": 4.1215, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.148284189278697e-05, + "loss": 4.132, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.147445594527645e-05, + "loss": 4.132, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.146606999776593e-05, + "loss": 4.1296, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.145768405025541e-05, + "loss": 4.1341, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.144929810274489e-05, + "loss": 4.1305, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.1440944912841836e-05, + "loss": 4.1331, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.1432558965331316e-05, + "loss": 4.1289, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.1424173017820796e-05, + "loss": 4.1267, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.1415787070310276e-05, + "loss": 4.1323, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.1407401122799756e-05, + "loss": 4.1376, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.1399015175289236e-05, + "loss": 4.1443, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.1390645606582445e-05, + "loss": 4.1241, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.1382259659071925e-05, + "loss": 4.1394, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.1373873711561405e-05, + "loss": 4.1322, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.1365487764050885e-05, + "loss": 4.141, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.1357101816540364e-05, + "loss": 4.132, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.134873224783358e-05, + "loss": 4.136, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.134034630032306e-05, + "loss": 4.1237, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.133196035281254e-05, + "loss": 4.1365, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.132357440530202e-05, + "loss": 4.12, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.13151884577915e-05, + "loss": 4.1274, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.130680251028098e-05, + "loss": 4.129, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.129841656277046e-05, + "loss": 4.1316, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.129003061525994e-05, + "loss": 4.1292, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128166104655315e-05, + "loss": 4.1305, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.127329147784636e-05, + "loss": 4.136, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.126490553033584e-05, + "loss": 4.1241, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125651958282532e-05, + "loss": 4.1327, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 4.1322855949401855, + "eval_runtime": 307.3004, + "eval_samples_per_second": 1241.753, + "eval_steps_per_second": 38.806, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.12481336353148e-05, + "loss": 4.1239, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.123974768780428e-05, + "loss": 4.1129, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.123136174029376e-05, + "loss": 4.1325, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.1222992171586974e-05, + "loss": 4.1275, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.1214606224076454e-05, + "loss": 4.1316, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.1206220276565934e-05, + "loss": 4.1254, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.1197834329055414e-05, + "loss": 4.122, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.118944838154489e-05, + "loss": 4.1204, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.118106243403437e-05, + "loss": 4.1236, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.117267648652385e-05, + "loss": 4.1188, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.116429053901333e-05, + "loss": 4.1346, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.1155920970306536e-05, + "loss": 4.1316, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.114755140159975e-05, + "loss": 4.1182, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.113916545408923e-05, + "loss": 4.1171, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.113077950657871e-05, + "loss": 4.1293, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.112239355906819e-05, + "loss": 4.1098, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.111400761155767e-05, + "loss": 4.1243, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.110562166404715e-05, + "loss": 4.1209, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.109723571653663e-05, + "loss": 4.1234, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.108884976902611e-05, + "loss": 4.1332, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.108048020031932e-05, + "loss": 4.1287, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.10720942528088e-05, + "loss": 4.1252, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.106370830529828e-05, + "loss": 4.119, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.105532235778776e-05, + "loss": 4.1254, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.104695278908097e-05, + "loss": 4.1198, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.103856684157045e-05, + "loss": 4.1242, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.1030180894059936e-05, + "loss": 4.1158, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.1021794946549416e-05, + "loss": 4.1119, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.1013408999038896e-05, + "loss": 4.1155, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.1005023051528376e-05, + "loss": 4.1234, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.0996653482821585e-05, + "loss": 4.1142, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.0988267535311065e-05, + "loss": 4.1258, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.0979881587800545e-05, + "loss": 4.1298, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.0971512019093754e-05, + "loss": 4.1255, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.0963126071583234e-05, + "loss": 4.1127, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.0954740124072714e-05, + "loss": 4.1221, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.0946354176562194e-05, + "loss": 4.1227, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.0937968229051674e-05, + "loss": 4.1125, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.0929582281541154e-05, + "loss": 4.1066, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.0921196334030634e-05, + "loss": 4.1094, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.091281038652012e-05, + "loss": 4.1165, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.090444081781333e-05, + "loss": 4.1218, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.089607124910654e-05, + "loss": 4.1073, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.088768530159602e-05, + "loss": 4.1147, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.08792993540855e-05, + "loss": 4.1326, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.087091340657498e-05, + "loss": 4.1158, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.086252745906446e-05, + "loss": 4.1241, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.085414151155394e-05, + "loss": 4.1089, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.084575556404342e-05, + "loss": 4.0974, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.08373696165329e-05, + "loss": 4.127, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.0829016426629844e-05, + "loss": 4.1101, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.0820630479119323e-05, + "loss": 4.1111, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.081226091041253e-05, + "loss": 4.1179, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.080387496290201e-05, + "loss": 4.1104, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.079548901539149e-05, + "loss": 4.1058, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.078710306788097e-05, + "loss": 4.1078, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.077871712037045e-05, + "loss": 4.1031, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.077033117285993e-05, + "loss": 4.1063, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.076194522534941e-05, + "loss": 4.1175, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.075355927783889e-05, + "loss": 4.1088, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.074517333032837e-05, + "loss": 4.1059, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.0736787382817845e-05, + "loss": 4.1188, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.072841781411106e-05, + "loss": 4.0959, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.072003186660054e-05, + "loss": 4.1061, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.071164591909002e-05, + "loss": 4.1048, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.07032599715795e-05, + "loss": 4.1097, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.069487402406898e-05, + "loss": 4.1042, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.068648807655846e-05, + "loss": 4.1079, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.067810212904794e-05, + "loss": 4.087, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.066971618153742e-05, + "loss": 4.1066, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.066134661283063e-05, + "loss": 4.1209, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.065296066532011e-05, + "loss": 4.1016, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.064459109661332e-05, + "loss": 4.1234, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.06362051491028e-05, + "loss": 4.1149, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.062781920159228e-05, + "loss": 4.1171, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.0619433254081766e-05, + "loss": 4.0982, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.0611047306571246e-05, + "loss": 4.1161, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.0602661359060726e-05, + "loss": 4.1085, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.0594291790353935e-05, + "loss": 4.1006, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.0585905842843415e-05, + "loss": 4.1161, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.0577519895332895e-05, + "loss": 4.1097, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.0569133947822375e-05, + "loss": 4.1151, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.0560764379115584e-05, + "loss": 4.1143, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.055239481040879e-05, + "loss": 4.0898, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.054400886289827e-05, + "loss": 4.1004, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.053562291538775e-05, + "loss": 4.0966, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.052723696787723e-05, + "loss": 4.1127, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.051885102036671e-05, + "loss": 4.107, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.051048145165993e-05, + "loss": 4.1024, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.050209550414941e-05, + "loss": 4.103, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.049370955663889e-05, + "loss": 4.1002, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.04853399879321e-05, + "loss": 4.1039, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.047695404042158e-05, + "loss": 4.099, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.046856809291106e-05, + "loss": 4.1158, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.046018214540054e-05, + "loss": 4.1193, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.045179619789002e-05, + "loss": 4.0988, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.04434102503795e-05, + "loss": 4.1001, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.043502430286898e-05, + "loss": 4.103, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.042663835535846e-05, + "loss": 4.0987, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.041825240784794e-05, + "loss": 4.1186, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.040986646033742e-05, + "loss": 4.1021, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.04014805128269e-05, + "loss": 4.1021, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.0393094565316384e-05, + "loss": 4.1069, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.038470861780586e-05, + "loss": 4.1084, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.037632267029534e-05, + "loss": 4.0919, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.036793672278482e-05, + "loss": 4.1012, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.03595507752743e-05, + "loss": 4.0977, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.0351181206567506e-05, + "loss": 4.0884, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.0342795259056986e-05, + "loss": 