diff --git "a/checkpoint-2594880/trainer_state.json" "b/checkpoint-2594880/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2594880/trainer_state.json" @@ -0,0 +1,30705 @@ +{ + "best_metric": 3.9754717350006104, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/full2/lstm/4/checkpoints/checkpoint-2594880", + "epoch": 1.0250006060157382, + "eval_steps": 10, + "global_step": 2594880, + "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 + }, + { + "epoch": 0.0, + "learning_rate": 3.250489890019609e-05, + "loss": 3.9566, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.249651295268557e-05, + "loss": 3.969, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.248812700517505e-05, + "loss": 3.9733, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.2479741057664525e-05, + "loss": 3.9897, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.2471355110154005e-05, + "loss": 3.9823, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.2462969162643485e-05, + "loss": 3.9775, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.2454583215132965e-05, + "loss": 3.9765, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.2446197267622445e-05, + "loss": 3.9778, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.2437811320111924e-05, + "loss": 3.9674, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.2429425372601404e-05, + "loss": 3.9758, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.2421039425090884e-05, + "loss": 3.9785, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.241265347758037e-05, + "loss": 3.9924, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.240428390887358e-05, + "loss": 3.9888, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.239589796136306e-05, + "loss": 3.9557, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.238751201385254e-05, + "loss": 3.9797, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.237912606634202e-05, + "loss": 3.9657, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.23707401188315e-05, + "loss": 3.9779, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.236235417132098e-05, + "loss": 3.975, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.235396822381046e-05, + "loss": 3.979, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.234558227629994e-05, + "loss": 3.9689, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.233719632878941e-05, + "loss": 3.9942, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.232881038127889e-05, + "loss": 3.977, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.232042443376837e-05, + "loss": 3.9767, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.231203848625785e-05, + "loss": 3.9744, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.230365253874734e-05, + "loss": 3.989, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.229528297004055e-05, + "loss": 3.9728, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.228689702253003e-05, + "loss": 3.9707, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.227851107501951e-05, + "loss": 3.971, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.227012512750899e-05, + "loss": 3.9767, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.22617555588022e-05, + "loss": 3.9695, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.2253385990095414e-05, + "loss": 3.9734, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.224500004258489e-05, + "loss": 3.9734, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.223661409507437e-05, + "loss": 3.9837, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.222822814756385e-05, + "loss": 3.9803, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.221984220005333e-05, + "loss": 3.9791, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.221147263134654e-05, + "loss": 3.9811, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.220308668383602e-05, + "loss": 3.9816, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.21947007363255e-05, + "loss": 3.9625, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.218631478881498e-05, + "loss": 3.9706, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.217792884130446e-05, + "loss": 3.9703, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.216954289379394e-05, + "loss": 3.9632, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.216115694628342e-05, + "loss": 3.9766, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.21527709987729e-05, + "loss": 3.9757, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.214440143006611e-05, + "loss": 3.9673, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.213601548255559e-05, + "loss": 3.9795, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.212762953504507e-05, + "loss": 3.9769, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.211924358753455e-05, + "loss": 3.9792, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.211087401882776e-05, + "loss": 3.9755, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.2102504450120976e-05, + "loss": 3.9554, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.2094118502610456e-05, + "loss": 3.9756, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.2085732555099936e-05, + "loss": 3.9742, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.2077346607589416e-05, + "loss": 3.9785, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.2068960660078896e-05, + "loss": 3.9698, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.2060574712568376e-05, + "loss": 3.9677, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.2052188765057856e-05, + "loss": 3.9653, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.2043802817547336e-05, + "loss": 3.9644, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.2035416870036816e-05, + "loss": 3.9714, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.2027030922526296e-05, + "loss": 3.9548, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.2018644975015776e-05, + "loss": 3.9839, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.201025902750525e-05, + "loss": 3.9768, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.2001889458798465e-05, + "loss": 3.9549, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.1993503511287945e-05, + "loss": 3.9851, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.198513394258116e-05, + "loss": 3.96, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.197674799507064e-05, + "loss": 3.964, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.196836204756012e-05, + "loss": 3.9629, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.19599761000496e-05, + "loss": 3.9734, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.1951590152539074e-05, + "loss": 3.9604, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.1943204205028554e-05, + "loss": 3.9771, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.193483463632177e-05, + "loss": 3.9508, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.192644868881125e-05, + "loss": 3.9619, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.191807912010446e-05, + "loss": 3.9775, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.190969317259394e-05, + "loss": 3.9684, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.190130722508342e-05, + "loss": 3.9784, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.18929212775729e-05, + "loss": 3.9712, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.188453533006238e-05, + "loss": 3.9868, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.187614938255186e-05, + "loss": 3.9634, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.186776343504134e-05, + "loss": 3.9809, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.185937748753082e-05, + "loss": 3.9659, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.18509915400203e-05, + "loss": 3.9677, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.184260559250978e-05, + "loss": 3.9697, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.183421964499926e-05, + "loss": 3.9781, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.182583369748874e-05, + "loss": 3.9738, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.181746412878195e-05, + "loss": 3.9814, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.180907818127143e-05, + "loss": 3.9619, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.180069223376091e-05, + "loss": 3.9554, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.179230628625039e-05, + "loss": 3.9636, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.178392033873987e-05, + "loss": 3.9723, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.177555077003308e-05, + "loss": 3.9686, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.176716482252256e-05, + "loss": 3.9643, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.175879525381577e-05, + "loss": 3.9686, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.175042568510898e-05, + "loss": 3.9642, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.174203973759846e-05, + "loss": 3.9698, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.173365379008794e-05, + "loss": 3.9645, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.172526784257742e-05, + "loss": 3.9775, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.17168818950669e-05, + "loss": 3.981, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.170849594755638e-05, + "loss": 3.9784, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.170011000004586e-05, + "loss": 3.9599, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.169172405253534e-05, + "loss": 3.9647, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.168333810502482e-05, + "loss": 3.9654, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.16749521575143e-05, + "loss": 3.9733, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.166656621000379e-05, + "loss": 3.9757, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.165818026249327e-05, + "loss": 3.9608, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.1649810693786476e-05, + "loss": 3.9696, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.1641424746275956e-05, + "loss": 3.9679, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.1633038798765436e-05, + "loss": 3.9711, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.162465285125491e-05, + "loss": 3.9628, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.161626690374439e-05, + "loss": 3.9668, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.1607897335037605e-05, + "loss": 3.9528, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.1599527766330814e-05, + "loss": 3.9709, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.1591141818820294e-05, + "loss": 3.96, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.1582755871309774e-05, + "loss": 3.9632, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.1574369923799254e-05, + "loss": 3.9631, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.1565983976288734e-05, + "loss": 3.966, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.1557598028778214e-05, + "loss": 3.9627, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.1549212081267694e-05, + "loss": 3.9721, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.1540826133757174e-05, + "loss": 3.9775, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.153245656505038e-05, + "loss": 3.9764, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.15240869963436e-05, + "loss": 3.9764, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.151570104883308e-05, + "loss": 3.9645, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.150731510132256e-05, + "loss": 3.9693, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.149892915381203e-05, + "loss": 3.9697, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.149054320630151e-05, + "loss": 3.9534, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.148215725879099e-05, + "loss": 3.9696, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.147377131128048e-05, + "loss": 3.9607, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.146538536376996e-05, + "loss": 3.9767, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.145701579506317e-05, + "loss": 3.9654, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.144862984755265e-05, + "loss": 3.9683, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.144024390004213e-05, + "loss": 3.9621, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.143185795253161e-05, + "loss": 3.9612, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.142348838382482e-05, + "loss": 3.972, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.14151024363143e-05, + "loss": 3.9674, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.140671648880378e-05, + "loss": 3.9772, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.139833054129326e-05, + "loss": 3.9636, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.1389960972586466e-05, + "loss": 3.9766, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.1381575025075946e-05, + "loss": 3.9724, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.137318907756543e-05, + "loss": 3.9716, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.136480313005491e-05, + "loss": 3.9725, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.135641718254439e-05, + "loss": 3.9664, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.134803123503387e-05, + "loss": 3.97, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.133964528752335e-05, + "loss": 3.9744, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.133125934001283e-05, + "loss": 3.9634, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.132288977130604e-05, + "loss": 3.9595, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.131450382379552e-05, + "loss": 3.9696, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.1306117876285e-05, + "loss": 3.9702, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.129773192877448e-05, + "loss": 3.9648, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.128936236006769e-05, + "loss": 3.9674, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.12809927913609e-05, + "loss": 3.9642, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.1272606843850386e-05, + "loss": 3.982, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.1264220896339866e-05, + "loss": 3.9663, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 4.023134231567383, + "eval_runtime": 289.0236, + "eval_samples_per_second": 1320.276, + "eval_steps_per_second": 41.26, + "step": 1144800 + }, + { + "epoch": 1.0, + "learning_rate": 3.1255834948829346e-05, + "loss": 3.9599, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.1247449001318826e-05, + "loss": 3.96, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.1239063053808306e-05, + "loss": 3.9599, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.1230677106297786e-05, + "loss": 3.9765, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.1222291158787266e-05, + "loss": 3.9685, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.1213905211276746e-05, + "loss": 3.9681, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.120551926376622e-05, + "loss": 3.9635, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.1197149695059435e-05, + "loss": 3.9637, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.1188763747548915e-05, + "loss": 3.9566, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.1180377800038395e-05, + "loss": 3.9631, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.117199185252787e-05, + "loss": 3.9645, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.1163622283821084e-05, + "loss": 3.9806, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.11552527151143e-05, + "loss": 3.9777, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.114686676760378e-05, + "loss": 3.9482, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.113848082009326e-05, + "loss": 3.9657, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.113009487258274e-05, + "loss": 3.9542, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.112170892507222e-05, + "loss": 3.9653, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.111332297756169e-05, + "loss": 3.9633, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.110493703005117e-05, + "loss": 3.9682, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.109655108254065e-05, + "loss": 3.9571, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.108816513503013e-05, + "loss": 3.9836, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.107977918751961e-05, + "loss": 3.9662, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.107139324000909e-05, + "loss": 3.9621, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.106300729249857e-05, + "loss": 3.9617, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.105462134498805e-05, + "loss": 3.9777, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.104625177628127e-05, + "loss": 3.9631, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.103786582877075e-05, + "loss": 3.9568, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.102947988126023e-05, + "loss": 3.9639, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.102109393374971e-05, + "loss": 3.9576, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.101272436504292e-05, + "loss": 3.96, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.10043384175324e-05, + "loss": 3.9627, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.099595247002188e-05, + "loss": 3.9617, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.098756652251136e-05, + "loss": 3.9704, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.0979196953804566e-05, + "loss": 3.9648, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.0970811006294046e-05, + "loss": 3.9718, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.0962441437587255e-05, + "loss": 3.9677, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.095405549007674e-05, + "loss": 3.9658, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.094566954256622e-05, + "loss": 3.9516, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.09372835950557e-05, + "loss": 3.9622, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.092889764754518e-05, + "loss": 3.9578, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.092051170003466e-05, + "loss": 3.9557, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.091212575252414e-05, + "loss": 3.9626, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.090373980501362e-05, + "loss": 3.9659, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.08953538575031e-05, + "loss": 3.9537, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.088696790999258e-05, + "loss": 3.9671, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.0878581962482055e-05, + "loss": 3.9674, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.087021239377527e-05, + "loss": 3.966, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.086182644626475e-05, + "loss": 3.964, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.0853440498754224e-05, + "loss": 3.9446, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.084505455124371e-05, + "loss": 3.9625, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.083666860373319e-05, + "loss": 3.9656, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.0828299035026406e-05, + "loss": 3.9654, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.081991308751588e-05, + "loss": 3.9562, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.081152714000536e-05, + "loss": 3.9555, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.080314119249484e-05, + "loss": 3.9526, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.0794771623788055e-05, + "loss": 3.9506, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.078638567627753e-05, + "loss": 3.9656, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.077799972876701e-05, + "loss": 3.9456, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.076961378125649e-05, + "loss": 3.969, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.076122783374597e-05, + "loss": 3.9627, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.075284188623545e-05, + "loss": 3.9509, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.074445593872493e-05, + "loss": 3.9702, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.073606999121441e-05, + "loss": 3.9478, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.072768404370389e-05, + "loss": 3.9523, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.0719314474997104e-05, + "loss": 3.9507, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.0710928527486584e-05, + "loss": 3.9665, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.0702542579976064e-05, + "loss": 3.9469, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.0694156632465544e-05, + "loss": 3.9618, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.068578706375875e-05, + "loss": 3.9389, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.067740111624823e-05, + "loss": 3.9492, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.066901516873771e-05, + "loss": 3.9667, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.066062922122719e-05, + "loss": 3.9619, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.065224327371667e-05, + "loss": 3.9626, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.064385732620615e-05, + "loss": 3.964, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.063547137869563e-05, + "loss": 3.9727, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.062708543118511e-05, + "loss": 3.9542, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.061871586247833e-05, + "loss": 3.9698, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.061032991496781e-05, + "loss": 3.9502, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.060194396745729e-05, + "loss": 3.9578, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.059355801994677e-05, + "loss": 3.9568, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.058517207243624e-05, + "loss": 3.967, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.057680250372946e-05, + "loss": 3.9623, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.056841655621894e-05, + "loss": 3.9724, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.056003060870842e-05, + "loss": 3.9539, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.055164466119789e-05, + "loss": 3.9434, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.0543275092491106e-05, + "loss": 3.9495, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.0534889144980586e-05, + "loss": 3.9621, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.0526503197470066e-05, + "loss": 3.9541, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.0518117249959546e-05, + "loss": 3.9548, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.0509731302449023e-05, + "loss": 3.9595, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.0501345354938503e-05, + "loss": 3.9526, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.0492959407427986e-05, + "loss": 3.9549, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.0484573459917466e-05, + "loss": 3.9535, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.0476203891210675e-05, + "loss": 3.9682, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.0467817943700155e-05, + "loss": 3.9674, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.0459431996189635e-05, + "loss": 3.9641, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.0451046048679115e-05, + "loss": 3.949, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.0442676479972328e-05, + "loss": 3.9574, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.0434290532461808e-05, + "loss": 3.9522, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.0425904584951288e-05, + "loss": 3.9644, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.0417518637440767e-05, + "loss": 3.9634, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.0409149068733977e-05, + "loss": 3.9495, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.0400763121223457e-05, + "loss": 3.959, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.039239355251667e-05, + "loss": 3.96, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.038400760500615e-05, + "loss": 3.9594, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.037562165749563e-05, + "loss": 3.9518, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.036723570998511e-05, + "loss": 3.9543, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.035884976247459e-05, + "loss": 3.9433, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.035046381496407e-05, + "loss": 3.956, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.034207786745355e-05, + "loss": 3.9502, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.033369191994303e-05, + "loss": 3.951, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.032532235123624e-05, + "loss": 3.9495, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.031693640372572e-05, + "loss": 3.9567, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.03085504562152e-05, + "loss": 3.9521, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.030016450870468e-05, + "loss": 3.9553, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.029177856119416e-05, + "loss": 3.969, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.0283408992487373e-05, + "loss": 3.9661, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.0275039423780583e-05, + "loss": 3.9637, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.0266653476270063e-05, + "loss": 3.9536, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.0258267528759542e-05, + "loss": 3.9576, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.0249881581249022e-05, + "loss": 3.9574, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.0241495633738502e-05, + "loss": 3.9483, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.0233109686227982e-05, + "loss": 3.9548, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.0224723738717466e-05, + "loss": 3.9511, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.0216337791206946e-05, + "loss": 3.9603, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.0207951843696426e-05, + "loss": 3.9541, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.01995658961859e-05, + "loss": 3.96, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.019117994867538e-05, + "loss": 3.9547, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.018279400116486e-05, + "loss": 3.9507, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.0174424432458075e-05, + "loss": 3.9542, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.016603848494755e-05, + "loss": 3.9631, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.015765253743703e-05, + "loss": 3.9625, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.014926658992651e-05, + "loss": 3.956, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.0140913400023456e-05, + "loss": 3.9645, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.0132527452512936e-05, + "loss": 3.9589, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.012414150500242e-05, + "loss": 3.9631, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.01157555574919e-05, + "loss": 3.9608, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.0107369609981372e-05, + "loss": 3.956, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.0098983662470852e-05, + "loss": 3.9567, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.0090597714960332e-05, + "loss": 3.9639, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.0082211767449812e-05, + "loss": 3.9548, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.0073842198743025e-05, + "loss": 3.949, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.0065456251232505e-05, + "loss": 3.9578, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.0057070303721985e-05, + "loss": 3.9601, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.0048684356211465e-05, + "loss": 3.9506, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.0040298408700945e-05, + "loss": 3.9613, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.0031912461190425e-05, + "loss": 3.9527, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.0023559271287373e-05, + "loss": 3.9678, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.0015173323776846e-05, + "loss": 3.9561, + "step": 1220608 + }, + { + "epoch": 1.03, + "learning_rate": 3.0006787376266326e-05, + "loss": 3.9521, + "step": 1221120 + }, + { + "epoch": 1.03, + "eval_loss": 4.017483234405518, + "eval_runtime": 288.3887, + "eval_samples_per_second": 1323.183, + "eval_steps_per_second": 41.35, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 2.9998401428755806e-05, + "loss": 3.9466, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.9990015481245286e-05, + "loss": 3.9455, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.9981629533734766e-05, + "loss": 3.9638, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.997324358622425e-05, + "loss": 3.9621, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.996485763871373e-05, + "loss": 3.9576, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.995647169120321e-05, + "loss": 3.9527, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.994808574369269e-05, + "loss": 3.9517, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.993969979618217e-05, + "loss": 3.9399, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.993131384867165e-05, + "loss": 3.9589, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.992292790116113e-05, + "loss": 3.9502, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.991454195365061e-05, + "loss": 3.9752, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.990617238494382e-05, + "loss": 3.967, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.98977864374333e-05, + "loss": 3.9363, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.988940048992278e-05, + "loss": 3.9509, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.988101454241226e-05, + "loss": 3.9487, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.9872628594901735e-05, + "loss": 3.9495, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.9864242647391218e-05, + "loss": 3.9549, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.985587307868443e-05, + "loss": 3.9556, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.9847487131173914e-05, + "loss": 3.9476, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.9839101183663387e-05, + "loss": 3.9719, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.9830715236152867e-05, + "loss": 3.953, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.9822329288642347e-05, + "loss": 3.9559, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.9813943341131827e-05, + "loss": 3.9514, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.9805557393621307e-05, + "loss": 3.9674, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.979717144611079e-05, + "loss": 3.9526, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.978878549860027e-05, + "loss": 3.947, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.978039955108975e-05, + "loss": 3.9514, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.977202998238296e-05, + "loss": 3.9488, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.976364403487244e-05, + "loss": 3.9492, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.975525808736192e-05, + "loss": 3.9485, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.97468721398514e-05, + "loss": 3.9529, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.9738486192340882e-05, + "loss": 3.9589, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.9730100244830362e-05, + "loss": 3.9552, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.9721714297319842e-05, + "loss": 3.959, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.971334472861305e-05, + "loss": 3.9589, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.970495878110253e-05, + "loss": 3.9575, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.969657283359201e-05, + "loss": 3.9433, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.968818688608149e-05, + "loss": 3.9498, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.9679800938570975e-05, + "loss": 3.9458, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.9671431369864184e-05, + "loss": 3.9485, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.9663045422353664e-05, + "loss": 3.9476, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.9654659474843144e-05, + "loss": 3.9546, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.9646273527332624e-05, + "loss": 3.9448, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.96378875798221e-05, + "loss": 3.9573, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.962950163231158e-05, + "loss": 3.9553, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.962111568480106e-05, + "loss": 3.9581, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.961274611609427e-05, + "loss": 3.9531, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.960436016858375e-05, + "loss": 3.9348, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.959597422107323e-05, + "loss": 3.9432, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.9587588273562712e-05, + "loss": 3.9635, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.9579202326052192e-05, + "loss": 3.9518, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.9570816378541672e-05, + "loss": 3.9451, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.956244680983488e-05, + "loss": 3.943, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.955406086232436e-05, + "loss": 3.9483, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.954567491481384e-05, + "loss": 3.9376, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.953728896730332e-05, + "loss": 3.957, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.9528903019792805e-05, + "loss": 3.9348, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.9520517072282285e-05, + "loss": 3.9514, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.9512131124771764e-05, + "loss": 3.9531, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.9503745177261244e-05, + "loss": 3.9383, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.9495375608554454e-05, + "loss": 3.9577, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.9486989661043933e-05, + "loss": 3.9392, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.9478603713533413e-05, + "loss": 3.9464, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.9470217766022897e-05, + "loss": 3.9353, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.9461848197316106e-05, + "loss": 3.9583, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.9453462249805586e-05, + "loss": 3.941, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.9445076302295066e-05, + "loss": 3.9448, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.9436690354784546e-05, + "loss": 3.9334, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.9428304407274026e-05, + "loss": 3.9393, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.9419934838567238e-05, + "loss": 3.9536, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.9411548891056718e-05, + "loss": 3.9542, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.9403162943546198e-05, + "loss": 3.9506, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.9394793374839407e-05, + "loss": 3.9522, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.9386407427328887e-05, + "loss": 3.9592, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.9378021479818367e-05, + "loss": 3.9437, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.936965191111158e-05, + "loss": 3.9606, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.936126596360106e-05, + "loss": 3.9431, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.935288001609054e-05, + "loss": 3.946, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.934449406858002e-05, + "loss": 3.9466, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.93361081210695e-05, + "loss": 3.9549, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.932772217355898e-05, + "loss": 3.9517, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.931933622604846e-05, + "loss": 3.9633, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.9310950278537936e-05, + "loss": 3.9462, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.9302564331027416e-05, + "loss": 3.9299, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.9294178383516896e-05, + "loss": 3.9396, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.9285792436006376e-05, + "loss": 3.9495, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.9277422867299585e-05, + "loss": 3.9432, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.9269036919789068e-05, + "loss": 3.9455, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.9260650972278548e-05, + "loss": 3.9507, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.9252265024768028e-05, + "loss": 3.9403, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.9243879077257508e-05, + "loss": 3.9471, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.9235493129746988e-05, + "loss": 3.9437, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.9227107182236468e-05, + "loss": 3.9564, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.9218737613529677e-05, + "loss": 3.9568, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.921035166601916e-05, + "loss": 3.9551, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.920196571850864e-05, + "loss": 3.9358, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.919357977099812e-05, + "loss": 3.9466, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.91851938234876e-05, + "loss": 3.9447, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.917680787597708e-05, + "loss": 3.9505, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.916842192846656e-05, + "loss": 3.955, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.916003598095604e-05, + "loss": 3.9398, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.9151666412249253e-05, + "loss": 3.946, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.9143280464738733e-05, + "loss": 3.9509, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.9134894517228213e-05, + "loss": 3.9497, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.9126508569717692e-05, + "loss": 3.9398, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.91181390010109e-05, + "loss": 3.9452, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.910975305350038e-05, + "loss": 3.9375, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.910136710598986e-05, + "loss": 3.9411, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.9092981158479345e-05, + "loss": 3.9389, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.9084595210968818e-05, + "loss": 3.942, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.9076209263458298e-05, + "loss": 3.9385, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.9067823315947778e-05, + "loss": 