diff --git "a/checkpoint-1908000/trainer_state.json" "b/checkpoint-1908000/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-1908000/trainer_state.json" @@ -0,0 +1,22581 @@ +{ + "best_metric": 3.987415313720703, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/binding-reconstruction/lstm/4/checkpoints/checkpoint-1908000", + "epoch": 0.025000606015738065, + "eval_steps": 10, + "global_step": 1908000, + "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": 10.8185, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 7.5433, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 7.0559, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 6.9906, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 6.9467, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 6.8761, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 6.7154, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 6.6163, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993292879871958e-05, + "loss": 6.5258, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992454285120906e-05, + "loss": 6.4501, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.991615690369854e-05, + "loss": 6.3868, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990777095618801e-05, + "loss": 6.328, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989938500867749e-05, + "loss": 6.259, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 6.1899, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 6.1409, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 6.0809, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 6.0473, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 6.0075, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.9568, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.9232, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.8839, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.982391148108281e-05, + "loss": 5.8518, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.981552553357229e-05, + "loss": 5.8216, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 5.7846, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 5.7675, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790384069844466e-05, + "loss": 5.7279, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9781998122333946e-05, + "loss": 5.7087, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773612174823426e-05, + "loss": 5.6832, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.97652262273129e-05, + "loss": 5.6563, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756856658606115e-05, + "loss": 5.6283, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748470711095595e-05, + "loss": 5.614, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.974008476358507e-05, + "loss": 5.6034, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.973169881607455e-05, + "loss": 5.5789, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.972331286856403e-05, + "loss": 5.5579, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.9714926921053515e-05, + "loss": 5.5494, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.9706557352346724e-05, + "loss": 5.5389, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 5.5135, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968980183612942e-05, + "loss": 5.4816, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.96814158886189e-05, + "loss": 5.4766, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967302994110837e-05, + "loss": 5.445, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966464399359785e-05, + "loss": 5.4494, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 5.4331, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 5.4314, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 5.4016, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.96311165823595e-05, + "loss": 5.4, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962273063484898e-05, + "loss": 5.3864, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.961434468733847e-05, + "loss": 5.379, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960595873982795e-05, + "loss": 5.3739, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959757279231743e-05, + "loss": 5.341, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.958920322361064e-05, + "loss": 5.3389, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958081727610012e-05, + "loss": 5.3428, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.95724313285896e-05, + "loss": 5.332, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956404538107908e-05, + "loss": 5.3082, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.955565943356856e-05, + "loss": 5.296, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.954727348605804e-05, + "loss": 5.2874, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.953890391735125e-05, + "loss": 5.2792, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530517969840727e-05, + "loss": 5.2906, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522132022330207e-05, + "loss": 5.2508, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.9513746074819686e-05, + "loss": 5.2611, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.9505360127309166e-05, + "loss": 5.2504, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949699055860238e-05, + "loss": 5.2354, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948862098989559e-05, + "loss": 5.2373, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.948023504238507e-05, + "loss": 5.2106, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947184909487455e-05, + "loss": 5.2055, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946346314736403e-05, + "loss": 5.2032, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945507719985351e-05, + "loss": 5.2153, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944669125234299e-05, + "loss": 5.1855, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943830530483247e-05, + "loss": 5.181, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942991935732195e-05, + "loss": 5.1606, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.942153340981143e-05, + "loss": 5.1701, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.941316384110464e-05, + "loss": 5.1689, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.940477789359412e-05, + "loss": 5.1685, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.93963919460836e-05, + "loss": 5.1453, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.938800599857309e-05, + "loss": 5.157, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.937962005106256e-05, + "loss": 5.1578, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.937123410355204e-05, + "loss": 5.1332, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.936284815604152e-05, + "loss": 5.1207, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.935447858733473e-05, + "loss": 5.1116, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.934609263982421e-05, + "loss": 5.1023, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.933770669231369e-05, + "loss": 5.1123, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.932932074480317e-05, + "loss": 5.0907, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.932093479729265e-05, + "loss": 5.1072, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931254884978213e-05, + "loss": 5.0995, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930417928107534e-05, + "loss": 5.0814, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.9295793333564825e-05, + "loss": 5.0679, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.9287407386054305e-05, + "loss": 5.0694, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.9279021438543785e-05, + "loss": 5.0694, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.9270635491033264e-05, + "loss": 5.0732, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.9262265922326474e-05, + "loss": 5.0527, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.9253879974815954e-05, + "loss": 5.0515, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.9245494027305433e-05, + "loss": 5.0474, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.9237108079794913e-05, + "loss": 5.0329, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922873851108812e-05, + "loss": 5.0317, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.92203525635776e-05, + "loss": 5.0284, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921196661606708e-05, + "loss": 5.021, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920358066855656e-05, + "loss": 5.0197, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919519472104604e-05, + "loss": 5.0085, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918680877353552e-05, + "loss": 5.0013, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.917842282602501e-05, + "loss": 5.0073, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.917003687851449e-05, + "loss": 5.0022, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.91616673098077e-05, + "loss": 4.9959, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.915328136229718e-05, + "loss": 4.9894, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914491179359039e-05, + "loss": 4.9801, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.913652584607987e-05, + "loss": 4.9745, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.912813989856935e-05, + "loss": 4.9717, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.911975395105883e-05, + "loss": 4.9503, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.911136800354831e-05, + "loss": 4.9574, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910298205603779e-05, + "loss": 4.9549, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.909459610852727e-05, + "loss": 4.958, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908621016101675e-05, + "loss": 4.945, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907782421350623e-05, + "loss": 4.9491, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.906943826599571e-05, + "loss": 4.9261, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906105231848519e-05, + "loss": 4.9461, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.9052682749778396e-05, + "loss": 4.9179, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.9044296802267876e-05, + "loss": 4.9265, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.9035910854757356e-05, + "loss": 4.9276, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.9027524907246836e-05, + "loss": 4.9236, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.9019155338540045e-05, + "loss": 4.9186, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.9010769391029525e-05, + "loss": 4.9054, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.9002383443519005e-05, + "loss": 4.9104, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8993997496008485e-05, + "loss": 4.9144, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985611548497965e-05, + "loss": 4.8975, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977225600987445e-05, + "loss": 4.893, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968839653476924e-05, + "loss": 4.8885, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.896045370596641e-05, + "loss": 4.9005, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.895208413725962e-05, + "loss": 4.8691, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.89436981897491e-05, + "loss": 4.8741, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.893532862104231e-05, + "loss": 4.8669, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.892694267353179e-05, + "loss": 4.8759, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.891855672602127e-05, + "loss": 4.8615, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.891017077851075e-05, + "loss": 4.8792, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890180120980396e-05, + "loss": 4.8686, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889341526229344e-05, + "loss": 4.8586, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888502931478292e-05, + "loss": 4.8507, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.8876659746076134e-05, + "loss": 4.8568, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.8868273798565614e-05, + "loss": 4.8555, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.8859887851055094e-05, + "loss": 4.8544, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.8851501903544574e-05, + "loss": 4.8407, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.8843115956034054e-05, + "loss": 4.8504, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.8834730008523534e-05, + "loss": 4.8391, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.8826344061013014e-05, + "loss": 4.8385, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.8817958113502494e-05, + "loss": 4.8202, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.88095885447957e-05, + "loss": 4.8369, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880120259728518e-05, + "loss": 4.8212, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879281664977466e-05, + "loss": 4.8019, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878443070226414e-05, + "loss": 4.8289, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877604475475362e-05, + "loss": 4.8157, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.87676588072431e-05, + "loss": 4.8132, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875927285973258e-05, + "loss": 4.8133, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875088691222206e-05, + "loss": 4.7992, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.764401912689209, + "eval_runtime": 299.3062, + "eval_samples_per_second": 1274.918, + "eval_steps_per_second": 39.842, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.874251734351528e-05, + "loss": 4.7826, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.873413139600475e-05, + "loss": 4.789, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.872574544849423e-05, + "loss": 4.8036, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.871735950098371e-05, + "loss": 4.7906, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.870897355347319e-05, + "loss": 4.7964, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.870058760596267e-05, + "loss": 4.7835, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.869220165845215e-05, + "loss": 4.7838, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.868381571094163e-05, + "loss": 4.7695, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.8675462521038576e-05, + "loss": 4.7723, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.8667076573528056e-05, + "loss": 4.7732, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.8658690626017536e-05, + "loss": 4.7864, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.865032105731075e-05, + "loss": 4.7789, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.8641935109800225e-05, + "loss": 4.7617, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.8633549162289705e-05, + "loss": 4.7572, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.8625163214779185e-05, + "loss": 4.7444, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.86167936460724e-05, + "loss": 4.7476, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.8608407698561874e-05, + "loss": 4.7591, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.8600021751051354e-05, + "loss": 4.7453, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.8591635803540834e-05, + "loss": 4.7423, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.858326623483405e-05, + "loss": 4.7573, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.857488028732352e-05, + "loss": 4.7461, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.856649433981301e-05, + "loss": 4.7397, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.855810839230249e-05, + "loss": 4.7398, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.854972244479197e-05, + "loss": 4.7527, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.854133649728145e-05, + "loss": 4.7244, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.853295054977093e-05, + "loss": 4.7293, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.852456460226041e-05, + "loss": 4.7359, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.851617865474989e-05, + "loss": 4.7263, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.85078090860431e-05, + "loss": 4.7099, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.849942313853258e-05, + "loss": 4.7139, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.849103719102206e-05, + "loss": 4.7273, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.848266762231527e-05, + "loss": 4.7177, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847428167480475e-05, + "loss": 4.7145, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846589572729423e-05, + "loss": 4.7184, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845750977978371e-05, + "loss": 4.7155, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.8449123832273194e-05, + "loss": 4.7117, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.8440737884762674e-05, + "loss": 4.6946, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.8432351937252154e-05, + "loss": 4.6992, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.8423965989741634e-05, + "loss": 4.6831, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.8415580042231114e-05, + "loss": 4.6972, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840721047352432e-05, + "loss": 4.6919, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.83988245260138e-05, + "loss": 4.7009, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839045495730701e-05, + "loss": 4.6824, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.838206900979649e-05, + "loss": 4.6937, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.837368306228597e-05, + "loss": 4.685, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.836529711477545e-05, + "loss": 4.6857, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.835691116726493e-05, + "loss": 4.6947, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.834852521975441e-05, + "loss": 4.6625, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834013927224389e-05, + "loss": 4.6669, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.833175332473337e-05, + "loss": 4.6859, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.832336737722285e-05, + "loss": 4.6784, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.831498142971233e-05, + "loss": 4.6676, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.830659548220181e-05, + "loss": 4.659, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.829820953469129e-05, + "loss": 4.6605, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.828985634478824e-05, + "loss": 4.6487, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.828147039727771e-05, + "loss": 4.6768, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.827308444976719e-05, + "loss": 4.6443, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.826469850225667e-05, + "loss": 4.6643, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.8256328933549886e-05, + "loss": 4.653, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.8247942986039366e-05, + "loss": 4.6465, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.8239557038528846e-05, + "loss": 4.6516, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.8231171091018326e-05, + "loss": 4.6381, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.8222785143507806e-05, + "loss": 4.6316, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.8214399195997286e-05, + "loss": 4.6396, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.8206029627290495e-05, + "loss": 4.6582, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.8197643679779975e-05, + "loss": 4.6277, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.8189257732269455e-05, + "loss": 4.6318, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.8180871784758935e-05, + "loss": 4.6177, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.8172502216052144e-05, + "loss": 4.6324, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.8164116268541624e-05, + "loss": 4.6451, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.8155730321031104e-05, + "loss": 4.6375, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.8147344373520584e-05, + "loss": 4.6243, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.8138958426010064e-05, + "loss": 4.6384, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.813057247849955e-05, + "loss": 4.6444, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.812218653098903e-05, + "loss": 4.6227, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.811381696228224e-05, + "loss": 4.6178, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.810543101477172e-05, + "loss": 4.6199, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.80970450672612e-05, + "loss": 4.6112, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.808865911975068e-05, + "loss": 4.6203, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808028955104389e-05, + "loss": 4.6084, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.807190360353337e-05, + "loss": 4.6225, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.806351765602285e-05, + "loss": 4.619, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805513170851233e-05, + "loss": 4.614, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804674576100181e-05, + "loss": 4.5967, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803835981349129e-05, + "loss": 4.6055, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.802997386598077e-05, + "loss": 4.6078, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.802158791847025e-05, + "loss": 4.6152, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.801320197095973e-05, + "loss": 4.6061, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.800481602344921e-05, + "loss": 4.6005, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.799643007593869e-05, + "loss": 4.6044, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.798804412842817e-05, + "loss": 4.5925, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.797967455972138e-05, + "loss": 4.5912, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.797128861221086e-05, + "loss": 4.5988, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.796290266470034e-05, + "loss": 4.5899, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.795451671718982e-05, + "loss": 4.5921, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.79461307696793e-05, + "loss": 4.5919, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.793774482216878e-05, + "loss": 4.5788, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.7929375253461986e-05, + "loss": 4.591, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.792098930595147e-05, + "loss": 4.5968, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.791261973724468e-05, + "loss": 4.5871, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.790423378973416e-05, + "loss": 4.5822, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.789584784222364e-05, + "loss": 4.5732, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.788746189471312e-05, + "loss": 4.578, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.78790759472026e-05, + "loss": 4.5778, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.787068999969208e-05, + "loss": 4.5613, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.786232043098529e-05, + "loss": 4.5651, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.785393448347477e-05, + "loss": 4.5697, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.784554853596425e-05, + "loss": 4.5774, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.783716258845373e-05, + "loss": 4.5651, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.782877664094321e-05, + "loss": 4.5702, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.782039069343269e-05, + "loss": 4.5531, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.781200474592217e-05, + "loss": 4.5751, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.780361879841165e-05, + "loss": 4.5542, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.779523285090114e-05, + "loss": 4.5592, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.7786863282194346e-05, + "loss": 4.5696, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.7778477334683826e-05, + "loss": 4.5639, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.7770091387173306e-05, + "loss": 4.5626, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.7761705439662786e-05, + "loss": 4.5488, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.7753335870955995e-05, + "loss": 4.5587, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.7744966302249204e-05, + "loss": 4.566, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.7736580354738684e-05, + "loss": 4.5484, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.7728194407228164e-05, + "loss": 4.5505, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.7719808459717644e-05, + "loss": 4.5451, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.7711422512207124e-05, + "loss": 4.5622, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.7703036564696604e-05, + "loss": 4.5333, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.7694650617186084e-05, + "loss": 4.5424, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.7686264669675564e-05, + "loss": 4.5339, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.767789510096878e-05, + "loss": 4.5474, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766950915345826e-05, + "loss": 4.5346, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766112320594773e-05, + "loss": 4.5548, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.765273725843721e-05, + "loss": 4.5489, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764435131092669e-05, + "loss": 4.5381, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.763596536341617e-05, + "loss": 4.5313, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762759579470938e-05, + "loss": 4.5422, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761920984719886e-05, + "loss": 4.5407, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.761082389968834e-05, + "loss": 4.5475, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.760243795217783e-05, + "loss": 4.525, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.759405200466731e-05, + "loss": 4.5431, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.758566605715679e-05, + "loss": 4.5349, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.757729648845e-05, + "loss": 4.5387, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.756891054093948e-05, + "loss": 4.5212, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.756052459342896e-05, + "loss": 4.5354, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.755213864591844e-05, + "loss": 4.5275, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.754375269840792e-05, + "loss": 4.5157, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.75353667508974e-05, + "loss": 4.5329, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.7526997182190606e-05, + "loss": 4.5275, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.7518611234680086e-05, + "loss": 4.5235, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.7510225287169566e-05, + "loss": 4.5208, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.7501839339659046e-05, + "loss": 4.5125, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.484683036804199, + "eval_runtime": 299.2612, + "eval_samples_per_second": 1275.11, + "eval_steps_per_second": 39.848, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.7493453392148526e-05, + "loss": 4.498, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748506744463801e-05, + "loss": 4.5051, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.747668149712749e-05, + "loss": 4.5258, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.746829554961697e-05, + "loss": 4.5149, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.7459909602106446e-05, + "loss": 4.5183, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.7451523654595926e-05, + "loss": 4.5055, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.7443137707085406e-05, + "loss": 4.5114, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.7434751759574886e-05, + "loss": 4.4992, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.7426365812064366e-05, + "loss": 4.5026, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.7417979864553846e-05, + "loss": 4.51, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.7409593917043326e-05, + "loss": 4.5148, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.7401207969532806e-05, + "loss": 4.5154, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.7392838400826015e-05, + "loss": 4.4974, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.7384452453315495e-05, + "loss": 4.4949, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.7376066505804975e-05, + "loss": 4.4923, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736768055829446e-05, + "loss": 4.4823, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735929461078394e-05, + "loss": 4.4999, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.735090866327342e-05, + "loss": 4.4874, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.73425227157629e-05, + "loss": 4.4908, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733413676825238e-05, + "loss": 4.509, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732575082074186e-05, + "loss": 4.4926, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.7317364873231334e-05, + "loss": 4.4918, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.7308978925720814e-05, + "loss": 4.4936, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.7300592978210294e-05, + "loss": 4.5058, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.729222340950351e-05, + "loss": 4.4754, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.728385384079672e-05, + "loss": 4.4837, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.72754678932862e-05, + "loss": 4.4914, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.726708194577568e-05, + "loss": 4.4867, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.725869599826516e-05, + "loss": 4.4738, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.725031005075464e-05, + "loss": 4.4698, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.724192410324412e-05, + "loss": 4.4918, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.72335381557336e-05, + "loss": 4.4875, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.722515220822308e-05, + "loss": 4.4773, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.721678263951629e-05, + "loss": 4.4852, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.7208413070809504e-05, + "loss": 4.4824, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.7200027123298984e-05, + "loss": 4.4777, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.719164117578846e-05, + "loss": 4.4651, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.718325522827794e-05, + "loss": 4.4753, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.717486928076742e-05, + "loss": 4.4544, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.71664833332569e-05, + "loss": 4.473, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.7158097385746384e-05, + "loss": 4.4674, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.714972781703959e-05, + "loss": 4.4749, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.714134186952907e-05, + "loss": 4.4633, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.713295592201855e-05, + "loss": 4.4704, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.712456997450803e-05, + "loss": 4.469, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.711618402699751e-05, + "loss": 4.4644, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.710779807948699e-05, + "loss": 4.4758, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.709941213197647e-05, + "loss": 4.4462, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.709102618446595e-05, + "loss": 4.4564, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.708265661575916e-05, + "loss": 4.469, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.707428704705237e-05, + "loss": 4.4657, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.7065917478345586e-05, + "loss": 4.4539, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.7057531530835066e-05, + "loss": 4.4457, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.7049145583324546e-05, + "loss": 4.4553, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.7040759635814026e-05, + "loss": 4.4358, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.7032373688303506e-05, + "loss": 4.4691, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.7023987740792986e-05, + "loss": 4.4423, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.7015601793282466e-05, + "loss": 4.4508, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.7007215845771946e-05, + "loss": 4.4498, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.6998829898261426e-05, + "loss": 4.4415, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.6990443950750906e-05, + "loss": 4.4478, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.6982058003240386e-05, + "loss": 4.4373, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.6973672055729866e-05, + "loss": 4.4331, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.6965302487023075e-05, + "loss": 4.4354, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.695693291831629e-05, + "loss": 4.4556, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694854697080577e-05, + "loss": 4.4329, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694016102329525e-05, + "loss": 4.4337, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693177507578473e-05, + "loss": 4.4215, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692338912827421e-05, + "loss": 4.4369, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.691500318076369e-05, + "loss": 4.4466, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.69066336120569e-05, + "loss": 4.4462, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.689824766454638e-05, + "loss": 4.4302, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.688986171703586e-05, + "loss": 4.4458, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.688147576952534e-05, + "loss": 4.4547, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.687308982201481e-05, + "loss": 4.4322, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.686472025330803e-05, + "loss": 4.4225, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.685633430579751e-05, + "loss": 4.4354, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.684794835828699e-05, + "loss": 4.427, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.683956241077647e-05, + "loss": 4.4312, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.683117646326595e-05, + "loss": 4.4213, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.682279051575543e-05, + "loss": 4.4346, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.681440456824491e-05, + "loss": 4.4379, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.680601862073439e-05, + "loss": 4.4291, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679763267322387e-05, + "loss": 4.4139, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678926310451708e-05, + "loss": 4.4229, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678087715700656e-05, + "loss": 4.4248, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.677249120949604e-05, + "loss": 4.4339, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.676410526198552e-05, + "loss": 4.4245, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.6755735693278726e-05, + "loss": 4.4261, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.6747349745768206e-05, + "loss": 4.4243, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.673896379825769e-05, + "loss": 4.4155, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.673057785074717e-05, + "loss": 4.4149, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.672220828204038e-05, + "loss": 4.4166, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.671382233452986e-05, + "loss": 4.4172, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.670543638701934e-05, + "loss": 4.4203, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.669705043950882e-05, + "loss": 4.4181, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.66886644919983e-05, + "loss": 4.402, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668027854448778e-05, + "loss": 4.4198, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667189259697726e-05, + "loss": 4.425, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.666350664946674e-05, + "loss": 4.4145, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665512070195622e-05, + "loss": 4.415, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664675113324943e-05, + "loss": 4.403, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663836518573891e-05, + "loss": 4.41, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.662997923822839e-05, + "loss": 4.4109, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662159329071788e-05, + "loss": 4.3898, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.661320734320736e-05, + "loss": 4.4002, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.6604837774500567e-05, + "loss": 4.4081, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.6596451826990047e-05, + "loss": 4.4075, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.6588082258283256e-05, + "loss": 4.3976, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.6579696310772736e-05, + "loss": 4.4059, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.6571310363262216e-05, + "loss": 4.3912, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.6562924415751695e-05, + "loss": 4.4102, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.6554538468241175e-05, + "loss": 4.394, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.6546168899534385e-05, + "loss": 4.3942, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.6537782952023865e-05, + "loss": 4.4095, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.6529397004513344e-05, + "loss": 4.4069, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.652101105700283e-05, + "loss": 4.4025, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.6512625109492304e-05, + "loss": 4.3938, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.6504239161981784e-05, + "loss": 4.3971, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.6495869593275e-05, + "loss": 4.4017, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648748364576447e-05, + "loss": 4.3939, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.647909769825395e-05, + "loss": 4.395, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.647071175074343e-05, + "loss": 4.3872, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.646234218203665e-05, + "loss": 4.399, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.645395623452612e-05, + "loss": 4.3873, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.64455702870156e-05, + "loss": 4.3884, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.643718433950508e-05, + "loss": 4.3754, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.642879839199457e-05, + "loss": 4.3959, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642041244448405e-05, + "loss": 4.3793, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.641202649697353e-05, + "loss": 4.4012, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640364054946301e-05, + "loss": 4.3971, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.639525460195249e-05, + "loss": 4.3902, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.63868850332457e-05, + "loss": 4.3761, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.637849908573518e-05, + "loss": 4.3957, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.637011313822466e-05, + "loss": 4.3911, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.636174356951787e-05, + "loss": 4.3954, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.635335762200735e-05, + "loss": 4.3816, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.634497167449683e-05, + "loss": 4.3893, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.633658572698631e-05, + "loss": 4.391, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.632819977947579e-05, + "loss": 4.3928, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.631981383196527e-05, + "loss": 4.3788, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.631142788445475e-05, + "loss": 4.3857, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.630304193694423e-05, + "loss": 4.3818, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629465598943371e-05, + "loss": 4.3702, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.628627004192319e-05, + "loss": 4.3889, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.6277884094412666e-05, + "loss": 4.3877, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.6269498146902146e-05, + "loss": 4.3753, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626114495699909e-05, + "loss": 4.381, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625275900948857e-05, + "loss": 4.3702, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 4.349175453186035, + "eval_runtime": 291.0538, + "eval_samples_per_second": 1311.067, + "eval_steps_per_second": 40.972, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.624437306197805e-05, + "loss": 4.3648, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.623598711446753e-05, + "loss": 4.3603, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.622760116695701e-05, + "loss": 4.385, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.6219215219446484e-05, + "loss": 4.371, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.621082927193597e-05, + "loss": 4.3821, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.620244332442545e-05, + "loss": 4.3657, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.619407375571867e-05, + "loss": 4.3724, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.618568780820814e-05, + "loss": 4.3582, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.6177318239501356e-05, + "loss": 4.3686, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.6168932291990836e-05, + "loss": 4.3685, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.616054634448031e-05, + "loss": 4.3799, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.615216039696979e-05, + "loss": 4.3782, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.6143790828263005e-05, + "loss": 4.3605, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.6135404880752485e-05, + "loss": 4.3603, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.612701893324196e-05, + "loss": 4.357, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.611863298573144e-05, + "loss": 4.3506, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.6110247038220925e-05, + "loss": 4.361, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.6101861090710405e-05, + "loss": 4.3552, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.6093475143199885e-05, + "loss": 4.3563, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.6085089195689365e-05, + "loss": 4.3791, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.6076703248178845e-05, + "loss": 4.3595, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.6068317300668325e-05, + "loss": 