4.0941, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.0334409311546466e-05, + "loss": 4.1023, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.0326023364035946e-05, + "loss": 4.1014, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.031767017413289e-05, + "loss": 4.0938, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.030928422662237e-05, + "loss": 4.0959, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.030089827911185e-05, + "loss": 4.0927, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.029251233160133e-05, + "loss": 4.112, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.028412638409081e-05, + "loss": 4.1136, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.0275756815384027e-05, + "loss": 4.1094, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.0267370867873506e-05, + "loss": 4.102, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.025898492036298e-05, + "loss": 4.0915, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.025059897285246e-05, + "loss": 4.1038, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.024221302534194e-05, + "loss": 4.0896, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.0233843456635155e-05, + "loss": 4.1011, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.022545750912463e-05, + "loss": 4.0925, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.021707156161411e-05, + "loss": 4.0972, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.020868561410359e-05, + "loss": 4.0986, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.0200299666593075e-05, + "loss": 4.0976, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.0191930097886284e-05, + "loss": 4.1003, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.0183544150375764e-05, + "loss": 4.0968, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.0175158202865244e-05, + "loss": 4.0922, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.0166772255354724e-05, + "loss": 4.0998, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.0158386307844204e-05, + "loss": 4.1031, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.0150000360333684e-05, + "loss": 4.1108, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.014163079162689e-05, + "loss": 4.092, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.013324484411637e-05, + "loss": 4.1061, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.012485889660585e-05, + "loss": 4.1011, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.011647294909533e-05, + "loss": 4.1051, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.010808700158481e-05, + "loss": 4.1006, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.009970105407429e-05, + "loss": 4.1013, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.009131510656377e-05, + "loss": 4.0928, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.008292915905325e-05, + "loss": 4.1065, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.007454321154274e-05, + "loss": 4.086, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.006617364283595e-05, + "loss": 4.0949, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.005778769532543e-05, + "loss": 4.1015, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.004940174781491e-05, + "loss": 4.1001, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.004101580030439e-05, + "loss": 4.0941, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.00326462315976e-05, + "loss": 4.0942, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.002427666289081e-05, + "loss": 4.1069, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.001589071538029e-05, + "loss": 4.0911, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.000750476786977e-05, + "loss": 4.1009, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 4.1073384284973145, + "eval_runtime": 307.1526, + "eval_samples_per_second": 1242.35, + "eval_steps_per_second": 38.824, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.999911882035925e-05, + "loss": 4.0802, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.999073287284873e-05, + "loss": 4.0868, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.9982346925338207e-05, + "loss": 4.0956, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.997396097782769e-05, + "loss": 4.0936, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.9965575030317167e-05, + "loss": 4.103, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.9957189082806646e-05, + "loss": 4.0899, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.9948803135296126e-05, + "loss": 4.0937, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.9940417187785606e-05, + "loss": 4.0906, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.9932031240275086e-05, + "loss": 4.0886, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.9923645292764566e-05, + "loss": 4.0869, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.9915259345254046e-05, + "loss": 4.1013, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.9906873397743526e-05, + "loss": 4.1011, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.9898503829036735e-05, + "loss": 4.0845, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.9890117881526215e-05, + "loss": 4.0849, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.9881731934015695e-05, + "loss": 4.098, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.9873345986505175e-05, + "loss": 4.078, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.986496003899466e-05, + "loss": 4.0934, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.985657409148414e-05, + "loss": 4.0876, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.984818814397362e-05, + "loss": 4.0931, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.98398021964631e-05, + "loss": 4.0957, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.983141624895258e-05, + "loss": 4.1003, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.982304668024579e-05, + "loss": 4.0941, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.981466073273527e-05, + "loss": 4.0874, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.980627478522475e-05, + "loss": 4.0909, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.979788883771423e-05, + "loss": 4.0931, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.9789502890203704e-05, + "loss": 4.0911, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.9781116942693184e-05, + "loss": 4.0853, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.9772730995182664e-05, + "loss": 4.0809, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.9764345047672144e-05, + "loss": 4.0891, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.975597547896536e-05, + "loss": 4.0888, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.974758953145484e-05, + "loss": 4.083, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.973920358394432e-05, + "loss": 4.0987, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.97308176364338e-05, + "loss": 4.0952, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.9722464446530744e-05, + "loss": 4.0928, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.9714078499020224e-05, + "loss": 4.0855, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.9705692551509704e-05, + "loss": 4.0969, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.969730660399918e-05, + "loss": 4.0901, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.968892065648866e-05, + "loss": 4.0839, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.968053470897814e-05, + "loss": 4.0736, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967214876146762e-05, + "loss": 4.0786, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.96637628139571e-05, + "loss": 4.0818, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.9655376866446584e-05, + "loss": 4.0945, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964700729773979e-05, + "loss": 4.0786, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.963862135022927e-05, + "loss": 4.0825, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.963023540271875e-05, + "loss": 4.0984, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.962184945520823e-05, + "loss": 4.0836, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.961349626530518e-05, + "loss": 4.0956, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.960511031779465e-05, + "loss": 4.0793, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.959672437028413e-05, + "loss": 4.0615, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958833842277361e-05, + "loss": 4.0982, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.957996885406682e-05, + "loss": 4.0818, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.957158290655631e-05, + "loss": 4.0831, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.956319695904579e-05, + "loss": 4.0825, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.955481101153527e-05, + "loss": 4.0821, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.954642506402475e-05, + "loss": 4.0743, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.9538055495317956e-05, + "loss": 4.0752, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.9529669547807436e-05, + "loss": 4.0743, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.9521283600296916e-05, + "loss": 4.075, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.9512897652786396e-05, + "loss": 4.0917, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.9504511705275876e-05, + "loss": 4.0785, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.9496142136569085e-05, + "loss": 4.0748, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.9487756189058565e-05, + "loss": 4.0954, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.9479370241548045e-05, + "loss": 4.0638, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.9470984294037525e-05, + "loss": 4.0722, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.9462598346527005e-05, + "loss": 4.0772, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.9454212399016485e-05, + "loss": 4.0802, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.944582645150597e-05, + "loss": 4.0735, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.943745688279918e-05, + "loss": 4.0817, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.942907093528866e-05, + "loss": 4.0587, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.942070136658187e-05, + "loss": 4.0737, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.941231541907135e-05, + "loss": 4.0909, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.940392947156083e-05, + "loss": 4.0722, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.939554352405031e-05, + "loss": 4.0931, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.938715757653979e-05, + "loss": 4.0874, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.937877162902927e-05, + "loss": 4.0905, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.937038568151875e-05, + "loss": 4.0672, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.936199973400823e-05, + "loss": 4.0851, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.935361378649771e-05, + "loss": 4.0837, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.934522783898719e-05, + "loss": 4.0686, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.9336858270280405e-05, + "loss": 4.0877, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.9328472322769885e-05, + "loss": 4.0799, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.9320086375259365e-05, + "loss": 4.0837, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.931170042774884e-05, + "loss": 4.0851, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.930331448023832e-05, + "loss": 4.0648, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.9294944911531534e-05, + "loss": 4.0685, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.928655896402101e-05, + "loss": 4.0713, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.927817301651049e-05, + "loss": 4.0798, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.926978706899997e-05, + "loss": 4.076, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.926141750029318e-05, + "loss": 4.0719, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925303155278266e-05, + "loss": 4.0728, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.924464560527214e-05, + "loss": 4.0737, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923627603656536e-05, + "loss": 4.0736, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.922789008905484e-05, + "loss": 4.0684, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.921950414154431e-05, + "loss": 4.0899, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.921111819403379e-05, + "loss": 4.0857, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.920273224652327e-05, + "loss": 