3.9471, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.9059437368437258e-05, + "loss": 3.9396, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.905106779973047e-05, + "loss": 3.9461, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.904268185221995e-05, + "loss": 3.9576, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.903429590470943e-05, + "loss": 3.9562, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.902590995719891e-05, + "loss": 3.9503, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.901754038849212e-05, + "loss": 3.9468, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.90091544409816e-05, + "loss": 3.9453, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.9000768493471083e-05, + "loss": 3.9465, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.8992382545960563e-05, + "loss": 3.9372, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.8983996598450043e-05, + "loss": 3.9428, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.897562702974325e-05, + "loss": 3.9436, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.896724108223273e-05, + "loss": 3.9496, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.895885513472221e-05, + "loss": 3.9441, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.895046918721169e-05, + "loss": 3.9499, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.8942083239701175e-05, + "loss": 3.9437, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.8933697292190655e-05, + "loss": 3.9422, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.8925311344680135e-05, + "loss": 3.939, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.8916925397169615e-05, + "loss": 3.9567, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.8908555828462824e-05, + "loss": 3.9511, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.8900169880952304e-05, + "loss": 3.9445, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.8891783933441784e-05, + "loss": 3.9493, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.8883397985931264e-05, + "loss": 3.9509, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.8875028417224476e-05, + "loss": 3.9508, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.8866642469713956e-05, + "loss": 3.954, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.8858272901007165e-05, + "loss": 3.9444, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.8849886953496645e-05, + "loss": 3.9482, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.8841501005986125e-05, + "loss": 3.9481, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.883311505847561e-05, + "loss": 3.9435, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.882472911096509e-05, + "loss": 3.9432, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.8816359542258298e-05, + "loss": 3.9434, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.8807973594747777e-05, + "loss": 3.9527, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.8799587647237257e-05, + "loss": 3.9389, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.8791201699726737e-05, + "loss": 3.9516, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.8782815752216217e-05, + "loss": 3.9436, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.87744298047057e-05, + "loss": 3.9509, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.876606023599891e-05, + "loss": 3.9533, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.875767428848839e-05, + "loss": 3.9375, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 4.012016773223877, + "eval_runtime": 293.2633, + "eval_samples_per_second": 1301.189, + "eval_steps_per_second": 40.663, + "step": 1297440 + }, + { + "epoch": 1.0, + "learning_rate": 2.874928834097787e-05, + "loss": 3.9376, + "step": 1297920 + }, + { + "epoch": 1.0, + "learning_rate": 2.874090239346735e-05, + "loss": 3.9355, + "step": 1298432 + }, + { + "epoch": 1.0, + "learning_rate": 2.873251644595683e-05, + "loss": 3.9546, + "step": 1298944 + }, + { + "epoch": 1.0, + "learning_rate": 2.8724130498446306e-05, + "loss": 3.9459, + "step": 1299456 + }, + { + "epoch": 1.0, + "learning_rate": 2.8715744550935786e-05, + "loss": 3.9484, + "step": 1299968 + }, + { + "epoch": 1.0, + "learning_rate": 2.8707358603425266e-05, + "loss": 3.9456, + "step": 1300480 + }, + { + "epoch": 1.0, + "learning_rate": 2.8698989034718482e-05, + "loss": 3.9368, + "step": 1300992 + }, + { + "epoch": 1.0, + "learning_rate": 2.8690603087207955e-05, + "loss": 3.9353, + "step": 1301504 + }, + { + "epoch": 1.0, + "learning_rate": 2.868221713969744e-05, + "loss": 3.9458, + "step": 1302016 + }, + { + "epoch": 1.0, + "learning_rate": 2.867383119218692e-05, + "loss": 3.939, + "step": 1302528 + }, + { + "epoch": 1.0, + "learning_rate": 2.86654452446764e-05, + "loss": 3.9644, + "step": 1303040 + }, + { + "epoch": 1.0, + "learning_rate": 2.8657092054773343e-05, + "loss": 3.9515, + "step": 1303552 + }, + { + "epoch": 1.0, + "learning_rate": 2.8648722486066553e-05, + "loss": 3.9331, + "step": 1304064 + }, + { + "epoch": 1.0, + "learning_rate": 2.8640336538556032e-05, + "loss": 3.9381, + "step": 1304576 + }, + { + "epoch": 1.0, + "learning_rate": 2.8631950591045516e-05, + "loss": 3.942, + "step": 1305088 + }, + { + "epoch": 1.0, + "learning_rate": 2.8623564643534996e-05, + "loss": 3.9335, + "step": 1305600 + }, + { + "epoch": 1.0, + "learning_rate": 2.8615178696024476e-05, + "loss": 3.9468, + "step": 1306112 + }, + { + "epoch": 1.0, + "learning_rate": 2.860679274851395e-05, + "loss": 3.9447, + "step": 1306624 + }, + { + "epoch": 1.0, + "learning_rate": 2.859840680100343e-05, + "loss": 3.9369, + "step": 1307136 + }, + { + "epoch": 1.0, + "learning_rate": 2.859002085349291e-05, + "loss": 3.9619, + "step": 1307648 + }, + { + "epoch": 1.0, + "learning_rate": 2.8581651284786125e-05, + "loss": 3.9419, + "step": 1308160 + }, + { + "epoch": 1.0, + "learning_rate": 2.85732653372756e-05, + "loss": 3.9457, + "step": 1308672 + }, + { + "epoch": 1.0, + "learning_rate": 2.856487938976508e-05, + "loss": 3.9402, + "step": 1309184 + }, + { + "epoch": 1.0, + "learning_rate": 2.8556509821058297e-05, + "loss": 3.9577, + "step": 1309696 + }, + { + "epoch": 1.0, + "learning_rate": 2.8548123873547777e-05, + "loss": 3.9373, + "step": 1310208 + }, + { + "epoch": 1.0, + "learning_rate": 2.8539737926037254e-05, + "loss": 3.9399, + "step": 1310720 + }, + { + "epoch": 1.0, + "learning_rate": 2.8531351978526734e-05, + "loss": 3.9351, + "step": 1311232 + }, + { + "epoch": 1.0, + "learning_rate": 2.8522966031016214e-05, + "loss": 3.94, + "step": 1311744 + }, + { + "epoch": 1.0, + "learning_rate": 2.8514580083505693e-05, + "loss": 3.9376, + "step": 1312256 + }, + { + "epoch": 1.01, + "learning_rate": 2.8506194135995173e-05, + "loss": 3.9409, + "step": 1312768 + }, + { + "epoch": 1.01, + "learning_rate": 2.8497808188484653e-05, + "loss": 3.945, + "step": 1313280 + }, + { + "epoch": 1.01, + "learning_rate": 2.8489422240974133e-05, + "loss": 3.9449, + "step": 1313792 + }, + { + "epoch": 1.01, + "learning_rate": 2.8481036293463613e-05, + "loss": 3.9427, + "step": 1314304 + }, + { + "epoch": 1.01, + "learning_rate": 2.8472650345953093e-05, + "loss": 3.9492, + "step": 1314816 + }, + { + "epoch": 1.01, + "learning_rate": 2.8464280777246306e-05, + "loss": 3.9444, + "step": 1315328 + }, + { + "epoch": 1.01, + "learning_rate": 2.8455894829735786e-05, + "loss": 3.9455, + "step": 1315840 + }, + { + "epoch": 1.01, + "learning_rate": 2.8447508882225266e-05, + "loss": 3.9336, + "step": 1316352 + }, + { + "epoch": 1.01, + "learning_rate": 2.8439122934714746e-05, + "loss": 3.94, + "step": 1316864 + }, + { + "epoch": 1.01, + "learning_rate": 2.8430736987204226e-05, + "loss": 3.9332, + "step": 1317376 + }, + { + "epoch": 1.01, + "learning_rate": 2.8422351039693706e-05, + "loss": 3.9395, + "step": 1317888 + }, + { + "epoch": 1.01, + "learning_rate": 2.8413965092183185e-05, + "loss": 3.9367, + "step": 1318400 + }, + { + "epoch": 1.01, + "learning_rate": 2.840557914467267e-05, + "loss": 3.9466, + "step": 1318912 + }, + { + "epoch": 1.01, + "learning_rate": 2.8397209575965878e-05, + "loss": 3.9293, + "step": 1319424 + }, + { + "epoch": 1.01, + "learning_rate": 2.8388823628455358e-05, + "loss": 3.9479, + "step": 1319936 + }, + { + "epoch": 1.01, + "learning_rate": 2.8380437680944838e-05, + "loss": 3.9452, + "step": 1320448 + }, + { + "epoch": 1.01, + "learning_rate": 2.8372068112238047e-05, + "loss": 3.9469, + "step": 1320960 + }, + { + "epoch": 1.01, + "learning_rate": 2.836368216472753e-05, + "loss": 3.9417, + "step": 1321472 + }, + { + "epoch": 1.01, + "learning_rate": 2.835531259602074e-05, + "loss": 3.9267, + "step": 1321984 + }, + { + "epoch": 1.01, + "learning_rate": 2.834692664851022e-05, + "loss": 3.9364, + "step": 1322496 + }, + { + "epoch": 1.01, + "learning_rate": 2.83385407009997e-05, + "loss": 3.95, + "step": 1323008 + }, + { + "epoch": 1.01, + "learning_rate": 2.833015475348918e-05, + "loss": 3.9378, + "step": 1323520 + }, + { + "epoch": 1.01, + "learning_rate": 2.832176880597866e-05, + "loss": 3.936, + "step": 1324032 + }, + { + "epoch": 1.01, + "learning_rate": 2.831338285846814e-05, + "loss": 3.9309, + "step": 1324544 + }, + { + "epoch": 1.01, + "learning_rate": 2.8304996910957616e-05, + "loss": 3.9414, + "step": 1325056 + }, + { + "epoch": 1.01, + "learning_rate": 2.8296610963447096e-05, + "loss": 3.9229, + "step": 1325568 + }, + { + "epoch": 1.01, + "learning_rate": 2.8288225015936576e-05, + "loss": 3.9512, + "step": 1326080 + }, + { + "epoch": 1.01, + "learning_rate": 2.8279839068426056e-05, + "loss": 3.9233, + "step": 1326592 + }, + { + "epoch": 1.01, + "learning_rate": 2.8271453120915536e-05, + "loss": 3.9439, + "step": 1327104 + }, + { + "epoch": 1.01, + "learning_rate": 2.8263067173405015e-05, + "loss": 3.9402, + "step": 1327616 + }, + { + "epoch": 1.01, + "learning_rate": 2.8254681225894495e-05, + "loss": 3.9308, + "step": 1328128 + }, + { + "epoch": 1.01, + "learning_rate": 2.824629527838398e-05, + "loss": 3.9439, + "step": 1328640 + }, + { + "epoch": 1.01, + "learning_rate": 2.8237925709677188e-05, + "loss": 3.935, + "step": 1329152 + }, + { + "epoch": 1.01, + "learning_rate": 2.8229539762166668e-05, + "loss": 3.9336, + "step": 1329664 + }, + { + "epoch": 1.01, + "learning_rate": 2.8221153814656148e-05, + "loss": 3.9235, + "step": 1330176 + }, + { + "epoch": 1.01, + "learning_rate": 2.8212767867145628e-05, + "loss": 3.951, + "step": 1330688 + }, + { + "epoch": 1.01, + "learning_rate": 2.8204381919635108e-05, + "loss": 3.9274, + "step": 1331200 + }, + { + "epoch": 1.01, + "learning_rate": 2.819601235092832e-05, + "loss": 3.9366, + "step": 1331712 + }, + { + "epoch": 1.01, + "learning_rate": 2.818764278222153e-05, + "loss": 3.9195, + "step": 1332224 + }, + { + "epoch": 1.01, + "learning_rate": 2.817925683471101e-05, + "loss": 3.9319, + "step": 1332736 + }, + { + "epoch": 1.01, + "learning_rate": 2.817087088720049e-05, + "loss": 3.9412, + "step": 1333248 + }, + { + "epoch": 1.01, + "learning_rate": 2.816248493968997e-05, + "loss": 3.944, + "step": 1333760 + }, + { + "epoch": 1.01, + "learning_rate": 2.815409899217945e-05, + "loss": 3.9395, + "step": 1334272 + }, + { + "epoch": 1.01, + "learning_rate": 2.8145713044668932e-05, + "loss": 3.9445, + "step": 1334784 + }, + { + "epoch": 1.01, + "learning_rate": 2.8137327097158412e-05, + "loss": 3.9468, + "step": 1335296 + }, + { + "epoch": 1.01, + "learning_rate": 2.8128941149647892e-05, + "loss": 3.9379, + "step": 1335808 + }, + { + "epoch": 1.01, + "learning_rate": 2.81205715809411e-05, + "loss": 3.9464, + "step": 1336320 + }, + { + "epoch": 1.01, + "learning_rate": 2.811218563343058e-05, + "loss": 3.934, + "step": 1336832 + }, + { + "epoch": 1.01, + "learning_rate": 2.810379968592006e-05, + "loss": 3.938, + "step": 1337344 + }, + { + "epoch": 1.01, + "learning_rate": 2.809541373840954e-05, + "loss": 3.9339, + "step": 1337856 + }, + { + "epoch": 1.01, + "learning_rate": 2.8087027790899025e-05, + "loss": 3.9431, + "step": 1338368 + }, + { + "epoch": 1.01, + "learning_rate": 2.8078641843388498e-05, + "loss": 3.9441, + "step": 1338880 + }, + { + "epoch": 1.01, + "learning_rate": 2.8070272274681714e-05, + "loss": 3.9512, + "step": 1339392 + }, + { + "epoch": 1.01, + "learning_rate": 2.8061886327171194e-05, + "loss": 3.9392, + "step": 1339904 + }, + { + "epoch": 1.01, + "learning_rate": 2.8053516758464403e-05, + "loss": 3.9194, + "step": 1340416 + }, + { + "epoch": 1.01, + "learning_rate": 2.8045130810953886e-05, + "loss": 3.928, + "step": 1340928 + }, + { + "epoch": 1.01, + "learning_rate": 2.8036744863443366e-05, + "loss": 3.9376, + "step": 1341440 + }, + { + "epoch": 1.01, + "learning_rate": 2.8028358915932846e-05, + "loss": 3.9356, + "step": 1341952 + }, + { + "epoch": 1.01, + "learning_rate": 2.8019989347226055e-05, + "loss": 3.9336, + "step": 1342464 + }, + { + "epoch": 1.01, + "learning_rate": 2.8011603399715535e-05, + "loss": 3.9419, + "step": 1342976 + }, + { + "epoch": 1.02, + "learning_rate": 2.8003217452205015e-05, + "loss": 3.9277, + "step": 1343488 + }, + { + "epoch": 1.02, + "learning_rate": 2.7994831504694495e-05, + "loss": 3.932, + "step": 1344000 + }, + { + "epoch": 1.02, + "learning_rate": 2.798644555718397e-05, + "loss": 3.9365, + "step": 1344512 + }, + { + "epoch": 1.02, + "learning_rate": 2.797805960967345e-05, + "loss": 3.9452, + "step": 1345024 + }, + { + "epoch": 1.02, + "learning_rate": 2.796967366216293e-05, + "loss": 3.9449, + "step": 1345536 + }, + { + "epoch": 1.02, + "learning_rate": 2.7961304093456147e-05, + "loss": 3.9493, + "step": 1346048 + }, + { + "epoch": 1.02, + "learning_rate": 2.7952918145945624e-05, + "loss": 3.9265, + "step": 1346560 + }, + { + "epoch": 1.02, + "learning_rate": 2.7944532198435104e-05, + "loss": 3.9365, + "step": 1347072 + }, + { + "epoch": 1.02, + "learning_rate": 2.7936146250924584e-05, + "loss": 3.9383, + "step": 1347584 + }, + { + "epoch": 1.02, + "learning_rate": 2.7927760303414064e-05, + "loss": 3.9375, + "step": 1348096 + }, + { + "epoch": 1.02, + "learning_rate": 2.7919374355903544e-05, + "loss": 3.9495, + "step": 1348608 + }, + { + "epoch": 1.02, + "learning_rate": 2.7910988408393024e-05, + "loss": 3.9298, + "step": 1349120 + }, + { + "epoch": 1.02, + "learning_rate": 2.7902602460882504e-05, + "loss": 3.9347, + "step": 1349632 + }, + { + "epoch": 1.02, + "learning_rate": 2.7894232892175716e-05, + "loss": 3.9414, + "step": 1350144 + }, + { + "epoch": 1.02, + "learning_rate": 2.7885846944665196e-05, + "loss": 3.9408, + "step": 1350656 + }, + { + "epoch": 1.02, + "learning_rate": 2.7877460997154676e-05, + "loss": 3.9253, + "step": 1351168 + }, + { + "epoch": 1.02, + "learning_rate": 2.7869091428447885e-05, + "loss": 3.9381, + "step": 1351680 + }, + { + "epoch": 1.02, + "learning_rate": 2.7860705480937365e-05, + "loss": 3.9299, + "step": 1352192 + }, + { + "epoch": 1.02, + "learning_rate": 2.7852319533426845e-05, + "loss": 3.9298, + "step": 1352704 + }, + { + "epoch": 1.02, + "learning_rate": 2.7843933585916325e-05, + "loss": 3.9291, + "step": 1353216 + }, + { + "epoch": 1.02, + "learning_rate": 2.783554763840581e-05, + "loss": 3.9328, + "step": 1353728 + }, + { + "epoch": 1.02, + "learning_rate": 2.7827161690895288e-05, + "loss": 3.9291, + "step": 1354240 + }, + { + "epoch": 1.02, + "learning_rate": 2.7818775743384768e-05, + "loss": 3.9392, + "step": 1354752 + }, + { + "epoch": 1.02, + "learning_rate": 2.7810389795874248e-05, + "loss": 3.9266, + "step": 1355264 + }, + { + "epoch": 1.02, + "learning_rate": 2.7802003848363728e-05, + "loss": 3.9364, + "step": 1355776 + }, + { + "epoch": 1.02, + "learning_rate": 2.7793634279656937e-05, + "loss": 3.9497, + "step": 1356288 + }, + { + "epoch": 1.02, + "learning_rate": 2.7785248332146417e-05, + "loss": 3.9425, + "step": 1356800 + }, + { + "epoch": 1.02, + "learning_rate": 2.7776862384635897e-05, + "loss": 3.9431, + "step": 1357312 + }, + { + "epoch": 1.02, + "learning_rate": 2.776849281592911e-05, + "loss": 3.9369, + "step": 1357824 + }, + { + "epoch": 1.02, + "learning_rate": 2.776010686841859e-05, + "loss": 3.9348, + "step": 1358336 + }, + { + "epoch": 1.02, + "learning_rate": 2.775172092090807e-05, + "loss": 3.9354, + "step": 1358848 + }, + { + "epoch": 1.02, + "learning_rate": 2.774335135220128e-05, + "loss": 3.9306, + "step": 1359360 + }, + { + "epoch": 1.02, + "learning_rate": 2.7734965404690762e-05, + "loss": 3.9295, + "step": 1359872 + }, + { + "epoch": 1.02, + "learning_rate": 2.7726579457180242e-05, + "loss": 3.9354, + "step": 1360384 + }, + { + "epoch": 1.02, + "learning_rate": 2.7718193509669722e-05, + "loss": 3.9402, + "step": 1360896 + }, + { + "epoch": 1.02, + "learning_rate": 2.7709807562159202e-05, + "loss": 3.9402, + "step": 1361408 + }, + { + "epoch": 1.02, + "learning_rate": 2.7701421614648682e-05, + "loss": 3.9349, + "step": 1361920 + }, + { + "epoch": 1.02, + "learning_rate": 2.7693035667138162e-05, + "loss": 3.9361, + "step": 1362432 + }, + { + "epoch": 1.02, + "learning_rate": 2.7684649719627635e-05, + "loss": 3.93, + "step": 1362944 + }, + { + "epoch": 1.02, + "learning_rate": 2.767626377211712e-05, + "loss": 3.9279, + "step": 1363456 + }, + { + "epoch": 1.02, + "learning_rate": 2.7667877824606598e-05, + "loss": 3.9491, + "step": 1363968 + }, + { + "epoch": 1.02, + "learning_rate": 2.7659491877096078e-05, + "loss": 3.9422, + "step": 1364480 + }, + { + "epoch": 1.02, + "learning_rate": 2.7651105929585558e-05, + "loss": 3.9398, + "step": 1364992 + }, + { + "epoch": 1.02, + "learning_rate": 2.7642736360878767e-05, + "loss": 3.9362, + "step": 1365504 + }, + { + "epoch": 1.02, + "learning_rate": 2.7634350413368247e-05, + "loss": 3.9407, + "step": 1366016 + }, + { + "epoch": 1.02, + "learning_rate": 2.762598084466146e-05, + "loss": 3.9396, + "step": 1366528 + }, + { + "epoch": 1.02, + "learning_rate": 2.761759489715094e-05, + "loss": 3.9478, + "step": 1367040 + }, + { + "epoch": 1.02, + "learning_rate": 2.760920894964042e-05, + "loss": 3.9377, + "step": 1367552 + }, + { + "epoch": 1.02, + "learning_rate": 2.76008230021299e-05, + "loss": 3.9359, + "step": 1368064 + }, + { + "epoch": 1.02, + "learning_rate": 2.759243705461938e-05, + "loss": 3.9374, + "step": 1368576 + }, + { + "epoch": 1.02, + "learning_rate": 2.758405110710886e-05, + "loss": 3.9352, + "step": 1369088 + }, + { + "epoch": 1.02, + "learning_rate": 2.7575681538402072e-05, + "loss": 3.9308, + "step": 1369600 + }, + { + "epoch": 1.02, + "learning_rate": 2.7567295590891552e-05, + "loss": 3.9368, + "step": 1370112 + }, + { + "epoch": 1.02, + "learning_rate": 2.7558909643381032e-05, + "loss": 3.9429, + "step": 1370624 + }, + { + "epoch": 1.02, + "learning_rate": 2.7550523695870512e-05, + "loss": 3.9279, + "step": 1371136 + }, + { + "epoch": 1.02, + "learning_rate": 2.7542137748359992e-05, + "loss": 3.9455, + "step": 1371648 + }, + { + "epoch": 1.02, + "learning_rate": 2.7533751800849472e-05, + "loss": 3.9372, + "step": 1372160 + }, + { + "epoch": 1.02, + "learning_rate": 2.7525365853338952e-05, + "loss": 3.9392, + "step": 1372672 + }, + { + "epoch": 1.02, + "learning_rate": 2.751697990582843e-05, + "loss": 3.9409, + "step": 1373184 + }, + { + "epoch": 1.02, + "learning_rate": 2.7508610337121644e-05, + "loss": 3.929, + "step": 1373696 + }, + { + "epoch": 1.03, + "eval_loss": 4.007248401641846, + "eval_runtime": 292.7931, + "eval_samples_per_second": 1303.279, + "eval_steps_per_second": 40.728, + "step": 1373760 + }, + { + "epoch": 0.0, + "learning_rate": 2.7500240768414853e-05, + "loss": 3.9259, + "step": 1374208 + }, + { + "epoch": 0.0, + "learning_rate": 2.7491854820904333e-05, + "loss": 3.9272, + "step": 1374720 + }, + { + "epoch": 0.0, + "learning_rate": 2.7483468873393813e-05, + "loss": 3.944, + "step": 1375232 + }, + { + "epoch": 0.0, + "learning_rate": 2.7475082925883293e-05, + "loss": 3.935, + "step": 1375744 + }, + { + "epoch": 0.0, + "learning_rate": 2.7466696978372773e-05, + "loss": 3.9438, + "step": 1376256 + }, + { + "epoch": 0.0, + "learning_rate": 2.7458311030862256e-05, + "loss": 3.9318, + "step": 1376768 + }, + { + "epoch": 0.0, + "learning_rate": 2.7449925083351736e-05, + "loss": 3.9329, + "step": 1377280 + }, + { + "epoch": 0.0, + "learning_rate": 2.7441539135841216e-05, + "loss": 3.9239, + "step": 1377792 + }, + { + "epoch": 0.0, + "learning_rate": 2.7433153188330696e-05, + "loss": 3.9363, + "step": 1378304 + }, + { + "epoch": 0.0, + "learning_rate": 2.742476724082017e-05, + "loss": 3.9307, + "step": 1378816 + }, + { + "epoch": 0.0, + "learning_rate": 2.741638129330965e-05, + "loss": 3.9509, + "step": 1379328 + }, + { + "epoch": 0.0, + "learning_rate": 2.7407995345799133e-05, + "loss": 3.9427, + "step": 1379840 + }, + { + "epoch": 0.0, + "learning_rate": 2.739962577709235e-05, + "loss": 3.9241, + "step": 1380352 + }, + { + "epoch": 0.0, + "learning_rate": 2.7391239829581822e-05, + "loss": 3.9287, + "step": 1380864 + }, + { + "epoch": 0.0, + "learning_rate": 2.7382853882071302e-05, + "loss": 3.9358, + "step": 1381376 + }, + { + "epoch": 0.0, + "learning_rate": 2.7374467934560782e-05, + "loss": 3.9221, + "step": 1381888 + }, + { + "epoch": 0.0, + "learning_rate": 2.736608198705026e-05, + "loss": 3.9347, + "step": 1382400 + }, + { + "epoch": 0.0, + "learning_rate": 2.735769603953974e-05, + "loss": 3.9346, + "step": 1382912 + }, + { + "epoch": 0.0, + "learning_rate": 2.7349326470832954e-05, + "loss": 3.9269, + "step": 1383424 + }, + { + "epoch": 0.0, + "learning_rate": 2.7340940523322434e-05, + "loss": 3.9551, + "step": 1383936 + }, + { + "epoch": 0.0, + "learning_rate": 2.7332554575811914e-05, + "loss": 3.9305, + "step": 1384448 + }, + { + "epoch": 0.0, + "learning_rate": 2.7324168628301394e-05, + "loss": 3.939, + "step": 1384960 + }, + { + "epoch": 0.0, + "learning_rate": 2.7315782680790874e-05, + "loss": 3.9314, + "step": 1385472 + }, + { + "epoch": 0.0, + "learning_rate": 2.7307396733280354e-05, + "loss": 3.9491, + "step": 1385984 + }, + { + "epoch": 0.0, + "learning_rate": 2.7299010785769834e-05, + "loss": 3.923, + "step": 1386496 + }, + { + "epoch": 0.0, + "learning_rate": 2.7290624838259314e-05, + "loss": 3.9321, + "step": 1387008 + }, + { + "epoch": 0.0, + "learning_rate": 2.7282238890748797e-05, + "loss": 3.9233, + "step": 1387520 + }, + { + "epoch": 0.0, + "learning_rate": 2.7273852943238277e-05, + "loss": 3.9349, + "step": 1388032 + }, + { + "epoch": 0.0, + "learning_rate": 2.7265466995727757e-05, + "loss": 3.9282, + "step": 1388544 + }, + { + "epoch": 0.01, + "learning_rate": 2.7257097427020966e-05, + "loss": 3.9281, + "step": 1389056 + }, + { + "epoch": 0.01, + "learning_rate": 2.7248711479510446e-05, + "loss": 3.9363, + "step": 1389568 + }, + { + "epoch": 0.01, + "learning_rate": 2.7240325531999926e-05, + "loss": 3.9385, + "step": 1390080 + }, + { + "epoch": 0.01, + "learning_rate": 2.7231939584489406e-05, + "loss": 3.9304, + "step": 1390592 + }, + { + "epoch": 0.01, + "learning_rate": 2.7223586394586348e-05, + "loss": 3.9468, + "step": 1391104 + }, + { + "epoch": 0.01, + "learning_rate": 2.7215216825879557e-05, + "loss": 3.9304, + "step": 1391616 + }, + { + "epoch": 0.01, + "learning_rate": 2.720683087836904e-05, + "loss": 3.9376, + "step": 1392128 + }, + { + "epoch": 0.01, + "learning_rate": 2.719844493085852e-05, + "loss": 3.9235, + "step": 1392640 + }, + { + "epoch": 0.01, + "learning_rate": 2.7190058983348e-05, + "loss": 3.9336, + "step": 1393152 + }, + { + "epoch": 0.01, + "learning_rate": 2.718167303583748e-05, + "loss": 3.9222, + "step": 1393664 + }, + { + "epoch": 0.01, + "learning_rate": 2.717328708832696e-05, + "loss": 3.9326, + "step": 1394176 + }, + { + "epoch": 0.01, + "learning_rate": 2.716490114081644e-05, + "loss": 3.9249, + "step": 1394688 + }, + { + "epoch": 0.01, + "learning_rate": 2.715651519330592e-05, + "loss": 3.938, + "step": 1395200 + }, + { + "epoch": 0.01, + "learning_rate": 2.71481292457954e-05, + "loss": 3.922, + "step": 1395712 + }, + { + "epoch": 0.01, + "learning_rate": 2.713974329828488e-05, + "loss": 3.9365, + "step": 1396224 + }, + { + "epoch": 0.01, + "learning_rate": 2.7131357350774356e-05, + "loss": 3.9405, + "step": 1396736 + }, + { + "epoch": 0.01, + "learning_rate": 2.7122971403263836e-05, + "loss": 3.9309, + "step": 1397248 + }, + { + "epoch": 0.01, + "learning_rate": 2.7114585455753316e-05, + "loss": 3.9359, + "step": 1397760 + }, + { + "epoch": 0.01, + "learning_rate": 2.7106199508242796e-05, + "loss": 3.9196, + "step": 1398272 + }, + { + "epoch": 0.01, + "learning_rate": 2.7097813560732276e-05, + "loss": 3.9247, + "step": 1398784 + }, + { + "epoch": 0.01, + "learning_rate": 2.7089427613221756e-05, + "loss": 3.941, + "step": 1399296 + }, + { + "epoch": 0.01, + "learning_rate": 2.708105804451497e-05, + "loss": 3.9296, + "step": 1399808 + }, + { + "epoch": 0.01, + "learning_rate": 2.707267209700445e-05, + "loss": 3.9306, + "step": 1400320 + }, + { + "epoch": 0.01, + "learning_rate": 2.706428614949393e-05, + "loss": 3.9194, + "step": 1400832 + }, + { + "epoch": 0.01, + "learning_rate": 2.705590020198341e-05, + "loss": 3.9331, + "step": 1401344 + }, + { + "epoch": 0.01, + "learning_rate": 2.7047530633276618e-05, + "loss": 3.9088, + "step": 1401856 + }, + { + "epoch": 0.01, + "learning_rate": 2.703916106456983e-05, + "loss": 3.9439, + "step": 1402368 + }, + { + "epoch": 0.01, + "learning_rate": 2.703077511705931e-05, + "loss": 3.9127, + "step": 1402880 + }, + { + "epoch": 0.01, + "learning_rate": 2.702238916954879e-05, + "loss": 3.9345, + "step": 1403392 + }, + { + "epoch": 0.01, + "learning_rate": 2.701400322203827e-05, + "loss": 3.9341, + "step": 1403904 + }, + { + "epoch": 0.01, + "learning_rate": 2.700561727452775e-05, + "loss": 3.9209, + "step": 1404416 + }, + { + "epoch": 0.01, + "learning_rate": 2.699723132701723e-05, + "loss": 3.9359, + "step": 1404928 + }, + { + "epoch": 0.01, + "learning_rate": 2.6988861758310442e-05, + "loss": 3.924, + "step": 1405440 + }, + { + "epoch": 0.01, + "learning_rate": 2.6980475810799922e-05, + "loss": 3.9214, + "step": 1405952 + }, + { + "epoch": 0.01, + "learning_rate": 2.6972089863289402e-05, + "loss": 3.9149, + "step": 1406464 + }, + { + "epoch": 0.01, + "learning_rate": 2.696372029458261e-05, + "loss": 3.9407, + "step": 1406976 + }, + { + "epoch": 0.01, + "learning_rate": 2.695533434707209e-05, + "loss": 3.9201, + "step": 1407488 + }, + { + "epoch": 0.01, + "learning_rate": 2.694694839956157e-05, + "loss": 3.9262, + "step": 1408000 + }, + { + "epoch": 0.01, + "learning_rate": 2.693856245205105e-05, + "loss": 3.9141, + "step": 1408512 + }, + { + "epoch": 0.01, + "learning_rate": 2.6930176504540534e-05, + "loss": 3.9199, + "step": 1409024 + }, + { + "epoch": 0.01, + "learning_rate": 2.6921790557030014e-05, + "loss": 3.9316, + "step": 1409536 + }, + { + "epoch": 0.01, + "learning_rate": 2.6913404609519494e-05, + "loss": 3.9352, + "step": 1410048 + }, + { + "epoch": 0.01, + "learning_rate": 2.6905018662008974e-05, + "loss": 3.9255, + "step": 1410560 + }, + { + "epoch": 0.01, + "learning_rate": 2.6896632714498454e-05, + "loss": 3.9403, + "step": 1411072 + }, + { + "epoch": 0.01, + "learning_rate": 2.6888263145791663e-05, + "loss": 3.936, + "step": 1411584 + }, + { + "epoch": 0.01, + "learning_rate": 2.6879877198281143e-05, + "loss": 3.9306, + "step": 1412096 + }, + { + "epoch": 0.01, + "learning_rate": 2.6871491250770627e-05, + "loss": 3.9304, + "step": 1412608 + }, + { + "epoch": 0.01, + "learning_rate": 2.6863105303260107e-05, + "loss": 3.9316, + "step": 1413120 + }, + { + "epoch": 0.01, + "learning_rate": 2.6854719355749587e-05, + "loss": 3.9272, + "step": 1413632 + }, + { + "epoch": 0.01, + "learning_rate": 2.6846333408239067e-05, + "loss": 3.9237, + "step": 1414144 + }, + { + "epoch": 0.01, + "learning_rate": 2.683794746072854e-05, + "loss": 3.9334, + "step": 1414656 + }, + { + "epoch": 0.01, + "learning_rate": 2.682956151321802e-05, + "loss": 3.9361, + "step": 1415168 + }, + { + "epoch": 0.01, + "learning_rate": 2.6821175565707503e-05, + "loss": 3.9442, + "step": 1415680 + }, + { + "epoch": 0.01, + "learning_rate": 2.681280599700072e-05, + "loss": 3.9295, + "step": 1416192 + }, + { + "epoch": 0.01, + "learning_rate": 2.6804436428293928e-05, + "loss": 3.9071, + "step": 1416704 + }, + { + "epoch": 0.01, + "learning_rate": 2.6796050480783408e-05, + "loss": 3.9201, + "step": 1417216 + }, + { + "epoch": 0.01, + "learning_rate": 2.6787664533272888e-05, + "loss": 3.9292, + "step": 1417728 + }, + { + "epoch": 0.01, + "learning_rate": 2.6779278585762368e-05, + "loss": 3.9281, + "step": 1418240 + }, + { + "epoch": 0.01, + "learning_rate": 2.6770892638251844e-05, + "loss": 3.9242, + "step": 1418752 + }, + { + "epoch": 0.01, + "learning_rate": 2.6762506690741324e-05, + "loss": 3.9297, + "step": 1419264 + }, + { + "epoch": 0.02, + "learning_rate": 2.675413712203454e-05, + "loss": 3.9255, + "step": 1419776 + }, + { + "epoch": 0.02, + "learning_rate": 2.6745751174524013e-05, + "loss": 3.918, + "step": 1420288 + }, + { + "epoch": 0.02, + "learning_rate": 2.6737365227013493e-05, + "loss": 3.9282, + "step": 1420800 + }, + { + "epoch": 0.02, + "learning_rate": 2.6728979279502973e-05, + "loss": 3.9371, + "step": 1421312 + }, + { + "epoch": 0.02, + "learning_rate": 2.6720593331992457e-05, + "loss": 3.932, + "step": 1421824 + }, + { + "epoch": 0.02, + "learning_rate": 2.6712223763285666e-05, + "loss": 3.9377, + "step": 1422336 + }, + { + "epoch": 0.02, + "learning_rate": 2.6703837815775146e-05, + "loss": 3.9231, + "step": 1422848 + }, + { + "epoch": 0.02, + "learning_rate": 2.6695451868264626e-05, + "loss": 3.9261, + "step": 1423360 + }, + { + "epoch": 0.02, + "learning_rate": 2.6687065920754106e-05, + "loss": 3.9254, + "step": 1423872 + }, + { + "epoch": 0.02, + "learning_rate": 2.6678679973243586e-05, + "loss": 3.9293, + "step": 1424384 + }, + { + "epoch": 0.02, + "learning_rate": 2.6670294025733066e-05, + "loss": 3.9383, + "step": 1424896 + }, + { + "epoch": 0.02, + "learning_rate": 2.6661924457026278e-05, + "loss": 3.9212, + "step": 1425408 + }, + { + "epoch": 0.02, + "learning_rate": 2.6653538509515758e-05, + "loss": 3.9234, + "step": 1425920 + }, + { + "epoch": 0.02, + "learning_rate": 2.6645152562005238e-05, + "loss": 3.932, + "step": 1426432 + }, + { + "epoch": 0.02, + "learning_rate": 2.6636766614494718e-05, + "loss": 3.9338, + "step": 1426944 + }, + { + "epoch": 0.02, + "learning_rate": 2.6628380666984198e-05, + "loss": 3.917, + "step": 1427456 + }, + { + "epoch": 0.02, + "learning_rate": 2.6619994719473678e-05, + "loss": 3.9242, + "step": 1427968 + }, + { + "epoch": 0.02, + "learning_rate": 2.6611608771963158e-05, + "loss": 3.9246, + "step": 1428480 + }, + { + "epoch": 0.02, + "learning_rate": 2.660323920325637e-05, + "loss": 3.9213, + "step": 1428992 + }, + { + "epoch": 0.02, + "learning_rate": 2.659485325574585e-05, + "loss": 3.9206, + "step": 1429504 + }, + { + "epoch": 0.02, + "learning_rate": 2.658646730823533e-05, + "loss": 3.9217, + "step": 1430016 + }, + { + "epoch": 0.02, + "learning_rate": 2.657808136072481e-05, + "loss": 3.9243, + "step": 1430528 + }, + { + "epoch": 0.02, + "learning_rate": 2.656969541321429e-05, + "loss": 3.928, + "step": 1431040 + }, + { + "epoch": 0.02, + "learning_rate": 2.656130946570377e-05, + "loss": 3.9152, + "step": 1431552 + }, + { + "epoch": 0.02, + "learning_rate": 2.6552939896996983e-05, + "loss": 3.9275, + "step": 1432064 + }, + { + "epoch": 0.02, + "learning_rate": 2.6544553949486463e-05, + "loss": 3.9382, + "step": 1432576 + }, + { + "epoch": 0.02, + "learning_rate": 2.6536168001975942e-05, + "loss": 3.939, + "step": 1433088 + }, + { + "epoch": 0.02, + "learning_rate": 2.6527782054465422e-05, + "loss": 3.9308, + "step": 1433600 + }, + { + "epoch": 0.02, + "learning_rate": 2.6519396106954902e-05, + "loss": 3.9307, + "step": 1434112 + }, + { + "epoch": 0.02, + "learning_rate": 2.6511010159444376e-05, + "loss": 3.9253, + "step": 1434624 + }, + { + "epoch": 0.02, + "learning_rate": 2.650264059073759e-05, + "loss": 3.9288, + "step": 1435136 + }, + { + "epoch": 0.02, + "learning_rate": 2.6494271022030804e-05, + "loss": 3.9197, + "step": 1435648 + }, + { + "epoch": 0.02, + "learning_rate": 2.6485885074520284e-05, + "loss": 3.9198, + "step": 1436160 + }, + { + "epoch": 0.02, + "learning_rate": 2.6477499127009764e-05, + "loss": 3.9236, + "step": 1436672 + }, + { + "epoch": 0.02, + "learning_rate": 2.6469113179499244e-05, + "loss": 3.9341, + "step": 1437184 + }, + { + "epoch": 0.02, + "learning_rate": 2.6460727231988724e-05, + "loss": 3.9276, + "step": 1437696 + }, + { + "epoch": 0.02, + "learning_rate": 2.6452341284478204e-05, + "loss": 3.9285, + "step": 1438208 + }, + { + "epoch": 0.02, + "learning_rate": 2.644395533696768e-05, + "loss": 3.9249, + "step": 1438720 + }, + { + "epoch": 0.02, + "learning_rate": 2.643556938945716e-05, + "loss": 3.9204, + "step": 1439232 + }, + { + "epoch": 0.02, + "learning_rate": 2.642718344194664e-05, + "loss": 3.9189, + "step": 1439744 + }, + { + "epoch": 0.02, + "learning_rate": 2.641879749443612e-05, + "loss": 3.9398, + "step": 1440256 + }, + { + "epoch": 0.02, + "learning_rate": 2.64104115469256e-05, + "loss": 3.9378, + "step": 1440768 + }, + { + "epoch": 0.02, + "learning_rate": 2.640202559941508e-05, + "loss": 3.9288, + "step": 1441280 + }, + { + "epoch": 0.02, + "learning_rate": 2.6393656030708293e-05, + "loss": 3.9269, + "step": 1441792 + }, + { + "epoch": 0.02, + "learning_rate": 2.6385270083197772e-05, + "loss": 3.9284, + "step": 1442304 + }, + { + "epoch": 0.02, + "learning_rate": 2.6376884135687252e-05, + "loss": 3.9329, + "step": 1442816 + }, + { + "epoch": 0.02, + "learning_rate": 2.6368498188176732e-05, + "loss": 3.9427, + "step": 1443328 + }, + { + "epoch": 0.02, + "learning_rate": 2.636012861946994e-05, + "loss": 3.9283, + "step": 1443840 + }, + { + "epoch": 0.02, + "learning_rate": 2.635174267195942e-05, + "loss": 3.9262, + "step": 1444352 + }, + { + "epoch": 0.02, + "learning_rate": 2.6343356724448905e-05, + "loss": 3.9263, + "step": 1444864 + }, + { + "epoch": 0.02, + "learning_rate": 2.6334970776938385e-05, + "loss": 3.9267, + "step": 1445376 + }, + { + "epoch": 0.02, + "learning_rate": 2.6326584829427865e-05, + "loss": 3.9249, + "step": 1445888 + }, + { + "epoch": 0.02, + "learning_rate": 2.6318198881917345e-05, + "loss": 3.9257, + "step": 1446400 + }, + { + "epoch": 0.02, + "learning_rate": 2.6309812934406825e-05, + "loss": 3.9331, + "step": 1446912 + }, + { + "epoch": 0.02, + "learning_rate": 2.6301426986896305e-05, + "loss": 3.9203, + "step": 1447424 + }, + { + "epoch": 0.02, + "learning_rate": 2.6293073796993246e-05, + "loss": 3.9322, + "step": 1447936 + }, + { + "epoch": 0.02, + "learning_rate": 2.6284687849482726e-05, + "loss": 3.9338, + "step": 1448448 + }, + { + "epoch": 0.02, + "learning_rate": 2.6276301901972206e-05, + "loss": 3.9272, + "step": 1448960 + }, + { + "epoch": 0.02, + "learning_rate": 2.6267915954461686e-05, + "loss": 3.9331, + "step": 1449472 + }, + { + "epoch": 0.02, + "learning_rate": 2.6259530006951166e-05, + "loss": 3.9164, + "step": 1449984 + }, + { + "epoch": 0.03, + "eval_loss": 4.003432273864746, + "eval_runtime": 293.3568, + "eval_samples_per_second": 1300.774, + "eval_steps_per_second": 40.65, + "step": 1450080 + }, + { + "epoch": 1.0, + "learning_rate": 2.6251160438244375e-05, + "loss": 3.9263, + "step": 1450496 + }, + { + "epoch": 1.0, + "learning_rate": 2.624277449073386e-05, + "loss": 3.9161, + "step": 1451008 + }, + { + "epoch": 1.0, + "learning_rate": 2.623438854322334e-05, + "loss": 3.9367, + "step": 1451520 + }, + { + "epoch": 1.0, + "learning_rate": 2.622600259571282e-05, + "loss": 3.9242, + "step": 1452032 + }, + { + "epoch": 1.0, + "learning_rate": 2.62176166482023e-05, + "loss": 3.9395, + "step": 1452544 + }, + { + "epoch": 1.0, + "learning_rate": 2.6209247079495507e-05, + "loss": 3.921, + "step": 1453056 + }, + { + "epoch": 1.0, + "learning_rate": 2.6200861131984987e-05, + "loss": 3.926, + "step": 1453568 + }, + { + "epoch": 1.0, + "learning_rate": 2.6192475184474467e-05, + "loss": 3.912, + "step": 1454080 + }, + { + "epoch": 1.0, + "learning_rate": 2.618408923696395e-05, + "loss": 3.9307, + "step": 1454592 + }, + { + "epoch": 1.0, + "learning_rate": 2.617570328945343e-05, + "loss": 3.9174, + "step": 1455104 + }, + { + "epoch": 1.0, + "learning_rate": 2.616731734194291e-05, + "loss": 3.9413, + "step": 1455616 + }, + { + "epoch": 1.0, + "learning_rate": 2.615894777323612e-05, + "loss": 3.935, + "step": 1456128 + }, + { + "epoch": 1.0, + "learning_rate": 2.615057820452933e-05, + "loss": 3.9143, + "step": 1456640 + }, + { + "epoch": 1.0, + "learning_rate": 2.6142192257018812e-05, + "loss": 3.9184, + "step": 1457152 + }, + { + "epoch": 1.0, + "learning_rate": 2.6133806309508292e-05, + "loss": 3.9292, + "step": 1457664 + }, + { + "epoch": 1.0, + "learning_rate": 2.6125420361997772e-05, + "loss": 3.9174, + "step": 1458176 + }, + { + "epoch": 1.0, + "learning_rate": 2.6117034414487252e-05, + "loss": 3.9245, + "step": 1458688 + }, + { + "epoch": 1.0, + "learning_rate": 2.6108648466976732e-05, + "loss": 3.9242, + "step": 1459200 + }, + { + "epoch": 1.0, + "learning_rate": 2.610027889826994e-05, + "loss": 3.9188, + "step": 1459712 + }, + { + "epoch": 1.0, + "learning_rate": 2.609189295075942e-05, + "loss": 3.9488, + "step": 1460224 + }, + { + "epoch": 1.0, + "learning_rate": 2.60835070032489e-05, + "loss": 3.9211, + "step": 1460736 + }, + { + "epoch": 1.0, + "learning_rate": 2.6075121055738384e-05, + "loss": 3.9268, + "step": 1461248 + }, + { + "epoch": 1.0, + "learning_rate": 2.6066735108227864e-05, + "loss": 3.9241, + "step": 1461760 + }, + { + "epoch": 1.0, + "learning_rate": 2.6058349160717337e-05, + "loss": 3.9347, + "step": 1462272 + }, + { + "epoch": 1.0, + "learning_rate": 2.6049963213206817e-05, + "loss": 3.9194, + "step": 1462784 + }, + { + "epoch": 1.0, + "learning_rate": 2.6041577265696297e-05, + "loss": 3.9256, + "step": 1463296 + }, + { + "epoch": 1.0, + "learning_rate": 2.6033191318185777e-05, + "loss": 3.917, + "step": 1463808 + }, + { + "epoch": 1.0, + "learning_rate": 2.602480537067526e-05, + "loss": 3.9259, + "step": 1464320 + }, + { + "epoch": 1.0, + "learning_rate": 2.601641942316474e-05, + "loss": 3.92, + "step": 1464832 + }, + { + "epoch": 1.01, + "learning_rate": 2.600803347565422e-05, + "loss": 3.9219, + "step": 1465344 + }, + { + "epoch": 1.01, + "learning_rate": 2.59996475281437e-05, + "loss": 3.9225, + "step": 1465856 + }, + { + "epoch": 1.01, + "learning_rate": 2.599127795943691e-05, + "loss": 3.9313, + "step": 1466368 + }, + { + "epoch": 1.01, + "learning_rate": 2.598289201192639e-05, + "loss": 3.9281, + "step": 1466880 + }, + { + "epoch": 1.01, + "learning_rate": 2.597450606441587e-05, + "loss": 3.9333, + "step": 1467392 + }, + { + "epoch": 1.01, + "learning_rate": 2.5966136495709082e-05, + "loss": 3.9213, + "step": 1467904 + }, + { + "epoch": 1.01, + "learning_rate": 