4.3563, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.6059947731961534e-05, + "loss": 4.3633, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.6051561784451014e-05, + "loss": 4.3702, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.6043175836940494e-05, + "loss": 4.3465, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.6034789889429974e-05, + "loss": 4.3525, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.6026403941919454e-05, + "loss": 4.3619, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.601803437321266e-05, + "loss": 4.3581, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.600964842570214e-05, + "loss": 4.3422, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.600126247819162e-05, + "loss": 4.3415, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.599287653068111e-05, + "loss": 4.3602, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.598449058317059e-05, + "loss": 4.3599, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.59761210144638e-05, + "loss": 4.3535, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.596773506695328e-05, + "loss": 4.3564, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.595934911944276e-05, + "loss": 4.3527, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.595096317193224e-05, + "loss": 4.3517, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.594257722442172e-05, + "loss": 4.3371, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.59341912769112e-05, + "loss": 4.3538, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.592580532940067e-05, + "loss": 4.331, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.591741938189015e-05, + "loss": 4.3458, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.590904981318337e-05, + "loss": 4.3406, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.590066386567285e-05, + "loss": 4.3544, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.589227791816233e-05, + "loss": 4.3421, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.588389197065181e-05, + "loss": 4.3442, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.587552240194502e-05, + "loss": 4.3444, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.5867136454434496e-05, + "loss": 4.3466, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.585876688572771e-05, + "loss": 4.3521, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.585038093821719e-05, + "loss": 4.3273, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.584199499070667e-05, + "loss": 4.3327, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.5833609043196145e-05, + "loss": 4.349, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.5825223095685625e-05, + "loss": 4.3446, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.5816837148175105e-05, + "loss": 4.3344, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.5808451200664585e-05, + "loss": 4.3284, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.5800065253154065e-05, + "loss": 4.3362, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.5791679305643545e-05, + "loss": 4.3194, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.5783293358133025e-05, + "loss": 4.3466, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.577490741062251e-05, + "loss": 4.3237, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.576652146311199e-05, + "loss": 4.332, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.57581518944052e-05, + "loss": 4.3354, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.574976594689468e-05, + "loss": 4.3244, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.574137999938416e-05, + "loss": 4.3272, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.573299405187364e-05, + "loss": 4.3238, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.572462448316685e-05, + "loss": 4.3166, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.571623853565633e-05, + "loss": 4.3255, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.570785258814581e-05, + "loss": 4.3343, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.569946664063529e-05, + "loss": 4.3203, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.56910970719285e-05, + "loss": 4.3208, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.568271112441798e-05, + "loss": 4.3101, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.5674325176907465e-05, + "loss": 4.3195, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.5665955608200674e-05, + "loss": 4.3303, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.5657569660690154e-05, + "loss": 4.339, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.5649183713179634e-05, + "loss": 4.3155, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.5640797765669114e-05, + "loss": 4.3324, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.5632411818158594e-05, + "loss": 4.3377, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.5624025870648074e-05, + "loss": 4.3297, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.561565630194128e-05, + "loss": 4.3059, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.560727035443076e-05, + "loss": 4.3258, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.559888440692024e-05, + "loss": 4.3208, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.559049845940972e-05, + "loss": 4.3145, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.55821125118992e-05, + "loss": 4.3193, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.557372656438868e-05, + "loss": 4.3194, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.556534061687816e-05, + "loss": 4.3294, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.555697104817138e-05, + "loss": 4.319, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.554858510066086e-05, + "loss": 4.306, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.554019915315033e-05, + "loss": 4.3169, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.553181320563981e-05, + "loss": 4.3113, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.552342725812929e-05, + "loss": 4.3252, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.551504131061877e-05, + "loss": 4.3225, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.550668812071572e-05, + "loss": 4.3141, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.5498318552008926e-05, + "loss": 4.3182, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.5489932604498406e-05, + "loss": 4.3053, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.5481546656987886e-05, + "loss": 4.3075, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.547316070947737e-05, + "loss": 4.3096, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.546477476196685e-05, + "loss": 4.3129, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.545638881445633e-05, + "loss": 4.3114, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.5448002866945806e-05, + "loss": 4.32, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.5439616919435286e-05, + "loss": 4.2945, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.5431230971924765e-05, + "loss": 4.3149, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.5422845024414245e-05, + "loss": 4.3218, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.5414459076903725e-05, + "loss": 4.3109, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.5406073129393205e-05, + "loss": 4.3074, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.5397687181882685e-05, + "loss": 4.3006, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.5389301234372165e-05, + "loss": 4.3075, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.5380931665665374e-05, + "loss": 4.3072, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.5372545718154854e-05, + "loss": 4.2867, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.536415977064434e-05, + "loss": 4.299, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.535577382313382e-05, + "loss": 4.3033, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.53473878756233e-05, + "loss": 4.307, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.533900192811278e-05, + "loss": 4.2914, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.533061598060226e-05, + "loss": 4.3111, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.532223003309174e-05, + "loss": 4.2854, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.531386046438495e-05, + "loss": 4.3089, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.530549089567816e-05, + "loss": 4.2957, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.529710494816764e-05, + "loss": 4.2903, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.528871900065712e-05, + "loss": 4.3087, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.52803330531466e-05, + "loss": 4.3082, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.527196348443981e-05, + "loss": 4.3024, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.5263593915733024e-05, + "loss": 4.297, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.5255207968222504e-05, + "loss": 4.2983, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.5246822020711984e-05, + "loss": 4.3021, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.5238436073201464e-05, + "loss": 4.2914, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.5230050125690944e-05, + "loss": 4.2972, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.5221664178180424e-05, + "loss": 4.2944, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.5213278230669904e-05, + "loss": 4.2973, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.5204892283159384e-05, + "loss": 4.2954, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.5196506335648863e-05, + "loss": 4.2929, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.5188120388138343e-05, + "loss": 4.2735, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.517976719823528e-05, + "loss": 4.298, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.517138125072476e-05, + "loss": 4.2853, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.516299530321425e-05, + "loss": 4.3017, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.515460935570373e-05, + "loss": 4.2994, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.514622340819321e-05, + "loss": 4.2983, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.513783746068269e-05, + "loss": 4.2799, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.512945151317217e-05, + "loss": 4.2999, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.512106556566164e-05, + "loss": 4.2949, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.511269599695486e-05, + "loss": 4.3008, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.510431004944434e-05, + "loss": 4.2832, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.509592410193382e-05, + "loss": 4.3015, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.508753815442329e-05, + "loss": 4.2979, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.507915220691277e-05, + "loss": 4.2999, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.507076625940225e-05, + "loss": 4.2788, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.506238031189173e-05, + "loss": 4.2936, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.505399436438121e-05, + "loss": 4.2891, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.50456084168707e-05, + "loss": 4.28, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.5037238848163906e-05, + "loss": 4.2909, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.5028852900653386e-05, + "loss": 4.2936, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.5020466953142866e-05, + "loss": 4.2846, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.5012081005632346e-05, + "loss": 4.2852, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.5003711436925555e-05, + "loss": 4.2826, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 4.2646164894104, + "eval_runtime": 293.7415, + "eval_samples_per_second": 1299.071, + "eval_steps_per_second": 40.597, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.4995325489415035e-05, + "loss": 4.2657, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.4986939541904515e-05, + "loss": 4.2712, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.4978553594393995e-05, + "loss": 4.2903, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.4970167646883475e-05, + "loss": 4.2816, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.4961781699372955e-05, + "loss": 4.2915, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.4953395751862435e-05, + "loss": 4.2765, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.4945009804351915e-05, + "loss": 4.2807, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.4936623856841395e-05, + "loss": 4.2691, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.492825428813461e-05, + "loss": 4.2801, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.491986834062409e-05, + "loss": 4.2803, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.491148239311357e-05, + "loss": 4.2862, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.490309644560305e-05, + "loss": 4.29, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.489471049809253e-05, + "loss": 4.2708, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.4886324550582003e-05, + "loss": 4.2737, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.4877938603071483e-05, + "loss": 4.2685, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.486955265556096e-05, + "loss": 4.2627, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486116670805044e-05, + "loss": 4.2736, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.485278076053992e-05, + "loss": 4.2697, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.48443948130294e-05, + "loss": 4.2688, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.483600886551888e-05, + "loss": 4.289, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.482762291800836e-05, + "loss": 4.2715, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481923697049785e-05, + "loss": 4.2704, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481085102298733e-05, + "loss": 4.2782, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480246507547681e-05, + "loss": 4.2834, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479409550677002e-05, + "loss": 4.2626, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.47857095592595e-05, + "loss": 4.2696, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477732361174898e-05, + "loss": 4.2743, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476893766423846e-05, + "loss": 4.2712, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476056809553167e-05, + "loss": 4.2557, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475218214802115e-05, + "loss": 4.2588, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474379620051063e-05, + "loss": 4.2738, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473541025300011e-05, + "loss": 4.2756, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472704068429332e-05, + "loss": 4.2711, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.4718654736782804e-05, + "loss": 4.2749, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.4710268789272283e-05, + "loss": 4.2668, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.4701882841761763e-05, + "loss": 4.2716, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.4693496894251243e-05, + "loss": 4.2573, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.4685110946740717e-05, + "loss": 4.2651, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.4676724999230197e-05, + "loss": 4.2497, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.4668339051719676e-05, + "loss": 4.2613, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.465996948301289e-05, + "loss": 4.2581, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.4651583535502366e-05, + "loss": 4.2737, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.4643197587991846e-05, + "loss": 4.2615, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.4634811640481325e-05, + "loss": 4.2625, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.462644207177454e-05, + "loss": 4.2626, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461805612426402e-05, + "loss": 4.2649, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.460968655555724e-05, + "loss": 4.271, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.460130060804672e-05, + "loss": 4.2482, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.459291466053619e-05, + "loss": 4.2499, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.458452871302567e-05, + "loss": 4.2688, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.4576159144318886e-05, + "loss": 4.2636, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.4567773196808366e-05, + "loss": 4.2518, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.455938724929784e-05, + "loss": 4.2476, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.455100130178732e-05, + "loss": 4.2582, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.45426153542768e-05, + "loss": 4.2426, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.453422940676628e-05, + "loss": 4.2635, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.452584345925576e-05, + "loss": 4.2428, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.451745751174524e-05, + "loss": 4.2527, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.4509087943038455e-05, + "loss": 4.2551, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.4500701995527935e-05, + "loss": 4.2492, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.4492316048017415e-05, + "loss": 4.2443, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.4483930100506895e-05, + "loss": 4.2485, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.4475560531800104e-05, + "loss": 4.2381, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.4467174584289584e-05, + "loss": 4.2474, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.4458788636779064e-05, + "loss": 4.2562, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.4450402689268544e-05, + "loss": 4.2437, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444204949936548e-05, + "loss": 4.243, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.443366355185496e-05, + "loss": 4.2326, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.442527760434444e-05, + "loss": 4.2389, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441689165683393e-05, + "loss": 4.2559, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.440852208812714e-05, + "loss": 4.2575, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440013614061662e-05, + "loss": 4.2438, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.43917501931061e-05, + "loss": 4.2539, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438336424559558e-05, + "loss": 4.2629, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437497829808506e-05, + "loss": 4.2516, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.436659235057454e-05, + "loss": 4.233, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435820640306402e-05, + "loss": 4.2503, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.4349836834357227e-05, + "loss": 4.2464, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.4341450886846707e-05, + "loss": 4.2399, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.4333081318139916e-05, + "loss": 4.2433, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.4324695370629396e-05, + "loss": 4.2483, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431630942311888e-05, + "loss": 4.2544, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.430792347560836e-05, + "loss": 4.2446, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.429953752809784e-05, + "loss": 4.2285, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.429115158058732e-05, + "loss": 4.2433, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.42827656330768e-05, + "loss": 4.241, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.427437968556628e-05, + "loss": 4.2443, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.426599373805576e-05, + "loss": 4.2475, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.425762416934897e-05, + "loss": 4.2426, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.424923822183845e-05, + "loss": 4.2455, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.424085227432793e-05, + "loss": 4.2338, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.423246632681741e-05, + "loss": 4.231, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422408037930689e-05, + "loss": 4.2344, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.421569443179637e-05, + "loss": 4.2441, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.420732486308958e-05, + "loss": 4.2386, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.419893891557907e-05, + "loss": 4.2449, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.419055296806855e-05, + "loss": 4.224, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.418216702055803e-05, + "loss": 4.2396, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.41737810730475e-05, + "loss": 4.2479, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.416539512553698e-05, + "loss": 4.242, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.415700917802646e-05, + "loss": 4.2356, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.4148639609319676e-05, + "loss": 4.2308, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.414025366180915e-05, + "loss": 4.2341, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.413186771429863e-05, + "loss": 4.2382, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.412348176678811e-05, + "loss": 4.2147, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.411509581927759e-05, + "loss": 4.2316, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.4106726250570805e-05, + "loss": 4.2279, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.4098340303060284e-05, + "loss": 4.2372, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.4089954355549764e-05, + "loss": 4.2216, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.4081568408039244e-05, + "loss": 4.2393, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.4073182460528724e-05, + "loss": 4.2254, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.4064812891821933e-05, + "loss": 4.2346, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.4056426944311413e-05, + "loss": 4.226, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404804099680089e-05, + "loss": 4.217, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.403965504929037e-05, + "loss": 4.2392, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.403126910177985e-05, + "loss": 4.2411, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402289953307306e-05, + "loss": 4.236, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.401451358556254e-05, + "loss": 4.2252, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400614401685576e-05, + "loss": 4.2291, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399775806934524e-05, + "loss": 4.235, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398937212183472e-05, + "loss": 4.2213, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.39809861743242e-05, + "loss": 4.2288, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.397260022681368e-05, + "loss": 4.2234, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396421427930316e-05, + "loss": 4.2275, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.395582833179264e-05, + "loss": 4.2279, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394744238428212e-05, + "loss": 4.2266, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.39390564367716e-05, + "loss": 4.2089, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.393067048926108e-05, + "loss": 4.2281, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.392228454175056e-05, + "loss": 4.2202, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.391389859424003e-05, + "loss": 4.2355, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.390552902553325e-05, + "loss": 4.2277, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.389714307802273e-05, + "loss": 4.2336, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.388875713051221e-05, + "loss": 4.214, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.388037118300169e-05, + "loss": 4.235, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.387198523549117e-05, + "loss": 4.2306, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.3863599287980647e-05, + "loss": 4.2318, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.3855213340470127e-05, + "loss": 4.2168, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.3846827392959606e-05, + "loss": 4.232, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.3838457824252816e-05, + "loss": 4.2318, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.3830071876742296e-05, + "loss": 4.2381, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.3821685929231775e-05, + "loss": 4.2116, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.3813299981721255e-05, + "loss": 4.2273, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.3804930413014465e-05, + "loss": 4.222, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.3796544465503944e-05, + "loss": 4.213, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378817489679716e-05, + "loss": 4.2258, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.377978894928664e-05, + "loss": 4.2277, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.3771419380579856e-05, + "loss": 4.2236, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.3763033433069336e-05, + "loss": 4.2181, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.375464748555881e-05, + "loss": 4.2213, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 4.208026885986328, + "eval_runtime": 297.3865, + "eval_samples_per_second": 1283.148, + "eval_steps_per_second": 40.099, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.374626153804829e-05, + "loss": 4.2087, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.373787559053777e-05, + "loss": 4.2043, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.372948964302725e-05, + "loss": 4.226, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.372110369551673e-05, + "loss": 4.2183, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.371271774800621e-05, + "loss": 4.2232, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.370433180049569e-05, + "loss": 4.2172, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.369594585298517e-05, + "loss": 4.2141, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.368755990547465e-05, + "loss": 4.2069, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.367917395796413e-05, + "loss": 4.2139, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.3670804389257345e-05, + "loss": 4.216, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.3662434820550554e-05, + "loss": 4.2227, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.3654048873040034e-05, + "loss": 4.2239, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.3645662925529514e-05, + "loss": 4.2083, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.3637276978018994e-05, + "loss": 4.2114, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.3628891030508474e-05, + "loss": 4.2096, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.3620505082997954e-05, + "loss": 4.1955, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.3612119135487434e-05, + "loss": 4.2126, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.360374956678064e-05, + "loss": 4.2076, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.359536361927012e-05, + "loss": 4.2038, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.35869776717596e-05, + "loss": 4.2225, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.357859172424908e-05, + "loss": 4.2143, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.357020577673856e-05, + "loss": 4.2105, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.356183620803178e-05, + "loss": 4.215, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.355345026052126e-05, + "loss": 4.2224, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.354506431301074e-05, + "loss": 4.1979, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.353667836550022e-05, + "loss": 4.2081, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.352830879679343e-05, + "loss": 4.2145, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.3519939228086636e-05, + "loss": 4.2049, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.3511553280576116e-05, + "loss": 4.1958, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.3503167333065596e-05, + "loss": 4.1975, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.3494781385555076e-05, + "loss": 4.2115, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.3486395438044556e-05, + "loss": 4.2127, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.3478009490534036e-05, + "loss": 4.2101, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.3469623543023516e-05, + "loss": 4.2137, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.346125397431673e-05, + "loss": 4.2073, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.345286802680621e-05, + "loss": 4.2062, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.344448207929569e-05, + "loss": 4.2001, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.3436096131785165e-05, + "loss": 4.2033, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.3427710184274645e-05, + "loss": 4.1916, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.3419324236764125e-05, + "loss": 4.1989, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.341097104686107e-05, + "loss": 4.2001, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.340258509935055e-05, + "loss": 4.213, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.339419915184003e-05, + "loss": 4.2014, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.338581320432951e-05, + "loss": 4.2036, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.337742725681899e-05, + "loss": 4.2062, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.336904130930847e-05, + "loss": 4.1986, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.336065536179795e-05, + "loss": 4.2105, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.335226941428743e-05, + "loss": 4.1933, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.334388346677691e-05, + "loss": 4.1882, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.333549751926639e-05, + "loss": 4.2077, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.332711157175587e-05, + "loss": 4.2052, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.331872562424535e-05, + "loss": 4.1929, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.331033967673483e-05, + "loss": 4.1935, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.330197010802804e-05, + "loss": 4.1992, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.329360053932125e-05, + "loss": 4.1814, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.328521459181073e-05, + "loss": 4.2044, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.327682864430021e-05, + "loss": 4.1873, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.326844269678969e-05, + "loss": 4.191, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.326005674927917e-05, + "loss": 4.2012, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.3251670801768654e-05, + "loss": 4.1913, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.3243284854258134e-05, + "loss": 4.1898, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.3234898906747614e-05, + "loss": 4.1896, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.3226512959237094e-05, + "loss": 4.1808, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.32181433905303e-05, + "loss": 4.1892, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.320977382182351e-05, + "loss": 4.1975, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.320138787431299e-05, + "loss": 4.1913, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.319300192680247e-05, + "loss": 4.1867, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.318461597929195e-05, + "loss": 4.1791, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.317623003178143e-05, + "loss": 4.1797, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.316784408427091e-05, + "loss": 4.1952, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.315945813676039e-05, + "loss": 4.2, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.315107218924987e-05, + "loss": 4.1923, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.314270262054309e-05, + "loss": 4.1964, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.313431667303257e-05, + "loss": 4.2041, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.312593072552205e-05, + "loss": 4.2016, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.311756115681526e-05, + "loss": 4.1757, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.310917520930474e-05, + "loss": 4.1895, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.310078926179422e-05, + "loss": 4.1941, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.30924033142837e-05, + "loss": 4.1783, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.308401736677318e-05, + "loss": 4.1915, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.307563141926265e-05, + "loss": 4.1874, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.306724547175213e-05, + "loss": 4.1995, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.305885952424161e-05, + "loss": 4.1901, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.3050489955534826e-05, + "loss": 4.1716, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.3042104008024306e-05, + "loss": 4.1871, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.3033718060513786e-05, + "loss": 4.1868, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.3025332113003266e-05, + "loss": 4.1932, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.3016962544296475e-05, + "loss": 4.1869, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.300859297558969e-05, + "loss": 4.1896, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.300020702807917e-05, + "loss": 4.1881, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.299182108056865e-05, + "loss": 4.1805, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.2983435133058124e-05, + "loss": 4.1741, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.2975049185547604e-05, + "loss": 4.1799, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.2966663238037084e-05, + "loss": 4.1913, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.2958277290526564e-05, + "loss": 4.1849, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.2949891343016043e-05, + "loss": 4.1874, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.294152177430926e-05, + "loss": 4.1736, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.293313582679874e-05, + "loss": 4.1846, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.292474987928822e-05, + "loss": 4.192, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.29163639317777e-05, + "loss": 4.1913, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.290799436307091e-05, + "loss": 4.1801, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.289960841556039e-05, + "loss": 4.1786, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.289122246804987e-05, + "loss": 4.1765, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.288283652053935e-05, + "loss": 4.1878, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.287445057302883e-05, + "loss": 4.1584, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.286608100432204e-05, + "loss": 4.1796, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.285769505681152e-05, + "loss": 4.1722, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.2849309109301e-05, + "loss": 4.1847, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.284092316179048e-05, + "loss": 4.1678, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.2832537214279964e-05, + "loss": 4.1894, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.282416764557317e-05, + "loss": 4.1743, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.281578169806265e-05, + "loss": 4.1821, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.280739575055213e-05, + "loss": 4.174, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.279900980304161e-05, + "loss": 4.1672, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.279064023433482e-05, + "loss": 4.1837, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.27822542868243e-05, + "loss": 4.1896, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.277388471811751e-05, + "loss": 4.1838, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.276549877060699e-05, + "loss": 4.1706, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.275711282309647e-05, + "loss": 4.1762, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.274872687558595e-05, + "loss": 4.1827, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.274034092807543e-05, + "loss": 4.1691, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.273195498056492e-05, + "loss": 4.1802, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.27235690330544e-05, + "loss": 4.1668, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.2715199464347607e-05, + "loss": 4.1755, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.2706813516837087e-05, + "loss": 4.1767, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.2698427569326566e-05, + "loss": 4.1767, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.2690041621816046e-05, + "loss": 4.1539, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.2681672053109256e-05, + "loss": 4.1771, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.2673286105598735e-05, + "loss": 4.168, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.2664900158088215e-05, + "loss": 4.1836, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.2656514210577695e-05, + "loss": 4.1787, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.2648128263067175e-05, + "loss": 4.1802, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.2639742315556655e-05, + "loss": 4.1624, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.2631356368046135e-05, + "loss": 4.1831, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.2622970420535615e-05, + "loss": 4.1804, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.2614584473025095e-05, + "loss": 4.1795, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.2606198525514575e-05, + "loss": 4.171, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.2597812578004055e-05, + "loss": 4.1797, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.2589443009297264e-05, + "loss": 4.1808, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.2581057061786744e-05, + "loss": 4.184, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.2572671114276224e-05, + "loss": 4.1632, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.2564285166765704e-05, + "loss": 4.1768, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.2555899219255184e-05, + "loss": 4.1731, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.2547513271744664e-05, + "loss": 4.1637, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.253914370303787e-05, + "loss": 4.1776, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.253075775552735e-05, + "loss": 4.1726, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.252237180801684e-05, + "loss": 4.1796, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.251398586050632e-05, + "loss": 4.1651, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.25055999129958e-05, + "loss": 4.1709, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 4.1663994789123535, + "eval_runtime": 301.3955, + "eval_samples_per_second": 1266.081, + "eval_steps_per_second": 39.566, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.249721396548528e-05, + "loss": 4.1578, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.248882801797476e-05, + "loss": 4.1522, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.248044207046424e-05, + "loss": 4.1764, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.247205612295372e-05, + "loss": 4.1722, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.24636701754432e-05, + "loss": 4.1756, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.245528422793267e-05, + "loss": 4.1682, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.244689828042215e-05, + "loss": 4.1594, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.243851233291163e-05, + "loss": 4.1609, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.243012638540111e-05, + "loss": 4.1637, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.242174043789059e-05, + "loss": 4.1655, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.241335449038007e-05, + "loss": 4.1749, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.240496854286955e-05, + "loss": 4.177, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.239659897416277e-05, + "loss": 4.1614, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.238821302665225e-05, + "loss": 4.1604, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.237982707914173e-05, + "loss": 4.164, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.237144113163121e-05, + "loss": 4.1465, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.236305518412069e-05, + "loss": 4.1632, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.235466923661017e-05, + "loss": 4.1577, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.234628328909965e-05, + "loss": 4.1561, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233789734158913e-05, + "loss": 4.1736, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.232952777288234e-05, + "loss": 4.1666, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232114182537182e-05, + "loss": 4.166, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.23127558778613e-05, + "loss": 4.1645, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.230436993035078e-05, + "loss": 4.1724, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.229598398284026e-05, + "loss": 4.153, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.228759803532974e-05, + "loss": 4.1644, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.227921208781922e-05, + "loss": 4.1615, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.22708261403087e-05, + "loss": 4.1567, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.226247295040564e-05, + "loss": 4.1548, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.225408700289512e-05, + "loss": 4.1464, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.22457010553846e-05, + "loss": 4.167, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.223731510787408e-05, + "loss": 4.1637, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.222892916036356e-05, + "loss": 4.1621, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.2220543212853035e-05, + "loss": 4.1679, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.2212157265342515e-05, + "loss": 4.1579, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.2203771317831995e-05, + "loss": 4.1618, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.2195385370321475e-05, + "loss": 4.1564, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.2186999422810955e-05, + "loss": 4.1514, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.217861347530044e-05, + "loss": 4.1449, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.217022752778992e-05, + "loss": 