4.0767, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.919436267781648e-05, + "loss": 4.0679, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.918597673030596e-05, + "loss": 4.0733, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.917759078279544e-05, + "loss": 4.0692, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.916920483528492e-05, + "loss": 4.088, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.91608188877744e-05, + "loss": 4.0725, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.915243294026388e-05, + "loss": 4.0719, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.9144063371557096e-05, + "loss": 4.0764, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.9135677424046576e-05, + "loss": 4.0825, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.9127291476536056e-05, + "loss": 4.0607, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.9118905529025536e-05, + "loss": 4.0734, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.9110519581515016e-05, + "loss": 4.0657, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.9102150012808225e-05, + "loss": 4.0635, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.9093764065297705e-05, + "loss": 4.065, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.9085378117787185e-05, + "loss": 4.0723, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.9076992170276665e-05, + "loss": 4.0689, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.9068606222766145e-05, + "loss": 4.073, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.9060220275255625e-05, + "loss": 4.0672, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.9051834327745105e-05, + "loss": 4.0628, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.9043464759038314e-05, + "loss": 4.0798, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.90350788115278e-05, + "loss": 4.0865, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.902669286401728e-05, + "loss": 4.0749, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.901830691650676e-05, + "loss": 4.0795, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.900993734779997e-05, + "loss": 4.0603, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.900155140028945e-05, + "loss": 4.0785, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.899316545277893e-05, + "loss": 4.067, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.898477950526841e-05, + "loss": 4.0699, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.897639355775789e-05, + "loss": 4.0642, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.896800761024737e-05, + "loss": 4.0691, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.895963804154058e-05, + "loss": 4.0723, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.895125209403006e-05, + "loss": 4.0679, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.894286614651954e-05, + "loss": 4.0736, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.893448019900902e-05, + "loss": 4.0691, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.8926110630302235e-05, + "loss": 4.0607, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.8917724682791715e-05, + "loss": 4.0733, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.8909338735281195e-05, + "loss": 4.0762, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.8900952787770674e-05, + "loss": 4.083, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.889256684026015e-05, + "loss": 4.0643, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.8884197271553364e-05, + "loss": 4.0812, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.8875811324042843e-05, + "loss": 4.0734, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.886742537653232e-05, + "loss": 4.076, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.8859039429021797e-05, + "loss": 4.0747, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.8850653481511277e-05, + "loss": 4.0723, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.8842267534000757e-05, + "loss": 4.0648, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.883389796529397e-05, + "loss": 4.0783, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.882551201778345e-05, + "loss": 4.0593, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.881712607027293e-05, + "loss": 4.0672, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.880874012276241e-05, + "loss": 4.0738, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.880035417525189e-05, + "loss": 4.0774, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.879196822774137e-05, + "loss": 4.0621, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.878358228023085e-05, + "loss": 4.0698, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.877519633272033e-05, + "loss": 4.0749, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.876682676401354e-05, + "loss": 4.0698, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.875844081650302e-05, + "loss": 4.0712, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 4.08776330947876, + "eval_runtime": 297.31, + "eval_samples_per_second": 1283.479, + "eval_steps_per_second": 40.11, + "step": 686880 + }, + { + "epoch": 1.0, + "learning_rate": 3.875007124779623e-05, + "loss": 4.0555, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.874168530028571e-05, + "loss": 4.0629, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.873329935277519e-05, + "loss": 4.0662, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.872491340526467e-05, + "loss": 4.069, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.871652745775416e-05, + "loss": 4.0767, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.870814151024364e-05, + "loss": 4.0622, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.869975556273312e-05, + "loss": 4.0683, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.86913696152226e-05, + "loss": 4.0653, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.8683000046515806e-05, + "loss": 4.0579, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.8674614099005286e-05, + "loss": 4.0628, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.8666228151494766e-05, + "loss": 4.0735, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.8657842203984246e-05, + "loss": 4.0705, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.8649489014081184e-05, + "loss": 4.0713, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.8641103066570664e-05, + "loss": 4.0493, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.8632717119060144e-05, + "loss": 4.0706, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.8624331171549624e-05, + "loss": 4.0519, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.861594522403911e-05, + "loss": 4.0658, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.860757565533232e-05, + "loss": 4.063, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.85991897078218e-05, + "loss": 4.064, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.859080376031128e-05, + "loss": 4.0679, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.858241781280076e-05, + "loss": 4.0741, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.857404824409397e-05, + "loss": 4.0692, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.856566229658345e-05, + "loss": 4.0648, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.855727634907293e-05, + "loss": 4.0599, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.854889040156241e-05, + "loss": 4.0681, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.854050445405189e-05, + "loss": 4.0629, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.853211850654137e-05, + "loss": 4.0631, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.852373255903085e-05, + "loss": 4.0555, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.851534661152033e-05, + "loss": 4.0596, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.8506977042813544e-05, + "loss": 4.0637, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.849860747410675e-05, + "loss": 4.0533, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.849022152659623e-05, + "loss": 4.0709, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.848183557908571e-05, + "loss": 4.0706, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.847344963157519e-05, + "loss": 4.0683, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.846506368406467e-05, + "loss": 4.06, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.845669411535788e-05, + "loss": 4.0642, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.844830816784736e-05, + "loss": 4.0642, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.843992222033684e-05, + "loss": 4.0575, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.843153627282632e-05, + "loss": 4.052, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.84231503253158e-05, + "loss": 4.053, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.841478075660902e-05, + "loss": 4.0539, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.84063948090985e-05, + "loss": 4.0655, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.839800886158798e-05, + "loss": 4.052, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.838962291407745e-05, + "loss": 4.0583, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.838123696656693e-05, + "loss": 4.0689, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.837285101905641e-05, + "loss": 4.0604, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.836446507154589e-05, + "loss": 4.0688, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.835607912403537e-05, + "loss": 4.0563, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.834770955532858e-05, + "loss": 4.0382, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.833932360781806e-05, + "loss": 4.0713, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.833093766030754e-05, + "loss": 4.0534, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.8322568091600756e-05, + "loss": 4.0632, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.8314182144090236e-05, + "loss": 4.057, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.8305796196579716e-05, + "loss": 4.0565, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.8297410249069195e-05, + "loss": 4.0464, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.8289040680362405e-05, + "loss": 4.0529, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.8280654732851885e-05, + "loss": 4.049, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.8272268785341364e-05, + "loss": 4.0486, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.8263882837830844e-05, + "loss": 4.0687, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.8255496890320324e-05, + "loss": 4.0517, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.8247127321613534e-05, + "loss": 4.0477, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.8238741374103013e-05, + "loss": 4.0699, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.823037180539622e-05, + "loss": 4.0373, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.822198585788571e-05, + "loss": 4.043, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.821359991037519e-05, + "loss": 4.0572, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.820521396286467e-05, + "loss": 4.054, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.819682801535415e-05, + "loss": 4.0468, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.818844206784363e-05, + "loss": 4.0582, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.818005612033311e-05, + "loss": 4.0341, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.817167017282259e-05, + "loss": 4.0476, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.816328422531207e-05, + "loss": 4.0622, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.815491465660528e-05, + "loss": 4.05, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.814652870909476e-05, + "loss": 4.0637, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.813814276158424e-05, + "loss": 4.06, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.812975681407372e-05, + "loss": 4.071, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.812138724536693e-05, + "loss": 4.0418, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.811300129785641e-05, + "loss": 4.0605, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.810461535034589e-05, + "loss": 4.0597, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.8096229402835374e-05, + "loss": 4.0387, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.8087843455324854e-05, + "loss": 4.0658, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.8079457507814334e-05, + "loss": 4.0537, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.8071071560303814e-05, + "loss": 4.0579, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.806268561279329e-05, + "loss": 