2.5957750548198562e-05, + "loss": 3.9287, + "step": 1468416 + }, + { + "epoch": 1.01, + "learning_rate": 2.5949364600688042e-05, + "loss": 3.9125, + "step": 1468928 + }, + { + "epoch": 1.01, + "learning_rate": 2.5940978653177522e-05, + "loss": 3.9301, + "step": 1469440 + }, + { + "epoch": 1.01, + "learning_rate": 2.593260908447073e-05, + "loss": 3.9137, + "step": 1469952 + }, + { + "epoch": 1.01, + "learning_rate": 2.5924223136960214e-05, + "loss": 3.9227, + "step": 1470464 + }, + { + "epoch": 1.01, + "learning_rate": 2.5915837189449694e-05, + "loss": 3.9179, + "step": 1470976 + }, + { + "epoch": 1.01, + "learning_rate": 2.5907451241939174e-05, + "loss": 3.9309, + "step": 1471488 + }, + { + "epoch": 1.01, + "learning_rate": 2.5899065294428654e-05, + "loss": 3.9132, + "step": 1472000 + }, + { + "epoch": 1.01, + "learning_rate": 2.5890679346918134e-05, + "loss": 3.9234, + "step": 1472512 + }, + { + "epoch": 1.01, + "learning_rate": 2.5882293399407614e-05, + "loss": 3.9342, + "step": 1473024 + }, + { + "epoch": 1.01, + "learning_rate": 2.5873907451897094e-05, + "loss": 3.9262, + "step": 1473536 + }, + { + "epoch": 1.01, + "learning_rate": 2.5865521504386574e-05, + "loss": 3.929, + "step": 1474048 + }, + { + "epoch": 1.01, + "learning_rate": 2.5857151935679786e-05, + "loss": 3.9117, + "step": 1474560 + }, + { + "epoch": 1.01, + "learning_rate": 2.5848765988169266e-05, + "loss": 3.9146, + "step": 1475072 + }, + { + "epoch": 1.01, + "learning_rate": 2.5840380040658746e-05, + "loss": 3.9281, + "step": 1475584 + }, + { + "epoch": 1.01, + "learning_rate": 2.5831994093148226e-05, + "loss": 3.9234, + "step": 1476096 + }, + { + "epoch": 1.01, + "learning_rate": 2.58236081456377e-05, + "loss": 3.9198, + "step": 1476608 + }, + { + "epoch": 1.01, + "learning_rate": 2.5815238576930915e-05, + "loss": 3.9157, + "step": 1477120 + }, + { + "epoch": 1.01, + "learning_rate": 2.58068526294204e-05, + "loss": 3.9261, + "step": 1477632 + }, + { + "epoch": 1.01, + "learning_rate": 2.5798466681909872e-05, + "loss": 3.9051, + "step": 1478144 + }, + { + "epoch": 1.01, + "learning_rate": 2.5790080734399352e-05, + "loss": 3.9272, + "step": 1478656 + }, + { + "epoch": 1.01, + "learning_rate": 2.5781694786888832e-05, + "loss": 3.9078, + "step": 1479168 + }, + { + "epoch": 1.01, + "learning_rate": 2.5773325218182048e-05, + "loss": 3.92, + "step": 1479680 + }, + { + "epoch": 1.01, + "learning_rate": 2.5764939270671524e-05, + "loss": 3.9288, + "step": 1480192 + }, + { + "epoch": 1.01, + "learning_rate": 2.5756553323161004e-05, + "loss": 3.9133, + "step": 1480704 + }, + { + "epoch": 1.01, + "learning_rate": 2.5748167375650484e-05, + "loss": 3.9253, + "step": 1481216 + }, + { + "epoch": 1.01, + "learning_rate": 2.5739781428139964e-05, + "loss": 3.9185, + "step": 1481728 + }, + { + "epoch": 1.01, + "learning_rate": 2.5731395480629444e-05, + "loss": 3.912, + "step": 1482240 + }, + { + "epoch": 1.01, + "learning_rate": 2.5723009533118924e-05, + "loss": 3.9117, + "step": 1482752 + }, + { + "epoch": 1.01, + "learning_rate": 2.5714623585608404e-05, + "loss": 3.9266, + "step": 1483264 + }, + { + "epoch": 1.01, + "learning_rate": 2.5706237638097884e-05, + "loss": 3.9134, + "step": 1483776 + }, + { + "epoch": 1.01, + "learning_rate": 2.5697884448194826e-05, + "loss": 3.9192, + "step": 1484288 + }, + { + "epoch": 1.01, + "learning_rate": 2.5689498500684306e-05, + "loss": 3.9065, + "step": 1484800 + }, + { + "epoch": 1.01, + "learning_rate": 2.5681112553173786e-05, + "loss": 3.9103, + "step": 1485312 + }, + { + "epoch": 1.01, + "learning_rate": 2.5672726605663265e-05, + "loss": 3.9236, + "step": 1485824 + }, + { + "epoch": 1.01, + "learning_rate": 2.5664340658152745e-05, + "loss": 3.9293, + "step": 1486336 + }, + { + "epoch": 1.01, + "learning_rate": 2.565595471064223e-05, + "loss": 3.9172, + "step": 1486848 + }, + { + "epoch": 1.01, + "learning_rate": 2.564756876313171e-05, + "loss": 3.9328, + "step": 1487360 + }, + { + "epoch": 1.01, + "learning_rate": 2.5639199194424918e-05, + "loss": 3.9267, + "step": 1487872 + }, + { + "epoch": 1.01, + "learning_rate": 2.5630813246914398e-05, + "loss": 3.9205, + "step": 1488384 + }, + { + "epoch": 1.01, + "learning_rate": 2.5622443678207607e-05, + "loss": 3.9249, + "step": 1488896 + }, + { + "epoch": 1.01, + "learning_rate": 2.561405773069709e-05, + "loss": 3.9218, + "step": 1489408 + }, + { + "epoch": 1.01, + "learning_rate": 2.560567178318657e-05, + "loss": 3.921, + "step": 1489920 + }, + { + "epoch": 1.01, + "learning_rate": 2.559728583567605e-05, + "loss": 3.9186, + "step": 1490432 + }, + { + "epoch": 1.01, + "learning_rate": 2.558889988816553e-05, + "loss": 3.9241, + "step": 1490944 + }, + { + "epoch": 1.01, + "learning_rate": 2.558051394065501e-05, + "loss": 3.9313, + "step": 1491456 + }, + { + "epoch": 1.01, + "learning_rate": 2.557212799314449e-05, + "loss": 3.928, + "step": 1491968 + }, + { + "epoch": 1.01, + "learning_rate": 2.556374204563397e-05, + "loss": 3.9245, + "step": 1492480 + }, + { + "epoch": 1.01, + "learning_rate": 2.555535609812345e-05, + "loss": 3.9049, + "step": 1492992 + }, + { + "epoch": 1.01, + "learning_rate": 2.554697015061293e-05, + "loss": 3.9094, + "step": 1493504 + }, + { + "epoch": 1.01, + "learning_rate": 2.553858420310241e-05, + "loss": 3.921, + "step": 1494016 + }, + { + "epoch": 1.01, + "learning_rate": 2.5530214634395622e-05, + "loss": 3.9197, + "step": 1494528 + }, + { + "epoch": 1.01, + "learning_rate": 2.5521828686885102e-05, + "loss": 3.9179, + "step": 1495040 + }, + { + "epoch": 1.01, + "learning_rate": 2.5513442739374582e-05, + "loss": 3.9241, + "step": 1495552 + }, + { + "epoch": 1.02, + "learning_rate": 2.5505056791864055e-05, + "loss": 3.9163, + "step": 1496064 + }, + { + "epoch": 1.02, + "learning_rate": 2.549668722315727e-05, + "loss": 3.9122, + "step": 1496576 + }, + { + "epoch": 1.02, + "learning_rate": 2.5488301275646755e-05, + "loss": 3.9184, + "step": 1497088 + }, + { + "epoch": 1.02, + "learning_rate": 2.5479915328136235e-05, + "loss": 3.926, + "step": 1497600 + }, + { + "epoch": 1.02, + "learning_rate": 2.5471529380625708e-05, + "loss": 3.9228, + "step": 1498112 + }, + { + "epoch": 1.02, + "learning_rate": 2.5463143433115188e-05, + "loss": 3.9327, + "step": 1498624 + }, + { + "epoch": 1.02, + "learning_rate": 2.5454757485604668e-05, + "loss": 3.9168, + "step": 1499136 + }, + { + "epoch": 1.02, + "learning_rate": 2.5446387916897884e-05, + "loss": 3.9149, + "step": 1499648 + }, + { + "epoch": 1.02, + "learning_rate": 2.543800196938736e-05, + "loss": 3.9188, + "step": 1500160 + }, + { + "epoch": 1.02, + "learning_rate": 2.542961602187684e-05, + "loss": 3.9202, + "step": 1500672 + }, + { + "epoch": 1.02, + "learning_rate": 2.542123007436632e-05, + "loss": 3.9316, + "step": 1501184 + }, + { + "epoch": 1.02, + "learning_rate": 2.54128441268558e-05, + "loss": 3.9124, + "step": 1501696 + }, + { + "epoch": 1.02, + "learning_rate": 2.540447455814901e-05, + "loss": 3.918, + "step": 1502208 + }, + { + "epoch": 1.02, + "learning_rate": 2.5396088610638492e-05, + "loss": 3.9221, + "step": 1502720 + }, + { + "epoch": 1.02, + "learning_rate": 2.5387702663127972e-05, + "loss": 3.9281, + "step": 1503232 + }, + { + "epoch": 1.02, + "learning_rate": 2.5379316715617452e-05, + "loss": 3.9093, + "step": 1503744 + }, + { + "epoch": 1.02, + "learning_rate": 2.5370930768106932e-05, + "loss": 3.9184, + "step": 1504256 + }, + { + "epoch": 1.02, + "learning_rate": 2.536256119940014e-05, + "loss": 3.9187, + "step": 1504768 + }, + { + "epoch": 1.02, + "learning_rate": 2.535417525188962e-05, + "loss": 3.9131, + "step": 1505280 + }, + { + "epoch": 1.02, + "learning_rate": 2.53457893043791e-05, + "loss": 3.9093, + "step": 1505792 + }, + { + "epoch": 1.02, + "learning_rate": 2.5337403356868585e-05, + "loss": 3.9152, + "step": 1506304 + }, + { + "epoch": 1.02, + "learning_rate": 2.5329017409358065e-05, + "loss": 3.9186, + "step": 1506816 + }, + { + "epoch": 1.02, + "learning_rate": 2.5320631461847545e-05, + "loss": 3.9156, + "step": 1507328 + }, + { + "epoch": 1.02, + "learning_rate": 2.5312245514337024e-05, + "loss": 3.9101, + "step": 1507840 + }, + { + "epoch": 1.02, + "learning_rate": 2.5303875945630234e-05, + "loss": 3.9161, + "step": 1508352 + }, + { + "epoch": 1.02, + "learning_rate": 2.5295489998119714e-05, + "loss": 3.9339, + "step": 1508864 + }, + { + "epoch": 1.02, + "learning_rate": 2.5287104050609193e-05, + "loss": 3.9284, + "step": 1509376 + }, + { + "epoch": 1.02, + "learning_rate": 2.5278718103098677e-05, + "loss": 3.9248, + "step": 1509888 + }, + { + "epoch": 1.02, + "learning_rate": 2.5270332155588157e-05, + "loss": 3.9212, + "step": 1510400 + }, + { + "epoch": 1.02, + "learning_rate": 2.5261962586881366e-05, + "loss": 3.9159, + "step": 1510912 + }, + { + "epoch": 1.02, + "learning_rate": 2.5253576639370846e-05, + "loss": 3.9193, + "step": 1511424 + }, + { + "epoch": 1.02, + "learning_rate": 2.5245190691860326e-05, + "loss": 3.9107, + "step": 1511936 + }, + { + "epoch": 1.02, + "learning_rate": 2.5236804744349806e-05, + "loss": 3.9134, + "step": 1512448 + }, + { + "epoch": 1.02, + "learning_rate": 2.5228418796839286e-05, + "loss": 3.9162, + "step": 1512960 + }, + { + "epoch": 1.02, + "learning_rate": 2.522003284932877e-05, + "loss": 3.925, + "step": 1513472 + }, + { + "epoch": 1.02, + "learning_rate": 2.5211663280621978e-05, + "loss": 3.9177, + "step": 1513984 + }, + { + "epoch": 1.02, + "learning_rate": 2.5203277333111458e-05, + "loss": 3.9248, + "step": 1514496 + }, + { + "epoch": 1.02, + "learning_rate": 2.5194891385600938e-05, + "loss": 3.9144, + "step": 1515008 + }, + { + "epoch": 1.02, + "learning_rate": 2.5186505438090418e-05, + "loss": 3.917, + "step": 1515520 + }, + { + "epoch": 1.02, + "learning_rate": 2.5178119490579895e-05, + "loss": 3.9094, + "step": 1516032 + }, + { + "epoch": 1.02, + "learning_rate": 2.5169733543069375e-05, + "loss": 3.9306, + "step": 1516544 + }, + { + "epoch": 1.02, + "learning_rate": 2.5161347595558854e-05, + "loss": 3.9326, + "step": 1517056 + }, + { + "epoch": 1.02, + "learning_rate": 2.515297802685207e-05, + "loss": 3.9219, + "step": 1517568 + }, + { + "epoch": 1.02, + "learning_rate": 2.5144592079341544e-05, + "loss": 3.9176, + "step": 1518080 + }, + { + "epoch": 1.02, + "learning_rate": 2.5136206131831023e-05, + "loss": 3.9239, + "step": 1518592 + }, + { + "epoch": 1.02, + "learning_rate": 2.5127820184320507e-05, + "loss": 3.9197, + "step": 1519104 + }, + { + "epoch": 1.02, + "learning_rate": 2.5119434236809987e-05, + "loss": 3.9356, + "step": 1519616 + }, + { + "epoch": 1.02, + "learning_rate": 2.5111048289299467e-05, + "loss": 3.9178, + "step": 1520128 + }, + { + "epoch": 1.02, + "learning_rate": 2.5102662341788947e-05, + "loss": 3.9213, + "step": 1520640 + }, + { + "epoch": 1.02, + "learning_rate": 2.5094276394278427e-05, + "loss": 3.9165, + "step": 1521152 + }, + { + "epoch": 1.02, + "learning_rate": 2.5085890446767907e-05, + "loss": 3.9247, + "step": 1521664 + }, + { + "epoch": 1.02, + "learning_rate": 2.5077520878061116e-05, + "loss": 3.9149, + "step": 1522176 + }, + { + "epoch": 1.02, + "learning_rate": 2.50691349305506e-05, + "loss": 3.9165, + "step": 1522688 + }, + { + "epoch": 1.02, + "learning_rate": 2.506074898304008e-05, + "loss": 3.9251, + "step": 1523200 + }, + { + "epoch": 1.02, + "learning_rate": 2.505236303552956e-05, + "loss": 3.9164, + "step": 1523712 + }, + { + "epoch": 1.02, + "learning_rate": 2.5043993466822768e-05, + "loss": 3.9223, + "step": 1524224 + }, + { + "epoch": 1.02, + "learning_rate": 2.5035607519312248e-05, + "loss": 3.9264, + "step": 1524736 + }, + { + "epoch": 1.02, + "learning_rate": 2.5027221571801728e-05, + "loss": 3.9173, + "step": 1525248 + }, + { + "epoch": 1.02, + "learning_rate": 2.5018835624291208e-05, + "loss": 3.9244, + "step": 1525760 + }, + { + "epoch": 1.02, + "learning_rate": 2.5010449676780688e-05, + "loss": 3.9149, + "step": 1526272 + }, + { + "epoch": 1.03, + "eval_loss": 3.999666213989258, + "eval_runtime": 292.8662, + "eval_samples_per_second": 1302.954, + "eval_steps_per_second": 40.718, + "step": 1526400 + }, + { + "epoch": 0.0, + "learning_rate": 2.500206372927017e-05, + "loss": 3.9085, + "step": 1526784 + }, + { + "epoch": 0.0, + "learning_rate": 2.4993677781759648e-05, + "loss": 3.9076, + "step": 1527296 + }, + { + "epoch": 0.0, + "learning_rate": 2.4985291834249128e-05, + "loss": 3.9265, + "step": 1527808 + }, + { + "epoch": 0.0, + "learning_rate": 2.4976905886738608e-05, + "loss": 3.9188, + "step": 1528320 + }, + { + "epoch": 0.0, + "learning_rate": 2.4968519939228088e-05, + "loss": 3.93, + "step": 1528832 + }, + { + "epoch": 0.0, + "learning_rate": 2.4960133991717568e-05, + "loss": 3.9134, + "step": 1529344 + }, + { + "epoch": 0.0, + "learning_rate": 2.4951748044207048e-05, + "loss": 3.9196, + "step": 1529856 + }, + { + "epoch": 0.0, + "learning_rate": 2.4943362096696528e-05, + "loss": 3.9025, + "step": 1530368 + }, + { + "epoch": 0.0, + "learning_rate": 2.493499252798974e-05, + "loss": 3.9267, + "step": 1530880 + }, + { + "epoch": 0.0, + "learning_rate": 2.492660658047922e-05, + "loss": 3.9084, + "step": 1531392 + }, + { + "epoch": 0.0, + "learning_rate": 2.4918220632968697e-05, + "loss": 3.9294, + "step": 1531904 + }, + { + "epoch": 0.0, + "learning_rate": 2.4909834685458176e-05, + "loss": 3.9299, + "step": 1532416 + }, + { + "epoch": 0.0, + "learning_rate": 2.4901465116751392e-05, + "loss": 3.9041, + "step": 1532928 + }, + { + "epoch": 0.0, + "learning_rate": 2.4893079169240872e-05, + "loss": 3.9153, + "step": 1533440 + }, + { + "epoch": 0.0, + "learning_rate": 2.488469322173035e-05, + "loss": 3.9196, + "step": 1533952 + }, + { + "epoch": 0.0, + "learning_rate": 2.487630727421983e-05, + "loss": 3.9091, + "step": 1534464 + }, + { + "epoch": 0.0, + "learning_rate": 2.486792132670931e-05, + "loss": 3.915, + "step": 1534976 + }, + { + "epoch": 0.0, + "learning_rate": 2.485953537919879e-05, + "loss": 3.9183, + "step": 1535488 + }, + { + "epoch": 0.0, + "learning_rate": 2.4851165810492e-05, + "loss": 3.9145, + "step": 1536000 + }, + { + "epoch": 0.0, + "learning_rate": 2.484277986298148e-05, + "loss": 3.9359, + "step": 1536512 + }, + { + "epoch": 0.0, + "learning_rate": 2.483439391547096e-05, + "loss": 3.9122, + "step": 1537024 + }, + { + "epoch": 0.0, + "learning_rate": 2.482600796796044e-05, + "loss": 3.9194, + "step": 1537536 + }, + { + "epoch": 0.0, + "learning_rate": 2.481762202044992e-05, + "loss": 3.9201, + "step": 1538048 + }, + { + "epoch": 0.0, + "learning_rate": 2.48092360729394e-05, + "loss": 3.926, + "step": 1538560 + }, + { + "epoch": 0.0, + "learning_rate": 2.4800850125428878e-05, + "loss": 3.912, + "step": 1539072 + }, + { + "epoch": 0.0, + "learning_rate": 2.4792464177918358e-05, + "loss": 3.9229, + "step": 1539584 + }, + { + "epoch": 0.0, + "learning_rate": 2.478407823040784e-05, + "loss": 3.9064, + "step": 1540096 + }, + { + "epoch": 0.0, + "learning_rate": 2.477569228289732e-05, + "loss": 3.9155, + "step": 1540608 + }, + { + "epoch": 0.0, + "learning_rate": 2.47673063353868e-05, + "loss": 3.9099, + "step": 1541120 + }, + { + "epoch": 0.0, + "learning_rate": 2.475892038787628e-05, + "loss": 3.915, + "step": 1541632 + }, + { + "epoch": 0.01, + "learning_rate": 2.475053444036576e-05, + "loss": 3.9158, + "step": 1542144 + }, + { + "epoch": 0.01, + "learning_rate": 2.4742148492855237e-05, + "loss": 3.9235, + "step": 1542656 + }, + { + "epoch": 0.01, + "learning_rate": 2.4733762545344717e-05, + "loss": 3.921, + "step": 1543168 + }, + { + "epoch": 0.01, + "learning_rate": 2.47253765978342e-05, + "loss": 3.9265, + "step": 1543680 + }, + { + "epoch": 0.01, + "learning_rate": 2.4717007029127413e-05, + "loss": 3.914, + "step": 1544192 + }, + { + "epoch": 0.01, + "learning_rate": 2.470862108161689e-05, + "loss": 3.922, + "step": 1544704 + }, + { + "epoch": 0.01, + "learning_rate": 2.470023513410637e-05, + "loss": 3.9102, + "step": 1545216 + }, + { + "epoch": 0.01, + "learning_rate": 2.469184918659585e-05, + "loss": 3.9149, + "step": 1545728 + }, + { + "epoch": 0.01, + "learning_rate": 2.468346323908533e-05, + "loss": 3.9086, + "step": 1546240 + }, + { + "epoch": 0.01, + "learning_rate": 2.467507729157481e-05, + "loss": 3.9124, + "step": 1546752 + }, + { + "epoch": 0.01, + "learning_rate": 2.466669134406429e-05, + "loss": 3.913, + "step": 1547264 + }, + { + "epoch": 0.01, + "learning_rate": 2.4658321775357502e-05, + "loss": 3.9237, + "step": 1547776 + }, + { + "epoch": 0.01, + "learning_rate": 2.4649935827846982e-05, + "loss": 3.9076, + "step": 1548288 + }, + { + "epoch": 0.01, + "learning_rate": 2.4641549880336462e-05, + "loss": 3.9155, + "step": 1548800 + }, + { + "epoch": 0.01, + "learning_rate": 2.4633163932825942e-05, + "loss": 3.9301, + "step": 1549312 + }, + { + "epoch": 0.01, + "learning_rate": 2.462477798531542e-05, + "loss": 3.9187, + "step": 1549824 + }, + { + "epoch": 0.01, + "learning_rate": 2.46163920378049e-05, + "loss": 3.9206, + "step": 1550336 + }, + { + "epoch": 0.01, + "learning_rate": 2.4608022469098114e-05, + "loss": 3.9075, + "step": 1550848 + }, + { + "epoch": 0.01, + "learning_rate": 2.459963652158759e-05, + "loss": 3.8993, + "step": 1551360 + }, + { + "epoch": 0.01, + "learning_rate": 2.459125057407707e-05, + "loss": 3.9231, + "step": 1551872 + }, + { + "epoch": 0.01, + "learning_rate": 2.458286462656655e-05, + "loss": 3.9175, + "step": 1552384 + }, + { + "epoch": 0.01, + "learning_rate": 2.457447867905603e-05, + "loss": 3.9102, + "step": 1552896 + }, + { + "epoch": 0.01, + "learning_rate": 2.4566109110349243e-05, + "loss": 3.9119, + "step": 1553408 + }, + { + "epoch": 0.01, + "learning_rate": 2.4557723162838723e-05, + "loss": 3.9199, + "step": 1553920 + }, + { + "epoch": 0.01, + "learning_rate": 2.4549337215328203e-05, + "loss": 3.8959, + "step": 1554432 + }, + { + "epoch": 0.01, + "learning_rate": 2.4540967646621415e-05, + "loss": 3.92, + "step": 1554944 + }, + { + "epoch": 0.01, + "learning_rate": 2.4532581699110892e-05, + "loss": 3.9006, + "step": 1555456 + }, + { + "epoch": 0.01, + "learning_rate": 2.4524195751600372e-05, + "loss": 3.9136, + "step": 1555968 + }, + { + "epoch": 0.01, + "learning_rate": 2.4515809804089855e-05, + "loss": 3.9178, + "step": 1556480 + }, + { + "epoch": 0.01, + "learning_rate": 2.4507423856579335e-05, + "loss": 3.9095, + "step": 1556992 + }, + { + "epoch": 0.01, + "learning_rate": 2.4499037909068815e-05, + "loss": 3.9134, + "step": 1557504 + }, + { + "epoch": 0.01, + "learning_rate": 2.4490651961558295e-05, + "loss": 3.912, + "step": 1558016 + }, + { + "epoch": 0.01, + "learning_rate": 2.4482266014047772e-05, + "loss": 3.9028, + "step": 1558528 + }, + { + "epoch": 0.01, + "learning_rate": 2.4473880066537252e-05, + "loss": 3.9113, + "step": 1559040 + }, + { + "epoch": 0.01, + "learning_rate": 2.446549411902673e-05, + "loss": 3.914, + "step": 1559552 + }, + { + "epoch": 0.01, + "learning_rate": 2.445710817151621e-05, + "loss": 3.9089, + "step": 1560064 + }, + { + "epoch": 0.01, + "learning_rate": 2.4448722224005695e-05, + "loss": 3.911, + "step": 1560576 + }, + { + "epoch": 0.01, + "learning_rate": 2.4440352655298904e-05, + "loss": 3.9005, + "step": 1561088 + }, + { + "epoch": 0.01, + "learning_rate": 2.4431966707788384e-05, + "loss": 3.8996, + "step": 1561600 + }, + { + "epoch": 0.01, + "learning_rate": 2.4423580760277864e-05, + "loss": 3.9147, + "step": 1562112 + }, + { + "epoch": 0.01, + "learning_rate": 2.4415194812767344e-05, + "loss": 3.9251, + "step": 1562624 + }, + { + "epoch": 0.01, + "learning_rate": 2.4406825244060556e-05, + "loss": 3.908, + "step": 1563136 + }, + { + "epoch": 0.01, + "learning_rate": 2.4398439296550036e-05, + "loss": 3.9276, + "step": 1563648 + }, + { + "epoch": 0.01, + "learning_rate": 2.4390069727843245e-05, + "loss": 3.9222, + "step": 1564160 + }, + { + "epoch": 0.01, + "learning_rate": 2.4381683780332725e-05, + "loss": 3.9108, + "step": 1564672 + }, + { + "epoch": 0.01, + "learning_rate": 2.4373314211625938e-05, + "loss": 3.9132, + "step": 1565184 + }, + { + "epoch": 0.01, + "learning_rate": 2.4364928264115418e-05, + "loss": 3.9211, + "step": 1565696 + }, + { + "epoch": 0.01, + "learning_rate": 2.4356542316604898e-05, + "loss": 3.9116, + "step": 1566208 + }, + { + "epoch": 0.01, + "learning_rate": 2.4348156369094378e-05, + "loss": 3.9108, + "step": 1566720 + }, + { + "epoch": 0.01, + "learning_rate": 2.4339770421583858e-05, + "loss": 3.9183, + "step": 1567232 + }, + { + "epoch": 0.01, + "learning_rate": 2.4331384474073338e-05, + "loss": 3.9192, + "step": 1567744 + }, + { + "epoch": 0.01, + "learning_rate": 2.4322998526562818e-05, + "loss": 3.9234, + "step": 1568256 + }, + { + "epoch": 0.01, + "learning_rate": 2.4314612579052298e-05, + "loss": 3.9149, + "step": 1568768 + }, + { + "epoch": 0.01, + "learning_rate": 2.4306226631541778e-05, + "loss": 3.8993, + "step": 1569280 + }, + { + "epoch": 0.01, + "learning_rate": 2.429785706283499e-05, + "loss": 3.9006, + "step": 1569792 + }, + { + "epoch": 0.01, + "learning_rate": 2.428947111532447e-05, + "loss": 3.9122, + "step": 1570304 + }, + { + "epoch": 0.01, + "learning_rate": 2.428108516781395e-05, + "loss": 3.9162, + "step": 1570816 + }, + { + "epoch": 0.01, + "learning_rate": 2.4272699220303427e-05, + "loss": 3.9117, + "step": 1571328 + }, + { + "epoch": 0.01, + "learning_rate": 2.4264313272792906e-05, + "loss": 3.9133, + "step": 1571840 + }, + { + "epoch": 0.02, + "learning_rate": 2.4255927325282386e-05, + "loss": 3.9092, + "step": 1572352 + }, + { + "epoch": 0.02, + "learning_rate": 2.4247541377771866e-05, + "loss": 3.9079, + "step": 1572864 + }, + { + "epoch": 0.02, + "learning_rate": 2.423915543026135e-05, + "loss": 3.9123, + "step": 1573376 + }, + { + "epoch": 0.02, + "learning_rate": 2.423078586155456e-05, + "loss": 3.9122, + "step": 1573888 + }, + { + "epoch": 0.02, + "learning_rate": 2.422239991404404e-05, + "loss": 3.919, + "step": 1574400 + }, + { + "epoch": 0.02, + "learning_rate": 2.421403034533725e-05, + "loss": 3.9168, + "step": 1574912 + }, + { + "epoch": 0.02, + "learning_rate": 2.4205644397826728e-05, + "loss": 3.9155, + "step": 1575424 + }, + { + "epoch": 0.02, + "learning_rate": 2.419725845031621e-05, + "loss": 3.9046, + "step": 1575936 + }, + { + "epoch": 0.02, + "learning_rate": 2.418887250280569e-05, + "loss": 3.9149, + "step": 1576448 + }, + { + "epoch": 0.02, + "learning_rate": 2.418048655529517e-05, + "loss": 3.9122, + "step": 1576960 + }, + { + "epoch": 0.02, + "learning_rate": 2.417210060778465e-05, + "loss": 3.9226, + "step": 1577472 + }, + { + "epoch": 0.02, + "learning_rate": 2.416371466027413e-05, + "loss": 3.9092, + "step": 1577984 + }, + { + "epoch": 0.02, + "learning_rate": 2.4155328712763608e-05, + "loss": 3.9038, + "step": 1578496 + }, + { + "epoch": 0.02, + "learning_rate": 2.414695914405682e-05, + "loss": 3.9195, + "step": 1579008 + }, + { + "epoch": 0.02, + "learning_rate": 2.4138573196546303e-05, + "loss": 3.9152, + "step": 1579520 + }, + { + "epoch": 0.02, + "learning_rate": 2.4130187249035783e-05, + "loss": 3.9062, + "step": 1580032 + }, + { + "epoch": 0.02, + "learning_rate": 2.4121817680328992e-05, + "loss": 3.911, + "step": 1580544 + }, + { + "epoch": 0.02, + "learning_rate": 2.4113431732818472e-05, + "loss": 3.9106, + "step": 1581056 + }, + { + "epoch": 0.02, + "learning_rate": 2.4105045785307952e-05, + "loss": 3.8975, + "step": 1581568 + }, + { + "epoch": 0.02, + "learning_rate": 2.4096659837797432e-05, + "loss": 3.904, + "step": 1582080 + }, + { + "epoch": 0.02, + "learning_rate": 2.4088273890286912e-05, + "loss": 3.9142, + "step": 1582592 + }, + { + "epoch": 0.02, + "learning_rate": 2.4079887942776392e-05, + "loss": 3.9077, + "step": 1583104 + }, + { + "epoch": 0.02, + "learning_rate": 2.4071501995265872e-05, + "loss": 3.9072, + "step": 1583616 + }, + { + "epoch": 0.02, + "learning_rate": 2.4063116047755352e-05, + "loss": 3.9031, + "step": 1584128 + }, + { + "epoch": 0.02, + "learning_rate": 2.4054730100244832e-05, + "loss": 3.9057, + "step": 1584640 + }, + { + "epoch": 0.02, + "learning_rate": 2.404636053153804e-05, + "loss": 3.9265, + "step": 1585152 + }, + { + "epoch": 0.02, + "learning_rate": 2.403797458402752e-05, + "loss": 3.9234, + "step": 1585664 + }, + { + "epoch": 0.02, + "learning_rate": 2.4029588636517004e-05, + "loss": 3.918, + "step": 1586176 + }, + { + "epoch": 0.02, + "learning_rate": 2.4021219067810214e-05, + "loss": 3.9146, + "step": 1586688 + }, + { + "epoch": 0.02, + "learning_rate": 2.4012833120299694e-05, + "loss": 3.9076, + "step": 1587200 + }, + { + "epoch": 0.02, + "learning_rate": 2.4004447172789174e-05, + "loss": 3.9105, + "step": 1587712 + }, + { + "epoch": 0.02, + "learning_rate": 2.3996061225278653e-05, + "loss": 3.905, + "step": 1588224 + }, + { + "epoch": 0.02, + "learning_rate": 2.3987675277768133e-05, + "loss": 3.9113, + "step": 1588736 + }, + { + "epoch": 0.02, + "learning_rate": 2.3979289330257613e-05, + "loss": 3.9075, + "step": 1589248 + }, + { + "epoch": 0.02, + "learning_rate": 2.3970919761550826e-05, + "loss": 3.9161, + "step": 1589760 + }, + { + "epoch": 0.02, + "learning_rate": 2.3962533814040306e-05, + "loss": 3.9104, + "step": 1590272 + }, + { + "epoch": 0.02, + "learning_rate": 2.3954147866529786e-05, + "loss": 3.9136, + "step": 1590784 + }, + { + "epoch": 0.02, + "learning_rate": 2.3945761919019262e-05, + "loss": 3.9083, + "step": 1591296 + }, + { + "epoch": 0.02, + "learning_rate": 2.3937375971508742e-05, + "loss": 3.9082, + "step": 1591808 + }, + { + "epoch": 0.02, + "learning_rate": 2.3928990023998226e-05, + "loss": 3.9055, + "step": 1592320 + }, + { + "epoch": 0.02, + "learning_rate": 2.3920604076487706e-05, + "loss": 3.9179, + "step": 1592832 + }, + { + "epoch": 0.02, + "learning_rate": 2.3912234507780915e-05, + "loss": 3.9253, + "step": 1593344 + }, + { + "epoch": 0.02, + "learning_rate": 2.3903864939074127e-05, + "loss": 3.9185, + "step": 1593856 + }, + { + "epoch": 0.02, + "learning_rate": 2.3895478991563607e-05, + "loss": 3.909, + "step": 1594368 + }, + { + "epoch": 0.02, + "learning_rate": 2.3887093044053087e-05, + "loss": 3.9168, + "step": 1594880 + }, + { + "epoch": 0.02, + "learning_rate": 2.3878707096542567e-05, + "loss": 3.9127, + "step": 1595392 + }, + { + "epoch": 0.02, + "learning_rate": 2.3870321149032047e-05, + "loss": 3.926, + "step": 1595904 + }, + { + "epoch": 0.02, + "learning_rate": 2.3861935201521527e-05, + "loss": 3.9115, + "step": 1596416 + }, + { + "epoch": 0.02, + "learning_rate": 2.3853549254011007e-05, + "loss": 3.9122, + "step": 1596928 + }, + { + "epoch": 0.02, + "learning_rate": 2.3845163306500487e-05, + "loss": 3.911, + "step": 1597440 + }, + { + "epoch": 0.02, + "learning_rate": 2.3836793737793696e-05, + "loss": 3.9183, + "step": 1597952 + }, + { + "epoch": 0.02, + "learning_rate": 2.3828407790283176e-05, + "loss": 3.9047, + "step": 1598464 + }, + { + "epoch": 0.02, + "learning_rate": 2.382002184277266e-05, + "loss": 3.9096, + "step": 1598976 + }, + { + "epoch": 0.02, + "learning_rate": 2.381163589526214e-05, + "loss": 3.916, + "step": 1599488 + }, + { + "epoch": 0.02, + "learning_rate": 2.380326632655535e-05, + "loss": 3.9094, + "step": 1600000 + }, + { + "epoch": 0.02, + "learning_rate": 2.3794880379044828e-05, + "loss": 3.9156, + "step": 1600512 + }, + { + "epoch": 0.02, + "learning_rate": 2.3786494431534308e-05, + "loss": 3.9179, + "step": 1601024 + }, + { + "epoch": 0.02, + "learning_rate": 2.3778108484023788e-05, + "loss": 3.9128, + "step": 1601536 + }, + { + "epoch": 0.02, + "learning_rate": 2.3769722536513268e-05, + "loss": 3.9112, + "step": 1602048 + }, + { + "epoch": 0.02, + "learning_rate": 2.376135296780648e-05, + "loss": 3.9088, + "step": 1602560 + }, + { + "epoch": 0.03, + "eval_loss": 3.9969327449798584, + "eval_runtime": 298.8854, + "eval_samples_per_second": 1276.713, + "eval_steps_per_second": 39.898, + "step": 1602720 + }, + { + "epoch": 1.0, + "learning_rate": 2.375296702029596e-05, + "loss": 3.9114, + "step": 1603072 + }, + { + "epoch": 1.0, + "learning_rate": 2.374458107278544e-05, + "loss": 3.8975, + "step": 1603584 + }, + { + "epoch": 1.0, + "learning_rate": 2.3736195125274917e-05, + "loss": 3.9211, + "step": 1604096 + }, + { + "epoch": 1.0, + "learning_rate": 2.3727809177764397e-05, + "loss": 3.9121, + "step": 1604608 + }, + { + "epoch": 1.0, + "learning_rate": 2.371942323025388e-05, + "loss": 3.9207, + "step": 1605120 + }, + { + "epoch": 1.0, + "learning_rate": 2.3711053661547093e-05, + "loss": 3.9103, + "step": 1605632 + }, + { + "epoch": 1.0, + "learning_rate": 2.370266771403657e-05, + "loss": 3.9088, + "step": 1606144 + }, + { + "epoch": 1.0, + "learning_rate": 2.369428176652605e-05, + "loss": 3.9001, + "step": 1606656 + }, + { + "epoch": 1.0, + "learning_rate": 2.368589581901553e-05, + "loss": 3.9112, + "step": 1607168 + }, + { + "epoch": 1.0, + "learning_rate": 2.367750987150501e-05, + "loss": 3.9055, + "step": 1607680 + }, + { + "epoch": 1.0, + "learning_rate": 2.366912392399449e-05, + "loss": 3.9199, + "step": 1608192 + }, + { + "epoch": 1.0, + "learning_rate": 2.3660754355287702e-05, + "loss": 3.9207, + "step": 1608704 + }, + { + "epoch": 1.0, + "learning_rate": 2.3652384786580914e-05, + "loss": 3.8948, + "step": 1609216 + }, + { + "epoch": 1.0, + "learning_rate": 2.364399883907039e-05, + "loss": 3.9097, + "step": 1609728 + }, + { + "epoch": 1.0, + "learning_rate": 2.363561289155987e-05, + "loss": 3.9167, + "step": 1610240 + }, + { + "epoch": 1.0, + "learning_rate": 2.362722694404935e-05, + "loss": 3.9012, + "step": 1610752 + }, + { + "epoch": 1.0, + "learning_rate": 2.3618840996538834e-05, + "loss": 3.9095, + "step": 1611264 + }, + { + "epoch": 1.0, + "learning_rate": 2.3610455049028314e-05, + "loss": 3.9083, + "step": 1611776 + }, + { + "epoch": 1.0, + "learning_rate": 2.3602069101517794e-05, + "loss": 3.908, + "step": 1612288 + }, + { + "epoch": 1.0, + "learning_rate": 2.3593683154007274e-05, + "loss": 3.9249, + "step": 1612800 + }, + { + "epoch": 1.0, + "learning_rate": 2.358529720649675e-05, + "loss": 3.9078, + "step": 1613312 + }, + { + "epoch": 1.0, + "learning_rate": 2.357691125898623e-05, + "loss": 3.9168, + "step": 1613824 + }, + { + "epoch": 1.0, + "learning_rate": 2.356852531147571e-05, + "loss": 3.911, + "step": 1614336 + }, + { + "epoch": 1.0, + "learning_rate": 2.3560155742768923e-05, + "loss": 3.9182, + "step": 1614848 + }, + { + "epoch": 1.0, + "learning_rate": 2.3551769795258403e-05, + "loss": 3.9063, + "step": 1615360 + }, + { + "epoch": 1.0, + "learning_rate": 2.3543383847747883e-05, + "loss": 3.9112, + "step": 1615872 + }, + { + "epoch": 1.0, + "learning_rate": 2.3534997900237363e-05, + "loss": 3.9034, + "step": 1616384 + }, + { + "epoch": 1.0, + "learning_rate": 2.3526628331530572e-05, + "loss": 3.9042, + "step": 1616896 + }, + { + "epoch": 1.0, + "learning_rate": 2.3518242384020052e-05, + "loss": 3.9041, + "step": 1617408 + }, + { + "epoch": 1.0, + "learning_rate": 2.3509856436509535e-05, + "loss": 3.9082, + "step": 1617920 + }, + { + "epoch": 1.01, + "learning_rate": 2.3501470488999015e-05, + "loss": 3.9079, + "step": 1618432 + }, + { + "epoch": 1.01, + "learning_rate": 2.3493084541488495e-05, + "loss": 3.9135, + "step": 1618944 + }, + { + "epoch": 1.01, + "learning_rate": 2.3484698593977975e-05, + "loss": 3.916, + "step": 1619456 + }, + { + "epoch": 1.01, + "learning_rate": 2.3476312646467455e-05, + "loss": 3.9167, + "step": 1619968 + }, + { + "epoch": 1.01, + "learning_rate": 2.3467943077760664e-05, + "loss": 3.9078, + "step": 1620480 + }, + { + "epoch": 1.01, + "learning_rate": 2.3459557130250144e-05, + "loss": 3.9119, + "step": 1620992 + }, + { + "epoch": 1.01, + "learning_rate": 2.3451171182739627e-05, + "loss": 3.9033, + "step": 1621504 + }, + { + "epoch": 1.01, + "learning_rate": 2.3442785235229104e-05, + "loss": 3.9089, + "step": 1622016 + }, + { + "epoch": 1.01, + "learning_rate": 2.3434399287718584e-05, + "loss": 3.8991, + "step": 1622528 + }, + { + "epoch": 1.01, + "learning_rate": 2.3426013340208064e-05, + "loss": 3.9028, + "step": 1623040 + }, + { + "epoch": 1.01, + "learning_rate": 2.3417627392697544e-05, + "loss": 3.9081, + "step": 1623552 + }, + { + "epoch": 1.01, + "learning_rate": 2.3409241445187024e-05, + "loss": 3.9139, + "step": 1624064 + }, + { + "epoch": 1.01, + "learning_rate": 2.3400855497676504e-05, + "loss": 3.9021, + "step": 1624576 + }, + { + "epoch": 1.01, + "learning_rate": 2.3392469550165984e-05, + "loss": 3.906, + "step": 1625088 + }, + { + "epoch": 1.01, + "learning_rate": 2.3384099981459196e-05, + "loss": 3.9236, + "step": 1625600 + }, + { + "epoch": 1.01, + "learning_rate": 2.3375714033948676e-05, + "loss": 3.9096, + "step": 1626112 + }, + { + "epoch": 1.01, + "learning_rate": 2.3367328086438156e-05, + "loss": 3.9143, + "step": 1626624 + }, + { + "epoch": 1.01, + "learning_rate": 2.3358942138927633e-05, + "loss": 3.9029, + "step": 1627136 + }, + { + "epoch": 1.01, + "learning_rate": 2.3350556191417113e-05, + "loss": 3.8904, + "step": 1627648 + }, + { + "epoch": 1.01, + "learning_rate": 2.334218662271033e-05, + "loss": 3.9141, + "step": 1628160 + }, + { + "epoch": 1.01, + "learning_rate": 2.333380067519981e-05, + "loss": 3.9097, + "step": 1628672 + }, + { + "epoch": 1.01, + "learning_rate": 2.3325414727689285e-05, + "loss": 3.9015, + "step": 1629184 + }, + { + "epoch": 1.01, + "learning_rate": 2.3317028780178765e-05, + "loss": 3.9046, + "step": 1629696 + }, + { + "epoch": 1.01, + "learning_rate": 2.3308642832668245e-05, + "loss": 3.9134, + "step": 1630208 + }, + { + "epoch": 1.01, + "learning_rate": 2.3300256885157725e-05, + "loss": 3.8877, + "step": 1630720 + }, + { + "epoch": 1.01, + "learning_rate": 2.3291870937647205e-05, + "loss": 3.9124, + "step": 1631232 + }, + { + "epoch": 1.01, + "learning_rate": 2.3283484990136685e-05, + "loss": 3.8941, + "step": 1631744 + }, + { + "epoch": 1.01, + "learning_rate": 2.3275099042626168e-05, + "loss": 3.9039, + "step": 1632256 + }, + { + "epoch": 1.01, + "learning_rate": 2.3266713095115645e-05, + "loss": 3.9131, + "step": 1632768 + }, + { + "epoch": 1.01, + "learning_rate": 2.3258343526408857e-05, + "loss": 3.9033, + "step": 1633280 + }, + { + "epoch": 1.01, + "learning_rate": 2.3249957578898337e-05, + "loss": 3.9012, + "step": 1633792 + }, + { + "epoch": 1.01, + "learning_rate": 2.3241571631387814e-05, + "loss": 3.9095, + "step": 1634304 + }, + { + "epoch": 1.01, + "learning_rate": 2.323320206268103e-05, + "loss": 3.8954, + "step": 1634816 + }, + { + "epoch": 1.01, + "learning_rate": 2.322484887277797e-05, + "loss": 3.8991, + "step": 1635328 + }, + { + "epoch": 1.01, + "learning_rate": 2.321646292526745e-05, + "loss": 3.9095, + "step": 1635840 + }, + { + "epoch": 1.01, + "learning_rate": 2.320807697775693e-05, + "loss": 3.9043, + "step": 1636352 + }, + { + "epoch": 1.01, + "learning_rate": 2.3199691030246408e-05, + "loss": 3.9008, + "step": 1636864 + }, + { + "epoch": 1.01, + "learning_rate": 2.319130508273589e-05, + "loss": 3.8966, + "step": 1637376 + }, + { + "epoch": 1.01, + "learning_rate": 2.318291913522537e-05, + "loss": 3.894, + "step": 1637888 + }, + { + "epoch": 1.01, + "learning_rate": 2.317453318771485e-05, + "loss": 3.9038, + "step": 1638400 + }, + { + "epoch": 1.01, + "learning_rate": 2.316614724020433e-05, + "loss": 3.9161, + "step": 1638912 + }, + { + "epoch": 1.01, + "learning_rate": 2.315776129269381e-05, + "loss": 3.901, + "step": 1639424 + }, + { + "epoch": 1.01, + "learning_rate": 2.3149375345183287e-05, + "loss": 3.9155, + "step": 1639936 + }, + { + "epoch": 1.01, + "learning_rate": 2.3140989397672767e-05, + "loss": 3.9147, + "step": 1640448 + }, + { + "epoch": 1.01, + "learning_rate": 2.313260345016225e-05, + "loss": 3.9071, + "step": 1640960 + }, + { + "epoch": 1.01, + "learning_rate": 2.3124233881455463e-05, + "loss": 3.9008, + "step": 1641472 + }, + { + "epoch": 1.01, + "learning_rate": 2.311584793394494e-05, + "loss": 3.9151, + "step": 1641984 + }, + { + "epoch": 1.01, + "learning_rate": 2.310746198643442e-05, + "loss": 3.9054, + "step": 1642496 + }, + { + "epoch": 1.01, + "learning_rate": 2.30990760389239e-05, + "loss": 3.9021, + "step": 1643008 + }, + { + "epoch": 1.01, + "learning_rate": 2.309069009141338e-05, + "loss": 3.9114, + "step": 1643520 + }, + { + "epoch": 1.01, + "learning_rate": 2.308230414390286e-05, + "loss": 3.9104, + "step": 1644032 + }, + { + "epoch": 1.01, + "learning_rate": 2.307391819639234e-05, + "loss": 3.9157, + "step": 1644544 + }, + { + "epoch": 1.01, + "learning_rate": 2.3065532248881823e-05, + "loss": 3.9087, + "step": 1645056 + }, + { + "epoch": 1.01, + "learning_rate": 2.3057162680175032e-05, + "loss": 3.8952, + "step": 1645568 + }, + { + "epoch": 1.01, + "learning_rate": 2.3048776732664512e-05, + "loss": 3.8926, + "step": 1646080 + }, + { + "epoch": 1.01, + "learning_rate": 2.3040390785153992e-05, + "loss": 3.9023, + "step": 1646592 + }, + { + "epoch": 1.01, + "learning_rate": 2.3032021216447204e-05, + "loss": 3.9077, + "step": 1647104 + }, + { + "epoch": 1.01, + "learning_rate": 2.3023635268936684e-05, + "loss": 3.9039, + "step": 1647616 + }, + { + "epoch": 1.01, + "learning_rate": 2.3015249321426164e-05, + "loss": 3.9049, + "step": 1648128 + }, + { + "epoch": 1.02, + "learning_rate": 2.3006863373915644e-05, + "loss": 3.903, + "step": 1648640 + }, + { + "epoch": 1.02, + "learning_rate": 2.2998493805208853e-05, + "loss": 3.8969, + "step": 1649152 + }, + { + "epoch": 1.02, + "learning_rate": 2.2990107857698333e-05, + "loss": 3.9086, + "step": 1649664 + }, + { + "epoch": 1.02, + "learning_rate": 2.2981721910187813e-05, + "loss": 3.8998, + "step": 1650176 + }, + { + "epoch": 1.02, + "learning_rate": 2.2973335962677293e-05, + "loss": 3.9135, + "step": 1650688 + }, + { + "epoch": 1.02, + "learning_rate": 2.2964950015166773e-05, + "loss": 3.9143, + "step": 1651200 + }, + { + "epoch": 1.02, + "learning_rate": 2.2956564067656253e-05, + "loss": 3.9084, + "step": 1651712 + }, + { + "epoch": 1.02, + "learning_rate": 2.2948178120145733e-05, + "loss": 3.9001, + "step": 1652224 + }, + { + "epoch": 1.02, + "learning_rate": 2.2939792172635213e-05, + "loss": 3.904, + "step": 1652736 + }, + { + "epoch": 1.02, + "learning_rate": 2.2931406225124693e-05, + "loss": 3.9045, + "step": 1653248 + }, + { + "epoch": 1.02, + "learning_rate": 2.2923020277614173e-05, + "loss": 3.9173, + "step": 1653760 + }, + { + "epoch": 1.02, + "learning_rate": 2.2914650708907385e-05, + "loss": 3.9006, + "step": 1654272 + }, + { + "epoch": 1.02, + "learning_rate": 2.2906264761396865e-05, + "loss": 3.8988, + "step": 1654784 + }, + { + "epoch": 1.02, + "learning_rate": 2.2897878813886345e-05, + "loss": 3.9115, + "step": 1655296 + }, + { + "epoch": 1.02, + "learning_rate": 2.2889492866375825e-05, + "loss": 3.9054, + "step": 1655808 + }, + { + "epoch": 1.02, + "learning_rate": 2.2881123297669034e-05, + "loss": 3.9011, + "step": 