4.1507, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.216187433788686e-05, + "loss": 4.1555, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.215348839037634e-05, + "loss": 4.1664, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.214510244286582e-05, + "loss": 4.155, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.21367164953553e-05, + "loss": 4.153, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.212833054784478e-05, + "loss": 4.1638, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.211994460033426e-05, + "loss": 4.1531, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.211155865282374e-05, + "loss": 4.1639, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.210317270531322e-05, + "loss": 4.1495, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.20947867578027e-05, + "loss": 4.1382, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208640081029218e-05, + "loss": 4.1627, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.207801486278166e-05, + "loss": 4.157, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.206962891527114e-05, + "loss": 4.1528, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.2061242967760626e-05, + "loss": 4.1446, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.2052873399053835e-05, + "loss": 4.1549, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.2044487451543315e-05, + "loss": 4.1344, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.2036101504032795e-05, + "loss": 4.1578, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.2027715556522275e-05, + "loss": 4.1426, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.2019345987815484e-05, + "loss": 4.1432, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.2010960040304964e-05, + "loss": 4.1573, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.2002574092794444e-05, + "loss": 4.1424, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.1994188145283924e-05, + "loss": 4.1433, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.19858021977734e-05, + "loss": 4.1479, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.197743262906661e-05, + "loss": 4.1326, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.196904668155609e-05, + "loss": 4.1453, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.196066073404557e-05, + "loss": 4.1507, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195227478653505e-05, + "loss": 4.1454, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.194390521782827e-05, + "loss": 4.1409, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.193551927031775e-05, + "loss": 4.1359, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.192713332280722e-05, + "loss": 4.1319, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.191876375410044e-05, + "loss": 4.1474, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.191037780658992e-05, + "loss": 4.156, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.19019918590794e-05, + "loss": 4.1454, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.189360591156887e-05, + "loss": 4.1521, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.188521996405835e-05, + "loss": 4.1541, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.187683401654783e-05, + "loss": 4.1592, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.1868464447841046e-05, + "loss": 4.1343, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.1860078500330526e-05, + "loss": 4.1475, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.1851692552820006e-05, + "loss": 4.1491, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.1843306605309486e-05, + "loss": 4.1296, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.1834920657798966e-05, + "loss": 4.1516, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.1826534710288446e-05, + "loss": 4.1446, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.1818165141581655e-05, + "loss": 4.1509, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.1809779194071135e-05, + "loss": 4.1482, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.1801393246560615e-05, + "loss": 4.1288, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.1793007299050095e-05, + "loss": 4.1405, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.1784621351539575e-05, + "loss": 4.1414, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.1776235404029055e-05, + "loss": 4.1467, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.1767865835322264e-05, + "loss": 4.1418, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.175947988781175e-05, + "loss": 4.1493, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.175109394030123e-05, + "loss": 4.1446, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.174270799279071e-05, + "loss": 4.1388, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.173433842408392e-05, + "loss": 4.1326, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.17259524765734e-05, + "loss": 4.135, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.171758290786661e-05, + "loss": 4.1502, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170919696035609e-05, + "loss": 4.1433, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.170081101284557e-05, + "loss": 4.1421, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.169242506533505e-05, + "loss": 4.1306, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.168403911782453e-05, + "loss": 4.1402, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.167565317031401e-05, + "loss": 4.1481, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.166726722280349e-05, + "loss": 4.1464, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.165888127529297e-05, + "loss": 4.1389, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.165049532778245e-05, + "loss": 4.1354, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.1642109380271935e-05, + "loss": 4.1362, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.163372343276141e-05, + "loss": 4.1434, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.162533748525089e-05, + "loss": 4.118, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.1616967916544104e-05, + "loss": 4.1321, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.160859834783731e-05, + "loss": 4.1307, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160021240032679e-05, + "loss": 4.1427, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.159182645281627e-05, + "loss": 4.129, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.158344050530575e-05, + "loss": 4.1451, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.1575054557795226e-05, + "loss": 4.1332, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.1566668610284706e-05, + "loss": 4.1382, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.1558282662774186e-05, + "loss": 4.1366, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.154989671526367e-05, + "loss": 4.1213, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154152714655688e-05, + "loss": 4.1399, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153314119904636e-05, + "loss": 4.149, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152475525153584e-05, + "loss": 4.1412, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151638568282906e-05, + "loss": 4.1372, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.150799973531853e-05, + "loss": 4.1251, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.149961378780801e-05, + "loss": 4.1424, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.149122784029749e-05, + "loss": 4.136, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.14828582715907e-05, + "loss": 4.1348, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.147447232408018e-05, + "loss": 4.1246, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.146608637656966e-05, + "loss": 4.1349, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.145770042905914e-05, + "loss": 4.1377, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.144931448154863e-05, + "loss": 4.1342, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.144092853403811e-05, + "loss": 4.1126, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.1432542586527587e-05, + "loss": 4.1386, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.1424156639017067e-05, + "loss": 4.123, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.1415770691506546e-05, + "loss": 4.1444, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.1407401122799756e-05, + "loss": 4.1345, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.1399015175289236e-05, + "loss": 4.1398, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.1390645606582445e-05, + "loss": 4.1201, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.1382259659071925e-05, + "loss": 4.1439, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.1373873711561405e-05, + "loss": 4.1371, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.1365487764050885e-05, + "loss": 4.1393, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.1357101816540364e-05, + "loss": 4.1259, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.1348715869029844e-05, + "loss": 4.1379, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.1340329921519324e-05, + "loss": 4.139, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.1331943974008804e-05, + "loss": 4.1434, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.132355802649829e-05, + "loss": 4.1237, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.13151884577915e-05, + "loss": 4.1353, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.130680251028098e-05, + "loss": 4.136, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.129841656277046e-05, + "loss": 4.1251, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.129003061525994e-05, + "loss": 4.132, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128166104655315e-05, + "loss": 4.1331, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.127327509904263e-05, + "loss": 4.1373, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.126490553033584e-05, + "loss": 4.1271, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125651958282532e-05, + "loss": 4.1309, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 4.134402751922607, + "eval_runtime": 292.8336, + "eval_samples_per_second": 1303.098, + "eval_steps_per_second": 40.723, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.12481336353148e-05, + "loss": 4.1221, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.123974768780428e-05, + "loss": 4.1122, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.123136174029376e-05, + "loss": 4.1346, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.1222975792783245e-05, + "loss": 4.1304, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.1214606224076454e-05, + "loss": 4.1315, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.120623665536966e-05, + "loss": 4.1308, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.119785070785914e-05, + "loss": 4.1223, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.118946476034862e-05, + "loss": 4.1202, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.11810788128381e-05, + "loss": 4.1258, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.117269286532758e-05, + "loss": 4.1247, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.116430691781706e-05, + "loss": 4.1336, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.1155920970306536e-05, + "loss": 4.1363, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.114756778040348e-05, + "loss": 4.124, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.113918183289297e-05, + "loss": 4.1242, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.113079588538245e-05, + "loss": 4.1219, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.112240993787193e-05, + "loss": 4.1044, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.111402399036141e-05, + "loss": 4.1252, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.110563804285089e-05, + "loss": 4.1184, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.109725209534036e-05, + "loss": 4.1215, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.108886614782984e-05, + "loss": 4.1305, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.1080496579123056e-05, + "loss": 4.1313, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.1072110631612536e-05, + "loss": 4.1254, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.106372468410201e-05, + "loss": 4.1262, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.105533873659149e-05, + "loss": 4.1328, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.104695278908097e-05, + "loss": 4.1156, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.103856684157045e-05, + "loss": 4.1244, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.1030180894059936e-05, + "loss": 4.1247, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.1021794946549416e-05, + "loss": 4.1194, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.1013408999038896e-05, + "loss": 4.114, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.1005023051528376e-05, + "loss": 4.112, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.0996637104017856e-05, + "loss": 4.1232, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.0988251156507336e-05, + "loss": 4.1294, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.0979865208996816e-05, + "loss": 4.1236, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.0971479261486296e-05, + "loss": 4.1289, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.0963093313975776e-05, + "loss": 4.1167, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.0954723745268985e-05, + "loss": 4.1253, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.0946337797758465e-05, + "loss": 4.1241, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.0937951850247945e-05, + "loss": 4.1092, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.0929565902737425e-05, + "loss": 4.1125, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.0921196334030634e-05, + "loss": 4.1123, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.091281038652012e-05, + "loss": 4.1167, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.09044244390096e-05, + "loss": 4.1299, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.089603849149908e-05, + "loss": 4.1145, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.088766892279229e-05, + "loss": 4.1123, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.087928297528177e-05, + "loss": 4.1288, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.087089702777125e-05, + "loss": 4.1178, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.086251108026072e-05, + "loss": 4.1269, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.08541251327502e-05, + "loss": 4.1119, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.084573918523968e-05, + "loss": 4.1005, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.083735323772916e-05, + "loss": 4.1314, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.082898366902237e-05, + "loss": 4.1168, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.082059772151186e-05, + "loss": 4.1154, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.081221177400134e-05, + "loss": 4.1115, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.080382582649082e-05, + "loss": 4.1103, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.07954398789803e-05, + "loss": 4.1046, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.078707031027351e-05, + "loss": 4.1141, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.077870074156672e-05, + "loss": 4.1076, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.0770314794056196e-05, + "loss": 4.1101, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.0761928846545676e-05, + "loss": 4.1204, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.0753542899035156e-05, + "loss": 4.1078, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.0745156951524636e-05, + "loss": 4.1039, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.0736771004014116e-05, + "loss": 4.1169, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.0728385056503596e-05, + "loss": 4.0952, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.0719999108993076e-05, + "loss": 4.109, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.0711613161482556e-05, + "loss": 4.1111, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.0703227213972036e-05, + "loss": 4.1124, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.069484126646152e-05, + "loss": 4.1036, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.068647169775473e-05, + "loss": 4.1031, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.067808575024421e-05, + "loss": 4.093, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.066969980273369e-05, + "loss": 4.1133, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.06613302340269e-05, + "loss": 4.1199, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.065294428651638e-05, + "loss": 4.112, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.064455833900586e-05, + "loss": 4.1125, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.063617239149534e-05, + "loss": 4.1197, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.062778644398482e-05, + "loss": 4.1257, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.061941687527803e-05, + "loss": 4.0955, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.061103092776751e-05, + "loss": 4.1139, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.060264498025699e-05, + "loss": 4.1161, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.0594259032746476e-05, + "loss": 4.0919, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.0585873085235956e-05, + "loss": 4.1192, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.0577487137725436e-05, + "loss": 4.1057, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.056910119021491e-05, + "loss": 4.1183, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.056071524270439e-05, + "loss": 4.1136, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.0552345673997605e-05, + "loss": 4.0951, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.0543959726487085e-05, + "loss": 4.1025, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.053557377897656e-05, + "loss": 4.1121, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.052718783146604e-05, + "loss": 4.1107, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.051880188395552e-05, + "loss": 4.1083, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.0510432315248734e-05, + "loss": 4.1133, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.0502046367738214e-05, + "loss": 4.109, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.0493660420227694e-05, + "loss": 4.1038, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.0485274472717174e-05, + "loss": 4.1036, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.0476888525206654e-05, + "loss": 4.0993, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.0468502577696134e-05, + "loss": 4.1139, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.0460116630185614e-05, + "loss": 4.1082, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.045174706147882e-05, + "loss": 4.1133, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.04433611139683e-05, + "loss": 4.0926, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.043497516645778e-05, + "loss": 4.1053, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.042660559775099e-05, + "loss": 4.1158, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.041821965024047e-05, + "loss": 4.1134, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.040983370272995e-05, + "loss": 4.1047, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.040144775521943e-05, + "loss": 4.1002, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.039306180770891e-05, + "loss": 4.1046, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.03846758601984e-05, + "loss": 4.1085, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.037628991268788e-05, + "loss": 4.0839, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.036792034398109e-05, + "loss": 4.1047, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.035953439647057e-05, + "loss": 4.0927, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.035114844896005e-05, + "loss": 4.1113, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.034276250144953e-05, + "loss": 4.097, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.033437655393901e-05, + "loss": 4.1052, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.032599060642849e-05, + "loss": 4.1001, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.031760465891797e-05, + "loss": 4.1084, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.030921871140745e-05, + "loss": 4.1011, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.030083276389692e-05, + "loss": 4.0893, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.02924468163864e-05, + "loss": 4.1073, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.0284077247679616e-05, + "loss": 4.1132, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.0275691300169096e-05, + "loss": 4.106, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.0267305352658576e-05, + "loss": 4.1061, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.0258919405148056e-05, + "loss": 4.0908, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.0250533457637536e-05, + "loss": 4.1061, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.0242147510127016e-05, + "loss": 4.1073, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.0233761562616496e-05, + "loss": 4.0944, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.0225375615105976e-05, + "loss": 4.096, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.0216989667595456e-05, + "loss": 4.1001, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.0208620098888665e-05, + "loss": 4.106, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.0200234151378145e-05, + "loss": 4.0995, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.0191848203867625e-05, + "loss": 4.08, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.0183462256357105e-05, + "loss": 4.1075, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.0175092687650314e-05, + "loss": 4.0896, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.01667067401398e-05, + "loss": 4.1098, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.015833717143301e-05, + "loss": 4.1031, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.014995122392249e-05, + "loss": 4.1062, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.014156527641197e-05, + "loss": 4.0881, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.013317932890145e-05, + "loss": 4.1143, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.012479338139093e-05, + "loss": 4.1053, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.011640743388041e-05, + "loss": 4.1041, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.010802148636989e-05, + "loss": 4.0998, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.009963553885937e-05, + "loss": 4.1011, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.009126597015258e-05, + "loss": 4.1057, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.008288002264206e-05, + "loss": 4.1138, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.007449407513154e-05, + "loss": 4.0923, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.006610812762102e-05, + "loss": 4.1031, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.00577221801105e-05, + "loss": 4.1072, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.0049352611403714e-05, + "loss": 4.0927, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.0040966663893194e-05, + "loss": 4.0953, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.0032580716382674e-05, + "loss": 4.1008, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.0024194768872154e-05, + "loss": 4.1062, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.0015808821361634e-05, + "loss": 4.0941, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.0007439252654843e-05, + "loss": 4.0996, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 4.109890937805176, + "eval_runtime": 292.6363, + "eval_samples_per_second": 1303.977, + "eval_steps_per_second": 40.75, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.999905330514432e-05, + "loss": 4.0835, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.99906673576338e-05, + "loss": 4.0844, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.998228141012328e-05, + "loss": 4.0981, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.9973895462612756e-05, + "loss": 4.0974, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.9965509515102236e-05, + "loss": 4.1051, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.995712356759172e-05, + "loss": 4.0957, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.99487376200812e-05, + "loss": 4.0935, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.994035167257068e-05, + "loss": 4.092, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.993196572506016e-05, + "loss": 4.0908, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.992357977754964e-05, + "loss": 4.0954, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.991519383003912e-05, + "loss": 4.101, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.99068078825286e-05, + "loss": 4.1018, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.989843831382181e-05, + "loss": 4.093, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.989005236631129e-05, + "loss": 4.0944, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.988166641880077e-05, + "loss": 4.0916, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.987328047129025e-05, + "loss": 4.0738, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.986489452377973e-05, + "loss": 4.0906, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.985650857626921e-05, + "loss": 4.0896, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.984812262875869e-05, + "loss": 4.0919, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.983973668124817e-05, + "loss": 4.0962, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.983136711254139e-05, + "loss": 4.1016, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.982298116503087e-05, + "loss": 4.0954, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.981459521752035e-05, + "loss": 4.0948, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.980620927000982e-05, + "loss": 4.098, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.97978233224993e-05, + "loss": 4.0878, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.978943737498878e-05, + "loss": 4.0932, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.978105142747826e-05, + "loss": 4.0927, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.977266547996774e-05, + "loss": 4.0887, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.976429591126095e-05, + "loss": 4.0879, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.9755926342554165e-05, + "loss": 4.0787, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.9747540395043645e-05, + "loss": 4.0898, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.9739154447533125e-05, + "loss": 4.0988, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.9730768500022605e-05, + "loss": 4.0938, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.9722382552512085e-05, + "loss": 4.094, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.9713996605001565e-05, + "loss": 4.0857, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.9705610657491045e-05, + "loss": 4.0977, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.9697224709980525e-05, + "loss": 4.0939, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.9688855141273734e-05, + "loss": 4.082, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.9680469193763214e-05, + "loss": 4.0833, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.9672083246252694e-05, + "loss": 4.0797, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.9663697298742174e-05, + "loss": 4.0835, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.965532773003538e-05, + "loss": 4.1009, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964694178252486e-05, + "loss": 4.0867, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.963855583501434e-05, + "loss": 4.0845, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.963016988750382e-05, + "loss": 4.0957, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.962180031879704e-05, + "loss": 4.0853, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.961341437128652e-05, + "loss": 4.0983, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.9605028423776e-05, + "loss": 4.0855, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.959664247626548e-05, + "loss": 4.0623, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958827290755869e-05, + "loss": 4.1041, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.957988696004817e-05, + "loss": 4.0876, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.957150101253765e-05, + "loss": 4.089, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.956311506502713e-05, + "loss": 4.0812, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.955472911751661e-05, + "loss": 4.0771, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.954635954880982e-05, + "loss": 4.08, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.95379736012993e-05, + "loss": 4.0844, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.952958765378878e-05, + "loss": 4.078, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.9521201706278263e-05, + "loss": 4.0786, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.951283213757147e-05, + "loss": 4.0918, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.950444619006095e-05, + "loss": 4.0772, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.949606024255043e-05, + "loss": 4.0714, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.948767429503991e-05, + "loss": 4.0911, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.947930472633312e-05, + "loss": 4.0647, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.94709187788226e-05, + "loss": 4.0731, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.946254921011581e-05, + "loss": 4.0881, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.945416326260529e-05, + "loss": 4.0833, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.944577731509477e-05, + "loss": 4.0711, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.943739136758425e-05, + "loss": 4.0767, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.942900542007373e-05, + "loss": 4.0648, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.9420635851366946e-05, + "loss": 4.0831, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.9412249903856426e-05, + "loss": 4.0895, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.9403863956345906e-05, + "loss": 4.0815, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.9395478008835386e-05, + "loss": 4.08, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.9387092061324866e-05, + "loss": 4.0918, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.9378706113814346e-05, + "loss": 4.0961, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.9370320166303826e-05, + "loss": 4.0676, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.9361934218793306e-05, + "loss": 4.0867, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.9353564650086515e-05, + "loss": 4.0823, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.9345178702575995e-05, + "loss": 4.0658, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.9336792755065475e-05, + "loss": 4.086, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.9328423186358684e-05, + "loss": 4.0798, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.932003723884817e-05, + "loss": 4.0905, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.931165129133765e-05, + "loss": 4.0836, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.930326534382713e-05, + "loss": 4.0681, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.9294879396316604e-05, + "loss": 4.072, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.9286493448806084e-05, + "loss": 4.085, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.9278107501295564e-05, + "loss": 4.0788, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.9269721553785044e-05, + "loss": 4.0835, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.926136836388199e-05, + "loss": 4.0806, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.92529987951752e-05, + "loss": 4.0753, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.924461284766468e-05, + "loss": 4.0774, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923622690015416e-05, + "loss": 4.0722, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.922784095264364e-05, + "loss": 4.0708, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.9219455005133124e-05, + "loss": 4.0851, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.9211069057622604e-05, + "loss": 4.077, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.920268311011208e-05, + "loss": 4.0849, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.919429716260156e-05, + "loss": 4.0643, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.918591121509104e-05, + "loss": 4.0758, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.917752526758052e-05, + "loss": 4.0871, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.916913932007e-05, + "loss": 4.0808, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.9160769751363206e-05, + "loss": 4.076, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.9152383803852686e-05, + "loss": 4.0729, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.9143997856342166e-05, + "loss": 4.0775, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.9135611908831646e-05, + "loss": 4.076, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.9127225961321126e-05, + "loss": 4.0627, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.9118840013810606e-05, + "loss": 4.073, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.9110454066300086e-05, + "loss": 4.0649, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.910206811878957e-05, + "loss": 4.0817, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.909369855008278e-05, + "loss": 4.0683, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.908531260257226e-05, + "loss": 4.0757, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.907692665506174e-05, + "loss": 4.0678, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.906854070755122e-05, + "loss": 4.0841, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.90601547600407e-05, + "loss": 4.071, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.905178519133391e-05, + "loss": 4.0608, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.904339924382339e-05, + "loss": 4.0815, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.90350296751166e-05, + "loss": 4.0855, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.902664372760608e-05, + "loss": 4.0777, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.901825778009556e-05, + "loss": 4.0775, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.900987183258504e-05, + "loss": 4.0643, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.9001485885074527e-05, + "loss": 4.0765, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.8993099937564007e-05, + "loss": 4.0789, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.8984713990053487e-05, + "loss": 4.0685, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.8976328042542966e-05, + "loss": 4.0658, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.8967958473836176e-05, + "loss": 4.0747, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.8959588905129385e-05, + "loss": 4.078, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.8951202957618865e-05, + "loss": 4.0739, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.8942817010108345e-05, + "loss": 4.0542, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.8934431062597825e-05, + "loss": 4.0776, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.8926045115087304e-05, + "loss": 4.0629, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.8917659167576784e-05, + "loss": 4.081, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.8909289598869994e-05, + "loss": 4.078, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.890090365135948e-05, + "loss": 4.0785, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.889251770384896e-05, + "loss": 4.0588, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.888413175633844e-05, + "loss": 4.0854, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.887574580882791e-05, + "loss": 4.0756, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.886737624012113e-05, + "loss": 4.0798, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.885899029261061e-05, + "loss": 4.0739, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.885060434510009e-05, + "loss": 4.0695, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.884221839758956e-05, + "loss": 4.0763, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.883384882888278e-05, + "loss": 4.0867, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.882546288137226e-05, + "loss": 4.0641, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.881707693386173e-05, + "loss": 4.0761, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.880869098635122e-05, + "loss": 4.0793, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.88003050388407e-05, + "loss": 4.064, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.879191909133018e-05, + "loss": 4.0699, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.878353314381966e-05, + "loss": 4.0732, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.877514719630914e-05, + "loss": 4.0789, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.876677762760235e-05, + "loss": 4.0725, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.875839168009183e-05, + "loss": 4.0726, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 4.090142250061035, + "eval_runtime": 296.3674, + "eval_samples_per_second": 1287.561, + "eval_steps_per_second": 40.237, + "step": 686880 + }, + { + "epoch": 0.0, + "learning_rate": 3.875000573258131e-05, + "loss": 4.0557, + "step": 687104 + }, + { + "epoch": 0.0, + "learning_rate": 3.874161978507079e-05, + "loss": 4.0576, + "step": 687616 + }, + { + "epoch": 0.0, + "learning_rate": 3.873323383756027e-05, + "loss": 4.071, + "step": 688128 + }, + { + "epoch": 0.0, + "learning_rate": 3.872484789004975e-05, + "loss": 4.074, + "step": 688640 + }, + { + "epoch": 0.0, + "learning_rate": 3.871646194253923e-05, + "loss": 4.0769, + "step": 689152 + }, + { + "epoch": 0.0, + "learning_rate": 3.870807599502871e-05, + "loss": 4.0668, + "step": 689664 + }, + { + "epoch": 0.0, + "learning_rate": 3.869969004751819e-05, + "loss": 4.0691, + "step": 690176 + }, + { + "epoch": 0.0, + "learning_rate": 3.8691304100007667e-05, + "loss": 4.0626, + "step": 690688 + }, + { + "epoch": 0.0, + "learning_rate": 3.8682918152497147e-05, + "loss": 4.0616, + "step": 691200 + }, + { + "epoch": 0.0, + "learning_rate": 3.8674532204986626e-05, + "loss": 4.0699, + "step": 691712 + }, + { + "epoch": 0.0, + "learning_rate": 3.8666146257476106e-05, + "loss": 4.0753, + "step": 692224 + }, + { + "epoch": 0.0, + "learning_rate": 3.8657760309965586e-05, + "loss": 4.0744, + "step": 692736 + }, + { + "epoch": 0.0, + "learning_rate": 3.86493907412588e-05, + "loss": 4.0753, + "step": 693248 + }, + { + "epoch": 0.0, + "learning_rate": 3.8641004793748275e-05, + "loss": 4.0625, + "step": 693760 + }, + { + "epoch": 0.0, + "learning_rate": 3.8632618846237755e-05, + "loss": 4.0639, + "step": 694272 + }, + { + "epoch": 0.0, + "learning_rate": 3.8624232898727235e-05, + "loss": 4.051, + "step": 694784 + }, + { + "epoch": 0.0, + "learning_rate": 3.8615846951216715e-05, + "loss": 4.0632, + "step": 695296 + }, + { + "epoch": 0.0, + "learning_rate": 3.8607461003706195e-05, + "loss": 4.0649, + "step": 695808 + }, + { + "epoch": 0.0, + "learning_rate": 3.8599075056195675e-05, + "loss": 4.0627, + "step": 696320 + }, + { + "epoch": 0.0, + "learning_rate": 3.8590689108685155e-05, + "loss": 4.069, + "step": 696832 + }, + { + "epoch": 0.0, + "learning_rate": 3.858231953997837e-05, + "loss": 4.077, + "step": 697344 + }, + { + "epoch": 0.0, + "learning_rate": 3.857393359246785e-05, + "loss": 4.0709, + "step": 697856 + }, + { + "epoch": 0.0, + "learning_rate": 3.856554764495733e-05, + "loss": 4.0678, + "step": 698368 + }, + { + "epoch": 0.0, + "learning_rate": 3.855716169744681e-05, + "loss": 4.0689, + "step": 698880 + }, + { + "epoch": 0.0, + "learning_rate": 3.854877574993629e-05, + "loss": 4.0633, + "step": 699392 + }, + { + "epoch": 0.0, + "learning_rate": 3.85404061812295e-05, + "loss": 4.0668, + "step": 699904 + }, + { + "epoch": 0.0, + "learning_rate": 3.853202023371898e-05, + "loss": 4.0667, + "step": 700416 + }, + { + "epoch": 0.0, + "learning_rate": 3.852363428620846e-05, + "loss": 4.0671, + "step": 700928 + }, + { + "epoch": 0.0, + "learning_rate": 3.851524833869794e-05, + "loss": 4.0596, + "step": 701440 + }, + { + "epoch": 0.0, + "learning_rate": 3.850686239118742e-05, + "loss": 4.0566, + "step": 701952 + }, + { + "epoch": 0.01, + "learning_rate": 3.84984764436769e-05, + "loss": 4.0609, + "step": 702464 + }, + { + "epoch": 0.01, + "learning_rate": 3.849009049616638e-05, + "loss": 4.0719, + "step": 702976 + }, + { + "epoch": 0.01, + "learning_rate": 3.848170454865586e-05, + "loss": 4.072, + "step": 703488 + }, + { + "epoch": 0.01, + "learning_rate": 3.847333497994907e-05, + "loss": 4.0697, + "step": 704000 + }, + { + "epoch": 0.01, + "learning_rate": 3.846494903243855e-05, + "loss": 4.0582, + "step": 704512 + }, + { + "epoch": 0.01, + "learning_rate": 3.8456563084928035e-05, + "loss": 4.067, + "step": 705024 + }, + { + "epoch": 0.01, + "learning_rate": 3.8448177137417515e-05, + "loss": 4.0726, + "step": 705536 + }, + { + "epoch": 0.01, + "learning_rate": 3.8439807568710724e-05, + "loss": 4.0544, + "step": 706048 + }, + { + "epoch": 0.01, + "learning_rate": 3.8431421621200204e-05, + "loss": 4.0578, + "step": 706560 + }, + { + "epoch": 0.01, + "learning_rate": 3.8423052052493414e-05, + "loss": 4.0513, + "step": 707072 + }, + { + "epoch": 0.01, + "learning_rate": 3.8414666104982894e-05, + "loss": 4.0576, + "step": 707584 + }, + { + "epoch": 0.01, + "learning_rate": 3.8406280157472373e-05, + "loss": 4.073, + "step": 708096 + }, + { + "epoch": 0.01, + "learning_rate": 3.8397894209961853e-05, + "loss": 4.0627, + "step": 708608 + }, + { + "epoch": 0.01, + "learning_rate": 3.838952464125506e-05, + "loss": 4.0581, + "step": 709120 + }, + { + "epoch": 0.01, + "learning_rate": 3.838113869374454e-05, + "loss": 4.072, + "step": 709632 + }, + { + "epoch": 0.01, + "learning_rate": 3.837275274623402e-05, + "loss": 4.0598, + "step": 710144 + }, + { + "epoch": 0.01, + "learning_rate": 3.83643667987235e-05, + "loss": 4.0677, + "step": 710656 + }, + { + "epoch": 0.01, + "learning_rate": 3.835598085121299e-05, + "loss": 4.0664, + "step": 711168 + }, + { + "epoch": 0.01, + "learning_rate": 3.834759490370246e-05, + "loss": 4.0342, + "step": 711680 + }, + { + "epoch": 0.01, + "learning_rate": 3.833922533499568e-05, + "loss": 4.0817, + "step": 712192 + }, + { + "epoch": 0.01, + "learning_rate": 3.833083938748516e-05, + "loss": 4.058, + "step": 712704 + }, + { + "epoch": 0.01, + "learning_rate": 3.832245343997464e-05, + "loss": 4.0702, + "step": 713216 + }, + { + "epoch": 0.01, + "learning_rate": 