4.0625, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.80543160440865e-05, + "loss": 4.044, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.804593009657598e-05, + "loss": 4.0408, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.803754414906546e-05, + "loss": 4.0448, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.8029158201554936e-05, + "loss": 4.0553, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.8020772254044416e-05, + "loss": 4.0506, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.801241906414136e-05, + "loss": 4.0467, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.8004049495434577e-05, + "loss": 4.0464, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.7995663547924056e-05, + "loss": 4.0526, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.7987277600413536e-05, + "loss": 4.0484, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.7978891652903016e-05, + "loss": 4.0406, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.7970505705392496e-05, + "loss": 4.0663, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.7962119757881976e-05, + "loss": 4.0608, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.7953733810371456e-05, + "loss": 4.0555, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.7945347862860936e-05, + "loss": 4.0402, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.793696191535041e-05, + "loss": 4.05, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.792857596783989e-05, + "loss": 4.0472, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.792019002032937e-05, + "loss": 4.0606, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.791182045162258e-05, + "loss": 4.0508, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.7903434504112065e-05, + "loss": 4.0441, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.7895048556601545e-05, + "loss": 4.0533, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.7886662609091025e-05, + "loss": 4.0591, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.7878293040384234e-05, + "loss": 4.036, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.7869907092873714e-05, + "loss": 4.0524, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.786153752416693e-05, + "loss": 4.0375, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.785315157665641e-05, + "loss": 4.0432, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.784476562914588e-05, + "loss": 4.0422, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.783637968163536e-05, + "loss": 4.0423, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.782799373412484e-05, + "loss": 4.0453, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.781960778661432e-05, + "loss": 4.0509, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.781123821790753e-05, + "loss": 4.0433, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.780285227039702e-05, + "loss": 4.0386, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.77944663228865e-05, + "loss": 4.0583, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.778608037537598e-05, + "loss": 4.0603, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.777769442786546e-05, + "loss": 4.0519, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.776932485915867e-05, + "loss": 4.0583, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.776093891164815e-05, + "loss": 4.039, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.775255296413763e-05, + "loss": 4.0498, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.774416701662711e-05, + "loss": 4.0435, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.773578106911659e-05, + "loss": 4.043, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.772739512160607e-05, + "loss": 4.0414, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.771900917409555e-05, + "loss": 4.0451, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.771062322658503e-05, + "loss": 4.0502, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.7702253657878237e-05, + "loss": 4.0442, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.7693867710367717e-05, + "loss": 4.0479, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.768549814166093e-05, + "loss": 4.0499, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.767711219415041e-05, + "loss": 4.0357, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.766872624663989e-05, + "loss": 4.0503, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.766034029912937e-05, + "loss": 4.054, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.765195435161885e-05, + "loss": 4.0561, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.764356840410833e-05, + "loss": 4.0421, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.763518245659781e-05, + "loss": 4.0595, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.762679650908729e-05, + "loss": 4.0482, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.761841056157677e-05, + "loss": 4.0515, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.761004099286998e-05, + "loss": 4.0535, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.760165504535946e-05, + "loss": 4.0451, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.759326909784894e-05, + "loss": 4.0411, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.758489952914215e-05, + "loss": 4.0573, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.757651358163164e-05, + "loss": 4.0302, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.756812763412112e-05, + "loss": 4.0474, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.75597416866106e-05, + "loss": 4.052, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.7551372117903806e-05, + "loss": 4.047, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.7542986170393286e-05, + "loss": 4.0408, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.7534600222882766e-05, + "loss": 4.0455, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.752621427537224e-05, + "loss": 4.0489, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.7517844706665455e-05, + "loss": 4.0517, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.7509475137958664e-05, + "loss": 4.0477, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 4.0715436935424805, + "eval_runtime": 297.4029, + "eval_samples_per_second": 1283.078, + "eval_steps_per_second": 40.097, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.7501089190448144e-05, + "loss": 4.0223, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.7492703242937624e-05, + "loss": 4.0387, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.7484317295427104e-05, + "loss": 4.0436, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.747593134791659e-05, + "loss": 4.0459, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.746754540040607e-05, + "loss": 4.0539, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.7459159452895544e-05, + "loss": 4.0407, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.7450773505385024e-05, + "loss": 4.0451, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.7442387557874504e-05, + "loss": 4.0405, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.7434001610363984e-05, + "loss": 4.0379, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.7425615662853463e-05, + "loss": 4.0368, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.7417229715342943e-05, + "loss": 4.0506, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.7408843767832423e-05, + "loss": 4.0509, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.740047419912563e-05, + "loss": 4.0504, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.739208825161511e-05, + "loss": 4.025, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.738370230410459e-05, + "loss": 4.0493, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.737531635659407e-05, + "loss": 4.0298, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.736693040908356e-05, + "loss": 4.0438, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.735854446157304e-05, + "loss": 4.0395, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.735015851406252e-05, + "loss": 4.0388, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.7341772566552e-05, + "loss": 4.0441, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.733340299784521e-05, + "loss": 4.0527, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.732501705033469e-05, + "loss": 4.0462, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.731663110282417e-05, + "loss": 4.0424, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.730824515531365e-05, + "loss": 4.0335, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.729985920780313e-05, + "loss": 4.05, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.72914732602926e-05, + "loss": 4.0412, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.728308731278208e-05, + "loss": 4.0362, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.727470136527156e-05, + "loss": 4.0357, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.726633179656478e-05, + "loss": 4.0354, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.725796222785799e-05, + "loss": 4.0422, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.724957628034747e-05, + "loss": 4.0282, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.724119033283695e-05, + "loss": 4.0486, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.723280438532643e-05, + "loss": 4.0525, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.722443481661964e-05, + "loss": 4.0416, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.721604886910912e-05, + "loss": 4.0394, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.72076629215986e-05, + "loss": 4.0388, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.7199276974088075e-05, + "loss": 4.0472, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.7190891026577555e-05, + "loss": 4.0368, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.7182505079067035e-05, + "loss": 4.0243, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.7174119131556515e-05, + "loss": 4.034, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.7165733184045995e-05, + "loss": 4.0327, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.715736361533921e-05, + "loss": 4.0396, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.7148994046632426e-05, + "loss": 4.0318, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.7140608099121906e-05, + "loss": 4.0354, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.713222215161138e-05, + "loss": 4.0457, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.712383620410086e-05, + "loss": 4.0394, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.7115466635394075e-05, + "loss": 4.0446, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.710708068788355e-05, + "loss": 4.0364, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.7098711119176764e-05, + "loss": 4.0135, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.7090325171666244e-05, + "loss": 4.0468, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.7081939224155724e-05, + "loss": 4.0321, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.7073553276645204e-05, + "loss": 4.0373, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.7065167329134684e-05, + "loss": 4.0371, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.7056781381624164e-05, + "loss": 4.0354, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.7048395434113644e-05, + "loss": 4.0255, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.7040009486603124e-05, + "loss": 4.0283, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.7031623539092604e-05, + "loss": 4.0297, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.7023237591582084e-05, + "loss": 4.0248, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.701486802287529e-05, + "loss": 4.0441, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.70064984541685e-05, + "loss": 4.0302, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.699811250665798e-05, + "loss": 4.0269, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.698972655914746e-05, + "loss": 4.0475, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.698134061163694e-05, + "loss": 4.0199, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.697295466412642e-05, + "loss": 4.0201, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.69645687166159e-05, + "loss": 4.0381, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.695618276910538e-05, + "loss": 4.0281, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.694779682159487e-05, + "loss": 4.025, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.693941087408435e-05, + "loss": 4.0333, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.693102492657383e-05, + "loss": 4.017, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.692263897906331e-05, + "loss": 4.0265, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.691425303155279e-05, + "loss": 