1656320 + }, + { + "epoch": 1.02, + "learning_rate": 2.2872737350158514e-05, + "loss": 3.9045, + "step": 1656832 + }, + { + "epoch": 1.02, + "learning_rate": 2.2864351402647998e-05, + "loss": 3.901, + "step": 1657344 + }, + { + "epoch": 1.02, + "learning_rate": 2.2855965455137474e-05, + "loss": 3.8972, + "step": 1657856 + }, + { + "epoch": 1.02, + "learning_rate": 2.2847595886430687e-05, + "loss": 3.8921, + "step": 1658368 + }, + { + "epoch": 1.02, + "learning_rate": 2.2839209938920167e-05, + "loss": 3.9081, + "step": 1658880 + }, + { + "epoch": 1.02, + "learning_rate": 2.2830823991409647e-05, + "loss": 3.9034, + "step": 1659392 + }, + { + "epoch": 1.02, + "learning_rate": 2.2822438043899123e-05, + "loss": 3.901, + "step": 1659904 + }, + { + "epoch": 1.02, + "learning_rate": 2.2814052096388607e-05, + "loss": 3.8976, + "step": 1660416 + }, + { + "epoch": 1.02, + "learning_rate": 2.2805666148878086e-05, + "loss": 3.8954, + "step": 1660928 + }, + { + "epoch": 1.02, + "learning_rate": 2.2797280201367566e-05, + "loss": 3.9185, + "step": 1661440 + }, + { + "epoch": 1.02, + "learning_rate": 2.2788894253857046e-05, + "loss": 3.9177, + "step": 1661952 + }, + { + "epoch": 1.02, + "learning_rate": 2.2780508306346526e-05, + "loss": 3.9129, + "step": 1662464 + }, + { + "epoch": 1.02, + "learning_rate": 2.2772138737639735e-05, + "loss": 3.9083, + "step": 1662976 + }, + { + "epoch": 1.02, + "learning_rate": 2.2763752790129215e-05, + "loss": 3.8997, + "step": 1663488 + }, + { + "epoch": 1.02, + "learning_rate": 2.27553668426187e-05, + "loss": 3.9049, + "step": 1664000 + }, + { + "epoch": 1.02, + "learning_rate": 2.2746997273911908e-05, + "loss": 3.8973, + "step": 1664512 + }, + { + "epoch": 1.02, + "learning_rate": 2.2738611326401388e-05, + "loss": 3.9007, + "step": 1665024 + }, + { + "epoch": 1.02, + "learning_rate": 2.2730225378890868e-05, + "loss": 3.9042, + "step": 1665536 + }, + { + "epoch": 1.02, + "learning_rate": 2.2721839431380348e-05, + "loss": 3.9075, + "step": 1666048 + }, + { + "epoch": 1.02, + "learning_rate": 2.2713453483869828e-05, + "loss": 3.9075, + "step": 1666560 + }, + { + "epoch": 1.02, + "learning_rate": 2.2705067536359308e-05, + "loss": 3.9043, + "step": 1667072 + }, + { + "epoch": 1.02, + "learning_rate": 2.2696681588848788e-05, + "loss": 3.9028, + "step": 1667584 + }, + { + "epoch": 1.02, + "learning_rate": 2.2688295641338268e-05, + "loss": 3.9014, + "step": 1668096 + }, + { + "epoch": 1.02, + "learning_rate": 2.267992607263148e-05, + "loss": 3.9005, + "step": 1668608 + }, + { + "epoch": 1.02, + "learning_rate": 2.2671540125120957e-05, + "loss": 3.9056, + "step": 1669120 + }, + { + "epoch": 1.02, + "learning_rate": 2.2663154177610437e-05, + "loss": 3.9159, + "step": 1669632 + }, + { + "epoch": 1.02, + "learning_rate": 2.2654768230099917e-05, + "loss": 3.917, + "step": 1670144 + }, + { + "epoch": 1.02, + "learning_rate": 2.264639866139313e-05, + "loss": 3.8995, + "step": 1670656 + }, + { + "epoch": 1.02, + "learning_rate": 2.263801271388261e-05, + "loss": 3.9116, + "step": 1671168 + }, + { + "epoch": 1.02, + "learning_rate": 2.262962676637209e-05, + "loss": 3.9073, + "step": 1671680 + }, + { + "epoch": 1.02, + "learning_rate": 2.262124081886157e-05, + "loss": 3.9137, + "step": 1672192 + }, + { + "epoch": 1.02, + "learning_rate": 2.2612871250154778e-05, + "loss": 3.907, + "step": 1672704 + }, + { + "epoch": 1.02, + "learning_rate": 2.260448530264426e-05, + "loss": 3.9093, + "step": 1673216 + }, + { + "epoch": 1.02, + "learning_rate": 2.259609935513374e-05, + "loss": 3.9026, + "step": 1673728 + }, + { + "epoch": 1.02, + "learning_rate": 2.258771340762322e-05, + "loss": 3.9094, + "step": 1674240 + }, + { + "epoch": 1.02, + "learning_rate": 2.25793274601127e-05, + "loss": 3.8982, + "step": 1674752 + }, + { + "epoch": 1.02, + "learning_rate": 2.257094151260218e-05, + "loss": 3.9037, + "step": 1675264 + }, + { + "epoch": 1.02, + "learning_rate": 2.256255556509166e-05, + "loss": 3.9048, + "step": 1675776 + }, + { + "epoch": 1.02, + "learning_rate": 2.2554169617581138e-05, + "loss": 3.9067, + "step": 1676288 + }, + { + "epoch": 1.02, + "learning_rate": 2.2545800048874354e-05, + "loss": 3.9079, + "step": 1676800 + }, + { + "epoch": 1.02, + "learning_rate": 2.2537414101363833e-05, + "loss": 3.9048, + "step": 1677312 + }, + { + "epoch": 1.02, + "learning_rate": 2.252902815385331e-05, + "loss": 3.9147, + "step": 1677824 + }, + { + "epoch": 1.02, + "learning_rate": 2.252064220634279e-05, + "loss": 3.9002, + "step": 1678336 + }, + { + "epoch": 1.02, + "learning_rate": 2.251225625883227e-05, + "loss": 3.9042, + "step": 1678848 + }, + { + "epoch": 1.03, + "eval_loss": 3.9940733909606934, + "eval_runtime": 295.4378, + "eval_samples_per_second": 1291.612, + "eval_steps_per_second": 40.364, + "step": 1679040 + }, + { + "epoch": 0.0, + "learning_rate": 2.2503886690125482e-05, + "loss": 3.9001, + "step": 1679360 + }, + { + "epoch": 0.0, + "learning_rate": 2.2495500742614962e-05, + "loss": 3.8902, + "step": 1679872 + }, + { + "epoch": 0.0, + "learning_rate": 2.2487114795104442e-05, + "loss": 3.9131, + "step": 1680384 + }, + { + "epoch": 0.0, + "learning_rate": 2.2478728847593922e-05, + "loss": 3.9062, + "step": 1680896 + }, + { + "epoch": 0.0, + "learning_rate": 2.2470342900083402e-05, + "loss": 3.9145, + "step": 1681408 + }, + { + "epoch": 0.0, + "learning_rate": 2.2461956952572882e-05, + "loss": 3.9024, + "step": 1681920 + }, + { + "epoch": 0.0, + "learning_rate": 2.2453571005062362e-05, + "loss": 3.8977, + "step": 1682432 + }, + { + "epoch": 0.0, + "learning_rate": 2.2445185057551842e-05, + "loss": 3.899, + "step": 1682944 + }, + { + "epoch": 0.0, + "learning_rate": 2.2436799110041322e-05, + "loss": 3.9034, + "step": 1683456 + }, + { + "epoch": 0.0, + "learning_rate": 2.2428413162530802e-05, + "loss": 3.8997, + "step": 1683968 + }, + { + "epoch": 0.0, + "learning_rate": 2.2420027215020282e-05, + "loss": 3.9129, + "step": 1684480 + }, + { + "epoch": 0.0, + "learning_rate": 2.2411641267509762e-05, + "loss": 3.9156, + "step": 1684992 + }, + { + "epoch": 0.0, + "learning_rate": 2.240327169880297e-05, + "loss": 3.8904, + "step": 1685504 + }, + { + "epoch": 0.0, + "learning_rate": 2.239488575129245e-05, + "loss": 3.8977, + "step": 1686016 + }, + { + "epoch": 0.0, + "learning_rate": 2.238649980378193e-05, + "loss": 3.9093, + "step": 1686528 + }, + { + "epoch": 0.0, + "learning_rate": 2.2378113856271414e-05, + "loss": 3.8927, + "step": 1687040 + }, + { + "epoch": 0.0, + "learning_rate": 2.2369727908760894e-05, + "loss": 3.9011, + "step": 1687552 + }, + { + "epoch": 0.0, + "learning_rate": 2.2361358340054103e-05, + "loss": 3.9007, + "step": 1688064 + }, + { + "epoch": 0.0, + "learning_rate": 2.2352972392543583e-05, + "loss": 3.9013, + "step": 1688576 + }, + { + "epoch": 0.0, + "learning_rate": 2.2344586445033063e-05, + "loss": 3.9152, + "step": 1689088 + }, + { + "epoch": 0.0, + "learning_rate": 2.2336200497522543e-05, + "loss": 3.9063, + "step": 1689600 + }, + { + "epoch": 0.0, + "learning_rate": 2.2327814550012023e-05, + "loss": 3.906, + "step": 1690112 + }, + { + "epoch": 0.0, + "learning_rate": 2.2319428602501503e-05, + "loss": 3.9039, + "step": 1690624 + }, + { + "epoch": 0.0, + "learning_rate": 2.2311042654990983e-05, + "loss": 3.9095, + "step": 1691136 + }, + { + "epoch": 0.0, + "learning_rate": 2.2302656707480463e-05, + "loss": 3.9018, + "step": 1691648 + }, + { + "epoch": 0.0, + "learning_rate": 2.2294270759969943e-05, + "loss": 3.9063, + "step": 1692160 + }, + { + "epoch": 0.0, + "learning_rate": 2.2285901191263152e-05, + "loss": 3.8951, + "step": 1692672 + }, + { + "epoch": 0.0, + "learning_rate": 2.2277515243752632e-05, + "loss": 3.8974, + "step": 1693184 + }, + { + "epoch": 0.0, + "learning_rate": 2.2269129296242115e-05, + "loss": 3.8991, + "step": 1693696 + }, + { + "epoch": 0.0, + "learning_rate": 2.2260743348731595e-05, + "loss": 3.9001, + "step": 1694208 + }, + { + "epoch": 0.01, + "learning_rate": 2.2252357401221075e-05, + "loss": 3.902, + "step": 1694720 + }, + { + "epoch": 0.01, + "learning_rate": 2.2243971453710555e-05, + "loss": 3.9053, + "step": 1695232 + }, + { + "epoch": 0.01, + "learning_rate": 2.2235585506200032e-05, + "loss": 3.9098, + "step": 1695744 + }, + { + "epoch": 0.01, + "learning_rate": 2.2227215937493244e-05, + "loss": 3.913, + "step": 1696256 + }, + { + "epoch": 0.01, + "learning_rate": 2.2218846368786457e-05, + "loss": 3.8999, + "step": 1696768 + }, + { + "epoch": 0.01, + "learning_rate": 2.2210460421275937e-05, + "loss": 3.9045, + "step": 1697280 + }, + { + "epoch": 0.01, + "learning_rate": 2.2202074473765417e-05, + "loss": 3.9025, + "step": 1697792 + }, + { + "epoch": 0.01, + "learning_rate": 2.2193688526254897e-05, + "loss": 3.8996, + "step": 1698304 + }, + { + "epoch": 0.01, + "learning_rate": 2.2185302578744377e-05, + "loss": 3.8903, + "step": 1698816 + }, + { + "epoch": 0.01, + "learning_rate": 2.2176916631233853e-05, + "loss": 3.8971, + "step": 1699328 + }, + { + "epoch": 0.01, + "learning_rate": 2.2168530683723333e-05, + "loss": 3.9015, + "step": 1699840 + }, + { + "epoch": 0.01, + "learning_rate": 2.2160144736212816e-05, + "loss": 3.9081, + "step": 1700352 + }, + { + "epoch": 0.01, + "learning_rate": 2.2151758788702296e-05, + "loss": 3.8944, + "step": 1700864 + }, + { + "epoch": 0.01, + "learning_rate": 2.2143389219995506e-05, + "loss": 3.8996, + "step": 1701376 + }, + { + "epoch": 0.01, + "learning_rate": 2.2135003272484985e-05, + "loss": 3.9199, + "step": 1701888 + }, + { + "epoch": 0.01, + "learning_rate": 2.2126617324974465e-05, + "loss": 3.902, + "step": 1702400 + }, + { + "epoch": 0.01, + "learning_rate": 2.2118231377463945e-05, + "loss": 3.9082, + "step": 1702912 + }, + { + "epoch": 0.01, + "learning_rate": 2.2109861808757158e-05, + "loss": 3.8914, + "step": 1703424 + }, + { + "epoch": 0.01, + "learning_rate": 2.2101475861246638e-05, + "loss": 3.8839, + "step": 1703936 + }, + { + "epoch": 0.01, + "learning_rate": 2.209310629253985e-05, + "loss": 3.9136, + "step": 1704448 + }, + { + "epoch": 0.01, + "learning_rate": 2.2084720345029327e-05, + "loss": 3.8979, + "step": 1704960 + }, + { + "epoch": 0.01, + "learning_rate": 2.2076334397518807e-05, + "loss": 3.8958, + "step": 1705472 + }, + { + "epoch": 0.01, + "learning_rate": 2.2067948450008287e-05, + "loss": 3.8966, + "step": 1705984 + }, + { + "epoch": 0.01, + "learning_rate": 2.205956250249777e-05, + "loss": 3.9044, + "step": 1706496 + }, + { + "epoch": 0.01, + "learning_rate": 2.205117655498725e-05, + "loss": 3.8826, + "step": 1707008 + }, + { + "epoch": 0.01, + "learning_rate": 2.204279060747673e-05, + "loss": 3.8991, + "step": 1707520 + }, + { + "epoch": 0.01, + "learning_rate": 2.203440465996621e-05, + "loss": 3.8927, + "step": 1708032 + }, + { + "epoch": 0.01, + "learning_rate": 2.2026018712455687e-05, + "loss": 3.8924, + "step": 1708544 + }, + { + "epoch": 0.01, + "learning_rate": 2.2017632764945167e-05, + "loss": 3.9108, + "step": 1709056 + }, + { + "epoch": 0.01, + "learning_rate": 2.2009246817434646e-05, + "loss": 3.8966, + "step": 1709568 + }, + { + "epoch": 0.01, + "learning_rate": 2.200087724872786e-05, + "loss": 3.8941, + "step": 1710080 + }, + { + "epoch": 0.01, + "learning_rate": 2.199249130121734e-05, + "loss": 3.906, + "step": 1710592 + }, + { + "epoch": 0.01, + "learning_rate": 2.198410535370682e-05, + "loss": 3.8871, + "step": 1711104 + }, + { + "epoch": 0.01, + "learning_rate": 2.19757194061963e-05, + "loss": 3.8961, + "step": 1711616 + }, + { + "epoch": 0.01, + "learning_rate": 2.196733345868578e-05, + "loss": 3.8969, + "step": 1712128 + }, + { + "epoch": 0.01, + "learning_rate": 2.195894751117526e-05, + "loss": 3.8977, + "step": 1712640 + }, + { + "epoch": 0.01, + "learning_rate": 2.195056156366474e-05, + "loss": 3.898, + "step": 1713152 + }, + { + "epoch": 0.01, + "learning_rate": 2.194217561615422e-05, + "loss": 3.8924, + "step": 1713664 + }, + { + "epoch": 0.01, + "learning_rate": 2.193380604744743e-05, + "loss": 3.8819, + "step": 1714176 + }, + { + "epoch": 0.01, + "learning_rate": 2.192542009993691e-05, + "loss": 3.8953, + "step": 1714688 + }, + { + "epoch": 0.01, + "learning_rate": 2.191703415242639e-05, + "loss": 3.909, + "step": 1715200 + }, + { + "epoch": 0.01, + "learning_rate": 2.19086645837196e-05, + "loss": 3.8931, + "step": 1715712 + }, + { + "epoch": 0.01, + "learning_rate": 2.190027863620908e-05, + "loss": 3.9131, + "step": 1716224 + }, + { + "epoch": 0.01, + "learning_rate": 2.1891892688698563e-05, + "loss": 3.9083, + "step": 1716736 + }, + { + "epoch": 0.01, + "learning_rate": 2.188350674118804e-05, + "loss": 3.9051, + "step": 1717248 + }, + { + "epoch": 0.01, + "learning_rate": 2.1875137172481253e-05, + "loss": 3.8906, + "step": 1717760 + }, + { + "epoch": 0.01, + "learning_rate": 2.1866751224970732e-05, + "loss": 3.9084, + "step": 1718272 + }, + { + "epoch": 0.01, + "learning_rate": 2.1858365277460212e-05, + "loss": 3.9006, + "step": 1718784 + }, + { + "epoch": 0.01, + "learning_rate": 2.1849979329949692e-05, + "loss": 3.8912, + "step": 1719296 + }, + { + "epoch": 0.01, + "learning_rate": 2.1841593382439172e-05, + "loss": 3.9083, + "step": 1719808 + }, + { + "epoch": 0.01, + "learning_rate": 2.1833223813732385e-05, + "loss": 3.9032, + "step": 1720320 + }, + { + "epoch": 0.01, + "learning_rate": 2.1824837866221865e-05, + "loss": 3.9096, + "step": 1720832 + }, + { + "epoch": 0.01, + "learning_rate": 2.181645191871134e-05, + "loss": 3.9024, + "step": 1721344 + }, + { + "epoch": 0.01, + "learning_rate": 2.180806597120082e-05, + "loss": 3.8863, + "step": 1721856 + }, + { + "epoch": 0.01, + "learning_rate": 2.17996800236903e-05, + "loss": 3.8852, + "step": 1722368 + }, + { + "epoch": 0.01, + "learning_rate": 2.1791294076179785e-05, + "loss": 3.8918, + "step": 1722880 + }, + { + "epoch": 0.01, + "learning_rate": 2.1782924507472994e-05, + "loss": 3.9036, + "step": 1723392 + }, + { + "epoch": 0.01, + "learning_rate": 2.1774538559962474e-05, + "loss": 3.8995, + "step": 1723904 + }, + { + "epoch": 0.01, + "learning_rate": 2.1766152612451954e-05, + "loss": 3.8947, + "step": 1724416 + }, + { + "epoch": 0.02, + "learning_rate": 2.1757766664941434e-05, + "loss": 3.8984, + "step": 1724928 + }, + { + "epoch": 0.02, + "learning_rate": 2.1749397096234646e-05, + "loss": 3.8931, + "step": 1725440 + }, + { + "epoch": 0.02, + "learning_rate": 2.1741011148724126e-05, + "loss": 3.8967, + "step": 1725952 + }, + { + "epoch": 0.02, + "learning_rate": 2.1732625201213606e-05, + "loss": 3.8909, + "step": 1726464 + }, + { + "epoch": 0.02, + "learning_rate": 2.1724239253703086e-05, + "loss": 3.9134, + "step": 1726976 + }, + { + "epoch": 0.02, + "learning_rate": 2.1715869684996295e-05, + "loss": 3.9071, + "step": 1727488 + }, + { + "epoch": 0.02, + "learning_rate": 2.1707483737485775e-05, + "loss": 3.9011, + "step": 1728000 + }, + { + "epoch": 0.02, + "learning_rate": 2.1699097789975255e-05, + "loss": 3.894, + "step": 1728512 + }, + { + "epoch": 0.02, + "learning_rate": 2.1690711842464735e-05, + "loss": 3.8994, + "step": 1729024 + }, + { + "epoch": 0.02, + "learning_rate": 2.1682325894954218e-05, + "loss": 3.8936, + "step": 1729536 + }, + { + "epoch": 0.02, + "learning_rate": 2.1673939947443695e-05, + "loss": 3.9129, + "step": 1730048 + }, + { + "epoch": 0.02, + "learning_rate": 2.1665553999933175e-05, + "loss": 3.8955, + "step": 1730560 + }, + { + "epoch": 0.02, + "learning_rate": 2.1657168052422655e-05, + "loss": 3.8935, + "step": 1731072 + }, + { + "epoch": 0.02, + "learning_rate": 2.1648782104912135e-05, + "loss": 3.901, + "step": 1731584 + }, + { + "epoch": 0.02, + "learning_rate": 2.1640412536205347e-05, + "loss": 3.9035, + "step": 1732096 + }, + { + "epoch": 0.02, + "learning_rate": 2.1632026588694827e-05, + "loss": 3.8908, + "step": 1732608 + }, + { + "epoch": 0.02, + "learning_rate": 2.1623640641184307e-05, + "loss": 3.8985, + "step": 1733120 + }, + { + "epoch": 0.02, + "learning_rate": 2.1615254693673787e-05, + "loss": 3.8909, + "step": 1733632 + }, + { + "epoch": 0.02, + "learning_rate": 2.1606868746163267e-05, + "loss": 3.8872, + "step": 1734144 + }, + { + "epoch": 0.02, + "learning_rate": 2.1598482798652747e-05, + "loss": 3.8888, + "step": 1734656 + }, + { + "epoch": 0.02, + "learning_rate": 2.1590096851142223e-05, + "loss": 3.8994, + "step": 1735168 + }, + { + "epoch": 0.02, + "learning_rate": 2.1581710903631703e-05, + "loss": 3.8992, + "step": 1735680 + }, + { + "epoch": 0.02, + "learning_rate": 2.1573324956121187e-05, + "loss": 3.8924, + "step": 1736192 + }, + { + "epoch": 0.02, + "learning_rate": 2.1564939008610667e-05, + "loss": 3.8915, + "step": 1736704 + }, + { + "epoch": 0.02, + "learning_rate": 2.1556553061100147e-05, + "loss": 3.8904, + "step": 1737216 + }, + { + "epoch": 0.02, + "learning_rate": 2.1548183492393356e-05, + "loss": 3.9078, + "step": 1737728 + }, + { + "epoch": 0.02, + "learning_rate": 2.1539797544882836e-05, + "loss": 3.9129, + "step": 1738240 + }, + { + "epoch": 0.02, + "learning_rate": 2.1531411597372316e-05, + "loss": 3.9069, + "step": 1738752 + }, + { + "epoch": 0.02, + "learning_rate": 2.1523025649861796e-05, + "loss": 3.9002, + "step": 1739264 + }, + { + "epoch": 0.02, + "learning_rate": 2.1514656081155008e-05, + "loss": 3.8921, + "step": 1739776 + }, + { + "epoch": 0.02, + "learning_rate": 2.150628651244822e-05, + "loss": 3.9001, + "step": 1740288 + }, + { + "epoch": 0.02, + "learning_rate": 2.1497900564937697e-05, + "loss": 3.8881, + "step": 1740800 + }, + { + "epoch": 0.02, + "learning_rate": 2.148953099623091e-05, + "loss": 3.8936, + "step": 1741312 + }, + { + "epoch": 0.02, + "learning_rate": 2.1481145048720393e-05, + "loss": 3.898, + "step": 1741824 + }, + { + "epoch": 0.02, + "learning_rate": 2.1472759101209873e-05, + "loss": 3.8976, + "step": 1742336 + }, + { + "epoch": 0.02, + "learning_rate": 2.146437315369935e-05, + "loss": 3.903, + "step": 1742848 + }, + { + "epoch": 0.02, + "learning_rate": 2.145598720618883e-05, + "loss": 3.8971, + "step": 1743360 + }, + { + "epoch": 0.02, + "learning_rate": 2.144760125867831e-05, + "loss": 3.9018, + "step": 1743872 + }, + { + "epoch": 0.02, + "learning_rate": 2.143921531116779e-05, + "loss": 3.8941, + "step": 1744384 + }, + { + "epoch": 0.02, + "learning_rate": 2.143082936365727e-05, + "loss": 3.8938, + "step": 1744896 + }, + { + "epoch": 0.02, + "learning_rate": 2.142244341614675e-05, + "loss": 3.8988, + "step": 1745408 + }, + { + "epoch": 0.02, + "learning_rate": 2.1414057468636233e-05, + "loss": 3.9057, + "step": 1745920 + }, + { + "epoch": 0.02, + "learning_rate": 2.140567152112571e-05, + "loss": 3.911, + "step": 1746432 + }, + { + "epoch": 0.02, + "learning_rate": 2.139728557361519e-05, + "loss": 3.8931, + "step": 1746944 + }, + { + "epoch": 0.02, + "learning_rate": 2.13889160049084e-05, + "loss": 3.9045, + "step": 1747456 + }, + { + "epoch": 0.02, + "learning_rate": 2.1380530057397878e-05, + "loss": 3.9022, + "step": 1747968 + }, + { + "epoch": 0.02, + "learning_rate": 2.1372144109887358e-05, + "loss": 3.9074, + "step": 1748480 + }, + { + "epoch": 0.02, + "learning_rate": 2.1363774541180574e-05, + "loss": 3.899, + "step": 1748992 + }, + { + "epoch": 0.02, + "learning_rate": 2.1355388593670054e-05, + "loss": 3.9025, + "step": 1749504 + }, + { + "epoch": 0.02, + "learning_rate": 2.134700264615953e-05, + "loss": 3.8926, + "step": 1750016 + }, + { + "epoch": 0.02, + "learning_rate": 2.133861669864901e-05, + "loss": 3.9059, + "step": 1750528 + }, + { + "epoch": 0.02, + "learning_rate": 2.133023075113849e-05, + "loss": 3.8904, + "step": 1751040 + }, + { + "epoch": 0.02, + "learning_rate": 2.132184480362797e-05, + "loss": 3.8959, + "step": 1751552 + }, + { + "epoch": 0.02, + "learning_rate": 2.1313475234921183e-05, + "loss": 3.9, + "step": 1752064 + }, + { + "epoch": 0.02, + "learning_rate": 2.1305089287410663e-05, + "loss": 3.9015, + "step": 1752576 + }, + { + "epoch": 0.02, + "learning_rate": 2.1296703339900143e-05, + "loss": 3.897, + "step": 1753088 + }, + { + "epoch": 0.02, + "learning_rate": 2.1288317392389623e-05, + "loss": 3.9002, + "step": 1753600 + }, + { + "epoch": 0.02, + "learning_rate": 2.1279931444879103e-05, + "loss": 3.9058, + "step": 1754112 + }, + { + "epoch": 0.02, + "learning_rate": 2.1271545497368583e-05, + "loss": 3.8937, + "step": 1754624 + }, + { + "epoch": 0.02, + "learning_rate": 2.1263159549858063e-05, + "loss": 3.9046, + "step": 1755136 + }, + { + "epoch": 0.03, + "eval_loss": 3.99149227142334, + "eval_runtime": 288.6073, + "eval_samples_per_second": 1322.181, + "eval_steps_per_second": 41.319, + "step": 1755360 + }, + { + "epoch": 1.0, + "learning_rate": 2.1254773602347543e-05, + "loss": 3.8957, + "step": 1755648 + }, + { + "epoch": 1.0, + "learning_rate": 2.1246404033640755e-05, + "loss": 3.8857, + "step": 1756160 + }, + { + "epoch": 1.0, + "learning_rate": 2.1238034464933964e-05, + "loss": 3.9023, + "step": 1756672 + }, + { + "epoch": 1.0, + "learning_rate": 2.1229648517423444e-05, + "loss": 3.9008, + "step": 1757184 + }, + { + "epoch": 1.0, + "learning_rate": 2.1221262569912924e-05, + "loss": 3.9043, + "step": 1757696 + }, + { + "epoch": 1.0, + "learning_rate": 2.1212876622402404e-05, + "loss": 3.8974, + "step": 1758208 + }, + { + "epoch": 1.0, + "learning_rate": 2.1204490674891887e-05, + "loss": 3.8946, + "step": 1758720 + }, + { + "epoch": 1.0, + "learning_rate": 2.1196104727381364e-05, + "loss": 3.8936, + "step": 1759232 + }, + { + "epoch": 1.0, + "learning_rate": 2.1187718779870844e-05, + "loss": 3.8996, + "step": 1759744 + }, + { + "epoch": 1.0, + "learning_rate": 2.1179332832360324e-05, + "loss": 3.8927, + "step": 1760256 + }, + { + "epoch": 1.0, + "learning_rate": 2.1170946884849804e-05, + "loss": 3.9043, + "step": 1760768 + }, + { + "epoch": 1.0, + "learning_rate": 2.116259369494675e-05, + "loss": 3.9048, + "step": 1761280 + }, + { + "epoch": 1.0, + "learning_rate": 2.1154224126239958e-05, + "loss": 3.8922, + "step": 1761792 + }, + { + "epoch": 1.0, + "learning_rate": 2.1145838178729438e-05, + "loss": 3.8886, + "step": 1762304 + }, + { + "epoch": 1.0, + "learning_rate": 2.1137452231218918e-05, + "loss": 3.903, + "step": 1762816 + }, + { + "epoch": 1.0, + "learning_rate": 2.1129066283708398e-05, + "loss": 3.8839, + "step": 1763328 + }, + { + "epoch": 1.0, + "learning_rate": 2.1120680336197878e-05, + "loss": 3.8983, + "step": 1763840 + }, + { + "epoch": 1.0, + "learning_rate": 2.1112294388687358e-05, + "loss": 3.8925, + "step": 1764352 + }, + { + "epoch": 1.0, + "learning_rate": 2.1103908441176838e-05, + "loss": 3.8978, + "step": 1764864 + }, + { + "epoch": 1.0, + "learning_rate": 2.109553887247005e-05, + "loss": 3.907, + "step": 1765376 + }, + { + "epoch": 1.0, + "learning_rate": 2.108715292495953e-05, + "loss": 3.9034, + "step": 1765888 + }, + { + "epoch": 1.0, + "learning_rate": 2.1078766977449007e-05, + "loss": 3.9, + "step": 1766400 + }, + { + "epoch": 1.0, + "learning_rate": 2.1070381029938487e-05, + "loss": 3.8949, + "step": 1766912 + }, + { + "epoch": 1.0, + "learning_rate": 2.1061995082427967e-05, + "loss": 3.8997, + "step": 1767424 + }, + { + "epoch": 1.0, + "learning_rate": 2.105360913491745e-05, + "loss": 3.8944, + "step": 1767936 + }, + { + "epoch": 1.0, + "learning_rate": 2.104523956621066e-05, + "loss": 3.8999, + "step": 1768448 + }, + { + "epoch": 1.0, + "learning_rate": 2.103685361870014e-05, + "loss": 3.8917, + "step": 1768960 + }, + { + "epoch": 1.0, + "learning_rate": 2.102846767118962e-05, + "loss": 3.8897, + "step": 1769472 + }, + { + "epoch": 1.0, + "learning_rate": 2.10200817236791e-05, + "loss": 3.8921, + "step": 1769984 + }, + { + "epoch": 1.0, + "learning_rate": 2.101169577616858e-05, + "loss": 3.8987, + "step": 1770496 + }, + { + "epoch": 1.01, + "learning_rate": 2.100330982865806e-05, + "loss": 3.8921, + "step": 1771008 + }, + { + "epoch": 1.01, + "learning_rate": 2.099492388114754e-05, + "loss": 3.9015, + "step": 1771520 + }, + { + "epoch": 1.01, + "learning_rate": 2.098653793363702e-05, + "loss": 3.9059, + "step": 1772032 + }, + { + "epoch": 1.01, + "learning_rate": 2.09781519861265e-05, + "loss": 3.9044, + "step": 1772544 + }, + { + "epoch": 1.01, + "learning_rate": 2.096978241741971e-05, + "loss": 3.8909, + "step": 1773056 + }, + { + "epoch": 1.01, + "learning_rate": 2.0961396469909188e-05, + "loss": 3.8995, + "step": 1773568 + }, + { + "epoch": 1.01, + "learning_rate": 2.0953026901202404e-05, + "loss": 3.8964, + "step": 1774080 + }, + { + "epoch": 1.01, + "learning_rate": 2.0944640953691884e-05, + "loss": 3.8909, + "step": 1774592 + }, + { + "epoch": 1.01, + "learning_rate": 2.0936255006181364e-05, + "loss": 3.8876, + "step": 1775104 + }, + { + "epoch": 1.01, + "learning_rate": 2.092786905867084e-05, + "loss": 3.8884, + "step": 1775616 + }, + { + "epoch": 1.01, + "learning_rate": 2.091948311116032e-05, + "loss": 3.8969, + "step": 1776128 + }, + { + "epoch": 1.01, + "learning_rate": 2.09110971636498e-05, + "loss": 3.9012, + "step": 1776640 + }, + { + "epoch": 1.01, + "learning_rate": 2.090271121613928e-05, + "loss": 3.8864, + "step": 1777152 + }, + { + "epoch": 1.01, + "learning_rate": 2.089432526862876e-05, + "loss": 3.8922, + "step": 1777664 + }, + { + "epoch": 1.01, + "learning_rate": 2.0885939321118243e-05, + "loss": 3.9096, + "step": 1778176 + }, + { + "epoch": 1.01, + "learning_rate": 2.087755337360772e-05, + "loss": 3.896, + "step": 1778688 + }, + { + "epoch": 1.01, + "learning_rate": 2.08691674260972e-05, + "loss": 3.9025, + "step": 1779200 + }, + { + "epoch": 1.01, + "learning_rate": 2.086078147858668e-05, + "loss": 3.8871, + "step": 1779712 + }, + { + "epoch": 1.01, + "learning_rate": 2.0852411909879892e-05, + "loss": 3.8776, + "step": 1780224 + }, + { + "epoch": 1.01, + "learning_rate": 2.0844025962369372e-05, + "loss": 3.9083, + "step": 1780736 + }, + { + "epoch": 1.01, + "learning_rate": 2.0835640014858852e-05, + "loss": 3.8911, + "step": 1781248 + }, + { + "epoch": 1.01, + "learning_rate": 2.0827254067348332e-05, + "loss": 3.8899, + "step": 1781760 + }, + { + "epoch": 1.01, + "learning_rate": 2.0818868119837812e-05, + "loss": 3.8961, + "step": 1782272 + }, + { + "epoch": 1.01, + "learning_rate": 2.0810482172327292e-05, + "loss": 3.8917, + "step": 1782784 + }, + { + "epoch": 1.01, + "learning_rate": 2.0802096224816772e-05, + "loss": 3.8848, + "step": 1783296 + }, + { + "epoch": 1.01, + "learning_rate": 2.079372665610998e-05, + "loss": 3.888, + "step": 1783808 + }, + { + "epoch": 1.01, + "learning_rate": 2.0785340708599464e-05, + "loss": 3.8855, + "step": 1784320 + }, + { + "epoch": 1.01, + "learning_rate": 2.0776954761088944e-05, + "loss": 3.8908, + "step": 1784832 + }, + { + "epoch": 1.01, + "learning_rate": 2.0768568813578424e-05, + "loss": 3.9014, + "step": 1785344 + }, + { + "epoch": 1.01, + "learning_rate": 2.07601828660679e-05, + "loss": 3.8914, + "step": 1785856 + }, + { + "epoch": 1.01, + "learning_rate": 2.075179691855738e-05, + "loss": 3.8892, + "step": 1786368 + }, + { + "epoch": 1.01, + "learning_rate": 2.0743427349850593e-05, + "loss": 3.9024, + "step": 1786880 + }, + { + "epoch": 1.01, + "learning_rate": 2.0735041402340073e-05, + "loss": 3.879, + "step": 1787392 + }, + { + "epoch": 1.01, + "learning_rate": 2.0726655454829553e-05, + "loss": 3.8895, + "step": 1787904 + }, + { + "epoch": 1.01, + "learning_rate": 2.0718269507319033e-05, + "loss": 3.8893, + "step": 1788416 + }, + { + "epoch": 1.01, + "learning_rate": 2.0709883559808513e-05, + "loss": 3.8934, + "step": 1788928 + }, + { + "epoch": 1.01, + "learning_rate": 2.0701497612297993e-05, + "loss": 3.8888, + "step": 1789440 + }, + { + "epoch": 1.01, + "learning_rate": 2.0693111664787473e-05, + "loss": 3.8915, + "step": 1789952 + }, + { + "epoch": 1.01, + "learning_rate": 2.0684742096080682e-05, + "loss": 3.8727, + "step": 1790464 + }, + { + "epoch": 1.01, + "learning_rate": 2.0676356148570166e-05, + "loss": 3.8893, + "step": 1790976 + }, + { + "epoch": 1.01, + "learning_rate": 2.0667970201059645e-05, + "loss": 3.9046, + "step": 1791488 + }, + { + "epoch": 1.01, + "learning_rate": 2.0659584253549125e-05, + "loss": 3.8874, + "step": 1792000 + }, + { + "epoch": 1.01, + "learning_rate": 2.0651198306038605e-05, + "loss": 3.906, + "step": 1792512 + }, + { + "epoch": 1.01, + "learning_rate": 2.0642812358528082e-05, + "loss": 3.8997, + "step": 1793024 + }, + { + "epoch": 1.01, + "learning_rate": 2.0634442789821294e-05, + "loss": 3.9029, + "step": 1793536 + }, + { + "epoch": 1.01, + "learning_rate": 2.0626056842310774e-05, + "loss": 3.8852, + "step": 1794048 + }, + { + "epoch": 1.01, + "learning_rate": 2.0617670894800258e-05, + "loss": 3.9013, + "step": 1794560 + }, + { + "epoch": 1.01, + "learning_rate": 2.0609284947289734e-05, + "loss": 3.8964, + "step": 1795072 + }, + { + "epoch": 1.01, + "learning_rate": 2.0600898999779214e-05, + "loss": 3.8858, + "step": 1795584 + }, + { + "epoch": 1.01, + "learning_rate": 2.0592513052268694e-05, + "loss": 3.9026, + "step": 1796096 + }, + { + "epoch": 1.01, + "learning_rate": 2.0584143483561907e-05, + "loss": 3.8957, + "step": 1796608 + }, + { + "epoch": 1.01, + "learning_rate": 2.0575757536051383e-05, + "loss": 3.9021, + "step": 1797120 + }, + { + "epoch": 1.01, + "learning_rate": 2.0567371588540867e-05, + "loss": 3.9, + "step": 1797632 + }, + { + "epoch": 1.01, + "learning_rate": 2.0558985641030347e-05, + "loss": 3.8767, + "step": 1798144 + }, + { + "epoch": 1.01, + "learning_rate": 2.0550599693519827e-05, + "loss": 3.8854, + "step": 1798656 + }, + { + "epoch": 1.01, + "learning_rate": 2.0542213746009306e-05, + "loss": 3.8832, + "step": 1799168 + }, + { + "epoch": 1.01, + "learning_rate": 2.0533844177302516e-05, + "loss": 3.8983, + "step": 1799680 + }, + { + "epoch": 1.01, + "learning_rate": 2.0525474608595728e-05, + "loss": 3.8948, + "step": 1800192 + }, + { + "epoch": 1.01, + "learning_rate": 2.0517088661085208e-05, + "loss": 3.8883, + "step": 1800704 + }, + { + "epoch": 1.02, + "learning_rate": 2.0508702713574688e-05, + "loss": 3.8914, + "step": 1801216 + }, + { + "epoch": 1.02, + "learning_rate": 2.0500316766064168e-05, + "loss": 3.8887, + "step": 1801728 + }, + { + "epoch": 1.02, + "learning_rate": 2.0491930818553648e-05, + "loss": 3.8898, + "step": 1802240 + }, + { + "epoch": 1.02, + "learning_rate": 2.0483544871043128e-05, + "loss": 3.8861, + "step": 1802752 + }, + { + "epoch": 1.02, + "learning_rate": 2.0475158923532608e-05, + "loss": 3.9037, + "step": 1803264 + }, + { + "epoch": 1.02, + "learning_rate": 2.0466772976022088e-05, + "loss": 3.9072, + "step": 1803776 + }, + { + "epoch": 1.02, + "learning_rate": 2.0458387028511568e-05, + "loss": 3.8898, + "step": 1804288 + }, + { + "epoch": 1.02, + "learning_rate": 2.045001745980478e-05, + "loss": 3.8878, + "step": 1804800 + }, + { + "epoch": 1.02, + "learning_rate": 2.044163151229426e-05, + "loss": 3.8929, + "step": 1805312 + }, + { + "epoch": 1.02, + "learning_rate": 2.0433245564783737e-05, + "loss": 3.888, + "step": 1805824 + }, + { + "epoch": 1.02, + "learning_rate": 2.0424859617273217e-05, + "loss": 3.9056, + "step": 1806336 + }, + { + "epoch": 1.02, + "learning_rate": 2.0416473669762697e-05, + "loss": 3.8914, + "step": 1806848 + }, + { + "epoch": 1.02, + "learning_rate": 2.0408104101055912e-05, + "loss": 3.8903, + "step": 1807360 + }, + { + "epoch": 1.02, + "learning_rate": 2.039971815354539e-05, + "loss": 3.8974, + "step": 1807872 + }, + { + "epoch": 1.02, + "learning_rate": 2.039133220603487e-05, + "loss": 3.8977, + "step": 1808384 + }, + { + "epoch": 1.02, + "learning_rate": 2.038294625852435e-05, + "loss": 3.8833, + "step": 1808896 + }, + { + "epoch": 1.02, + "learning_rate": 2.037456031101383e-05, + "loss": 3.8917, + "step": 1809408 + }, + { + "epoch": 1.02, + "learning_rate": 2.036619074230704e-05, + "loss": 3.8891, + "step": 1809920 + }, + { + "epoch": 1.02, + "learning_rate": 2.0357821173600254e-05, + "loss": 3.8808, + "step": 1810432 + }, + { + "epoch": 1.02, + "learning_rate": 2.0349435226089734e-05, + "loss": 3.8845, + "step": 1810944 + }, + { + "epoch": 1.02, + "learning_rate": 2.034104927857921e-05, + "loss": 3.8926, + "step": 1811456 + }, + { + "epoch": 1.02, + "learning_rate": 2.033266333106869e-05, + "loss": 3.8917, + "step": 1811968 + }, + { + "epoch": 1.02, + "learning_rate": 2.032427738355817e-05, + "loss": 3.8868, + "step": 1812480 + }, + { + "epoch": 1.02, + "learning_rate": 2.031589143604765e-05, + "loss": 3.8879, + "step": 1812992 + }, + { + "epoch": 1.02, + "learning_rate": 2.030750548853713e-05, + "loss": 3.8854, + "step": 1813504 + }, + { + "epoch": 1.02, + "learning_rate": 2.0299119541026614e-05, + "loss": 3.9047, + "step": 1814016 + }, + { + "epoch": 1.02, + "learning_rate": 2.0290733593516094e-05, + "loss": 3.9068, + "step": 1814528 + }, + { + "epoch": 1.02, + "learning_rate": 2.0282364024809303e-05, + "loss": 3.9009, + "step": 1815040 + }, + { + "epoch": 1.02, + "learning_rate": 2.0273978077298783e-05, + "loss": 3.8935, + "step": 1815552 + }, + { + "epoch": 1.02, + "learning_rate": 2.026560850859199e-05, + "loss": 3.8838, + "step": 1816064 + }, + { + "epoch": 1.02, + "learning_rate": 2.0257222561081475e-05, + "loss": 3.8956, + "step": 1816576 + }, + { + "epoch": 1.02, + "learning_rate": 2.0248836613570955e-05, + "loss": 3.8837, + "step": 1817088 + }, + { + "epoch": 1.02, + "learning_rate": 2.0240450666060435e-05, + "loss": 3.8919, + "step": 1817600 + }, + { + "epoch": 1.02, + "learning_rate": 2.0232064718549915e-05, + "loss": 3.885, + "step": 1818112 + }, + { + "epoch": 1.02, + "learning_rate": 2.022367877103939e-05, + "loss": 3.8915, + "step": 1818624 + }, + { + "epoch": 1.02, + "learning_rate": 2.021529282352887e-05, + "loss": 3.893, + "step": 1819136 + }, + { + "epoch": 1.02, + "learning_rate": 2.020690687601835e-05, + "loss": 3.8936, + "step": 1819648 + }, + { + "epoch": 1.02, + "learning_rate": 2.0198520928507835e-05, + "loss": 3.8958, + "step": 1820160 + }, + { + "epoch": 1.02, + "learning_rate": 2.0190134980997315e-05, + "loss": 3.8911, + "step": 1820672 + }, + { + "epoch": 1.02, + "learning_rate": 2.0181749033486795e-05, + "loss": 3.8886, + "step": 1821184 + }, + { + "epoch": 1.02, + "learning_rate": 2.0173363085976275e-05, + "loss": 3.8954, + "step": 1821696 + }, + { + "epoch": 1.02, + "learning_rate": 2.0164993517269484e-05, + "loss": 3.897, + "step": 1822208 + }, + { + "epoch": 1.02, + "learning_rate": 2.0156607569758964e-05, + "loss": 3.9049, + "step": 1822720 + }, + { + "epoch": 1.02, + "learning_rate": 2.0148221622248444e-05, + "loss": 3.8878, + "step": 1823232 + }, + { + "epoch": 1.02, + "learning_rate": 2.0139852053541656e-05, + "loss": 3.9018, + "step": 1823744 + }, + { + "epoch": 1.02, + "learning_rate": 2.0131466106031136e-05, + "loss": 3.8949, + "step": 1824256 + }, + { + "epoch": 1.02, + "learning_rate": 2.0123080158520616e-05, + "loss": 3.9014, + "step": 1824768 + }, + { + "epoch": 1.02, + "learning_rate": 2.0114694211010096e-05, + "loss": 3.8956, + "step": 1825280 + }, + { + "epoch": 1.02, + "learning_rate": 2.0106324642303305e-05, + "loss": 3.8952, + "step": 1825792 + }, + { + "epoch": 1.02, + "learning_rate": 2.0097938694792785e-05, + "loss": 3.8882, + "step": 1826304 + }, + { + "epoch": 1.02, + "learning_rate": 2.008955274728227e-05, + "loss": 3.9015, + "step": 1826816 + }, + { + "epoch": 1.02, + "learning_rate": 2.0081166799771748e-05, + "loss": 3.8808, + "step": 1827328 + }, + { + "epoch": 1.02, + "learning_rate": 2.0072780852261225e-05, + "loss": 3.8909, + "step": 1827840 + }, + { + "epoch": 1.02, + "learning_rate": 2.0064394904750705e-05, + "loss": 3.8973, + "step": 1828352 + }, + { + "epoch": 1.02, + "learning_rate": 2.0056008957240185e-05, + "loss": 3.8959, + "step": 1828864 + }, + { + "epoch": 1.02, + "learning_rate": 2.0047623009729665e-05, + "loss": 3.8888, + "step": 1829376 + }, + { + "epoch": 1.02, + "learning_rate": 2.0039237062219145e-05, + "loss": 3.8909, + "step": 1829888 + }, + { + "epoch": 1.02, + "learning_rate": 2.0030867493512357e-05, + "loss": 3.9043, + "step": 1830400 + }, + { + "epoch": 1.02, + "learning_rate": 2.0022481546001837e-05, + "loss": 3.886, + "step": 1830912 + }, + { + "epoch": 1.02, + "learning_rate": 2.0014111977295046e-05, + "loss": 3.8983, + "step": 1831424 + }, + { + "epoch": 1.03, + "eval_loss": 3.989114999771118, + "eval_runtime": 286.6918, + "eval_samples_per_second": 1331.015, + "eval_steps_per_second": 41.595, + "step": 1831680 + }, + { + "epoch": 0.0, + "learning_rate": 2.0005726029784526e-05, + "loss": 3.8791, + "step": 1831936 + }, + { + "epoch": 0.0, + "learning_rate": 1.9997340082274006e-05, + "loss": 3.8868, + "step": 1832448 + }, + { + "epoch": 0.0, + "learning_rate": 1.998895413476349e-05, + "loss": 3.8912, + "step": 1832960 + }, + { + "epoch": 0.0, + "learning_rate": 1.998056818725297e-05, + "loss": 3.8937, + "step": 1833472 + }, + { + "epoch": 0.0, + "learning_rate": 1.997218223974245e-05, + "loss": 3.9027, + "step": 1833984 + }, + { + "epoch": 0.0, + "learning_rate": 1.996379629223193e-05, + "loss": 3.8879, + "step": 1834496 + }, + { + "epoch": 0.0, + "learning_rate": 1.9955410344721406e-05, + "loss": 3.8915, + "step": 1835008 + }, + { + "epoch": 0.0, + "learning_rate": 1.9947024397210886e-05, + "loss": 3.8903, + "step": 1835520 + }, + { + "epoch": 0.0, + "learning_rate": 1.9938638449700366e-05, + "loss": 3.8879, + "step": 1836032 + }, + { + "epoch": 0.0, + "learning_rate": 1.9930252502189846e-05, + "loss": 3.8875, + "step": 1836544 + }, + { + "epoch": 0.0, + "learning_rate": 1.992186655467933e-05, + "loss": 3.8988, + "step": 1837056 + }, + { + "epoch": 0.0, + "learning_rate": 1.991348060716881e-05, + "loss": 3.9013, + "step": 1837568 + }, + { + "epoch": 0.0, + "learning_rate": 1.9905111038462018e-05, + "loss": 3.886, + "step": 1838080 + }, + { + "epoch": 0.0, + "learning_rate": 1.9896725090951498e-05, + "loss": 3.8839, + "step": 1838592 + }, + { + "epoch": 0.0, + "learning_rate": 1.9888339143440978e-05, + "loss": 3.8961, + "step": 1839104 + }, + { + "epoch": 0.0, + "learning_rate": 1.9879953195930458e-05, + "loss": 3.8769, + "step": 1839616 + }, + { + "epoch": 0.0, + "learning_rate": 1.9871567248419938e-05, + "loss": 3.8933, + "step": 1840128 + }, + { + "epoch": 0.0, + "learning_rate": 1.9863181300909418e-05, + "loss": 3.8864, + "step": 1840640 + }, + { + "epoch": 0.0, + "learning_rate": 1.9854795353398898e-05, + "loss": 3.8916, + "step": 1841152 + }, + { + "epoch": 0.0, + "learning_rate": 1.9846409405888378e-05, + "loss": 3.8966, + "step": 1841664 + }, + { + "epoch": 0.0, + "learning_rate": 1.9838023458377858e-05, + "loss": 3.9009, + "step": 1842176 + }, + { + "epoch": 0.0, + "learning_rate": 1.9829637510867338e-05, + "loss": 3.895, + "step": 1842688 + }, + { + "epoch": 0.0, + "learning_rate": 1.9821251563356814e-05, + "loss": 3.889, + "step": 1843200 + }, + { + "epoch": 0.0, + "learning_rate": 1.9812865615846298e-05, + "loss": 