3.831406749246411e-05, + "loss": 4.0494, + "step": 713728 + }, + { + "epoch": 0.01, + "learning_rate": 3.830568154495359e-05, + "loss": 4.0552, + "step": 714240 + }, + { + "epoch": 0.01, + "learning_rate": 3.829729559744307e-05, + "loss": 4.0529, + "step": 714752 + }, + { + "epoch": 0.01, + "learning_rate": 3.828890964993255e-05, + "loss": 4.0553, + "step": 715264 + }, + { + "epoch": 0.01, + "learning_rate": 3.828052370242203e-05, + "loss": 4.0535, + "step": 715776 + }, + { + "epoch": 0.01, + "learning_rate": 3.827215413371524e-05, + "loss": 4.0511, + "step": 716288 + }, + { + "epoch": 0.01, + "learning_rate": 3.826376818620473e-05, + "loss": 4.071, + "step": 716800 + }, + { + "epoch": 0.01, + "learning_rate": 3.825538223869421e-05, + "loss": 4.0524, + "step": 717312 + }, + { + "epoch": 0.01, + "learning_rate": 3.824699629118369e-05, + "loss": 4.0462, + "step": 717824 + }, + { + "epoch": 0.01, + "learning_rate": 3.8238626722476896e-05, + "loss": 4.0657, + "step": 718336 + }, + { + "epoch": 0.01, + "learning_rate": 3.8230240774966376e-05, + "loss": 4.0421, + "step": 718848 + }, + { + "epoch": 0.01, + "learning_rate": 3.8221871206259585e-05, + "loss": 4.0466, + "step": 719360 + }, + { + "epoch": 0.01, + "learning_rate": 3.8213485258749065e-05, + "loss": 4.062, + "step": 719872 + }, + { + "epoch": 0.01, + "learning_rate": 3.8205099311238545e-05, + "loss": 4.0563, + "step": 720384 + }, + { + "epoch": 0.01, + "learning_rate": 3.8196713363728025e-05, + "loss": 4.0498, + "step": 720896 + }, + { + "epoch": 0.01, + "learning_rate": 3.8188327416217505e-05, + "loss": 4.0481, + "step": 721408 + }, + { + "epoch": 0.01, + "learning_rate": 3.8179941468706985e-05, + "loss": 4.0442, + "step": 721920 + }, + { + "epoch": 0.01, + "learning_rate": 3.8171555521196465e-05, + "loss": 4.0578, + "step": 722432 + }, + { + "epoch": 0.01, + "learning_rate": 3.816318595248968e-05, + "loss": 4.0657, + "step": 722944 + }, + { + "epoch": 0.01, + "learning_rate": 3.815480000497916e-05, + "loss": 4.0548, + "step": 723456 + }, + { + "epoch": 0.01, + "learning_rate": 3.814641405746864e-05, + "loss": 4.0581, + "step": 723968 + }, + { + "epoch": 0.01, + "learning_rate": 3.813802810995812e-05, + "loss": 4.0644, + "step": 724480 + }, + { + "epoch": 0.01, + "learning_rate": 3.81296421624476e-05, + "loss": 4.0731, + "step": 724992 + }, + { + "epoch": 0.01, + "learning_rate": 3.812127259374081e-05, + "loss": 4.0411, + "step": 725504 + }, + { + "epoch": 0.01, + "learning_rate": 3.811288664623029e-05, + "loss": 4.0631, + "step": 726016 + }, + { + "epoch": 0.01, + "learning_rate": 3.810450069871977e-05, + "loss": 4.0549, + "step": 726528 + }, + { + "epoch": 0.01, + "learning_rate": 3.809611475120925e-05, + "loss": 4.0443, + "step": 727040 + }, + { + "epoch": 0.01, + "learning_rate": 3.808772880369873e-05, + "loss": 4.0564, + "step": 727552 + }, + { + "epoch": 0.01, + "learning_rate": 3.807934285618821e-05, + "loss": 4.0636, + "step": 728064 + }, + { + "epoch": 0.01, + "learning_rate": 3.807095690867769e-05, + "loss": 4.0619, + "step": 728576 + }, + { + "epoch": 0.01, + "learning_rate": 3.806257096116717e-05, + "loss": 4.064, + "step": 729088 + }, + { + "epoch": 0.01, + "learning_rate": 3.805418501365665e-05, + "loss": 4.041, + "step": 729600 + }, + { + "epoch": 0.01, + "learning_rate": 3.8045831823753594e-05, + "loss": 4.0451, + "step": 730112 + }, + { + "epoch": 0.01, + "learning_rate": 3.8037445876243074e-05, + "loss": 4.0625, + "step": 730624 + }, + { + "epoch": 0.01, + "learning_rate": 3.8029059928732554e-05, + "loss": 4.0509, + "step": 731136 + }, + { + "epoch": 0.01, + "learning_rate": 3.8020673981222034e-05, + "loss": 4.0577, + "step": 731648 + }, + { + "epoch": 0.01, + "learning_rate": 3.801230441251524e-05, + "loss": 4.0611, + "step": 732160 + }, + { + "epoch": 0.02, + "learning_rate": 3.800391846500472e-05, + "loss": 4.0522, + "step": 732672 + }, + { + "epoch": 0.02, + "learning_rate": 3.79955325174942e-05, + "loss": 4.0527, + "step": 733184 + }, + { + "epoch": 0.02, + "learning_rate": 3.798714656998368e-05, + "loss": 4.0516, + "step": 733696 + }, + { + "epoch": 0.02, + "learning_rate": 3.797876062247316e-05, + "loss": 4.0453, + "step": 734208 + }, + { + "epoch": 0.02, + "learning_rate": 3.797037467496264e-05, + "loss": 4.0619, + "step": 734720 + }, + { + "epoch": 0.02, + "learning_rate": 3.7961988727452116e-05, + "loss": 4.0551, + "step": 735232 + }, + { + "epoch": 0.02, + "learning_rate": 3.7953602779941596e-05, + "loss": 4.0569, + "step": 735744 + }, + { + "epoch": 0.02, + "learning_rate": 3.794523321123481e-05, + "loss": 4.0475, + "step": 736256 + }, + { + "epoch": 0.02, + "learning_rate": 3.79368472637243e-05, + "loss": 4.0465, + "step": 736768 + }, + { + "epoch": 0.02, + "learning_rate": 3.792846131621377e-05, + "loss": 4.0622, + "step": 737280 + }, + { + "epoch": 0.02, + "learning_rate": 3.792007536870325e-05, + "loss": 4.0583, + "step": 737792 + }, + { + "epoch": 0.02, + "learning_rate": 3.791168942119273e-05, + "loss": 4.0543, + "step": 738304 + }, + { + "epoch": 0.02, + "learning_rate": 3.790331985248594e-05, + "loss": 4.051, + "step": 738816 + }, + { + "epoch": 0.02, + "learning_rate": 3.789493390497542e-05, + "loss": 4.0537, + "step": 739328 + }, + { + "epoch": 0.02, + "learning_rate": 3.78865479574649e-05, + "loss": 4.0462, + "step": 739840 + }, + { + "epoch": 0.02, + "learning_rate": 3.787816200995438e-05, + "loss": 4.0469, + "step": 740352 + }, + { + "epoch": 0.02, + "learning_rate": 3.786979244124759e-05, + "loss": 4.0453, + "step": 740864 + }, + { + "epoch": 0.02, + "learning_rate": 3.7861422872540806e-05, + "loss": 4.041, + "step": 741376 + }, + { + "epoch": 0.02, + "learning_rate": 3.7853036925030286e-05, + "loss": 4.0604, + "step": 741888 + }, + { + "epoch": 0.02, + "learning_rate": 3.7844650977519766e-05, + "loss": 4.0453, + "step": 742400 + }, + { + "epoch": 0.02, + "learning_rate": 3.7836265030009246e-05, + "loss": 4.0509, + "step": 742912 + }, + { + "epoch": 0.02, + "learning_rate": 3.7827879082498725e-05, + "loss": 4.0427, + "step": 743424 + }, + { + "epoch": 0.02, + "learning_rate": 3.7819493134988205e-05, + "loss": 4.058, + "step": 743936 + }, + { + "epoch": 0.02, + "learning_rate": 3.7811107187477685e-05, + "loss": 4.0489, + "step": 744448 + }, + { + "epoch": 0.02, + "learning_rate": 3.7802721239967165e-05, + "loss": 4.0387, + "step": 744960 + }, + { + "epoch": 0.02, + "learning_rate": 3.7794351671260374e-05, + "loss": 4.0614, + "step": 745472 + }, + { + "epoch": 0.02, + "learning_rate": 3.7785965723749854e-05, + "loss": 4.058, + "step": 745984 + }, + { + "epoch": 0.02, + "learning_rate": 3.7777579776239334e-05, + "loss": 4.0553, + "step": 746496 + }, + { + "epoch": 0.02, + "learning_rate": 3.7769193828728814e-05, + "loss": 4.0533, + "step": 747008 + }, + { + "epoch": 0.02, + "learning_rate": 3.7760824260022023e-05, + "loss": 4.045, + "step": 747520 + }, + { + "epoch": 0.02, + "learning_rate": 3.77524383125115e-05, + "loss": 4.0488, + "step": 748032 + }, + { + "epoch": 0.02, + "learning_rate": 3.774405236500099e-05, + "loss": 4.0571, + "step": 748544 + }, + { + "epoch": 0.02, + "learning_rate": 3.773566641749047e-05, + "loss": 4.0431, + "step": 749056 + }, + { + "epoch": 0.02, + "learning_rate": 3.772728046997995e-05, + "loss": 4.0439, + "step": 749568 + }, + { + "epoch": 0.02, + "learning_rate": 3.771891090127316e-05, + "loss": 4.0499, + "step": 750080 + }, + { + "epoch": 0.02, + "learning_rate": 3.771052495376264e-05, + "loss": 4.0534, + "step": 750592 + }, + { + "epoch": 0.02, + "learning_rate": 3.770213900625212e-05, + "loss": 4.0484, + "step": 751104 + }, + { + "epoch": 0.02, + "learning_rate": 3.769376943754533e-05, + "loss": 4.0325, + "step": 751616 + }, + { + "epoch": 0.02, + "learning_rate": 3.768538349003481e-05, + "loss": 4.0548, + "step": 752128 + }, + { + "epoch": 0.02, + "learning_rate": 3.767699754252429e-05, + "loss": 4.0375, + "step": 752640 + }, + { + "epoch": 0.02, + "learning_rate": 3.766861159501377e-05, + "loss": 4.0572, + "step": 753152 + }, + { + "epoch": 0.02, + "learning_rate": 3.766022564750325e-05, + "loss": 4.0497, + "step": 753664 + }, + { + "epoch": 0.02, + "learning_rate": 3.765183969999273e-05, + "loss": 4.0603, + "step": 754176 + }, + { + "epoch": 0.02, + "learning_rate": 3.764345375248221e-05, + "loss": 4.0329, + "step": 754688 + }, + { + "epoch": 0.02, + "learning_rate": 3.763506780497169e-05, + "loss": 4.065, + "step": 755200 + }, + { + "epoch": 0.02, + "learning_rate": 3.7626698236264904e-05, + "loss": 4.0502, + "step": 755712 + }, + { + "epoch": 0.02, + "learning_rate": 3.7618312288754384e-05, + "loss": 4.057, + "step": 756224 + }, + { + "epoch": 0.02, + "learning_rate": 3.7609926341243864e-05, + "loss": 4.052, + "step": 756736 + }, + { + "epoch": 0.02, + "learning_rate": 3.7601540393733344e-05, + "loss": 4.043, + "step": 757248 + }, + { + "epoch": 0.02, + "learning_rate": 3.7593154446222823e-05, + "loss": 4.0568, + "step": 757760 + }, + { + "epoch": 0.02, + "learning_rate": 3.758478487751603e-05, + "loss": 4.0634, + "step": 758272 + }, + { + "epoch": 0.02, + "learning_rate": 3.757639893000551e-05, + "loss": 4.0448, + "step": 758784 + }, + { + "epoch": 0.02, + "learning_rate": 3.756801298249499e-05, + "loss": 4.0514, + "step": 759296 + }, + { + "epoch": 0.02, + "learning_rate": 3.755962703498447e-05, + "loss": 4.0569, + "step": 759808 + }, + { + "epoch": 0.02, + "learning_rate": 3.755125746627768e-05, + "loss": 4.0414, + "step": 760320 + }, + { + "epoch": 0.02, + "learning_rate": 3.75428878975709e-05, + "loss": 4.0463, + "step": 760832 + }, + { + "epoch": 0.02, + "learning_rate": 3.753450195006038e-05, + "loss": 4.0523, + "step": 761344 + }, + { + "epoch": 0.02, + "learning_rate": 3.752611600254986e-05, + "loss": 4.0528, + "step": 761856 + }, + { + "epoch": 0.02, + "learning_rate": 3.751773005503934e-05, + "loss": 4.0539, + "step": 762368 + }, + { + "epoch": 0.02, + "learning_rate": 3.750934410752882e-05, + "loss": 4.0467, + "step": 762880 + }, + { + "epoch": 0.03, + "eval_loss": 4.074407577514648, + "eval_runtime": 296.2319, + "eval_samples_per_second": 1288.149, + "eval_steps_per_second": 40.256, + "step": 763200 + }, + { + "epoch": 1.0, + "learning_rate": 3.75009581600183e-05, + "loss": 4.0357, + "step": 763392 + }, + { + "epoch": 1.0, + "learning_rate": 3.749257221250778e-05, + "loss": 4.0357, + "step": 763904 + }, + { + "epoch": 1.0, + "learning_rate": 3.748418626499725e-05, + "loss": 4.0474, + "step": 764416 + }, + { + "epoch": 1.0, + "learning_rate": 3.7475816696290466e-05, + "loss": 4.0515, + "step": 764928 + }, + { + "epoch": 1.0, + "learning_rate": 3.7467430748779946e-05, + "loss": 4.0541, + "step": 765440 + }, + { + "epoch": 1.0, + "learning_rate": 3.7459044801269426e-05, + "loss": 4.0468, + "step": 765952 + }, + { + "epoch": 1.0, + "learning_rate": 3.74506588537589e-05, + "loss": 4.0473, + "step": 766464 + }, + { + "epoch": 1.0, + "learning_rate": 3.7442289285052115e-05, + "loss": 4.0398, + "step": 766976 + }, + { + "epoch": 1.0, + "learning_rate": 3.7433903337541595e-05, + "loss": 4.043, + "step": 767488 + }, + { + "epoch": 1.0, + "learning_rate": 3.742553376883481e-05, + "loss": 4.0439, + "step": 768000 + }, + { + "epoch": 1.0, + "learning_rate": 3.741714782132429e-05, + "loss": 4.0506, + "step": 768512 + }, + { + "epoch": 1.0, + "learning_rate": 3.740876187381377e-05, + "loss": 4.0511, + "step": 769024 + }, + { + "epoch": 1.0, + "learning_rate": 3.740039230510698e-05, + "loss": 4.0553, + "step": 769536 + }, + { + "epoch": 1.0, + "learning_rate": 3.739200635759646e-05, + "loss": 4.0381, + "step": 770048 + }, + { + "epoch": 1.0, + "learning_rate": 3.738362041008594e-05, + "loss": 4.044, + "step": 770560 + }, + { + "epoch": 1.0, + "learning_rate": 3.737523446257542e-05, + "loss": 4.024, + "step": 771072 + }, + { + "epoch": 1.0, + "learning_rate": 3.73668485150649e-05, + "loss": 4.0417, + "step": 771584 + }, + { + "epoch": 1.0, + "learning_rate": 3.735847894635811e-05, + "loss": 4.0416, + "step": 772096 + }, + { + "epoch": 1.0, + "learning_rate": 3.735009299884759e-05, + "loss": 4.0399, + "step": 772608 + }, + { + "epoch": 1.0, + "learning_rate": 3.734170705133707e-05, + "loss": 4.0449, + "step": 773120 + }, + { + "epoch": 1.0, + "learning_rate": 3.733332110382655e-05, + "loss": 4.0527, + "step": 773632 + }, + { + "epoch": 1.0, + "learning_rate": 3.732493515631603e-05, + "loss": 4.0486, + "step": 774144 + }, + { + "epoch": 1.0, + "learning_rate": 3.731654920880551e-05, + "loss": 4.0487, + "step": 774656 + }, + { + "epoch": 1.0, + "learning_rate": 3.730816326129499e-05, + "loss": 4.0422, + "step": 775168 + }, + { + "epoch": 1.0, + "learning_rate": 3.729977731378447e-05, + "loss": 4.0443, + "step": 775680 + }, + { + "epoch": 1.0, + "learning_rate": 3.7291424123881414e-05, + "loss": 4.045, + "step": 776192 + }, + { + "epoch": 1.0, + "learning_rate": 3.7283038176370894e-05, + "loss": 4.0417, + "step": 776704 + }, + { + "epoch": 1.0, + "learning_rate": 3.7274652228860374e-05, + "loss": 4.0463, + "step": 777216 + }, + { + "epoch": 1.0, + "learning_rate": 3.726626628134985e-05, + "loss": 4.0357, + "step": 777728 + }, + { + "epoch": 1.0, + "learning_rate": 3.725788033383933e-05, + "loss": 4.0339, + "step": 778240 + }, + { + "epoch": 1.01, + "learning_rate": 3.724949438632881e-05, + "loss": 4.0342, + "step": 778752 + }, + { + "epoch": 1.01, + "learning_rate": 3.7241108438818287e-05, + "loss": 4.0519, + "step": 779264 + }, + { + "epoch": 1.01, + "learning_rate": 3.7232722491307767e-05, + "loss": 4.052, + "step": 779776 + }, + { + "epoch": 1.01, + "learning_rate": 3.722433654379725e-05, + "loss": 4.0417, + "step": 780288 + }, + { + "epoch": 1.01, + "learning_rate": 3.721595059628673e-05, + "loss": 4.0408, + "step": 780800 + }, + { + "epoch": 1.01, + "learning_rate": 3.720756464877621e-05, + "loss": 4.0393, + "step": 781312 + }, + { + "epoch": 1.01, + "learning_rate": 3.719917870126569e-05, + "loss": 4.0523, + "step": 781824 + }, + { + "epoch": 1.01, + "learning_rate": 3.71908091325589e-05, + "loss": 4.0355, + "step": 782336 + }, + { + "epoch": 1.01, + "learning_rate": 3.718242318504838e-05, + "loss": 4.0356, + "step": 782848 + }, + { + "epoch": 1.01, + "learning_rate": 3.717403723753786e-05, + "loss": 4.0285, + "step": 783360 + }, + { + "epoch": 1.01, + "learning_rate": 3.716565129002734e-05, + "loss": 4.0377, + "step": 783872 + }, + { + "epoch": 1.01, + "learning_rate": 3.715728172132055e-05, + "loss": 4.0452, + "step": 784384 + }, + { + "epoch": 1.01, + "learning_rate": 3.714889577381003e-05, + "loss": 4.0409, + "step": 784896 + }, + { + "epoch": 1.01, + "learning_rate": 3.714052620510324e-05, + "loss": 4.0393, + "step": 785408 + }, + { + "epoch": 1.01, + "learning_rate": 3.713214025759272e-05, + "loss": 4.0488, + "step": 785920 + }, + { + "epoch": 1.01, + "learning_rate": 3.712375431008221e-05, + "loss": 4.0363, + "step": 786432 + }, + { + "epoch": 1.01, + "learning_rate": 3.711536836257169e-05, + "loss": 4.0454, + "step": 786944 + }, + { + "epoch": 1.01, + "learning_rate": 3.710698241506117e-05, + "loss": 4.0435, + "step": 787456 + }, + { + "epoch": 1.01, + "learning_rate": 3.709859646755065e-05, + "loss": 4.0154, + "step": 787968 + }, + { + "epoch": 1.01, + "learning_rate": 3.7090226898843856e-05, + "loss": 4.0549, + "step": 788480 + }, + { + "epoch": 1.01, + "learning_rate": 3.7081840951333336e-05, + "loss": 4.0349, + "step": 788992 + }, + { + "epoch": 1.01, + "learning_rate": 3.7073455003822816e-05, + "loss": 4.0492, + "step": 789504 + }, + { + "epoch": 1.01, + "learning_rate": 3.7065069056312296e-05, + "loss": 4.0325, + "step": 790016 + }, + { + "epoch": 1.01, + "learning_rate": 3.7056683108801776e-05, + "loss": 4.0336, + "step": 790528 + }, + { + "epoch": 1.01, + "learning_rate": 3.7048297161291256e-05, + "loss": 4.0285, + "step": 791040 + }, + { + "epoch": 1.01, + "learning_rate": 3.703991121378073e-05, + "loss": 4.0359, + "step": 791552 + }, + { + "epoch": 1.01, + "learning_rate": 3.703152526627021e-05, + "loss": 4.0329, + "step": 792064 + }, + { + "epoch": 1.01, + "learning_rate": 3.7023155697563425e-05, + "loss": 4.0264, + "step": 792576 + }, + { + "epoch": 1.01, + "learning_rate": 3.7014769750052905e-05, + "loss": 4.0488, + "step": 793088 + }, + { + "epoch": 1.01, + "learning_rate": 3.7006383802542385e-05, + "loss": 4.0361, + "step": 793600 + }, + { + "epoch": 1.01, + "learning_rate": 3.6997997855031865e-05, + "loss": 4.0176, + "step": 794112 + }, + { + "epoch": 1.01, + "learning_rate": 3.698962828632508e-05, + "loss": 4.0456, + "step": 794624 + }, + { + "epoch": 1.01, + "learning_rate": 3.698124233881456e-05, + "loss": 4.0229, + "step": 795136 + }, + { + "epoch": 1.01, + "learning_rate": 3.6972856391304034e-05, + "loss": 4.0234, + "step": 795648 + }, + { + "epoch": 1.01, + "learning_rate": 3.6964470443793514e-05, + "loss": 4.0407, + "step": 796160 + }, + { + "epoch": 1.01, + "learning_rate": 3.695610087508673e-05, + "loss": 4.0344, + "step": 796672 + }, + { + "epoch": 1.01, + "learning_rate": 3.69477149275762e-05, + "loss": 4.0269, + "step": 797184 + }, + { + "epoch": 1.01, + "learning_rate": 3.693932898006568e-05, + "loss": 4.0267, + "step": 797696 + }, + { + "epoch": 1.01, + "learning_rate": 3.693094303255516e-05, + "loss": 4.0234, + "step": 798208 + }, + { + "epoch": 1.01, + "learning_rate": 3.692257346384838e-05, + "loss": 4.035, + "step": 798720 + }, + { + "epoch": 1.01, + "learning_rate": 3.691418751633786e-05, + "loss": 4.0431, + "step": 799232 + }, + { + "epoch": 1.01, + "learning_rate": 3.690580156882734e-05, + "loss": 4.0351, + "step": 799744 + }, + { + "epoch": 1.01, + "learning_rate": 3.689741562131682e-05, + "loss": 4.0389, + "step": 800256 + }, + { + "epoch": 1.01, + "learning_rate": 3.68890296738063e-05, + "loss": 4.0386, + "step": 800768 + }, + { + "epoch": 1.01, + "learning_rate": 3.688066010509951e-05, + "loss": 4.0497, + "step": 801280 + }, + { + "epoch": 1.01, + "learning_rate": 3.687229053639272e-05, + "loss": 4.027, + "step": 801792 + }, + { + "epoch": 1.01, + "learning_rate": 3.68639045888822e-05, + "loss": 4.0372, + "step": 802304 + }, + { + "epoch": 1.01, + "learning_rate": 3.6855518641371676e-05, + "loss": 4.0294, + "step": 802816 + }, + { + "epoch": 1.01, + "learning_rate": 3.6847132693861156e-05, + "loss": 4.0251, + "step": 803328 + }, + { + "epoch": 1.01, + "learning_rate": 3.6838746746350636e-05, + "loss": 4.0328, + "step": 803840 + }, + { + "epoch": 1.01, + "learning_rate": 3.683037717764385e-05, + "loss": 4.0439, + "step": 804352 + }, + { + "epoch": 1.01, + "learning_rate": 3.682199123013333e-05, + "loss": 4.0381, + "step": 804864 + }, + { + "epoch": 1.01, + "learning_rate": 3.681360528262281e-05, + "loss": 4.0472, + "step": 805376 + }, + { + "epoch": 1.01, + "learning_rate": 3.680521933511229e-05, + "loss": 4.0139, + "step": 805888 + }, + { + "epoch": 1.01, + "learning_rate": 3.679683338760177e-05, + "loss": 4.0298, + "step": 806400 + }, + { + "epoch": 1.01, + "learning_rate": 3.678844744009125e-05, + "loss": 4.0383, + "step": 806912 + }, + { + "epoch": 1.01, + "learning_rate": 3.678006149258073e-05, + "loss": 4.0348, + "step": 807424 + }, + { + "epoch": 1.01, + "learning_rate": 3.677169192387394e-05, + "loss": 4.0299, + "step": 807936 + }, + { + "epoch": 1.01, + "learning_rate": 3.676330597636342e-05, + "loss": 4.042, + "step": 808448 + }, + { + "epoch": 1.01, + "learning_rate": 3.67549200288529e-05, + "loss": 4.0326, + "step": 808960 + }, + { + "epoch": 1.02, + "learning_rate": 3.674653408134238e-05, + "loss": 4.0347, + "step": 809472 + }, + { + "epoch": 1.02, + "learning_rate": 3.673816451263559e-05, + "loss": 4.0232, + "step": 809984 + }, + { + "epoch": 1.02, + "learning_rate": 3.672977856512507e-05, + "loss": 4.0249, + "step": 810496 + }, + { + "epoch": 1.02, + "learning_rate": 3.672139261761455e-05, + "loss": 4.0409, + "step": 811008 + }, + { + "epoch": 1.02, + "learning_rate": 3.6713006670104037e-05, + "loss": 4.0335, + "step": 811520 + }, + { + "epoch": 1.02, + "learning_rate": 3.6704620722593516e-05, + "loss": 4.0367, + "step": 812032 + }, + { + "epoch": 1.02, + "learning_rate": 3.6696234775082996e-05, + "loss": 4.0273, + "step": 812544 + }, + { + "epoch": 1.02, + "learning_rate": 3.6687848827572476e-05, + "loss": 4.0231, + "step": 813056 + }, + { + "epoch": 1.02, + "learning_rate": 3.6679479258865685e-05, + "loss": 4.0396, + "step": 813568 + }, + { + "epoch": 1.02, + "learning_rate": 3.6671093311355165e-05, + "loss": 4.0387, + "step": 814080 + }, + { + "epoch": 1.02, + "learning_rate": 3.6662707363844645e-05, + "loss": 4.0336, + "step": 814592 + }, + { + "epoch": 1.02, + "learning_rate": 3.6654321416334125e-05, + "loss": 4.0292, + "step": 815104 + }, + { + "epoch": 1.02, + "learning_rate": 3.6645935468823605e-05, + "loss": 4.0317, + "step": 815616 + }, + { + "epoch": 1.02, + "learning_rate": 3.6637549521313085e-05, + "loss": 4.026, + "step": 816128 + }, + { + "epoch": 1.02, + "learning_rate": 3.6629163573802565e-05, + "loss": 4.0277, + "step": 816640 + }, + { + "epoch": 1.02, + "learning_rate": 3.662077762629204e-05, + "loss": 4.0201, + "step": 817152 + }, + { + "epoch": 1.02, + "learning_rate": 3.6612408057585254e-05, + "loss": 4.0234, + "step": 817664 + }, + { + "epoch": 1.02, + "learning_rate": 3.6604022110074734e-05, + "loss": 4.0303, + "step": 818176 + }, + { + "epoch": 1.02, + "learning_rate": 3.6595636162564214e-05, + "loss": 4.0313, + "step": 818688 + }, + { + "epoch": 1.02, + "learning_rate": 3.6587250215053694e-05, + "loss": 4.0225, + "step": 819200 + }, + { + "epoch": 1.02, + "learning_rate": 3.6578864267543174e-05, + "loss": 4.0285, + "step": 819712 + }, + { + "epoch": 1.02, + "learning_rate": 3.657049469883639e-05, + "loss": 4.0325, + "step": 820224 + }, + { + "epoch": 1.02, + "learning_rate": 3.656210875132587e-05, + "loss": 4.0302, + "step": 820736 + }, + { + "epoch": 1.02, + "learning_rate": 3.655372280381534e-05, + "loss": 4.0178, + "step": 821248 + }, + { + "epoch": 1.02, + "learning_rate": 3.654533685630482e-05, + "loss": 4.0395, + "step": 821760 + }, + { + "epoch": 1.02, + "learning_rate": 3.653696728759804e-05, + "loss": 4.0377, + "step": 822272 + }, + { + "epoch": 1.02, + "learning_rate": 3.652858134008751e-05, + "loss": 4.0375, + "step": 822784 + }, + { + "epoch": 1.02, + "learning_rate": 3.652021177138073e-05, + "loss": 4.0298, + "step": 823296 + }, + { + "epoch": 1.02, + "learning_rate": 3.651182582387021e-05, + "loss": 4.0228, + "step": 823808 + }, + { + "epoch": 1.02, + "learning_rate": 3.650343987635969e-05, + "loss": 4.0285, + "step": 824320 + }, + { + "epoch": 1.02, + "learning_rate": 3.649505392884917e-05, + "loss": 4.0415, + "step": 824832 + }, + { + "epoch": 1.02, + "learning_rate": 3.648666798133865e-05, + "loss": 4.0237, + "step": 825344 + }, + { + "epoch": 1.02, + "learning_rate": 3.647828203382813e-05, + "loss": 4.0241, + "step": 825856 + }, + { + "epoch": 1.02, + "learning_rate": 3.646989608631761e-05, + "loss": 4.0244, + "step": 826368 + }, + { + "epoch": 1.02, + "learning_rate": 3.646152651761082e-05, + "loss": 4.0366, + "step": 826880 + }, + { + "epoch": 1.02, + "learning_rate": 3.64531405701003e-05, + "loss": 4.0262, + "step": 827392 + }, + { + "epoch": 1.02, + "learning_rate": 3.644475462258978e-05, + "loss": 4.012, + "step": 827904 + }, + { + "epoch": 1.02, + "learning_rate": 3.643636867507926e-05, + "loss": 4.0336, + "step": 828416 + }, + { + "epoch": 1.02, + "learning_rate": 3.642798272756874e-05, + "loss": 4.0182, + "step": 828928 + }, + { + "epoch": 1.02, + "learning_rate": 3.6419596780058217e-05, + "loss": 4.0374, + "step": 829440 + }, + { + "epoch": 1.02, + "learning_rate": 3.6411210832547697e-05, + "loss": 4.029, + "step": 829952 + }, + { + "epoch": 1.02, + "learning_rate": 3.6402841263840906e-05, + "loss": 4.036, + "step": 830464 + }, + { + "epoch": 1.02, + "learning_rate": 3.639445531633039e-05, + "loss": 4.0167, + "step": 830976 + }, + { + "epoch": 1.02, + "learning_rate": 3.638606936881987e-05, + "loss": 4.0408, + "step": 831488 + }, + { + "epoch": 1.02, + "learning_rate": 3.637768342130935e-05, + "loss": 4.0349, + "step": 832000 + }, + { + "epoch": 1.02, + "learning_rate": 3.636929747379883e-05, + "loss": 4.0338, + "step": 832512 + }, + { + "epoch": 1.02, + "learning_rate": 3.636091152628831e-05, + "loss": 4.0319, + "step": 833024 + }, + { + "epoch": 1.02, + "learning_rate": 3.635254195758152e-05, + "loss": 4.021, + "step": 833536 + }, + { + "epoch": 1.02, + "learning_rate": 3.6344156010071e-05, + "loss": 4.0396, + "step": 834048 + }, + { + "epoch": 1.02, + "learning_rate": 3.633577006256048e-05, + "loss": 4.0383, + "step": 834560 + }, + { + "epoch": 1.02, + "learning_rate": 3.632738411504996e-05, + "loss": 4.0275, + "step": 835072 + }, + { + "epoch": 1.02, + "learning_rate": 3.631899816753944e-05, + "loss": 4.0292, + "step": 835584 + }, + { + "epoch": 1.02, + "learning_rate": 3.631061222002892e-05, + "loss": 4.0356, + "step": 836096 + }, + { + "epoch": 1.02, + "learning_rate": 3.63022262725184e-05, + "loss": 4.0255, + "step": 836608 + }, + { + "epoch": 1.02, + "learning_rate": 3.6293840325007874e-05, + "loss": 4.0199, + "step": 837120 + }, + { + "epoch": 1.02, + "learning_rate": 3.628545437749736e-05, + "loss": 4.0345, + "step": 837632 + }, + { + "epoch": 1.02, + "learning_rate": 3.6277101187594306e-05, + "loss": 4.0307, + "step": 838144 + }, + { + "epoch": 1.02, + "learning_rate": 3.6268715240083786e-05, + "loss": 4.037, + "step": 838656 + }, + { + "epoch": 1.02, + "learning_rate": 3.6260329292573266e-05, + "loss": 4.0258, + "step": 839168 + }, + { + "epoch": 1.03, + "eval_loss": 4.060638427734375, + "eval_runtime": 297.1011, + "eval_samples_per_second": 1284.381, + "eval_steps_per_second": 40.138, + "step": 839520 + }, + { + "epoch": 0.0, + "learning_rate": 3.6251943345062746e-05, + "loss": 4.0108, + "step": 839680 + }, + { + "epoch": 0.0, + "learning_rate": 3.6243557397552226e-05, + "loss": 4.0128, + "step": 840192 + }, + { + "epoch": 0.0, + "learning_rate": 3.62351714500417e-05, + "loss": 4.0278, + "step": 840704 + }, + { + "epoch": 0.0, + "learning_rate": 3.622678550253118e-05, + "loss": 4.0318, + "step": 841216 + }, + { + "epoch": 0.0, + "learning_rate": 3.621839955502066e-05, + "loss": 4.0365, + "step": 841728 + }, + { + "epoch": 0.0, + "learning_rate": 3.621001360751014e-05, + "loss": 4.027, + "step": 842240 + }, + { + "epoch": 0.0, + "learning_rate": 3.620162765999962e-05, + "loss": 4.0253, + "step": 842752 + }, + { + "epoch": 0.0, + "learning_rate": 3.61932417124891e-05, + "loss": 4.0241, + "step": 843264 + }, + { + "epoch": 0.0, + "learning_rate": 3.618485576497858e-05, + "loss": 4.0217, + "step": 843776 + }, + { + "epoch": 0.0, + "learning_rate": 3.617646981746806e-05, + "loss": 4.0212, + "step": 844288 + }, + { + "epoch": 0.0, + "learning_rate": 3.616808386995754e-05, + "loss": 4.0326, + "step": 844800 + }, + { + "epoch": 0.0, + "learning_rate": 3.6159697922447025e-05, + "loss": 4.0339, + "step": 845312 + }, + { + "epoch": 0.0, + "learning_rate": 3.6151328353740234e-05, + "loss": 4.0344, + "step": 845824 + }, + { + "epoch": 0.0, + "learning_rate": 3.6142942406229714e-05, + "loss": 4.0157, + "step": 846336 + }, + { + "epoch": 0.0, + "learning_rate": 3.6134556458719194e-05, + "loss": 4.0233, + "step": 846848 + }, + { + "epoch": 0.0, + "learning_rate": 3.6126170511208674e-05, + "loss": 4.0007, + "step": 847360 + }, + { + "epoch": 0.0, + "learning_rate": 3.6117784563698154e-05, + "loss": 4.0248, + "step": 847872 + }, + { + "epoch": 0.0, + "learning_rate": 3.6109398616187634e-05, + "loss": 4.025, + "step": 848384 + }, + { + "epoch": 0.0, + "learning_rate": 3.6101012668677114e-05, + "loss": 4.0164, + "step": 848896 + }, + { + "epoch": 0.0, + "learning_rate": 3.609262672116659e-05, + "loss": 4.024, + "step": 849408 + }, + { + "epoch": 0.0, + "learning_rate": 3.608424077365607e-05, + "loss": 4.0316, + "step": 849920 + }, + { + "epoch": 0.0, + "learning_rate": 3.607585482614555e-05, + "loss": 4.026, + "step": 850432 + }, + { + "epoch": 0.0, + "learning_rate": 3.606746887863503e-05, + "loss": 4.0336, + "step": 850944 + }, + { + "epoch": 0.0, + "learning_rate": 3.605908293112451e-05, + "loss": 4.0236, + "step": 851456 + }, + { + "epoch": 0.0, + "learning_rate": 3.605071336241772e-05, + "loss": 4.0242, + "step": 851968 + }, + { + "epoch": 0.0, + "learning_rate": 3.604234379371094e-05, + "loss": 4.0207, + "step": 852480 + }, + { + "epoch": 0.0, + "learning_rate": 3.603395784620042e-05, + "loss": 4.02, + "step": 852992 + }, + { + "epoch": 0.0, + "learning_rate": 3.602557189868989e-05, + "loss": 4.0281, + "step": 853504 + }, + { + "epoch": 0.0, + "learning_rate": 3.601718595117937e-05, + "loss": 4.0193, + "step": 854016 + }, + { + "epoch": 0.0, + "learning_rate": 3.600880000366885e-05, + "loss": 4.0134, + "step": 854528 + }, + { + "epoch": 0.01, + "learning_rate": 3.600041405615833e-05, + "loss": 4.0173, + "step": 855040 + }, + { + "epoch": 0.01, + "learning_rate": 3.599202810864781e-05, + "loss": 4.0288, + "step": 855552 + }, + { + "epoch": 0.01, + "learning_rate": 3.598364216113729e-05, + "loss": 4.029, + "step": 856064 + }, + { + "epoch": 0.01, + "learning_rate": 3.59752725924305e-05, + "loss": 4.0263, + "step": 856576 + }, + { + "epoch": 0.01, + "learning_rate": 3.596690302372372e-05, + "loss": 4.0207, + "step": 857088 + }, + { + "epoch": 0.01, + "learning_rate": 3.59585170762132e-05, + "loss": 4.0239, + "step": 857600 + }, + { + "epoch": 0.01, + "learning_rate": 3.595013112870268e-05, + "loss": 4.0313, + "step": 858112 + }, + { + "epoch": 0.01, + "learning_rate": 3.594174518119216e-05, + "loss": 4.0108, + "step": 858624 + }, + { + "epoch": 0.01, + "learning_rate": 3.5933359233681637e-05, + "loss": 4.0167, + "step": 859136 + }, + { + "epoch": 0.01, + "learning_rate": 3.5924973286171117e-05, + "loss": 4.0139, + "step": 859648 + }, + { + "epoch": 0.01, + "learning_rate": 3.5916587338660597e-05, + "loss": 4.0168, + "step": 860160 + }, + { + "epoch": 0.01, + "learning_rate": 3.5908201391150076e-05, + "loss": 4.0274, + "step": 860672 + }, + { + "epoch": 0.01, + "learning_rate": 3.5899831822443286e-05, + "loss": 4.0149, + "step": 861184 + }, + { + "epoch": 0.01, + "learning_rate": 3.5891462253736495e-05, + "loss": 4.0254, + "step": 861696 + }, + { + "epoch": 0.01, + "learning_rate": 3.5883076306225975e-05, + "loss": 4.0243, + "step": 862208 + }, + { + "epoch": 0.01, + "learning_rate": 3.5874690358715455e-05, + "loss": 4.0225, + "step": 862720 + }, + { + "epoch": 0.01, + "learning_rate": 3.5866304411204935e-05, + "loss": 4.0226, + "step": 863232 + }, + { + "epoch": 0.01, + "learning_rate": 3.5857918463694414e-05, + "loss": 4.0266, + "step": 863744 + }, + { + "epoch": 0.01, + "learning_rate": 3.58495325161839e-05, + "loss": 3.9939, + "step": 864256 + }, + { + "epoch": 0.01, + "learning_rate": 3.584116294747711e-05, + "loss": 4.0345, + "step": 864768 + }, + { + "epoch": 0.01, + "learning_rate": 3.583279337877032e-05, + "loss": 4.0176, + "step": 865280 + }, + { + "epoch": 0.01, + "learning_rate": 3.58244074312598e-05, + "loss": 4.0293, + "step": 865792 + }, + { + "epoch": 0.01, + "learning_rate": 3.581602148374928e-05, + "loss": 4.0128, + "step": 866304 + }, + { + "epoch": 0.01, + "learning_rate": 3.580763553623876e-05, + "loss": 4.0155, + "step": 866816 + }, + { + "epoch": 0.01, + "learning_rate": 3.579924958872824e-05, + "loss": 4.0078, + "step": 867328 + }, + { + "epoch": 0.01, + "learning_rate": 3.579086364121772e-05, + "loss": 4.0143, + "step": 867840 + }, + { + "epoch": 0.01, + "learning_rate": 3.57824776937072e-05, + "loss": 4.0189, + "step": 868352 + }, + { + "epoch": 0.01, + "learning_rate": 3.577409174619668e-05, + "loss": 4.0025, + "step": 868864 + }, + { + "epoch": 0.01, + "learning_rate": 3.576570579868616e-05, + "loss": 4.0322, + "step": 869376 + }, + { + "epoch": 0.01, + "learning_rate": 3.575731985117564e-05, + "loss": 4.0178, + "step": 869888 + }, + { + "epoch": 0.01, + "learning_rate": 3.574893390366512e-05, + "loss": 3.9992, + "step": 870400 + }, + { + "epoch": 0.01, + "learning_rate": 3.57405479561546e-05, + "loss": 4.0239, + "step": 870912 + }, + { + "epoch": 0.01, + "learning_rate": 3.573216200864408e-05, + "loss": 4.0078, + "step": 871424 + }, + { + "epoch": 0.01, + "learning_rate": 3.5723792439937295e-05, + "loss": 4.0046, + "step": 871936 + }, + { + "epoch": 0.01, + "learning_rate": 3.5715406492426775e-05, + "loss": 4.0204, + "step": 872448 + }, + { + "epoch": 0.01, + "learning_rate": 3.570702054491625e-05, + "loss": 4.0163, + "step": 872960 + }, + { + "epoch": 0.01, + "learning_rate": 3.569863459740573e-05, + "loss": 4.0071, + "step": 873472 + }, + { + "epoch": 0.01, + "learning_rate": 3.569024864989521e-05, + "loss": 4.0087, + "step": 873984 + }, + { + "epoch": 0.01, + "learning_rate": 3.5681879081188424e-05, + "loss": 4.0043, + "step": 874496 + }, + { + "epoch": 0.01, + "learning_rate": 3.56734931336779e-05, + "loss": 4.0155, + "step": 875008 + }, + { + "epoch": 0.01, + "learning_rate": 3.566512356497111e-05, + "loss": 4.023, + "step": 875520 + }, + { + "epoch": 0.01, + "learning_rate": 3.565673761746059e-05, + "loss": 4.0147, + "step": 876032 + }, + { + "epoch": 0.01, + "learning_rate": 3.564835166995007e-05, + "loss": 4.0207, + "step": 876544 + }, + { + "epoch": 0.01, + "learning_rate": 3.563996572243955e-05, + "loss": 4.0174, + "step": 877056 + }, + { + "epoch": 0.01, + "learning_rate": 3.563157977492903e-05, + "loss": 4.0295, + "step": 877568 + }, + { + "epoch": 0.01, + "learning_rate": 3.562321020622225e-05, + "loss": 4.0101, + "step": 878080 + }, + { + "epoch": 0.01, + "learning_rate": 3.561482425871172e-05, + "loss": 4.0202, + "step": 878592 + }, + { + "epoch": 0.01, + "learning_rate": 3.56064383112012e-05, + "loss": 4.0084, + "step": 879104 + }, + { + "epoch": 0.01, + "learning_rate": 3.559805236369068e-05, + "loss": 4.0061, + "step": 879616 + }, + { + "epoch": 0.01, + "learning_rate": 3.558966641618016e-05, + "loss": 4.018, + "step": 880128 + }, + { + "epoch": 0.01, + "learning_rate": 3.558129684747337e-05, + "loss": 4.0195, + "step": 880640 + }, + { + "epoch": 0.01, + "learning_rate": 3.557291089996285e-05, + "loss": 4.0211, + "step": 881152 + }, + { + "epoch": 0.01, + "learning_rate": 3.556452495245233e-05, + "loss": 4.0288, + "step": 881664 + }, + { + "epoch": 0.01, + "learning_rate": 3.555613900494181e-05, + "loss": 3.9931, + "step": 882176 + }, + { + "epoch": 0.01, + "learning_rate": 3.554775305743129e-05, + "loss": 4.0123, + "step": 882688 + }, + { + "epoch": 0.01, + "learning_rate": 3.553936710992077e-05, + "loss": 4.0196, + "step": 883200 + }, + { + "epoch": 0.01, + "learning_rate": 3.553098116241026e-05, + "loss": 4.0168, + "step": 883712 + }, + { + "epoch": 0.01, + "learning_rate": 3.552259521489974e-05, + "loss": 4.0105, + "step": 884224 + }, + { + "epoch": 0.01, + "learning_rate": 3.5514225646192946e-05, + "loss": 4.0223, + "step": 884736 + }, + { + "epoch": 0.01, + "learning_rate": 3.5505839698682426e-05, + "loss": 4.0154, + "step": 885248 + }, + { + "epoch": 0.02, + "learning_rate": 3.5497453751171906e-05, + "loss": 4.0147, + "step": 885760 + }, + { + "epoch": 0.02, + "learning_rate": 3.5489084182465115e-05, + "loss": 4.0073, + "step": 886272 + }, + { + "epoch": 0.02, + "learning_rate": 3.5480698234954595e-05, + "loss": 4.0051, + "step": 886784 + }, + { + "epoch": 0.02, + "learning_rate": 3.5472312287444075e-05, + "loss": 4.0198, + "step": 887296 + }, + { + "epoch": 0.02, + "learning_rate": 3.5463926339933555e-05, + "loss": 4.0176, + "step": 887808 + }, + { + "epoch": 0.02, + "learning_rate": 3.5455540392423035e-05, + "loss": 4.0139, + "step": 888320 + }, + { + "epoch": 0.02, + "learning_rate": 3.5447154444912515e-05, + "loss": 4.0107, + "step": 888832 + }, + { + "epoch": 0.02, + "learning_rate": 3.5438768497401995e-05, + "loss": 4.0064, + "step": 889344 + }, + { + "epoch": 0.02, + "learning_rate": 3.5430382549891475e-05, + "loss": 4.021, + "step": 889856 + }, + { + "epoch": 0.02, + "learning_rate": 3.542201298118469e-05, + "loss": 4.0211, + "step": 890368 + }, + { + "epoch": 0.02, + "learning_rate": 3.541362703367417e-05, + "loss": 4.0126, + "step": 890880 + }, + { + "epoch": 0.02, + "learning_rate": 3.540524108616365e-05, + "loss": 4.0113, + "step": 891392 + }, + { + "epoch": 0.02, + "learning_rate": 3.539685513865313e-05, + "loss": 4.0129, + "step": 891904 + }, + { + "epoch": 0.02, + "learning_rate": 3.538848556994634e-05, + "loss": 4.0112, + "step": 892416 + }, + { + "epoch": 0.02, + "learning_rate": 3.538009962243582e-05, + "loss": 4.0033, + "step": 892928 + }, + { + "epoch": 0.02, + "learning_rate": 3.53717136749253e-05, + "loss": 4.004, + "step": 893440 + }, + { + "epoch": 0.02, + "learning_rate": 3.536332772741478e-05, + "loss": 4.0047, + "step": 893952 + }, + { + "epoch": 0.02, + "learning_rate": 3.535494177990426e-05, + "loss": 4.0154, + "step": 894464 + }, + { + "epoch": 0.02, + "learning_rate": 3.534655583239373e-05, + "loss": 4.0105, + "step": 894976 + }, + { + "epoch": 0.02, + "learning_rate": 3.533816988488321e-05, + "loss": 4.0077, + "step": 895488 + }, + { + "epoch": 0.02, + "learning_rate": 3.532978393737269e-05, + "loss": 4.0043, + "step": 896000 + }, + { + "epoch": 0.02, + "learning_rate": 3.532141436866591e-05, + "loss": 4.0124, + "step": 896512 + }, + { + "epoch": 0.02, + "learning_rate": 3.531302842115539e-05, + "loss": 4.0156, + "step": 897024 + }, + { + "epoch": 0.02, + "learning_rate": 3.530464247364487e-05, + "loss": 4.0044, + "step": 897536 + }, + { + "epoch": 0.02, + "learning_rate": 3.529625652613435e-05, + "loss": 4.014, + "step": 898048 + }, + { + "epoch": 0.02, + "learning_rate": 3.528788695742756e-05, + "loss": 4.0169, + "step": 898560 + }, + { + "epoch": 0.02, + "learning_rate": 3.527950100991704e-05, + "loss": 4.0196, + "step": 899072 + }, + { + "epoch": 0.02, + "learning_rate": 3.527113144121025e-05, + "loss": 4.013, + "step": 899584 + }, + { + "epoch": 0.02, + "learning_rate": 3.526274549369973e-05, + "loss": 4.0082, + "step": 900096 + }, + { + "epoch": 0.02, + "learning_rate": 3.5254359546189206e-05, + "loss": 4.0094, + "step": 900608 + }, + { + "epoch": 0.02, + "learning_rate": 3.5245973598678686e-05, + "loss": 4.0241, + "step": 901120 + }, + { + "epoch": 0.02, + "learning_rate": 3.5237587651168166e-05, + "loss": 4.0046, + "step": 901632 + }, + { + "epoch": 0.02, + "learning_rate": 3.5229201703657646e-05, + "loss": 4.0041, + "step": 902144 + }, + { + "epoch": 0.02, + "learning_rate": 3.522081575614713e-05, + "loss": 4.0059, + "step": 902656 + }, + { + "epoch": 0.02, + "learning_rate": 3.521242980863661e-05, + "loss": 4.017, + "step": 903168 + }, + { + "epoch": 0.02, + "learning_rate": 3.520406023992982e-05, + "loss": 4.0121, + "step": 903680 + }, + { + "epoch": 0.02, + "learning_rate": 3.51956742924193e-05, + "loss": 3.9957, + "step": 904192 + }, + { + "epoch": 0.02, + "learning_rate": 3.518728834490878e-05, + "loss": 4.0104, + "step": 904704 + }, + { + "epoch": 0.02, + "learning_rate": 3.517890239739826e-05, + "loss": 3.9989, + "step": 905216 + }, + { + "epoch": 0.02, + "learning_rate": 3.517053282869147e-05, + "loss": 4.0196, + "step": 905728 + }, + { + "epoch": 0.02, + "learning_rate": 3.516214688118095e-05, + "loss": 4.0164, + "step": 906240 + }, + { + "epoch": 0.02, + "learning_rate": 3.515376093367043e-05, + "loss": 4.015, + "step": 906752 + }, + { + "epoch": 0.02, + "learning_rate": 3.514537498615991e-05, + "loss": 4.0015, + "step": 907264 + }, + { + "epoch": 0.02, + "learning_rate": 3.513698903864939e-05, + "loss": 4.0167, + "step": 907776 + }, + { + "epoch": 0.02, + "learning_rate": 3.51286194699426e-05, + "loss": 4.0193, + "step": 908288 + }, + { + "epoch": 0.02, + "learning_rate": 3.512023352243209e-05, + "loss": 4.0117, + "step": 908800 + }, + { + "epoch": 0.02, + "learning_rate": 3.5111847574921567e-05, + "loss": 4.0144, + "step": 909312 + }, + { + "epoch": 0.02, + "learning_rate": 3.5103461627411047e-05, + "loss": 4.0029, + "step": 909824 + }, + { + "epoch": 0.02, + "learning_rate": 3.5095075679900526e-05, + "loss": 4.0232, + "step": 910336 + }, + { + "epoch": 0.02, + "learning_rate": 3.5086706111193736e-05, + "loss": 4.0211, + "step": 910848 + }, + { + "epoch": 0.02, + "learning_rate": 3.5078320163683216e-05, + "loss": 4.0134, + "step": 911360 + }, + { + "epoch": 0.02, + "learning_rate": 3.5069934216172696e-05, + "loss": 4.0099, + "step": 911872 + }, + { + "epoch": 0.02, + "learning_rate": 3.5061548268662175e-05, + "loss": 4.0174, + "step": 912384 + }, + { + "epoch": 0.02, + "learning_rate": 3.5053178699955385e-05, + "loss": 4.0061, + "step": 912896 + }, + { + "epoch": 0.02, + "learning_rate": 3.5044809131248594e-05, + "loss": 4.0021, + "step": 913408 + }, + { + "epoch": 0.02, + "learning_rate": 3.5036423183738074e-05, + "loss": 4.0175, + "step": 913920 + }, + { + "epoch": 0.02, + "learning_rate": 3.5028037236227554e-05, + "loss": 4.0133, + "step": 914432 + }, + { + "epoch": 0.02, + "learning_rate": 3.501965128871704e-05, + "loss": 4.0189, + "step": 914944 + }, + { + "epoch": 0.02, + "learning_rate": 3.501126534120652e-05, + "loss": 4.0085, + "step": 915456 + }, + { + "epoch": 0.03, + "eval_loss": 4.049461364746094, + "eval_runtime": 307.0119, + "eval_samples_per_second": 1242.919, + "eval_steps_per_second": 38.842, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.5002879393696e-05, + "loss": 4.0056, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.499449344618548e-05, + "loss": 3.9907, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.498610749867496e-05, + "loss": 4.0087, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.497772155116444e-05, + "loss": 4.0135, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.496933560365392e-05, + "loss": 4.0146, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.496094965614339e-05, + "loss": 4.0083, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.495256370863287e-05, + "loss": 4.0136, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.494417776112235e-05, + "loss": 4.0028, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.493579181361183e-05, + "loss": 4.0025, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.492740586610131e-05, + "loss": 4.0016, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.491903629739452e-05, + "loss": 4.0169, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.4910650349884e-05, + "loss": 4.0147, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.490226440237349e-05, + "loss": 4.0176, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.489387845486297e-05, + "loss": 4.0016, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.488549250735245e-05, + "loss": 4.0077, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.487710655984193e-05, + "loss": 3.9805, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.486872061233141e-05, + "loss": 4.0077, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.486033466482089e-05, + "loss": 4.007, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.485194871731037e-05, + "loss": 3.9977, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.484356276979985e-05, + "loss": 4.008, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.483517682228933e-05, + "loss": 4.0118, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.482679087477881e-05, + "loss": 4.0102, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.481840492726828e-05, + "loss": 4.0159, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.481001897975776e-05, + "loss": 