4.0413, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.6905883462846e-05, + "loss": 4.0299, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.689749751533548e-05, + "loss": 4.041, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.688911156782496e-05, + "loss": 4.0349, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.6880741999118167e-05, + "loss": 4.0501, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.6872356051607646e-05, + "loss": 4.0223, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.6863970104097126e-05, + "loss": 4.0372, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.6855584156586606e-05, + "loss": 4.0393, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.6847198209076086e-05, + "loss": 4.0191, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.6838812261565566e-05, + "loss": 4.041, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.683044269285878e-05, + "loss": 4.0342, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.682205674534826e-05, + "loss": 4.0374, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.6813670797837735e-05, + "loss": 4.041, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.6805284850327215e-05, + "loss": 4.0229, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.6796898902816695e-05, + "loss": 4.0167, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.6788512955306175e-05, + "loss": 4.0225, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.6780127007795655e-05, + "loss": 4.0372, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.6771757439088864e-05, + "loss": 4.0269, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.6763371491578344e-05, + "loss": 4.0255, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.6754985544067824e-05, + "loss": 4.0261, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.6746599596557304e-05, + "loss": 4.0326, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.673821364904679e-05, + "loss": 4.0266, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.672982770153627e-05, + "loss": 4.0242, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.672145813282948e-05, + "loss": 4.0429, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.671307218531896e-05, + "loss": 4.0417, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.670468623780844e-05, + "loss": 4.0324, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.669630029029792e-05, + "loss": 4.0245, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.66879143427874e-05, + "loss": 4.0271, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.667954477408061e-05, + "loss": 4.0231, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.667115882657009e-05, + "loss": 4.0389, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.666277287905957e-05, + "loss": 4.0294, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.665438693154905e-05, + "loss": 4.0278, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.664600098403853e-05, + "loss": 4.0261, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.663761503652801e-05, + "loss": 4.0317, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.662922908901749e-05, + "loss": 4.0274, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.6620859520310704e-05, + "loss": 4.0257, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.6612489951603914e-05, + "loss": 4.0175, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.6604104004093393e-05, + "loss": 4.0217, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.6595718056582873e-05, + "loss": 4.0228, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.658733210907235e-05, + "loss": 4.0214, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.657894616156183e-05, + "loss": 4.0237, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.657056021405131e-05, + "loss": 4.0249, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.656217426654079e-05, + "loss": 4.0235, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.655378831903027e-05, + "loss": 4.0176, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.6545402371519746e-05, + "loss": 4.0382, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.6537016424009226e-05, + "loss": 4.0413, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.652863047649871e-05, + "loss": 4.0288, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.652024452898819e-05, + "loss": 4.035, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.651185858147767e-05, + "loss": 4.0235, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.650348901277088e-05, + "loss": 4.0281, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.649510306526036e-05, + "loss": 4.0267, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.648673349655357e-05, + "loss": 4.0185, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.647834754904305e-05, + "loss": 4.0224, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.646996160153253e-05, + "loss": 4.0286, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.646157565402201e-05, + "loss": 4.0317, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.645318970651149e-05, + "loss": 4.0268, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.644480375900097e-05, + "loss": 4.0271, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.643641781149045e-05, + "loss": 4.0264, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.642803186397993e-05, + "loss": 4.0191, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.6419678674076876e-05, + "loss": 4.0257, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.6411292726566356e-05, + "loss": 4.0352, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.6402906779055836e-05, + "loss": 4.035, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.6394520831545316e-05, + "loss": 4.0186, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.6386134884034796e-05, + "loss": 4.0416, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.6377748936524276e-05, + "loss": 4.0276, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.6369362989013756e-05, + "loss": 4.0346, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.6360977041503236e-05, + "loss": 4.0339, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.6352607472796445e-05, + "loss": 4.0233, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.6344221525285925e-05, + "loss": 4.0214, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.6335835577775405e-05, + "loss": 4.0401, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.6327449630264884e-05, + "loss": 4.0146, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.6319063682754364e-05, + "loss": 4.0236, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.6310677735243844e-05, + "loss": 4.0311, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.630229178773333e-05, + "loss": 4.0305, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.629390584022281e-05, + "loss": 4.0192, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.628553627151602e-05, + "loss": 4.0246, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.627716670280923e-05, + "loss": 4.0283, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.626878075529871e-05, + "loss": 4.0367, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.626039480778819e-05, + "loss": 4.0282, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 4.058162212371826, + "eval_runtime": 289.1475, + "eval_samples_per_second": 1319.71, + "eval_steps_per_second": 41.242, + "step": 839520 + }, + { + "epoch": 1.0, + "learning_rate": 3.62520252390814e-05, + "loss": 4.0103, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.624363929157088e-05, + "loss": 4.0202, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.623525334406036e-05, + "loss": 4.0233, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.622686739654984e-05, + "loss": 4.0272, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.621848144903932e-05, + "loss": 4.0326, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.62100955015288e-05, + "loss": 4.0218, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.6201709554018285e-05, + "loss": 4.0237, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.619332360650776e-05, + "loss": 4.024, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.618493765899724e-05, + "loss": 4.0161, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.617655171148672e-05, + "loss": 4.011, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.61681657639762e-05, + "loss": 4.029, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.615979619526941e-05, + "loss": 4.0376, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.615142662656262e-05, + "loss": 4.0279, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.61430406790521e-05, + "loss": 4.0065, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.613465473154158e-05, + "loss": 4.0269, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.6126268784031056e-05, + "loss": 4.0112, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.6117882836520536e-05, + "loss": 4.0243, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.610949688901002e-05, + "loss": 4.0209, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.610112732030323e-05, + "loss": 4.0215, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.609274137279271e-05, + "loss": 4.024, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.608435542528219e-05, + "loss": 4.0323, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.607596947777167e-05, + "loss": 4.0229, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.606758353026115e-05, + "loss": 4.0246, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.605919758275063e-05, + "loss": 4.0189, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.605082801404384e-05, + "loss": 4.0281, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.604244206653332e-05, + "loss": 4.0213, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.60340561190228e-05, + "loss": 4.0147, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.602567017151228e-05, + "loss": 4.0167, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.601728422400176e-05, + "loss": 4.0168, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.6008914655294976e-05, + "loss": 4.0217, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.6000528707784456e-05, + "loss": 4.0131, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.5992142760273936e-05, + "loss": 4.0266, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.5983756812763416e-05, + "loss": 4.0283, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.5975370865252896e-05, + "loss": 4.0269, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.5966984917742376e-05, + "loss": 4.02, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.5958615349035585e-05, + "loss": 4.021, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.5950229401525065e-05, + "loss": 4.0269, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.5941843454014545e-05, + "loss": 4.0123, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.5933457506504025e-05, + "loss": 4.0112, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.5925071558993505e-05, + "loss": 4.0182, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.5916685611482985e-05, + "loss": 4.0121, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.5908316042776194e-05, + "loss": 4.0204, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.5899930095265674e-05, + "loss": 4.0082, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.5891544147755154e-05, + "loss": 4.0221, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.588315820024464e-05, + "loss": 4.0207, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.587477225273412e-05, + "loss": 4.0231, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.5866386305223594e-05, + "loss": 4.0242, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.5858000357713074e-05, + "loss": 4.0194, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.5849614410202554e-05, + "loss": 3.9961, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.584124484149577e-05, + "loss": 4.027, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.583287527278898e-05, + "loss": 4.0131, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.582448932527846e-05, + "loss": 4.0176, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.581610337776794e-05, + "loss": 4.0185, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.580771743025742e-05, + "loss": 4.0149, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.579933148274689e-05, + "loss": 4.0052, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.579094553523638e-05, + "loss": 4.0096, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.578255958772586e-05, + "loss": 4.0112, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.577419001901907e-05, + "loss": 