3.8926, + "step": 1843712 + }, + { + "epoch": 0.0, + "learning_rate": 1.980449604713951e-05, + "loss": 3.8933, + "step": 1844224 + }, + { + "epoch": 0.0, + "learning_rate": 1.979611009962899e-05, + "loss": 3.8947, + "step": 1844736 + }, + { + "epoch": 0.0, + "learning_rate": 1.9787724152118467e-05, + "loss": 3.8871, + "step": 1845248 + }, + { + "epoch": 0.0, + "learning_rate": 1.9779338204607947e-05, + "loss": 3.8839, + "step": 1845760 + }, + { + "epoch": 0.0, + "learning_rate": 1.977096863590116e-05, + "loss": 3.8894, + "step": 1846272 + }, + { + "epoch": 0.0, + "learning_rate": 1.976258268839064e-05, + "loss": 3.8868, + "step": 1846784 + }, + { + "epoch": 0.01, + "learning_rate": 1.975419674088012e-05, + "loss": 3.8853, + "step": 1847296 + }, + { + "epoch": 0.01, + "learning_rate": 1.97458107933696e-05, + "loss": 3.9001, + "step": 1847808 + }, + { + "epoch": 0.01, + "learning_rate": 1.973742484585908e-05, + "loss": 3.8965, + "step": 1848320 + }, + { + "epoch": 0.01, + "learning_rate": 1.972903889834856e-05, + "loss": 3.8955, + "step": 1848832 + }, + { + "epoch": 0.01, + "learning_rate": 1.972065295083804e-05, + "loss": 3.8861, + "step": 1849344 + }, + { + "epoch": 0.01, + "learning_rate": 1.971228338213125e-05, + "loss": 3.8984, + "step": 1849856 + }, + { + "epoch": 0.01, + "learning_rate": 1.970389743462073e-05, + "loss": 3.8922, + "step": 1850368 + }, + { + "epoch": 0.01, + "learning_rate": 1.969551148711021e-05, + "loss": 3.8877, + "step": 1850880 + }, + { + "epoch": 0.01, + "learning_rate": 1.968712553959969e-05, + "loss": 3.8774, + "step": 1851392 + }, + { + "epoch": 0.01, + "learning_rate": 1.967873959208917e-05, + "loss": 3.8818, + "step": 1851904 + }, + { + "epoch": 0.01, + "learning_rate": 1.9670353644578648e-05, + "loss": 3.887, + "step": 1852416 + }, + { + "epoch": 0.01, + "learning_rate": 1.9661967697068128e-05, + "loss": 3.8974, + "step": 1852928 + }, + { + "epoch": 0.01, + "learning_rate": 1.965359812836134e-05, + "loss": 3.8825, + "step": 1853440 + }, + { + "epoch": 0.01, + "learning_rate": 1.9645212180850824e-05, + "loss": 3.8864, + "step": 1853952 + }, + { + "epoch": 0.01, + "learning_rate": 1.9636842612144033e-05, + "loss": 3.9028, + "step": 1854464 + }, + { + "epoch": 0.01, + "learning_rate": 1.9628456664633513e-05, + "loss": 3.8895, + "step": 1854976 + }, + { + "epoch": 0.01, + "learning_rate": 1.9620070717122993e-05, + "loss": 3.8985, + "step": 1855488 + }, + { + "epoch": 0.01, + "learning_rate": 1.961168476961247e-05, + "loss": 3.8827, + "step": 1856000 + }, + { + "epoch": 0.01, + "learning_rate": 1.9603298822101952e-05, + "loss": 3.8669, + "step": 1856512 + }, + { + "epoch": 0.01, + "learning_rate": 1.9594912874591432e-05, + "loss": 3.9042, + "step": 1857024 + }, + { + "epoch": 0.01, + "learning_rate": 1.9586526927080912e-05, + "loss": 3.888, + "step": 1857536 + }, + { + "epoch": 0.01, + "learning_rate": 1.9578140979570392e-05, + "loss": 3.8865, + "step": 1858048 + }, + { + "epoch": 0.01, + "learning_rate": 1.9569755032059872e-05, + "loss": 3.8856, + "step": 1858560 + }, + { + "epoch": 0.01, + "learning_rate": 1.9561369084549352e-05, + "loss": 3.8876, + "step": 1859072 + }, + { + "epoch": 0.01, + "learning_rate": 1.955298313703883e-05, + "loss": 3.8787, + "step": 1859584 + }, + { + "epoch": 0.01, + "learning_rate": 1.9544613568332045e-05, + "loss": 3.8797, + "step": 1860096 + }, + { + "epoch": 0.01, + "learning_rate": 1.9536227620821525e-05, + "loss": 3.8823, + "step": 1860608 + }, + { + "epoch": 0.01, + "learning_rate": 1.9527841673311005e-05, + "loss": 3.8825, + "step": 1861120 + }, + { + "epoch": 0.01, + "learning_rate": 1.951945572580048e-05, + "loss": 3.8973, + "step": 1861632 + }, + { + "epoch": 0.01, + "learning_rate": 1.951106977828996e-05, + "loss": 3.8839, + "step": 1862144 + }, + { + "epoch": 0.01, + "learning_rate": 1.950268383077944e-05, + "loss": 3.8818, + "step": 1862656 + }, + { + "epoch": 0.01, + "learning_rate": 1.9494314262072654e-05, + "loss": 3.9035, + "step": 1863168 + }, + { + "epoch": 0.01, + "learning_rate": 1.9485928314562133e-05, + "loss": 3.8702, + "step": 1863680 + }, + { + "epoch": 0.01, + "learning_rate": 1.9477542367051613e-05, + "loss": 3.8798, + "step": 1864192 + }, + { + "epoch": 0.01, + "learning_rate": 1.9469156419541093e-05, + "loss": 3.8871, + "step": 1864704 + }, + { + "epoch": 0.01, + "learning_rate": 1.9460770472030573e-05, + "loss": 3.8887, + "step": 1865216 + }, + { + "epoch": 0.01, + "learning_rate": 1.9452384524520053e-05, + "loss": 3.8819, + "step": 1865728 + }, + { + "epoch": 0.01, + "learning_rate": 1.9443998577009533e-05, + "loss": 3.8878, + "step": 1866240 + }, + { + "epoch": 0.01, + "learning_rate": 1.9435629008302746e-05, + "loss": 3.8679, + "step": 1866752 + }, + { + "epoch": 0.01, + "learning_rate": 1.9427243060792226e-05, + "loss": 3.8811, + "step": 1867264 + }, + { + "epoch": 0.01, + "learning_rate": 1.9418857113281706e-05, + "loss": 3.8979, + "step": 1867776 + }, + { + "epoch": 0.01, + "learning_rate": 1.9410471165771186e-05, + "loss": 3.8801, + "step": 1868288 + }, + { + "epoch": 0.01, + "learning_rate": 1.9402085218260662e-05, + "loss": 3.9, + "step": 1868800 + }, + { + "epoch": 0.01, + "learning_rate": 1.9393699270750142e-05, + "loss": 3.8969, + "step": 1869312 + }, + { + "epoch": 0.01, + "learning_rate": 1.9385329702043355e-05, + "loss": 3.9002, + "step": 1869824 + }, + { + "epoch": 0.01, + "learning_rate": 1.9376943754532835e-05, + "loss": 3.8764, + "step": 1870336 + }, + { + "epoch": 0.01, + "learning_rate": 1.9368557807022315e-05, + "loss": 3.8953, + "step": 1870848 + }, + { + "epoch": 0.01, + "learning_rate": 1.9360171859511794e-05, + "loss": 3.8934, + "step": 1871360 + }, + { + "epoch": 0.01, + "learning_rate": 1.9351785912001274e-05, + "loss": 3.8772, + "step": 1871872 + }, + { + "epoch": 0.01, + "learning_rate": 1.9343416343294484e-05, + "loss": 3.8983, + "step": 1872384 + }, + { + "epoch": 0.01, + "learning_rate": 1.9335030395783964e-05, + "loss": 3.8907, + "step": 1872896 + }, + { + "epoch": 0.01, + "learning_rate": 1.9326644448273447e-05, + "loss": 3.8943, + "step": 1873408 + }, + { + "epoch": 0.01, + "learning_rate": 1.9318258500762927e-05, + "loss": 3.8943, + "step": 1873920 + }, + { + "epoch": 0.01, + "learning_rate": 1.9309872553252407e-05, + "loss": 3.8751, + "step": 1874432 + }, + { + "epoch": 0.01, + "learning_rate": 1.9301486605741887e-05, + "loss": 3.8776, + "step": 1874944 + }, + { + "epoch": 0.01, + "learning_rate": 1.9293100658231363e-05, + "loss": 3.8803, + "step": 1875456 + }, + { + "epoch": 0.01, + "learning_rate": 1.9284714710720843e-05, + "loss": 3.8896, + "step": 1875968 + }, + { + "epoch": 0.01, + "learning_rate": 1.9276345142014056e-05, + "loss": 3.8883, + "step": 1876480 + }, + { + "epoch": 0.01, + "learning_rate": 1.9267975573307268e-05, + "loss": 3.8819, + "step": 1876992 + }, + { + "epoch": 0.02, + "learning_rate": 1.9259589625796748e-05, + "loss": 3.885, + "step": 1877504 + }, + { + "epoch": 0.02, + "learning_rate": 1.9251203678286228e-05, + "loss": 3.8867, + "step": 1878016 + }, + { + "epoch": 0.02, + "learning_rate": 1.9242817730775708e-05, + "loss": 3.8842, + "step": 1878528 + }, + { + "epoch": 0.02, + "learning_rate": 1.9234431783265188e-05, + "loss": 3.8808, + "step": 1879040 + }, + { + "epoch": 0.02, + "learning_rate": 1.92260622145584e-05, + "loss": 3.9018, + "step": 1879552 + }, + { + "epoch": 0.02, + "learning_rate": 1.921767626704788e-05, + "loss": 3.8965, + "step": 1880064 + }, + { + "epoch": 0.02, + "learning_rate": 1.920929031953736e-05, + "loss": 3.8912, + "step": 1880576 + }, + { + "epoch": 0.02, + "learning_rate": 1.9200904372026837e-05, + "loss": 3.8796, + "step": 1881088 + }, + { + "epoch": 0.02, + "learning_rate": 1.9192518424516317e-05, + "loss": 3.8871, + "step": 1881600 + }, + { + "epoch": 0.02, + "learning_rate": 1.9184165234613262e-05, + "loss": 3.8835, + "step": 1882112 + }, + { + "epoch": 0.02, + "learning_rate": 1.9175779287102742e-05, + "loss": 3.9, + "step": 1882624 + }, + { + "epoch": 0.02, + "learning_rate": 1.9167393339592222e-05, + "loss": 3.8848, + "step": 1883136 + }, + { + "epoch": 0.02, + "learning_rate": 1.9159007392081702e-05, + "loss": 3.8847, + "step": 1883648 + }, + { + "epoch": 0.02, + "learning_rate": 1.9150621444571182e-05, + "loss": 3.8891, + "step": 1884160 + }, + { + "epoch": 0.02, + "learning_rate": 1.9142235497060662e-05, + "loss": 3.8947, + "step": 1884672 + }, + { + "epoch": 0.02, + "learning_rate": 1.913384954955014e-05, + "loss": 3.8775, + "step": 1885184 + }, + { + "epoch": 0.02, + "learning_rate": 1.9125463602039618e-05, + "loss": 3.8857, + "step": 1885696 + }, + { + "epoch": 0.02, + "learning_rate": 1.91170776545291e-05, + "loss": 3.8802, + "step": 1886208 + }, + { + "epoch": 0.02, + "learning_rate": 1.910869170701858e-05, + "loss": 3.8776, + "step": 1886720 + }, + { + "epoch": 0.02, + "learning_rate": 1.910030575950806e-05, + "loss": 3.8787, + "step": 1887232 + }, + { + "epoch": 0.02, + "learning_rate": 1.909191981199754e-05, + "loss": 3.885, + "step": 1887744 + }, + { + "epoch": 0.02, + "learning_rate": 1.908355024329075e-05, + "loss": 3.8827, + "step": 1888256 + }, + { + "epoch": 0.02, + "learning_rate": 1.907516429578023e-05, + "loss": 3.8864, + "step": 1888768 + }, + { + "epoch": 0.02, + "learning_rate": 1.906677834826971e-05, + "loss": 3.8825, + "step": 1889280 + }, + { + "epoch": 0.02, + "learning_rate": 1.9058408779562923e-05, + "loss": 3.8792, + "step": 1889792 + }, + { + "epoch": 0.02, + "learning_rate": 1.9050022832052403e-05, + "loss": 3.8945, + "step": 1890304 + }, + { + "epoch": 0.02, + "learning_rate": 1.9041636884541883e-05, + "loss": 3.9021, + "step": 1890816 + }, + { + "epoch": 0.02, + "learning_rate": 1.9033250937031363e-05, + "loss": 3.8921, + "step": 1891328 + }, + { + "epoch": 0.02, + "learning_rate": 1.9024881368324572e-05, + "loss": 3.8949, + "step": 1891840 + }, + { + "epoch": 0.02, + "learning_rate": 1.9016495420814055e-05, + "loss": 3.8746, + "step": 1892352 + }, + { + "epoch": 0.02, + "learning_rate": 1.9008109473303535e-05, + "loss": 3.8907, + "step": 1892864 + }, + { + "epoch": 0.02, + "learning_rate": 1.8999723525793015e-05, + "loss": 3.8827, + "step": 1893376 + }, + { + "epoch": 0.02, + "learning_rate": 1.8991337578282492e-05, + "loss": 3.8832, + "step": 1893888 + }, + { + "epoch": 0.02, + "learning_rate": 1.8982951630771972e-05, + "loss": 3.8794, + "step": 1894400 + }, + { + "epoch": 0.02, + "learning_rate": 1.897456568326145e-05, + "loss": 3.8833, + "step": 1894912 + }, + { + "epoch": 0.02, + "learning_rate": 1.896617973575093e-05, + "loss": 3.8886, + "step": 1895424 + }, + { + "epoch": 0.02, + "learning_rate": 1.8957793788240415e-05, + "loss": 3.886, + "step": 1895936 + }, + { + "epoch": 0.02, + "learning_rate": 1.8949424219533624e-05, + "loss": 3.8915, + "step": 1896448 + }, + { + "epoch": 0.02, + "learning_rate": 1.8941038272023104e-05, + "loss": 3.8863, + "step": 1896960 + }, + { + "epoch": 0.02, + "learning_rate": 1.8932652324512584e-05, + "loss": 3.8795, + "step": 1897472 + }, + { + "epoch": 0.02, + "learning_rate": 1.8924266377002064e-05, + "loss": 3.8918, + "step": 1897984 + }, + { + "epoch": 0.02, + "learning_rate": 1.8915896808295276e-05, + "loss": 3.8925, + "step": 1898496 + }, + { + "epoch": 0.02, + "learning_rate": 1.8907510860784756e-05, + "loss": 3.8992, + "step": 1899008 + }, + { + "epoch": 0.02, + "learning_rate": 1.8899124913274236e-05, + "loss": 3.879, + "step": 1899520 + }, + { + "epoch": 0.02, + "learning_rate": 1.8890755344567445e-05, + "loss": 3.897, + "step": 1900032 + }, + { + "epoch": 0.02, + "learning_rate": 1.8882369397056925e-05, + "loss": 3.8893, + "step": 1900544 + }, + { + "epoch": 0.02, + "learning_rate": 1.8873983449546405e-05, + "loss": 3.8945, + "step": 1901056 + }, + { + "epoch": 0.02, + "learning_rate": 1.8865597502035885e-05, + "loss": 3.8905, + "step": 1901568 + }, + { + "epoch": 0.02, + "learning_rate": 1.8857227933329098e-05, + "loss": 3.889, + "step": 1902080 + }, + { + "epoch": 0.02, + "learning_rate": 1.8848841985818578e-05, + "loss": 3.8826, + "step": 1902592 + }, + { + "epoch": 0.02, + "learning_rate": 1.8840456038308058e-05, + "loss": 3.8961, + "step": 1903104 + }, + { + "epoch": 0.02, + "learning_rate": 1.8832070090797538e-05, + "loss": 3.8797, + "step": 1903616 + }, + { + "epoch": 0.02, + "learning_rate": 1.8823684143287018e-05, + "loss": 3.8845, + "step": 1904128 + }, + { + "epoch": 0.02, + "learning_rate": 1.8815298195776498e-05, + "loss": 3.8906, + "step": 1904640 + }, + { + "epoch": 0.02, + "learning_rate": 1.8806912248265978e-05, + "loss": 3.8948, + "step": 1905152 + }, + { + "epoch": 0.02, + "learning_rate": 1.879854267955919e-05, + "loss": 3.8802, + "step": 1905664 + }, + { + "epoch": 0.02, + "learning_rate": 1.879015673204867e-05, + "loss": 3.8874, + "step": 1906176 + }, + { + "epoch": 0.02, + "learning_rate": 1.8781770784538147e-05, + "loss": 3.8935, + "step": 1906688 + }, + { + "epoch": 0.02, + "learning_rate": 1.8773384837027626e-05, + "loss": 3.888, + "step": 1907200 + }, + { + "epoch": 0.02, + "learning_rate": 1.876501526832084e-05, + "loss": 3.8929, + "step": 1907712 + }, + { + "epoch": 0.03, + "eval_loss": 3.9868273735046387, + "eval_runtime": 286.6646, + "eval_samples_per_second": 1331.141, + "eval_steps_per_second": 41.599, + "step": 1908000 + }, + { + "epoch": 1.0, + "learning_rate": 1.875662932081032e-05, + "loss": 3.875, + "step": 1908224 + }, + { + "epoch": 1.0, + "learning_rate": 1.87482433732998e-05, + "loss": 3.8837, + "step": 1908736 + }, + { + "epoch": 1.0, + "learning_rate": 1.873985742578928e-05, + "loss": 3.8868, + "step": 1909248 + }, + { + "epoch": 1.0, + "learning_rate": 1.873147147827876e-05, + "loss": 3.8893, + "step": 1909760 + }, + { + "epoch": 1.0, + "learning_rate": 1.8723101909571968e-05, + "loss": 3.8973, + "step": 1910272 + }, + { + "epoch": 1.0, + "learning_rate": 1.8714715962061448e-05, + "loss": 3.882, + "step": 1910784 + }, + { + "epoch": 1.0, + "learning_rate": 1.870633001455093e-05, + "loss": 3.8854, + "step": 1911296 + }, + { + "epoch": 1.0, + "learning_rate": 1.869794406704041e-05, + "loss": 3.8849, + "step": 1911808 + }, + { + "epoch": 1.0, + "learning_rate": 1.868955811952989e-05, + "loss": 3.879, + "step": 1912320 + }, + { + "epoch": 1.0, + "learning_rate": 1.868117217201937e-05, + "loss": 3.884, + "step": 1912832 + }, + { + "epoch": 1.0, + "learning_rate": 1.867278622450885e-05, + "loss": 3.8926, + "step": 1913344 + }, + { + "epoch": 1.0, + "learning_rate": 1.866441665580206e-05, + "loss": 3.8929, + "step": 1913856 + }, + { + "epoch": 1.0, + "learning_rate": 1.8656047087095273e-05, + "loss": 3.8912, + "step": 1914368 + }, + { + "epoch": 1.0, + "learning_rate": 1.8647661139584753e-05, + "loss": 3.8703, + "step": 1914880 + }, + { + "epoch": 1.0, + "learning_rate": 1.8639275192074232e-05, + "loss": 3.8918, + "step": 1915392 + }, + { + "epoch": 1.0, + "learning_rate": 1.8630889244563712e-05, + "loss": 3.8745, + "step": 1915904 + }, + { + "epoch": 1.0, + "learning_rate": 1.8622503297053192e-05, + "loss": 3.8854, + "step": 1916416 + }, + { + "epoch": 1.0, + "learning_rate": 1.8614117349542672e-05, + "loss": 3.8846, + "step": 1916928 + }, + { + "epoch": 1.0, + "learning_rate": 1.860573140203215e-05, + "loss": 3.8843, + "step": 1917440 + }, + { + "epoch": 1.0, + "learning_rate": 1.8597345454521632e-05, + "loss": 3.8907, + "step": 1917952 + }, + { + "epoch": 1.0, + "learning_rate": 1.8588975885814845e-05, + "loss": 3.8953, + "step": 1918464 + }, + { + "epoch": 1.0, + "learning_rate": 1.8580589938304325e-05, + "loss": 3.8913, + "step": 1918976 + }, + { + "epoch": 1.0, + "learning_rate": 1.85722039907938e-05, + "loss": 3.8878, + "step": 1919488 + }, + { + "epoch": 1.0, + "learning_rate": 1.856381804328328e-05, + "loss": 3.8813, + "step": 1920000 + }, + { + "epoch": 1.0, + "learning_rate": 1.8555448474576494e-05, + "loss": 3.8893, + "step": 1920512 + }, + { + "epoch": 1.0, + "learning_rate": 1.8547062527065974e-05, + "loss": 3.8884, + "step": 1921024 + }, + { + "epoch": 1.0, + "learning_rate": 1.8538676579555454e-05, + "loss": 3.8853, + "step": 1921536 + }, + { + "epoch": 1.0, + "learning_rate": 1.8530290632044934e-05, + "loss": 3.8808, + "step": 1922048 + }, + { + "epoch": 1.0, + "learning_rate": 1.8521904684534414e-05, + "loss": 3.8818, + "step": 1922560 + }, + { + "epoch": 1.0, + "learning_rate": 1.8513518737023893e-05, + "loss": 3.886, + "step": 1923072 + }, + { + "epoch": 1.01, + "learning_rate": 1.8505132789513373e-05, + "loss": 3.8755, + "step": 1923584 + }, + { + "epoch": 1.01, + "learning_rate": 1.8496763220806586e-05, + "loss": 3.8937, + "step": 1924096 + }, + { + "epoch": 1.01, + "learning_rate": 1.8488377273296066e-05, + "loss": 3.893, + "step": 1924608 + }, + { + "epoch": 1.01, + "learning_rate": 1.8479991325785546e-05, + "loss": 3.8905, + "step": 1925120 + }, + { + "epoch": 1.01, + "learning_rate": 1.8471605378275026e-05, + "loss": 3.882, + "step": 1925632 + }, + { + "epoch": 1.01, + "learning_rate": 1.8463235809568235e-05, + "loss": 3.8869, + "step": 1926144 + }, + { + "epoch": 1.01, + "learning_rate": 1.8454849862057715e-05, + "loss": 3.8877, + "step": 1926656 + }, + { + "epoch": 1.01, + "learning_rate": 1.8446463914547195e-05, + "loss": 3.8821, + "step": 1927168 + }, + { + "epoch": 1.01, + "learning_rate": 1.8438077967036678e-05, + "loss": 3.8779, + "step": 1927680 + }, + { + "epoch": 1.01, + "learning_rate": 1.8429692019526158e-05, + "loss": 3.8775, + "step": 1928192 + }, + { + "epoch": 1.01, + "learning_rate": 1.8421306072015635e-05, + "loss": 3.8788, + "step": 1928704 + }, + { + "epoch": 1.01, + "learning_rate": 1.8412920124505115e-05, + "loss": 3.8903, + "step": 1929216 + }, + { + "epoch": 1.01, + "learning_rate": 1.8404534176994595e-05, + "loss": 3.8786, + "step": 1929728 + }, + { + "epoch": 1.01, + "learning_rate": 1.8396148229484075e-05, + "loss": 3.8808, + "step": 1930240 + }, + { + "epoch": 1.01, + "learning_rate": 1.8387778660777287e-05, + "loss": 3.8937, + "step": 1930752 + }, + { + "epoch": 1.01, + "learning_rate": 1.8379392713266767e-05, + "loss": 3.8864, + "step": 1931264 + }, + { + "epoch": 1.01, + "learning_rate": 1.8371006765756247e-05, + "loss": 3.8918, + "step": 1931776 + }, + { + "epoch": 1.01, + "learning_rate": 1.8362620818245727e-05, + "loss": 3.8796, + "step": 1932288 + }, + { + "epoch": 1.01, + "learning_rate": 1.8354234870735207e-05, + "loss": 3.8654, + "step": 1932800 + }, + { + "epoch": 1.01, + "learning_rate": 1.8345848923224687e-05, + "loss": 3.8966, + "step": 1933312 + }, + { + "epoch": 1.01, + "learning_rate": 1.8337462975714163e-05, + "loss": 3.8796, + "step": 1933824 + }, + { + "epoch": 1.01, + "learning_rate": 1.8329077028203647e-05, + "loss": 3.8878, + "step": 1934336 + }, + { + "epoch": 1.01, + "learning_rate": 1.832070745949686e-05, + "loss": 3.8807, + "step": 1934848 + }, + { + "epoch": 1.01, + "learning_rate": 1.831232151198634e-05, + "loss": 3.8825, + "step": 1935360 + }, + { + "epoch": 1.01, + "learning_rate": 1.8303935564475816e-05, + "loss": 3.8701, + "step": 1935872 + }, + { + "epoch": 1.01, + "learning_rate": 1.8295565995769028e-05, + "loss": 3.8771, + "step": 1936384 + }, + { + "epoch": 1.01, + "learning_rate": 1.8287180048258508e-05, + "loss": 3.8756, + "step": 1936896 + }, + { + "epoch": 1.01, + "learning_rate": 1.8278794100747988e-05, + "loss": 3.8773, + "step": 1937408 + }, + { + "epoch": 1.01, + "learning_rate": 1.8270408153237468e-05, + "loss": 3.8956, + "step": 1937920 + }, + { + "epoch": 1.01, + "learning_rate": 1.8262022205726948e-05, + "loss": 3.8783, + "step": 1938432 + }, + { + "epoch": 1.01, + "learning_rate": 1.8253636258216428e-05, + "loss": 3.8751, + "step": 1938944 + }, + { + "epoch": 1.01, + "learning_rate": 1.8245250310705908e-05, + "loss": 3.8979, + "step": 1939456 + }, + { + "epoch": 1.01, + "learning_rate": 1.8236864363195388e-05, + "loss": 3.8641, + "step": 1939968 + }, + { + "epoch": 1.01, + "learning_rate": 1.8228494794488597e-05, + "loss": 3.8702, + "step": 1940480 + }, + { + "epoch": 1.01, + "learning_rate": 1.8220125225781813e-05, + "loss": 3.8848, + "step": 1940992 + }, + { + "epoch": 1.01, + "learning_rate": 1.821173927827129e-05, + "loss": 3.8825, + "step": 1941504 + }, + { + "epoch": 1.01, + "learning_rate": 1.820335333076077e-05, + "loss": 3.8728, + "step": 1942016 + }, + { + "epoch": 1.01, + "learning_rate": 1.819496738325025e-05, + "loss": 3.8849, + "step": 1942528 + }, + { + "epoch": 1.01, + "learning_rate": 1.818658143573973e-05, + "loss": 3.8618, + "step": 1943040 + }, + { + "epoch": 1.01, + "learning_rate": 1.817819548822921e-05, + "loss": 3.8753, + "step": 1943552 + }, + { + "epoch": 1.01, + "learning_rate": 1.816980954071869e-05, + "loss": 3.8895, + "step": 1944064 + }, + { + "epoch": 1.01, + "learning_rate": 1.81614399720119e-05, + "loss": 3.8778, + "step": 1944576 + }, + { + "epoch": 1.01, + "learning_rate": 1.815305402450138e-05, + "loss": 3.8906, + "step": 1945088 + }, + { + "epoch": 1.01, + "learning_rate": 1.814466807699086e-05, + "loss": 3.8891, + "step": 1945600 + }, + { + "epoch": 1.01, + "learning_rate": 1.813628212948034e-05, + "loss": 3.8982, + "step": 1946112 + }, + { + "epoch": 1.01, + "learning_rate": 1.812791256077355e-05, + "loss": 3.8707, + "step": 1946624 + }, + { + "epoch": 1.01, + "learning_rate": 1.8119526613263034e-05, + "loss": 3.8874, + "step": 1947136 + }, + { + "epoch": 1.01, + "learning_rate": 1.8111140665752514e-05, + "loss": 3.8887, + "step": 1947648 + }, + { + "epoch": 1.01, + "learning_rate": 1.810275471824199e-05, + "loss": 3.8687, + "step": 1948160 + }, + { + "epoch": 1.01, + "learning_rate": 1.8094385149535203e-05, + "loss": 3.896, + "step": 1948672 + }, + { + "epoch": 1.01, + "learning_rate": 1.8085999202024683e-05, + "loss": 3.8844, + "step": 1949184 + }, + { + "epoch": 1.01, + "learning_rate": 1.8077613254514163e-05, + "loss": 3.8885, + "step": 1949696 + }, + { + "epoch": 1.01, + "learning_rate": 1.8069227307003643e-05, + "loss": 3.8905, + "step": 1950208 + }, + { + "epoch": 1.01, + "learning_rate": 1.8060841359493123e-05, + "loss": 3.8727, + "step": 1950720 + }, + { + "epoch": 1.01, + "learning_rate": 1.8052455411982603e-05, + "loss": 3.8685, + "step": 1951232 + }, + { + "epoch": 1.01, + "learning_rate": 1.8044069464472083e-05, + "loss": 3.8768, + "step": 1951744 + }, + { + "epoch": 1.01, + "learning_rate": 1.8035683516961563e-05, + "loss": 3.8846, + "step": 1952256 + }, + { + "epoch": 1.01, + "learning_rate": 1.8027313948254772e-05, + "loss": 3.8817, + "step": 1952768 + }, + { + "epoch": 1.01, + "learning_rate": 1.8018928000744255e-05, + "loss": 3.8771, + "step": 1953280 + }, + { + "epoch": 1.02, + "learning_rate": 1.8010542053233735e-05, + "loss": 3.8779, + "step": 1953792 + }, + { + "epoch": 1.02, + "learning_rate": 1.8002156105723215e-05, + "loss": 3.8827, + "step": 1954304 + }, + { + "epoch": 1.02, + "learning_rate": 1.7993770158212695e-05, + "loss": 3.878, + "step": 1954816 + }, + { + "epoch": 1.02, + "learning_rate": 1.7985400589505904e-05, + "loss": 3.8728, + "step": 1955328 + }, + { + "epoch": 1.02, + "learning_rate": 1.7977014641995384e-05, + "loss": 3.8979, + "step": 1955840 + }, + { + "epoch": 1.02, + "learning_rate": 1.7968645073288597e-05, + "loss": 3.8896, + "step": 1956352 + }, + { + "epoch": 1.02, + "learning_rate": 1.7960259125778076e-05, + "loss": 3.8877, + "step": 1956864 + }, + { + "epoch": 1.02, + "learning_rate": 1.7951873178267556e-05, + "loss": 3.871, + "step": 1957376 + }, + { + "epoch": 1.02, + "learning_rate": 1.7943487230757036e-05, + "loss": 3.8824, + "step": 1957888 + }, + { + "epoch": 1.02, + "learning_rate": 1.7935101283246516e-05, + "loss": 3.8763, + "step": 1958400 + }, + { + "epoch": 1.02, + "learning_rate": 1.7926715335735996e-05, + "loss": 3.8922, + "step": 1958912 + }, + { + "epoch": 1.02, + "learning_rate": 1.7918329388225473e-05, + "loss": 3.8806, + "step": 1959424 + }, + { + "epoch": 1.02, + "learning_rate": 1.7909943440714956e-05, + "loss": 3.8756, + "step": 1959936 + }, + { + "epoch": 1.02, + "learning_rate": 1.7901557493204436e-05, + "loss": 3.8845, + "step": 1960448 + }, + { + "epoch": 1.02, + "learning_rate": 1.7893171545693916e-05, + "loss": 3.8913, + "step": 1960960 + }, + { + "epoch": 1.02, + "learning_rate": 1.7884785598183396e-05, + "loss": 3.8712, + "step": 1961472 + }, + { + "epoch": 1.02, + "learning_rate": 1.7876399650672876e-05, + "loss": 3.8852, + "step": 1961984 + }, + { + "epoch": 1.02, + "learning_rate": 1.7868046460769818e-05, + "loss": 3.8709, + "step": 1962496 + }, + { + "epoch": 1.02, + "learning_rate": 1.7859660513259298e-05, + "loss": 3.8764, + "step": 1963008 + }, + { + "epoch": 1.02, + "learning_rate": 1.7851274565748778e-05, + "loss": 3.8754, + "step": 1963520 + }, + { + "epoch": 1.02, + "learning_rate": 1.7842888618238258e-05, + "loss": 3.8747, + "step": 1964032 + }, + { + "epoch": 1.02, + "learning_rate": 1.7834502670727737e-05, + "loss": 3.878, + "step": 1964544 + }, + { + "epoch": 1.02, + "learning_rate": 1.7826116723217217e-05, + "loss": 3.8829, + "step": 1965056 + }, + { + "epoch": 1.02, + "learning_rate": 1.7817730775706697e-05, + "loss": 3.8751, + "step": 1965568 + }, + { + "epoch": 1.02, + "learning_rate": 1.7809344828196177e-05, + "loss": 3.874, + "step": 1966080 + }, + { + "epoch": 1.02, + "learning_rate": 1.780097525948939e-05, + "loss": 3.8908, + "step": 1966592 + }, + { + "epoch": 1.02, + "learning_rate": 1.779258931197887e-05, + "loss": 3.8966, + "step": 1967104 + }, + { + "epoch": 1.02, + "learning_rate": 1.778421974327208e-05, + "loss": 3.8845, + "step": 1967616 + }, + { + "epoch": 1.02, + "learning_rate": 1.777583379576156e-05, + "loss": 3.8916, + "step": 1968128 + }, + { + "epoch": 1.02, + "learning_rate": 1.776744784825104e-05, + "loss": 3.871, + "step": 1968640 + }, + { + "epoch": 1.02, + "learning_rate": 1.775906190074052e-05, + "loss": 3.8829, + "step": 1969152 + }, + { + "epoch": 1.02, + "learning_rate": 1.7750675953230002e-05, + "loss": 3.8777, + "step": 1969664 + }, + { + "epoch": 1.02, + "learning_rate": 1.774230638452321e-05, + "loss": 3.8739, + "step": 1970176 + }, + { + "epoch": 1.02, + "learning_rate": 1.773392043701269e-05, + "loss": 3.8766, + "step": 1970688 + }, + { + "epoch": 1.02, + "learning_rate": 1.77255508683059e-05, + "loss": 3.8797, + "step": 1971200 + }, + { + "epoch": 1.02, + "learning_rate": 1.771716492079538e-05, + "loss": 3.8844, + "step": 1971712 + }, + { + "epoch": 1.02, + "learning_rate": 1.7708778973284864e-05, + "loss": 3.88, + "step": 1972224 + }, + { + "epoch": 1.02, + "learning_rate": 1.7700393025774344e-05, + "loss": 3.884, + "step": 1972736 + }, + { + "epoch": 1.02, + "learning_rate": 1.7692007078263823e-05, + "loss": 3.8852, + "step": 1973248 + }, + { + "epoch": 1.02, + "learning_rate": 1.76836211307533e-05, + "loss": 3.8717, + "step": 1973760 + }, + { + "epoch": 1.02, + "learning_rate": 1.767523518324278e-05, + "loss": 3.8849, + "step": 1974272 + }, + { + "epoch": 1.02, + "learning_rate": 1.766684923573226e-05, + "loss": 3.8876, + "step": 1974784 + }, + { + "epoch": 1.02, + "learning_rate": 1.765846328822174e-05, + "loss": 3.8921, + "step": 1975296 + }, + { + "epoch": 1.02, + "learning_rate": 1.7650093719514952e-05, + "loss": 3.8772, + "step": 1975808 + }, + { + "epoch": 1.02, + "learning_rate": 1.7641707772004432e-05, + "loss": 3.8933, + "step": 1976320 + }, + { + "epoch": 1.02, + "learning_rate": 1.7633321824493912e-05, + "loss": 3.8844, + "step": 1976832 + }, + { + "epoch": 1.02, + "learning_rate": 1.7624935876983392e-05, + "loss": 3.8872, + "step": 1977344 + }, + { + "epoch": 1.02, + "learning_rate": 1.7616549929472872e-05, + "loss": 3.888, + "step": 1977856 + }, + { + "epoch": 1.02, + "learning_rate": 1.760818036076608e-05, + "loss": 3.8813, + "step": 1978368 + }, + { + "epoch": 1.02, + "learning_rate": 1.7599794413255565e-05, + "loss": 3.8763, + "step": 1978880 + }, + { + "epoch": 1.02, + "learning_rate": 1.7591408465745045e-05, + "loss": 3.8945, + "step": 1979392 + }, + { + "epoch": 1.02, + "learning_rate": 1.7583022518234525e-05, + "loss": 3.8673, + "step": 1979904 + }, + { + "epoch": 1.02, + "learning_rate": 1.7574652949527734e-05, + "loss": 3.8831, + "step": 1980416 + }, + { + "epoch": 1.02, + "learning_rate": 1.7566267002017214e-05, + "loss": 3.8882, + "step": 1980928 + }, + { + "epoch": 1.02, + "learning_rate": 1.7557881054506694e-05, + "loss": 3.8817, + "step": 1981440 + }, + { + "epoch": 1.02, + "learning_rate": 1.7549495106996174e-05, + "loss": 3.8767, + "step": 1981952 + }, + { + "epoch": 1.02, + "learning_rate": 1.7541109159485657e-05, + "loss": 3.882, + "step": 1982464 + }, + { + "epoch": 1.02, + "learning_rate": 1.7532723211975133e-05, + "loss": 3.8867, + "step": 1982976 + }, + { + "epoch": 1.02, + "learning_rate": 1.7524337264464613e-05, + "loss": 3.8863, + "step": 1983488 + }, + { + "epoch": 1.02, + "learning_rate": 1.7515951316954093e-05, + "loss": 3.8857, + "step": 1984000 + }, + { + "epoch": 1.03, + "eval_loss": 3.984929323196411, + "eval_runtime": 286.4709, + "eval_samples_per_second": 1332.041, + "eval_steps_per_second": 41.627, + "step": 1984320 + }, + { + "epoch": 0.0, + "learning_rate": 1.7507565369443573e-05, + "loss": 3.8618, + "step": 1984512 + }, + { + "epoch": 0.0, + "learning_rate": 1.7499179421933053e-05, + "loss": 3.8791, + "step": 1985024 + }, + { + "epoch": 0.0, + "learning_rate": 1.7490793474422533e-05, + "loss": 3.8808, + "step": 1985536 + }, + { + "epoch": 0.0, + "learning_rate": 1.7482407526912013e-05, + "loss": 3.885, + "step": 1986048 + }, + { + "epoch": 0.0, + "learning_rate": 1.7474021579401493e-05, + "loss": 3.8929, + "step": 1986560 + }, + { + "epoch": 0.0, + "learning_rate": 1.7465635631890973e-05, + "loss": 3.8777, + "step": 1987072 + }, + { + "epoch": 0.0, + "learning_rate": 1.7457249684380453e-05, + "loss": 3.8819, + "step": 1987584 + }, + { + "epoch": 0.0, + "learning_rate": 1.7448863736869933e-05, + "loss": 3.8772, + "step": 1988096 + }, + { + "epoch": 0.0, + "learning_rate": 1.7440477789359413e-05, + "loss": 3.8765, + "step": 1988608 + }, + { + "epoch": 0.0, + "learning_rate": 1.7432091841848893e-05, + "loss": 3.8762, + "step": 1989120 + }, + { + "epoch": 0.0, + "learning_rate": 1.7423705894338373e-05, + "loss": 3.8866, + "step": 1989632 + }, + { + "epoch": 0.0, + "learning_rate": 1.7415319946827853e-05, + "loss": 3.8899, + "step": 1990144 + }, + { + "epoch": 0.0, + "learning_rate": 1.7406950378121065e-05, + "loss": 3.8888, + "step": 1990656 + }, + { + "epoch": 0.0, + "learning_rate": 1.7398564430610545e-05, + "loss": 3.8623, + "step": 1991168 + }, + { + "epoch": 0.0, + "learning_rate": 1.7390178483100022e-05, + "loss": 3.8851, + "step": 1991680 + }, + { + "epoch": 0.0, + "learning_rate": 1.7381792535589502e-05, + "loss": 3.8678, + "step": 1992192 + }, + { + "epoch": 0.0, + "learning_rate": 1.7373406588078982e-05, + "loss": 3.8807, + "step": 1992704 + }, + { + "epoch": 0.0, + "learning_rate": 1.7365020640568465e-05, + "loss": 3.8766, + "step": 1993216 + }, + { + "epoch": 0.0, + "learning_rate": 1.7356634693057945e-05, + "loss": 3.8799, + "step": 1993728 + }, + { + "epoch": 0.0, + "learning_rate": 1.7348248745547425e-05, + "loss": 3.8851, + "step": 1994240 + }, + { + "epoch": 0.0, + "learning_rate": 1.73398627980369e-05, + "loss": 3.8925, + "step": 1994752 + }, + { + "epoch": 0.0, + "learning_rate": 1.7331493229330114e-05, + "loss": 3.8837, + "step": 1995264 + }, + { + "epoch": 0.0, + "learning_rate": 1.7323107281819594e-05, + "loss": 3.8826, + "step": 1995776 + }, + { + "epoch": 0.0, + "learning_rate": 1.7314721334309074e-05, + "loss": 3.875, + "step": 1996288 + }, + { + "epoch": 0.0, + "learning_rate": 1.7306335386798554e-05, + "loss": 3.8877, + "step": 1996800 + }, + { + "epoch": 0.0, + "learning_rate": 1.7297965818091766e-05, + "loss": 3.8827, + "step": 1997312 + }, + { + "epoch": 0.0, + "learning_rate": 1.7289579870581246e-05, + "loss": 3.8773, + "step": 1997824 + }, + { + "epoch": 0.0, + "learning_rate": 1.7281193923070726e-05, + "loss": 3.8764, + "step": 1998336 + }, + { + "epoch": 0.0, + "learning_rate": 1.7272807975560203e-05, + "loss": 3.8756, + "step": 1998848 + }, + { + "epoch": 0.0, + "learning_rate": 1.726443840685342e-05, + "loss": 3.8796, + "step": 1999360 + }, + { + "epoch": 0.01, + "learning_rate": 1.72560524593429e-05, + "loss": 3.8684, + "step": 1999872 + }, + { + "epoch": 0.01, + "learning_rate": 1.7247666511832375e-05, + "loss": 3.8897, + "step": 2000384 + }, + { + "epoch": 0.01, + "learning_rate": 1.7239280564321855e-05, + "loss": 3.8917, + "step": 2000896 + }, + { + "epoch": 0.01, + "learning_rate": 1.7230894616811335e-05, + "loss": 3.8838, + "step": 2001408 + }, + { + "epoch": 0.01, + "learning_rate": 1.7222525048104548e-05, + "loss": 3.8784, + "step": 2001920 + }, + { + "epoch": 0.01, + "learning_rate": 1.721415547939776e-05, + "loss": 3.8794, + "step": 2002432 + }, + { + "epoch": 0.01, + "learning_rate": 1.720576953188724e-05, + "loss": 3.8869, + "step": 2002944 + }, + { + "epoch": 0.01, + "learning_rate": 1.719738358437672e-05, + "loss": 3.8779, + "step": 2003456 + }, + { + "epoch": 0.01, + "learning_rate": 1.71889976368662e-05, + "loss": 3.8657, + "step": 2003968 + }, + { + "epoch": 0.01, + "learning_rate": 1.7180611689355677e-05, + "loss": 3.876, + "step": 2004480 + }, + { + "epoch": 0.01, + "learning_rate": 1.7172225741845157e-05, + "loss": 3.8747, + "step": 2004992 + }, + { + "epoch": 0.01, + "learning_rate": 1.7163839794334636e-05, + "loss": 3.8817, + "step": 2005504 + }, + { + "epoch": 0.01, + "learning_rate": 1.715545384682412e-05, + "loss": 3.8753, + "step": 2006016 + }, + { + "epoch": 0.01, + "learning_rate": 1.71470678993136e-05, + "loss": 3.8772, + "step": 2006528 + }, + { + "epoch": 0.01, + "learning_rate": 1.713868195180308e-05, + "loss": 3.8875, + "step": 2007040 + }, + { + "epoch": 0.01, + "learning_rate": 1.7130296004292556e-05, + "loss": 3.881, + "step": 2007552 + }, + { + "epoch": 0.01, + "learning_rate": 1.7121910056782036e-05, + "loss": 3.8857, + "step": 2008064 + }, + { + "epoch": 0.01, + "learning_rate": 1.711355686687898e-05, + "loss": 3.8785, + "step": 2008576 + }, + { + "epoch": 0.01, + "learning_rate": 1.710517091936846e-05, + "loss": 3.855, + "step": 2009088 + }, + { + "epoch": 0.01, + "learning_rate": 1.709678497185794e-05, + "loss": 3.8906, + "step": 2009600 + }, + { + "epoch": 0.01, + "learning_rate": 1.708839902434742e-05, + "loss": 3.8745, + "step": 2010112 + }, + { + "epoch": 0.01, + "learning_rate": 1.70800130768369e-05, + "loss": 3.8802, + "step": 2010624 + }, + { + "epoch": 0.01, + "learning_rate": 1.707164350813011e-05, + "loss": 3.8784, + "step": 2011136 + }, + { + "epoch": 0.01, + "learning_rate": 1.706325756061959e-05, + "loss": 3.8777, + "step": 2011648 + }, + { + "epoch": 0.01, + "learning_rate": 1.7054871613109074e-05, + "loss": 3.8658, + "step": 2012160 + }, + { + "epoch": 0.01, + "learning_rate": 1.7046485665598553e-05, + "loss": 3.8708, + "step": 2012672 + }, + { + "epoch": 0.01, + "learning_rate": 1.703809971808803e-05, + "loss": 3.8742, + "step": 2013184 + }, + { + "epoch": 0.01, + "learning_rate": 1.702971377057751e-05, + "loss": 3.8709, + "step": 2013696 + }, + { + "epoch": 0.01, + "learning_rate": 1.702132782306699e-05, + "loss": 3.8868, + "step": 2014208 + }, + { + "epoch": 0.01, + "learning_rate": 1.701294187555647e-05, + "loss": 3.8745, + "step": 2014720 + }, + { + "epoch": 0.01, + "learning_rate": 1.7004572306849682e-05, + "loss": 3.8713, + "step": 2015232 + }, + { + "epoch": 0.01, + "learning_rate": 1.6996186359339162e-05, + "loss": 3.8896, + "step": 2015744 + }, + { + "epoch": 0.01, + "learning_rate": 1.6987800411828642e-05, + "loss": 3.8638, + "step": 2016256 + }, + { + "epoch": 0.01, + "learning_rate": 1.6979414464318122e-05, + "loss": 3.8644, + "step": 2016768 + }, + { + "epoch": 0.01, + "learning_rate": 1.6971028516807602e-05, + "loss": 3.8829, + "step": 2017280 + }, + { + "epoch": 0.01, + "learning_rate": 1.696265894810081e-05, + "loss": 3.8749, + "step": 2017792 + }, + { + "epoch": 0.01, + "learning_rate": 1.695427300059029e-05, + "loss": 3.868, + "step": 2018304 + }, + { + "epoch": 0.01, + "learning_rate": 1.6945887053079775e-05, + "loss": 3.8769, + "step": 2018816 + }, + { + "epoch": 0.01, + "learning_rate": 1.6937517484372984e-05, + "loss": 3.8614, + "step": 2019328 + }, + { + "epoch": 0.01, + "learning_rate": 1.6929131536862464e-05, + "loss": 3.8717, + "step": 2019840 + }, + { + "epoch": 0.01, + "learning_rate": 1.6920745589351944e-05, + "loss": 3.886, + "step": 2020352 + }, + { + "epoch": 0.01, + "learning_rate": 1.6912359641841424e-05, + "loss": 3.8761, + "step": 2020864 + }, + { + "epoch": 0.01, + "learning_rate": 1.6903990073134636e-05, + "loss": 3.8842, + "step": 2021376 + }, + { + "epoch": 0.01, + "learning_rate": 1.6895604125624116e-05, + "loss": 3.8805, + "step": 2021888 + }, + { + "epoch": 0.01, + "learning_rate": 1.6887218178113596e-05, + "loss": 3.8937, + "step": 2022400 + }, + { + "epoch": 0.01, + "learning_rate": 1.6878848609406805e-05, + "loss": 3.8677, + "step": 2022912 + }, + { + "epoch": 0.01, + "learning_rate": 1.6870462661896285e-05, + "loss": 3.884, + "step": 2023424 + }, + { + "epoch": 0.01, + "learning_rate": 1.6862076714385765e-05, + "loss": 3.8839, + "step": 2023936 + }, + { + "epoch": 0.01, + "learning_rate": 1.6853690766875245e-05, + "loss": 3.8651, + "step": 2024448 + }, + { + "epoch": 0.01, + "learning_rate": 1.6845304819364728e-05, + "loss": 3.8869, + "step": 2024960 + }, + { + "epoch": 0.01, + "learning_rate": 1.6836918871854208e-05, + "loss": 3.8797, + "step": 2025472 + }, + { + "epoch": 0.01, + "learning_rate": 1.6828532924343685e-05, + "loss": 3.8826, + "step": 2025984 + }, + { + "epoch": 0.01, + "learning_rate": 1.6820146976833165e-05, + "loss": 3.8872, + "step": 2026496 + }, + { + "epoch": 0.01, + "learning_rate": 1.6811761029322645e-05, + "loss": 3.8695, + "step": 2027008 + }, + { + "epoch": 0.01, + "learning_rate": 1.6803375081812125e-05, + "loss": 3.8646, + "step": 2027520 + }, + { + "epoch": 0.01, + "learning_rate": 1.6794989134301605e-05, + "loss": 3.8693, + "step": 2028032 + }, + { + "epoch": 0.01, + "learning_rate": 1.6786603186791085e-05, + "loss": 3.8815, + "step": 2028544 + }, + { + "epoch": 0.01, + "learning_rate": 1.6778233618084297e-05, + "loss": 3.8732, + "step": 2029056 + }, + { + "epoch": 0.01, + "learning_rate": 1.6769847670573777e-05, + "loss": 3.8717, + "step": 2029568 + }, + { + "epoch": 0.01, + "learning_rate": 1.6761461723063257e-05, + "loss": 3.8725, + "step": 2030080 + }, + { + "epoch": 0.02, + "learning_rate": 1.6753075775552737e-05, + "loss": 3.8788, + "step": 2030592 + }, + { + "epoch": 0.02, + "learning_rate": 1.6744706206845946e-05, + "loss": 3.8731, + "step": 2031104 + }, + { + "epoch": 0.02, + "learning_rate": 1.673633663813916e-05, + "loss": 3.8709, + "step": 2031616 + }, + { + "epoch": 