4.0061, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.480163303224724e-05, + "loss": 4.0084, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.479324708473672e-05, + "loss": 4.0041, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.478487751602994e-05, + "loss": 4.0016, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.477649156851942e-05, + "loss": 4.0113, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.47681056210089e-05, + "loss": 4.0032, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.475971967349838e-05, + "loss": 3.9944, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.4751350104791586e-05, + "loss": 4.0013, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.4742964157281066e-05, + "loss": 4.0092, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.473459458857428e-05, + "loss": 4.0101, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.4726208641063755e-05, + "loss": 4.0105, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.4717822693553235e-05, + "loss": 4.0036, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.4709436746042715e-05, + "loss": 4.0065, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.4701050798532195e-05, + "loss": 4.0133, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.4692664851021675e-05, + "loss": 3.9932, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.4684278903511155e-05, + "loss": 3.9983, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.467589295600064e-05, + "loss": 3.9985, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.466750700849012e-05, + "loss": 3.998, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.465913743978333e-05, + "loss": 4.0076, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.465075149227281e-05, + "loss": 4.0034, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.464238192356602e-05, + "loss": 4.0063, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.46339959760555e-05, + "loss": 4.006, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.462561002854498e-05, + "loss": 4.0051, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.461722408103446e-05, + "loss": 4.0047, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.460883813352394e-05, + "loss": 4.0146, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.460045218601342e-05, + "loss": 3.978, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.459208261730663e-05, + "loss": 4.0164, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.458369666979611e-05, + "loss": 3.9993, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.4575310722285595e-05, + "loss": 4.0087, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.4566924774775075e-05, + "loss": 3.9961, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.4558538827264555e-05, + "loss": 3.9986, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.4550152879754035e-05, + "loss": 3.9904, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.4541766932243515e-05, + "loss": 3.9941, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.4533380984732995e-05, + "loss": 4.005, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.4525011416026204e-05, + "loss": 3.9877, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.4516625468515684e-05, + "loss": 4.0162, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.4508239521005164e-05, + "loss": 4.0006, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.4499853573494644e-05, + "loss": 3.9795, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.449148400478785e-05, + "loss": 4.009, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.448309805727733e-05, + "loss": 3.9878, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.447471210976681e-05, + "loss": 3.9884, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.446632616225629e-05, + "loss": 4.0019, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.445795659354951e-05, + "loss": 4.0002, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.444957064603899e-05, + "loss": 3.9905, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.444118469852847e-05, + "loss": 3.9948, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.443279875101794e-05, + "loss": 3.9854, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.442442918231116e-05, + "loss": 3.9956, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.441604323480064e-05, + "loss": 4.0085, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.440765728729012e-05, + "loss": 4.001, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.439927133977959e-05, + "loss": 4.0043, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.439090177107281e-05, + "loss": 4.0005, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.438251582356229e-05, + "loss": 4.0127, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.437412987605177e-05, + "loss": 3.9952, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.436576030734498e-05, + "loss": 4.0051, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.435737435983446e-05, + "loss": 3.9896, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.434898841232394e-05, + "loss": 3.9873, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.4340602464813416e-05, + "loss": 3.9993, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.4332216517302896e-05, + "loss": 3.999, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.4323830569792376e-05, + "loss": 4.0093, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.4315444622281856e-05, + "loss": 4.0098, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.4307075053575065e-05, + "loss": 3.9847, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.4298689106064545e-05, + "loss": 3.9909, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.4290303158554025e-05, + "loss": 3.9983, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.4281917211043505e-05, + "loss": 4.0005, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.4273531263532985e-05, + "loss": 3.9923, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.42651616948262e-05, + "loss": 4.0057, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.425677574731568e-05, + "loss": 4.0051, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.424838979980516e-05, + "loss": 3.9919, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.424002023109837e-05, + "loss": 3.991, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.423163428358785e-05, + "loss": 3.9926, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.422324833607733e-05, + "loss": 4.0001, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.421486238856681e-05, + "loss": 4.003, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.420647644105629e-05, + "loss": 3.998, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.419809049354577e-05, + "loss": 3.994, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.418972092483898e-05, + "loss": 3.9874, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.418133497732846e-05, + "loss": 4.0072, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.417294902981794e-05, + "loss": 4.0051, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.416456308230742e-05, + "loss": 4.0004, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.4156177134796905e-05, + "loss": 3.992, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.4147791187286385e-05, + "loss": 3.9952, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.4139405239775865e-05, + "loss": 3.9922, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.4131019292265345e-05, + "loss": 3.988, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.4122633344754825e-05, + "loss": 3.991, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.4114263776048034e-05, + "loss": 3.9898, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.410589420734124e-05, + "loss": 3.9953, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.409750825983072e-05, + "loss": 4.0002, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.40891223123202e-05, + "loss": 3.9861, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.408073636480968e-05, + "loss": 3.9897, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.407235041729916e-05, + "loss": 3.9954, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.406398084859237e-05, + "loss": 4.0003, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.405559490108186e-05, + "loss": 3.9868, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.404720895357134e-05, + "loss": 4.0017, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.403882300606082e-05, + "loss": 3.995, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.40304370585503e-05, + "loss": 4.0072, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.402205111103978e-05, + "loss": 3.9993, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.401368154233299e-05, + "loss": 3.9919, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.400529559482247e-05, + "loss": 3.9953, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.399690964731195e-05, + "loss": 4.0064, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.398852369980142e-05, + "loss": 3.986, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.39801377522909e-05, + "loss": 3.9942, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.3971768183584117e-05, + "loss": 3.9931, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.3963382236073596e-05, + "loss": 3.9969, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.3954996288563076e-05, + "loss": 3.9928, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.3946610341052556e-05, + "loss": 3.9839, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.3938224393542036e-05, + "loss": 3.9906, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.392985482483525e-05, + "loss": 3.987, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.3921468877324725e-05, + "loss": 4.0056, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.3913082929814205e-05, + "loss": 3.9951, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.3904696982303685e-05, + "loss": 4.0002, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.3896311034793165e-05, + "loss": 3.9846, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.3887925087282645e-05, + "loss": 4.0015, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.3879539139772125e-05, + "loss": 4.0043, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.3871153192261605e-05, + "loss": 3.9982, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.3862783623554814e-05, + "loss": 3.9928, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.3854397676044294e-05, + "loss": 3.986, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.3846011728533774e-05, + "loss": 4.01, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.383762578102326e-05, + "loss": 4.0029, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.382923983351274e-05, + "loss": 3.997, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.382087026480595e-05, + "loss": 3.9896, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.381248431729543e-05, + "loss": 4.0044, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.380409836978491e-05, + "loss": 3.9922, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.379571242227439e-05, + "loss": 3.9832, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.378732647476387e-05, + "loss": 4.0057, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.377897328486081e-05, + "loss": 3.9925, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.377058733735029e-05, + "loss": 4.0046, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.376220138983977e-05, + "loss": 3.9942, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 4.040131092071533, + "eval_runtime": 298.5788, + "eval_samples_per_second": 1278.024, + "eval_steps_per_second": 39.939, + "step": 992160 + }, + { + "epoch": 1.0, + "learning_rate": 3.375381544232925e-05, + "loss": 3.9869, + "step": 992256 + }, + { + "epoch": 1.0, + "learning_rate": 3.374542949481873e-05, + "loss": 3.972, + "step": 992768 + }, + { + "epoch": 1.0, + "learning_rate": 3.3737059926111944e-05, + "loss": 3.9907, + "step": 993280 + }, + { + "epoch": 1.0, + "learning_rate": 3.3728673978601424e-05, + "loss": 4.0021, + "step": 993792 + }, + { + "epoch": 1.0, + "learning_rate": 3.372030440989463e-05, + "loss": 3.9949, + "step": 994304 + }, + { + "epoch": 1.0, + "learning_rate": 3.371191846238411e-05, + "loss": 3.9956, + "step": 994816 + }, + { + "epoch": 1.0, + "learning_rate": 3.370353251487359e-05, + "loss": 3.9959, + "step": 995328 + }, + { + "epoch": 1.0, + "learning_rate": 3.369514656736307e-05, + "loss": 3.9889, + "step": 995840 + }, + { + "epoch": 1.0, + "learning_rate": 3.368676061985255e-05, + "loss": 3.9861, + "step": 996352 + }, + { + "epoch": 1.0, + "learning_rate": 3.367837467234203e-05, + "loss": 3.9889, + "step": 996864 + }, + { + "epoch": 1.0, + "learning_rate": 3.366998872483151e-05, + "loss": 4.0011, + "step": 997376 + }, + { + "epoch": 1.0, + "learning_rate": 3.366160277732099e-05, + "loss": 3.9963, + "step": 997888 + }, + { + "epoch": 1.0, + "learning_rate": 3.36532332086142e-05, + "loss": 4.0081, + "step": 998400 + }, + { + "epoch": 1.0, + "learning_rate": 3.364484726110368e-05, + "loss": 3.9813, + "step": 998912 + }, + { + "epoch": 1.0, + "learning_rate": 3.363646131359317e-05, + "loss": 3.9874, + "step": 999424 + }, + { + "epoch": 1.0, + "learning_rate": 3.362807536608265e-05, + "loss": 3.9735, + "step": 999936 + }, + { + "epoch": 1.0, + "learning_rate": 3.361968941857213e-05, + "loss": 3.9883, + "step": 1000448 + }, + { + "epoch": 1.0, + "learning_rate": 3.361130347106161e-05, + "loss": 3.9949, + "step": 1000960 + }, + { + "epoch": 1.0, + "learning_rate": 3.360291752355109e-05, + "loss": 3.9862, + "step": 1001472 + }, + { + "epoch": 1.0, + "learning_rate": 3.359453157604056e-05, + "loss": 3.9857, + "step": 1001984 + }, + { + "epoch": 1.0, + "learning_rate": 3.358616200733378e-05, + "loss": 4.0033, + "step": 1002496 + }, + { + "epoch": 1.0, + "learning_rate": 3.357777605982326e-05, + "loss": 3.9938, + "step": 1003008 + }, + { + "epoch": 1.0, + "learning_rate": 3.356939011231273e-05, + "loss": 3.9994, + "step": 1003520 + }, + { + "epoch": 1.0, + "learning_rate": 3.356100416480221e-05, + "loss": 3.9939, + "step": 1004032 + }, + { + "epoch": 1.0, + "learning_rate": 3.355261821729169e-05, + "loss": 3.995, + "step": 1004544 + }, + { + "epoch": 1.0, + "learning_rate": 3.354423226978117e-05, + "loss": 3.9867, + "step": 1005056 + }, + { + "epoch": 1.0, + "learning_rate": 3.353584632227065e-05, + "loss": 3.9859, + "step": 1005568 + }, + { + "epoch": 1.0, + "learning_rate": 3.352746037476014e-05, + "loss": 3.9966, + "step": 1006080 + }, + { + "epoch": 1.0, + "learning_rate": 3.3519090806053346e-05, + "loss": 3.9902, + "step": 1006592 + }, + { + "epoch": 1.0, + "learning_rate": 3.3510704858542826e-05, + "loss": 3.9745, + "step": 1007104 + }, + { + "epoch": 1.01, + "learning_rate": 3.3502318911032306e-05, + "loss": 3.991, + "step": 1007616 + }, + { + "epoch": 1.01, + "learning_rate": 3.3493932963521786e-05, + "loss": 3.9917, + "step": 1008128 + }, + { + "epoch": 1.01, + "learning_rate": 3.3485563394814995e-05, + "loss": 3.9955, + "step": 1008640 + }, + { + "epoch": 1.01, + "learning_rate": 3.3477177447304475e-05, + "loss": 3.9921, + "step": 1009152 + }, + { + "epoch": 1.01, + "learning_rate": 3.3468791499793955e-05, + "loss": 3.9911, + "step": 1009664 + }, + { + "epoch": 1.01, + "learning_rate": 3.3460421931087164e-05, + "loss": 3.9942, + "step": 1010176 + }, + { + "epoch": 1.01, + "learning_rate": 3.3452035983576644e-05, + "loss": 3.9977, + "step": 1010688 + }, + { + "epoch": 1.01, + "learning_rate": 3.3443650036066124e-05, + "loss": 3.9733, + "step": 1011200 + }, + { + "epoch": 1.01, + "learning_rate": 3.3435264088555604e-05, + "loss": 3.9841, + "step": 1011712 + }, + { + "epoch": 1.01, + "learning_rate": 3.342687814104509e-05, + "loss": 3.9803, + "step": 1012224 + }, + { + "epoch": 1.01, + "learning_rate": 3.341849219353457e-05, + "loss": 3.9838, + "step": 1012736 + }, + { + "epoch": 1.01, + "learning_rate": 3.341010624602405e-05, + "loss": 3.9973, + "step": 1013248 + }, + { + "epoch": 1.01, + "learning_rate": 3.340172029851353e-05, + "loss": 3.9917, + "step": 1013760 + }, + { + "epoch": 1.01, + "learning_rate": 3.339335072980674e-05, + "loss": 3.9899, + "step": 1014272 + }, + { + "epoch": 1.01, + "learning_rate": 3.338496478229622e-05, + "loss": 3.9911, + "step": 1014784 + }, + { + "epoch": 1.01, + "learning_rate": 3.33765788347857e-05, + "loss": 3.9869, + "step": 1015296 + }, + { + "epoch": 1.01, + "learning_rate": 3.336819288727518e-05, + "loss": 3.9897, + "step": 1015808 + }, + { + "epoch": 1.01, + "learning_rate": 3.335982331856839e-05, + "loss": 3.9976, + "step": 1016320 + }, + { + "epoch": 1.01, + "learning_rate": 3.335143737105787e-05, + "loss": 3.9643, + "step": 1016832 + }, + { + "epoch": 1.01, + "learning_rate": 3.334305142354735e-05, + "loss": 3.9981, + "step": 1017344 + }, + { + "epoch": 1.01, + "learning_rate": 3.333468185484056e-05, + "loss": 3.989, + "step": 1017856 + }, + { + "epoch": 1.01, + "learning_rate": 3.3326295907330044e-05, + "loss": 3.9929, + "step": 1018368 + }, + { + "epoch": 1.01, + "learning_rate": 3.3317909959819524e-05, + "loss": 3.9828, + "step": 1018880 + }, + { + "epoch": 1.01, + "learning_rate": 3.3309524012309004e-05, + "loss": 3.9804, + "step": 1019392 + }, + { + "epoch": 1.01, + "learning_rate": 3.3301138064798484e-05, + "loss": 3.9804, + "step": 1019904 + }, + { + "epoch": 1.01, + "learning_rate": 3.3292752117287964e-05, + "loss": 3.9787, + "step": 1020416 + }, + { + "epoch": 1.01, + "learning_rate": 3.328438254858117e-05, + "loss": 3.9887, + "step": 1020928 + }, + { + "epoch": 1.01, + "learning_rate": 3.327599660107065e-05, + "loss": 3.9718, + "step": 1021440 + }, + { + "epoch": 1.01, + "learning_rate": 3.326761065356013e-05, + "loss": 4.0031, + "step": 1021952 + }, + { + "epoch": 1.01, + "learning_rate": 3.325922470604961e-05, + "loss": 3.9852, + "step": 1022464 + }, + { + "epoch": 1.01, + "learning_rate": 3.325083875853909e-05, + "loss": 3.9661, + "step": 1022976 + }, + { + "epoch": 1.01, + "learning_rate": 3.3242452811028566e-05, + "loss": 3.9922, + "step": 1023488 + }, + { + "epoch": 1.01, + "learning_rate": 3.323408324232178e-05, + "loss": 3.9715, + "step": 1024000 + }, + { + "epoch": 1.01, + "learning_rate": 3.322569729481126e-05, + "loss": 3.9765, + "step": 1024512 + }, + { + "epoch": 1.01, + "learning_rate": 3.321731134730074e-05, + "loss": 3.9835, + "step": 1025024 + }, + { + "epoch": 1.01, + "learning_rate": 3.320892539979022e-05, + "loss": 3.9883, + "step": 1025536 + }, + { + "epoch": 1.01, + "learning_rate": 3.32005394522797e-05, + "loss": 3.9725, + "step": 1026048 + }, + { + "epoch": 1.01, + "learning_rate": 3.319215350476918e-05, + "loss": 3.9859, + "step": 1026560 + }, + { + "epoch": 1.01, + "learning_rate": 3.318376755725866e-05, + "loss": 3.9676, + "step": 1027072 + }, + { + "epoch": 1.01, + "learning_rate": 3.317538160974814e-05, + "loss": 3.9803, + "step": 1027584 + }, + { + "epoch": 1.01, + "learning_rate": 3.316701204104135e-05, + "loss": 3.9954, + "step": 1028096 + }, + { + "epoch": 1.01, + "learning_rate": 3.315862609353083e-05, + "loss": 3.983, + "step": 1028608 + }, + { + "epoch": 1.01, + "learning_rate": 3.315025652482404e-05, + "loss": 3.9902, + "step": 1029120 + }, + { + "epoch": 1.01, + "learning_rate": 3.314187057731352e-05, + "loss": 3.9835, + "step": 1029632 + }, + { + "epoch": 1.01, + "learning_rate": 3.3133484629803e-05, + "loss": 4.002, + "step": 1030144 + }, + { + "epoch": 1.01, + "learning_rate": 3.312509868229248e-05, + "loss": 3.9804, + "step": 1030656 + }, + { + "epoch": 1.01, + "learning_rate": 3.3116729113585695e-05, + "loss": 3.9883, + "step": 1031168 + }, + { + "epoch": 1.01, + "learning_rate": 3.3108343166075175e-05, + "loss": 3.9777, + "step": 1031680 + }, + { + "epoch": 1.01, + "learning_rate": 3.3099957218564655e-05, + "loss": 3.9745, + "step": 1032192 + }, + { + "epoch": 1.01, + "learning_rate": 3.3091571271054135e-05, + "loss": 3.9861, + "step": 1032704 + }, + { + "epoch": 1.01, + "learning_rate": 3.3083185323543615e-05, + "loss": 3.9814, + "step": 1033216 + }, + { + "epoch": 1.01, + "learning_rate": 3.3074799376033095e-05, + "loss": 3.9917, + "step": 1033728 + }, + { + "epoch": 1.01, + "learning_rate": 3.3066413428522575e-05, + "loss": 3.9959, + "step": 1034240 + }, + { + "epoch": 1.01, + "learning_rate": 3.3058027481012055e-05, + "loss": 3.9763, + "step": 1034752 + }, + { + "epoch": 1.01, + "learning_rate": 3.3049641533501535e-05, + "loss": 3.9718, + "step": 1035264 + }, + { + "epoch": 1.01, + "learning_rate": 3.3041255585991015e-05, + "loss": 3.981, + "step": 1035776 + }, + { + "epoch": 1.01, + "learning_rate": 3.3032869638480495e-05, + "loss": 3.9879, + "step": 1036288 + }, + { + "epoch": 1.01, + "learning_rate": 3.3024483690969975e-05, + "loss": 3.9805, + "step": 1036800 + }, + { + "epoch": 1.01, + "learning_rate": 3.3016114122263184e-05, + "loss": 3.9877, + "step": 1037312 + }, + { + "epoch": 1.01, + "learning_rate": 3.3007728174752664e-05, + "loss": 3.9885, + "step": 1037824 + }, + { + "epoch": 1.02, + "learning_rate": 3.299935860604588e-05, + "loss": 3.9802, + "step": 1038336 + }, + { + "epoch": 1.02, + "learning_rate": 3.299097265853536e-05, + "loss": 3.9812, + "step": 1038848 + }, + { + "epoch": 1.02, + "learning_rate": 3.298258671102484e-05, + "loss": 3.9707, + "step": 1039360 + }, + { + "epoch": 1.02, + "learning_rate": 3.297421714231805e-05, + "loss": 3.9905, + "step": 1039872 + }, + { + "epoch": 1.02, + "learning_rate": 3.296583119480753e-05, + "loss": 3.9864, + "step": 1040384 + }, + { + "epoch": 1.02, + "learning_rate": 3.295744524729701e-05, + "loss": 3.9847, + "step": 1040896 + }, + { + "epoch": 1.02, + "learning_rate": 3.294905929978649e-05, + "loss": 3.9779, + "step": 1041408 + }, + { + "epoch": 1.02, + "learning_rate": 3.294067335227597e-05, + "loss": 3.9738, + "step": 1041920 + }, + { + "epoch": 1.02, + "learning_rate": 3.293228740476545e-05, + "loss": 3.9914, + "step": 1042432 + }, + { + "epoch": 1.02, + "learning_rate": 3.292390145725493e-05, + "loss": 3.9901, + "step": 1042944 + }, + { + "epoch": 1.02, + "learning_rate": 3.29155155097444e-05, + "loss": 3.9837, + "step": 1043456 + }, + { + "epoch": 1.02, + "learning_rate": 3.290712956223388e-05, + "loss": 3.978, + "step": 1043968 + }, + { + "epoch": 1.02, + "learning_rate": 3.289874361472337e-05, + "loss": 3.9799, + "step": 1044480 + }, + { + "epoch": 1.02, + "learning_rate": 3.289035766721285e-05, + "loss": 3.9829, + "step": 1044992 + }, + { + "epoch": 1.02, + "learning_rate": 3.288197171970233e-05, + "loss": 3.9764, + "step": 1045504 + }, + { + "epoch": 1.02, + "learning_rate": 3.287358577219181e-05, + "loss": 3.9724, + "step": 1046016 + }, + { + "epoch": 1.02, + "learning_rate": 3.286523258228875e-05, + "loss": 3.9762, + "step": 1046528 + }, + { + "epoch": 1.02, + "learning_rate": 3.2856846634778227e-05, + "loss": 3.9806, + "step": 1047040 + }, + { + "epoch": 1.02, + "learning_rate": 3.2848460687267707e-05, + "loss": 3.9869, + "step": 1047552 + }, + { + "epoch": 1.02, + "learning_rate": 3.2840074739757186e-05, + "loss": 3.9718, + "step": 1048064 + }, + { + "epoch": 1.02, + "learning_rate": 3.2831688792246666e-05, + "loss": 3.9781, + "step": 1048576 + }, + { + "epoch": 1.02, + "learning_rate": 3.2823302844736146e-05, + "loss": 3.975, + "step": 1049088 + }, + { + "epoch": 1.02, + "learning_rate": 3.2814933276029355e-05, + "loss": 3.9865, + "step": 1049600 + }, + { + "epoch": 1.02, + "learning_rate": 3.2806547328518835e-05, + "loss": 3.9728, + "step": 1050112 + }, + { + "epoch": 1.02, + "learning_rate": 3.279816138100832e-05, + "loss": 3.9802, + "step": 1050624 + }, + { + "epoch": 1.02, + "learning_rate": 3.27897754334978e-05, + "loss": 3.9848, + "step": 1051136 + }, + { + "epoch": 1.02, + "learning_rate": 3.278138948598728e-05, + "loss": 3.9949, + "step": 1051648 + }, + { + "epoch": 1.02, + "learning_rate": 3.277300353847676e-05, + "loss": 3.9819, + "step": 1052160 + }, + { + "epoch": 1.02, + "learning_rate": 3.276463396976997e-05, + "loss": 3.9765, + "step": 1052672 + }, + { + "epoch": 1.02, + "learning_rate": 3.275624802225945e-05, + "loss": 3.9827, + "step": 1053184 + }, + { + "epoch": 1.02, + "learning_rate": 3.274787845355266e-05, + "loss": 3.9872, + "step": 1053696 + }, + { + "epoch": 1.02, + "learning_rate": 3.273949250604214e-05, + "loss": 3.9733, + "step": 1054208 + }, + { + "epoch": 1.02, + "learning_rate": 3.273110655853162e-05, + "loss": 3.9789, + "step": 1054720 + }, + { + "epoch": 1.02, + "learning_rate": 3.27227206110211e-05, + "loss": 3.9762, + "step": 1055232 + }, + { + "epoch": 1.02, + "learning_rate": 3.271433466351058e-05, + "loss": 3.9834, + "step": 1055744 + }, + { + "epoch": 1.02, + "learning_rate": 3.270594871600006e-05, + "loss": 3.9773, + "step": 1056256 + }, + { + "epoch": 1.02, + "learning_rate": 3.269756276848954e-05, + "loss": 3.9713, + "step": 1056768 + }, + { + "epoch": 1.02, + "learning_rate": 3.268917682097902e-05, + "loss": 3.978, + "step": 1057280 + }, + { + "epoch": 1.02, + "learning_rate": 3.26807908734685e-05, + "loss": 3.9731, + "step": 1057792 + }, + { + "epoch": 1.02, + "learning_rate": 3.2672404925957987e-05, + "loss": 3.9873, + "step": 1058304 + }, + { + "epoch": 1.02, + "learning_rate": 3.2664018978447467e-05, + "loss": 3.9832, + "step": 1058816 + }, + { + "epoch": 1.02, + "learning_rate": 3.2655649409740676e-05, + "loss": 3.9863, + "step": 1059328 + }, + { + "epoch": 1.02, + "learning_rate": 3.2647279841033885e-05, + "loss": 3.9727, + "step": 1059840 + }, + { + "epoch": 1.02, + "learning_rate": 3.2638893893523365e-05, + "loss": 3.9861, + "step": 1060352 + }, + { + "epoch": 1.02, + "learning_rate": 3.2630507946012845e-05, + "loss": 3.9899, + "step": 1060864 + }, + { + "epoch": 1.02, + "learning_rate": 3.2622121998502325e-05, + "loss": 3.9808, + "step": 1061376 + }, + { + "epoch": 1.02, + "learning_rate": 3.2613736050991805e-05, + "loss": 3.9809, + "step": 1061888 + }, + { + "epoch": 1.02, + "learning_rate": 3.2605350103481284e-05, + "loss": 3.9741, + "step": 1062400 + }, + { + "epoch": 1.02, + "learning_rate": 3.2596964155970764e-05, + "loss": 3.9925, + "step": 1062912 + }, + { + "epoch": 1.02, + "learning_rate": 3.2588594587263974e-05, + "loss": 3.9911, + "step": 1063424 + }, + { + "epoch": 1.02, + "learning_rate": 3.2580208639753453e-05, + "loss": 3.9824, + "step": 1063936 + }, + { + "epoch": 1.02, + "learning_rate": 3.257182269224294e-05, + "loss": 3.9765, + "step": 1064448 + }, + { + "epoch": 1.02, + "learning_rate": 3.2563436744732413e-05, + "loss": 3.993, + "step": 1064960 + }, + { + "epoch": 1.02, + "learning_rate": 3.255505079722189e-05, + "loss": 3.9758, + "step": 1065472 + }, + { + "epoch": 1.02, + "learning_rate": 3.254666484971137e-05, + "loss": 3.9679, + "step": 1065984 + }, + { + "epoch": 1.02, + "learning_rate": 3.253827890220085e-05, + "loss": 3.9917, + "step": 1066496 + }, + { + "epoch": 1.02, + "learning_rate": 3.252989295469033e-05, + "loss": 3.9765, + "step": 1067008 + }, + { + "epoch": 1.02, + "learning_rate": 3.252152338598354e-05, + "loss": 3.9937, + "step": 1067520 + }, + { + "epoch": 1.02, + "learning_rate": 3.251315381727676e-05, + "loss": 3.9738, + "step": 1068032 + }, + { + "epoch": 1.03, + "eval_loss": 4.031523704528809, + "eval_runtime": 298.7009, + "eval_samples_per_second": 1277.502, + "eval_steps_per_second": 39.923, + "step": 1068480 + }, + { + "epoch": 0.0, + "learning_rate": 3.250476786976624e-05, + "loss": 3.9761, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.249638192225571e-05, + "loss": 3.9642, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.248799597474519e-05, + "loss": 3.9741, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.247961002723468e-05, + "loss": 3.988, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.247122407972416e-05, + "loss": 3.983, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.246283813221364e-05, + "loss": 3.9797, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.245445218470312e-05, + "loss": 3.9766, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.24460662371926e-05, + "loss": 3.9753, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.243768028968208e-05, + "loss": 3.9727, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.242929434217156e-05, + "loss": 3.9761, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.242090839466104e-05, + "loss": 3.9834, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.241252244715052e-05, + "loss": 3.9873, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.240415287844373e-05, + "loss": 3.9879, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.239576693093321e-05, + "loss": 3.9688, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.238738098342269e-05, + "loss": 3.9778, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.237899503591217e-05, + "loss": 3.9564, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.2370609088401647e-05, + "loss": 3.9734, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.2362223140891127e-05, + "loss": 3.9757, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.2353837193380606e-05, + "loss": 3.9743, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.2345451245870086e-05, + "loss": 3.9682, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.2337065298359566e-05, + "loss": 3.9917, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.2328679350849046e-05, + "loss": 3.9774, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.2320293403338526e-05, + "loss": 3.9843, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.2311907455828006e-05, + "loss": 3.9771, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.2303537887121215e-05, + "loss": 3.9864, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.2295151939610695e-05, + "loss": 3.9691, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.2286765992100175e-05, + "loss": 3.9719, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.2278380044589655e-05, + "loss": 3.9841, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.2269994097079135e-05, + "loss": 3.9744, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.2261608149568615e-05, + "loss": 3.9638, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.2253238580861824e-05, + "loss": 3.9741, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.224485263335131e-05, + "loss": 3.9763, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.223646668584079e-05, + "loss": 3.9848, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.2228097117134e-05, + "loss": 3.979, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.221971116962348e-05, + "loss": 3.9751, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.221134160091669e-05, + "loss": 3.9821, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.220295565340617e-05, + "loss": 3.9832, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.219456970589565e-05, + "loss": 3.9594, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.218618375838513e-05, + "loss": 3.9728, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.217779781087461e-05, + "loss": 3.9633, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.216941186336409e-05, + "loss": 3.9685, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.216102591585357e-05, + "loss": 3.9816, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.215265634714678e-05, + "loss": 3.9812, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.2144270399636265e-05, + "loss": 3.9713, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.2135884452125745e-05, + "loss": 3.9783, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.2127498504615225e-05, + "loss": 3.9778, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.2119112557104705e-05, + "loss": 3.9706, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.2110726609594184e-05, + "loss": 3.9826, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.2102340662083664e-05, + "loss": 3.9526, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.2093971093376874e-05, + "loss": 3.9797, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.2085585145866353e-05, + "loss": 3.9777, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.2077199198355833e-05, + "loss": 3.9819, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.206881325084531e-05, + "loss": 3.9673, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.206044368213852e-05, + "loss": 3.9675, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.2052057734628e-05, + "loss": 3.9644, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.204367178711748e-05, + "loss": 3.9647, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.203528583960696e-05, + "loss": 3.9733, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.202689989209644e-05, + "loss": 3.958, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.201851394458592e-05, + "loss": 3.9845, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.201014437587914e-05, + "loss": 3.9721, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.200175842836861e-05, + "loss": 3.9586, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.199337248085809e-05, + "loss": 3.975, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.198498653334757e-05, + "loss": 3.957, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.197660058583705e-05, + "loss": 3.9626, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.196821463832653e-05, + "loss": 3.9686, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.195982869081601e-05, + "loss": 3.9765, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.195145912210922e-05, + "loss": 3.9572, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.19430731745987e-05, + "loss": 3.9682, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.193468722708819e-05, + "loss": 3.9535, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.192630127957767e-05, + "loss": 3.9682, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.1917931710870876e-05, + "loss": 3.9784, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.1909545763360356e-05, + "loss": 3.9759, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.1901159815849836e-05, + "loss": 3.9705, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.1892773868339316e-05, + "loss": 3.9729, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.1884387920828796e-05, + "loss": 3.9874, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.1876001973318276e-05, + "loss": 3.9654, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.1867632404611485e-05, + "loss": 3.9719, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.1859246457100965e-05, + "loss": 3.9646, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.1850860509590445e-05, + "loss": 3.9624, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.1842474562079925e-05, + "loss": 3.9734, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.1834088614569405e-05, + "loss": 3.9648, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.182571904586262e-05, + "loss": 3.9795, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.18173330983521e-05, + "loss": 3.9814, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.180894715084158e-05, + "loss": 3.9692, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.180056120333106e-05, + "loss": 3.9562, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.179217525582054e-05, + "loss": 3.9667, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.178378930831002e-05, + "loss": 3.972, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.17754033607995e-05, + "loss": 3.9702, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.1767017413288973e-05, + "loss": 3.9741, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.175866422338592e-05, + "loss": 3.9738, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.17502782758754e-05, + "loss": 3.9689, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.174189232836488e-05, + "loss": 3.9646, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.173350638085436e-05, + "loss": 3.964, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.172512043334384e-05, + "loss": 3.9709, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.171673448583332e-05, + "loss": 3.9769, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.17083485383228e-05, + "loss": 3.9694, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.169996259081228e-05, + "loss": 3.9653, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.1691593022105494e-05, + "loss": 3.9613, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.16832234533987e-05, + "loss": 3.9785, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.167485388469191e-05, + "loss": 3.9756, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.166646793718139e-05, + "loss": 3.969, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.165808198967087e-05, + "loss": 3.9676, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.164969604216035e-05, + "loss": 3.9628, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.164131009464983e-05, + "loss": 3.9672, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.163292414713931e-05, + "loss": 3.9665, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.162453819962879e-05, + "loss": 3.9578, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.161615225211827e-05, + "loss": 3.9641, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.160776630460775e-05, + "loss": 3.9649, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.159938035709723e-05, + "loss": 3.9744, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.159099440958671e-05, + "loss": 3.9578, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.158260846207619e-05, + "loss": 3.9665, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.15742388933694e-05, + "loss": 3.9575, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.156585294585888e-05, + "loss": 3.977, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.155746699834836e-05, + "loss": 3.9603, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.154908105083784e-05, + "loss": 3.9663, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.154071148213105e-05, + "loss": 3.9727, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.153232553462053e-05, + "loss": 3.9797, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.1523955965913746e-05, + "loss": 3.9679, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.1515570018403226e-05, + "loss": 3.9606, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.1507184070892705e-05, + "loss": 3.9723, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.1498798123382185e-05, + "loss": 3.9739, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.1490412175871665e-05, + "loss": 3.9579, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.1482026228361145e-05, + "loss": 3.9649, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.1473640280850625e-05, + "loss": 3.9655, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.1465254333340105e-05, + "loss": 3.9709, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.1456884764633314e-05, + "loss": 3.965, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.1448498817122794e-05, + "loss": 3.9551, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.1440129248416003e-05, + "loss": 3.9675, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.143174330090548e-05, + "loss": 3.9622, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.142335735339496e-05, + "loss": 3.968, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.141497140588445e-05, + "loss": 3.973, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.140658545837393e-05, + "loss": 3.969, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.139821588966714e-05, + "loss": 3.965, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.138982994215662e-05, + "loss": 3.9664, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.13814439946461e-05, + "loss": 3.9796, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.137305804713558e-05, + "loss": 3.9673, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.136467209962506e-05, + "loss": 3.969, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.135630253091827e-05, + "loss": 3.9593, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.134791658340775e-05, + "loss": 3.9855, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.133954701470096e-05, + "loss": 3.9717, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.133116106719044e-05, + "loss": 3.9727, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.132277511967992e-05, + "loss": 3.9627, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.1314389172169404e-05, + "loss": 3.9747, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.1306003224658884e-05, + "loss": 3.9638, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.1297617277148364e-05, + "loss": 3.9545, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.128924770844157e-05, + "loss": 3.9808, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.128086176093105e-05, + "loss": 3.9664, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.127247581342053e-05, + "loss": 3.9786, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.126408986591001e-05, + "loss": 3.9598, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 4.024088382720947, + "eval_runtime": 291.2306, + "eval_samples_per_second": 1310.271, + "eval_steps_per_second": 40.947, + "step": 1144800 + }, + { + "epoch": 1.0, + "learning_rate": 3.125570391839949e-05, + "loss": 3.9602, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.124731797088897e-05, + "loss": 3.9535, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.123893202337845e-05, + "loss": 3.9613, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.1230546075867926e-05, + "loss": 3.9745, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.1222160128357406e-05, + "loss": 3.9701, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.1213774180846886e-05, + "loss": 3.9706, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.120538823333637e-05, + "loss": 3.9641, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.119700228582585e-05, + "loss": 3.9619, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.118861633831533e-05, + "loss": 3.9623, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.118024676960854e-05, + "loss": 3.9643, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.1171893579705486e-05, + "loss": 3.9686, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.1163507632194966e-05, + "loss": 3.9731, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.1155138063488175e-05, + "loss": 3.9774, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.1146752115977655e-05, + "loss": 3.9564, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.1138366168467135e-05, + "loss": 3.9659, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.1129980220956615e-05, + "loss": 3.9429, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.1121594273446095e-05, + "loss": 3.9634, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.1113208325935575e-05, + "loss": 3.9613, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.1104822378425055e-05, + "loss": 3.9612, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.1096436430914535e-05, + "loss": 3.9593, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.1088050483404015e-05, + "loss": 3.9755, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.1079664535893495e-05, + "loss": 3.9687, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.1071278588382975e-05, + "loss": 