4.0047, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.576582045031228e-05, + "loss": 4.0271, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.575743450280176e-05, + "loss": 4.0161, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.574904855529124e-05, + "loss": 4.0015, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.5740662607780716e-05, + "loss": 4.0287, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.5732276660270196e-05, + "loss": 4.0054, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.5723890712759676e-05, + "loss": 4.0006, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.5715504765249156e-05, + "loss": 4.0205, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.5707118817738636e-05, + "loss": 4.0121, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.5698749249031845e-05, + "loss": 4.0062, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.569036330152133e-05, + "loss": 4.0144, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.568197735401081e-05, + "loss": 3.9977, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.567360778530402e-05, + "loss": 4.0074, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.56652218377935e-05, + "loss": 4.0189, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.565683589028298e-05, + "loss": 4.0143, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.564844994277246e-05, + "loss": 4.0237, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.564008037406567e-05, + "loss": 4.0152, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.5631710805358886e-05, + "loss": 4.0306, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.5623341236652095e-05, + "loss": 4.0013, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.5614955289141575e-05, + "loss": 4.0188, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.5606569341631055e-05, + "loss": 4.0183, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.5598183394120535e-05, + "loss": 4.0024, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.5589797446610015e-05, + "loss": 4.0207, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.5581411499099495e-05, + "loss": 4.0193, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.557304193039271e-05, + "loss": 4.0192, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.556465598288219e-05, + "loss": 4.0263, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.5556270035371664e-05, + "loss": 4.0047, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.5547884087861144e-05, + "loss": 3.9974, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.5539498140350624e-05, + "loss": 4.0047, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.5531112192840104e-05, + "loss": 4.0206, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.5522726245329584e-05, + "loss": 4.0113, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.5514340297819064e-05, + "loss": 4.0091, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.5505954350308544e-05, + "loss": 4.0072, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.549758478160175e-05, + "loss": 4.0105, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.548919883409124e-05, + "loss": 4.012, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.548081288658072e-05, + "loss": 4.0072, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.54724269390702e-05, + "loss": 4.0182, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.546404099155968e-05, + "loss": 4.0246, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.545567142285289e-05, + "loss": 4.0166, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.54473018541461e-05, + "loss": 4.0079, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.543891590663558e-05, + "loss": 4.0049, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.543052995912506e-05, + "loss": 4.0077, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.542214401161454e-05, + "loss": 4.0192, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.541375806410402e-05, + "loss": 4.0155, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.54053721165935e-05, + "loss": 4.009, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.539698616908298e-05, + "loss": 4.013, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.538860022157246e-05, + "loss": 4.0104, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.538021427406194e-05, + "loss": 4.0125, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.537184470535515e-05, + "loss": 4.0054, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.536345875784463e-05, + "loss": 4.0012, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.535507281033411e-05, + "loss": 4.0011, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.534668686282359e-05, + "loss": 4.0108, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.533830091531307e-05, + "loss": 4.0025, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.532991496780255e-05, + "loss": 4.0068, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.532154539909576e-05, + "loss": 4.0091, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.531315945158524e-05, + "loss": 4.0051, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.530477350407472e-05, + "loss": 4.0006, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.5296387556564195e-05, + "loss": 4.0229, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.528801798785741e-05, + "loss": 4.0222, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.527963204034689e-05, + "loss": 4.0109, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.527124609283637e-05, + "loss": 4.0185, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.526286014532585e-05, + "loss": 4.0073, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.525447419781533e-05, + "loss": 4.0106, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.5246104629108547e-05, + "loss": 4.0107, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.5237718681598027e-05, + "loss": 3.9997, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.52293327340875e-05, + "loss": 4.0073, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.522094678657698e-05, + "loss": 4.0088, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.521256083906646e-05, + "loss": 4.0174, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.520417489155594e-05, + "loss": 4.0053, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.519578894404542e-05, + "loss": 4.0118, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.51874029965349e-05, + "loss": 4.0073, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.5179049806631844e-05, + "loss": 4.0034, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.5170663859121324e-05, + "loss": 4.0112, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.5162277911610804e-05, + "loss": 4.0143, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.5153891964100284e-05, + "loss": 4.0184, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.5145506016589764e-05, + "loss": 3.9997, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.5137120069079244e-05, + "loss": 4.0246, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.5128734121568724e-05, + "loss": 4.0095, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.5120348174058204e-05, + "loss": 4.0189, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.511197860535141e-05, + "loss": 4.0155, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.510359265784089e-05, + "loss": 4.0067, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.509520671033037e-05, + "loss": 4.0021, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.508682076281985e-05, + "loss": 4.023, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.507843481530933e-05, + "loss": 3.9959, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.507006524660255e-05, + "loss": 4.0073, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.506167929909203e-05, + "loss": 4.0128, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.505329335158151e-05, + "loss": 4.0091, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.504490740407099e-05, + "loss": 4.0075, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.50365378353642e-05, + "loss": 4.0074, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.502815188785368e-05, + "loss": 4.0096, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.501976594034316e-05, + "loss": 4.0198, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.501137999283264e-05, + "loss": 4.0086, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 4.047217845916748, + "eval_runtime": 288.9513, + "eval_samples_per_second": 1320.607, + "eval_steps_per_second": 41.27, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.500299404532212e-05, + "loss": 3.9915, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.49946080978116e-05, + "loss": 3.9987, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.498622215030108e-05, + "loss": 4.005, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.497783620279056e-05, + "loss": 4.0129, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.496945025528003e-05, + "loss": 4.0111, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.496106430776952e-05, + "loss": 4.0067, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.4952678360259e-05, + "loss": 4.0121, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.494429241274848e-05, + "loss": 4.0039, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.493590646523796e-05, + "loss": 4.0005, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.492752051772744e-05, + "loss": 3.9955, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.491913457021692e-05, + "loss": 4.0159, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.49107486227064e-05, + "loss": 4.0177, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.4902379053999606e-05, + "loss": 4.0116, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.4893993106489086e-05, + "loss": 3.9891, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.4885607158978566e-05, + "loss": 4.0118, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.4877221211468046e-05, + "loss": 3.9918, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.4868835263957526e-05, + "loss": 4.0103, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.4860449316447006e-05, + "loss": 4.0026, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.4852063368936486e-05, + "loss": 4.0018, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.4843677421425966e-05, + "loss": 4.0083, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.4835291473915446e-05, + "loss": 4.0171, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.4826905526404926e-05, + "loss": 4.0051, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.4818519578894406e-05, + "loss": 4.0069, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.4810133631383886e-05, + "loss": 4.0054, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.48017640626771e-05, + "loss": 4.0107, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.4793378115166575e-05, + "loss": 4.0076, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.4784992167656055e-05, + "loss": 3.9986, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.4776606220145535e-05, + "loss": 3.9979, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.4768220272635015e-05, + "loss": 4.0002, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.4759834325124495e-05, + "loss": 4.003, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.4751448377613975e-05, + "loss": 3.9996, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.4743062430103455e-05, + "loss": 4.0058, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.47347092402004e-05, + "loss": 4.008, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.472632329268988e-05, + "loss": 4.0141, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.471793734517936e-05, + "loss": 4.0033, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.4709567776472575e-05, + "loss": 4.003, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.470118182896205e-05, + "loss": 4.0128, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.469279588145153e-05, + "loss": 3.9921, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.468440993394101e-05, + "loss": 3.9956, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.467602398643049e-05, + "loss": 4.0013, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.466763803891997e-05, + "loss": 3.9956, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.465925209140945e-05, + "loss": 4.0008, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.465086614389893e-05, + "loss": 3.9962, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.464248019638841e-05, + "loss": 4.0029, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.463409424887789e-05, + "loss": 4.0057, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.462570830136737e-05, + "loss": 