0.02, + "learning_rate": 1.672795069062864e-05, + "loss": 3.8899, + "step": 2032128 + }, + { + "epoch": 0.02, + "learning_rate": 1.671956474311812e-05, + "loss": 3.8879, + "step": 2032640 + }, + { + "epoch": 0.02, + "learning_rate": 1.67111787956076e-05, + "loss": 3.8807, + "step": 2033152 + }, + { + "epoch": 0.02, + "learning_rate": 1.670279284809708e-05, + "loss": 3.8696, + "step": 2033664 + }, + { + "epoch": 0.02, + "learning_rate": 1.6694406900586558e-05, + "loss": 3.8759, + "step": 2034176 + }, + { + "epoch": 0.02, + "learning_rate": 1.6686020953076038e-05, + "loss": 3.8687, + "step": 2034688 + }, + { + "epoch": 0.02, + "learning_rate": 1.667765138436925e-05, + "loss": 3.8884, + "step": 2035200 + }, + { + "epoch": 0.02, + "learning_rate": 1.666926543685873e-05, + "loss": 3.877, + "step": 2035712 + }, + { + "epoch": 0.02, + "learning_rate": 1.666087948934821e-05, + "loss": 3.8767, + "step": 2036224 + }, + { + "epoch": 0.02, + "learning_rate": 1.665250992064142e-05, + "loss": 3.8758, + "step": 2036736 + }, + { + "epoch": 0.02, + "learning_rate": 1.66441239731309e-05, + "loss": 3.8793, + "step": 2037248 + }, + { + "epoch": 0.02, + "learning_rate": 1.6635738025620383e-05, + "loss": 3.8755, + "step": 2037760 + }, + { + "epoch": 0.02, + "learning_rate": 1.6627352078109863e-05, + "loss": 3.8733, + "step": 2038272 + }, + { + "epoch": 0.02, + "learning_rate": 1.661896613059934e-05, + "loss": 3.8673, + "step": 2038784 + }, + { + "epoch": 0.02, + "learning_rate": 1.6610596561892552e-05, + "loss": 3.8704, + "step": 2039296 + }, + { + "epoch": 0.02, + "learning_rate": 1.6602210614382032e-05, + "loss": 3.872, + "step": 2039808 + }, + { + "epoch": 0.02, + "learning_rate": 1.6593824666871512e-05, + "loss": 3.8689, + "step": 2040320 + }, + { + "epoch": 0.02, + "learning_rate": 1.6585438719360992e-05, + "loss": 3.8721, + "step": 2040832 + }, + { + "epoch": 0.02, + "learning_rate": 1.6577052771850472e-05, + "loss": 3.8742, + "step": 2041344 + }, + { + "epoch": 0.02, + "learning_rate": 1.6568683203143684e-05, + "loss": 3.8741, + "step": 2041856 + }, + { + "epoch": 0.02, + "learning_rate": 1.656029725563316e-05, + "loss": 3.8683, + "step": 2042368 + }, + { + "epoch": 0.02, + "learning_rate": 1.655191130812264e-05, + "loss": 3.886, + "step": 2042880 + }, + { + "epoch": 0.02, + "learning_rate": 1.654352536061212e-05, + "loss": 3.8909, + "step": 2043392 + }, + { + "epoch": 0.02, + "learning_rate": 1.6535155791905337e-05, + "loss": 3.8781, + "step": 2043904 + }, + { + "epoch": 0.02, + "learning_rate": 1.6526786223198546e-05, + "loss": 3.8852, + "step": 2044416 + }, + { + "epoch": 0.02, + "learning_rate": 1.6518400275688026e-05, + "loss": 3.8737, + "step": 2044928 + }, + { + "epoch": 0.02, + "learning_rate": 1.6510014328177506e-05, + "loss": 3.8746, + "step": 2045440 + }, + { + "epoch": 0.02, + "learning_rate": 1.6501628380666986e-05, + "loss": 3.8759, + "step": 2045952 + }, + { + "epoch": 0.02, + "learning_rate": 1.6493242433156462e-05, + "loss": 3.8656, + "step": 2046464 + }, + { + "epoch": 0.02, + "learning_rate": 1.6484856485645946e-05, + "loss": 3.8719, + "step": 2046976 + }, + { + "epoch": 0.02, + "learning_rate": 1.6476470538135426e-05, + "loss": 3.8784, + "step": 2047488 + }, + { + "epoch": 0.02, + "learning_rate": 1.6468084590624905e-05, + "loss": 3.8828, + "step": 2048000 + }, + { + "epoch": 0.02, + "learning_rate": 1.6459698643114385e-05, + "loss": 3.8762, + "step": 2048512 + }, + { + "epoch": 0.02, + "learning_rate": 1.6451312695603865e-05, + "loss": 3.8776, + "step": 2049024 + }, + { + "epoch": 0.02, + "learning_rate": 1.6442926748093342e-05, + "loss": 3.8754, + "step": 2049536 + }, + { + "epoch": 0.02, + "learning_rate": 1.6434557179386554e-05, + "loss": 3.87, + "step": 2050048 + }, + { + "epoch": 0.02, + "learning_rate": 1.6426171231876038e-05, + "loss": 3.8775, + "step": 2050560 + }, + { + "epoch": 0.02, + "learning_rate": 1.6417785284365518e-05, + "loss": 3.8861, + "step": 2051072 + }, + { + "epoch": 0.02, + "learning_rate": 1.6409399336854994e-05, + "loss": 3.8841, + "step": 2051584 + }, + { + "epoch": 0.02, + "learning_rate": 1.6401013389344474e-05, + "loss": 3.8695, + "step": 2052096 + }, + { + "epoch": 0.02, + "learning_rate": 1.6392643820637687e-05, + "loss": 3.8905, + "step": 2052608 + }, + { + "epoch": 0.02, + "learning_rate": 1.63842742519309e-05, + "loss": 3.8785, + "step": 2053120 + }, + { + "epoch": 0.02, + "learning_rate": 1.637588830442038e-05, + "loss": 3.8862, + "step": 2053632 + }, + { + "epoch": 0.02, + "learning_rate": 1.636750235690986e-05, + "loss": 3.8831, + "step": 2054144 + }, + { + "epoch": 0.02, + "learning_rate": 1.635911640939934e-05, + "loss": 3.8727, + "step": 2054656 + }, + { + "epoch": 0.02, + "learning_rate": 1.6350730461888816e-05, + "loss": 3.8709, + "step": 2055168 + }, + { + "epoch": 0.02, + "learning_rate": 1.6342344514378296e-05, + "loss": 3.8908, + "step": 2055680 + }, + { + "epoch": 0.02, + "learning_rate": 1.6333958566867776e-05, + "loss": 3.8653, + "step": 2056192 + }, + { + "epoch": 0.02, + "learning_rate": 1.632557261935726e-05, + "loss": 3.8753, + "step": 2056704 + }, + { + "epoch": 0.02, + "learning_rate": 1.631718667184674e-05, + "loss": 3.8814, + "step": 2057216 + }, + { + "epoch": 0.02, + "learning_rate": 1.6308817103139948e-05, + "loss": 3.8821, + "step": 2057728 + }, + { + "epoch": 0.02, + "learning_rate": 1.6300431155629428e-05, + "loss": 3.872, + "step": 2058240 + }, + { + "epoch": 0.02, + "learning_rate": 1.6292045208118908e-05, + "loss": 3.8761, + "step": 2058752 + }, + { + "epoch": 0.02, + "learning_rate": 1.6283659260608388e-05, + "loss": 3.8797, + "step": 2059264 + }, + { + "epoch": 0.02, + "learning_rate": 1.62752896919016e-05, + "loss": 3.8873, + "step": 2059776 + }, + { + "epoch": 0.02, + "learning_rate": 1.626690374439108e-05, + "loss": 3.8807, + "step": 2060288 + }, + { + "epoch": 0.03, + "eval_loss": 3.983076810836792, + "eval_runtime": 301.1742, + "eval_samples_per_second": 1267.011, + "eval_steps_per_second": 39.595, + "step": 2060640 + }, + { + "epoch": 0.0, + "learning_rate": 1.625851779688056e-05, + "loss": 3.8466, + "step": 2060800 + }, + { + "epoch": 0.0, + "learning_rate": 1.625013184937004e-05, + "loss": 3.8731, + "step": 2061312 + }, + { + "epoch": 0.0, + "learning_rate": 1.624174590185952e-05, + "loss": 3.875, + "step": 2061824 + }, + { + "epoch": 0.0, + "learning_rate": 1.6233359954348997e-05, + "loss": 3.8803, + "step": 2062336 + }, + { + "epoch": 0.0, + "learning_rate": 1.6224974006838477e-05, + "loss": 3.888, + "step": 2062848 + }, + { + "epoch": 0.0, + "learning_rate": 1.621658805932796e-05, + "loss": 3.8744, + "step": 2063360 + }, + { + "epoch": 0.0, + "learning_rate": 1.620820211181744e-05, + "loss": 3.8767, + "step": 2063872 + }, + { + "epoch": 0.0, + "learning_rate": 1.619981616430692e-05, + "loss": 3.8754, + "step": 2064384 + }, + { + "epoch": 0.0, + "learning_rate": 1.61914302167964e-05, + "loss": 3.8716, + "step": 2064896 + }, + { + "epoch": 0.0, + "learning_rate": 1.618304426928588e-05, + "loss": 3.8662, + "step": 2065408 + }, + { + "epoch": 0.0, + "learning_rate": 1.6174658321775356e-05, + "loss": 3.8819, + "step": 2065920 + }, + { + "epoch": 0.0, + "learning_rate": 1.6166272374264836e-05, + "loss": 3.8919, + "step": 2066432 + }, + { + "epoch": 0.0, + "learning_rate": 1.6157902805558052e-05, + "loss": 3.8798, + "step": 2066944 + }, + { + "epoch": 0.0, + "learning_rate": 1.614951685804753e-05, + "loss": 3.8582, + "step": 2067456 + }, + { + "epoch": 0.0, + "learning_rate": 1.614113091053701e-05, + "loss": 3.8805, + "step": 2067968 + }, + { + "epoch": 0.0, + "learning_rate": 1.613274496302649e-05, + "loss": 3.8641, + "step": 2068480 + }, + { + "epoch": 0.0, + "learning_rate": 1.612435901551597e-05, + "loss": 3.8766, + "step": 2068992 + }, + { + "epoch": 0.0, + "learning_rate": 1.611597306800545e-05, + "loss": 3.8743, + "step": 2069504 + }, + { + "epoch": 0.0, + "learning_rate": 1.610758712049493e-05, + "loss": 3.8743, + "step": 2070016 + }, + { + "epoch": 0.0, + "learning_rate": 1.609920117298441e-05, + "loss": 3.8786, + "step": 2070528 + }, + { + "epoch": 0.0, + "learning_rate": 1.609081522547389e-05, + "loss": 3.8857, + "step": 2071040 + }, + { + "epoch": 0.0, + "learning_rate": 1.608242927796337e-05, + "loss": 3.877, + "step": 2071552 + }, + { + "epoch": 0.0, + "learning_rate": 1.607404333045285e-05, + "loss": 3.8792, + "step": 2072064 + }, + { + "epoch": 0.0, + "learning_rate": 1.606565738294233e-05, + "loss": 3.873, + "step": 2072576 + }, + { + "epoch": 0.0, + "learning_rate": 1.6057287814235537e-05, + "loss": 3.8818, + "step": 2073088 + }, + { + "epoch": 0.0, + "learning_rate": 1.6048901866725017e-05, + "loss": 3.8757, + "step": 2073600 + }, + { + "epoch": 0.0, + "learning_rate": 1.60405159192145e-05, + "loss": 3.8699, + "step": 2074112 + }, + { + "epoch": 0.0, + "learning_rate": 1.603212997170398e-05, + "loss": 3.8724, + "step": 2074624 + }, + { + "epoch": 0.0, + "learning_rate": 1.602374402419346e-05, + "loss": 3.8717, + "step": 2075136 + }, + { + "epoch": 0.0, + "learning_rate": 1.601535807668294e-05, + "loss": 3.875, + "step": 2075648 + }, + { + "epoch": 0.01, + "learning_rate": 1.6007004886779882e-05, + "loss": 3.8676, + "step": 2076160 + }, + { + "epoch": 0.01, + "learning_rate": 1.5998618939269362e-05, + "loss": 3.8791, + "step": 2076672 + }, + { + "epoch": 0.01, + "learning_rate": 1.5990232991758842e-05, + "loss": 3.8804, + "step": 2077184 + }, + { + "epoch": 0.01, + "learning_rate": 1.5981847044248322e-05, + "loss": 3.8832, + "step": 2077696 + }, + { + "epoch": 0.01, + "learning_rate": 1.5973461096737802e-05, + "loss": 3.8738, + "step": 2078208 + }, + { + "epoch": 0.01, + "learning_rate": 1.596509152803101e-05, + "loss": 3.8756, + "step": 2078720 + }, + { + "epoch": 0.01, + "learning_rate": 1.595670558052049e-05, + "loss": 3.8829, + "step": 2079232 + }, + { + "epoch": 0.01, + "learning_rate": 1.594831963300997e-05, + "loss": 3.8685, + "step": 2079744 + }, + { + "epoch": 0.01, + "learning_rate": 1.5939933685499454e-05, + "loss": 3.8663, + "step": 2080256 + }, + { + "epoch": 0.01, + "learning_rate": 1.5931547737988934e-05, + "loss": 3.8732, + "step": 2080768 + }, + { + "epoch": 0.01, + "learning_rate": 1.5923161790478414e-05, + "loss": 3.8678, + "step": 2081280 + }, + { + "epoch": 0.01, + "learning_rate": 1.591477584296789e-05, + "loss": 3.8755, + "step": 2081792 + }, + { + "epoch": 0.01, + "learning_rate": 1.590638989545737e-05, + "loss": 3.8697, + "step": 2082304 + }, + { + "epoch": 0.01, + "learning_rate": 1.589800394794685e-05, + "loss": 3.878, + "step": 2082816 + }, + { + "epoch": 0.01, + "learning_rate": 1.588961800043633e-05, + "loss": 3.8772, + "step": 2083328 + }, + { + "epoch": 0.01, + "learning_rate": 1.5881248431729543e-05, + "loss": 3.8781, + "step": 2083840 + }, + { + "epoch": 0.01, + "learning_rate": 1.5872862484219023e-05, + "loss": 3.8795, + "step": 2084352 + }, + { + "epoch": 0.01, + "learning_rate": 1.5864476536708503e-05, + "loss": 3.8748, + "step": 2084864 + }, + { + "epoch": 0.01, + "learning_rate": 1.5856090589197983e-05, + "loss": 3.852, + "step": 2085376 + }, + { + "epoch": 0.01, + "learning_rate": 1.5847721020491192e-05, + "loss": 3.8843, + "step": 2085888 + }, + { + "epoch": 0.01, + "learning_rate": 1.5839335072980676e-05, + "loss": 3.8712, + "step": 2086400 + }, + { + "epoch": 0.01, + "learning_rate": 1.5830949125470156e-05, + "loss": 3.8728, + "step": 2086912 + }, + { + "epoch": 0.01, + "learning_rate": 1.5822563177959635e-05, + "loss": 3.8756, + "step": 2087424 + }, + { + "epoch": 0.01, + "learning_rate": 1.5814177230449115e-05, + "loss": 3.8715, + "step": 2087936 + }, + { + "epoch": 0.01, + "learning_rate": 1.5805807661742325e-05, + "loss": 3.8617, + "step": 2088448 + }, + { + "epoch": 0.01, + "learning_rate": 1.5797421714231804e-05, + "loss": 3.8664, + "step": 2088960 + }, + { + "epoch": 0.01, + "learning_rate": 1.5789035766721284e-05, + "loss": 3.8684, + "step": 2089472 + }, + { + "epoch": 0.01, + "learning_rate": 1.5780649819210764e-05, + "loss": 3.8638, + "step": 2089984 + }, + { + "epoch": 0.01, + "learning_rate": 1.5772263871700248e-05, + "loss": 3.8839, + "step": 2090496 + }, + { + "epoch": 0.01, + "learning_rate": 1.5763877924189724e-05, + "loss": 3.8721, + "step": 2091008 + }, + { + "epoch": 0.01, + "learning_rate": 1.5755491976679204e-05, + "loss": 3.8594, + "step": 2091520 + }, + { + "epoch": 0.01, + "learning_rate": 1.5747106029168684e-05, + "loss": 3.8877, + "step": 2092032 + }, + { + "epoch": 0.01, + "learning_rate": 1.5738720081658164e-05, + "loss": 3.862, + "step": 2092544 + }, + { + "epoch": 0.01, + "learning_rate": 1.5730350512951377e-05, + "loss": 3.8597, + "step": 2093056 + }, + { + "epoch": 0.01, + "learning_rate": 1.5721964565440857e-05, + "loss": 3.8775, + "step": 2093568 + }, + { + "epoch": 0.01, + "learning_rate": 1.5713578617930337e-05, + "loss": 3.8733, + "step": 2094080 + }, + { + "epoch": 0.01, + "learning_rate": 1.5705209049223546e-05, + "loss": 3.8631, + "step": 2094592 + }, + { + "epoch": 0.01, + "learning_rate": 1.5696823101713026e-05, + "loss": 3.872, + "step": 2095104 + }, + { + "epoch": 0.01, + "learning_rate": 1.5688437154202506e-05, + "loss": 3.857, + "step": 2095616 + }, + { + "epoch": 0.01, + "learning_rate": 1.5680051206691986e-05, + "loss": 3.8668, + "step": 2096128 + }, + { + "epoch": 0.01, + "learning_rate": 1.567166525918147e-05, + "loss": 3.8773, + "step": 2096640 + }, + { + "epoch": 0.01, + "learning_rate": 1.566327931167095e-05, + "loss": 3.8719, + "step": 2097152 + }, + { + "epoch": 0.01, + "learning_rate": 1.565489336416043e-05, + "loss": 3.8819, + "step": 2097664 + }, + { + "epoch": 0.01, + "learning_rate": 1.5646507416649905e-05, + "loss": 3.8748, + "step": 2098176 + }, + { + "epoch": 0.01, + "learning_rate": 1.5638137847943118e-05, + "loss": 3.8902, + "step": 2098688 + }, + { + "epoch": 0.01, + "learning_rate": 1.562976827923633e-05, + "loss": 3.8621, + "step": 2099200 + }, + { + "epoch": 0.01, + "learning_rate": 1.562138233172581e-05, + "loss": 3.879, + "step": 2099712 + }, + { + "epoch": 0.01, + "learning_rate": 1.561299638421529e-05, + "loss": 3.8771, + "step": 2100224 + }, + { + "epoch": 0.01, + "learning_rate": 1.560461043670477e-05, + "loss": 3.8628, + "step": 2100736 + }, + { + "epoch": 0.01, + "learning_rate": 1.559622448919425e-05, + "loss": 3.8809, + "step": 2101248 + }, + { + "epoch": 0.01, + "learning_rate": 1.558785492048746e-05, + "loss": 3.8805, + "step": 2101760 + }, + { + "epoch": 0.01, + "learning_rate": 1.557946897297694e-05, + "loss": 3.8772, + "step": 2102272 + }, + { + "epoch": 0.01, + "learning_rate": 1.5571083025466423e-05, + "loss": 3.8843, + "step": 2102784 + }, + { + "epoch": 0.01, + "learning_rate": 1.5562697077955902e-05, + "loss": 3.8634, + "step": 2103296 + }, + { + "epoch": 0.01, + "learning_rate": 1.555431113044538e-05, + "loss": 3.8566, + "step": 2103808 + }, + { + "epoch": 0.01, + "learning_rate": 1.554594156173859e-05, + "loss": 3.8652, + "step": 2104320 + }, + { + "epoch": 0.01, + "learning_rate": 1.553755561422807e-05, + "loss": 3.8778, + "step": 2104832 + }, + { + "epoch": 0.01, + "learning_rate": 1.5529186045521284e-05, + "loss": 3.8717, + "step": 2105344 + }, + { + "epoch": 0.01, + "learning_rate": 1.5520800098010764e-05, + "loss": 3.8687, + "step": 2105856 + }, + { + "epoch": 0.01, + "learning_rate": 1.5512414150500244e-05, + "loss": 3.8682, + "step": 2106368 + }, + { + "epoch": 0.02, + "learning_rate": 1.5504028202989724e-05, + "loss": 3.8714, + "step": 2106880 + }, + { + "epoch": 0.02, + "learning_rate": 1.54956422554792e-05, + "loss": 3.8714, + "step": 2107392 + }, + { + "epoch": 0.02, + "learning_rate": 1.548725630796868e-05, + "loss": 3.8693, + "step": 2107904 + }, + { + "epoch": 0.02, + "learning_rate": 1.547887036045816e-05, + "loss": 3.8795, + "step": 2108416 + }, + { + "epoch": 0.02, + "learning_rate": 1.547048441294764e-05, + "loss": 3.8842, + "step": 2108928 + }, + { + "epoch": 0.02, + "learning_rate": 1.5462114844240853e-05, + "loss": 3.8782, + "step": 2109440 + }, + { + "epoch": 0.02, + "learning_rate": 1.5453728896730333e-05, + "loss": 3.8671, + "step": 2109952 + }, + { + "epoch": 0.02, + "learning_rate": 1.5445342949219813e-05, + "loss": 3.8681, + "step": 2110464 + }, + { + "epoch": 0.02, + "learning_rate": 1.5436957001709293e-05, + "loss": 3.8669, + "step": 2110976 + }, + { + "epoch": 0.02, + "learning_rate": 1.5428571054198773e-05, + "loss": 3.8811, + "step": 2111488 + }, + { + "epoch": 0.02, + "learning_rate": 1.5420185106688253e-05, + "loss": 3.8752, + "step": 2112000 + }, + { + "epoch": 0.02, + "learning_rate": 1.5411799159177732e-05, + "loss": 3.8707, + "step": 2112512 + }, + { + "epoch": 0.02, + "learning_rate": 1.5403413211667212e-05, + "loss": 3.8746, + "step": 2113024 + }, + { + "epoch": 0.02, + "learning_rate": 1.5395043642960425e-05, + "loss": 3.8723, + "step": 2113536 + }, + { + "epoch": 0.02, + "learning_rate": 1.5386657695449905e-05, + "loss": 3.8749, + "step": 2114048 + }, + { + "epoch": 0.02, + "learning_rate": 1.537827174793938e-05, + "loss": 3.8658, + "step": 2114560 + }, + { + "epoch": 0.02, + "learning_rate": 1.5369902179232594e-05, + "loss": 3.8629, + "step": 2115072 + }, + { + "epoch": 0.02, + "learning_rate": 1.5361516231722077e-05, + "loss": 3.8627, + "step": 2115584 + }, + { + "epoch": 0.02, + "learning_rate": 1.5353130284211557e-05, + "loss": 3.8721, + "step": 2116096 + }, + { + "epoch": 0.02, + "learning_rate": 1.5344744336701034e-05, + "loss": 3.8646, + "step": 2116608 + }, + { + "epoch": 0.02, + "learning_rate": 1.5336374767994246e-05, + "loss": 3.866, + "step": 2117120 + }, + { + "epoch": 0.02, + "learning_rate": 1.5327988820483726e-05, + "loss": 3.8712, + "step": 2117632 + }, + { + "epoch": 0.02, + "learning_rate": 1.5319602872973203e-05, + "loss": 3.866, + "step": 2118144 + }, + { + "epoch": 0.02, + "learning_rate": 1.5311216925462686e-05, + "loss": 3.8622, + "step": 2118656 + }, + { + "epoch": 0.02, + "learning_rate": 1.5302830977952166e-05, + "loss": 3.8835, + "step": 2119168 + }, + { + "epoch": 0.02, + "learning_rate": 1.5294445030441646e-05, + "loss": 3.8861, + "step": 2119680 + }, + { + "epoch": 0.02, + "learning_rate": 1.5286059082931126e-05, + "loss": 3.8733, + "step": 2120192 + }, + { + "epoch": 0.02, + "learning_rate": 1.5277689514224335e-05, + "loss": 3.8791, + "step": 2120704 + }, + { + "epoch": 0.02, + "learning_rate": 1.5269303566713815e-05, + "loss": 3.87, + "step": 2121216 + }, + { + "epoch": 0.02, + "learning_rate": 1.5260917619203295e-05, + "loss": 3.871, + "step": 2121728 + }, + { + "epoch": 0.02, + "learning_rate": 1.5252531671692777e-05, + "loss": 3.8734, + "step": 2122240 + }, + { + "epoch": 0.02, + "learning_rate": 1.5244162102985987e-05, + "loss": 3.8594, + "step": 2122752 + }, + { + "epoch": 0.02, + "learning_rate": 1.5235776155475467e-05, + "loss": 3.8691, + "step": 2123264 + }, + { + "epoch": 0.02, + "learning_rate": 1.5227390207964947e-05, + "loss": 3.8721, + "step": 2123776 + }, + { + "epoch": 0.02, + "learning_rate": 1.5219004260454427e-05, + "loss": 3.8811, + "step": 2124288 + }, + { + "epoch": 0.02, + "learning_rate": 1.5210618312943909e-05, + "loss": 3.8685, + "step": 2124800 + }, + { + "epoch": 0.02, + "learning_rate": 1.5202232365433386e-05, + "loss": 3.8767, + "step": 2125312 + }, + { + "epoch": 0.02, + "learning_rate": 1.5193846417922866e-05, + "loss": 3.8698, + "step": 2125824 + }, + { + "epoch": 0.02, + "learning_rate": 1.5185460470412347e-05, + "loss": 3.8657, + "step": 2126336 + }, + { + "epoch": 0.02, + "learning_rate": 1.517709090170556e-05, + "loss": 3.8735, + "step": 2126848 + }, + { + "epoch": 0.02, + "learning_rate": 1.5168704954195038e-05, + "loss": 3.878, + "step": 2127360 + }, + { + "epoch": 0.02, + "learning_rate": 1.5160319006684518e-05, + "loss": 3.8826, + "step": 2127872 + }, + { + "epoch": 0.02, + "learning_rate": 1.5151933059173998e-05, + "loss": 3.8643, + "step": 2128384 + }, + { + "epoch": 0.02, + "learning_rate": 1.5143579869270941e-05, + "loss": 3.8892, + "step": 2128896 + }, + { + "epoch": 0.02, + "learning_rate": 1.5135193921760421e-05, + "loss": 3.872, + "step": 2129408 + }, + { + "epoch": 0.02, + "learning_rate": 1.5126807974249901e-05, + "loss": 3.8831, + "step": 2129920 + }, + { + "epoch": 0.02, + "learning_rate": 1.5118422026739381e-05, + "loss": 3.879, + "step": 2130432 + }, + { + "epoch": 0.02, + "learning_rate": 1.5110052458032592e-05, + "loss": 3.8689, + "step": 2130944 + }, + { + "epoch": 0.02, + "learning_rate": 1.5101666510522072e-05, + "loss": 3.8665, + "step": 2131456 + }, + { + "epoch": 0.02, + "learning_rate": 1.5093280563011553e-05, + "loss": 3.8852, + "step": 2131968 + }, + { + "epoch": 0.02, + "learning_rate": 1.5084894615501033e-05, + "loss": 3.8601, + "step": 2132480 + }, + { + "epoch": 0.02, + "learning_rate": 1.507650866799051e-05, + "loss": 3.8713, + "step": 2132992 + }, + { + "epoch": 0.02, + "learning_rate": 1.5068139099283724e-05, + "loss": 3.8776, + "step": 2133504 + }, + { + "epoch": 0.02, + "learning_rate": 1.5059753151773204e-05, + "loss": 3.8741, + "step": 2134016 + }, + { + "epoch": 0.02, + "learning_rate": 1.505136720426268e-05, + "loss": 3.8698, + "step": 2134528 + }, + { + "epoch": 0.02, + "learning_rate": 1.5042981256752162e-05, + "loss": 3.8714, + "step": 2135040 + }, + { + "epoch": 0.02, + "learning_rate": 1.5034595309241642e-05, + "loss": 3.8735, + "step": 2135552 + }, + { + "epoch": 0.02, + "learning_rate": 1.5026209361731122e-05, + "loss": 3.8828, + "step": 2136064 + }, + { + "epoch": 0.02, + "learning_rate": 1.5017839793024333e-05, + "loss": 3.8737, + "step": 2136576 + }, + { + "epoch": 0.03, + "eval_loss": 3.981804847717285, + "eval_runtime": 299.3879, + "eval_samples_per_second": 1274.571, + "eval_steps_per_second": 39.831, + "step": 2136960 + }, + { + "epoch": 1.0, + "learning_rate": 1.5009453845513813e-05, + "loss": 3.8669, + "step": 2137088 + }, + { + "epoch": 1.0, + "learning_rate": 1.5001067898003293e-05, + "loss": 3.8638, + "step": 2137600 + }, + { + "epoch": 1.0, + "learning_rate": 1.4992681950492773e-05, + "loss": 3.8705, + "step": 2138112 + }, + { + "epoch": 1.0, + "learning_rate": 1.4984296002982255e-05, + "loss": 3.8773, + "step": 2138624 + }, + { + "epoch": 1.0, + "learning_rate": 1.4975910055471734e-05, + "loss": 3.8761, + "step": 2139136 + }, + { + "epoch": 1.0, + "learning_rate": 1.4967524107961214e-05, + "loss": 3.8731, + "step": 2139648 + }, + { + "epoch": 1.0, + "learning_rate": 1.4959138160450693e-05, + "loss": 3.8767, + "step": 2140160 + }, + { + "epoch": 1.0, + "learning_rate": 1.4950768591743905e-05, + "loss": 3.869, + "step": 2140672 + }, + { + "epoch": 1.0, + "learning_rate": 1.4942382644233385e-05, + "loss": 3.8671, + "step": 2141184 + }, + { + "epoch": 1.0, + "learning_rate": 1.4933996696722863e-05, + "loss": 3.8608, + "step": 2141696 + }, + { + "epoch": 1.0, + "learning_rate": 1.4925610749212343e-05, + "loss": 3.8793, + "step": 2142208 + }, + { + "epoch": 1.0, + "learning_rate": 1.4917241180505556e-05, + "loss": 3.884, + "step": 2142720 + }, + { + "epoch": 1.0, + "learning_rate": 1.4908871611798767e-05, + "loss": 3.8783, + "step": 2143232 + }, + { + "epoch": 1.0, + "learning_rate": 1.4900485664288247e-05, + "loss": 3.8556, + "step": 2143744 + }, + { + "epoch": 1.0, + "learning_rate": 1.4892099716777727e-05, + "loss": 3.8768, + "step": 2144256 + }, + { + "epoch": 1.0, + "learning_rate": 1.4883713769267208e-05, + "loss": 3.8579, + "step": 2144768 + }, + { + "epoch": 1.0, + "learning_rate": 1.4875327821756688e-05, + "loss": 3.8747, + "step": 2145280 + }, + { + "epoch": 1.0, + "learning_rate": 1.4866941874246165e-05, + "loss": 3.8681, + "step": 2145792 + }, + { + "epoch": 1.0, + "learning_rate": 1.4858555926735646e-05, + "loss": 3.8671, + "step": 2146304 + }, + { + "epoch": 1.0, + "learning_rate": 1.4850169979225126e-05, + "loss": 3.8756, + "step": 2146816 + }, + { + "epoch": 1.0, + "learning_rate": 1.4841784031714606e-05, + "loss": 3.883, + "step": 2147328 + }, + { + "epoch": 1.0, + "learning_rate": 1.4833414463007817e-05, + "loss": 3.871, + "step": 2147840 + }, + { + "epoch": 1.0, + "learning_rate": 1.4825028515497297e-05, + "loss": 3.8744, + "step": 2148352 + }, + { + "epoch": 1.0, + "learning_rate": 1.4816642567986777e-05, + "loss": 3.8712, + "step": 2148864 + }, + { + "epoch": 1.0, + "learning_rate": 1.4808256620476257e-05, + "loss": 3.877, + "step": 2149376 + }, + { + "epoch": 1.0, + "learning_rate": 1.4799870672965737e-05, + "loss": 3.8739, + "step": 2149888 + }, + { + "epoch": 1.0, + "learning_rate": 1.4791484725455219e-05, + "loss": 3.8665, + "step": 2150400 + }, + { + "epoch": 1.0, + "learning_rate": 1.4783098777944695e-05, + "loss": 3.8668, + "step": 2150912 + }, + { + "epoch": 1.0, + "learning_rate": 1.4774712830434175e-05, + "loss": 3.8673, + "step": 2151424 + }, + { + "epoch": 1.0, + "learning_rate": 1.476634326172739e-05, + "loss": 3.8702, + "step": 2151936 + }, + { + "epoch": 1.01, + "learning_rate": 1.475795731421687e-05, + "loss": 3.8682, + "step": 2152448 + }, + { + "epoch": 1.01, + "learning_rate": 1.4749571366706347e-05, + "loss": 3.8729, + "step": 2152960 + }, + { + "epoch": 1.01, + "learning_rate": 1.4741185419195827e-05, + "loss": 3.8743, + "step": 2153472 + }, + { + "epoch": 1.01, + "learning_rate": 1.4732799471685307e-05, + "loss": 3.8805, + "step": 2153984 + }, + { + "epoch": 1.01, + "learning_rate": 1.4724413524174787e-05, + "loss": 3.8712, + "step": 2154496 + }, + { + "epoch": 1.01, + "learning_rate": 1.4716043955467998e-05, + "loss": 3.8709, + "step": 2155008 + }, + { + "epoch": 1.01, + "learning_rate": 1.4707658007957478e-05, + "loss": 3.8797, + "step": 2155520 + }, + { + "epoch": 1.01, + "learning_rate": 1.4699272060446958e-05, + "loss": 3.8579, + "step": 2156032 + }, + { + "epoch": 1.01, + "learning_rate": 1.469088611293644e-05, + "loss": 3.8629, + "step": 2156544 + }, + { + "epoch": 1.01, + "learning_rate": 1.468250016542592e-05, + "loss": 3.8673, + "step": 2157056 + }, + { + "epoch": 1.01, + "learning_rate": 1.46741142179154e-05, + "loss": 3.8644, + "step": 2157568 + }, + { + "epoch": 1.01, + "learning_rate": 1.4665728270404878e-05, + "loss": 3.8693, + "step": 2158080 + }, + { + "epoch": 1.01, + "learning_rate": 1.4657342322894358e-05, + "loss": 3.8646, + "step": 2158592 + }, + { + "epoch": 1.01, + "learning_rate": 1.464897275418757e-05, + "loss": 3.871, + "step": 2159104 + }, + { + "epoch": 1.01, + "learning_rate": 1.4640586806677049e-05, + "loss": 3.874, + "step": 2159616 + }, + { + "epoch": 1.01, + "learning_rate": 1.4632200859166528e-05, + "loss": 3.8764, + "step": 2160128 + }, + { + "epoch": 1.01, + "learning_rate": 1.4623814911656008e-05, + "loss": 3.8745, + "step": 2160640 + }, + { + "epoch": 1.01, + "learning_rate": 1.4615445342949221e-05, + "loss": 3.8708, + "step": 2161152 + }, + { + "epoch": 1.01, + "learning_rate": 1.4607075774242432e-05, + "loss": 3.8496, + "step": 2161664 + }, + { + "epoch": 1.01, + "learning_rate": 1.4598689826731912e-05, + "loss": 3.8778, + "step": 2162176 + }, + { + "epoch": 1.01, + "learning_rate": 1.4590303879221393e-05, + "loss": 3.8666, + "step": 2162688 + }, + { + "epoch": 1.01, + "learning_rate": 1.4581917931710873e-05, + "loss": 3.871, + "step": 2163200 + }, + { + "epoch": 1.01, + "learning_rate": 1.457353198420035e-05, + "loss": 3.867, + "step": 2163712 + }, + { + "epoch": 1.01, + "learning_rate": 1.4565162415493564e-05, + "loss": 3.8649, + "step": 2164224 + }, + { + "epoch": 1.01, + "learning_rate": 1.4556792846786773e-05, + "loss": 3.8601, + "step": 2164736 + }, + { + "epoch": 1.01, + "learning_rate": 1.4548406899276255e-05, + "loss": 3.8627, + "step": 2165248 + }, + { + "epoch": 1.01, + "learning_rate": 1.4540020951765735e-05, + "loss": 3.8667, + "step": 2165760 + }, + { + "epoch": 1.01, + "learning_rate": 1.4531635004255215e-05, + "loss": 3.856, + "step": 2166272 + }, + { + "epoch": 1.01, + "learning_rate": 1.4523249056744695e-05, + "loss": 3.8795, + "step": 2166784 + }, + { + "epoch": 1.01, + "learning_rate": 1.4514863109234173e-05, + "loss": 3.8697, + "step": 2167296 + }, + { + "epoch": 1.01, + "learning_rate": 1.4506477161723653e-05, + "loss": 3.8512, + "step": 2167808 + }, + { + "epoch": 1.01, + "learning_rate": 1.4498091214213133e-05, + "loss": 3.8844, + "step": 2168320 + }, + { + "epoch": 1.01, + "learning_rate": 1.4489721645506347e-05, + "loss": 3.8566, + "step": 2168832 + }, + { + "epoch": 1.01, + "learning_rate": 1.4481335697995824e-05, + "loss": 3.855, + "step": 2169344 + }, + { + "epoch": 1.01, + "learning_rate": 1.4472949750485304e-05, + "loss": 3.8695, + "step": 2169856 + }, + { + "epoch": 1.01, + "learning_rate": 1.4464563802974783e-05, + "loss": 3.8677, + "step": 2170368 + }, + { + "epoch": 1.01, + "learning_rate": 1.4456177855464265e-05, + "loss": 3.8569, + "step": 2170880 + }, + { + "epoch": 1.01, + "learning_rate": 1.4447791907953745e-05, + "loss": 3.8708, + "step": 2171392 + }, + { + "epoch": 1.01, + "learning_rate": 1.4439422339246956e-05, + "loss": 3.8539, + "step": 2171904 + }, + { + "epoch": 1.01, + "learning_rate": 1.4431036391736436e-05, + "loss": 3.8578, + "step": 2172416 + }, + { + "epoch": 1.01, + "learning_rate": 1.4422650444225916e-05, + "loss": 3.8757, + "step": 2172928 + }, + { + "epoch": 1.01, + "learning_rate": 1.4414264496715396e-05, + "loss": 3.8685, + "step": 2173440 + }, + { + "epoch": 1.01, + "learning_rate": 1.4405878549204876e-05, + "loss": 3.8742, + "step": 2173952 + }, + { + "epoch": 1.01, + "learning_rate": 1.4397492601694354e-05, + "loss": 3.8719, + "step": 2174464 + }, + { + "epoch": 1.01, + "learning_rate": 1.4389106654183834e-05, + "loss": 3.8828, + "step": 2174976 + }, + { + "epoch": 1.01, + "learning_rate": 1.4380737085477048e-05, + "loss": 3.8606, + "step": 2175488 + }, + { + "epoch": 1.01, + "learning_rate": 1.4372351137966528e-05, + "loss": 3.8753, + "step": 2176000 + }, + { + "epoch": 1.01, + "learning_rate": 1.4363965190456005e-05, + "loss": 3.8701, + "step": 2176512 + }, + { + "epoch": 1.01, + "learning_rate": 1.4355579242945486e-05, + "loss": 3.8626, + "step": 2177024 + }, + { + "epoch": 1.01, + "learning_rate": 1.4347193295434966e-05, + "loss": 3.8697, + "step": 2177536 + }, + { + "epoch": 1.01, + "learning_rate": 1.4338807347924446e-05, + "loss": 3.8813, + "step": 2178048 + }, + { + "epoch": 1.01, + "learning_rate": 1.4330421400413926e-05, + "loss": 3.8713, + "step": 2178560 + }, + { + "epoch": 1.01, + "learning_rate": 1.4322035452903406e-05, + "loss": 3.8809, + "step": 2179072 + }, + { + "epoch": 1.01, + "learning_rate": 1.4313665884196617e-05, + "loss": 3.8587, + "step": 2179584 + }, + { + "epoch": 1.01, + "learning_rate": 1.4305296315489828e-05, + "loss": 3.8514, + "step": 2180096 + }, + { + "epoch": 1.01, + "learning_rate": 1.4296910367979308e-05, + "loss": 3.8596, + "step": 2180608 + }, + { + "epoch": 1.01, + "learning_rate": 1.4288524420468788e-05, + "loss": 3.8708, + "step": 2181120 + }, + { + "epoch": 1.01, + "learning_rate": 1.4280138472958268e-05, + "loss": 3.8685, + "step": 2181632 + }, + { + "epoch": 1.01, + "learning_rate": 1.427175252544775e-05, + "loss": 3.8654, + "step": 2182144 + }, + { + "epoch": 1.01, + "learning_rate": 1.4263366577937229e-05, + "loss": 3.8607, + "step": 2182656 + }, + { + "epoch": 1.02, + "learning_rate": 1.4254980630426709e-05, + "loss": 3.8678, + "step": 2183168 + }, + { + "epoch": 1.02, + "learning_rate": 1.4246594682916187e-05, + "loss": 3.8664, + "step": 2183680 + }, + { + "epoch": 1.02, + "learning_rate": 1.42382251142094e-05, + "loss": 3.8616, + "step": 2184192 + }, + { + "epoch": 1.02, + "learning_rate": 1.422985554550261e-05, + "loss": 3.8772, + "step": 2184704 + }, + { + "epoch": 1.02, + "learning_rate": 1.4221485976795823e-05, + "loss": 3.8786, + "step": 2185216 + }, + { + "epoch": 1.02, + "learning_rate": 1.4213100029285301e-05, + "loss": 3.8773, + "step": 2185728 + }, + { + "epoch": 1.02, + "learning_rate": 1.4204714081774781e-05, + "loss": 3.8589, + "step": 2186240 + }, + { + "epoch": 1.02, + "learning_rate": 1.4196328134264261e-05, + "loss": 3.8666, + "step": 2186752 + }, + { + "epoch": 1.02, + "learning_rate": 1.4187942186753741e-05, + "loss": 3.8625, + "step": 2187264 + }, + { + "epoch": 1.02, + "learning_rate": 1.4179556239243221e-05, + "loss": 3.8772, + "step": 2187776 + }, + { + "epoch": 1.02, + "learning_rate": 1.4171170291732703e-05, + "loss": 3.8732, + "step": 2188288 + }, + { + "epoch": 1.02, + "learning_rate": 1.4162784344222183e-05, + "loss": 3.8634, + "step": 2188800 + }, + { + "epoch": 1.02, + "learning_rate": 1.415439839671166e-05, + "loss": 3.869, + "step": 2189312 + }, + { + "epoch": 1.02, + "learning_rate": 1.4146012449201141e-05, + "loss": 3.8686, + "step": 2189824 + }, + { + "epoch": 1.02, + "learning_rate": 1.4137626501690621e-05, + "loss": 3.8707, + "step": 2190336 + }, + { + "epoch": 1.02, + "learning_rate": 1.4129240554180101e-05, + "loss": 3.8632, + "step": 2190848 + }, + { + "epoch": 1.02, + "learning_rate": 1.4120870985473312e-05, + "loss": 3.863, + "step": 2191360 + }, + { + "epoch": 1.02, + "learning_rate": 1.4112485037962792e-05, + "loss": 3.8557, + "step": 2191872 + }, + { + "epoch": 1.02, + "learning_rate": 1.4104099090452272e-05, + "loss": 3.8662, + "step": 2192384 + }, + { + "epoch": 1.02, + "learning_rate": 1.4095713142941752e-05, + "loss": 3.8643, + "step": 2192896 + }, + { + "epoch": 1.02, + "learning_rate": 1.4087343574234962e-05, + "loss": 3.8596, + "step": 2193408 + }, + { + "epoch": 1.02, + "learning_rate": 1.4078974005528175e-05, + "loss": 3.8658, + "step": 2193920 + }, + { + "epoch": 1.02, + "learning_rate": 1.4070588058017657e-05, + "loss": 3.8655, + "step": 2194432 + }, + { + "epoch": 1.02, + "learning_rate": 1.4062202110507133e-05, + "loss": 3.8554, + "step": 2194944 + }, + { + "epoch": 1.02, + "learning_rate": 1.4053816162996613e-05, + "loss": 3.8788, + "step": 2195456 + }, + { + "epoch": 1.02, + "learning_rate": 1.4045430215486095e-05, + "loss": 3.8827, + "step": 2195968 + }, + { + "epoch": 1.02, + "learning_rate": 1.4037044267975575e-05, + "loss": 3.8733, + "step": 2196480 + }, + { + "epoch": 1.02, + "learning_rate": 1.4028674699268784e-05, + "loss": 3.8723, + "step": 2196992 + }, + { + "epoch": 1.02, + "learning_rate": 1.4020288751758265e-05, + "loss": 3.8708, + "step": 2197504 + }, + { + "epoch": 1.02, + "learning_rate": 1.4011902804247745e-05, + "loss": 3.8631, + "step": 2198016 + }, + { + "epoch": 1.02, + "learning_rate": 1.4003533235540956e-05, + "loss": 3.8775, + "step": 2198528 + }, + { + "epoch": 1.02, + "learning_rate": 1.3995147288030436e-05, + "loss": 3.8497, + "step": 2199040 + }, + { + "epoch": 1.02, + "learning_rate": 1.3986761340519916e-05, + "loss": 3.8676, + "step": 2199552 + }, + { + "epoch": 1.02, + "learning_rate": 1.3978375393009396e-05, + "loss": 3.8649, + "step": 2200064 + }, + { + "epoch": 1.02, + "learning_rate": 1.3969989445498876e-05, + "loss": 3.8731, + "step": 2200576 + }, + { + "epoch": 1.02, + "learning_rate": 1.3961603497988358e-05, + "loss": 3.8646, + "step": 2201088 + }, + { + "epoch": 1.02, + "learning_rate": 1.3953217550477834e-05, + "loss": 3.8702, + "step": 2201600 + }, + { + "epoch": 1.02, + "learning_rate": 1.3944831602967314e-05, + "loss": 3.8621, + "step": 2202112 + }, + { + "epoch": 1.02, + "learning_rate": 1.3936445655456796e-05, + "loss": 3.8602, + "step": 2202624 + }, + { + "epoch": 1.02, + "learning_rate": 1.3928059707946276e-05, + "loss": 3.8732, + "step": 2203136 + }, + { + "epoch": 1.02, + "learning_rate": 1.3919673760435756e-05, + "loss": 3.8713, + "step": 2203648 + }, + { + "epoch": 1.02, + "learning_rate": 1.3911304191728966e-05, + "loss": 3.8792, + "step": 2204160 + }, + { + "epoch": 1.02, + "learning_rate": 1.3902918244218446e-05, + "loss": 3.8646, + "step": 2204672 + }, + { + "epoch": 1.02, + "learning_rate": 1.3894532296707926e-05, + "loss": 3.8789, + "step": 2205184 + }, + { + "epoch": 1.02, + "learning_rate": 1.3886146349197406e-05, + "loss": 3.8699, + "step": 2205696 + }, + { + "epoch": 1.02, + "learning_rate": 1.3877760401686888e-05, + "loss": 3.8731, + "step": 2206208 + }, + { + "epoch": 1.02, + "learning_rate": 1.3869374454176368e-05, + "loss": 3.877, + "step": 2206720 + }, + { + "epoch": 1.02, + "learning_rate": 1.3860988506665845e-05, + "loss": 3.8674, + "step": 2207232 + }, + { + "epoch": 1.02, + "learning_rate": 1.3852602559155326e-05, + "loss": 3.8624, + "step": 2207744 + }, + { + "epoch": 1.02, + "learning_rate": 1.3844232990448539e-05, + "loss": 3.8796, + "step": 2208256 + }, + { + "epoch": 1.02, + "learning_rate": 1.3835847042938015e-05, + "loss": 3.8607, + "step": 2208768 + }, + { + "epoch": 1.02, + "learning_rate": 1.3827461095427497e-05, + "loss": 3.8648, + "step": 2209280 + }, + { + "epoch": 1.02, + "learning_rate": 1.381909152672071e-05, + "loss": 3.8747, + "step": 2209792 + }, + { + "epoch": 1.02, + "learning_rate": 1.381070557921019e-05, + "loss": 3.8703, + "step": 2210304 + }, + { + "epoch": 1.02, + "learning_rate": 1.3802319631699668e-05, + "loss": 3.8659, + "step": 2210816 + }, + { + "epoch": 1.02, + "learning_rate": 1.3793933684189148e-05, + "loss": 3.8688, + "step": 2211328 + }, + { + "epoch": 1.02, + "learning_rate": 1.3785547736678627e-05, + "loss": 3.869, + "step": 2211840 + }, + { + "epoch": 1.02, + "learning_rate": 1.3777161789168107e-05, + "loss": 3.8774, + "step": 2212352 + }, + { + "epoch": 1.02, + "learning_rate": 1.3768792220461318e-05, + "loss": 3.8729, + "step": 2212864 + }, + { + "epoch": 1.03, + "eval_loss": 3.980177879333496, + "eval_runtime": 296.1897, + "eval_samples_per_second": 1288.333, + "eval_steps_per_second": 40.261, + "step": 2213280 + }, + { + "epoch": 0.0, + "learning_rate": 1.3760406272950798e-05, + "loss": 3.8555, + "step": 2213376 + }, + { + "epoch": 0.0, + "learning_rate": 1.375202032544028e-05, + "loss": 3.8592, + "step": 2213888 + }, + { + "epoch": 0.0, + "learning_rate": 1.374363437792976e-05, + "loss": 3.864, + "step": 2214400 + }, + { + "epoch": 0.0, + "learning_rate": 1.373524843041924e-05, + "loss": 3.8777, + "step": 2214912 + }, + { + "epoch": 0.0, + "learning_rate": 1.372686248290872e-05, + "loss": 3.8715, + "step": 2215424 + }, + { + "epoch": 0.0, + "learning_rate": 1.3718476535398198e-05, + "loss": 3.8684, + "step": 2215936 + }, + { + "epoch": 0.0, + "learning_rate": 1.3710090587887678e-05, + "loss": 3.8691, + "step": 2216448 + }, + { + "epoch": 0.0, + "learning_rate": 1.3701704640377158e-05, + "loss": 3.8669, + "step": 2216960 + }, + { + "epoch": 0.0, + "learning_rate": 1.3693318692866638e-05, + "loss": 3.8592, + "step": 2217472 + }, + { + "epoch": 0.0, + "learning_rate": 1.368493274535612e-05, + "loss": 3.863, + "step": 2217984 + }, + { + "epoch": 0.0, + "learning_rate": 1.36765467978456e-05, + "loss": 3.8744, + "step": 2218496 + }, + { + "epoch": 0.0, + "learning_rate": 1.366816085033508e-05, + "loss": 3.8766, + "step": 2219008 + }, + { + "epoch": 0.0, + "learning_rate": 1.365979128162829e-05, + "loss": 3.8806, + "step": 2219520 + }, + { + "epoch": 0.0, + "learning_rate": 1.365140533411777e-05, + "loss": 3.847, + "step": 2220032 + }, + { + "epoch": 0.0, + "learning_rate": 1.364301938660725e-05, + "loss": 3.8669, + "step": 2220544 + }, + { + "epoch": 0.0, + "learning_rate": 1.363463343909673e-05, + "loss": 3.8574, + "step": 2221056 + }, + { + "epoch": 0.0, + "learning_rate": 1.3626247491586208e-05, + "loss": 3.8705, + "step": 2221568 + }, + { + "epoch": 0.0, + "learning_rate": 1.3617861544075688e-05, + "loss": 3.8641, + "step": 2222080 + }, + { + "epoch": 0.0, + "learning_rate": 1.3609475596565168e-05, + "loss": 3.8655, + "step": 2222592 + }, + { + "epoch": 0.0, + "learning_rate": 1.360108964905465e-05, + "loss": 3.8637, + "step": 2223104 + }, + { + "epoch": 0.0, + "learning_rate": 1.359270370154413e-05, + "loss": 3.8849, + "step": 2223616 + }, + { + "epoch": 0.0, + "learning_rate": 1.358431775403361e-05, + "loss": 3.8654, + "step": 2224128 + }, + { + "epoch": 0.0, + "learning_rate": 1.3575931806523088e-05, + "loss": 3.8696, + "step": 2224640 + }, + { + "epoch": 0.0, + "learning_rate": 1.35675622378163e-05, + "loss": 3.8667, + "step": 2225152 + }, + { + "epoch": 0.0, + "learning_rate": 1.355917629030578e-05, + "loss": 3.8757, + "step": 2225664 + }, + { + "epoch": 0.0, + "learning_rate": 1.355079034279526e-05, + "loss": 3.8672, + "step": 2226176 + }, + { + "epoch": 0.0, + "learning_rate": 1.3542404395284739e-05, + "loss": 3.8619, + "step": 2226688 + }, + { + "epoch": 0.0, + "learning_rate": 1.3534018447774219e-05, + "loss": 3.8642, + "step": 2227200 + }, + { + "epoch": 0.0, + "learning_rate": 1.3525632500263699e-05, + "loss": 3.8643, + "step": 2227712 + }, + { + "epoch": 0.0, + "learning_rate": 1.351724655275318e-05, + "loss": 3.8613, + "step": 2228224 + }, + { + "epoch": 0.01, + "learning_rate": 1.350886060524266e-05, + "loss": 3.8658, + "step": 2228736 + }, + { + "epoch": 0.01, + "learning_rate": 1.3500507415339604e-05, + "loss": 3.8658, + "step": 2229248 + }, + { + "epoch": 0.01, + "learning_rate": 1.3492121467829083e-05, + "loss": 3.8736, + "step": 2229760 + }, + { + "epoch": 0.01, + "learning_rate": 1.348373552031856e-05, + "loss": 3.8725, + "step": 2230272 + }, + { + "epoch": 0.01, + "learning_rate": 1.3475349572808042e-05, + "loss": 3.8673, + "step": 2230784 + }, + { + "epoch": 0.01, + "learning_rate": 1.3466980004101254e-05, + "loss": 3.8697, + "step": 2231296 + }, + { + "epoch": 0.01, + "learning_rate": 1.3458594056590734e-05, + "loss": 3.8769, + "step": 2231808 + }, + { + "epoch": 0.01, + "learning_rate": 1.3450208109080212e-05, + "loss": 3.8517, + "step": 2232320 + }, + { + "epoch": 0.01, + "learning_rate": 1.3441822161569692e-05, + "loss": 3.8632, + "step": 2232832 + }, + { + "epoch": 0.01, + "learning_rate": 1.3433452592862905e-05, + "loss": 3.8667, + "step": 2233344 + }, + { + "epoch": 0.01, + "learning_rate": 1.3425066645352383e-05, + "loss": 3.8544, + "step": 2233856 + }, + { + "epoch": 0.01, + "learning_rate": 1.3416680697841863e-05, + "loss": 3.8677, + "step": 2234368 + }, + { + "epoch": 0.01, + "learning_rate": 1.3408294750331343e-05, + "loss": 3.8636, + "step": 2234880 + }, + { + "epoch": 0.01, + "learning_rate": 1.3399908802820823e-05, + "loss": 3.8644, + "step": 2235392 + }, + { + "epoch": 0.01, + "learning_rate": 1.3391522855310305e-05, + "loss": 3.8697, + "step": 2235904 + }, + { + "epoch": 0.01, + "learning_rate": 1.3383136907799785e-05, + "loss": 3.8695, + "step": 2236416 + }, + { + "epoch": 0.01, + "learning_rate": 1.3374750960289265e-05, + "loss": 3.873, + "step": 2236928 + }, + { + "epoch": 0.01, + "learning_rate": 1.3366365012778743e-05, + "loss": 3.8653, + "step": 2237440 + }, + { + "epoch": 0.01, + "learning_rate": 1.3357995444071955e-05, + "loss": 3.8489, + "step": 2237952 + }, + { + "epoch": 0.01, + "learning_rate": 1.3349609496561435e-05, + "loss": 3.8692, + "step": 2238464 + }, + { + "epoch": 0.01, + "learning_rate": 1.3341223549050915e-05, + "loss": 3.8658, + "step": 2238976 + }, + { + "epoch": 0.01, + "learning_rate": 1.3332837601540393e-05, + "loss": 3.8705, + "step": 2239488 + }, + { + "epoch": 0.01, + "learning_rate": 1.3324451654029873e-05, + "loss": 3.864, + "step": 2240000 + }, + { + "epoch": 0.01, + "learning_rate": 1.3316065706519353e-05, + "loss": 3.8582, + "step": 2240512 + }, + { + "epoch": 0.01, + "learning_rate": 1.3307679759008835e-05, + "loss": 3.8584, + "step": 2241024 + }, + { + "epoch": 0.01, + "learning_rate": 1.3299293811498315e-05, + "loss": 3.8581, + "step": 2241536 + }, + { + "epoch": 0.01, + "learning_rate": 1.3290924242791524e-05, + "loss": 3.864, + "step": 2242048 + }, + { + "epoch": 0.01, + "learning_rate": 1.3282554674084738e-05, + "loss": 3.8512, + "step": 2242560 + }, + { + "epoch": 0.01, + "learning_rate": 1.3274168726574215e-05, + "loss": 3.8768, + "step": 2243072 + }, + { + "epoch": 0.01, + "learning_rate": 1.3265782779063696e-05, + "loss": 3.868, + "step": 2243584 + }, + { + "epoch": 0.01, + "learning_rate": 1.3257396831553176e-05, + "loss": 3.8489, + "step": 2244096 + }, + { + "epoch": 0.01, + "learning_rate": 1.3249010884042656e-05, + "loss": 3.8759, + "step": 2244608 + }, + { + "epoch": 0.01, + "learning_rate": 1.3240624936532136e-05, + "loss": 3.853, + "step": 2245120 + }, + { + "epoch": 0.01, + "learning_rate": 1.3232238989021616e-05, + "loss": 3.8564, + "step": 2245632 + }, + { + "epoch": 0.01, + "learning_rate": 1.3223869420314827e-05, + "loss": 3.8587, + "step": 2246144 + }, + { + "epoch": 0.01, + "learning_rate": 1.3215483472804307e-05, + "loss": 3.8706, + "step": 2246656 + }, + { + "epoch": 0.01, + "learning_rate": 1.3207097525293789e-05, + "loss": 3.8538, + "step": 2247168 + }, + { + "epoch": 0.01, + "learning_rate": 1.3198711577783269e-05, + "loss": 3.8696, + "step": 2247680 + }, + { + "epoch": 0.01, + "learning_rate": 1.3190342009076478e-05, + "loss": 3.8457, + "step": 2248192 + }, + { + "epoch": 0.01, + "learning_rate": 1.318195606156596e-05, + "loss": 3.8556, + "step": 2248704 + }, + { + "epoch": 0.01, + "learning_rate": 1.317357011405544e-05, + "loss": 3.8744, + "step": 2249216 + }, + { + "epoch": 0.01, + "learning_rate": 1.316518416654492e-05, + "loss": 3.8611, + "step": 2249728 + }, + { + "epoch": 0.01, + "learning_rate": 1.3156798219034398e-05, + "loss": 3.8707, + "step": 2250240 + }, + { + "epoch": 0.01, + "learning_rate": 1.314842865032761e-05, + "loss": 3.8668, + "step": 2250752 + }, + { + "epoch": 0.01, + "learning_rate": 1.314004270281709e-05, + "loss": 3.8785, + "step": 2251264 + }, + { + "epoch": 0.01, + "learning_rate": 1.313165675530657e-05, + "loss": 3.8534, + "step": 2251776 + }, + { + "epoch": 0.01, + "learning_rate": 1.3123270807796048e-05, + "loss": 3.8723, + "step": 2252288 + }, + { + "epoch": 0.01, + "learning_rate": 1.3114884860285528e-05, + "loss": 3.862, + "step": 2252800 + }, + { + "epoch": 0.01, + "learning_rate": 1.3106498912775008e-05, + "loss": 3.8618, + "step": 2253312 + }, + { + "epoch": 0.01, + "learning_rate": 1.3098129344068219e-05, + "loss": 3.866, + "step": 2253824 + }, + { + "epoch": 0.01, + "learning_rate": 1.3089743396557699e-05, + "loss": 3.8775, + "step": 2254336 + }, + { + "epoch": 0.01, + "learning_rate": 1.3081357449047179e-05, + "loss": 3.8681, + "step": 2254848 + }, + { + "epoch": 0.01, + "learning_rate": 1.307297150153666e-05, + "loss": 3.8757, + "step": 2255360 + }, + { + "epoch": 0.01, + "learning_rate": 1.306458555402614e-05, + "loss": 3.8525, + "step": 2255872 + }, + { + "epoch": 0.01, + "learning_rate": 1.3056215985319351e-05, + "loss": 3.8531, + "step": 2256384 + }, + { + "epoch": 0.01, + "learning_rate": 1.3047830037808831e-05, + "loss": 3.8577, + "step": 2256896 + }, + { + "epoch": 0.01, + "learning_rate": 1.3039444090298311e-05, + "loss": 3.8642, + "step": 2257408 + }, + { + "epoch": 0.01, + "learning_rate": 1.3031058142787791e-05, + "loss": 3.8637, + "step": 2257920 + }, + { + "epoch": 0.01, + "learning_rate": 1.3022672195277271e-05, + "loss": 3.8629, + "step": 2258432 + }, + { + "epoch": 0.01, + "learning_rate": 1.3014286247766753e-05, + "loss": 3.863, + "step": 2258944 + }, + { + "epoch": 0.02, + "learning_rate": 1.3005916679059962e-05, + "loss": 3.8608, + "step": 2259456 + }, + { + "epoch": 0.02, + "learning_rate": 1.2997530731549443e-05, + "loss": 3.8637, + "step": 2259968 + }, + { + "epoch": 0.02, + "learning_rate": 1.2989144784038923e-05, + "loss": 3.8574, + "step": 2260480 + }, + { + "epoch": 0.02, + "learning_rate": 1.29807588365284e-05, + "loss": 3.8722, + "step": 2260992 + }, + { + "epoch": 0.02, + "learning_rate": 1.2972389267821614e-05, + "loss": 3.8766, + "step": 2261504 + }, + { + "epoch": 0.02, + "learning_rate": 1.2964003320311094e-05, + "loss": 3.8716, + "step": 2262016 + }, + { + "epoch": 0.02, + "learning_rate": 1.2955617372800574e-05, + "loss": 3.8574, + "step": 2262528 + }, + { + "epoch": 0.02, + "learning_rate": 1.2947231425290052e-05, + "loss": 3.8598, + "step": 2263040 + }, + { + "epoch": 0.02, + "learning_rate": 1.2938845477779532e-05, + "loss": 3.8604, + "step": 2263552 + }, + { + "epoch": 0.02, + "learning_rate": 1.2930475909072745e-05, + "loss": 3.8707, + "step": 2264064 + }, + { + "epoch": 0.02, + "learning_rate": 1.2922089961562225e-05, + "loss": 3.8691, + "step": 2264576 + }, + { + "epoch": 0.02, + "learning_rate": 1.2913704014051703e-05, + "loss": 3.8595, + "step": 2265088 + }, + { + "epoch": 0.02, + "learning_rate": 1.2905318066541183e-05, + "loss": 3.865, + "step": 2265600 + }, + { + "epoch": 0.02, + "learning_rate": 1.2896932119030663e-05, + "loss": 3.868, + "step": 2266112 + }, + { + "epoch": 0.02, + "learning_rate": 1.2888562550323874e-05, + "loss": 3.8652, + "step": 2266624 + }, + { + "epoch": 0.02, + "learning_rate": 1.2880176602813354e-05, + "loss": 3.8623, + "step": 2267136 + }, + { + "epoch": 0.02, + "learning_rate": 1.2871790655302835e-05, + "loss": 3.8558, + "step": 2267648 + }, + { + "epoch": 0.02, + "learning_rate": 1.2863404707792315e-05, + "loss": 3.8511, + "step": 2268160 + }, + { + "epoch": 0.02, + "learning_rate": 1.2855018760281795e-05, + "loss": 3.8665, + "step": 2268672 + }, + { + "epoch": 0.02, + "learning_rate": 1.2846632812771275e-05, + "loss": 3.854, + "step": 2269184 + }, + { + "epoch": 0.02, + "learning_rate": 1.2838246865260755e-05, + "loss": 3.8577, + "step": 2269696 + }, + { + "epoch": 0.02, + "learning_rate": 1.2829877296553966e-05, + "loss": 3.861, + "step": 2270208 + }, + { + "epoch": 0.02, + "learning_rate": 1.2821491349043446e-05, + "loss": 3.8604, + "step": 2270720 + }, + { + "epoch": 0.02, + "learning_rate": 1.2813105401532926e-05, + "loss": 3.8586, + "step": 2271232 + }, + { + "epoch": 0.02, + "learning_rate": 1.2804719454022404e-05, + "loss": 3.8688, + "step": 2271744 + }, + { + "epoch": 0.02, + "learning_rate": 1.2796333506511884e-05, + "loss": 3.8755, + "step": 2272256 + }, + { + "epoch": 0.02, + "learning_rate": 1.2787963937805098e-05, + "loss": 3.8701, + "step": 2272768 + }, + { + "epoch": 0.02, + "learning_rate": 1.2779577990294578e-05, + "loss": 3.8719, + "step": 2273280 + }, + { + "epoch": 0.02, + "learning_rate": 1.2771192042784055e-05, + "loss": 3.8613, + "step": 2273792 + }, + { + "epoch": 0.02, + "learning_rate": 1.2762806095273536e-05, + "loss": 3.863, + "step": 2274304 + }, + { + "epoch": 0.02, + "learning_rate": 1.2754436526566749e-05, + "loss": 3.8673, + "step": 2274816 + }, + { + "epoch": 0.02, + "learning_rate": 1.2746050579056229e-05, + "loss": 3.8486, + "step": 2275328 + }, + { + "epoch": 0.02, + "learning_rate": 1.2737664631545707e-05, + "loss": 3.8649, + "step": 2275840 + }, + { + "epoch": 0.02, + "learning_rate": 1.2729278684035187e-05, + "loss": 3.857, + "step": 2276352 + }, + { + "epoch": 0.02, + "learning_rate": 1.2720892736524667e-05, + "loss": 3.8709, + "step": 2276864 + }, + { + "epoch": 0.02, + "learning_rate": 1.2712506789014147e-05, + "loss": 3.8674, + "step": 2277376 + }, + { + "epoch": 0.02, + "learning_rate": 1.2704120841503629e-05, + "loss": 3.865, + "step": 2277888 + }, + { + "epoch": 0.02, + "learning_rate": 1.2695734893993109e-05, + "loss": 3.8573, + "step": 2278400 + }, + { + "epoch": 0.02, + "learning_rate": 1.2687348946482585e-05, + "loss": 3.8583, + "step": 2278912 + }, + { + "epoch": 0.02, + "learning_rate": 1.2678995756579528e-05, + "loss": 3.8708, + "step": 2279424 + }, + { + "epoch": 0.02, + "learning_rate": 1.2670609809069008e-05, + "loss": 3.8678, + "step": 2279936 + }, + { + "epoch": 0.02, + "learning_rate": 1.2662240240362223e-05, + "loss": 3.8732, + "step": 2280448 + }, + { + "epoch": 0.02, + "learning_rate": 1.2653854292851703e-05, + "loss": 3.8585, + "step": 2280960 + }, + { + "epoch": 0.02, + "learning_rate": 1.2645468345341179e-05, + "loss": 3.8742, + "step": 2281472 + }, + { + "epoch": 0.02, + "learning_rate": 1.263708239783066e-05, + "loss": 3.8685, + "step": 2281984 + }, + { + "epoch": 0.02, + "learning_rate": 1.262869645032014e-05, + "loss": 3.8683, + "step": 2282496 + }, + { + "epoch": 0.02, + "learning_rate": 1.262031050280962e-05, + "loss": 3.8756, + "step": 2283008 + }, + { + "epoch": 0.02, + "learning_rate": 1.2611940934102831e-05, + "loss": 3.8643, + "step": 2283520 + }, + { + "epoch": 0.02, + "learning_rate": 1.2603554986592311e-05, + "loss": 3.8615, + "step": 2284032 + }, + { + "epoch": 0.02, + "learning_rate": 1.2595169039081791e-05, + "loss": 3.8746, + "step": 2284544 + }, + { + "epoch": 0.02, + "learning_rate": 1.2586783091571271e-05, + "loss": 3.8593, + "step": 2285056 + }, + { + "epoch": 0.02, + "learning_rate": 1.2578397144060753e-05, + "loss": 3.8567, + "step": 2285568 + }, + { + "epoch": 0.02, + "learning_rate": 1.2570011196550233e-05, + "loss": 3.8727, + "step": 2286080 + }, + { + "epoch": 0.02, + "learning_rate": 1.256162524903971e-05, + "loss": 3.8683, + "step": 2286592 + }, + { + "epoch": 0.02, + "learning_rate": 1.2553239301529191e-05, + "loss": 3.8598, + "step": 2287104 + }, + { + "epoch": 0.02, + "learning_rate": 1.2544853354018671e-05, + "loss": 3.8652, + "step": 2287616 + }, + { + "epoch": 0.02, + "learning_rate": 1.2536467406508151e-05, + "loss": 3.8598, + "step": 2288128 + }, + { + "epoch": 0.02, + "learning_rate": 1.2528081458997631e-05, + "loss": 3.8763, + "step": 2288640 + }, + { + "epoch": 0.02, + "learning_rate": 1.2519711890290842e-05, + "loss": 3.8669, + "step": 2289152 + }, + { + "epoch": 0.03, + "eval_loss": 3.9789247512817383, + "eval_runtime": 290.6537, + "eval_samples_per_second": 1312.872, + "eval_steps_per_second": 41.028, + "step": 2289600 + }, + { + "epoch": 0.0, + "learning_rate": 1.2511325942780322e-05, + "loss": 3.8447, + "step": 2289664 + }, + { + "epoch": 0.0, + "learning_rate": 1.2502939995269802e-05, + "loss": 3.8554, + "step": 2290176 + }, + { + "epoch": 0.0, + "learning_rate": 1.2494554047759283e-05, + "loss": 3.862, + "step": 2290688 + }, + { + "epoch": 0.0, + "learning_rate": 1.2486168100248762e-05, + "loss": 3.8751, + "step": 2291200 + }, + { + "epoch": 0.0, + "learning_rate": 1.2477782152738242e-05, + "loss": 3.8696, + "step": 2291712 + }, + { + "epoch": 0.0, + "learning_rate": 1.2469396205227722e-05, + "loss": 3.8641, + "step": 2292224 + }, + { + "epoch": 0.0, + "learning_rate": 1.2461010257717201e-05, + "loss": 3.8615, + "step": 2292736 + }, + { + "epoch": 0.0, + "learning_rate": 1.2452624310206681e-05, + "loss": 3.8636, + "step": 2293248 + }, + { + "epoch": 0.0, + "learning_rate": 1.2444238362696161e-05, + "loss": 3.8544, + "step": 2293760 + }, + { + "epoch": 0.0, + "learning_rate": 1.2435852415185641e-05, + "loss": 3.8643, + "step": 2294272 + }, + { + "epoch": 0.0, + "learning_rate": 1.2427466467675121e-05, + "loss": 3.8649, + "step": 2294784 + }, + { + "epoch": 0.0, + "learning_rate": 1.2419080520164601e-05, + "loss": 3.8782, + "step": 2295296 + }, + { + "epoch": 0.0, + "learning_rate": 1.2410710951457814e-05, + "loss": 3.8755, + "step": 2295808 + }, + { + "epoch": 0.0, + "learning_rate": 1.2402325003947292e-05, + "loss": 3.8419, + "step": 2296320 + }, + { + "epoch": 0.0, + "learning_rate": 1.2393939056436772e-05, + "loss": 3.8661, + "step": 2296832 + }, + { + "epoch": 0.0, + "learning_rate": 1.2385553108926252e-05, + "loss": 3.8535, + "step": 2297344 + }, + { + "epoch": 0.0, + "learning_rate": 1.2377167161415732e-05, + "loss": 3.8652, + "step": 2297856 + }, + { + "epoch": 0.0, + "learning_rate": 1.2368781213905212e-05, + "loss": 3.8615, + "step": 2298368 + }, + { + "epoch": 0.0, + "learning_rate": 1.2360395266394692e-05, + "loss": 3.8654, + "step": 2298880 + }, + { + "epoch": 0.0, + "learning_rate": 1.2352009318884172e-05, + "loss": 3.8583, + "step": 2299392 + }, + { + "epoch": 0.0, + "learning_rate": 1.2343623371373652e-05, + "loss": 3.8786, + "step": 2299904 + }, + { + "epoch": 0.0, + "learning_rate": 1.2335237423863132e-05, + "loss": 3.8631, + "step": 2300416 + }, + { + "epoch": 0.0, + "learning_rate": 1.2326851476352612e-05, + "loss": 3.8658, + "step": 2300928 + }, + { + "epoch": 0.0, + "learning_rate": 1.2318465528842092e-05, + "loss": 3.8603, + "step": 2301440 + }, + { + "epoch": 0.0, + "learning_rate": 1.2310095960135302e-05, + "loss": 3.8755, + "step": 2301952 + }, + { + "epoch": 0.0, + "learning_rate": 1.2301710012624782e-05, + "loss": 3.8612, + "step": 2302464 + }, + { + "epoch": 0.0, + "learning_rate": 1.2293340443917995e-05, + "loss": 3.8582, + "step": 2302976 + }, + { + "epoch": 0.0, + "learning_rate": 1.2284954496407473e-05, + "loss": 3.8597, + "step": 2303488 + }, + { + "epoch": 0.0, + "learning_rate": 1.2276568548896953e-05, + "loss": 3.8642, + "step": 2304000 + }, + { + "epoch": 0.0, + "learning_rate": 1.2268182601386435e-05, + "loss": 3.8575, + "step": 2304512 + }, + { + "epoch": 0.01, + "learning_rate": 1.2259796653875913e-05, + "loss": 3.8601, + "step": 2305024 + }, + { + "epoch": 0.01, + "learning_rate": 1.2251410706365393e-05, + "loss": 3.8596, + "step": 2305536 + }, + { + "epoch": 0.01, + "learning_rate": 1.2243024758854873e-05, + "loss": 3.8695, + "step": 2306048 + }, + { + "epoch": 0.01, + "learning_rate": 1.2234638811344353e-05, + "loss": 3.8686, + "step": 2306560 + }, + { + "epoch": 0.01, + "learning_rate": 1.2226269242637564e-05, + "loss": 3.8668, + "step": 2307072 + }, + { + "epoch": 0.01, + "learning_rate": 1.2217899673930776e-05, + "loss": 3.8712, + "step": 2307584 + }, + { + "epoch": 0.01, + "learning_rate": 1.2209513726420256e-05, + "loss": 3.8659, + "step": 2308096 + }, + { + "epoch": 0.01, + "learning_rate": 1.2201127778909734e-05, + "loss": 3.85, + "step": 2308608 + }, + { + "epoch": 0.01, + "learning_rate": 1.2192741831399216e-05, + "loss": 3.8596, + "step": 2309120 + }, + { + "epoch": 0.01, + "learning_rate": 1.2184355883888696e-05, + "loss": 3.8607, + "step": 2309632 + }, + { + "epoch": 0.01, + "learning_rate": 1.2175986315181907e-05, + "loss": 3.852, + "step": 2310144 + }, + { + "epoch": 0.01, + "learning_rate": 1.2167600367671387e-05, + "loss": 3.8654, + "step": 2310656 + }, + { + "epoch": 0.01, + "learning_rate": 1.2159230798964597e-05, + "loss": 3.8638, + "step": 2311168 + }, + { + "epoch": 0.01, + "learning_rate": 1.2150844851454077e-05, + "loss": 3.8594, + "step": 2311680 + }, + { + "epoch": 0.01, + "learning_rate": 1.2142458903943559e-05, + "loss": 3.8659, + "step": 2312192 + }, + { + "epoch": 0.01, + "learning_rate": 1.2134072956433037e-05, + "loss": 3.8662, + "step": 2312704 + }, + { + "epoch": 0.01, + "learning_rate": 1.2125687008922517e-05, + "loss": 3.8683, + "step": 2313216 + }, + { + "epoch": 0.01, + "learning_rate": 1.2117301061411999e-05, + "loss": 3.8632, + "step": 2313728 + }, + { + "epoch": 0.01, + "learning_rate": 1.2108915113901477e-05, + "loss": 3.8457, + "step": 2314240 + }, + { + "epoch": 0.01, + "learning_rate": 1.2100529166390957e-05, + "loss": 3.8647, + "step": 2314752 + }, + { + "epoch": 0.01, + "learning_rate": 1.209215959768417e-05, + "loss": 3.8643, + "step": 2315264 + }, + { + "epoch": 0.01, + "learning_rate": 1.208377365017365e-05, + "loss": 3.8676, + "step": 2315776 + }, + { + "epoch": 0.01, + "learning_rate": 1.2075387702663128e-05, + "loss": 3.8588, + "step": 2316288 + }, + { + "epoch": 0.01, + "learning_rate": 1.2067001755152608e-05, + "loss": 3.8553, + "step": 2316800 + }, + { + "epoch": 0.01, + "learning_rate": 1.205861580764209e-05, + "loss": 3.853, + "step": 2317312 + }, + { + "epoch": 0.01, + "learning_rate": 1.2050229860131568e-05, + "loss": 3.8537, + "step": 2317824 + }, + { + "epoch": 0.01, + "learning_rate": 1.2041843912621048e-05, + "loss": 3.8637, + "step": 2318336 + }, + { + "epoch": 0.01, + "learning_rate": 1.2033457965110528e-05, + "loss": 3.8433, + "step": 2318848 + }, + { + "epoch": 0.01, + "learning_rate": 1.202508839640374e-05, + "loss": 3.8707, + "step": 2319360 + }, + { + "epoch": 0.01, + "learning_rate": 1.2016702448893218e-05, + "loss": 3.8644, + "step": 2319872 + }, + { + "epoch": 0.01, + "learning_rate": 1.20083165013827e-05, + "loss": 3.8433, + "step": 2320384 + }, + { + "epoch": 0.01, + "learning_rate": 1.199993055387218e-05, + "loss": 3.8743, + "step": 2320896 + }, + { + "epoch": 0.01, + "learning_rate": 1.1991560985165389e-05, + "loss": 3.8483, + "step": 2321408 + }, + { + "epoch": 0.01, + "learning_rate": 1.198317503765487e-05, + "loss": 3.8548, + "step": 2321920 + }, + { + "epoch": 0.01, + "learning_rate": 1.197478909014435e-05, + "loss": 3.8542, + "step": 2322432 + }, + { + "epoch": 0.01, + "learning_rate": 1.1966419521437561e-05, + "loss": 3.8648, + "step": 2322944 + }, + { + "epoch": 0.01, + "learning_rate": 1.1958033573927041e-05, + "loss": 3.85, + "step": 2323456 + }, + { + "epoch": 0.01, + "learning_rate": 1.1949647626416521e-05, + "loss": 3.8662, + "step": 2323968 + }, + { + "epoch": 0.01, + "learning_rate": 1.1941261678906001e-05, + "loss": 3.8403, + "step": 2324480 + }, + { + "epoch": 0.01, + "learning_rate": 1.1932875731395481e-05, + "loss": 3.8524, + "step": 2324992 + }, + { + "epoch": 0.01, + "learning_rate": 1.1924506162688692e-05, + "loss": 3.8676, + "step": 2325504 + }, + { + "epoch": 0.01, + "learning_rate": 1.1916120215178172e-05, + "loss": 3.8584, + "step": 2326016 + }, + { + "epoch": 0.01, + "learning_rate": 1.1907734267667654e-05, + "loss": 3.8652, + "step": 2326528 + }, + { + "epoch": 0.01, + "learning_rate": 1.1899348320157132e-05, + "loss": 3.8639, + "step": 2327040 + }, + { + "epoch": 0.01, + "learning_rate": 1.1890962372646612e-05, + "loss": 3.8763, + "step": 2327552 + }, + { + "epoch": 0.01, + "learning_rate": 1.1882609182743555e-05, + "loss": 3.8541, + "step": 2328064 + }, + { + "epoch": 0.01, + "learning_rate": 1.1874223235233035e-05, + "loss": 3.8698, + "step": 2328576 + }, + { + "epoch": 0.01, + "learning_rate": 1.1865837287722515e-05, + "loss": 3.8563, + "step": 2329088 + }, + { + "epoch": 0.01, + "learning_rate": 1.1857451340211995e-05, + "loss": 3.859, + "step": 2329600 + }, + { + "epoch": 0.01, + "learning_rate": 1.1849065392701475e-05, + "loss": 3.8606, + "step": 2330112 + }, + { + "epoch": 0.01, + "learning_rate": 1.1840679445190953e-05, + "loss": 3.8715, + "step": 2330624 + }, + { + "epoch": 0.01, + "learning_rate": 1.1832293497680435e-05, + "loss": 3.867, + "step": 2331136 + }, + { + "epoch": 0.01, + "learning_rate": 1.1823907550169915e-05, + "loss": 3.8711, + "step": 2331648 + }, + { + "epoch": 0.01, + "learning_rate": 1.1815521602659395e-05, + "loss": 3.8522, + "step": 2332160 + }, + { + "epoch": 0.01, + "learning_rate": 1.1807135655148873e-05, + "loss": 3.8455, + "step": 2332672 + }, + { + "epoch": 0.01, + "learning_rate": 1.1798749707638355e-05, + "loss": 3.8561, + "step": 2333184 + }, + { + "epoch": 0.01, + "learning_rate": 1.1790363760127835e-05, + "loss": 3.8631, + "step": 2333696 + }, + { + "epoch": 0.01, + "learning_rate": 1.1781994191421045e-05, + "loss": 3.8612, + "step": 2334208 + }, + { + "epoch": 0.01, + "learning_rate": 1.1773608243910525e-05, + "loss": 3.8564, + "step": 2334720 + }, + { + "epoch": 0.01, + "learning_rate": 1.1765238675203736e-05, + "loss": 3.8615, + "step": 2335232 + }, + { + "epoch": 0.02, + "learning_rate": 1.1756852727693216e-05, + "loss": 3.8557, + "step": 2335744 + }, + { + "epoch": 0.02, + "learning_rate": 1.1748466780182696e-05, + "loss": 3.8601, + "step": 2336256 + }, + { + "epoch": 0.02, + "learning_rate": 1.1740080832672176e-05, + "loss": 3.8556, + "step": 2336768 + }, + { + "epoch": 0.02, + "learning_rate": 1.1731694885161656e-05, + "loss": 3.8687, + "step": 2337280 + }, + { + "epoch": 0.02, + "learning_rate": 1.1723308937651136e-05, + "loss": 3.8711, + "step": 2337792 + }, + { + "epoch": 0.02, + "learning_rate": 1.1714922990140616e-05, + "loss": 3.8684, + "step": 2338304 + }, + { + "epoch": 0.02, + "learning_rate": 1.1706537042630096e-05, + "loss": 3.8514, + "step": 2338816 + }, + { + "epoch": 0.02, + "learning_rate": 1.1698167473923308e-05, + "loss": 3.8598, + "step": 2339328 + }, + { + "epoch": 0.02, + "learning_rate": 1.1689781526412787e-05, + "loss": 3.8568, + "step": 2339840 + }, + { + "epoch": 0.02, + "learning_rate": 1.1681395578902267e-05, + "loss": 3.866, + "step": 2340352 + }, + { + "epoch": 0.02, + "learning_rate": 1.1673009631391747e-05, + "loss": 3.8668, + "step": 2340864 + }, + { + "epoch": 0.02, + "learning_rate": 1.1664623683881227e-05, + "loss": 3.8537, + "step": 2341376 + }, + { + "epoch": 0.02, + "learning_rate": 1.1656237736370706e-05, + "loss": 3.8634, + "step": 2341888 + }, + { + "epoch": 0.02, + "learning_rate": 1.1647851788860186e-05, + "loss": 3.8613, + "step": 2342400 + }, + { + "epoch": 0.02, + "learning_rate": 1.1639465841349666e-05, + "loss": 3.8632, + "step": 2342912 + }, + { + "epoch": 0.02, + "learning_rate": 1.1631079893839146e-05, + "loss": 3.8552, + "step": 2343424 + }, + { + "epoch": 0.02, + "learning_rate": 1.162272670393609e-05, + "loss": 3.8601, + "step": 2343936 + }, + { + "epoch": 0.02, + "learning_rate": 1.161434075642557e-05, + "loss": 3.8453, + "step": 2344448 + }, + { + "epoch": 0.02, + "learning_rate": 1.1605954808915048e-05, + "loss": 3.8638, + "step": 2344960 + }, + { + "epoch": 0.02, + "learning_rate": 1.159758524020826e-05, + "loss": 3.8512, + "step": 2345472 + }, + { + "epoch": 0.02, + "learning_rate": 1.158919929269774e-05, + "loss": 3.8543, + "step": 2345984 + }, + { + "epoch": 0.02, + "learning_rate": 1.158081334518722e-05, + "loss": 3.8546, + "step": 2346496 + }, + { + "epoch": 0.02, + "learning_rate": 1.15724273976767e-05, + "loss": 3.8585, + "step": 2347008 + }, + { + "epoch": 0.02, + "learning_rate": 1.156404145016618e-05, + "loss": 3.8543, + "step": 2347520 + }, + { + "epoch": 0.02, + "learning_rate": 1.155565550265566e-05, + "loss": 3.8648, + "step": 2348032 + }, + { + "epoch": 0.02, + "learning_rate": 1.1547269555145138e-05, + "loss": 3.8714, + "step": 2348544 + }, + { + "epoch": 0.02, + "learning_rate": 1.153888360763462e-05, + "loss": 3.8699, + "step": 2349056 + }, + { + "epoch": 0.02, + "learning_rate": 1.15304976601241e-05, + "loss": 3.8685, + "step": 2349568 + }, + { + "epoch": 0.02, + "learning_rate": 1.152211171261358e-05, + "loss": 3.8575, + "step": 2350080 + }, + { + "epoch": 0.02, + "learning_rate": 1.1513725765103058e-05, + "loss": 3.862, + "step": 2350592 + }, + { + "epoch": 0.02, + "learning_rate": 1.150533981759254e-05, + "loss": 3.8626, + "step": 2351104 + }, + { + "epoch": 0.02, + "learning_rate": 1.149695387008202e-05, + "loss": 3.8455, + "step": 2351616 + }, + { + "epoch": 0.02, + "learning_rate": 1.1488567922571498e-05, + "loss": 3.8621, + "step": 2352128 + }, + { + "epoch": 0.02, + "learning_rate": 1.1480181975060978e-05, + "loss": 3.8549, + "step": 2352640 + }, + { + "epoch": 0.02, + "learning_rate": 1.147179602755046e-05, + "loss": 3.8694, + "step": 2353152 + }, + { + "epoch": 0.02, + "learning_rate": 1.146342645884367e-05, + "loss": 3.8616, + "step": 2353664 + }, + { + "epoch": 0.02, + "learning_rate": 1.145504051133315e-05, + "loss": 3.8621, + "step": 2354176 + }, + { + "epoch": 0.02, + "learning_rate": 1.144665456382263e-05, + "loss": 3.8558, + "step": 2354688 + }, + { + "epoch": 0.02, + "learning_rate": 1.143826861631211e-05, + "loss": 3.855, + "step": 2355200 + }, + { + "epoch": 0.02, + "learning_rate": 1.1429899047605321e-05, + "loss": 3.8659, + "step": 2355712 + }, + { + "epoch": 0.02, + "learning_rate": 1.1421513100094801e-05, + "loss": 3.8627, + "step": 2356224 + }, + { + "epoch": 0.02, + "learning_rate": 1.1413143531388012e-05, + "loss": 3.8718, + "step": 2356736 + }, + { + "epoch": 0.02, + "learning_rate": 1.1404757583877494e-05, + "loss": 3.858, + "step": 2357248 + }, + { + "epoch": 0.02, + "learning_rate": 1.1396371636366972e-05, + "loss": 3.8677, + "step": 2357760 + }, + { + "epoch": 0.02, + "learning_rate": 1.1388002067660183e-05, + "loss": 3.8643, + "step": 2358272 + }, + { + "epoch": 0.02, + "learning_rate": 1.1379616120149664e-05, + "loss": 3.8667, + "step": 2358784 + }, + { + "epoch": 0.02, + "learning_rate": 1.1371230172639144e-05, + "loss": 3.8663, + "step": 2359296 + }, + { + "epoch": 0.02, + "learning_rate": 1.1362844225128622e-05, + "loss": 3.8568, + "step": 2359808 + }, + { + "epoch": 0.02, + "learning_rate": 1.1354458277618102e-05, + "loss": 3.8645, + "step": 2360320 + }, + { + "epoch": 0.02, + "learning_rate": 1.1346072330107584e-05, + "loss": 3.8709, + "step": 2360832 + }, + { + "epoch": 0.02, + "learning_rate": 1.1337686382597062e-05, + "loss": 3.8579, + "step": 2361344 + }, + { + "epoch": 0.02, + "learning_rate": 1.1329300435086542e-05, + "loss": 3.8542, + "step": 2361856 + }, + { + "epoch": 0.02, + "learning_rate": 1.1320914487576024e-05, + "loss": 3.8624, + "step": 2362368 + }, + { + "epoch": 0.02, + "learning_rate": 1.1312528540065502e-05, + "loss": 3.8632, + "step": 2362880 + }, + { + "epoch": 0.02, + "learning_rate": 1.1304142592554982e-05, + "loss": 3.858, + "step": 2363392 + }, + { + "epoch": 0.02, + "learning_rate": 1.1295756645044462e-05, + "loss": 3.8611, + "step": 2363904 + }, + { + "epoch": 0.02, + "learning_rate": 1.1287387076337675e-05, + "loss": 3.8574, + "step": 2364416 + }, + { + "epoch": 0.02, + "learning_rate": 1.1279001128827153e-05, + "loss": 3.8758, + "step": 2364928 + }, + { + "epoch": 0.02, + "learning_rate": 1.1270631560120365e-05, + "loss": 3.8603, + "step": 2365440 + }, + { + "epoch": 0.03, + "eval_loss": 3.9780802726745605, + "eval_runtime": 302.3751, + "eval_samples_per_second": 1261.979, + "eval_steps_per_second": 39.438, + "step": 2365920 + }, + { + "epoch": 1.0, + "learning_rate": 1.1262245612609845e-05, + "loss": 3.8562, + "step": 2365952 + }, + { + "epoch": 1.0, + "learning_rate": 1.1253859665099325e-05, + "loss": 3.855, + "step": 2366464 + }, + { + "epoch": 1.0, + "learning_rate": 1.1245473717588805e-05, + "loss": 3.8546, + "step": 2366976 + }, + { + "epoch": 1.0, + "learning_rate": 1.1237087770078285e-05, + "loss": 3.8702, + "step": 2367488 + }, + { + "epoch": 1.0, + "learning_rate": 1.1228718201371496e-05, + "loss": 3.8641, + "step": 2368000 + }, + { + "epoch": 1.0, + "learning_rate": 1.1220332253860976e-05, + "loss": 3.8637, + "step": 2368512 + }, + { + "epoch": 1.0, + "learning_rate": 1.1211946306350456e-05, + "loss": 3.8579, + "step": 2369024 + }, + { + "epoch": 1.0, + "learning_rate": 1.1203560358839936e-05, + "loss": 3.8594, + "step": 2369536 + }, + { + "epoch": 1.0, + "learning_rate": 1.1195190790133148e-05, + "loss": 3.8531, + "step": 2370048 + }, + { + "epoch": 1.0, + "learning_rate": 1.1186804842622627e-05, + "loss": 3.8598, + "step": 2370560 + }, + { + "epoch": 1.0, + "learning_rate": 1.1178418895112107e-05, + "loss": 3.8614, + "step": 2371072 + }, + { + "epoch": 1.0, + "learning_rate": 1.1170032947601586e-05, + "loss": 3.8768, + "step": 2371584 + }, + { + "epoch": 1.0, + "learning_rate": 1.1161663378894799e-05, + "loss": 3.8704, + "step": 2372096 + }, + { + "epoch": 1.0, + "learning_rate": 1.1153277431384277e-05, + "loss": 3.8429, + "step": 2372608 + }, + { + "epoch": 1.0, + "learning_rate": 1.1144891483873759e-05, + "loss": 3.8623, + "step": 2373120 + }, + { + "epoch": 1.0, + "learning_rate": 1.1136505536363239e-05, + "loss": 3.8495, + "step": 2373632 + }, + { + "epoch": 1.0, + "learning_rate": 1.1128119588852717e-05, + "loss": 3.8597, + "step": 2374144 + }, + { + "epoch": 1.0, + "learning_rate": 1.1119733641342197e-05, + "loss": 3.8578, + "step": 2374656 + }, + { + "epoch": 1.0, + "learning_rate": 1.1111347693831679e-05, + "loss": 3.861, + "step": 2375168 + }, + { + "epoch": 1.0, + "learning_rate": 1.1102978125124888e-05, + "loss": 3.8529, + "step": 2375680 + }, + { + "epoch": 1.0, + "learning_rate": 1.1094592177614368e-05, + "loss": 3.8757, + "step": 2376192 + }, + { + "epoch": 1.0, + "learning_rate": 1.108620623010385e-05, + "loss": 3.863, + "step": 2376704 + }, + { + "epoch": 1.0, + "learning_rate": 1.107782028259333e-05, + "loss": 3.8576, + "step": 2377216 + }, + { + "epoch": 1.0, + "learning_rate": 1.106945071388654e-05, + "loss": 3.858, + "step": 2377728 + }, + { + "epoch": 1.0, + "learning_rate": 1.106106476637602e-05, + "loss": 3.875, + "step": 2378240 + }, + { + "epoch": 1.0, + "learning_rate": 1.10526788188655e-05, + "loss": 3.8574, + "step": 2378752 + }, + { + "epoch": 1.0, + "learning_rate": 1.1044292871354978e-05, + "loss": 3.8539, + "step": 2379264 + }, + { + "epoch": 1.0, + "learning_rate": 1.103590692384446e-05, + "loss": 3.8603, + "step": 2379776 + }, + { + "epoch": 1.0, + "learning_rate": 1.102753735513767e-05, + "loss": 3.8552, + "step": 2380288 + }, + { + "epoch": 1.0, + "learning_rate": 1.101915140762715e-05, + "loss": 3.8543, + "step": 2380800 + }, + { + "epoch": 1.01, + "learning_rate": 1.1010781838920362e-05, + "loss": 3.8582, + "step": 2381312 + }, + { + "epoch": 1.01, + "learning_rate": 1.1002395891409841e-05, + "loss": 3.8575, + "step": 2381824 + }, + { + "epoch": 1.01, + "learning_rate": 1.0994009943899321e-05, + "loss": 3.8649, + "step": 2382336 + }, + { + "epoch": 1.01, + "learning_rate": 1.0985623996388803e-05, + "loss": 3.8606, + "step": 2382848 + }, + { + "epoch": 1.01, + "learning_rate": 1.0977238048878281e-05, + "loss": 3.8692, + "step": 2383360 + }, + { + "epoch": 1.01, + "learning_rate": 1.0968868480171494e-05, + "loss": 3.864, + "step": 2383872 + }, + { + "epoch": 1.01, + "learning_rate": 1.0960482532660974e-05, + "loss": 3.8637, + "step": 2384384 + }, + { + "epoch": 1.01, + "learning_rate": 1.0952096585150452e-05, + "loss": 3.8478, + "step": 2384896 + }, + { + "epoch": 1.01, + "learning_rate": 1.0943710637639932e-05, + "loss": 3.8589, + "step": 2385408 + }, + { + "epoch": 1.01, + "learning_rate": 1.0935324690129414e-05, + "loss": 3.8555, + "step": 2385920 + }, + { + "epoch": 1.01, + "learning_rate": 1.0926938742618894e-05, + "loss": 3.8517, + "step": 2386432 + }, + { + "epoch": 1.01, + "learning_rate": 1.0918552795108372e-05, + "loss": 3.859, + "step": 2386944 + }, + { + "epoch": 1.01, + "learning_rate": 1.0910166847597852e-05, + "loss": 3.864, + "step": 2387456 + }, + { + "epoch": 1.01, + "learning_rate": 1.0901780900087333e-05, + "loss": 3.8522, + "step": 2387968 + }, + { + "epoch": 1.01, + "learning_rate": 1.0893394952576812e-05, + "loss": 3.8631, + "step": 2388480 + }, + { + "epoch": 1.01, + "learning_rate": 1.0885025383870023e-05, + "loss": 3.8651, + "step": 2388992 + }, + { + "epoch": 1.01, + "learning_rate": 1.0876639436359504e-05, + "loss": 3.865, + "step": 2389504 + }, + { + "epoch": 1.01, + "learning_rate": 1.0868253488848984e-05, + "loss": 3.8587, + "step": 2390016 + }, + { + "epoch": 1.01, + "learning_rate": 1.0859883920142195e-05, + "loss": 3.842, + "step": 2390528 + }, + { + "epoch": 1.01, + "learning_rate": 1.0851497972631675e-05, + "loss": 3.8599, + "step": 2391040 + }, + { + "epoch": 1.01, + "learning_rate": 1.0843112025121155e-05, + "loss": 3.8645, + "step": 2391552 + }, + { + "epoch": 1.01, + "learning_rate": 1.0834726077610633e-05, + "loss": 3.8619, + "step": 2392064 + }, + { + "epoch": 1.01, + "learning_rate": 1.0826340130100115e-05, + "loss": 3.8537, + "step": 2392576 + }, + { + "epoch": 1.01, + "learning_rate": 1.0817954182589595e-05, + "loss": 3.8541, + "step": 2393088 + }, + { + "epoch": 1.01, + "learning_rate": 1.0809584613882805e-05, + "loss": 3.8486, + "step": 2393600 + }, + { + "epoch": 1.01, + "learning_rate": 1.0801198666372285e-05, + "loss": 3.8467, + "step": 2394112 + }, + { + "epoch": 1.01, + "learning_rate": 1.0792812718861765e-05, + "loss": 3.8632, + "step": 2394624 + }, + { + "epoch": 1.01, + "learning_rate": 1.0784426771351245e-05, + "loss": 3.8432, + "step": 2395136 + }, + { + "epoch": 1.01, + "learning_rate": 1.0776040823840725e-05, + "loss": 3.8665, + "step": 2395648 + }, + { + "epoch": 1.01, + "learning_rate": 1.0767654876330205e-05, + "loss": 3.8599, + "step": 2396160 + }, + { + "epoch": 1.01, + "learning_rate": 1.0759268928819685e-05, + "loss": 3.8483, + "step": 2396672 + }, + { + "epoch": 1.01, + "learning_rate": 1.0750882981309165e-05, + "loss": 3.8684, + "step": 2397184 + }, + { + "epoch": 1.01, + "learning_rate": 1.0742497033798645e-05, + "loss": 3.8469, + "step": 2397696 + }, + { + "epoch": 1.01, + "learning_rate": 1.0734111086288125e-05, + "loss": 3.8498, + "step": 2398208 + }, + { + "epoch": 1.01, + "learning_rate": 1.0725725138777605e-05, + "loss": 3.847, + "step": 2398720 + }, + { + "epoch": 1.01, + "learning_rate": 1.0717339191267083e-05, + "loss": 3.864, + "step": 2399232 + }, + { + "epoch": 1.01, + "learning_rate": 1.0708953243756565e-05, + "loss": 3.8447, + "step": 2399744 + }, + { + "epoch": 1.01, + "learning_rate": 1.0700583675049776e-05, + "loss": 3.8599, + "step": 2400256 + }, + { + "epoch": 1.01, + "learning_rate": 1.0692230485146719e-05, + "loss": 3.8382, + "step": 2400768 + }, + { + "epoch": 1.01, + "learning_rate": 1.0683844537636197e-05, + "loss": 3.8487, + "step": 2401280 + }, + { + "epoch": 1.01, + "learning_rate": 1.0675458590125679e-05, + "loss": 3.866, + "step": 2401792 + }, + { + "epoch": 1.01, + "learning_rate": 1.0667072642615159e-05, + "loss": 3.8585, + "step": 2402304 + }, + { + "epoch": 1.01, + "learning_rate": 1.0658686695104639e-05, + "loss": 3.8594, + "step": 2402816 + }, + { + "epoch": 1.01, + "learning_rate": 1.0650300747594117e-05, + "loss": 3.862, + "step": 2403328 + }, + { + "epoch": 1.01, + "learning_rate": 1.0641914800083599e-05, + "loss": 3.8678, + "step": 2403840 + }, + { + "epoch": 1.01, + "learning_rate": 1.0633528852573079e-05, + "loss": 3.8516, + "step": 2404352 + }, + { + "epoch": 1.01, + "learning_rate": 1.0625159283866288e-05, + "loss": 3.8705, + "step": 2404864 + }, + { + "epoch": 1.01, + "learning_rate": 1.061677333635577e-05, + "loss": 3.8493, + "step": 2405376 + }, + { + "epoch": 1.01, + "learning_rate": 1.060838738884525e-05, + "loss": 3.8575, + "step": 2405888 + }, + { + "epoch": 1.01, + "learning_rate": 1.060000144133473e-05, + "loss": 3.856, + "step": 2406400 + }, + { + "epoch": 1.01, + "learning_rate": 1.0591615493824208e-05, + "loss": 3.868, + "step": 2406912 + }, + { + "epoch": 