3.9655, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.1062892640872455e-05, + "loss": 3.9685, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.1054506693361935e-05, + "loss": 3.9751, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.1046120745851415e-05, + "loss": 3.9576, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.1037751177144624e-05, + "loss": 3.9585, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.1029365229634104e-05, + "loss": 3.9726, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.1020979282123584e-05, + "loss": 3.9574, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.101260971341679e-05, + "loss": 3.948, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.100422376590627e-05, + "loss": 3.963, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.099583781839576e-05, + "loss": 3.965, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.098745187088524e-05, + "loss": 3.9705, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.097906592337472e-05, + "loss": 3.965, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.09706799758642e-05, + "loss": 3.965, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.096231040715741e-05, + "loss": 3.9698, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.095392445964689e-05, + "loss": 3.9682, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.094553851213637e-05, + "loss": 3.9481, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.093715256462585e-05, + "loss": 3.9655, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.092878299591906e-05, + "loss": 3.9479, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.092039704840854e-05, + "loss": 3.9591, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.091201110089802e-05, + "loss": 3.9654, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.09036251533875e-05, + "loss": 3.97, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.089523920587698e-05, + "loss": 3.9615, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.088685325836646e-05, + "loss": 3.9634, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.0878467310855944e-05, + "loss": 3.9651, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.087008136334542e-05, + "loss": 3.9604, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.08616954158349e-05, + "loss": 3.9711, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.085330946832438e-05, + "loss": 3.9403, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.084492352081386e-05, + "loss": 3.9654, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.083653757330334e-05, + "loss": 3.9659, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.0828168004596546e-05, + "loss": 3.9701, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.0819782057086026e-05, + "loss": 3.9576, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.0811396109575506e-05, + "loss": 3.9565, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.0803010162064986e-05, + "loss": 3.9472, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.0794624214554466e-05, + "loss": 3.95, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.0786238267043946e-05, + "loss": 3.9676, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.0777852319533426e-05, + "loss": 3.948, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.076948275082664e-05, + "loss": 3.9675, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.076109680331612e-05, + "loss": 3.9605, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.07527108558056e-05, + "loss": 3.9457, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.074432490829508e-05, + "loss": 3.9628, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.073593896078456e-05, + "loss": 3.9444, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.072755301327404e-05, + "loss": 3.9505, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.071916706576352e-05, + "loss": 3.9561, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.0710781118253e-05, + "loss": 3.9692, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.070241154954621e-05, + "loss": 3.9466, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.069402560203569e-05, + "loss": 3.9521, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.068563965452517e-05, + "loss": 3.9412, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.067725370701465e-05, + "loss": 3.9559, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.0668884138307866e-05, + "loss": 3.9648, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.0660498190797346e-05, + "loss": 3.9651, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.0652112243286826e-05, + "loss": 3.956, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.0643726295776306e-05, + "loss": 3.9634, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.0635356727069515e-05, + "loss": 3.974, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.0626970779558995e-05, + "loss": 3.9559, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.0618584832048475e-05, + "loss": 3.9564, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.061019888453795e-05, + "loss": 3.9546, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.060181293702743e-05, + "loss": 3.9526, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.059342698951691e-05, + "loss": 3.9629, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.0585057420810124e-05, + "loss": 3.9534, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.0576671473299604e-05, + "loss": 3.9683, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.0568285525789084e-05, + "loss": 3.967, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.0559899578278564e-05, + "loss": 3.9575, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.0551513630768044e-05, + "loss": 3.9433, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.0543127683257524e-05, + "loss": 3.9564, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.0534741735747004e-05, + "loss": 3.9618, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.0526355788236484e-05, + "loss": 3.9597, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.051798621952969e-05, + "loss": 3.9595, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.0509616650822902e-05, + "loss": 3.9637, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.0501230703312382e-05, + "loss": 3.9588, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.0492844755801865e-05, + "loss": 3.9525, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.0484458808291345e-05, + "loss": 3.9497, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.0476072860780825e-05, + "loss": 3.9607, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.0467686913270305e-05, + "loss": 3.9625, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.0459300965759785e-05, + "loss": 3.9606, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.0450931397052994e-05, + "loss": 3.951, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.0442561828346207e-05, + "loss": 3.9509, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.0434192259639423e-05, + "loss": 3.9641, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.0425806312128896e-05, + "loss": 3.9644, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.0417420364618376e-05, + "loss": 3.9615, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.0409034417107856e-05, + "loss": 3.949, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.0400648469597336e-05, + "loss": 3.9515, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.039226252208682e-05, + "loss": 3.9576, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.03838765745763e-05, + "loss": 3.9562, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.037549062706578e-05, + "loss": 3.945, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.036710467955526e-05, + "loss": 3.9495, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.035871873204474e-05, + "loss": 3.9574, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.035033278453422e-05, + "loss": 3.9597, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.0341963215827428e-05, + "loss": 3.9506, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.033357726831691e-05, + "loss": 3.9611, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.032519132080639e-05, + "loss": 3.9405, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.031680537329587e-05, + "loss": 3.9689, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.030841942578535e-05, + "loss": 3.9457, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.030003347827483e-05, + "loss": 3.9567, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.029166390956804e-05, + "loss": 3.9622, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.028327796205752e-05, + "loss": 3.9675, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.0274892014547e-05, + "loss": 3.9547, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.0266522445840212e-05, + "loss": 3.9506, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.0258136498329692e-05, + "loss": 3.9576, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.0249750550819172e-05, + "loss": 3.9609, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.0241364603308652e-05, + "loss": 3.9497, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.0232978655798132e-05, + "loss": 3.9524, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.022459270828761e-05, + "loss": 3.9551, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.0216223139580825e-05, + "loss": 3.9643, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.0207837192070305e-05, + "loss": 3.9507, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.0199451244559785e-05, + "loss": 3.9448, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.0191065297049258e-05, + "loss": 3.9529, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.0182695728342474e-05, + "loss": 3.9545, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.0174309780831954e-05, + "loss": 3.9482, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.0165923833321437e-05, + "loss": 3.9671, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.015753788581091e-05, + "loss": 3.9622, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.014915193830039e-05, + "loss": 3.951, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.014076599078987e-05, + "loss": 3.954, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.013238004327935e-05, + "loss": 3.9674, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.012399409576883e-05, + "loss": 3.9583, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.0115608148258313e-05, + "loss": 3.9603, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.0107222200747793e-05, + "loss": 3.9508, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.0098852632041002e-05, + "loss": 3.9701, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.0090466684530482e-05, + "loss": 3.959, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.0082080737019962e-05, + "loss": 3.9624, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.0073694789509442e-05, + "loss": 3.9492, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.0065308841998922e-05, + "loss": 3.9672, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.0056922894488406e-05, + "loss": 3.9526, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.0048553325781615e-05, + "loss": 3.9431, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.0040167378271095e-05, + "loss": 3.9698, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.0031781430760575e-05, + "loss": 3.956, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.0023395483250055e-05, + "loss": 3.9647, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.0015025914543267e-05, + "loss": 3.9522, + "step": 1220608 + }, + { + "epoch": 1.03, + "learning_rate": 3.0006639967032747e-05, + "loss": 3.9496, + "step": 1221120 + }, + { + "epoch": 1.03, + "eval_loss": 4.018298625946045, + "eval_runtime": 314.2677, + "eval_samples_per_second": 1214.223, + "eval_steps_per_second": 37.945, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 2.9998254019522227e-05, + "loss": 3.9398, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.9989868072011707e-05, + "loss": 3.9482, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.9981482124501187e-05, + "loss": 3.9629, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.9973096176990667e-05, + "loss": 3.9578, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.9964710229480147e-05, + "loss": 3.9628, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.9956324281969623e-05, + "loss": 3.9544, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.9947938334459103e-05, + "loss": 3.9486, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.9939552386948583e-05, + "loss": 3.944, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.9931166439438063e-05, + "loss": 3.9594, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.9922780491927543e-05, + "loss": 3.9524, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.9914394544417023e-05, + "loss": 3.9682, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.9906024975710236e-05, + "loss": 3.967, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.9897639028199716e-05, + "loss": 3.9457, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.9889253080689195e-05, + "loss": 3.95, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.9880867133178675e-05, + "loss": 3.9338, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.9872481185668155e-05, + "loss": 3.9456, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.9864095238157635e-05, + "loss": 3.9551, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.9855709290647115e-05, + "loss": 3.947, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.9847323343136595e-05, + "loss": 3.9469, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.9838937395626075e-05, + "loss": 3.965, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.9830551448115555e-05, + "loss": 3.9557, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.982216550060504e-05, + "loss": 3.9537, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.981377955309451e-05, + "loss": 3.9563, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.980539360558399e-05, + "loss": 3.967, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.9797024036877208e-05, + "loss": 3.9437, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.9788638089366684e-05, + "loss": 3.9482, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.9780252141856164e-05, + "loss": 3.9629, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.9771866194345644e-05, + "loss": 3.9432, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.976351300444259e-05, + "loss": 3.9426, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.975512705693207e-05, + "loss": 3.9481, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.974674110942155e-05, + "loss": 3.9546, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.973835516191103e-05, + "loss": 3.9576, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.972996921440051e-05, + "loss": 3.9527, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.972159964569372e-05, + "loss": 3.9542, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.971323007698693e-05, + "loss": 3.958, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.9704860508280143e-05, + "loss": 3.9534, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.9696474560769623e-05, + "loss": 3.9435, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.9688088613259103e-05, + "loss": 3.9533, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.9679702665748583e-05, + "loss": 3.9358, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.9671316718238063e-05, + "loss": 3.9517, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.9662930770727543e-05, + "loss": 3.9505, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.9654544823217023e-05, + "loss": 3.9583, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.9646158875706503e-05, + "loss": 3.949, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.9637772928195983e-05, + "loss": 3.9528, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.962938698068546e-05, + "loss": 3.9529, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.962100103317494e-05, + "loss": 3.9495, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.961261508566442e-05, + "loss": 3.9622, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.96042291381539e-05, + "loss": 3.9284, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.959584319064338e-05, + "loss": 3.9541, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.958745724313286e-05, + "loss": 3.9572, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.957907129562234e-05, + "loss": 3.9584, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.957070172691555e-05, + "loss": 3.9448, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.956231577940503e-05, + "loss": 3.9442, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.955392983189451e-05, + "loss": 3.939, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.954556026318772e-05, + "loss": 3.9368, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.95371743156772e-05, + "loss": 3.9593, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.9528788368166684e-05, + "loss": 3.9354, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.9520402420656164e-05, + "loss": 3.9553, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.9512016473145644e-05, + "loss": 3.9523, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.9503630525635123e-05, + "loss": 3.9343, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.9495244578124603e-05, + "loss": 3.9511, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.9486891388221545e-05, + "loss": 3.9381, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.9478505440711025e-05, + "loss": 3.9409, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.9470119493200505e-05, + "loss": 3.944, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.9461733545689985e-05, + "loss": 3.9592, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.9453347598179465e-05, + "loss": 3.9365, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.9444961650668945e-05, + "loss": 3.9416, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.9436592081962154e-05, + "loss": 3.9317, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.9428206134451637e-05, + "loss": 3.9443, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.9419820186941117e-05, + "loss": 3.9526, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.9411434239430597e-05, + "loss": 3.9587, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.9403048291920077e-05, + "loss": 3.9427, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.9394662344409557e-05, + "loss": 3.9531, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.9386292775702766e-05, + "loss": 3.9631, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.9377906828192246e-05, + "loss": 3.9467, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.936952088068173e-05, + "loss": 3.9466, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.936113493317121e-05, + "loss": 3.9419, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.935274898566069e-05, + "loss": 3.9431, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.934436303815017e-05, + "loss": 3.9527, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.933599346944338e-05, + "loss": 3.9367, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.932760752193286e-05, + "loss": 3.9613, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.931922157442234e-05, + "loss": 3.9589, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.9310835626911815e-05, + "loss": 3.9439, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.9302449679401295e-05, + "loss": 3.9339, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.9294063731890775e-05, + "loss": 3.9445, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.9285677784380255e-05, + "loss": 3.9468, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.9277291836869735e-05, + "loss": 3.9529, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.9268905889359215e-05, + "loss": 3.9468, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.9260536320652427e-05, + "loss": 3.9548, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.9252150373141907e-05, + "loss": 3.9496, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.9243764425631387e-05, + "loss": 3.939, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.9235378478120867e-05, + "loss": 3.9379, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.9226992530610347e-05, + "loss": 3.9512, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.9218606583099827e-05, + "loss": 3.9485, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.9210220635589307e-05, + "loss": 3.9528, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.9201834688078787e-05, + "loss": 3.9376, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.9193465119372e-05, + "loss": 3.9414, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.918509555066521e-05, + "loss": 3.9565, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.917670960315469e-05, + "loss": 3.9544, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.916832365564417e-05, + "loss": 3.9468, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.915993770813365e-05, + "loss": 3.9442, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.915155176062313e-05, + "loss": 3.9409, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.914318219191634e-05, + "loss": 3.9432, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.913479624440582e-05, + "loss": 3.9502, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.91264102968953e-05, + "loss": 3.9282, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.911802434938478e-05, + "loss": 3.9414, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.910963840187426e-05, + "loss": 3.9482, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.910125245436374e-05, + "loss": 3.9495, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.9092882885656953e-05, + "loss": 3.9344, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.9084513316950162e-05, + "loss": 3.9503, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.9076127369439642e-05, + "loss": 3.9343, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.9067741421929122e-05, + "loss": 3.9604, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.9059355474418602e-05, + "loss": 3.9315, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.9050969526908085e-05, + "loss": 3.9456, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.9042583579397565e-05, + "loss": 3.949, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.9034197631887045e-05, + "loss": 3.9589, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.9025828063180254e-05, + "loss": 3.9473, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.9017442115669734e-05, + "loss": 3.9421, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.9009056168159214e-05, + "loss": 3.9454, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.9000670220648694e-05, + "loss": 3.9493, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.8992284273138178e-05, + "loss": 3.9385, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.898389832562765e-05, + "loss": 3.9421, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.897551237811713e-05, + "loss": 3.9395, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.896712643060661e-05, + "loss": 3.9607, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.895874048309609e-05, + "loss": 3.9335, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.895035453558557e-05, + "loss": 3.9383, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.8941968588075054e-05, + "loss": 3.9392, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.8933599019368263e-05, + "loss": 3.9457, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.8925213071857743e-05, + "loss": 3.9397, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.8916827124347223e-05, + "loss": 3.9573, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.8908441176836703e-05, + "loss": 3.9509, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.8900055229326183e-05, + "loss": 3.9452, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.8891669281815663e-05, + "loss": 3.9405, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.8883299713108875e-05, + "loss": 3.9523, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.8874930144402084e-05, + "loss": 3.9519, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.8866544196891564e-05, + "loss": 3.9497, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.8858158249381044e-05, + "loss": 3.9411, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.8849772301870524e-05, + "loss": 3.9585, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.8841386354360008e-05, + "loss": 3.9473, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.8833000406849488e-05, + "loss": 3.9555, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.8824614459338968e-05, + "loss": 3.9378, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.8816228511828447e-05, + "loss": 3.9592, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.8807842564317927e-05, + "loss": 3.9456, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.8799456616807407e-05, + "loss": 3.9283, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.8791087048100616e-05, + "loss": 3.9613, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.87827011005901e-05, + "loss": 3.9469, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.877431515307958e-05, + "loss": 3.9502, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.876594558437279e-05, + "loss": 3.9473, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.875755963686227e-05, + "loss": 3.9373, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 4.0131072998046875, + "eval_runtime": 297.1276, + "eval_samples_per_second": 1284.267, + "eval_steps_per_second": 40.134, + "step": 1297440 + }, + { + "epoch": 1.0, + "learning_rate": 2.874917368935175e-05, + "loss": 3.9312, + "step": 1297920 + }, + { + "epoch": 1.0, + "learning_rate": 2.874078774184123e-05, + "loss": 3.9398, + "step": 1298432 + }, + { + "epoch": 1.0, + "learning_rate": 2.873240179433071e-05, + "loss": 3.9552, + "step": 1298944 + }, + { + "epoch": 1.0, + "learning_rate": 2.872401584682019e-05, + "loss": 3.9448, + "step": 1299456 + }, + { + "epoch": 1.0, + "learning_rate": 2.8715629899309665e-05, + "loss": 3.9517, + "step": 1299968 + }, + { + "epoch": 1.0, + "learning_rate": 2.8707243951799145e-05, + "loss": 3.9459, + "step": 1300480 + }, + { + "epoch": 1.0, + "learning_rate": 2.8698858004288625e-05, + "loss": 3.9378, + "step": 1300992 + }, + { + "epoch": 1.0, + "learning_rate": 2.8690472056778105e-05, + "loss": 3.9376, + "step": 1301504 + }, + { + "epoch": 1.0, + "learning_rate": 2.8682086109267585e-05, + "loss": 3.9458, + "step": 1302016 + }, + { + "epoch": 1.0, + "learning_rate": 2.8673700161757065e-05, + "loss": 3.9424, + "step": 1302528 + }, + { + "epoch": 1.0, + "learning_rate": 2.8665330593050277e-05, + "loss": 3.9565, + "step": 1303040 + }, + { + "epoch": 1.0, + "learning_rate": 2.8656944645539757e-05, + "loss": 3.9548, + "step": 1303552 + }, + { + "epoch": 1.0, + "learning_rate": 2.8648591455636702e-05, + "loss": 3.9428, + "step": 1304064 + }, + { + "epoch": 1.0, + "learning_rate": 2.8640205508126182e-05, + "loss": 3.9356, + "step": 1304576 + }, + { + "epoch": 1.0, + "learning_rate": 2.8631819560615662e-05, + "loss": 3.9292, + "step": 1305088 + }, + { + "epoch": 1.0, + "learning_rate": 2.862343361310514e-05, + "loss": 3.9313, + "step": 1305600 + }, + { + "epoch": 1.0, + "learning_rate": 2.861504766559462e-05, + "loss": 3.9457, + "step": 1306112 + }, + { + "epoch": 1.0, + "learning_rate": 2.86066617180841e-05, + "loss": 3.9402, + "step": 1306624 + }, + { + "epoch": 1.0, + "learning_rate": 2.859827577057358e-05, + "loss": 3.935, + "step": 1307136 + }, + { + "epoch": 1.0, + "learning_rate": 2.858988982306306e-05, + "loss": 3.9572, + "step": 1307648 + }, + { + "epoch": 1.0, + "learning_rate": 2.858152025435627e-05, + "loss": 3.9444, + "step": 1308160 + }, + { + "epoch": 1.0, + "learning_rate": 2.857313430684575e-05, + "loss": 3.9435, + "step": 1308672 + }, + { + "epoch": 1.0, + "learning_rate": 2.856474835933523e-05, + "loss": 3.9487, + "step": 1309184 + }, + { + "epoch": 1.0, + "learning_rate": 2.855636241182471e-05, + "loss": 3.9571, + "step": 1309696 + }, + { + "epoch": 1.0, + "learning_rate": 2.854797646431419e-05, + "loss": 3.9313, + "step": 1310208 + }, + { + "epoch": 1.0, + "learning_rate": 2.853959051680367e-05, + "loss": 3.9393, + "step": 1310720 + }, + { + "epoch": 1.0, + "learning_rate": 2.853120456929315e-05, + "loss": 3.9495, + "step": 1311232 + }, + { + "epoch": 1.0, + "learning_rate": 2.852281862178263e-05, + "loss": 3.9396, + "step": 1311744 + }, + { + "epoch": 1.0, + "learning_rate": 2.8514449053075843e-05, + "loss": 3.9303, + "step": 1312256 + }, + { + "epoch": 1.01, + "learning_rate": 2.8506063105565323e-05, + "loss": 3.9353, + "step": 1312768 + }, + { + "epoch": 1.01, + "learning_rate": 2.8497677158054803e-05, + "loss": 3.9473, + "step": 1313280 + }, + { + "epoch": 1.01, + "learning_rate": 2.8489291210544283e-05, + "loss": 3.9451, + "step": 1313792 + }, + { + "epoch": 1.01, + "learning_rate": 2.8480921641837492e-05, + "loss": 3.9436, + "step": 1314304 + }, + { + "epoch": 1.01, + "learning_rate": 2.8472535694326972e-05, + "loss": 3.9465, + "step": 1314816 + }, + { + "epoch": 1.01, + "learning_rate": 2.8464166125620185e-05, + "loss": 3.9477, + "step": 1315328 + }, + { + "epoch": 1.01, + "learning_rate": 2.8455780178109665e-05, + "loss": 3.944, + "step": 1315840 + }, + { + "epoch": 1.01, + "learning_rate": 2.8447394230599145e-05, + "loss": 3.935, + "step": 1316352 + }, + { + "epoch": 1.01, + "learning_rate": 2.8439008283088625e-05, + "loss": 3.9412, + "step": 1316864 + }, + { + "epoch": 1.01, + "learning_rate": 2.8430622335578105e-05, + "loss": 3.9281, + "step": 1317376 + }, + { + "epoch": 1.01, + "learning_rate": 2.8422236388067585e-05, + "loss": 3.9404, + "step": 1317888 + }, + { + "epoch": 1.01, + "learning_rate": 2.8413850440557065e-05, + "loss": 3.9409, + "step": 1318400 + }, + { + "epoch": 1.01, + "learning_rate": 2.8405464493046548e-05, + "loss": 3.9495, + "step": 1318912 + }, + { + "epoch": 1.01, + "learning_rate": 2.8397078545536028e-05, + "loss": 3.9388, + "step": 1319424 + }, + { + "epoch": 1.01, + "learning_rate": 2.83886925980255e-05, + "loss": 3.9447, + "step": 1319936 + }, + { + "epoch": 1.01, + "learning_rate": 2.838030665051498e-05, + "loss": 3.942, + "step": 1320448 + }, + { + "epoch": 1.01, + "learning_rate": 2.837192070300446e-05, + "loss": 3.9415, + "step": 1320960 + }, + { + "epoch": 1.01, + "learning_rate": 2.8363551134297673e-05, + "loss": 3.9528, + "step": 1321472 + }, + { + "epoch": 1.01, + "learning_rate": 2.8355165186787153e-05, + "loss": 3.9211, + "step": 1321984 + }, + { + "epoch": 1.01, + "learning_rate": 2.8346779239276633e-05, + "loss": 3.9364, + "step": 1322496 + }, + { + "epoch": 1.01, + "learning_rate": 2.833840967056985e-05, + "loss": 3.9527, + "step": 1323008 + }, + { + "epoch": 1.01, + "learning_rate": 2.8330023723059322e-05, + "loss": 3.9475, + "step": 1323520 + }, + { + "epoch": 1.01, + "learning_rate": 2.8321637775548802e-05, + "loss": 3.9355, + "step": 1324032 + }, + { + "epoch": 1.01, + "learning_rate": 2.8313251828038286e-05, + "loss": 3.9316, + "step": 1324544 + }, + { + "epoch": 1.01, + "learning_rate": 2.8304865880527766e-05, + "loss": 3.9356, + "step": 1325056 + }, + { + "epoch": 1.01, + "learning_rate": 2.8296479933017246e-05, + "loss": 3.9224, + "step": 1325568 + }, + { + "epoch": 1.01, + "learning_rate": 2.8288110364310455e-05, + "loss": 3.9503, + "step": 1326080 + }, + { + "epoch": 1.01, + "learning_rate": 2.8279724416799935e-05, + "loss": 3.9275, + "step": 1326592 + }, + { + "epoch": 1.01, + "learning_rate": 2.8271338469289415e-05, + "loss": 3.9468, + "step": 1327104 + }, + { + "epoch": 1.01, + "learning_rate": 2.8262952521778895e-05, + "loss": 3.9408, + "step": 1327616 + }, + { + "epoch": 1.01, + "learning_rate": 2.8254566574268378e-05, + "loss": 3.9285, + "step": 1328128 + }, + { + "epoch": 1.01, + "learning_rate": 2.8246180626757858e-05, + "loss": 3.9367, + "step": 1328640 + }, + { + "epoch": 1.01, + "learning_rate": 2.8237794679247338e-05, + "loss": 3.9297, + "step": 1329152 + }, + { + "epoch": 1.01, + "learning_rate": 2.8229408731736818e-05, + "loss": 3.9292, + "step": 1329664 + }, + { + "epoch": 1.01, + "learning_rate": 2.8221039163030027e-05, + "loss": 3.9336, + "step": 1330176 + }, + { + "epoch": 1.01, + "learning_rate": 2.8212653215519507e-05, + "loss": 3.9514, + "step": 1330688 + }, + { + "epoch": 1.01, + "learning_rate": 2.8204267268008987e-05, + "loss": 3.9261, + "step": 1331200 + }, + { + "epoch": 1.01, + "learning_rate": 2.819588132049847e-05, + "loss": 3.9324, + "step": 1331712 + }, + { + "epoch": 1.01, + "learning_rate": 2.818749537298795e-05, + "loss": 3.9206, + "step": 1332224 + }, + { + "epoch": 1.01, + "learning_rate": 2.817912580428116e-05, + "loss": 3.9329, + "step": 1332736 + }, + { + "epoch": 1.01, + "learning_rate": 2.8170756235574368e-05, + "loss": 3.9482, + "step": 1333248 + }, + { + "epoch": 1.01, + "learning_rate": 2.8162370288063848e-05, + "loss": 3.9438, + "step": 1333760 + }, + { + "epoch": 1.01, + "learning_rate": 2.815398434055333e-05, + "loss": 3.9338, + "step": 1334272 + }, + { + "epoch": 1.01, + "learning_rate": 2.814559839304281e-05, + "loss": 3.9448, + "step": 1334784 + }, + { + "epoch": 1.01, + "learning_rate": 2.813721244553229e-05, + "loss": 3.9518, + "step": 1335296 + }, + { + "epoch": 1.01, + "learning_rate": 2.812882649802177e-05, + "loss": 3.9367, + "step": 1335808 + }, + { + "epoch": 1.01, + "learning_rate": 2.812045692931498e-05, + "loss": 3.9346, + "step": 1336320 + }, + { + "epoch": 1.01, + "learning_rate": 2.811207098180446e-05, + "loss": 3.9348, + "step": 1336832 + }, + { + "epoch": 1.01, + "learning_rate": 2.810368503429394e-05, + "loss": 3.935, + "step": 1337344 + }, + { + "epoch": 1.01, + "learning_rate": 2.809529908678342e-05, + "loss": 3.9421, + "step": 1337856 + }, + { + "epoch": 1.01, + "learning_rate": 2.8086913139272904e-05, + "loss": 3.9317, + "step": 1338368 + }, + { + "epoch": 1.01, + "learning_rate": 2.8078543570566113e-05, + "loss": 3.9462, + "step": 1338880 + }, + { + "epoch": 1.01, + "learning_rate": 2.8070157623055593e-05, + "loss": 3.9438, + "step": 1339392 + }, + { + "epoch": 1.01, + "learning_rate": 2.8061771675545073e-05, + "loss": 3.9408, + "step": 1339904 + }, + { + "epoch": 1.01, + "learning_rate": 2.8053385728034553e-05, + "loss": 3.9238, + "step": 1340416 + }, + { + "epoch": 1.01, + "learning_rate": 2.8044999780524033e-05, + "loss": 3.9356, + "step": 1340928 + }, + { + "epoch": 1.01, + "learning_rate": 2.803661383301351e-05, + "loss": 3.94, + "step": 1341440 + }, + { + "epoch": 1.01, + "learning_rate": 2.802822788550299e-05, + "loss": 3.9434, + "step": 1341952 + }, + { + "epoch": 1.01, + "learning_rate": 2.801984193799247e-05, + "loss": 3.9426, + "step": 1342464 + }, + { + "epoch": 1.01, + "learning_rate": 2.8011488748089414e-05, + "loss": 3.9383, + "step": 1342976 + }, + { + "epoch": 1.02, + "learning_rate": 2.8003102800578894e-05, + "loss": 3.942, + "step": 1343488 + }, + { + "epoch": 1.02, + "learning_rate": 2.7994716853068374e-05, + "loss": 3.9301, + "step": 1344000 + }, + { + "epoch": 1.02, + "learning_rate": 2.7986330905557857e-05, + "loss": 3.9271, + "step": 1344512 + }, + { + "epoch": 1.02, + "learning_rate": 2.797794495804733e-05, + "loss": 3.943, + "step": 1345024 + }, + { + "epoch": 1.02, + "learning_rate": 2.796955901053681e-05, + "loss": 3.9375, + "step": 1345536 + }, + { + "epoch": 1.02, + "learning_rate": 2.7961189441830026e-05, + "loss": 3.9405, + "step": 1346048 + }, + { + "epoch": 1.02, + "learning_rate": 2.7952803494319506e-05, + "loss": 3.9357, + "step": 1346560 + }, + { + "epoch": 1.02, + "learning_rate": 2.7944417546808983e-05, + "loss": 3.9294, + "step": 1347072 + }, + { + "epoch": 1.02, + "learning_rate": 2.7936031599298463e-05, + "loss": 3.9435, + "step": 1347584 + }, + { + "epoch": 1.02, + "learning_rate": 2.7927645651787943e-05, + "loss": 3.949, + "step": 1348096 + }, + { + "epoch": 1.02, + "learning_rate": 2.7919259704277423e-05, + "loss": 3.9374, + "step": 1348608 + }, + { + "epoch": 1.02, + "learning_rate": 2.7910873756766903e-05, + "loss": 3.9345, + "step": 1349120 + }, + { + "epoch": 1.02, + "learning_rate": 2.7902487809256383e-05, + "loss": 3.9285, + "step": 1349632 + }, + { + "epoch": 1.02, + "learning_rate": 2.7894118240549595e-05, + "loss": 3.9354, + "step": 1350144 + }, + { + "epoch": 1.02, + "learning_rate": 2.7885732293039075e-05, + "loss": 3.9401, + "step": 1350656 + }, + { + "epoch": 1.02, + "learning_rate": 2.7877346345528555e-05, + "loss": 3.9221, + "step": 1351168 + }, + { + "epoch": 1.02, + "learning_rate": 2.7868960398018035e-05, + "loss": 3.9291, + "step": 1351680 + }, + { + "epoch": 1.02, + "learning_rate": 2.7860590829311244e-05, + "loss": 3.9363, + "step": 1352192 + }, + { + "epoch": 1.02, + "learning_rate": 2.7852204881800724e-05, + "loss": 3.9411, + "step": 1352704 + }, + { + "epoch": 1.02, + "learning_rate": 2.7843835313093937e-05, + "loss": 3.925, + "step": 1353216 + }, + { + "epoch": 1.02, + "learning_rate": 2.7835465744387152e-05, + "loss": 3.9373, + "step": 1353728 + }, + { + "epoch": 1.02, + "learning_rate": 2.7827079796876632e-05, + "loss": 3.926, + "step": 1354240 + }, + { + "epoch": 1.02, + "learning_rate": 2.7818693849366106e-05, + "loss": 3.945, + "step": 1354752 + }, + { + "epoch": 1.02, + "learning_rate": 2.7810307901855586e-05, + "loss": 3.9255, + "step": 1355264 + }, + { + "epoch": 1.02, + "learning_rate": 2.7801921954345066e-05, + "loss": 3.9347, + "step": 1355776 + }, + { + "epoch": 1.02, + "learning_rate": 2.779353600683455e-05, + "loss": 3.9436, + "step": 1356288 + }, + { + "epoch": 1.02, + "learning_rate": 2.7785166438127758e-05, + "loss": 3.9464, + "step": 1356800 + }, + { + "epoch": 1.02, + "learning_rate": 2.7776780490617238e-05, + "loss": 3.9385, + "step": 1357312 + }, + { + "epoch": 1.02, + "learning_rate": 2.7768394543106718e-05, + "loss": 3.9287, + "step": 1357824 + }, + { + "epoch": 1.02, + "learning_rate": 2.7760008595596198e-05, + "loss": 3.9368, + "step": 1358336 + }, + { + "epoch": 1.02, + "learning_rate": 2.775163902688941e-05, + "loss": 3.9433, + "step": 1358848 + }, + { + "epoch": 1.02, + "learning_rate": 2.774325307937889e-05, + "loss": 3.9289, + "step": 1359360 + }, + { + "epoch": 1.02, + "learning_rate": 2.773486713186837e-05, + "loss": 3.9347, + "step": 1359872 + }, + { + "epoch": 1.02, + "learning_rate": 2.772648118435785e-05, + "loss": 3.9296, + "step": 1360384 + }, + { + "epoch": 1.02, + "learning_rate": 2.771809523684733e-05, + "loss": 3.9495, + "step": 1360896 + }, + { + "epoch": 1.02, + "learning_rate": 2.770970928933681e-05, + "loss": 3.9241, + "step": 1361408 + }, + { + "epoch": 1.02, + "learning_rate": 2.770132334182629e-05, + "loss": 3.9304, + "step": 1361920 + }, + { + "epoch": 1.02, + "learning_rate": 2.769293739431577e-05, + "loss": 3.9297, + "step": 1362432 + }, + { + "epoch": 1.02, + "learning_rate": 2.7684567825608982e-05, + "loss": 3.9348, + "step": 1362944 + }, + { + "epoch": 1.02, + "learning_rate": 2.7676181878098462e-05, + "loss": 3.9266, + "step": 1363456 + }, + { + "epoch": 1.02, + "learning_rate": 2.7667795930587942e-05, + "loss": 3.9492, + "step": 1363968 + }, + { + "epoch": 1.02, + "learning_rate": 2.7659409983077422e-05, + "loss": 3.9439, + "step": 1364480 + }, + { + "epoch": 1.02, + "learning_rate": 2.7651024035566902e-05, + "loss": 3.9354, + "step": 1364992 + }, + { + "epoch": 1.02, + "learning_rate": 2.7642638088056382e-05, + "loss": 3.9288, + "step": 1365504 + }, + { + "epoch": 1.02, + "learning_rate": 2.7634252140545862e-05, + "loss": 3.9434, + "step": 1366016 + }, + { + "epoch": 1.02, + "learning_rate": 2.7625866193035342e-05, + "loss": 3.9412, + "step": 1366528 + }, + { + "epoch": 1.02, + "learning_rate": 2.7617496624328555e-05, + "loss": 3.9458, + "step": 1367040 + }, + { + "epoch": 1.02, + "learning_rate": 2.7609110676818035e-05, + "loss": 3.9255, + "step": 1367552 + }, + { + "epoch": 1.02, + "learning_rate": 2.7600724729307515e-05, + "loss": 3.9496, + "step": 1368064 + }, + { + "epoch": 1.02, + "learning_rate": 2.7592371539404456e-05, + "loss": 3.938, + "step": 1368576 + }, + { + "epoch": 1.02, + "learning_rate": 2.7583985591893936e-05, + "loss": 3.9472, + "step": 1369088 + }, + { + "epoch": 1.02, + "learning_rate": 2.7575599644383416e-05, + "loss": 3.9303, + "step": 1369600 + }, + { + "epoch": 1.02, + "learning_rate": 2.7567213696872896e-05, + "loss": 3.9463, + "step": 1370112 + }, + { + "epoch": 1.02, + "learning_rate": 2.7558827749362376e-05, + "loss": 3.9366, + "step": 1370624 + }, + { + "epoch": 1.02, + "learning_rate": 2.7550441801851856e-05, + "loss": 3.9246, + "step": 1371136 + }, + { + "epoch": 1.02, + "learning_rate": 2.7542055854341336e-05, + "loss": 3.945, + "step": 1371648 + }, + { + "epoch": 1.02, + "learning_rate": 2.7533669906830816e-05, + "loss": 3.9417, + "step": 1372160 + }, + { + "epoch": 1.02, + "learning_rate": 2.752530033812403e-05, + "loss": 3.9392, + "step": 1372672 + }, + { + "epoch": 1.02, + "learning_rate": 2.751691439061351e-05, + "loss": 3.9351, + "step": 1373184 + }, + { + "epoch": 1.02, + "learning_rate": 2.7508528443102988e-05, + "loss": 3.9283, + "step": 1373696 + }, + { + "epoch": 1.03, + "eval_loss": 4.00883674621582, + "eval_runtime": 297.0923, + "eval_samples_per_second": 1284.419, + "eval_steps_per_second": 40.139, + "step": 1373760 + }, + { + "epoch": 0.0, + "learning_rate": 2.750014249559246e-05, + "loss": 3.9206, + "step": 1374208 + }, + { + "epoch": 0.0, + "learning_rate": 2.749175654808194e-05, + "loss": 3.9292, + "step": 1374720 + }, + { + "epoch": 0.0, + "learning_rate": 2.7483370600571425e-05, + "loss": 3.9438, + "step": 1375232 + }, + { + "epoch": 0.0, + "learning_rate": 2.7474984653060905e-05, + "loss": 3.9358, + "step": 1375744 + }, + { + "epoch": 0.0, + "learning_rate": 2.7466598705550385e-05, + "loss": 3.943, + "step": 1376256 + }, + { + "epoch": 0.0, + "learning_rate": 2.7458212758039865e-05, + "loss": 3.9309, + "step": 1376768 + }, + { + "epoch": 0.0, + "learning_rate": 2.7449826810529345e-05, + "loss": 3.9304, + "step": 1377280 + }, + { + "epoch": 0.0, + "learning_rate": 2.7441440863018825e-05, + "loss": 3.9264, + "step": 1377792 + }, + { + "epoch": 0.0, + "learning_rate": 2.7433054915508304e-05, + "loss": 3.9341, + "step": 1378304 + }, + { + "epoch": 0.0, + "learning_rate": 2.7424668967997784e-05, + "loss": 3.9361, + "step": 1378816 + }, + { + "epoch": 0.0, + "learning_rate": 2.7416283020487264e-05, + "loss": 3.943, + "step": 1379328 + }, + { + "epoch": 0.0, + "learning_rate": 2.7407897072976744e-05, + "loss": 3.9453, + "step": 1379840 + }, + { + "epoch": 0.0, + "learning_rate": 2.7399527504269957e-05, + "loss": 3.9314, + "step": 1380352 + }, + { + "epoch": 0.0, + "learning_rate": 2.7391141556759437e-05, + "loss": 3.926, + "step": 1380864 + }, + { + "epoch": 0.0, + "learning_rate": 2.7382755609248917e-05, + "loss": 3.9271, + "step": 1381376 + }, + { + "epoch": 0.0, + "learning_rate": 2.7374369661738397e-05, + "loss": 3.9183, + "step": 1381888 + }, + { + "epoch": 0.0, + "learning_rate": 2.7365983714227877e-05, + "loss": 3.9346, + "step": 1382400 + }, + { + "epoch": 0.0, + "learning_rate": 