4.0081, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.461732235385685e-05, + "loss": 4.0069, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.4608952785150064e-05, + "loss": 4.0047, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.4600566837639544e-05, + "loss": 3.9804, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.459219726893275e-05, + "loss": 4.0099, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.458381132142223e-05, + "loss": 3.9958, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.457542537391171e-05, + "loss": 4.002, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.456703942640119e-05, + "loss": 3.9983, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.455865347889067e-05, + "loss": 3.9967, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.455026753138015e-05, + "loss": 3.9922, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.454189796267336e-05, + "loss": 3.9939, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.453351201516284e-05, + "loss": 3.9982, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.452512606765232e-05, + "loss": 3.9859, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.45167401201418e-05, + "loss": 4.0101, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.450837055143502e-05, + "loss": 4.0016, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.44999846039245e-05, + "loss": 3.9833, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.449159865641398e-05, + "loss": 4.0145, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.448321270890346e-05, + "loss": 3.987, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.447482676139293e-05, + "loss": 3.9847, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.446645719268615e-05, + "loss": 3.9988, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.4458071245175627e-05, + "loss": 3.9966, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.4449685297665107e-05, + "loss": 3.9862, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.444129935015458e-05, + "loss": 4.0022, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.443291340264406e-05, + "loss": 3.9829, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.442452745513354e-05, + "loss": 3.9878, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.4416141507623026e-05, + "loss": 4.0064, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.4407755560112506e-05, + "loss": 3.9977, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.4399385991405715e-05, + "loss": 4.0045, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.4391000043895195e-05, + "loss": 3.9992, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.4382614096384675e-05, + "loss": 4.0139, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.4374244527677884e-05, + "loss": 3.9879, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.4365858580167364e-05, + "loss": 4.0044, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.4357472632656844e-05, + "loss": 3.9983, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.4349086685146324e-05, + "loss": 3.9917, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.4340700737635804e-05, + "loss": 3.9984, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.4332314790125284e-05, + "loss": 4.01, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.4323928842614764e-05, + "loss": 3.9981, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.4315542895104244e-05, + "loss": 4.0101, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.4307156947593724e-05, + "loss": 3.9868, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.429878737888694e-05, + "loss": 3.9831, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.429040143137642e-05, + "loss": 3.9889, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.42820154838659e-05, + "loss": 4.0025, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.427362953635538e-05, + "loss": 3.9972, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.426525996764859e-05, + "loss": 3.9965, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.425687402013807e-05, + "loss": 3.9895, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.424848807262755e-05, + "loss": 3.9941, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.424010212511703e-05, + "loss": 3.9937, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.423173255641024e-05, + "loss": 3.9895, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.422334660889972e-05, + "loss": 4.005, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.42149606613892e-05, + "loss": 4.0058, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.420657471387868e-05, + "loss": 4.0019, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.419822152397562e-05, + "loss": 3.9866, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.41898355764651e-05, + "loss": 3.992, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.418144962895458e-05, + "loss": 3.9904, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.417306368144406e-05, + "loss": 4.0044, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.416467773393354e-05, + "loss": 4.0021, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.415630816522675e-05, + "loss": 3.9903, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.414792221771623e-05, + "loss": 3.9959, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.413953627020571e-05, + "loss": 3.9962, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.413115032269519e-05, + "loss": 3.9969, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.412276437518467e-05, + "loss": 3.9904, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.411437842767415e-05, + "loss": 3.9892, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.410599248016363e-05, + "loss": 3.9816, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.409762291145685e-05, + "loss": 3.9927, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.408923696394633e-05, + "loss": 3.9896, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.408085101643581e-05, + "loss": 3.9866, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.407246506892529e-05, + "loss": 3.9908, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.406407912141477e-05, + "loss": 3.9921, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.405569317390424e-05, + "loss": 3.9808, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.404730722639372e-05, + "loss": 4.0046, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.4038937657686936e-05, + "loss": 4.0071, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.4030568088980145e-05, + "loss": 3.9982, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.4022182141469625e-05, + "loss": 3.9966, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.4013796193959105e-05, + "loss": 3.995, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.4005410246448585e-05, + "loss": 3.9906, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.3997024298938065e-05, + "loss": 4.0019, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.3988638351427545e-05, + "loss": 3.9776, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.3980252403917025e-05, + "loss": 3.9931, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.3971866456406505e-05, + "loss": 3.992, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.3963480508895985e-05, + "loss": 4.0001, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.3955094561385465e-05, + "loss": 3.9919, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.3946708613874945e-05, + "loss": 3.994, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.3938322666364425e-05, + "loss": 3.9872, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.3929953097657634e-05, + "loss": 3.9846, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.3921567150147114e-05, + "loss": 3.9984, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.3913181202636594e-05, + "loss": 3.9986, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.3904795255126074e-05, + "loss": 4.0035, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.3896409307615554e-05, + "loss": 3.9894, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.388803973890877e-05, + "loss": 4.0041, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.387965379139825e-05, + "loss": 3.996, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.387126784388773e-05, + "loss": 3.9981, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.386288189637721e-05, + "loss": 4.0025, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.385451232767042e-05, + "loss": 3.9954, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.38461263801599e-05, + "loss": 3.986, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.383774043264938e-05, + "loss": 4.0042, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.382937086394259e-05, + "loss": 3.9834, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.382098491643207e-05, + "loss": 3.9887, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.381259896892155e-05, + "loss": 3.9986, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.3804229400214757e-05, + "loss": 3.9945, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.379584345270424e-05, + "loss": 3.991, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.378745750519372e-05, + "loss": 3.9915, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.37790715576832e-05, + "loss": 3.9937, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.377068561017268e-05, + "loss": 3.9993, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.376231604146589e-05, + "loss": 3.9979, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 4.037529468536377, + "eval_runtime": 289.5297, + "eval_samples_per_second": 1317.968, + "eval_steps_per_second": 41.187, + "step": 992160 + }, + { + "epoch": 1.0, + "learning_rate": 3.375393009395537e-05, + "loss": 3.9847, + "step": 992256 + }, + { + "epoch": 1.0, + "learning_rate": 3.374554414644485e-05, + "loss": 3.9812, + "step": 992768 + }, + { + "epoch": 1.0, + "learning_rate": 3.373715819893433e-05, + "loss": 3.9864, + "step": 993280 + }, + { + "epoch": 1.0, + "learning_rate": 3.372877225142381e-05, + "loss": 4.0029, + "step": 993792 + }, + { + "epoch": 1.0, + "learning_rate": 3.372038630391329e-05, + "loss": 3.9939, + "step": 994304 + }, + { + "epoch": 1.0, + "learning_rate": 3.371200035640277e-05, + "loss": 3.9924, + "step": 994816 + }, + { + "epoch": 1.0, + "learning_rate": 3.370361440889225e-05, + "loss": 3.994, + "step": 995328 + }, + { + "epoch": 1.0, + "learning_rate": 3.369524484018546e-05, + "loss": 3.992, + "step": 995840 + }, + { + "epoch": 1.0, + "learning_rate": 3.368685889267494e-05, + "loss": 3.981, + "step": 996352 + }, + { + "epoch": 1.0, + "learning_rate": 3.367847294516443e-05, + "loss": 3.9845, + "step": 996864 + }, + { + "epoch": 1.0, + "learning_rate": 3.36700869976539e-05, + "loss": 3.9952, + "step": 997376 + }, + { + "epoch": 1.0, + "learning_rate": 3.366170105014338e-05, + "loss": 4.0002, + "step": 997888 + }, + { + "epoch": 1.0, + "learning_rate": 3.36533314814366e-05, + "loss": 4.0047, + "step": 998400 + }, + { + "epoch": 1.0, + "learning_rate": 3.3644961912729806e-05, + "loss": 3.9708, + "step": 998912 + }, + { + "epoch": 1.0, + "learning_rate": 3.3636575965219286e-05, + "loss": 3.9886, + "step": 999424 + }, + { + "epoch": 1.0, + "learning_rate": 3.3628190017708766e-05, + "loss": 3.9793, + "step": 999936 + }, + { + "epoch": 1.0, + "learning_rate": 3.3619804070198246e-05, + "loss": 3.9941, + "step": 1000448 + }, + { + "epoch": 1.0, + "learning_rate": 3.3611418122687726e-05, + "loss": 3.988, + "step": 1000960 + }, + { + "epoch": 1.0, + "learning_rate": 3.3603048553980935e-05, + "loss": 3.9895, + "step": 1001472 + }, + { + "epoch": 1.0, + "learning_rate": 3.3594662606470415e-05, + "loss": 3.986, + "step": 1001984 + }, + { + "epoch": 1.0, + "learning_rate": 3.3586276658959895e-05, + "loss": 4.0088, + "step": 1002496 + }, + { + "epoch": 1.0, + "learning_rate": 3.3577890711449375e-05, + "loss": 3.9883, + "step": 1003008 + }, + { + "epoch": 1.0, + "learning_rate": 3.3569504763938855e-05, + "loss": 3.9917, + "step": 1003520 + }, + { + "epoch": 1.0, + "learning_rate": 3.356113519523207e-05, + "loss": 3.9901, + "step": 1004032 + }, + { + "epoch": 1.0, + "learning_rate": 3.355274924772155e-05, + "loss": 3.9965, + "step": 1004544 + }, + { + "epoch": 1.0, + "learning_rate": 3.3544363300211024e-05, + "loss": 3.9898, + "step": 1005056 + }, + { + "epoch": 1.0, + "learning_rate": 3.3535977352700503e-05, + "loss": 3.9818, + "step": 1005568 + }, + { + "epoch": 1.0, + "learning_rate": 3.3527591405189983e-05, + "loss": 3.9859, + "step": 1006080 + }, + { + "epoch": 1.0, + "learning_rate": 3.3519205457679463e-05, + "loss": 3.9847, + "step": 1006592 + }, + { + "epoch": 1.0, + "learning_rate": 