1.01, + "learning_rate": 1.058322954631369e-05, + "loss": 3.8603, + "step": 2407424 + }, + { + "epoch": 1.01, + "learning_rate": 1.057484359880317e-05, + "loss": 3.8705, + "step": 2407936 + }, + { + "epoch": 1.01, + "learning_rate": 1.0566457651292648e-05, + "loss": 3.8532, + "step": 2408448 + }, + { + "epoch": 1.01, + "learning_rate": 1.055808808258586e-05, + "loss": 3.8412, + "step": 2408960 + }, + { + "epoch": 1.01, + "learning_rate": 1.054970213507534e-05, + "loss": 3.8504, + "step": 2409472 + }, + { + "epoch": 1.01, + "learning_rate": 1.054131618756482e-05, + "loss": 3.8588, + "step": 2409984 + }, + { + "epoch": 1.01, + "learning_rate": 1.05329302400543e-05, + "loss": 3.8519, + "step": 2410496 + }, + { + "epoch": 1.01, + "learning_rate": 1.052456067134751e-05, + "loss": 3.8553, + "step": 2411008 + }, + { + "epoch": 1.01, + "learning_rate": 1.051617472383699e-05, + "loss": 3.8594, + "step": 2411520 + }, + { + "epoch": 1.02, + "learning_rate": 1.050778877632647e-05, + "loss": 3.8528, + "step": 2412032 + }, + { + "epoch": 1.02, + "learning_rate": 1.049940282881595e-05, + "loss": 3.8547, + "step": 2412544 + }, + { + "epoch": 1.02, + "learning_rate": 1.049101688130543e-05, + "loss": 3.8516, + "step": 2413056 + }, + { + "epoch": 1.02, + "learning_rate": 1.0482647312598643e-05, + "loss": 3.8663, + "step": 2413568 + }, + { + "epoch": 1.02, + "learning_rate": 1.0474277743891852e-05, + "loss": 3.8672, + "step": 2414080 + }, + { + "epoch": 1.02, + "learning_rate": 1.0465891796381334e-05, + "loss": 3.8629, + "step": 2414592 + }, + { + "epoch": 1.02, + "learning_rate": 1.0457505848870814e-05, + "loss": 3.849, + "step": 2415104 + }, + { + "epoch": 1.02, + "learning_rate": 1.0449119901360292e-05, + "loss": 3.8581, + "step": 2415616 + }, + { + "epoch": 1.02, + "learning_rate": 1.0440733953849772e-05, + "loss": 3.8516, + "step": 2416128 + }, + { + "epoch": 1.02, + "learning_rate": 1.0432348006339254e-05, + "loss": 3.863, + "step": 2416640 + }, + { + "epoch": 1.02, + "learning_rate": 1.0423962058828734e-05, + "loss": 3.8638, + "step": 2417152 + }, + { + "epoch": 1.02, + "learning_rate": 1.0415576111318212e-05, + "loss": 3.8495, + "step": 2417664 + }, + { + "epoch": 1.02, + "learning_rate": 1.0407190163807692e-05, + "loss": 3.8586, + "step": 2418176 + }, + { + "epoch": 1.02, + "learning_rate": 1.0398804216297173e-05, + "loss": 3.8601, + "step": 2418688 + }, + { + "epoch": 1.02, + "learning_rate": 1.0390418268786652e-05, + "loss": 3.8611, + "step": 2419200 + }, + { + "epoch": 1.02, + "learning_rate": 1.0382032321276132e-05, + "loss": 3.8518, + "step": 2419712 + }, + { + "epoch": 1.02, + "learning_rate": 1.0373679131373075e-05, + "loss": 3.8556, + "step": 2420224 + }, + { + "epoch": 1.02, + "learning_rate": 1.0365293183862555e-05, + "loss": 3.8438, + "step": 2420736 + }, + { + "epoch": 1.02, + "learning_rate": 1.0356907236352035e-05, + "loss": 3.8557, + "step": 2421248 + }, + { + "epoch": 1.02, + "learning_rate": 1.0348521288841515e-05, + "loss": 3.8491, + "step": 2421760 + }, + { + "epoch": 1.02, + "learning_rate": 1.0340135341330995e-05, + "loss": 3.8504, + "step": 2422272 + }, + { + "epoch": 1.02, + "learning_rate": 1.0331749393820473e-05, + "loss": 3.8497, + "step": 2422784 + }, + { + "epoch": 1.02, + "learning_rate": 1.0323363446309955e-05, + "loss": 3.8565, + "step": 2423296 + }, + { + "epoch": 1.02, + "learning_rate": 1.0315010256406896e-05, + "loss": 3.853, + "step": 2423808 + }, + { + "epoch": 1.02, + "learning_rate": 1.0306624308896378e-05, + "loss": 3.8563, + "step": 2424320 + }, + { + "epoch": 1.02, + "learning_rate": 1.0298238361385856e-05, + "loss": 3.8707, + "step": 2424832 + }, + { + "epoch": 1.02, + "learning_rate": 1.0289852413875336e-05, + "loss": 3.8682, + "step": 2425344 + }, + { + "epoch": 1.02, + "learning_rate": 1.0281466466364816e-05, + "loss": 3.8628, + "step": 2425856 + }, + { + "epoch": 1.02, + "learning_rate": 1.0273080518854298e-05, + "loss": 3.8531, + "step": 2426368 + }, + { + "epoch": 1.02, + "learning_rate": 1.0264694571343776e-05, + "loss": 3.8576, + "step": 2426880 + }, + { + "epoch": 1.02, + "learning_rate": 1.0256308623833256e-05, + "loss": 3.8579, + "step": 2427392 + }, + { + "epoch": 1.02, + "learning_rate": 1.0247922676322738e-05, + "loss": 3.8449, + "step": 2427904 + }, + { + "epoch": 1.02, + "learning_rate": 1.0239536728812216e-05, + "loss": 3.8562, + "step": 2428416 + }, + { + "epoch": 1.02, + "learning_rate": 1.0231150781301696e-05, + "loss": 3.8535, + "step": 2428928 + }, + { + "epoch": 1.02, + "learning_rate": 1.0222781212594908e-05, + "loss": 3.8634, + "step": 2429440 + }, + { + "epoch": 1.02, + "learning_rate": 1.0214411643888119e-05, + "loss": 3.8564, + "step": 2429952 + }, + { + "epoch": 1.02, + "learning_rate": 1.0206025696377599e-05, + "loss": 3.8613, + "step": 2430464 + }, + { + "epoch": 1.02, + "learning_rate": 1.0197639748867079e-05, + "loss": 3.8545, + "step": 2430976 + }, + { + "epoch": 1.02, + "learning_rate": 1.0189253801356559e-05, + "loss": 3.8513, + "step": 2431488 + }, + { + "epoch": 1.02, + "learning_rate": 1.0180867853846037e-05, + "loss": 3.858, + "step": 2432000 + }, + { + "epoch": 1.02, + "learning_rate": 1.0172481906335519e-05, + "loss": 3.8645, + "step": 2432512 + }, + { + "epoch": 1.02, + "learning_rate": 1.0164095958824999e-05, + "loss": 3.8641, + "step": 2433024 + }, + { + "epoch": 1.02, + "learning_rate": 1.0155710011314479e-05, + "loss": 3.8586, + "step": 2433536 + }, + { + "epoch": 1.02, + "learning_rate": 1.0147324063803957e-05, + "loss": 3.8648, + "step": 2434048 + }, + { + "epoch": 1.02, + "learning_rate": 1.0138938116293439e-05, + "loss": 3.8607, + "step": 2434560 + }, + { + "epoch": 1.02, + "learning_rate": 1.0130552168782919e-05, + "loss": 3.8632, + "step": 2435072 + }, + { + "epoch": 1.02, + "learning_rate": 1.0122166221272397e-05, + "loss": 3.8625, + "step": 2435584 + }, + { + "epoch": 1.02, + "learning_rate": 1.011379665256561e-05, + "loss": 3.8572, + "step": 2436096 + }, + { + "epoch": 1.02, + "learning_rate": 1.010542708385882e-05, + "loss": 3.8609, + "step": 2436608 + }, + { + "epoch": 1.02, + "learning_rate": 1.00970411363483e-05, + "loss": 3.8649, + "step": 2437120 + }, + { + "epoch": 1.02, + "learning_rate": 1.008865518883778e-05, + "loss": 3.8564, + "step": 2437632 + }, + { + "epoch": 1.02, + "learning_rate": 1.008026924132726e-05, + "loss": 3.8516, + "step": 2438144 + }, + { + "epoch": 1.02, + "learning_rate": 1.007188329381674e-05, + "loss": 3.8599, + "step": 2438656 + }, + { + "epoch": 1.02, + "learning_rate": 1.006349734630622e-05, + "loss": 3.8612, + "step": 2439168 + }, + { + "epoch": 1.02, + "learning_rate": 1.00551113987957e-05, + "loss": 3.851, + "step": 2439680 + }, + { + "epoch": 1.02, + "learning_rate": 1.004672545128518e-05, + "loss": 3.8642, + "step": 2440192 + }, + { + "epoch": 1.02, + "learning_rate": 1.0038355882578392e-05, + "loss": 3.8531, + "step": 2440704 + }, + { + "epoch": 1.02, + "learning_rate": 1.0029986313871601e-05, + "loss": 3.8695, + "step": 2441216 + }, + { + "epoch": 1.02, + "learning_rate": 1.0021600366361081e-05, + "loss": 3.8581, + "step": 2441728 + }, + { + "epoch": 1.03, + "learning_rate": 1.0013214418850563e-05, + "loss": 3.8562, + "step": 2442240 + }, + { + "epoch": 1.03, + "eval_loss": 3.9771416187286377, + "eval_runtime": 304.7193, + "eval_samples_per_second": 1252.271, + "eval_steps_per_second": 39.134, + "step": 2442240 + }, + { + "epoch": 0.0, + "learning_rate": 1.0004828471340043e-05, + "loss": 3.8493, + "step": 2442752 + }, + { + "epoch": 0.0, + "learning_rate": 9.996442523829521e-06, + "loss": 3.8499, + "step": 2443264 + }, + { + "epoch": 0.0, + "learning_rate": 9.988056576319001e-06, + "loss": 3.8647, + "step": 2443776 + }, + { + "epoch": 0.0, + "learning_rate": 9.979670628808483e-06, + "loss": 3.8647, + "step": 2444288 + }, + { + "epoch": 0.0, + "learning_rate": 9.971284681297961e-06, + "loss": 3.8614, + "step": 2444800 + }, + { + "epoch": 0.0, + "learning_rate": 9.962898733787441e-06, + "loss": 3.8565, + "step": 2445312 + }, + { + "epoch": 0.0, + "learning_rate": 9.954512786276921e-06, + "loss": 3.854, + "step": 2445824 + }, + { + "epoch": 0.0, + "learning_rate": 9.946126838766401e-06, + "loss": 3.8429, + "step": 2446336 + }, + { + "epoch": 0.0, + "learning_rate": 9.937740891255881e-06, + "loss": 3.8604, + "step": 2446848 + }, + { + "epoch": 0.0, + "learning_rate": 9.929354943745361e-06, + "loss": 3.8518, + "step": 2447360 + }, + { + "epoch": 0.0, + "learning_rate": 9.920968996234841e-06, + "loss": 3.8756, + "step": 2447872 + }, + { + "epoch": 0.0, + "learning_rate": 9.912599427528052e-06, + "loss": 3.8677, + "step": 2448384 + }, + { + "epoch": 0.0, + "learning_rate": 9.904213480017532e-06, + "loss": 3.8405, + "step": 2448896 + }, + { + "epoch": 0.0, + "learning_rate": 9.895827532507013e-06, + "loss": 3.8531, + "step": 2449408 + }, + { + "epoch": 0.0, + "learning_rate": 9.887441584996492e-06, + "loss": 3.8501, + "step": 2449920 + }, + { + "epoch": 0.0, + "learning_rate": 9.879055637485971e-06, + "loss": 3.853, + "step": 2450432 + }, + { + "epoch": 0.0, + "learning_rate": 9.870669689975451e-06, + "loss": 3.8591, + "step": 2450944 + }, + { + "epoch": 0.0, + "learning_rate": 9.862283742464931e-06, + "loss": 3.8574, + "step": 2451456 + }, + { + "epoch": 0.0, + "learning_rate": 9.853897794954411e-06, + "loss": 3.8481, + "step": 2451968 + }, + { + "epoch": 0.0, + "learning_rate": 9.845511847443891e-06, + "loss": 3.873, + "step": 2452480 + }, + { + "epoch": 0.0, + "learning_rate": 9.837125899933371e-06, + "loss": 3.8547, + "step": 2452992 + }, + { + "epoch": 0.0, + "learning_rate": 9.828739952422851e-06, + "loss": 3.8577, + "step": 2453504 + }, + { + "epoch": 0.0, + "learning_rate": 9.820354004912331e-06, + "loss": 3.8554, + "step": 2454016 + }, + { + "epoch": 0.0, + "learning_rate": 9.811984436205544e-06, + "loss": 3.8709, + "step": 2454528 + }, + { + "epoch": 0.0, + "learning_rate": 9.803598488695022e-06, + "loss": 3.8544, + "step": 2455040 + }, + { + "epoch": 0.0, + "learning_rate": 9.795212541184502e-06, + "loss": 3.851, + "step": 2455552 + }, + { + "epoch": 0.0, + "learning_rate": 9.786842972477714e-06, + "loss": 3.8556, + "step": 2456064 + }, + { + "epoch": 0.0, + "learning_rate": 9.778457024967194e-06, + "loss": 3.8543, + "step": 2456576 + }, + { + "epoch": 0.0, + "learning_rate": 9.770071077456673e-06, + "loss": 3.8521, + "step": 2457088 + }, + { + "epoch": 0.01, + "learning_rate": 9.761685129946154e-06, + "loss": 3.8539, + "step": 2457600 + }, + { + "epoch": 0.01, + "learning_rate": 9.753315561239365e-06, + "loss": 3.8564, + "step": 2458112 + }, + { + "epoch": 0.01, + "learning_rate": 9.744929613728845e-06, + "loss": 3.8596, + "step": 2458624 + }, + { + "epoch": 0.01, + "learning_rate": 9.736543666218325e-06, + "loss": 3.8574, + "step": 2459136 + }, + { + "epoch": 0.01, + "learning_rate": 9.728157718707805e-06, + "loss": 3.8622, + "step": 2459648 + }, + { + "epoch": 0.01, + "learning_rate": 9.719788150001016e-06, + "loss": 3.8628, + "step": 2460160 + }, + { + "epoch": 0.01, + "learning_rate": 9.711402202490496e-06, + "loss": 3.8623, + "step": 2460672 + }, + { + "epoch": 0.01, + "learning_rate": 9.703016254979976e-06, + "loss": 3.8457, + "step": 2461184 + }, + { + "epoch": 0.01, + "learning_rate": 9.694630307469456e-06, + "loss": 3.8545, + "step": 2461696 + }, + { + "epoch": 0.01, + "learning_rate": 9.686244359958936e-06, + "loss": 3.8491, + "step": 2462208 + }, + { + "epoch": 0.01, + "learning_rate": 9.677858412448415e-06, + "loss": 3.8521, + "step": 2462720 + }, + { + "epoch": 0.01, + "learning_rate": 9.669472464937895e-06, + "loss": 3.8526, + "step": 2463232 + }, + { + "epoch": 0.01, + "learning_rate": 9.661086517427375e-06, + "loss": 3.8588, + "step": 2463744 + }, + { + "epoch": 0.01, + "learning_rate": 9.652700569916855e-06, + "loss": 3.8502, + "step": 2464256 + }, + { + "epoch": 0.01, + "learning_rate": 9.644314622406335e-06, + "loss": 3.8614, + "step": 2464768 + }, + { + "epoch": 0.01, + "learning_rate": 9.635928674895815e-06, + "loss": 3.8589, + "step": 2465280 + }, + { + "epoch": 0.01, + "learning_rate": 9.627542727385294e-06, + "loss": 3.8637, + "step": 2465792 + }, + { + "epoch": 0.01, + "learning_rate": 9.619156779874775e-06, + "loss": 3.857, + "step": 2466304 + }, + { + "epoch": 0.01, + "learning_rate": 9.610787211167986e-06, + "loss": 3.84, + "step": 2466816 + }, + { + "epoch": 0.01, + "learning_rate": 9.602401263657466e-06, + "loss": 3.8481, + "step": 2467328 + }, + { + "epoch": 0.01, + "learning_rate": 9.594015316146946e-06, + "loss": 3.8681, + "step": 2467840 + }, + { + "epoch": 0.01, + "learning_rate": 9.585629368636426e-06, + "loss": 3.8537, + "step": 2468352 + }, + { + "epoch": 0.01, + "learning_rate": 9.577243421125906e-06, + "loss": 3.8489, + "step": 2468864 + }, + { + "epoch": 0.01, + "learning_rate": 9.568857473615386e-06, + "loss": 3.8472, + "step": 2469376 + }, + { + "epoch": 0.01, + "learning_rate": 9.560471526104866e-06, + "loss": 3.8524, + "step": 2469888 + }, + { + "epoch": 0.01, + "learning_rate": 9.552085578594346e-06, + "loss": 3.8416, + "step": 2470400 + }, + { + "epoch": 0.01, + "learning_rate": 9.543716009887556e-06, + "loss": 3.8637, + "step": 2470912 + }, + { + "epoch": 0.01, + "learning_rate": 9.535330062377036e-06, + "loss": 3.8404, + "step": 2471424 + }, + { + "epoch": 0.01, + "learning_rate": 9.526960493670247e-06, + "loss": 3.8583, + "step": 2471936 + }, + { + "epoch": 0.01, + "learning_rate": 9.518574546159729e-06, + "loss": 3.8564, + "step": 2472448 + }, + { + "epoch": 0.01, + "learning_rate": 9.510188598649209e-06, + "loss": 3.8424, + "step": 2472960 + }, + { + "epoch": 0.01, + "learning_rate": 9.501802651138687e-06, + "loss": 3.8628, + "step": 2473472 + }, + { + "epoch": 0.01, + "learning_rate": 9.493416703628167e-06, + "loss": 3.8438, + "step": 2473984 + }, + { + "epoch": 0.01, + "learning_rate": 9.485030756117649e-06, + "loss": 3.8512, + "step": 2474496 + }, + { + "epoch": 0.01, + "learning_rate": 9.476644808607127e-06, + "loss": 3.8417, + "step": 2475008 + }, + { + "epoch": 0.01, + "learning_rate": 9.46827523990034e-06, + "loss": 3.8654, + "step": 2475520 + }, + { + "epoch": 0.01, + "learning_rate": 9.45988929238982e-06, + "loss": 3.8474, + "step": 2476032 + }, + { + "epoch": 0.01, + "learning_rate": 9.4515033448793e-06, + "loss": 3.8502, + "step": 2476544 + }, + { + "epoch": 0.01, + "learning_rate": 9.443117397368778e-06, + "loss": 3.8402, + "step": 2477056 + }, + { + "epoch": 0.01, + "learning_rate": 9.43473144985826e-06, + "loss": 3.8444, + "step": 2477568 + }, + { + "epoch": 0.01, + "learning_rate": 9.42634550234774e-06, + "loss": 3.8588, + "step": 2478080 + }, + { + "epoch": 0.01, + "learning_rate": 9.417959554837217e-06, + "loss": 3.8619, + "step": 2478592 + }, + { + "epoch": 0.01, + "learning_rate": 9.409573607326697e-06, + "loss": 3.854, + "step": 2479104 + }, + { + "epoch": 0.01, + "learning_rate": 9.40120403861991e-06, + "loss": 3.8573, + "step": 2479616 + }, + { + "epoch": 0.01, + "learning_rate": 9.39281809110939e-06, + "loss": 3.8645, + "step": 2480128 + }, + { + "epoch": 0.01, + "learning_rate": 9.384432143598868e-06, + "loss": 3.8494, + "step": 2480640 + }, + { + "epoch": 0.01, + "learning_rate": 9.37606257489208e-06, + "loss": 3.8674, + "step": 2481152 + }, + { + "epoch": 0.01, + "learning_rate": 9.36767662738156e-06, + "loss": 3.8489, + "step": 2481664 + }, + { + "epoch": 0.01, + "learning_rate": 9.35929067987104e-06, + "loss": 3.8521, + "step": 2482176 + }, + { + "epoch": 0.01, + "learning_rate": 9.35090473236052e-06, + "loss": 3.8546, + "step": 2482688 + }, + { + "epoch": 0.01, + "learning_rate": 9.34251878485e-06, + "loss": 3.8638, + "step": 2483200 + }, + { + "epoch": 0.01, + "learning_rate": 9.334132837339479e-06, + "loss": 3.8577, + "step": 2483712 + }, + { + "epoch": 0.01, + "learning_rate": 9.32574688982896e-06, + "loss": 3.8676, + "step": 2484224 + }, + { + "epoch": 0.01, + "learning_rate": 9.31736094231844e-06, + "loss": 3.854, + "step": 2484736 + }, + { + "epoch": 0.01, + "learning_rate": 9.30897499480792e-06, + "loss": 3.8353, + "step": 2485248 + }, + { + "epoch": 0.01, + "learning_rate": 9.300605426101131e-06, + "loss": 3.8463, + "step": 2485760 + }, + { + "epoch": 0.01, + "learning_rate": 9.292219478590611e-06, + "loss": 3.8543, + "step": 2486272 + }, + { + "epoch": 0.01, + "learning_rate": 9.283833531080091e-06, + "loss": 3.8487, + "step": 2486784 + }, + { + "epoch": 0.01, + "learning_rate": 9.275463962373303e-06, + "loss": 3.8527, + "step": 2487296 + }, + { + "epoch": 0.01, + "learning_rate": 9.267078014862782e-06, + "loss": 3.8578, + "step": 2487808 + }, + { + "epoch": 0.02, + "learning_rate": 9.258692067352262e-06, + "loss": 3.8471, + "step": 2488320 + }, + { + "epoch": 0.02, + "learning_rate": 9.250306119841742e-06, + "loss": 3.8538, + "step": 2488832 + }, + { + "epoch": 0.02, + "learning_rate": 9.241920172331222e-06, + "loss": 3.851, + "step": 2489344 + }, + { + "epoch": 0.02, + "learning_rate": 9.233534224820701e-06, + "loss": 3.8614, + "step": 2489856 + }, + { + "epoch": 0.02, + "learning_rate": 9.225164656113914e-06, + "loss": 3.8636, + "step": 2490368 + }, + { + "epoch": 0.02, + "learning_rate": 9.216778708603394e-06, + "loss": 3.8633, + "step": 2490880 + }, + { + "epoch": 0.02, + "learning_rate": 9.208392761092872e-06, + "loss": 3.8428, + "step": 2491392 + }, + { + "epoch": 0.02, + "learning_rate": 9.200006813582352e-06, + "loss": 3.853, + "step": 2491904 + }, + { + "epoch": 0.02, + "learning_rate": 9.191620866071834e-06, + "loss": 3.8514, + "step": 2492416 + }, + { + "epoch": 0.02, + "learning_rate": 9.183234918561312e-06, + "loss": 3.8581, + "step": 2492928 + }, + { + "epoch": 0.02, + "learning_rate": 9.174848971050792e-06, + "loss": 3.8625, + "step": 2493440 + }, + { + "epoch": 0.02, + "learning_rate": 9.166463023540272e-06, + "loss": 3.8457, + "step": 2493952 + }, + { + "epoch": 0.02, + "learning_rate": 9.158077076029752e-06, + "loss": 3.8525, + "step": 2494464 + }, + { + "epoch": 0.02, + "learning_rate": 9.149691128519232e-06, + "loss": 3.8591, + "step": 2494976 + }, + { + "epoch": 0.02, + "learning_rate": 9.141305181008712e-06, + "loss": 3.8584, + "step": 2495488 + }, + { + "epoch": 0.02, + "learning_rate": 9.132919233498192e-06, + "loss": 3.8488, + "step": 2496000 + }, + { + "epoch": 0.02, + "learning_rate": 9.124549664791403e-06, + "loss": 3.8538, + "step": 2496512 + }, + { + "epoch": 0.02, + "learning_rate": 9.116163717280883e-06, + "loss": 3.8457, + "step": 2497024 + }, + { + "epoch": 0.02, + "learning_rate": 9.107777769770364e-06, + "loss": 3.8483, + "step": 2497536 + }, + { + "epoch": 0.02, + "learning_rate": 9.099391822259842e-06, + "loss": 3.8484, + "step": 2498048 + }, + { + "epoch": 0.02, + "learning_rate": 9.091005874749322e-06, + "loss": 3.8492, + "step": 2498560 + }, + { + "epoch": 0.02, + "learning_rate": 9.082619927238802e-06, + "loss": 3.8477, + "step": 2499072 + }, + { + "epoch": 0.02, + "learning_rate": 9.074250358532015e-06, + "loss": 3.8535, + "step": 2499584 + }, + { + "epoch": 0.02, + "learning_rate": 9.065864411021493e-06, + "loss": 3.8479, + "step": 2500096 + }, + { + "epoch": 0.02, + "learning_rate": 9.057478463510973e-06, + "loss": 3.8533, + "step": 2500608 + }, + { + "epoch": 0.02, + "learning_rate": 9.049092516000455e-06, + "loss": 3.8672, + "step": 2501120 + }, + { + "epoch": 0.02, + "learning_rate": 9.040706568489933e-06, + "loss": 3.8656, + "step": 2501632 + }, + { + "epoch": 0.02, + "learning_rate": 9.032320620979413e-06, + "loss": 3.8579, + "step": 2502144 + }, + { + "epoch": 0.02, + "learning_rate": 9.023934673468893e-06, + "loss": 3.8548, + "step": 2502656 + }, + { + "epoch": 0.02, + "learning_rate": 9.015565104762105e-06, + "loss": 3.8541, + "step": 2503168 + }, + { + "epoch": 0.02, + "learning_rate": 9.007179157251584e-06, + "loss": 3.8544, + "step": 2503680 + }, + { + "epoch": 0.02, + "learning_rate": 8.998793209741065e-06, + "loss": 3.8457, + "step": 2504192 + }, + { + "epoch": 0.02, + "learning_rate": 8.990407262230545e-06, + "loss": 3.8491, + "step": 2504704 + }, + { + "epoch": 0.02, + "learning_rate": 8.982021314720023e-06, + "loss": 3.8526, + "step": 2505216 + }, + { + "epoch": 0.02, + "learning_rate": 8.973635367209503e-06, + "loss": 3.8582, + "step": 2505728 + }, + { + "epoch": 0.02, + "learning_rate": 8.965249419698985e-06, + "loss": 3.8533, + "step": 2506240 + }, + { + "epoch": 0.02, + "learning_rate": 8.956879850992196e-06, + "loss": 3.8588, + "step": 2506752 + }, + { + "epoch": 0.02, + "learning_rate": 8.948493903481676e-06, + "loss": 3.8534, + "step": 2507264 + }, + { + "epoch": 0.02, + "learning_rate": 8.940107955971156e-06, + "loss": 3.8524, + "step": 2507776 + }, + { + "epoch": 0.02, + "learning_rate": 8.931722008460636e-06, + "loss": 3.8487, + "step": 2508288 + }, + { + "epoch": 0.02, + "learning_rate": 8.923336060950114e-06, + "loss": 3.8651, + "step": 2508800 + }, + { + "epoch": 0.02, + "learning_rate": 8.914950113439596e-06, + "loss": 3.8614, + "step": 2509312 + }, + { + "epoch": 0.02, + "learning_rate": 8.906564165929076e-06, + "loss": 3.8539, + "step": 2509824 + }, + { + "epoch": 0.02, + "learning_rate": 8.898194597222286e-06, + "loss": 3.8582, + "step": 2510336 + }, + { + "epoch": 0.02, + "learning_rate": 8.889808649711766e-06, + "loss": 3.8617, + "step": 2510848 + }, + { + "epoch": 0.02, + "learning_rate": 8.881422702201246e-06, + "loss": 3.8594, + "step": 2511360 + }, + { + "epoch": 0.02, + "learning_rate": 8.873036754690726e-06, + "loss": 3.8625, + "step": 2511872 + }, + { + "epoch": 0.02, + "learning_rate": 8.864667185983939e-06, + "loss": 3.8539, + "step": 2512384 + }, + { + "epoch": 0.02, + "learning_rate": 8.856281238473417e-06, + "loss": 3.858, + "step": 2512896 + }, + { + "epoch": 0.02, + "learning_rate": 8.847895290962897e-06, + "loss": 3.8571, + "step": 2513408 + }, + { + "epoch": 0.02, + "learning_rate": 8.839509343452377e-06, + "loss": 3.8529, + "step": 2513920 + }, + { + "epoch": 0.02, + "learning_rate": 8.831123395941857e-06, + "loss": 3.8523, + "step": 2514432 + }, + { + "epoch": 0.02, + "learning_rate": 8.822737448431337e-06, + "loss": 3.8517, + "step": 2514944 + }, + { + "epoch": 0.02, + "learning_rate": 8.814351500920817e-06, + "loss": 3.8598, + "step": 2515456 + }, + { + "epoch": 0.02, + "learning_rate": 8.805965553410297e-06, + "loss": 3.8476, + "step": 2515968 + }, + { + "epoch": 0.02, + "learning_rate": 8.797612363507238e-06, + "loss": 3.8621, + "step": 2516480 + }, + { + "epoch": 0.02, + "learning_rate": 8.78922641599672e-06, + "loss": 3.856, + "step": 2516992 + }, + { + "epoch": 0.02, + "learning_rate": 8.7808404684862e-06, + "loss": 3.861, + "step": 2517504 + }, + { + "epoch": 0.02, + "learning_rate": 8.772454520975678e-06, + "loss": 3.8608, + "step": 2518016 + }, + { + "epoch": 0.02, + "learning_rate": 8.76408495226889e-06, + "loss": 3.8473, + "step": 2518528 + }, + { + "epoch": 0.03, + "eval_loss": 3.9762721061706543, + "eval_runtime": 290.1675, + "eval_samples_per_second": 1315.072, + "eval_steps_per_second": 41.097, + "step": 2518560 + }, + { + "epoch": 1.0, + "learning_rate": 8.75569900475837e-06, + "loss": 3.8465, + "step": 2519040 + }, + { + "epoch": 1.0, + "learning_rate": 8.74731305724785e-06, + "loss": 3.8485, + "step": 2519552 + }, + { + "epoch": 1.0, + "learning_rate": 8.73892710973733e-06, + "loss": 3.866, + "step": 2520064 + }, + { + "epoch": 1.0, + "learning_rate": 8.73054116222681e-06, + "loss": 3.8557, + "step": 2520576 + }, + { + "epoch": 1.0, + "learning_rate": 8.72215521471629e-06, + "loss": 3.8597, + "step": 2521088 + }, + { + "epoch": 1.0, + "learning_rate": 8.713785646009501e-06, + "loss": 3.8539, + "step": 2521600 + }, + { + "epoch": 1.0, + "learning_rate": 8.705399698498981e-06, + "loss": 3.8478, + "step": 2522112 + }, + { + "epoch": 1.0, + "learning_rate": 8.697013750988461e-06, + "loss": 3.845, + "step": 2522624 + }, + { + "epoch": 1.0, + "learning_rate": 8.688627803477941e-06, + "loss": 3.8557, + "step": 2523136 + }, + { + "epoch": 1.0, + "learning_rate": 8.680241855967421e-06, + "loss": 3.8505, + "step": 2523648 + }, + { + "epoch": 1.0, + "learning_rate": 8.671855908456901e-06, + "loss": 3.8718, + "step": 2524160 + }, + { + "epoch": 1.0, + "learning_rate": 8.663486339750112e-06, + "loss": 3.8604, + "step": 2524672 + }, + { + "epoch": 1.0, + "learning_rate": 8.655116771043324e-06, + "loss": 3.8437, + "step": 2525184 + }, + { + "epoch": 1.0, + "learning_rate": 8.646730823532803e-06, + "loss": 3.8483, + "step": 2525696 + }, + { + "epoch": 1.0, + "learning_rate": 8.638344876022284e-06, + "loss": 3.8521, + "step": 2526208 + }, + { + "epoch": 1.0, + "learning_rate": 8.629958928511764e-06, + "loss": 3.8434, + "step": 2526720 + }, + { + "epoch": 1.0, + "learning_rate": 8.621572981001242e-06, + "loss": 3.8567, + "step": 2527232 + }, + { + "epoch": 1.0, + "learning_rate": 8.613187033490722e-06, + "loss": 3.8553, + "step": 2527744 + }, + { + "epoch": 1.0, + "learning_rate": 8.604817464783935e-06, + "loss": 3.8449, + "step": 2528256 + }, + { + "epoch": 1.0, + "learning_rate": 8.596431517273415e-06, + "loss": 3.872, + "step": 2528768 + }, + { + "epoch": 1.0, + "learning_rate": 8.588045569762893e-06, + "loss": 3.8518, + "step": 2529280 + }, + { + "epoch": 1.0, + "learning_rate": 8.579659622252375e-06, + "loss": 3.8579, + "step": 2529792 + }, + { + "epoch": 1.0, + "learning_rate": 8.571273674741855e-06, + "loss": 3.8516, + "step": 2530304 + }, + { + "epoch": 1.0, + "learning_rate": 8.562887727231333e-06, + "loss": 3.869, + "step": 2530816 + }, + { + "epoch": 1.0, + "learning_rate": 8.554501779720813e-06, + "loss": 3.8489, + "step": 2531328 + }, + { + "epoch": 1.0, + "learning_rate": 8.546115832210295e-06, + "loss": 3.8512, + "step": 2531840 + }, + { + "epoch": 1.0, + "learning_rate": 8.537729884699773e-06, + "loss": 3.8474, + "step": 2532352 + }, + { + "epoch": 1.0, + "learning_rate": 8.529343937189253e-06, + "loss": 3.8514, + "step": 2532864 + }, + { + "epoch": 1.0, + "learning_rate": 8.520990747286196e-06, + "loss": 3.8487, + "step": 2533376 + }, + { + "epoch": 1.01, + "learning_rate": 8.512604799775676e-06, + "loss": 3.8523, + "step": 2533888 + }, + { + "epoch": 1.01, + "learning_rate": 8.504218852265156e-06, + "loss": 3.8553, + "step": 2534400 + }, + { + "epoch": 1.01, + "learning_rate": 8.495832904754636e-06, + "loss": 3.856, + "step": 2534912 + }, + { + "epoch": 1.01, + "learning_rate": 8.487446957244116e-06, + "loss": 3.8559, + "step": 2535424 + }, + { + "epoch": 1.01, + "learning_rate": 8.479061009733596e-06, + "loss": 3.8617, + "step": 2535936 + }, + { + "epoch": 1.01, + "learning_rate": 8.470691441026807e-06, + "loss": 3.8582, + "step": 2536448 + }, + { + "epoch": 1.01, + "learning_rate": 8.462305493516287e-06, + "loss": 3.8573, + "step": 2536960 + }, + { + "epoch": 1.01, + "learning_rate": 8.453919546005767e-06, + "loss": 3.8457, + "step": 2537472 + }, + { + "epoch": 1.01, + "learning_rate": 8.445533598495247e-06, + "loss": 3.8535, + "step": 2537984 + }, + { + "epoch": 1.01, + "learning_rate": 8.437147650984727e-06, + "loss": 3.845, + "step": 2538496 + }, + { + "epoch": 1.01, + "learning_rate": 8.428761703474207e-06, + "loss": 3.8521, + "step": 2539008 + }, + { + "epoch": 1.01, + "learning_rate": 8.420375755963686e-06, + "loss": 3.8508, + "step": 2539520 + }, + { + "epoch": 1.01, + "learning_rate": 8.411989808453166e-06, + "loss": 3.8583, + "step": 2540032 + }, + { + "epoch": 1.01, + "learning_rate": 8.403603860942646e-06, + "loss": 3.8433, + "step": 2540544 + }, + { + "epoch": 1.01, + "learning_rate": 8.395234292235859e-06, + "loss": 3.8615, + "step": 2541056 + }, + { + "epoch": 1.01, + "learning_rate": 8.386848344725337e-06, + "loss": 3.8561, + "step": 2541568 + }, + { + "epoch": 1.01, + "learning_rate": 8.378462397214817e-06, + "loss": 3.8578, + "step": 2542080 + }, + { + "epoch": 1.01, + "learning_rate": 8.370076449704297e-06, + "loss": 3.8529, + "step": 2542592 + }, + { + "epoch": 1.01, + "learning_rate": 8.361690502193779e-06, + "loss": 3.8393, + "step": 2543104 + }, + { + "epoch": 1.01, + "learning_rate": 8.353304554683257e-06, + "loss": 3.8465, + "step": 2543616 + }, + { + "epoch": 1.01, + "learning_rate": 8.34493498597647e-06, + "loss": 3.8629, + "step": 2544128 + }, + { + "epoch": 1.01, + "learning_rate": 8.33654903846595e-06, + "loss": 3.8519, + "step": 2544640 + }, + { + "epoch": 1.01, + "learning_rate": 8.328163090955428e-06, + "loss": 3.8482, + "step": 2545152 + }, + { + "epoch": 1.01, + "learning_rate": 8.319777143444908e-06, + "loss": 3.8424, + "step": 2545664 + }, + { + "epoch": 1.01, + "learning_rate": 8.31140757473812e-06, + "loss": 3.8521, + "step": 2546176 + }, + { + "epoch": 1.01, + "learning_rate": 8.3030216272276e-06, + "loss": 3.8333, + "step": 2546688 + }, + { + "epoch": 1.01, + "learning_rate": 8.294635679717078e-06, + "loss": 3.8616, + "step": 2547200 + }, + { + "epoch": 1.01, + "learning_rate": 8.28624973220656e-06, + "loss": 3.8352, + "step": 2547712 + }, + { + "epoch": 1.01, + "learning_rate": 8.27786378469604e-06, + "loss": 3.8567, + "step": 2548224 + }, + { + "epoch": 1.01, + "learning_rate": 8.269477837185518e-06, + "loss": 3.8521, + "step": 2548736 + }, + { + "epoch": 1.01, + "learning_rate": 8.261091889674998e-06, + "loss": 3.8449, + "step": 2549248 + }, + { + "epoch": 1.01, + "learning_rate": 8.25270594216448e-06, + "loss": 3.8545, + "step": 2549760 + }, + { + "epoch": 1.01, + "learning_rate": 8.24433637345769e-06, + "loss": 3.8465, + "step": 2550272 + }, + { + "epoch": 1.01, + "learning_rate": 8.235966804750901e-06, + "loss": 3.8473, + "step": 2550784 + }, + { + "epoch": 1.01, + "learning_rate": 8.227597236044112e-06, + "loss": 3.8367, + "step": 2551296 + }, + { + "epoch": 1.01, + "learning_rate": 8.219211288533594e-06, + "loss": 3.8642, + "step": 2551808 + }, + { + "epoch": 1.01, + "learning_rate": 8.210825341023074e-06, + "loss": 3.8403, + "step": 2552320 + }, + { + "epoch": 1.01, + "learning_rate": 8.202439393512552e-06, + "loss": 3.8493, + "step": 2552832 + }, + { + "epoch": 1.01, + "learning_rate": 8.194053446002032e-06, + "loss": 3.8332, + "step": 2553344 + }, + { + "epoch": 1.01, + "learning_rate": 8.185667498491514e-06, + "loss": 3.8439, + "step": 2553856 + }, + { + "epoch": 1.01, + "learning_rate": 8.177281550980992e-06, + "loss": 3.8543, + "step": 2554368 + }, + { + "epoch": 1.01, + "learning_rate": 8.168895603470472e-06, + "loss": 3.8562, + "step": 2554880 + }, + { + "epoch": 1.01, + "learning_rate": 8.160509655959952e-06, + "loss": 3.8508, + "step": 2555392 + }, + { + "epoch": 1.01, + "learning_rate": 8.152123708449432e-06, + "loss": 3.8582, + "step": 2555904 + }, + { + "epoch": 1.01, + "learning_rate": 8.143737760938912e-06, + "loss": 3.8595, + "step": 2556416 + }, + { + "epoch": 1.01, + "learning_rate": 8.135351813428392e-06, + "loss": 3.8507, + "step": 2556928 + }, + { + "epoch": 1.01, + "learning_rate": 8.126982244721604e-06, + "loss": 3.86, + "step": 2557440 + }, + { + "epoch": 1.01, + "learning_rate": 8.118596297211082e-06, + "loss": 3.8479, + "step": 2557952 + }, + { + "epoch": 1.01, + "learning_rate": 8.110210349700562e-06, + "loss": 3.8529, + "step": 2558464 + }, + { + "epoch": 1.01, + "learning_rate": 8.101824402190044e-06, + "loss": 3.8476, + "step": 2558976 + }, + { + "epoch": 1.01, + "learning_rate": 8.093438454679522e-06, + "loss": 3.8576, + "step": 2559488 + }, + { + "epoch": 1.01, + "learning_rate": 8.085052507169002e-06, + "loss": 3.8567, + "step": 2560000 + }, + { + "epoch": 1.01, + "learning_rate": 8.076666559658482e-06, + "loss": 3.8637, + "step": 2560512 + }, + { + "epoch": 1.01, + "learning_rate": 8.068280612147964e-06, + "loss": 3.8541, + "step": 2561024 + }, + { + "epoch": 1.01, + "learning_rate": 8.059911043441173e-06, + "loss": 3.8328, + "step": 2561536 + }, + { + "epoch": 1.01, + "learning_rate": 8.051541474734385e-06, + "loss": 3.8428, + "step": 2562048 + }, + { + "epoch": 1.01, + "learning_rate": 8.043155527223865e-06, + "loss": 3.8515, + "step": 2562560 + }, + { + "epoch": 1.01, + "learning_rate": 8.034769579713345e-06, + "loss": 3.8492, + "step": 2563072 + }, + { + "epoch": 1.01, + "learning_rate": 8.026400011006556e-06, + "loss": 3.8474, + "step": 2563584 + }, + { + "epoch": 1.01, + "learning_rate": 8.018014063496036e-06, + "loss": 3.8568, + "step": 2564096 + }, + { + "epoch": 1.02, + "learning_rate": 8.009628115985516e-06, + "loss": 3.8426, + "step": 2564608 + }, + { + "epoch": 1.02, + "learning_rate": 8.001242168474996e-06, + "loss": 3.846, + "step": 2565120 + }, + { + "epoch": 1.02, + "learning_rate": 7.992856220964476e-06, + "loss": 3.8494, + "step": 2565632 + }, + { + "epoch": 1.02, + "learning_rate": 7.984470273453956e-06, + "loss": 3.8596, + "step": 2566144 + }, + { + "epoch": 1.02, + "learning_rate": 7.976084325943436e-06, + "loss": 3.8574, + "step": 2566656 + }, + { + "epoch": 1.02, + "learning_rate": 7.967698378432916e-06, + "loss": 3.8639, + "step": 2567168 + }, + { + "epoch": 1.02, + "learning_rate": 7.959312430922396e-06, + "loss": 3.8396, + "step": 2567680 + }, + { + "epoch": 1.02, + "learning_rate": 7.950942862215607e-06, + "loss": 3.851, + "step": 2568192 + }, + { + "epoch": 1.02, + "learning_rate": 7.942556914705086e-06, + "loss": 3.8523, + "step": 2568704 + }, + { + "epoch": 1.02, + "learning_rate": 7.934170967194566e-06, + "loss": 3.851, + "step": 2569216 + }, + { + "epoch": 1.02, + "learning_rate": 7.925785019684046e-06, + "loss": 3.8623, + "step": 2569728 + }, + { + "epoch": 1.02, + "learning_rate": 7.917399072173528e-06, + "loss": 3.8432, + "step": 2570240 + }, + { + "epoch": 1.02, + "learning_rate": 7.909013124663006e-06, + "loss": 3.8503, + "step": 2570752 + }, + { + "epoch": 1.02, + "learning_rate": 7.900627177152486e-06, + "loss": 3.8567, + "step": 2571264 + }, + { + "epoch": 1.02, + "learning_rate": 7.892241229641966e-06, + "loss": 3.8561, + "step": 2571776 + }, + { + "epoch": 1.02, + "learning_rate": 7.883871660935177e-06, + "loss": 3.8384, + "step": 2572288 + }, + { + "epoch": 1.02, + "learning_rate": 7.87550209222839e-06, + "loss": 3.8531, + "step": 2572800 + }, + { + "epoch": 1.02, + "learning_rate": 7.86711614471787e-06, + "loss": 3.8431, + "step": 2573312 + }, + { + "epoch": 1.02, + "learning_rate": 7.85873019720735e-06, + "loss": 3.8455, + "step": 2573824 + }, + { + "epoch": 1.02, + "learning_rate": 7.850344249696828e-06, + "loss": 3.8427, + "step": 2574336 + }, + { + "epoch": 1.02, + "learning_rate": 7.84195830218631e-06, + "loss": 3.8467, + "step": 2574848 + }, + { + "epoch": 1.02, + "learning_rate": 7.83357235467579e-06, + "loss": 3.8426, + "step": 2575360 + }, + { + "epoch": 1.02, + "learning_rate": 7.825202785969e-06, + "loss": 3.8536, + "step": 2575872 + }, + { + "epoch": 1.02, + "learning_rate": 7.81681683845848e-06, + "loss": 3.8426, + "step": 2576384 + }, + { + "epoch": 1.02, + "learning_rate": 7.80843089094796e-06, + "loss": 3.8517, + "step": 2576896 + }, + { + "epoch": 1.02, + "learning_rate": 7.80004494343744e-06, + "loss": 3.8664, + "step": 2577408 + }, + { + "epoch": 1.02, + "learning_rate": 7.791658995926918e-06, + "loss": 3.8578, + "step": 2577920 + }, + { + "epoch": 1.02, + "learning_rate": 7.78328942722013e-06, + "loss": 3.8559, + "step": 2578432 + }, + { + "epoch": 1.02, + "learning_rate": 7.77490347970961e-06, + "loss": 3.8531, + "step": 2578944 + }, + { + "epoch": 1.02, + "learning_rate": 7.76651753219909e-06, + "loss": 3.8487, + "step": 2579456 + }, + { + "epoch": 1.02, + "learning_rate": 7.758147963492301e-06, + "loss": 3.85, + "step": 2579968 + }, + { + "epoch": 1.02, + "learning_rate": 7.749762015981781e-06, + "loss": 3.8445, + "step": 2580480 + }, + { + "epoch": 1.02, + "learning_rate": 7.741376068471263e-06, + "loss": 3.8447, + "step": 2580992 + }, + { + "epoch": 1.02, + "learning_rate": 7.732990120960741e-06, + "loss": 3.8501, + "step": 2581504 + }, + { + "epoch": 1.02, + "learning_rate": 7.724604173450221e-06, + "loss": 3.8564, + "step": 2582016 + }, + { + "epoch": 1.02, + "learning_rate": 7.716218225939701e-06, + "loss": 3.8544, + "step": 2582528 + }, + { + "epoch": 1.02, + "learning_rate": 7.707832278429183e-06, + "loss": 3.8502, + "step": 2583040 + }, + { + "epoch": 1.02, + "learning_rate": 7.699462709722392e-06, + "loss": 3.8521, + "step": 2583552 + }, + { + "epoch": 1.02, + "learning_rate": 7.691076762211872e-06, + "loss": 3.8455, + "step": 2584064 + }, + { + "epoch": 1.02, + "learning_rate": 7.682690814701354e-06, + "loss": 3.8429, + "step": 2584576 + }, + { + "epoch": 1.02, + "learning_rate": 7.674304867190832e-06, + "loss": 3.8652, + "step": 2585088 + }, + { + "epoch": 1.02, + "learning_rate": 7.665918919680312e-06, + "loss": 3.8599, + "step": 2585600 + }, + { + "epoch": 1.02, + "learning_rate": 7.657532972169792e-06, + "loss": 3.8556, + "step": 2586112 + }, + { + "epoch": 1.02, + "learning_rate": 7.649147024659273e-06, + "loss": 3.8517, + "step": 2586624 + }, + { + "epoch": 1.02, + "learning_rate": 7.640761077148752e-06, + "loss": 3.855, + "step": 2587136 + }, + { + "epoch": 1.02, + "learning_rate": 7.632375129638232e-06, + "loss": 3.8559, + "step": 2587648 + }, + { + "epoch": 1.02, + "learning_rate": 7.623989182127712e-06, + "loss": 3.8644, + "step": 2588160 + }, + { + "epoch": 1.02, + "learning_rate": 7.615619613420922e-06, + "loss": 3.8535, + "step": 2588672 + }, + { + "epoch": 1.02, + "learning_rate": 7.607233665910403e-06, + "loss": 3.8512, + "step": 2589184 + }, + { + "epoch": 1.02, + "learning_rate": 7.598864097203615e-06, + "loss": 3.8533, + "step": 2589696 + }, + { + "epoch": 1.02, + "learning_rate": 7.590478149693095e-06, + "loss": 3.8531, + "step": 2590208 + }, + { + "epoch": 1.02, + "learning_rate": 7.582092202182574e-06, + "loss": 3.847, + "step": 2590720 + }, + { + "epoch": 1.02, + "learning_rate": 7.573706254672054e-06, + "loss": 3.8518, + "step": 2591232 + }, + { + "epoch": 1.02, + "learning_rate": 7.5653203071615346e-06, + "loss": 3.8575, + "step": 2591744 + }, + { + "epoch": 1.02, + "learning_rate": 7.556934359651014e-06, + "loss": 3.8415, + "step": 2592256 + }, + { + "epoch": 1.02, + "learning_rate": 7.548564790944225e-06, + "loss": 3.8596, + "step": 2592768 + }, + { + "epoch": 1.02, + "learning_rate": 7.540178843433705e-06, + "loss": 3.8536, + "step": 2593280 + }, + { + "epoch": 1.02, + "learning_rate": 7.531792895923186e-06, + "loss": 3.8542, + "step": 2593792 + }, + { + "epoch": 1.02, + "learning_rate": 7.523406948412664e-06, + "loss": 3.8575, + "step": 2594304 + }, + { + "epoch": 1.02, + "learning_rate": 7.515021000902145e-06, + "loss": 3.8437, + "step": 2594816 + }, + { + "epoch": 1.03, + "eval_loss": 3.9754717350006104, + "eval_runtime": 291.4947, + "eval_samples_per_second": 1309.084, + "eval_steps_per_second": 40.91, + "step": 2594880 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.0720550480797699e+18, + "trial_name": null, + "trial_params": null +}