3.351081951016894e-05, + "loss": 3.9842, + "step": 1007104 + }, + { + "epoch": 1.01, + "learning_rate": 3.350243356265842e-05, + "loss": 3.9874, + "step": 1007616 + }, + { + "epoch": 1.01, + "learning_rate": 3.34940476151479e-05, + "loss": 3.9885, + "step": 1008128 + }, + { + "epoch": 1.01, + "learning_rate": 3.348567804644111e-05, + "loss": 3.9969, + "step": 1008640 + }, + { + "epoch": 1.01, + "learning_rate": 3.34772920989306e-05, + "loss": 3.9948, + "step": 1009152 + }, + { + "epoch": 1.01, + "learning_rate": 3.346890615142008e-05, + "loss": 3.9892, + "step": 1009664 + }, + { + "epoch": 1.01, + "learning_rate": 3.346052020390956e-05, + "loss": 3.9905, + "step": 1010176 + }, + { + "epoch": 1.01, + "learning_rate": 3.345215063520277e-05, + "loss": 3.9985, + "step": 1010688 + }, + { + "epoch": 1.01, + "learning_rate": 3.344376468769225e-05, + "loss": 3.9745, + "step": 1011200 + }, + { + "epoch": 1.01, + "learning_rate": 3.343537874018173e-05, + "loss": 3.9803, + "step": 1011712 + }, + { + "epoch": 1.01, + "learning_rate": 3.342699279267121e-05, + "loss": 3.9882, + "step": 1012224 + }, + { + "epoch": 1.01, + "learning_rate": 3.341860684516069e-05, + "loss": 3.9772, + "step": 1012736 + }, + { + "epoch": 1.01, + "learning_rate": 3.341022089765017e-05, + "loss": 3.9892, + "step": 1013248 + }, + { + "epoch": 1.01, + "learning_rate": 3.340185132894338e-05, + "loss": 3.9862, + "step": 1013760 + }, + { + "epoch": 1.01, + "learning_rate": 3.339346538143286e-05, + "loss": 3.9854, + "step": 1014272 + }, + { + "epoch": 1.01, + "learning_rate": 3.338507943392234e-05, + "loss": 3.9901, + "step": 1014784 + }, + { + "epoch": 1.01, + "learning_rate": 3.337669348641182e-05, + "loss": 3.9909, + "step": 1015296 + }, + { + "epoch": 1.01, + "learning_rate": 3.33683075389013e-05, + "loss": 3.9933, + "step": 1015808 + }, + { + "epoch": 1.01, + "learning_rate": 3.3359921591390784e-05, + "loss": 3.9866, + "step": 1016320 + }, + { + "epoch": 1.01, + "learning_rate": 3.3351535643880263e-05, + "loss": 3.9696, + "step": 1016832 + }, + { + "epoch": 1.01, + "learning_rate": 3.334314969636974e-05, + "loss": 3.9891, + "step": 1017344 + }, + { + "epoch": 1.01, + "learning_rate": 3.333478012766295e-05, + "loss": 3.9835, + "step": 1017856 + }, + { + "epoch": 1.01, + "learning_rate": 3.332639418015243e-05, + "loss": 3.9904, + "step": 1018368 + }, + { + "epoch": 1.01, + "learning_rate": 3.331802461144564e-05, + "loss": 3.9853, + "step": 1018880 + }, + { + "epoch": 1.01, + "learning_rate": 3.330963866393512e-05, + "loss": 3.9782, + "step": 1019392 + }, + { + "epoch": 1.01, + "learning_rate": 3.330126909522833e-05, + "loss": 3.9772, + "step": 1019904 + }, + { + "epoch": 1.01, + "learning_rate": 3.329288314771781e-05, + "loss": 3.9788, + "step": 1020416 + }, + { + "epoch": 1.01, + "learning_rate": 3.328449720020729e-05, + "loss": 3.9848, + "step": 1020928 + }, + { + "epoch": 1.01, + "learning_rate": 3.327611125269677e-05, + "loss": 3.9696, + "step": 1021440 + }, + { + "epoch": 1.01, + "learning_rate": 3.326772530518625e-05, + "loss": 3.9961, + "step": 1021952 + }, + { + "epoch": 1.01, + "learning_rate": 3.3259355736479466e-05, + "loss": 3.9895, + "step": 1022464 + }, + { + "epoch": 1.01, + "learning_rate": 3.3250969788968946e-05, + "loss": 3.9669, + "step": 1022976 + }, + { + "epoch": 1.01, + "learning_rate": 3.3242583841458426e-05, + "loss": 3.9968, + "step": 1023488 + }, + { + "epoch": 1.01, + "learning_rate": 3.3234197893947906e-05, + "loss": 3.9731, + "step": 1024000 + }, + { + "epoch": 1.01, + "learning_rate": 3.3225811946437386e-05, + "loss": 3.9742, + "step": 1024512 + }, + { + "epoch": 1.01, + "learning_rate": 3.321742599892686e-05, + "loss": 3.9795, + "step": 1025024 + }, + { + "epoch": 1.01, + "learning_rate": 3.320904005141634e-05, + "loss": 3.9882, + "step": 1025536 + }, + { + "epoch": 1.01, + "learning_rate": 3.320065410390582e-05, + "loss": 3.9712, + "step": 1026048 + }, + { + "epoch": 1.01, + "learning_rate": 3.31922681563953e-05, + "loss": 3.9896, + "step": 1026560 + }, + { + "epoch": 1.01, + "learning_rate": 3.318389858768851e-05, + "loss": 3.9653, + "step": 1027072 + }, + { + "epoch": 1.01, + "learning_rate": 3.317551264017799e-05, + "loss": 3.9748, + "step": 1027584 + }, + { + "epoch": 1.01, + "learning_rate": 3.3167126692667475e-05, + "loss": 3.9927, + "step": 1028096 + }, + { + "epoch": 1.01, + "learning_rate": 3.3158740745156955e-05, + "loss": 3.9808, + "step": 1028608 + }, + { + "epoch": 1.01, + "learning_rate": 3.3150354797646435e-05, + "loss": 3.9919, + "step": 1029120 + }, + { + "epoch": 1.01, + "learning_rate": 3.3141968850135915e-05, + "loss": 3.9857, + "step": 1029632 + }, + { + "epoch": 1.01, + "learning_rate": 3.3133599281429124e-05, + "loss": 3.9997, + "step": 1030144 + }, + { + "epoch": 1.01, + "learning_rate": 3.3125213333918604e-05, + "loss": 3.9736, + "step": 1030656 + }, + { + "epoch": 1.01, + "learning_rate": 3.3116827386408084e-05, + "loss": 3.9911, + "step": 1031168 + }, + { + "epoch": 1.01, + "learning_rate": 3.3108441438897564e-05, + "loss": 3.9806, + "step": 1031680 + }, + { + "epoch": 1.01, + "learning_rate": 3.3100055491387044e-05, + "loss": 3.9796, + "step": 1032192 + }, + { + "epoch": 1.01, + "learning_rate": 3.3091669543876524e-05, + "loss": 3.9831, + "step": 1032704 + }, + { + "epoch": 1.01, + "learning_rate": 3.308329997516973e-05, + "loss": 3.9923, + "step": 1033216 + }, + { + "epoch": 1.01, + "learning_rate": 3.307491402765921e-05, + "loss": 3.9852, + "step": 1033728 + }, + { + "epoch": 1.01, + "learning_rate": 3.306652808014869e-05, + "loss": 3.9948, + "step": 1034240 + }, + { + "epoch": 1.01, + "learning_rate": 3.305814213263817e-05, + "loss": 3.971, + "step": 1034752 + }, + { + "epoch": 1.01, + "learning_rate": 3.304977256393139e-05, + "loss": 3.9714, + "step": 1035264 + }, + { + "epoch": 1.01, + "learning_rate": 3.304138661642087e-05, + "loss": 3.9763, + "step": 1035776 + }, + { + "epoch": 1.01, + "learning_rate": 3.303300066891035e-05, + "loss": 3.9827, + "step": 1036288 + }, + { + "epoch": 1.01, + "learning_rate": 3.302461472139983e-05, + "loss": 3.9814, + "step": 1036800 + }, + { + "epoch": 1.01, + "learning_rate": 3.301624515269304e-05, + "loss": 3.98, + "step": 1037312 + }, + { + "epoch": 1.01, + "learning_rate": 3.300785920518252e-05, + "loss": 3.9817, + "step": 1037824 + }, + { + "epoch": 1.02, + "learning_rate": 3.2999473257672e-05, + "loss": 3.9787, + "step": 1038336 + }, + { + "epoch": 1.02, + "learning_rate": 3.299108731016148e-05, + "loss": 3.9818, + "step": 1038848 + }, + { + "epoch": 1.02, + "learning_rate": 3.298270136265096e-05, + "loss": 3.9772, + "step": 1039360 + }, + { + "epoch": 1.02, + "learning_rate": 3.297431541514044e-05, + "loss": 3.9891, + "step": 1039872 + }, + { + "epoch": 1.02, + "learning_rate": 3.296592946762992e-05, + "loss": 3.9916, + "step": 1040384 + }, + { + "epoch": 1.02, + "learning_rate": 3.29575435201194e-05, + "loss": 3.9874, + "step": 1040896 + }, + { + "epoch": 1.02, + "learning_rate": 3.2949173951412606e-05, + "loss": 3.9751, + "step": 1041408 + }, + { + "epoch": 1.02, + "learning_rate": 3.294080438270582e-05, + "loss": 3.9767, + "step": 1041920 + }, + { + "epoch": 1.02, + "learning_rate": 3.29324184351953e-05, + "loss": 3.9789, + "step": 1042432 + }, + { + "epoch": 1.02, + "learning_rate": 3.292403248768478e-05, + "loss": 3.9869, + "step": 1042944 + }, + { + "epoch": 1.02, + "learning_rate": 3.291564654017426e-05, + "loss": 3.9859, + "step": 1043456 + }, + { + "epoch": 1.02, + "learning_rate": 3.290726059266374e-05, + "loss": 3.9766, + "step": 1043968 + }, + { + "epoch": 1.02, + "learning_rate": 3.289887464515322e-05, + "loss": 3.9814, + "step": 1044480 + }, + { + "epoch": 1.02, + "learning_rate": 3.2890488697642695e-05, + "loss": 3.9863, + "step": 1044992 + }, + { + "epoch": 1.02, + "learning_rate": 3.2882102750132175e-05, + "loss": 3.9805, + "step": 1045504 + }, + { + "epoch": 1.02, + "learning_rate": 3.2873716802621655e-05, + "loss": 3.98, + "step": 1046016 + }, + { + "epoch": 1.02, + "learning_rate": 3.2865347233914864e-05, + "loss": 3.9722, + "step": 1046528 + }, + { + "epoch": 1.02, + "learning_rate": 3.2856961286404344e-05, + "loss": 3.968, + "step": 1047040 + }, + { + "epoch": 1.02, + "learning_rate": 3.284859171769756e-05, + "loss": 3.9823, + "step": 1047552 + }, + { + "epoch": 1.02, + "learning_rate": 3.284020577018705e-05, + "loss": 3.9719, + "step": 1048064 + }, + { + "epoch": 1.02, + "learning_rate": 3.283181982267652e-05, + "loss": 3.974, + "step": 1048576 + }, + { + "epoch": 1.02, + "learning_rate": 3.2823433875166e-05, + "loss": 3.9749, + "step": 1049088 + }, + { + "epoch": 1.02, + "learning_rate": 3.281504792765548e-05, + "loss": 3.9769, + "step": 1049600 + }, + { + "epoch": 1.02, + "learning_rate": 3.280666198014496e-05, + "loss": 3.9756, + "step": 1050112 + }, + { + "epoch": 1.02, + "learning_rate": 3.279829241143817e-05, + "loss": 3.9849, + "step": 1050624 + }, + { + "epoch": 1.02, + "learning_rate": 3.278990646392765e-05, + "loss": 3.9903, + "step": 1051136 + }, + { + "epoch": 1.02, + "learning_rate": 3.278152051641713e-05, + "loss": 3.9864, + "step": 1051648 + }, + { + "epoch": 1.02, + "learning_rate": 3.277313456890661e-05, + "loss": 3.9892, + "step": 1052160 + }, + { + "epoch": 1.02, + "learning_rate": 3.276476500019982e-05, + "loss": 3.9778, + "step": 1052672 + }, + { + "epoch": 1.02, + "learning_rate": 3.27563790526893e-05, + "loss": 3.9815, + "step": 1053184 + }, + { + "epoch": 1.02, + "learning_rate": 3.2748009483982514e-05, + "loss": 3.9833, + "step": 1053696 + }, + { + "epoch": 1.02, + "learning_rate": 3.2739623536471994e-05, + "loss": 3.9674, + "step": 1054208 + }, + { + "epoch": 1.02, + "learning_rate": 3.2731237588961474e-05, + "loss": 3.9793, + "step": 1054720 + }, + { + "epoch": 1.02, + "learning_rate": 3.2722851641450954e-05, + "loss": 3.9721, + "step": 1055232 + }, + { + "epoch": 1.02, + "learning_rate": 3.2714465693940433e-05, + "loss": 3.9869, + "step": 1055744 + }, + { + "epoch": 1.02, + "learning_rate": 3.2706079746429913e-05, + "loss": 3.9828, + "step": 1056256 + }, + { + "epoch": 1.02, + "learning_rate": 3.269769379891939e-05, + "loss": 3.9813, + "step": 1056768 + }, + { + "epoch": 1.02, + "learning_rate": 3.268930785140887e-05, + "loss": 3.9709, + "step": 1057280 + }, + { + "epoch": 1.02, + "learning_rate": 3.268092190389835e-05, + "loss": 3.9741, + "step": 1057792 + }, + { + "epoch": 1.02, + "learning_rate": 3.267255233519156e-05, + "loss": 3.9857, + "step": 1058304 + }, + { + "epoch": 1.02, + "learning_rate": 3.266416638768104e-05, + "loss": 3.9829, + "step": 1058816 + }, + { + "epoch": 1.02, + "learning_rate": 3.265578044017052e-05, + "loss": 3.9891, + "step": 1059328 + }, + { + "epoch": 1.02, + "learning_rate": 3.264739449266e-05, + "loss": 3.9736, + "step": 1059840 + }, + { + "epoch": 1.02, + "learning_rate": 3.263902492395322e-05, + "loss": 3.9898, + "step": 1060352 + }, + { + "epoch": 1.02, + "learning_rate": 3.26306389764427e-05, + "loss": 3.9819, + "step": 1060864 + }, + { + "epoch": 1.02, + "learning_rate": 3.262225302893218e-05, + "loss": 3.9852, + "step": 1061376 + }, + { + "epoch": 1.02, + "learning_rate": 3.261386708142166e-05, + "loss": 3.9909, + "step": 1061888 + }, + { + "epoch": 1.02, + "learning_rate": 3.260548113391114e-05, + "loss": 3.9803, + "step": 1062400 + }, + { + "epoch": 1.02, + "learning_rate": 3.259709518640062e-05, + "loss": 3.9745, + "step": 1062912 + }, + { + "epoch": 1.02, + "learning_rate": 3.258872561769383e-05, + "loss": 3.9901, + "step": 1063424 + }, + { + "epoch": 1.02, + "learning_rate": 3.258033967018331e-05, + "loss": 3.9726, + "step": 1063936 + }, + { + "epoch": 1.02, + "learning_rate": 3.257195372267279e-05, + "loss": 3.9715, + "step": 1064448 + }, + { + "epoch": 1.02, + "learning_rate": 3.2563584153965996e-05, + "loss": 3.9867, + "step": 1064960 + }, + { + "epoch": 1.02, + "learning_rate": 3.2555198206455476e-05, + "loss": 3.9819, + "step": 1065472 + }, + { + "epoch": 1.02, + "learning_rate": 3.2546812258944956e-05, + "loss": 3.9765, + "step": 1065984 + }, + { + "epoch": 1.02, + "learning_rate": 3.2538426311434436e-05, + "loss": 3.9799, + "step": 1066496 + }, + { + "epoch": 1.02, + "learning_rate": 3.253004036392392e-05, + "loss": 3.9742, + "step": 1067008 + }, + { + "epoch": 1.02, + "learning_rate": 3.252167079521713e-05, + "loss": 3.9913, + "step": 1067520 + }, + { + "epoch": 1.02, + "learning_rate": 3.251328484770661e-05, + "loss": 3.9819, + "step": 1068032 + }, + { + "epoch": 1.03, + "eval_loss": 4.0296406745910645, + "eval_runtime": 290.565, + "eval_samples_per_second": 1313.272, + "eval_steps_per_second": 41.041, + "step": 1068480 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 4.414344315622582e+17, + "trial_name": null, + "trial_params": null +}