2.7357597766717353e-05, + "loss": 3.929, + "step": 1382912 + }, + { + "epoch": 0.0, + "learning_rate": 2.7349211819206833e-05, + "loss": 3.9272, + "step": 1383424 + }, + { + "epoch": 0.0, + "learning_rate": 2.7340825871696313e-05, + "loss": 3.9511, + "step": 1383936 + }, + { + "epoch": 0.0, + "learning_rate": 2.7332439924185793e-05, + "loss": 3.9337, + "step": 1384448 + }, + { + "epoch": 0.0, + "learning_rate": 2.7324053976675273e-05, + "loss": 3.9366, + "step": 1384960 + }, + { + "epoch": 0.0, + "learning_rate": 2.7315684407968482e-05, + "loss": 3.9385, + "step": 1385472 + }, + { + "epoch": 0.0, + "learning_rate": 2.7307298460457965e-05, + "loss": 3.9463, + "step": 1385984 + }, + { + "epoch": 0.0, + "learning_rate": 2.7298912512947445e-05, + "loss": 3.9193, + "step": 1386496 + }, + { + "epoch": 0.0, + "learning_rate": 2.7290526565436925e-05, + "loss": 3.9308, + "step": 1387008 + }, + { + "epoch": 0.0, + "learning_rate": 2.7282140617926405e-05, + "loss": 3.9379, + "step": 1387520 + }, + { + "epoch": 0.0, + "learning_rate": 2.7273754670415885e-05, + "loss": 3.9323, + "step": 1388032 + }, + { + "epoch": 0.0, + "learning_rate": 2.7265401480512827e-05, + "loss": 3.924, + "step": 1388544 + }, + { + "epoch": 0.01, + "learning_rate": 2.7257015533002307e-05, + "loss": 3.9216, + "step": 1389056 + }, + { + "epoch": 0.01, + "learning_rate": 2.7248629585491787e-05, + "loss": 3.9401, + "step": 1389568 + }, + { + "epoch": 0.01, + "learning_rate": 2.7240243637981267e-05, + "loss": 3.9387, + "step": 1390080 + }, + { + "epoch": 0.01, + "learning_rate": 2.7231857690470747e-05, + "loss": 3.9321, + "step": 1390592 + }, + { + "epoch": 0.01, + "learning_rate": 2.7223471742960227e-05, + "loss": 3.939, + "step": 1391104 + }, + { + "epoch": 0.01, + "learning_rate": 2.7215102174253436e-05, + "loss": 3.9356, + "step": 1391616 + }, + { + "epoch": 0.01, + "learning_rate": 2.720671622674292e-05, + "loss": 3.9324, + "step": 1392128 + }, + { + "epoch": 0.01, + "learning_rate": 2.71983302792324e-05, + "loss": 3.9236, + "step": 1392640 + }, + { + "epoch": 0.01, + "learning_rate": 2.718994433172188e-05, + "loss": 3.9362, + "step": 1393152 + }, + { + "epoch": 0.01, + "learning_rate": 2.718155838421136e-05, + "loss": 3.9137, + "step": 1393664 + }, + { + "epoch": 0.01, + "learning_rate": 2.717317243670084e-05, + "loss": 3.9322, + "step": 1394176 + }, + { + "epoch": 0.01, + "learning_rate": 2.716478648919032e-05, + "loss": 3.9311, + "step": 1394688 + }, + { + "epoch": 0.01, + "learning_rate": 2.71564005416798e-05, + "loss": 3.9402, + "step": 1395200 + }, + { + "epoch": 0.01, + "learning_rate": 2.714803097297301e-05, + "loss": 3.9284, + "step": 1395712 + }, + { + "epoch": 0.01, + "learning_rate": 2.713964502546249e-05, + "loss": 3.933, + "step": 1396224 + }, + { + "epoch": 0.01, + "learning_rate": 2.713125907795197e-05, + "loss": 3.9366, + "step": 1396736 + }, + { + "epoch": 0.01, + "learning_rate": 2.712288950924518e-05, + "loss": 3.9291, + "step": 1397248 + }, + { + "epoch": 0.01, + "learning_rate": 2.711450356173466e-05, + "loss": 3.9417, + "step": 1397760 + }, + { + "epoch": 0.01, + "learning_rate": 2.710611761422414e-05, + "loss": 3.9113, + "step": 1398272 + }, + { + "epoch": 0.01, + "learning_rate": 2.709773166671362e-05, + "loss": 3.9321, + "step": 1398784 + }, + { + "epoch": 0.01, + "learning_rate": 2.7089345719203104e-05, + "loss": 3.94, + "step": 1399296 + }, + { + "epoch": 0.01, + "learning_rate": 2.7080959771692584e-05, + "loss": 3.9372, + "step": 1399808 + }, + { + "epoch": 0.01, + "learning_rate": 2.7072573824182064e-05, + "loss": 3.9263, + "step": 1400320 + }, + { + "epoch": 0.01, + "learning_rate": 2.7064187876671543e-05, + "loss": 3.9208, + "step": 1400832 + }, + { + "epoch": 0.01, + "learning_rate": 2.7055801929161017e-05, + "loss": 3.9282, + "step": 1401344 + }, + { + "epoch": 0.01, + "learning_rate": 2.7047415981650497e-05, + "loss": 3.9101, + "step": 1401856 + }, + { + "epoch": 0.01, + "learning_rate": 2.703903003413998e-05, + "loss": 3.9439, + "step": 1402368 + }, + { + "epoch": 0.01, + "learning_rate": 2.703064408662946e-05, + "loss": 3.9209, + "step": 1402880 + }, + { + "epoch": 0.01, + "learning_rate": 2.702227451792267e-05, + "loss": 3.9331, + "step": 1403392 + }, + { + "epoch": 0.01, + "learning_rate": 2.701388857041215e-05, + "loss": 3.9319, + "step": 1403904 + }, + { + "epoch": 0.01, + "learning_rate": 2.700550262290163e-05, + "loss": 3.9196, + "step": 1404416 + }, + { + "epoch": 0.01, + "learning_rate": 2.699711667539111e-05, + "loss": 3.9272, + "step": 1404928 + }, + { + "epoch": 0.01, + "learning_rate": 2.698874710668432e-05, + "loss": 3.92, + "step": 1405440 + }, + { + "epoch": 0.01, + "learning_rate": 2.69803611591738e-05, + "loss": 3.9219, + "step": 1405952 + }, + { + "epoch": 0.01, + "learning_rate": 2.697197521166328e-05, + "loss": 3.9197, + "step": 1406464 + }, + { + "epoch": 0.01, + "learning_rate": 2.696358926415276e-05, + "loss": 3.9414, + "step": 1406976 + }, + { + "epoch": 0.01, + "learning_rate": 2.695521969544597e-05, + "loss": 3.9221, + "step": 1407488 + }, + { + "epoch": 0.01, + "learning_rate": 2.694683374793545e-05, + "loss": 3.9211, + "step": 1408000 + }, + { + "epoch": 0.01, + "learning_rate": 2.693844780042493e-05, + "loss": 3.9109, + "step": 1408512 + }, + { + "epoch": 0.01, + "learning_rate": 2.6930061852914414e-05, + "loss": 3.9244, + "step": 1409024 + }, + { + "epoch": 0.01, + "learning_rate": 2.6921675905403894e-05, + "loss": 3.9352, + "step": 1409536 + }, + { + "epoch": 0.01, + "learning_rate": 2.6913306336697103e-05, + "loss": 3.9376, + "step": 1410048 + }, + { + "epoch": 0.01, + "learning_rate": 2.6904936767990312e-05, + "loss": 3.9237, + "step": 1410560 + }, + { + "epoch": 0.01, + "learning_rate": 2.689655082047979e-05, + "loss": 3.9346, + "step": 1411072 + }, + { + "epoch": 0.01, + "learning_rate": 2.6888164872969275e-05, + "loss": 3.9428, + "step": 1411584 + }, + { + "epoch": 0.01, + "learning_rate": 2.6879778925458755e-05, + "loss": 3.9304, + "step": 1412096 + }, + { + "epoch": 0.01, + "learning_rate": 2.6871392977948235e-05, + "loss": 3.918, + "step": 1412608 + }, + { + "epoch": 0.01, + "learning_rate": 2.6863007030437715e-05, + "loss": 3.9313, + "step": 1413120 + }, + { + "epoch": 0.01, + "learning_rate": 2.6854621082927195e-05, + "loss": 3.9252, + "step": 1413632 + }, + { + "epoch": 0.01, + "learning_rate": 2.6846235135416675e-05, + "loss": 3.9317, + "step": 1414144 + }, + { + "epoch": 0.01, + "learning_rate": 2.6837881945513616e-05, + "loss": 3.9208, + "step": 1414656 + }, + { + "epoch": 0.01, + "learning_rate": 2.6829512376806832e-05, + "loss": 3.9334, + "step": 1415168 + }, + { + "epoch": 0.01, + "learning_rate": 2.6821126429296312e-05, + "loss": 3.9399, + "step": 1415680 + }, + { + "epoch": 0.01, + "learning_rate": 2.6812740481785785e-05, + "loss": 3.9269, + "step": 1416192 + }, + { + "epoch": 0.01, + "learning_rate": 2.6804354534275265e-05, + "loss": 3.913, + "step": 1416704 + }, + { + "epoch": 0.01, + "learning_rate": 2.6795968586764745e-05, + "loss": 3.9236, + "step": 1417216 + }, + { + "epoch": 0.01, + "learning_rate": 2.678758263925423e-05, + "loss": 3.9282, + "step": 1417728 + }, + { + "epoch": 0.01, + "learning_rate": 2.677919669174371e-05, + "loss": 3.9354, + "step": 1418240 + }, + { + "epoch": 0.01, + "learning_rate": 2.677081074423319e-05, + "loss": 3.9304, + "step": 1418752 + }, + { + "epoch": 0.01, + "learning_rate": 2.676242479672267e-05, + "loss": 3.9341, + "step": 1419264 + }, + { + "epoch": 0.02, + "learning_rate": 2.6754055228015878e-05, + "loss": 3.9307, + "step": 1419776 + }, + { + "epoch": 0.02, + "learning_rate": 2.6745669280505358e-05, + "loss": 3.9232, + "step": 1420288 + }, + { + "epoch": 0.02, + "learning_rate": 2.6737283332994838e-05, + "loss": 3.9194, + "step": 1420800 + }, + { + "epoch": 0.02, + "learning_rate": 2.672889738548432e-05, + "loss": 3.9249, + "step": 1421312 + }, + { + "epoch": 0.02, + "learning_rate": 2.672052781677753e-05, + "loss": 3.9291, + "step": 1421824 + }, + { + "epoch": 0.02, + "learning_rate": 2.671214186926701e-05, + "loss": 3.9311, + "step": 1422336 + }, + { + "epoch": 0.02, + "learning_rate": 2.670375592175649e-05, + "loss": 3.9287, + "step": 1422848 + }, + { + "epoch": 0.02, + "learning_rate": 2.669536997424597e-05, + "loss": 3.916, + "step": 1423360 + }, + { + "epoch": 0.02, + "learning_rate": 2.668698402673545e-05, + "loss": 3.9344, + "step": 1423872 + }, + { + "epoch": 0.02, + "learning_rate": 2.667859807922493e-05, + "loss": 3.9403, + "step": 1424384 + }, + { + "epoch": 0.02, + "learning_rate": 2.6670212131714413e-05, + "loss": 3.9279, + "step": 1424896 + }, + { + "epoch": 0.02, + "learning_rate": 2.6661826184203893e-05, + "loss": 3.9286, + "step": 1425408 + }, + { + "epoch": 0.02, + "learning_rate": 2.6653456615497102e-05, + "loss": 3.9166, + "step": 1425920 + }, + { + "epoch": 0.02, + "learning_rate": 2.6645070667986582e-05, + "loss": 3.9252, + "step": 1426432 + }, + { + "epoch": 0.02, + "learning_rate": 2.6636684720476062e-05, + "loss": 3.9323, + "step": 1426944 + }, + { + "epoch": 0.02, + "learning_rate": 2.6628298772965542e-05, + "loss": 3.9079, + "step": 1427456 + }, + { + "epoch": 0.02, + "learning_rate": 2.6619929204258755e-05, + "loss": 3.9202, + "step": 1427968 + }, + { + "epoch": 0.02, + "learning_rate": 2.6611559635551964e-05, + "loss": 3.9302, + "step": 1428480 + }, + { + "epoch": 0.02, + "learning_rate": 2.6603173688041444e-05, + "loss": 3.9271, + "step": 1428992 + }, + { + "epoch": 0.02, + "learning_rate": 2.6594787740530924e-05, + "loss": 3.9156, + "step": 1429504 + }, + { + "epoch": 0.02, + "learning_rate": 2.6586401793020403e-05, + "loss": 3.928, + "step": 1430016 + }, + { + "epoch": 0.02, + "learning_rate": 2.6578015845509883e-05, + "loss": 3.9163, + "step": 1430528 + }, + { + "epoch": 0.02, + "learning_rate": 2.6569646276803096e-05, + "loss": 3.9358, + "step": 1431040 + }, + { + "epoch": 0.02, + "learning_rate": 2.6561260329292576e-05, + "loss": 3.9197, + "step": 1431552 + }, + { + "epoch": 0.02, + "learning_rate": 2.6552874381782056e-05, + "loss": 3.9214, + "step": 1432064 + }, + { + "epoch": 0.02, + "learning_rate": 2.6544488434271536e-05, + "loss": 3.935, + "step": 1432576 + }, + { + "epoch": 0.02, + "learning_rate": 2.6536102486761016e-05, + "loss": 3.9387, + "step": 1433088 + }, + { + "epoch": 0.02, + "learning_rate": 2.6527716539250496e-05, + "loss": 3.93, + "step": 1433600 + }, + { + "epoch": 0.02, + "learning_rate": 2.6519330591739972e-05, + "loss": 3.9206, + "step": 1434112 + }, + { + "epoch": 0.02, + "learning_rate": 2.6510944644229452e-05, + "loss": 3.9251, + "step": 1434624 + }, + { + "epoch": 0.02, + "learning_rate": 2.6502558696718932e-05, + "loss": 3.9284, + "step": 1435136 + }, + { + "epoch": 0.02, + "learning_rate": 2.6494189128012148e-05, + "loss": 3.9223, + "step": 1435648 + }, + { + "epoch": 0.02, + "learning_rate": 2.648580318050162e-05, + "loss": 3.9264, + "step": 1436160 + }, + { + "epoch": 0.02, + "learning_rate": 2.6477417232991105e-05, + "loss": 3.9182, + "step": 1436672 + }, + { + "epoch": 0.02, + "learning_rate": 2.646904766428432e-05, + "loss": 3.932, + "step": 1437184 + }, + { + "epoch": 0.02, + "learning_rate": 2.6460661716773794e-05, + "loss": 3.9236, + "step": 1437696 + }, + { + "epoch": 0.02, + "learning_rate": 2.6452275769263274e-05, + "loss": 3.9207, + "step": 1438208 + }, + { + "epoch": 0.02, + "learning_rate": 2.6443889821752754e-05, + "loss": 3.9145, + "step": 1438720 + }, + { + "epoch": 0.02, + "learning_rate": 2.643552025304597e-05, + "loss": 3.9275, + "step": 1439232 + }, + { + "epoch": 0.02, + "learning_rate": 2.6427134305535446e-05, + "loss": 3.917, + "step": 1439744 + }, + { + "epoch": 0.02, + "learning_rate": 2.6418748358024926e-05, + "loss": 3.9384, + "step": 1440256 + }, + { + "epoch": 0.02, + "learning_rate": 2.6410362410514406e-05, + "loss": 3.9339, + "step": 1440768 + }, + { + "epoch": 0.02, + "learning_rate": 2.6401976463003886e-05, + "loss": 3.9283, + "step": 1441280 + }, + { + "epoch": 0.02, + "learning_rate": 2.6393606894297095e-05, + "loss": 3.9167, + "step": 1441792 + }, + { + "epoch": 0.02, + "learning_rate": 2.6385220946786575e-05, + "loss": 3.9362, + "step": 1442304 + }, + { + "epoch": 0.02, + "learning_rate": 2.6376834999276058e-05, + "loss": 3.9292, + "step": 1442816 + }, + { + "epoch": 0.02, + "learning_rate": 2.6368449051765538e-05, + "loss": 3.9323, + "step": 1443328 + }, + { + "epoch": 0.02, + "learning_rate": 2.6360063104255018e-05, + "loss": 3.9216, + "step": 1443840 + }, + { + "epoch": 0.02, + "learning_rate": 2.6351677156744498e-05, + "loss": 3.932, + "step": 1444352 + }, + { + "epoch": 0.02, + "learning_rate": 2.6343291209233978e-05, + "loss": 3.9316, + "step": 1444864 + }, + { + "epoch": 0.02, + "learning_rate": 2.6334921640527187e-05, + "loss": 3.9378, + "step": 1445376 + }, + { + "epoch": 0.02, + "learning_rate": 2.63265520718204e-05, + "loss": 3.9231, + "step": 1445888 + }, + { + "epoch": 0.02, + "learning_rate": 2.631816612430988e-05, + "loss": 3.9305, + "step": 1446400 + }, + { + "epoch": 0.02, + "learning_rate": 2.630978017679936e-05, + "loss": 3.928, + "step": 1446912 + }, + { + "epoch": 0.02, + "learning_rate": 2.630139422928884e-05, + "loss": 3.914, + "step": 1447424 + }, + { + "epoch": 0.02, + "learning_rate": 2.629300828177832e-05, + "loss": 3.9344, + "step": 1447936 + }, + { + "epoch": 0.02, + "learning_rate": 2.62846223342678e-05, + "loss": 3.9347, + "step": 1448448 + }, + { + "epoch": 0.02, + "learning_rate": 2.627623638675728e-05, + "loss": 3.9262, + "step": 1448960 + }, + { + "epoch": 0.02, + "learning_rate": 2.626785043924676e-05, + "loss": 3.9269, + "step": 1449472 + }, + { + "epoch": 0.02, + "learning_rate": 2.62594972493437e-05, + "loss": 3.9186, + "step": 1449984 + }, + { + "epoch": 0.03, + "eval_loss": 4.003667831420898, + "eval_runtime": 295.0786, + "eval_samples_per_second": 1293.184, + "eval_steps_per_second": 40.413, + "step": 1450080 + }, + { + "epoch": 1.0, + "learning_rate": 2.625111130183318e-05, + "loss": 3.9191, + "step": 1450496 + }, + { + "epoch": 1.0, + "learning_rate": 2.624272535432266e-05, + "loss": 3.9177, + "step": 1451008 + }, + { + "epoch": 1.0, + "learning_rate": 2.623433940681214e-05, + "loss": 3.9347, + "step": 1451520 + }, + { + "epoch": 1.0, + "learning_rate": 2.622595345930162e-05, + "loss": 3.9235, + "step": 1452032 + }, + { + "epoch": 1.0, + "learning_rate": 2.62175675117911e-05, + "loss": 3.9401, + "step": 1452544 + }, + { + "epoch": 1.0, + "learning_rate": 2.6209181564280584e-05, + "loss": 3.921, + "step": 1453056 + }, + { + "epoch": 1.0, + "learning_rate": 2.6200795616770064e-05, + "loss": 3.9232, + "step": 1453568 + }, + { + "epoch": 1.0, + "learning_rate": 2.6192426048063273e-05, + "loss": 3.9132, + "step": 1454080 + }, + { + "epoch": 1.0, + "learning_rate": 2.6184040100552753e-05, + "loss": 3.9274, + "step": 1454592 + }, + { + "epoch": 1.0, + "learning_rate": 2.6175654153042233e-05, + "loss": 3.923, + "step": 1455104 + }, + { + "epoch": 1.0, + "learning_rate": 2.6167284584335446e-05, + "loss": 3.9345, + "step": 1455616 + }, + { + "epoch": 1.0, + "learning_rate": 2.6158898636824925e-05, + "loss": 3.9337, + "step": 1456128 + }, + { + "epoch": 1.0, + "learning_rate": 2.6150529068118135e-05, + "loss": 3.9213, + "step": 1456640 + }, + { + "epoch": 1.0, + "learning_rate": 2.6142143120607615e-05, + "loss": 3.9172, + "step": 1457152 + }, + { + "epoch": 1.0, + "learning_rate": 2.6133757173097094e-05, + "loss": 3.918, + "step": 1457664 + }, + { + "epoch": 1.0, + "learning_rate": 2.6125371225586574e-05, + "loss": 3.912, + "step": 1458176 + }, + { + "epoch": 1.0, + "learning_rate": 2.6116985278076054e-05, + "loss": 3.9196, + "step": 1458688 + }, + { + "epoch": 1.0, + "learning_rate": 2.6108599330565538e-05, + "loss": 3.9192, + "step": 1459200 + }, + { + "epoch": 1.0, + "learning_rate": 2.6100213383055018e-05, + "loss": 3.9173, + "step": 1459712 + }, + { + "epoch": 1.0, + "learning_rate": 2.6091827435544498e-05, + "loss": 3.9449, + "step": 1460224 + }, + { + "epoch": 1.0, + "learning_rate": 2.6083441488033978e-05, + "loss": 3.9247, + "step": 1460736 + }, + { + "epoch": 1.0, + "learning_rate": 2.607505554052345e-05, + "loss": 3.9253, + "step": 1461248 + }, + { + "epoch": 1.0, + "learning_rate": 2.6066685971816667e-05, + "loss": 3.9322, + "step": 1461760 + }, + { + "epoch": 1.0, + "learning_rate": 2.6058300024306147e-05, + "loss": 3.9345, + "step": 1462272 + }, + { + "epoch": 1.0, + "learning_rate": 2.604991407679563e-05, + "loss": 3.9129, + "step": 1462784 + }, + { + "epoch": 1.0, + "learning_rate": 2.6041528129285103e-05, + "loss": 3.9199, + "step": 1463296 + }, + { + "epoch": 1.0, + "learning_rate": 2.6033142181774583e-05, + "loss": 3.9292, + "step": 1463808 + }, + { + "epoch": 1.0, + "learning_rate": 2.6024756234264063e-05, + "loss": 3.9255, + "step": 1464320 + }, + { + "epoch": 1.0, + "learning_rate": 2.6016370286753543e-05, + "loss": 3.9118, + "step": 1464832 + }, + { + "epoch": 1.01, + "learning_rate": 2.6007984339243023e-05, + "loss": 3.9122, + "step": 1465344 + }, + { + "epoch": 1.01, + "learning_rate": 2.5999614770536235e-05, + "loss": 3.929, + "step": 1465856 + }, + { + "epoch": 1.01, + "learning_rate": 2.5991228823025715e-05, + "loss": 3.9315, + "step": 1466368 + }, + { + "epoch": 1.01, + "learning_rate": 2.5982842875515195e-05, + "loss": 3.9266, + "step": 1466880 + }, + { + "epoch": 1.01, + "learning_rate": 2.5974456928004675e-05, + "loss": 3.9283, + "step": 1467392 + }, + { + "epoch": 1.01, + "learning_rate": 2.5966087359297884e-05, + "loss": 3.9251, + "step": 1467904 + }, + { + "epoch": 1.01, + "learning_rate": 2.5957701411787368e-05, + "loss": 3.9257, + "step": 1468416 + }, + { + "epoch": 1.01, + "learning_rate": 2.5949315464276848e-05, + "loss": 3.9129, + "step": 1468928 + }, + { + "epoch": 1.01, + "learning_rate": 2.5940929516766328e-05, + "loss": 3.9293, + "step": 1469440 + }, + { + "epoch": 1.01, + "learning_rate": 2.5932543569255808e-05, + "loss": 3.9074, + "step": 1469952 + }, + { + "epoch": 1.01, + "learning_rate": 2.5924174000549017e-05, + "loss": 3.9218, + "step": 1470464 + }, + { + "epoch": 1.01, + "learning_rate": 2.5915788053038497e-05, + "loss": 3.9179, + "step": 1470976 + }, + { + "epoch": 1.01, + "learning_rate": 2.5907402105527977e-05, + "loss": 3.9342, + "step": 1471488 + }, + { + "epoch": 1.01, + "learning_rate": 2.589901615801746e-05, + "loss": 3.9231, + "step": 1472000 + }, + { + "epoch": 1.01, + "learning_rate": 2.589064658931067e-05, + "loss": 3.9231, + "step": 1472512 + }, + { + "epoch": 1.01, + "learning_rate": 2.588226064180015e-05, + "loss": 3.9257, + "step": 1473024 + }, + { + "epoch": 1.01, + "learning_rate": 2.587387469428963e-05, + "loss": 3.9246, + "step": 1473536 + }, + { + "epoch": 1.01, + "learning_rate": 2.586548874677911e-05, + "loss": 3.9311, + "step": 1474048 + }, + { + "epoch": 1.01, + "learning_rate": 2.585710279926859e-05, + "loss": 3.9063, + "step": 1474560 + }, + { + "epoch": 1.01, + "learning_rate": 2.584871685175807e-05, + "loss": 3.9168, + "step": 1475072 + }, + { + "epoch": 1.01, + "learning_rate": 2.5840330904247552e-05, + "loss": 3.9321, + "step": 1475584 + }, + { + "epoch": 1.01, + "learning_rate": 2.583196133554076e-05, + "loss": 3.9281, + "step": 1476096 + }, + { + "epoch": 1.01, + "learning_rate": 2.582357538803024e-05, + "loss": 3.9169, + "step": 1476608 + }, + { + "epoch": 1.01, + "learning_rate": 2.581518944051972e-05, + "loss": 3.9153, + "step": 1477120 + }, + { + "epoch": 1.01, + "learning_rate": 2.58068034930092e-05, + "loss": 3.9183, + "step": 1477632 + }, + { + "epoch": 1.01, + "learning_rate": 2.5798450303106143e-05, + "loss": 3.9031, + "step": 1478144 + }, + { + "epoch": 1.01, + "learning_rate": 2.5790064355595623e-05, + "loss": 3.9303, + "step": 1478656 + }, + { + "epoch": 1.01, + "learning_rate": 2.5781694786888832e-05, + "loss": 3.9116, + "step": 1479168 + }, + { + "epoch": 1.01, + "learning_rate": 2.5773308839378312e-05, + "loss": 3.9243, + "step": 1479680 + }, + { + "epoch": 1.01, + "learning_rate": 2.5764922891867792e-05, + "loss": 3.9261, + "step": 1480192 + }, + { + "epoch": 1.01, + "learning_rate": 2.5756536944357275e-05, + "loss": 3.9116, + "step": 1480704 + }, + { + "epoch": 1.01, + "learning_rate": 2.5748150996846755e-05, + "loss": 3.9145, + "step": 1481216 + }, + { + "epoch": 1.01, + "learning_rate": 2.5739765049336235e-05, + "loss": 3.914, + "step": 1481728 + }, + { + "epoch": 1.01, + "learning_rate": 2.5731379101825715e-05, + "loss": 3.9087, + "step": 1482240 + }, + { + "epoch": 1.01, + "learning_rate": 2.5722993154315195e-05, + "loss": 3.9176, + "step": 1482752 + }, + { + "epoch": 1.01, + "learning_rate": 2.5714607206804675e-05, + "loss": 3.9271, + "step": 1483264 + }, + { + "epoch": 1.01, + "learning_rate": 2.5706221259294155e-05, + "loss": 3.9144, + "step": 1483776 + }, + { + "epoch": 1.01, + "learning_rate": 2.5697835311783635e-05, + "loss": 3.9125, + "step": 1484288 + }, + { + "epoch": 1.01, + "learning_rate": 2.568944936427311e-05, + "loss": 3.905, + "step": 1484800 + }, + { + "epoch": 1.01, + "learning_rate": 2.568106341676259e-05, + "loss": 3.9133, + "step": 1485312 + }, + { + "epoch": 1.01, + "learning_rate": 2.567267746925207e-05, + "loss": 3.9214, + "step": 1485824 + }, + { + "epoch": 1.01, + "learning_rate": 2.566429152174155e-05, + "loss": 3.9349, + "step": 1486336 + }, + { + "epoch": 1.01, + "learning_rate": 2.565590557423103e-05, + "loss": 3.9142, + "step": 1486848 + }, + { + "epoch": 1.01, + "learning_rate": 2.5647536005524244e-05, + "loss": 3.9245, + "step": 1487360 + }, + { + "epoch": 1.01, + "learning_rate": 2.5639150058013724e-05, + "loss": 3.9297, + "step": 1487872 + }, + { + "epoch": 1.01, + "learning_rate": 2.563078048930694e-05, + "loss": 3.9292, + "step": 1488384 + }, + { + "epoch": 1.01, + "learning_rate": 2.5622394541796413e-05, + "loss": 3.904, + "step": 1488896 + }, + { + "epoch": 1.01, + "learning_rate": 2.5614008594285893e-05, + "loss": 3.9251, + "step": 1489408 + }, + { + "epoch": 1.01, + "learning_rate": 2.560563902557911e-05, + "loss": 3.9195, + "step": 1489920 + }, + { + "epoch": 1.01, + "learning_rate": 2.5597269456872318e-05, + "loss": 3.9149, + "step": 1490432 + }, + { + "epoch": 1.01, + "learning_rate": 2.55888835093618e-05, + "loss": 3.9203, + "step": 1490944 + }, + { + "epoch": 1.01, + "learning_rate": 2.558049756185128e-05, + "loss": 3.921, + "step": 1491456 + }, + { + "epoch": 1.01, + "learning_rate": 2.557211161434076e-05, + "loss": 3.9303, + "step": 1491968 + }, + { + "epoch": 1.01, + "learning_rate": 2.5563725666830234e-05, + "loss": 3.9197, + "step": 1492480 + }, + { + "epoch": 1.01, + "learning_rate": 2.5555339719319714e-05, + "loss": 3.9064, + "step": 1492992 + }, + { + "epoch": 1.01, + "learning_rate": 2.5546953771809194e-05, + "loss": 3.9167, + "step": 1493504 + }, + { + "epoch": 1.01, + "learning_rate": 2.5538567824298677e-05, + "loss": 3.9154, + "step": 1494016 + }, + { + "epoch": 1.01, + "learning_rate": 2.5530181876788157e-05, + "loss": 3.9257, + "step": 1494528 + }, + { + "epoch": 1.01, + "learning_rate": 2.5521795929277637e-05, + "loss": 3.9254, + "step": 1495040 + }, + { + "epoch": 1.01, + "learning_rate": 2.5513409981767117e-05, + "loss": 3.9219, + "step": 1495552 + }, + { + "epoch": 1.02, + "learning_rate": 2.5505024034256597e-05, + "loss": 3.9253, + "step": 1496064 + }, + { + "epoch": 1.02, + "learning_rate": 2.5496638086746077e-05, + "loss": 3.9124, + "step": 1496576 + }, + { + "epoch": 1.02, + "learning_rate": 2.5488268518039286e-05, + "loss": 3.9117, + "step": 1497088 + }, + { + "epoch": 1.02, + "learning_rate": 2.547988257052877e-05, + "loss": 3.9154, + "step": 1497600 + }, + { + "epoch": 1.02, + "learning_rate": 2.547149662301825e-05, + "loss": 3.9227, + "step": 1498112 + }, + { + "epoch": 1.02, + "learning_rate": 2.546311067550773e-05, + "loss": 3.9209, + "step": 1498624 + }, + { + "epoch": 1.02, + "learning_rate": 2.545472472799721e-05, + "loss": 3.929, + "step": 1499136 + }, + { + "epoch": 1.02, + "learning_rate": 2.544633878048669e-05, + "loss": 3.9028, + "step": 1499648 + }, + { + "epoch": 1.02, + "learning_rate": 2.543795283297617e-05, + "loss": 3.9265, + "step": 1500160 + }, + { + "epoch": 1.02, + "learning_rate": 2.542956688546565e-05, + "loss": 3.9314, + "step": 1500672 + }, + { + "epoch": 1.02, + "learning_rate": 2.5421197316758862e-05, + "loss": 3.9213, + "step": 1501184 + }, + { + "epoch": 1.02, + "learning_rate": 2.541282774805207e-05, + "loss": 3.919, + "step": 1501696 + }, + { + "epoch": 1.02, + "learning_rate": 2.540445817934528e-05, + "loss": 3.9108, + "step": 1502208 + }, + { + "epoch": 1.02, + "learning_rate": 2.539607223183476e-05, + "loss": 3.921, + "step": 1502720 + }, + { + "epoch": 1.02, + "learning_rate": 2.538768628432424e-05, + "loss": 3.9222, + "step": 1503232 + }, + { + "epoch": 1.02, + "learning_rate": 2.5379300336813723e-05, + "loss": 3.9037, + "step": 1503744 + }, + { + "epoch": 1.02, + "learning_rate": 2.5370914389303203e-05, + "loss": 3.9153, + "step": 1504256 + }, + { + "epoch": 1.02, + "learning_rate": 2.5362528441792683e-05, + "loss": 3.9153, + "step": 1504768 + }, + { + "epoch": 1.02, + "learning_rate": 2.5354142494282163e-05, + "loss": 3.9219, + "step": 1505280 + }, + { + "epoch": 1.02, + "learning_rate": 2.5345756546771643e-05, + "loss": 3.9072, + "step": 1505792 + }, + { + "epoch": 1.02, + "learning_rate": 2.5337386978064852e-05, + "loss": 3.928, + "step": 1506304 + }, + { + "epoch": 1.02, + "learning_rate": 2.5329001030554332e-05, + "loss": 3.9025, + "step": 1506816 + }, + { + "epoch": 1.02, + "learning_rate": 2.5320615083043815e-05, + "loss": 3.928, + "step": 1507328 + }, + { + "epoch": 1.02, + "learning_rate": 2.5312229135533295e-05, + "loss": 3.9146, + "step": 1507840 + }, + { + "epoch": 1.02, + "learning_rate": 2.5303843188022775e-05, + "loss": 3.9084, + "step": 1508352 + }, + { + "epoch": 1.02, + "learning_rate": 2.529545724051225e-05, + "loss": 3.9268, + "step": 1508864 + }, + { + "epoch": 1.02, + "learning_rate": 2.5287087671805464e-05, + "loss": 3.9317, + "step": 1509376 + }, + { + "epoch": 1.02, + "learning_rate": 2.5278701724294944e-05, + "loss": 3.9219, + "step": 1509888 + }, + { + "epoch": 1.02, + "learning_rate": 2.527031577678442e-05, + "loss": 3.9139, + "step": 1510400 + }, + { + "epoch": 1.02, + "learning_rate": 2.52619298292739e-05, + "loss": 3.9189, + "step": 1510912 + }, + { + "epoch": 1.02, + "learning_rate": 2.525354388176338e-05, + "loss": 3.9207, + "step": 1511424 + }, + { + "epoch": 1.02, + "learning_rate": 2.524515793425286e-05, + "loss": 3.9115, + "step": 1511936 + }, + { + "epoch": 1.02, + "learning_rate": 2.523677198674234e-05, + "loss": 3.919, + "step": 1512448 + }, + { + "epoch": 1.02, + "learning_rate": 2.522838603923182e-05, + "loss": 3.9149, + "step": 1512960 + }, + { + "epoch": 1.02, + "learning_rate": 2.5220016470525033e-05, + "loss": 3.9218, + "step": 1513472 + }, + { + "epoch": 1.02, + "learning_rate": 2.521164690181825e-05, + "loss": 3.918, + "step": 1513984 + }, + { + "epoch": 1.02, + "learning_rate": 2.5203260954307722e-05, + "loss": 3.9162, + "step": 1514496 + }, + { + "epoch": 1.02, + "learning_rate": 2.5194875006797202e-05, + "loss": 3.9004, + "step": 1515008 + }, + { + "epoch": 1.02, + "learning_rate": 2.5186489059286682e-05, + "loss": 3.9203, + "step": 1515520 + }, + { + "epoch": 1.02, + "learning_rate": 2.5178103111776162e-05, + "loss": 3.911, + "step": 1516032 + }, + { + "epoch": 1.02, + "learning_rate": 2.5169717164265645e-05, + "loss": 3.9272, + "step": 1516544 + }, + { + "epoch": 1.02, + "learning_rate": 2.5161331216755125e-05, + "loss": 3.9253, + "step": 1517056 + }, + { + "epoch": 1.02, + "learning_rate": 2.5152945269244605e-05, + "loss": 3.9249, + "step": 1517568 + }, + { + "epoch": 1.02, + "learning_rate": 2.5144575700537814e-05, + "loss": 3.907, + "step": 1518080 + }, + { + "epoch": 1.02, + "learning_rate": 2.5136189753027294e-05, + "loss": 3.928, + "step": 1518592 + }, + { + "epoch": 1.02, + "learning_rate": 2.5127803805516774e-05, + "loss": 3.9233, + "step": 1519104 + }, + { + "epoch": 1.02, + "learning_rate": 2.5119417858006254e-05, + "loss": 3.9273, + "step": 1519616 + }, + { + "epoch": 1.02, + "learning_rate": 2.5111048289299467e-05, + "loss": 3.9108, + "step": 1520128 + }, + { + "epoch": 1.02, + "learning_rate": 2.5102662341788947e-05, + "loss": 3.9289, + "step": 1520640 + }, + { + "epoch": 1.02, + "learning_rate": 2.5094276394278427e-05, + "loss": 3.9271, + "step": 1521152 + }, + { + "epoch": 1.02, + "learning_rate": 2.5085890446767907e-05, + "loss": 3.9329, + "step": 1521664 + }, + { + "epoch": 1.02, + "learning_rate": 2.5077520878061116e-05, + "loss": 3.911, + "step": 1522176 + }, + { + "epoch": 1.02, + "learning_rate": 2.50691349305506e-05, + "loss": 3.9237, + "step": 1522688 + }, + { + "epoch": 1.02, + "learning_rate": 2.506074898304008e-05, + "loss": 3.9214, + "step": 1523200 + }, + { + "epoch": 1.02, + "learning_rate": 2.5052379414333288e-05, + "loss": 3.9107, + "step": 1523712 + }, + { + "epoch": 1.02, + "learning_rate": 2.5043993466822768e-05, + "loss": 3.9221, + "step": 1524224 + }, + { + "epoch": 1.02, + "learning_rate": 2.5035607519312248e-05, + "loss": 3.9293, + "step": 1524736 + }, + { + "epoch": 1.02, + "learning_rate": 2.5027221571801728e-05, + "loss": 3.9197, + "step": 1525248 + }, + { + "epoch": 1.02, + "learning_rate": 2.5018835624291208e-05, + "loss": 3.9158, + "step": 1525760 + }, + { + "epoch": 1.02, + "learning_rate": 2.5010449676780688e-05, + "loss": 3.9159, + "step": 1526272 + }, + { + "epoch": 1.03, + "eval_loss": 4.00024938583374, + "eval_runtime": 296.5121, + "eval_samples_per_second": 1286.932, + "eval_steps_per_second": 40.218, + "step": 1526400 + }, + { + "epoch": 0.0, + "learning_rate": 2.500206372927017e-05, + "loss": 3.9022, + "step": 1526784 + }, + { + "epoch": 0.0, + "learning_rate": 2.4993677781759648e-05, + "loss": 3.9107, + "step": 1527296 + }, + { + "epoch": 0.0, + "learning_rate": 2.4985291834249128e-05, + "loss": 3.9235, + "step": 1527808 + }, + { + "epoch": 0.0, + "learning_rate": 2.4976905886738608e-05, + "loss": 3.918, + "step": 1528320 + }, + { + "epoch": 0.0, + "learning_rate": 2.4968519939228088e-05, + "loss": 3.9284, + "step": 1528832 + }, + { + "epoch": 0.0, + "learning_rate": 2.4960133991717568e-05, + "loss": 3.9147, + "step": 1529344 + }, + { + "epoch": 0.0, + "learning_rate": 2.4951748044207048e-05, + "loss": 3.9162, + "step": 1529856 + }, + { + "epoch": 0.0, + "learning_rate": 2.4943362096696528e-05, + "loss": 3.9029, + "step": 1530368 + }, + { + "epoch": 0.0, + "learning_rate": 2.4934976149186007e-05, + "loss": 3.92, + "step": 1530880 + }, + { + "epoch": 0.0, + "learning_rate": 2.4926590201675487e-05, + "loss": 3.9167, + "step": 1531392 + }, + { + "epoch": 0.0, + "learning_rate": 2.4918204254164967e-05, + "loss": 3.9231, + "step": 1531904 + }, + { + "epoch": 0.0, + "learning_rate": 2.4909818306654447e-05, + "loss": 3.9274, + "step": 1532416 + }, + { + "epoch": 0.0, + "learning_rate": 2.4901448737947656e-05, + "loss": 3.9138, + "step": 1532928 + }, + { + "epoch": 0.0, + "learning_rate": 2.489306279043714e-05, + "loss": 3.9114, + "step": 1533440 + }, + { + "epoch": 0.0, + "learning_rate": 2.488467684292662e-05, + "loss": 3.9099, + "step": 1533952 + }, + { + "epoch": 0.0, + "learning_rate": 2.48762908954161e-05, + "loss": 3.9041, + "step": 1534464 + }, + { + "epoch": 0.0, + "learning_rate": 2.486790494790558e-05, + "loss": 3.9133, + "step": 1534976 + }, + { + "epoch": 0.0, + "learning_rate": 2.4859519000395056e-05, + "loss": 3.9116, + "step": 1535488 + }, + { + "epoch": 0.0, + "learning_rate": 2.4851133052884536e-05, + "loss": 3.9113, + "step": 1536000 + }, + { + "epoch": 0.0, + "learning_rate": 2.4842747105374016e-05, + "loss": 3.9339, + "step": 1536512 + }, + { + "epoch": 0.0, + "learning_rate": 2.4834377536667232e-05, + "loss": 3.9171, + "step": 1537024 + }, + { + "epoch": 0.0, + "learning_rate": 2.482599158915671e-05, + "loss": 3.9156, + "step": 1537536 + }, + { + "epoch": 0.0, + "learning_rate": 2.481760564164619e-05, + "loss": 3.9247, + "step": 1538048 + }, + { + "epoch": 0.0, + "learning_rate": 2.480921969413567e-05, + "loss": 3.9255, + "step": 1538560 + }, + { + "epoch": 0.0, + "learning_rate": 2.480083374662515e-05, + "loss": 3.9088, + "step": 1539072 + }, + { + "epoch": 0.0, + "learning_rate": 2.479244779911463e-05, + "loss": 3.9164, + "step": 1539584 + }, + { + "epoch": 0.0, + "learning_rate": 2.478406185160411e-05, + "loss": 3.9188, + "step": 1540096 + }, + { + "epoch": 0.0, + "learning_rate": 2.477567590409359e-05, + "loss": 3.9182, + "step": 1540608 + }, + { + "epoch": 0.0, + "learning_rate": 2.47673063353868e-05, + "loss": 3.9033, + "step": 1541120 + }, + { + "epoch": 0.0, + "learning_rate": 2.475892038787628e-05, + "loss": 3.9075, + "step": 1541632 + }, + { + "epoch": 0.01, + "learning_rate": 2.475053444036576e-05, + "loss": 3.9194, + "step": 1542144 + }, + { + "epoch": 0.01, + "learning_rate": 2.4742148492855237e-05, + "loss": 3.9224, + "step": 1542656 + }, + { + "epoch": 0.01, + "learning_rate": 2.4733795302952182e-05, + "loss": 3.918, + "step": 1543168 + }, + { + "epoch": 0.01, + "learning_rate": 2.4725409355441662e-05, + "loss": 3.9235, + "step": 1543680 + }, + { + "epoch": 0.01, + "learning_rate": 2.4717039786734875e-05, + "loss": 3.9147, + "step": 1544192 + }, + { + "epoch": 0.01, + "learning_rate": 2.470865383922435e-05, + "loss": 3.9197, + "step": 1544704 + }, + { + "epoch": 0.01, + "learning_rate": 2.470026789171383e-05, + "loss": 3.907, + "step": 1545216 + }, + { + "epoch": 0.01, + "learning_rate": 2.469188194420331e-05, + "loss": 3.9162, + "step": 1545728 + }, + { + "epoch": 0.01, + "learning_rate": 2.4683495996692795e-05, + "loss": 3.9006, + "step": 1546240 + }, + { + "epoch": 0.01, + "learning_rate": 2.4675110049182275e-05, + "loss": 3.9126, + "step": 1546752 + }, + { + "epoch": 0.01, + "learning_rate": 2.4666724101671754e-05, + "loss": 3.9097, + "step": 1547264 + }, + { + "epoch": 0.01, + "learning_rate": 2.4658338154161234e-05, + "loss": 3.9285, + "step": 1547776 + }, + { + "epoch": 0.01, + "learning_rate": 2.464995220665071e-05, + "loss": 3.9161, + "step": 1548288 + }, + { + "epoch": 0.01, + "learning_rate": 2.464156625914019e-05, + "loss": 3.9158, + "step": 1548800 + }, + { + "epoch": 0.01, + "learning_rate": 2.463318031162967e-05, + "loss": 3.9178, + "step": 1549312 + }, + { + "epoch": 0.01, + "learning_rate": 2.462479436411915e-05, + "loss": 3.9178, + "step": 1549824 + }, + { + "epoch": 0.01, + "learning_rate": 2.4616424795412363e-05, + "loss": 3.9242, + "step": 1550336 + }, + { + "epoch": 0.01, + "learning_rate": 2.4608038847901843e-05, + "loss": 3.9023, + "step": 1550848 + }, + { + "epoch": 0.01, + "learning_rate": 2.4599652900391323e-05, + "loss": 3.9067, + "step": 1551360 + }, + { + "epoch": 0.01, + "learning_rate": 2.4591266952880803e-05, + "loss": 3.9262, + "step": 1551872 + }, + { + "epoch": 0.01, + "learning_rate": 2.4582881005370283e-05, + "loss": 3.9202, + "step": 1552384 + }, + { + "epoch": 0.01, + "learning_rate": 2.4574527815467228e-05, + "loss": 3.9073, + "step": 1552896 + }, + { + "epoch": 0.01, + "learning_rate": 2.4566141867956708e-05, + "loss": 3.9043, + "step": 1553408 + }, + { + "epoch": 0.01, + "learning_rate": 2.4557772299249917e-05, + "loss": 3.9144, + "step": 1553920 + }, + { + "epoch": 0.01, + "learning_rate": 2.4549386351739397e-05, + "loss": 3.8993, + "step": 1554432 + }, + { + "epoch": 0.01, + "learning_rate": 2.4541000404228877e-05, + "loss": 3.921, + "step": 1554944 + }, + { + "epoch": 0.01, + "learning_rate": 2.4532614456718357e-05, + "loss": 3.9058, + "step": 1555456 + }, + { + "epoch": 0.01, + "learning_rate": 2.4524228509207837e-05, + "loss": 3.9158, + "step": 1555968 + }, + { + "epoch": 0.01, + "learning_rate": 2.4515842561697317e-05, + "loss": 3.9156, + "step": 1556480 + }, + { + "epoch": 0.01, + "learning_rate": 2.4507456614186797e-05, + "loss": 3.9089, + "step": 1556992 + }, + { + "epoch": 0.01, + "learning_rate": 2.4499087045480006e-05, + "loss": 3.9025, + "step": 1557504 + }, + { + "epoch": 0.01, + "learning_rate": 2.4490701097969486e-05, + "loss": 3.9099, + "step": 1558016 + }, + { + "epoch": 0.01, + "learning_rate": 2.4482315150458966e-05, + "loss": 3.8999, + "step": 1558528 + }, + { + "epoch": 0.01, + "learning_rate": 2.447392920294845e-05, + "loss": 3.9107, + "step": 1559040 + }, + { + "epoch": 0.01, + "learning_rate": 2.446554325543793e-05, + "loss": 3.9181, + "step": 1559552 + }, + { + "epoch": 0.01, + "learning_rate": 2.445715730792741e-05, + "loss": 3.9082, + "step": 1560064 + }, + { + "epoch": 0.01, + "learning_rate": 2.444877136041689e-05, + "loss": 3.9072, + "step": 1560576 + }, + { + "epoch": 0.01, + "learning_rate": 2.4440385412906366e-05, + "loss": 3.8956, + "step": 1561088 + }, + { + "epoch": 0.01, + "learning_rate": 2.4431999465395846e-05, + "loss": 3.9027, + "step": 1561600 + }, + { + "epoch": 0.01, + "learning_rate": 2.4423613517885326e-05, + "loss": 3.9161, + "step": 1562112 + }, + { + "epoch": 0.01, + "learning_rate": 2.4415243949178538e-05, + "loss": 3.9234, + "step": 1562624 + }, + { + "epoch": 0.01, + "learning_rate": 2.4406858001668018e-05, + "loss": 3.9085, + "step": 1563136 + }, + { + "epoch": 0.01, + "learning_rate": 2.4398472054157498e-05, + "loss": 3.9159, + "step": 1563648 + }, + { + "epoch": 0.01, + "learning_rate": 2.4390086106646978e-05, + "loss": 3.9266, + "step": 1564160 + }, + { + "epoch": 0.01, + "learning_rate": 2.4381700159136458e-05, + "loss": 3.9183, + "step": 1564672 + }, + { + "epoch": 0.01, + "learning_rate": 2.437333059042967e-05, + "loss": 3.8975, + "step": 1565184 + }, + { + "epoch": 0.01, + "learning_rate": 2.436494464291915e-05, + "loss": 3.9153, + "step": 1565696 + }, + { + "epoch": 0.01, + "learning_rate": 2.435655869540863e-05, + "loss": 3.9128, + "step": 1566208 + }, + { + "epoch": 0.01, + "learning_rate": 2.434817274789811e-05, + "loss": 3.9077, + "step": 1566720 + }, + { + "epoch": 0.01, + "learning_rate": 2.433980317919132e-05, + "loss": 3.9096, + "step": 1567232 + }, + { + "epoch": 0.01, + "learning_rate": 2.43314172316808e-05, + "loss": 3.9166, + "step": 1567744 + }, + { + "epoch": 0.01, + "learning_rate": 2.432303128417028e-05, + "loss": 3.9251, + "step": 1568256 + }, + { + "epoch": 0.01, + "learning_rate": 2.431464533665976e-05, + "loss": 3.9122, + "step": 1568768 + }, + { + "epoch": 0.01, + "learning_rate": 2.4306259389149243e-05, + "loss": 3.8959, + "step": 1569280 + }, + { + "epoch": 0.01, + "learning_rate": 2.429787344163872e-05, + "loss": 3.9115, + "step": 1569792 + }, + { + "epoch": 0.01, + "learning_rate": 2.42894874941282e-05, + "loss": 3.9124, + "step": 1570304 + }, + { + "epoch": 0.01, + "learning_rate": 2.428110154661768e-05, + "loss": 3.9139, + "step": 1570816 + }, + { + "epoch": 0.01, + "learning_rate": 2.427273197791089e-05, + "loss": 3.9183, + "step": 1571328 + }, + { + "epoch": 0.01, + "learning_rate": 2.4264362409204104e-05, + "loss": 3.9166, + "step": 1571840 + }, + { + "epoch": 0.02, + "learning_rate": 2.4255976461693584e-05, + "loss": 3.918, + "step": 1572352 + }, + { + "epoch": 0.02, + "learning_rate": 2.4247590514183064e-05, + "loss": 3.9057, + "step": 1572864 + }, + { + "epoch": 0.02, + "learning_rate": 2.4239204566672544e-05, + "loss": 3.9019, + "step": 1573376 + }, + { + "epoch": 0.02, + "learning_rate": 2.423081861916202e-05, + "loss": 3.9057, + "step": 1573888 + }, + { + "epoch": 0.02, + "learning_rate": 2.4222449050455233e-05, + "loss": 3.9186, + "step": 1574400 + }, + { + "epoch": 0.02, + "learning_rate": 2.4214063102944713e-05, + "loss": 3.913, + "step": 1574912 + }, + { + "epoch": 0.02, + "learning_rate": 2.4205677155434193e-05, + "loss": 3.9189, + "step": 1575424 + }, + { + "epoch": 0.02, + "learning_rate": 2.4197291207923673e-05, + "loss": 3.8983, + "step": 1575936 + }, + { + "epoch": 0.02, + "learning_rate": 2.4188905260413153e-05, + "loss": 3.9156, + "step": 1576448 + }, + { + "epoch": 0.02, + "learning_rate": 2.4180519312902633e-05, + "loss": 3.92, + "step": 1576960 + }, + { + "epoch": 0.02, + "learning_rate": 2.4172133365392113e-05, + "loss": 3.9157, + "step": 1577472 + }, + { + "epoch": 0.02, + "learning_rate": 2.4163747417881593e-05, + "loss": 3.9113, + "step": 1577984 + }, + { + "epoch": 0.02, + "learning_rate": 2.4155361470371073e-05, + "loss": 3.906, + "step": 1578496 + }, + { + "epoch": 0.02, + "learning_rate": 2.4146991901664285e-05, + "loss": 3.9085, + "step": 1579008 + }, + { + "epoch": 0.02, + "learning_rate": 2.4138605954153765e-05, + "loss": 3.916, + "step": 1579520 + }, + { + "epoch": 0.02, + "learning_rate": 2.4130220006643245e-05, + "loss": 3.8924, + "step": 1580032 + }, + { + "epoch": 0.02, + "learning_rate": 2.4121850437936454e-05, + "loss": 3.9104, + "step": 1580544 + }, + { + "epoch": 0.02, + "learning_rate": 2.4113464490425934e-05, + "loss": 3.9064, + "step": 1581056 + }, + { + "epoch": 0.02, + "learning_rate": 2.4105078542915417e-05, + "loss": 3.9135, + "step": 1581568 + }, + { + "epoch": 0.02, + "learning_rate": 2.4096708974208627e-05, + "loss": 3.8986, + "step": 1582080 + }, + { + "epoch": 0.02, + "learning_rate": 2.4088323026698106e-05, + "loss": 3.9183, + "step": 1582592 + }, + { + "epoch": 0.02, + "learning_rate": 2.4079937079187586e-05, + "loss": 3.9047, + "step": 1583104 + }, + { + "epoch": 0.02, + "learning_rate": 2.4071551131677066e-05, + "loss": 3.9166, + "step": 1583616 + }, + { + "epoch": 0.02, + "learning_rate": 2.4063165184166546e-05, + "loss": 3.9074, + "step": 1584128 + }, + { + "epoch": 0.02, + "learning_rate": 2.4054779236656026e-05, + "loss": 3.901, + "step": 1584640 + }, + { + "epoch": 0.02, + "learning_rate": 2.4046393289145506e-05, + "loss": 3.9176, + "step": 1585152 + }, + { + "epoch": 0.02, + "learning_rate": 2.4038007341634986e-05, + "loss": 3.9233, + "step": 1585664 + }, + { + "epoch": 0.02, + "learning_rate": 2.40296377729282e-05, + "loss": 3.9155, + "step": 1586176 + }, + { + "epoch": 0.02, + "learning_rate": 2.4021251825417675e-05, + "loss": 3.903, + "step": 1586688 + }, + { + "epoch": 0.02, + "learning_rate": 2.4012865877907155e-05, + "loss": 3.9095, + "step": 1587200 + }, + { + "epoch": 0.02, + "learning_rate": 2.4004479930396635e-05, + "loss": 3.915, + "step": 1587712 + }, + { + "epoch": 0.02, + "learning_rate": 2.3996110361689848e-05, + "loss": 3.9031, + "step": 1588224 + }, + { + "epoch": 0.02, + "learning_rate": 2.3987724414179328e-05, + "loss": 3.9115, + "step": 1588736 + }, + { + "epoch": 0.02, + "learning_rate": 2.3979338466668808e-05, + "loss": 3.907, + "step": 1589248 + }, + { + "epoch": 0.02, + "learning_rate": 2.3970952519158288e-05, + "loss": 3.9108, + "step": 1589760 + }, + { + "epoch": 0.02, + "learning_rate": 2.3962566571647767e-05, + "loss": 3.9095, + "step": 1590272 + }, + { + "epoch": 0.02, + "learning_rate": 2.3954180624137247e-05, + "loss": 3.911, + "step": 1590784 + }, + { + "epoch": 0.02, + "learning_rate": 2.3945794676626727e-05, + "loss": 3.8947, + "step": 1591296 + }, + { + "epoch": 0.02, + "learning_rate": 2.3937408729116207e-05, + "loss": 3.9104, + "step": 1591808 + }, + { + "epoch": 0.02, + "learning_rate": 2.392905553921315e-05, + "loss": 3.9067, + "step": 1592320 + }, + { + "epoch": 0.02, + "learning_rate": 2.392066959170263e-05, + "loss": 3.9202, + "step": 1592832 + }, + { + "epoch": 0.02, + "learning_rate": 2.391228364419211e-05, + "loss": 3.9122, + "step": 1593344 + }, + { + "epoch": 0.02, + "learning_rate": 2.390389769668159e-05, + "loss": 3.9188, + "step": 1593856 + }, + { + "epoch": 0.02, + "learning_rate": 2.3895511749171072e-05, + "loss": 3.9013, + "step": 1594368 + }, + { + "epoch": 0.02, + "learning_rate": 2.3887125801660552e-05, + "loss": 3.9213, + "step": 1594880 + }, + { + "epoch": 0.02, + "learning_rate": 2.387873985415003e-05, + "loss": 3.9157, + "step": 1595392 + }, + { + "epoch": 0.02, + "learning_rate": 2.387035390663951e-05, + "loss": 3.9166, + "step": 1595904 + }, + { + "epoch": 0.02, + "learning_rate": 2.386196795912899e-05, + "loss": 3.9038, + "step": 1596416 + }, + { + "epoch": 0.02, + "learning_rate": 2.385358201161847e-05, + "loss": 3.9175, + "step": 1596928 + }, + { + "epoch": 0.02, + "learning_rate": 2.384521244291168e-05, + "loss": 3.917, + "step": 1597440 + }, + { + "epoch": 0.02, + "learning_rate": 2.383682649540116e-05, + "loss": 3.9298, + "step": 1597952 + }, + { + "epoch": 0.02, + "learning_rate": 2.382844054789064e-05, + "loss": 3.9002, + "step": 1598464 + }, + { + "epoch": 0.02, + "learning_rate": 2.382005460038012e-05, + "loss": 3.9168, + "step": 1598976 + }, + { + "epoch": 0.02, + "learning_rate": 2.38116686528696e-05, + "loss": 3.9131, + "step": 1599488 + }, + { + "epoch": 0.02, + "learning_rate": 2.380328270535908e-05, + "loss": 3.9029, + "step": 1600000 + }, + { + "epoch": 0.02, + "learning_rate": 2.3794896757848557e-05, + "loss": 3.9159, + "step": 1600512 + }, + { + "epoch": 0.02, + "learning_rate": 2.378651081033804e-05, + "loss": 3.9191, + "step": 1601024 + }, + { + "epoch": 0.02, + "learning_rate": 2.3778141241631253e-05, + "loss": 3.915, + "step": 1601536 + }, + { + "epoch": 0.02, + "learning_rate": 2.3769771672924462e-05, + "loss": 3.9063, + "step": 1602048 + }, + { + "epoch": 0.02, + "learning_rate": 2.3761385725413942e-05, + "loss": 3.9113, + "step": 1602560 + }, + { + "epoch": 0.03, + "eval_loss": 3.9974782466888428, + "eval_runtime": 293.5121, + "eval_samples_per_second": 1300.086, + "eval_steps_per_second": 40.629, + "step": 1602720 + }, + { + "epoch": 1.0, + "learning_rate": 2.3752999777903422e-05, + "loss": 3.9039, + "step": 1603072 + }, + { + "epoch": 1.0, + "learning_rate": 2.3744613830392902e-05, + "loss": 3.9008, + "step": 1603584 + }, + { + "epoch": 1.0, + "learning_rate": 2.3736227882882382e-05, + "loss": 3.9165, + "step": 1604096 + }, + { + "epoch": 1.0, + "learning_rate": 2.3727841935371862e-05, + "loss": 3.9115, + "step": 1604608 + }, + { + "epoch": 1.0, + "learning_rate": 2.3719455987861342e-05, + "loss": 3.9191, + "step": 1605120 + }, + { + "epoch": 1.0, + "learning_rate": 2.3711070040350822e-05, + "loss": 3.9112, + "step": 1605632 + }, + { + "epoch": 1.0, + "learning_rate": 2.370270047164403e-05, + "loss": 3.9091, + "step": 1606144 + }, + { + "epoch": 1.0, + "learning_rate": 2.369431452413351e-05, + "loss": 3.8992, + "step": 1606656 + }, + { + "epoch": 1.0, + "learning_rate": 2.368592857662299e-05, + "loss": 3.9116, + "step": 1607168 + }, + { + "epoch": 1.0, + "learning_rate": 2.3677542629112474e-05, + "loss": 3.9111, + "step": 1607680 + }, + { + "epoch": 1.0, + "learning_rate": 2.3669156681601954e-05, + "loss": 3.9163, + "step": 1608192 + }, + { + "epoch": 1.0, + "learning_rate": 2.3660787112895163e-05, + "loss": 3.9172, + "step": 1608704 + }, + { + "epoch": 1.0, + "learning_rate": 2.3652417544188376e-05, + "loss": 3.9066, + "step": 1609216 + }, + { + "epoch": 1.0, + "learning_rate": 2.3644031596677856e-05, + "loss": 3.9061, + "step": 1609728 + }, + { + "epoch": 1.0, + "learning_rate": 2.3635645649167336e-05, + "loss": 3.906, + "step": 1610240 + }, + { + "epoch": 1.0, + "learning_rate": 2.3627259701656816e-05, + "loss": 3.8944, + "step": 1610752 + }, + { + "epoch": 1.0, + "learning_rate": 2.3618873754146296e-05, + "loss": 3.9088, + "step": 1611264 + }, + { + "epoch": 1.0, + "learning_rate": 2.3610487806635776e-05, + "loss": 3.9046, + "step": 1611776 + }, + { + "epoch": 1.0, + "learning_rate": 2.3602101859125256e-05, + "loss": 3.9005, + "step": 1612288 + }, + { + "epoch": 1.0, + "learning_rate": 2.3593715911614736e-05, + "loss": 3.9221, + "step": 1612800 + }, + { + "epoch": 1.0, + "learning_rate": 2.3585346342907945e-05, + "loss": 3.9151, + "step": 1613312 + }, + { + "epoch": 1.0, + "learning_rate": 2.3576960395397428e-05, + "loss": 3.9112, + "step": 1613824 + }, + { + "epoch": 1.0, + "learning_rate": 2.3568574447886908e-05, + "loss": 3.916, + "step": 1614336 + }, + { + "epoch": 1.0, + "learning_rate": 2.3560188500376388e-05, + "loss": 3.9208, + "step": 1614848 + }, + { + "epoch": 1.0, + "learning_rate": 2.3551818931669597e-05, + "loss": 3.8973, + "step": 1615360 + }, + { + "epoch": 1.0, + "learning_rate": 2.3543449362962806e-05, + "loss": 3.9081, + "step": 1615872 + }, + { + "epoch": 1.0, + "learning_rate": 2.353506341545229e-05, + "loss": 3.9144, + "step": 1616384 + }, + { + "epoch": 1.0, + "learning_rate": 2.352667746794177e-05, + "loss": 3.9051, + "step": 1616896 + }, + { + "epoch": 1.0, + "learning_rate": 2.351829152043125e-05, + "loss": 3.8975, + "step": 1617408 + }, + { + "epoch": 1.0, + "learning_rate": 2.350990557292073e-05, + "loss": 3.901, + "step": 1617920 + }, + { + "epoch": 1.01, + "learning_rate": 2.350151962541021e-05, + "loss": 3.9137, + "step": 1618432 + }, + { + "epoch": 1.01, + "learning_rate": 2.3493133677899686e-05, + "loss": 3.9139, + "step": 1618944 + }, + { + "epoch": 1.01, + "learning_rate": 2.3484747730389166e-05, + "loss": 3.9112, + "step": 1619456 + }, + { + "epoch": 1.01, + "learning_rate": 2.3476378161682382e-05, + "loss": 3.9179, + "step": 1619968 + }, + { + "epoch": 1.01, + "learning_rate": 2.346800859297559e-05, + "loss": 3.9078, + "step": 1620480 + }, + { + "epoch": 1.01, + "learning_rate": 2.345962264546507e-05, + "loss": 3.9105, + "step": 1620992 + }, + { + "epoch": 1.01, + "learning_rate": 2.345123669795455e-05, + "loss": 3.9037, + "step": 1621504 + }, + { + "epoch": 1.01, + "learning_rate": 2.344285075044403e-05, + "loss": 3.9089, + "step": 1622016 + }, + { + "epoch": 1.01, + "learning_rate": 2.343446480293351e-05, + "loss": 3.8953, + "step": 1622528 + }, + { + "epoch": 1.01, + "learning_rate": 2.342607885542299e-05, + "loss": 3.9027, + "step": 1623040 + }, + { + "epoch": 1.01, + "learning_rate": 2.3417709286716203e-05, + "loss": 3.9044, + "step": 1623552 + }, + { + "epoch": 1.01, + "learning_rate": 2.3409323339205683e-05, + "loss": 3.9202, + "step": 1624064 + }, + { + "epoch": 1.01, + "learning_rate": 2.340093739169516e-05, + "loss": 3.9082, + "step": 1624576 + }, + { + "epoch": 1.01, + "learning_rate": 2.339255144418464e-05, + "loss": 3.909, + "step": 1625088 + }, + { + "epoch": 1.01, + "learning_rate": 2.338416549667412e-05, + "loss": 3.914, + "step": 1625600 + }, + { + "epoch": 1.01, + "learning_rate": 2.33757795491636e-05, + "loss": 3.9043, + "step": 1626112 + }, + { + "epoch": 1.01, + "learning_rate": 2.3367393601653083e-05, + "loss": 3.918, + "step": 1626624 + }, + { + "epoch": 1.01, + "learning_rate": 2.3359007654142563e-05, + "loss": 3.8977, + "step": 1627136 + }, + { + "epoch": 1.01, + "learning_rate": 2.3350621706632043e-05, + "loss": 3.8955, + "step": 1627648 + }, + { + "epoch": 1.01, + "learning_rate": 2.334223575912152e-05, + "loss": 3.9161, + "step": 1628160 + }, + { + "epoch": 1.01, + "learning_rate": 2.3333849811611e-05, + "loss": 3.9112, + "step": 1628672 + }, + { + "epoch": 1.01, + "learning_rate": 2.332546386410048e-05, + "loss": 3.9006, + "step": 1629184 + }, + { + "epoch": 1.01, + "learning_rate": 2.331707791658996e-05, + "loss": 3.9027, + "step": 1629696 + }, + { + "epoch": 1.01, + "learning_rate": 2.330870834788317e-05, + "loss": 3.9079, + "step": 1630208 + }, + { + "epoch": 1.01, + "learning_rate": 2.330032240037265e-05, + "loss": 3.8906, + "step": 1630720 + }, + { + "epoch": 1.01, + "learning_rate": 2.329193645286213e-05, + "loss": 3.9128, + "step": 1631232 + }, + { + "epoch": 1.01, + "learning_rate": 2.328355050535161e-05, + "loss": 3.8985, + "step": 1631744 + }, + { + "epoch": 1.01, + "learning_rate": 2.327518093664482e-05, + "loss": 3.9043, + "step": 1632256 + }, + { + "epoch": 1.01, + "learning_rate": 2.3266811367938036e-05, + "loss": 3.9129, + "step": 1632768 + }, + { + "epoch": 1.01, + "learning_rate": 2.3258425420427516e-05, + "loss": 3.9012, + "step": 1633280 + }, + { + "epoch": 1.01, + "learning_rate": 2.3250039472916993e-05, + "loss": 3.8997, + "step": 1633792 + }, + { + "epoch": 1.01, + "learning_rate": 2.3241653525406473e-05, + "loss": 3.9014, + "step": 1634304 + }, + { + "epoch": 1.01, + "learning_rate": 2.3233267577895953e-05, + "loss": 3.8934, + "step": 1634816 + }, + { + "epoch": 1.01, + "learning_rate": 2.3224881630385433e-05, + "loss": 3.9011, + "step": 1635328 + }, + { + "epoch": 1.01, + "learning_rate": 2.3216495682874913e-05, + "loss": 3.912, + "step": 1635840 + }, + { + "epoch": 1.01, + "learning_rate": 2.3208109735364396e-05, + "loss": 3.9039, + "step": 1636352 + }, + { + "epoch": 1.01, + "learning_rate": 2.3199740166657605e-05, + "loss": 3.8962, + "step": 1636864 + }, + { + "epoch": 1.01, + "learning_rate": 2.3191370597950814e-05, + "loss": 3.893, + "step": 1637376 + }, + { + "epoch": 1.01, + "learning_rate": 2.3182984650440294e-05, + "loss": 3.8932, + "step": 1637888 + }, + { + "epoch": 1.01, + "learning_rate": 2.3174598702929774e-05, + "loss": 3.9061, + "step": 1638400 + }, + { + "epoch": 1.01, + "learning_rate": 2.3166212755419258e-05, + "loss": 3.9137, + "step": 1638912 + }, + { + "epoch": 1.01, + "learning_rate": 2.3157826807908738e-05, + "loss": 3.9056, + "step": 1639424 + }, + { + "epoch": 1.01, + "learning_rate": 2.3149440860398218e-05, + "loss": 3.9102, + "step": 1639936 + }, + { + "epoch": 1.01, + "learning_rate": 2.3141054912887697e-05, + "loss": 3.9152, + "step": 1640448 + }, + { + "epoch": 1.01, + "learning_rate": 2.3132668965377174e-05, + "loss": 3.9172, + "step": 1640960 + }, + { + "epoch": 1.01, + "learning_rate": 2.312431577547412e-05, + "loss": 3.8895, + "step": 1641472 + }, + { + "epoch": 1.01, + "learning_rate": 2.31159298279636e-05, + "loss": 3.905, + "step": 1641984 + }, + { + "epoch": 1.01, + "learning_rate": 2.310754388045308e-05, + "loss": 3.9089, + "step": 1642496 + }, + { + "epoch": 1.01, + "learning_rate": 2.309915793294256e-05, + "loss": 3.8964, + "step": 1643008 + }, + { + "epoch": 1.01, + "learning_rate": 2.309077198543204e-05, + "loss": 3.9083, + "step": 1643520 + }, + { + "epoch": 1.01, + "learning_rate": 2.3082402416725248e-05, + "loss": 3.9023, + "step": 1644032 + }, + { + "epoch": 1.01, + "learning_rate": 2.3074016469214728e-05, + "loss": 3.9174, + "step": 1644544 + }, + { + "epoch": 1.01, + "learning_rate": 2.3065630521704208e-05, + "loss": 3.9077, + "step": 1645056 + }, + { + "epoch": 1.01, + "learning_rate": 2.305724457419369e-05, + "loss": 3.8893, + "step": 1645568 + }, + { + "epoch": 1.01, + "learning_rate": 2.304885862668317e-05, + "loss": 3.9032, + "step": 1646080 + }, + { + "epoch": 1.01, + "learning_rate": 2.3040472679172648e-05, + "loss": 3.9036, + "step": 1646592 + }, + { + "epoch": 1.01, + "learning_rate": 2.3032086731662128e-05, + "loss": 3.9095, + "step": 1647104 + }, + { + "epoch": 1.01, + "learning_rate": 2.3023700784151608e-05, + "loss": 3.9069, + "step": 1647616 + }, + { + "epoch": 1.01, + "learning_rate": 2.301533121544482e-05, + "loss": 3.912, + "step": 1648128 + }, + { + "epoch": 1.02, + "learning_rate": 2.30069452679343e-05, + "loss": 3.9098, + "step": 1648640 + }, + { + "epoch": 1.02, + "learning_rate": 2.299855932042378e-05, + "loss": 3.9005, + "step": 1649152 + }, + { + "epoch": 1.02, + "learning_rate": 2.299017337291326e-05, + "loss": 3.8916, + "step": 1649664 + }, + { + "epoch": 1.02, + "learning_rate": 2.298180380420647e-05, + "loss": 3.8992, + "step": 1650176 + }, + { + "epoch": 1.02, + "learning_rate": 2.297341785669595e-05, + "loss": 3.9126, + "step": 1650688 + }, + { + "epoch": 1.02, + "learning_rate": 2.296503190918543e-05, + "loss": 3.9059, + "step": 1651200 + }, + { + "epoch": 1.02, + "learning_rate": 2.2956645961674912e-05, + "loss": 3.9094, + "step": 1651712 + }, + { + "epoch": 1.02, + "learning_rate": 2.294827639296812e-05, + "loss": 3.8936, + "step": 1652224 + }, + { + "epoch": 1.02, + "learning_rate": 2.29398904454576e-05, + "loss": 3.9084, + "step": 1652736 + }, + { + "epoch": 1.02, + "learning_rate": 2.293150449794708e-05, + "loss": 3.9133, + "step": 1653248 + }, + { + "epoch": 1.02, + "learning_rate": 2.292311855043656e-05, + "loss": 3.9114, + "step": 1653760 + }, + { + "epoch": 1.02, + "learning_rate": 2.291473260292604e-05, + "loss": 3.9037, + "step": 1654272 + }, + { + "epoch": 1.02, + "learning_rate": 2.2906363034219254e-05, + "loss": 3.901, + "step": 1654784 + }, + { + "epoch": 1.02, + "learning_rate": 2.2897977086708734e-05, + "loss": 3.8995, + "step": 1655296 + }, + { + "epoch": 1.02, + "learning_rate": 2.2889591139198214e-05, + "loss": 3.912, + "step": 1655808 + }, + { + "epoch": 1.02, + "learning_rate": 2.2881205191687694e-05, + "loss": 3.8834, + "step": 1656320 + }, + { + "epoch": 1.02, + "learning_rate": 2.2872835622980903e-05, + "loss": 3.9023, + "step": 1656832 + }, + { + "epoch": 1.02, + "learning_rate": 2.2864466054274115e-05, + "loss": 3.8971, + "step": 1657344 + }, + { + "epoch": 1.02, + "learning_rate": 2.2856096485567328e-05, + "loss": 3.9072, + "step": 1657856 + }, + { + "epoch": 1.02, + "learning_rate": 2.2847710538056808e-05, + "loss": 3.8903, + "step": 1658368 + }, + { + "epoch": 1.02, + "learning_rate": 2.2839324590546288e-05, + "loss": 3.9152, + "step": 1658880 + }, + { + "epoch": 1.02, + "learning_rate": 2.2830938643035764e-05, + "loss": 3.8978, + "step": 1659392 + }, + { + "epoch": 1.02, + "learning_rate": 2.2822552695525244e-05, + "loss": 3.9089, + "step": 1659904 + }, + { + "epoch": 1.02, + "learning_rate": 2.2814166748014727e-05, + "loss": 3.899, + "step": 1660416 + }, + { + "epoch": 1.02, + "learning_rate": 2.2805780800504207e-05, + "loss": 3.8958, + "step": 1660928 + }, + { + "epoch": 1.02, + "learning_rate": 2.2797394852993687e-05, + "loss": 3.9073, + "step": 1661440 + }, + { + "epoch": 1.02, + "learning_rate": 2.2789025284286896e-05, + "loss": 3.9172, + "step": 1661952 + }, + { + "epoch": 1.02, + "learning_rate": 2.278065571558011e-05, + "loss": 3.9083, + "step": 1662464 + }, + { + "epoch": 1.02, + "learning_rate": 2.277226976806959e-05, + "loss": 3.8952, + "step": 1662976 + }, + { + "epoch": 1.02, + "learning_rate": 2.276388382055907e-05, + "loss": 3.9038, + "step": 1663488 + }, + { + "epoch": 1.02, + "learning_rate": 2.275549787304855e-05, + "loss": 3.9078, + "step": 1664000 + }, + { + "epoch": 1.02, + "learning_rate": 2.274711192553803e-05, + "loss": 3.8959, + "step": 1664512 + }, + { + "epoch": 1.02, + "learning_rate": 2.273872597802751e-05, + "loss": 3.907, + "step": 1665024 + }, + { + "epoch": 1.02, + "learning_rate": 2.273034003051699e-05, + "loss": 3.8955, + "step": 1665536 + }, + { + "epoch": 1.02, + "learning_rate": 2.272195408300647e-05, + "loss": 3.9048, + "step": 1666048 + }, + { + "epoch": 1.02, + "learning_rate": 2.2713568135495945e-05, + "loss": 3.9046, + "step": 1666560 + }, + { + "epoch": 1.02, + "learning_rate": 2.270518218798543e-05, + "loss": 3.9052, + "step": 1667072 + }, + { + "epoch": 1.02, + "learning_rate": 2.269681261927864e-05, + "loss": 3.8859, + "step": 1667584 + }, + { + "epoch": 1.02, + "learning_rate": 2.268842667176812e-05, + "loss": 3.9063, + "step": 1668096 + }, + { + "epoch": 1.02, + "learning_rate": 2.268005710306133e-05, + "loss": 3.8979, + "step": 1668608 + }, + { + "epoch": 1.02, + "learning_rate": 2.267167115555081e-05, + "loss": 3.9123, + "step": 1669120 + }, + { + "epoch": 1.02, + "learning_rate": 2.266328520804029e-05, + "loss": 3.9072, + "step": 1669632 + }, + { + "epoch": 1.02, + "learning_rate": 2.265489926052977e-05, + "loss": 3.912, + "step": 1670144 + }, + { + "epoch": 1.02, + "learning_rate": 2.264651331301925e-05, + "loss": 3.8935, + "step": 1670656 + }, + { + "epoch": 1.02, + "learning_rate": 2.263812736550873e-05, + "loss": 3.9126, + "step": 1671168 + }, + { + "epoch": 1.02, + "learning_rate": 2.262974141799821e-05, + "loss": 3.911, + "step": 1671680 + }, + { + "epoch": 1.02, + "learning_rate": 2.262135547048769e-05, + "loss": 3.9086, + "step": 1672192 + }, + { + "epoch": 1.02, + "learning_rate": 2.261296952297717e-05, + "loss": 3.9009, + "step": 1672704 + }, + { + "epoch": 1.02, + "learning_rate": 2.260458357546665e-05, + "loss": 3.9096, + "step": 1673216 + }, + { + "epoch": 1.02, + "learning_rate": 2.259619762795613e-05, + "loss": 3.9112, + "step": 1673728 + }, + { + "epoch": 1.02, + "learning_rate": 2.258781168044561e-05, + "loss": 3.9182, + "step": 1674240 + }, + { + "epoch": 1.02, + "learning_rate": 2.257942573293509e-05, + "loss": 3.8964, + "step": 1674752 + }, + { + "epoch": 1.02, + "learning_rate": 2.2571056164228302e-05, + "loss": 3.9106, + "step": 1675264 + }, + { + "epoch": 1.02, + "learning_rate": 2.256267021671778e-05, + "loss": 3.906, + "step": 1675776 + }, + { + "epoch": 1.02, + "learning_rate": 2.255428426920726e-05, + "loss": 3.8979, + "step": 1676288 + }, + { + "epoch": 1.02, + "learning_rate": 2.2545914700500474e-05, + "loss": 3.9106, + "step": 1676800 + }, + { + "epoch": 1.02, + "learning_rate": 2.253752875298995e-05, + "loss": 3.907, + "step": 1677312 + }, + { + "epoch": 1.02, + "learning_rate": 2.252914280547943e-05, + "loss": 3.914, + "step": 1677824 + }, + { + "epoch": 1.02, + "learning_rate": 2.2520773236772643e-05, + "loss": 3.897, + "step": 1678336 + }, + { + "epoch": 1.02, + "learning_rate": 2.2512387289262123e-05, + "loss": 3.9049, + "step": 1678848 + }, + { + "epoch": 1.03, + "eval_loss": 3.994375467300415, + "eval_runtime": 293.3334, + "eval_samples_per_second": 1300.878, + "eval_steps_per_second": 40.653, + "step": 1679040 + }, + { + "epoch": 0.0, + "learning_rate": 2.25040013417516e-05, + "loss": 3.8972, + "step": 1679360 + }, + { + "epoch": 0.0, + "learning_rate": 2.2495615394241083e-05, + "loss": 3.8895, + "step": 1679872 + }, + { + "epoch": 0.0, + "learning_rate": 2.2487229446730563e-05, + "loss": 3.9094, + "step": 1680384 + }, + { + "epoch": 0.0, + "learning_rate": 2.2478843499220043e-05, + "loss": 3.9066, + "step": 1680896 + }, + { + "epoch": 0.0, + "learning_rate": 2.2470457551709523e-05, + "loss": 3.9133, + "step": 1681408 + }, + { + "epoch": 0.0, + "learning_rate": 2.2462071604199003e-05, + "loss": 3.9041, + "step": 1681920 + }, + { + "epoch": 0.0, + "learning_rate": 2.2453685656688483e-05, + "loss": 3.8971, + "step": 1682432 + }, + { + "epoch": 0.0, + "learning_rate": 2.244529970917796e-05, + "loss": 3.8964, + "step": 1682944 + }, + { + "epoch": 0.0, + "learning_rate": 2.243691376166744e-05, + "loss": 3.9019, + "step": 1683456 + }, + { + "epoch": 0.0, + "learning_rate": 2.2428527814156923e-05, + "loss": 3.9027, + "step": 1683968 + }, + { + "epoch": 0.0, + "learning_rate": 2.2420141866646403e-05, + "loss": 3.9102, + "step": 1684480 + }, + { + "epoch": 0.0, + "learning_rate": 2.2411755919135883e-05, + "loss": 3.9143, + "step": 1684992 + }, + { + "epoch": 0.0, + "learning_rate": 2.2403386350429092e-05, + "loss": 3.9015, + "step": 1685504 + }, + { + "epoch": 0.0, + "learning_rate": 2.2395000402918572e-05, + "loss": 3.8972, + "step": 1686016 + }, + { + "epoch": 0.0, + "learning_rate": 2.2386614455408052e-05, + "loss": 3.9027, + "step": 1686528 + }, + { + "epoch": 0.0, + "learning_rate": 2.2378228507897532e-05, + "loss": 3.8868, + "step": 1687040 + }, + { + "epoch": 0.0, + "learning_rate": 2.2369842560387015e-05, + "loss": 3.9004, + "step": 1687552 + }, + { + "epoch": 0.0, + "learning_rate": 2.2361456612876492e-05, + "loss": 3.8974, + "step": 1688064 + }, + { + "epoch": 0.0, + "learning_rate": 2.2353070665365972e-05, + "loss": 3.8963, + "step": 1688576 + }, + { + "epoch": 0.0, + "learning_rate": 2.234468471785545e-05, + "loss": 3.9139, + "step": 1689088 + }, + { + "epoch": 0.0, + "learning_rate": 2.2336315149148664e-05, + "loss": 3.907, + "step": 1689600 + }, + { + "epoch": 0.0, + "learning_rate": 2.2327929201638144e-05, + "loss": 3.9058, + "step": 1690112 + }, + { + "epoch": 0.0, + "learning_rate": 2.2319543254127624e-05, + "loss": 3.9055, + "step": 1690624 + }, + { + "epoch": 0.0, + "learning_rate": 2.2311157306617104e-05, + "loss": 3.9131, + "step": 1691136 + }, + { + "epoch": 0.0, + "learning_rate": 2.2302771359106584e-05, + "loss": 3.893, + "step": 1691648 + }, + { + "epoch": 0.0, + "learning_rate": 2.2294385411596064e-05, + "loss": 3.9043, + "step": 1692160 + }, + { + "epoch": 0.0, + "learning_rate": 2.2286015842889273e-05, + "loss": 3.9018, + "step": 1692672 + }, + { + "epoch": 0.0, + "learning_rate": 2.2277629895378753e-05, + "loss": 3.897, + "step": 1693184 + }, + { + "epoch": 0.0, + "learning_rate": 2.2269243947868236e-05, + "loss": 3.8968, + "step": 1693696 + }, + { + "epoch": 0.0, + "learning_rate": 2.2260858000357716e-05, + "loss": 3.8909, + "step": 1694208 + }, + { + "epoch": 0.01, + "learning_rate": 2.2252472052847196e-05, + "loss": 3.9084, + "step": 1694720 + }, + { + "epoch": 0.01, + "learning_rate": 2.2244086105336673e-05, + "loss": 3.9067, + "step": 1695232 + }, + { + "epoch": 0.01, + "learning_rate": 2.2235700157826153e-05, + "loss": 3.9047, + "step": 1695744 + }, + { + "epoch": 0.01, + "learning_rate": 2.2227314210315633e-05, + "loss": 3.912, + "step": 1696256 + }, + { + "epoch": 0.01, + "learning_rate": 2.2218961020412578e-05, + "loss": 3.8996, + "step": 1696768 + }, + { + "epoch": 0.01, + "learning_rate": 2.2210575072902058e-05, + "loss": 3.9037, + "step": 1697280 + }, + { + "epoch": 0.01, + "learning_rate": 2.2202189125391538e-05, + "loss": 3.8997, + "step": 1697792 + }, + { + "epoch": 0.01, + "learning_rate": 2.2193803177881018e-05, + "loss": 3.8962, + "step": 1698304 + }, + { + "epoch": 0.01, + "learning_rate": 2.2185417230370494e-05, + "loss": 3.8892, + "step": 1698816 + }, + { + "epoch": 0.01, + "learning_rate": 2.2177031282859974e-05, + "loss": 3.8964, + "step": 1699328 + }, + { + "epoch": 0.01, + "learning_rate": 2.2168645335349454e-05, + "loss": 3.9007, + "step": 1699840 + }, + { + "epoch": 0.01, + "learning_rate": 2.216027576664267e-05, + "loss": 3.9143, + "step": 1700352 + }, + { + "epoch": 0.01, + "learning_rate": 2.2151889819132147e-05, + "loss": 3.8999, + "step": 1700864 + }, + { + "epoch": 0.01, + "learning_rate": 2.2143503871621626e-05, + "loss": 3.8999, + "step": 1701376 + }, + { + "epoch": 0.01, + "learning_rate": 2.2135117924111106e-05, + "loss": 3.9097, + "step": 1701888 + }, + { + "epoch": 0.01, + "learning_rate": 2.2126731976600586e-05, + "loss": 3.8986, + "step": 1702400 + }, + { + "epoch": 0.01, + "learning_rate": 2.2118346029090066e-05, + "loss": 3.9092, + "step": 1702912 + }, + { + "epoch": 0.01, + "learning_rate": 2.2109960081579546e-05, + "loss": 3.8937, + "step": 1703424 + }, + { + "epoch": 0.01, + "learning_rate": 2.2101574134069026e-05, + "loss": 3.8857, + "step": 1703936 + }, + { + "epoch": 0.01, + "learning_rate": 2.209320456536224e-05, + "loss": 3.9099, + "step": 1704448 + }, + { + "epoch": 0.01, + "learning_rate": 2.208481861785172e-05, + "loss": 3.9048, + "step": 1704960 + }, + { + "epoch": 0.01, + "learning_rate": 2.2076449049144928e-05, + "loss": 3.8998, + "step": 1705472 + }, + { + "epoch": 0.01, + "learning_rate": 2.2068063101634408e-05, + "loss": 3.8914, + "step": 1705984 + }, + { + "epoch": 0.01, + "learning_rate": 2.205967715412389e-05, + "loss": 3.9048, + "step": 1706496 + }, + { + "epoch": 0.01, + "learning_rate": 2.205129120661337e-05, + "loss": 3.8814, + "step": 1707008 + }, + { + "epoch": 0.01, + "learning_rate": 2.204290525910285e-05, + "loss": 3.9047, + "step": 1707520 + }, + { + "epoch": 0.01, + "learning_rate": 2.2034519311592328e-05, + "loss": 3.8927, + "step": 1708032 + }, + { + "epoch": 0.01, + "learning_rate": 2.2026133364081808e-05, + "loss": 3.8937, + "step": 1708544 + }, + { + "epoch": 0.01, + "learning_rate": 2.2017747416571287e-05, + "loss": 3.908, + "step": 1709056 + }, + { + "epoch": 0.01, + "learning_rate": 2.20093778478645e-05, + "loss": 3.8927, + "step": 1709568 + }, + { + "epoch": 0.01, + "learning_rate": 2.2001008279157712e-05, + "loss": 3.8935, + "step": 1710080 + }, + { + "epoch": 0.01, + "learning_rate": 2.1992622331647192e-05, + "loss": 3.8983, + "step": 1710592 + }, + { + "epoch": 0.01, + "learning_rate": 2.1984236384136672e-05, + "loss": 3.8832, + "step": 1711104 + }, + { + "epoch": 0.01, + "learning_rate": 2.197586681542988e-05, + "loss": 3.8961, + "step": 1711616 + }, + { + "epoch": 0.01, + "learning_rate": 2.196748086791936e-05, + "loss": 3.9036, + "step": 1712128 + }, + { + "epoch": 0.01, + "learning_rate": 2.1959094920408845e-05, + "loss": 3.8994, + "step": 1712640 + }, + { + "epoch": 0.01, + "learning_rate": 2.1950708972898325e-05, + "loss": 3.8909, + "step": 1713152 + }, + { + "epoch": 0.01, + "learning_rate": 2.19423230253878e-05, + "loss": 3.8876, + "step": 1713664 + }, + { + "epoch": 0.01, + "learning_rate": 2.193393707787728e-05, + "loss": 3.8831, + "step": 1714176 + }, + { + "epoch": 0.01, + "learning_rate": 2.192555113036676e-05, + "loss": 3.897, + "step": 1714688 + }, + { + "epoch": 0.01, + "learning_rate": 2.191716518285624e-05, + "loss": 3.9082, + "step": 1715200 + }, + { + "epoch": 0.01, + "learning_rate": 2.1908795614149454e-05, + "loss": 3.8996, + "step": 1715712 + }, + { + "epoch": 0.01, + "learning_rate": 2.1900409666638934e-05, + "loss": 3.9041, + "step": 1716224 + }, + { + "epoch": 0.01, + "learning_rate": 2.1892023719128414e-05, + "loss": 3.9049, + "step": 1716736 + }, + { + "epoch": 0.01, + "learning_rate": 2.1883637771617893e-05, + "loss": 3.915, + "step": 1717248 + }, + { + "epoch": 0.01, + "learning_rate": 2.1875268202911103e-05, + "loss": 3.8856, + "step": 1717760 + }, + { + "epoch": 0.01, + "learning_rate": 2.1866882255400583e-05, + "loss": 3.9024, + "step": 1718272 + }, + { + "epoch": 0.01, + "learning_rate": 2.1858496307890063e-05, + "loss": 3.9021, + "step": 1718784 + }, + { + "epoch": 0.01, + "learning_rate": 2.1850110360379546e-05, + "loss": 3.884, + "step": 1719296 + }, + { + "epoch": 0.01, + "learning_rate": 2.1841740791672755e-05, + "loss": 3.9041, + "step": 1719808 + }, + { + "epoch": 0.01, + "learning_rate": 2.1833354844162235e-05, + "loss": 3.8999, + "step": 1720320 + }, + { + "epoch": 0.01, + "learning_rate": 2.1824968896651715e-05, + "loss": 3.9054, + "step": 1720832 + }, + { + "epoch": 0.01, + "learning_rate": 2.1816582949141195e-05, + "loss": 3.9018, + "step": 1721344 + }, + { + "epoch": 0.01, + "learning_rate": 2.1808197001630675e-05, + "loss": 3.8841, + "step": 1721856 + }, + { + "epoch": 0.01, + "learning_rate": 2.179984381172762e-05, + "loss": 3.8955, + "step": 1722368 + }, + { + "epoch": 0.01, + "learning_rate": 2.1791457864217096e-05, + "loss": 3.8971, + "step": 1722880 + }, + { + "epoch": 0.01, + "learning_rate": 2.1783071916706576e-05, + "loss": 3.9014, + "step": 1723392 + }, + { + "epoch": 0.01, + "learning_rate": 2.1774685969196056e-05, + "loss": 3.8988, + "step": 1723904 + }, + { + "epoch": 0.01, + "learning_rate": 2.1766300021685536e-05, + "loss": 3.9065, + "step": 1724416 + }, + { + "epoch": 0.02, + "learning_rate": 2.1757914074175016e-05, + "loss": 3.9017, + "step": 1724928 + }, + { + "epoch": 0.02, + "learning_rate": 2.17495281266645e-05, + "loss": 3.8956, + "step": 1725440 + }, + { + "epoch": 0.02, + "learning_rate": 2.174114217915398e-05, + "loss": 3.8896, + "step": 1725952 + }, + { + "epoch": 0.02, + "learning_rate": 2.1732756231643456e-05, + "loss": 3.8902, + "step": 1726464 + }, + { + "epoch": 0.02, + "learning_rate": 2.172438666293667e-05, + "loss": 3.9087, + "step": 1726976 + }, + { + "epoch": 0.02, + "learning_rate": 2.171600071542615e-05, + "loss": 3.901, + "step": 1727488 + }, + { + "epoch": 0.02, + "learning_rate": 2.1707614767915625e-05, + "loss": 3.9009, + "step": 1728000 + }, + { + "epoch": 0.02, + "learning_rate": 2.169922882040511e-05, + "loss": 3.8873, + "step": 1728512 + }, + { + "epoch": 0.02, + "learning_rate": 2.169084287289459e-05, + "loss": 3.8992, + "step": 1729024 + }, + { + "epoch": 0.02, + "learning_rate": 2.1682456925384068e-05, + "loss": 3.908, + "step": 1729536 + }, + { + "epoch": 0.02, + "learning_rate": 2.1674070977873548e-05, + "loss": 3.9044, + "step": 1730048 + }, + { + "epoch": 0.02, + "learning_rate": 2.1665685030363028e-05, + "loss": 3.8979, + "step": 1730560 + }, + { + "epoch": 0.02, + "learning_rate": 2.1657299082852508e-05, + "loss": 3.8951, + "step": 1731072 + }, + { + "epoch": 0.02, + "learning_rate": 2.1648929514145717e-05, + "loss": 3.8959, + "step": 1731584 + }, + { + "epoch": 0.02, + "learning_rate": 2.16405435666352e-05, + "loss": 3.9033, + "step": 1732096 + }, + { + "epoch": 0.02, + "learning_rate": 2.163217399792841e-05, + "loss": 3.8786, + "step": 1732608 + }, + { + "epoch": 0.02, + "learning_rate": 2.162378805041789e-05, + "loss": 3.8929, + "step": 1733120 + }, + { + "epoch": 0.02, + "learning_rate": 2.161540210290737e-05, + "loss": 3.8909, + "step": 1733632 + }, + { + "epoch": 0.02, + "learning_rate": 2.160701615539685e-05, + "loss": 3.9031, + "step": 1734144 + }, + { + "epoch": 0.02, + "learning_rate": 2.1598646586690062e-05, + "loss": 3.888, + "step": 1734656 + }, + { + "epoch": 0.02, + "learning_rate": 2.1590260639179542e-05, + "loss": 3.9059, + "step": 1735168 + }, + { + "epoch": 0.02, + "learning_rate": 2.1581874691669022e-05, + "loss": 3.8931, + "step": 1735680 + }, + { + "epoch": 0.02, + "learning_rate": 2.1573488744158502e-05, + "loss": 3.9001, + "step": 1736192 + }, + { + "epoch": 0.02, + "learning_rate": 2.1565102796647982e-05, + "loss": 3.8985, + "step": 1736704 + }, + { + "epoch": 0.02, + "learning_rate": 2.155673322794119e-05, + "loss": 3.886, + "step": 1737216 + }, + { + "epoch": 0.02, + "learning_rate": 2.154834728043067e-05, + "loss": 3.9013, + "step": 1737728 + }, + { + "epoch": 0.02, + "learning_rate": 2.1539961332920154e-05, + "loss": 3.9125, + "step": 1738240 + }, + { + "epoch": 0.02, + "learning_rate": 2.1531591764213363e-05, + "loss": 3.9003, + "step": 1738752 + }, + { + "epoch": 0.02, + "learning_rate": 2.1523205816702843e-05, + "loss": 3.8979, + "step": 1739264 + }, + { + "epoch": 0.02, + "learning_rate": 2.1514819869192323e-05, + "loss": 3.8892, + "step": 1739776 + }, + { + "epoch": 0.02, + "learning_rate": 2.1506433921681803e-05, + "loss": 3.9017, + "step": 1740288 + }, + { + "epoch": 0.02, + "learning_rate": 2.149804797417128e-05, + "loss": 3.8972, + "step": 1740800 + }, + { + "epoch": 0.02, + "learning_rate": 2.1489662026660763e-05, + "loss": 3.8971, + "step": 1741312 + }, + { + "epoch": 0.02, + "learning_rate": 2.1481276079150243e-05, + "loss": 3.8878, + "step": 1741824 + }, + { + "epoch": 0.02, + "learning_rate": 2.1472890131639723e-05, + "loss": 3.8976, + "step": 1742336 + }, + { + "epoch": 0.02, + "learning_rate": 2.1464504184129203e-05, + "loss": 3.8997, + "step": 1742848 + }, + { + "epoch": 0.02, + "learning_rate": 2.1456118236618683e-05, + "loss": 3.897, + "step": 1743360 + }, + { + "epoch": 0.02, + "learning_rate": 2.1447732289108163e-05, + "loss": 3.8793, + "step": 1743872 + }, + { + "epoch": 0.02, + "learning_rate": 2.143934634159764e-05, + "loss": 3.9019, + "step": 1744384 + }, + { + "epoch": 0.02, + "learning_rate": 2.1430993151694585e-05, + "loss": 3.8892, + "step": 1744896 + }, + { + "epoch": 0.02, + "learning_rate": 2.1422607204184064e-05, + "loss": 3.9082, + "step": 1745408 + }, + { + "epoch": 0.02, + "learning_rate": 2.1414221256673544e-05, + "loss": 3.8981, + "step": 1745920 + }, + { + "epoch": 0.02, + "learning_rate": 2.1405835309163024e-05, + "loss": 3.9067, + "step": 1746432 + }, + { + "epoch": 0.02, + "learning_rate": 2.1397449361652504e-05, + "loss": 3.8864, + "step": 1746944 + }, + { + "epoch": 0.02, + "learning_rate": 2.1389063414141984e-05, + "loss": 3.9069, + "step": 1747456 + }, + { + "epoch": 0.02, + "learning_rate": 2.1380693845435197e-05, + "loss": 3.904, + "step": 1747968 + }, + { + "epoch": 0.02, + "learning_rate": 2.1372307897924677e-05, + "loss": 3.9024, + "step": 1748480 + }, + { + "epoch": 0.02, + "learning_rate": 2.1363921950414157e-05, + "loss": 3.8895, + "step": 1748992 + }, + { + "epoch": 0.02, + "learning_rate": 2.1355536002903637e-05, + "loss": 3.9042, + "step": 1749504 + }, + { + "epoch": 0.02, + "learning_rate": 2.1347150055393113e-05, + "loss": 3.9052, + "step": 1750016 + }, + { + "epoch": 0.02, + "learning_rate": 2.1338764107882593e-05, + "loss": 3.9115, + "step": 1750528 + }, + { + "epoch": 0.02, + "learning_rate": 2.1330378160372077e-05, + "loss": 3.8922, + "step": 1751040 + }, + { + "epoch": 0.02, + "learning_rate": 2.1321992212861556e-05, + "loss": 3.9015, + "step": 1751552 + }, + { + "epoch": 0.02, + "learning_rate": 2.1313606265351036e-05, + "loss": 3.9011, + "step": 1752064 + }, + { + "epoch": 0.02, + "learning_rate": 2.1305236696644246e-05, + "loss": 3.894, + "step": 1752576 + }, + { + "epoch": 0.02, + "learning_rate": 2.1296850749133725e-05, + "loss": 3.8972, + "step": 1753088 + }, + { + "epoch": 0.02, + "learning_rate": 2.1288464801623205e-05, + "loss": 3.9038, + "step": 1753600 + }, + { + "epoch": 0.02, + "learning_rate": 2.1280078854112685e-05, + "loss": 3.9055, + "step": 1754112 + }, + { + "epoch": 0.02, + "learning_rate": 2.1271692906602165e-05, + "loss": 3.8942, + "step": 1754624 + }, + { + "epoch": 0.02, + "learning_rate": 2.1263306959091645e-05, + "loss": 3.8979, + "step": 1755136 + }, + { + "epoch": 0.03, + "eval_loss": 3.9918322563171387, + "eval_runtime": 284.8355, + "eval_samples_per_second": 1339.689, + "eval_steps_per_second": 41.866, + "step": 1755360 + }, + { + "epoch": 1.0, + "learning_rate": 2.1254921011581125e-05, + "loss": 3.8935, + "step": 1755648 + }, + { + "epoch": 1.0, + "learning_rate": 2.1246535064070605e-05, + "loss": 3.8825, + "step": 1756160 + }, + { + "epoch": 1.0, + "learning_rate": 2.1238165495363818e-05, + "loss": 3.9006, + "step": 1756672 + }, + { + "epoch": 1.0, + "learning_rate": 2.1229779547853294e-05, + "loss": 3.8997, + "step": 1757184 + }, + { + "epoch": 1.0, + "learning_rate": 2.1221393600342778e-05, + "loss": 3.9021, + "step": 1757696 + }, + { + "epoch": 1.0, + "learning_rate": 2.1213007652832258e-05, + "loss": 3.9004, + "step": 1758208 + }, + { + "epoch": 1.0, + "learning_rate": 2.1204638084125467e-05, + "loss": 3.8912, + "step": 1758720 + }, + { + "epoch": 1.0, + "learning_rate": 2.1196252136614947e-05, + "loss": 3.8884, + "step": 1759232 + }, + { + "epoch": 1.0, + "learning_rate": 2.1187866189104427e-05, + "loss": 3.8974, + "step": 1759744 + }, + { + "epoch": 1.0, + "learning_rate": 2.1179480241593907e-05, + "loss": 3.8942, + "step": 1760256 + }, + { + "epoch": 1.0, + "learning_rate": 2.1171094294083386e-05, + "loss": 3.903, + "step": 1760768 + }, + { + "epoch": 1.0, + "learning_rate": 2.116270834657287e-05, + "loss": 3.9063, + "step": 1761280 + }, + { + "epoch": 1.0, + "learning_rate": 2.115433877786608e-05, + "loss": 3.8952, + "step": 1761792 + }, + { + "epoch": 1.0, + "learning_rate": 2.114595283035556e-05, + "loss": 3.8921, + "step": 1762304 + }, + { + "epoch": 1.0, + "learning_rate": 2.113756688284504e-05, + "loss": 3.8912, + "step": 1762816 + }, + { + "epoch": 1.0, + "learning_rate": 2.112918093533452e-05, + "loss": 3.878, + "step": 1763328 + }, + { + "epoch": 1.0, + "learning_rate": 2.1120794987824e-05, + "loss": 3.8962, + "step": 1763840 + }, + { + "epoch": 1.0, + "learning_rate": 2.111240904031348e-05, + "loss": 3.8911, + "step": 1764352 + }, + { + "epoch": 1.0, + "learning_rate": 2.110405585041042e-05, + "loss": 3.8937, + "step": 1764864 + }, + { + "epoch": 1.0, + "learning_rate": 2.10956699028999e-05, + "loss": 3.9031, + "step": 1765376 + }, + { + "epoch": 1.0, + "learning_rate": 2.108728395538938e-05, + "loss": 3.9047, + "step": 1765888 + }, + { + "epoch": 1.0, + "learning_rate": 2.107889800787886e-05, + "loss": 3.899, + "step": 1766400 + }, + { + "epoch": 1.0, + "learning_rate": 2.107051206036834e-05, + "loss": 3.8971, + "step": 1766912 + }, + { + "epoch": 1.0, + "learning_rate": 2.106212611285782e-05, + "loss": 3.9037, + "step": 1767424 + }, + { + "epoch": 1.0, + "learning_rate": 2.10537401653473e-05, + "loss": 3.8889, + "step": 1767936 + }, + { + "epoch": 1.0, + "learning_rate": 2.104535421783678e-05, + "loss": 3.8983, + "step": 1768448 + }, + { + "epoch": 1.0, + "learning_rate": 2.103696827032626e-05, + "loss": 3.8984, + "step": 1768960 + }, + { + "epoch": 1.0, + "learning_rate": 2.102858232281574e-05, + "loss": 3.8924, + "step": 1769472 + }, + { + "epoch": 1.0, + "learning_rate": 2.102019637530522e-05, + "loss": 3.8882, + "step": 1769984 + }, + { + "epoch": 1.0, + "learning_rate": 2.10118104277947e-05, + "loss": 3.8873, + "step": 1770496 + }, + { + "epoch": 1.01, + "learning_rate": 2.1003440859087912e-05, + "loss": 3.8996, + "step": 1771008 + }, + { + "epoch": 1.01, + "learning_rate": 2.0995054911577392e-05, + "loss": 3.9031, + "step": 1771520 + }, + { + "epoch": 1.01, + "learning_rate": 2.0986668964066872e-05, + "loss": 3.8979, + "step": 1772032 + }, + { + "epoch": 1.01, + "learning_rate": 2.0978283016556352e-05, + "loss": 3.9047, + "step": 1772544 + }, + { + "epoch": 1.01, + "learning_rate": 2.096991344784956e-05, + "loss": 3.89, + "step": 1773056 + }, + { + "epoch": 1.01, + "learning_rate": 2.096152750033904e-05, + "loss": 3.8993, + "step": 1773568 + }, + { + "epoch": 1.01, + "learning_rate": 2.0953141552828525e-05, + "loss": 3.8997, + "step": 1774080 + }, + { + "epoch": 1.01, + "learning_rate": 2.0944755605318005e-05, + "loss": 3.8847, + "step": 1774592 + }, + { + "epoch": 1.01, + "learning_rate": 2.093636965780748e-05, + "loss": 3.8888, + "step": 1775104 + }, + { + "epoch": 1.01, + "learning_rate": 2.0928000089100694e-05, + "loss": 3.8883, + "step": 1775616 + }, + { + "epoch": 1.01, + "learning_rate": 2.0919614141590174e-05, + "loss": 3.8921, + "step": 1776128 + }, + { + "epoch": 1.01, + "learning_rate": 2.091122819407965e-05, + "loss": 3.9077, + "step": 1776640 + }, + { + "epoch": 1.01, + "learning_rate": 2.0902842246569133e-05, + "loss": 3.8929, + "step": 1777152 + }, + { + "epoch": 1.01, + "learning_rate": 2.0894472677862346e-05, + "loss": 3.8887, + "step": 1777664 + }, + { + "epoch": 1.01, + "learning_rate": 2.0886086730351826e-05, + "loss": 3.9072, + "step": 1778176 + }, + { + "epoch": 1.01, + "learning_rate": 2.0877700782841302e-05, + "loss": 3.8942, + "step": 1778688 + }, + { + "epoch": 1.01, + "learning_rate": 2.0869314835330782e-05, + "loss": 3.9013, + "step": 1779200 + }, + { + "epoch": 1.01, + "learning_rate": 2.0860945266623995e-05, + "loss": 3.8878, + "step": 1779712 + }, + { + "epoch": 1.01, + "learning_rate": 2.0852559319113478e-05, + "loss": 3.8805, + "step": 1780224 + }, + { + "epoch": 1.01, + "learning_rate": 2.0844189750406687e-05, + "loss": 3.9093, + "step": 1780736 + }, + { + "epoch": 1.01, + "learning_rate": 2.0835803802896167e-05, + "loss": 3.8948, + "step": 1781248 + }, + { + "epoch": 1.01, + "learning_rate": 2.0827434234189376e-05, + "loss": 3.8939, + "step": 1781760 + }, + { + "epoch": 1.01, + "learning_rate": 2.0819048286678856e-05, + "loss": 3.8904, + "step": 1782272 + }, + { + "epoch": 1.01, + "learning_rate": 2.081066233916834e-05, + "loss": 3.8888, + "step": 1782784 + }, + { + "epoch": 1.01, + "learning_rate": 2.080227639165782e-05, + "loss": 3.8808, + "step": 1783296 + }, + { + "epoch": 1.01, + "learning_rate": 2.07938904441473e-05, + "loss": 3.8931, + "step": 1783808 + }, + { + "epoch": 1.01, + "learning_rate": 2.0785504496636776e-05, + "loss": 3.8882, + "step": 1784320 + }, + { + "epoch": 1.01, + "learning_rate": 2.0777118549126256e-05, + "loss": 3.8899, + "step": 1784832 + }, + { + "epoch": 1.01, + "learning_rate": 2.0768732601615736e-05, + "loss": 3.8993, + "step": 1785344 + }, + { + "epoch": 1.01, + "learning_rate": 2.0760346654105216e-05, + "loss": 3.8877, + "step": 1785856 + }, + { + "epoch": 1.01, + "learning_rate": 2.075197708539843e-05, + "loss": 3.8842, + "step": 1786368 + }, + { + "epoch": 1.01, + "learning_rate": 2.074359113788791e-05, + "loss": 3.8982, + "step": 1786880 + }, + { + "epoch": 1.01, + "learning_rate": 2.073520519037739e-05, + "loss": 3.8777, + "step": 1787392 + }, + { + "epoch": 1.01, + "learning_rate": 2.072681924286687e-05, + "loss": 3.8892, + "step": 1787904 + }, + { + "epoch": 1.01, + "learning_rate": 2.071843329535635e-05, + "loss": 3.8945, + "step": 1788416 + }, + { + "epoch": 1.01, + "learning_rate": 2.0710047347845828e-05, + "loss": 3.8938, + "step": 1788928 + }, + { + "epoch": 1.01, + "learning_rate": 2.0701661400335305e-05, + "loss": 3.8833, + "step": 1789440 + }, + { + "epoch": 1.01, + "learning_rate": 2.0693275452824788e-05, + "loss": 3.8848, + "step": 1789952 + }, + { + "epoch": 1.01, + "learning_rate": 2.0684905884118e-05, + "loss": 3.8744, + "step": 1790464 + }, + { + "epoch": 1.01, + "learning_rate": 2.067651993660748e-05, + "loss": 3.8918, + "step": 1790976 + }, + { + "epoch": 1.01, + "learning_rate": 2.0668133989096957e-05, + "loss": 3.9023, + "step": 1791488 + }, + { + "epoch": 1.01, + "learning_rate": 2.0659748041586437e-05, + "loss": 3.8946, + "step": 1792000 + }, + { + "epoch": 1.01, + "learning_rate": 2.065137847287965e-05, + "loss": 3.8932, + "step": 1792512 + }, + { + "epoch": 1.01, + "learning_rate": 2.0642992525369133e-05, + "loss": 3.8997, + "step": 1793024 + }, + { + "epoch": 1.01, + "learning_rate": 2.063460657785861e-05, + "loss": 3.9099, + "step": 1793536 + }, + { + "epoch": 1.01, + "learning_rate": 2.062625338795555e-05, + "loss": 3.8788, + "step": 1794048 + }, + { + "epoch": 1.01, + "learning_rate": 2.061786744044503e-05, + "loss": 3.8964, + "step": 1794560 + }, + { + "epoch": 1.01, + "learning_rate": 2.060948149293451e-05, + "loss": 3.8988, + "step": 1795072 + }, + { + "epoch": 1.01, + "learning_rate": 2.0601095545423994e-05, + "loss": 3.8739, + "step": 1795584 + }, + { + "epoch": 1.01, + "learning_rate": 2.0592709597913474e-05, + "loss": 3.9016, + "step": 1796096 + }, + { + "epoch": 1.01, + "learning_rate": 2.0584323650402954e-05, + "loss": 3.8899, + "step": 1796608 + }, + { + "epoch": 1.01, + "learning_rate": 2.057593770289243e-05, + "loss": 3.9015, + "step": 1797120 + }, + { + "epoch": 1.01, + "learning_rate": 2.056755175538191e-05, + "loss": 3.8975, + "step": 1797632 + }, + { + "epoch": 1.01, + "learning_rate": 2.0559182186675123e-05, + "loss": 3.8781, + "step": 1798144 + }, + { + "epoch": 1.01, + "learning_rate": 2.0550796239164603e-05, + "loss": 3.8872, + "step": 1798656 + }, + { + "epoch": 1.01, + "learning_rate": 2.0542410291654083e-05, + "loss": 3.8947, + "step": 1799168 + }, + { + "epoch": 1.01, + "learning_rate": 2.0534024344143563e-05, + "loss": 3.8937, + "step": 1799680 + }, + { + "epoch": 1.01, + "learning_rate": 2.0525638396633043e-05, + "loss": 3.8944, + "step": 1800192 + }, + { + "epoch": 1.01, + "learning_rate": 2.0517268827926252e-05, + "loss": 3.8988, + "step": 1800704 + }, + { + "epoch": 1.02, + "learning_rate": 2.0508899259219465e-05, + "loss": 3.8935, + "step": 1801216 + }, + { + "epoch": 1.02, + "learning_rate": 2.0500513311708948e-05, + "loss": 3.8887, + "step": 1801728 + }, + { + "epoch": 1.02, + "learning_rate": 2.0492127364198428e-05, + "loss": 3.8873, + "step": 1802240 + }, + { + "epoch": 1.02, + "learning_rate": 2.0483741416687905e-05, + "loss": 3.8827, + "step": 1802752 + }, + { + "epoch": 1.02, + "learning_rate": 2.0475355469177385e-05, + "loss": 3.9008, + "step": 1803264 + }, + { + "epoch": 1.02, + "learning_rate": 2.0466969521666865e-05, + "loss": 3.8946, + "step": 1803776 + }, + { + "epoch": 1.02, + "learning_rate": 2.0458583574156345e-05, + "loss": 3.9001, + "step": 1804288 + }, + { + "epoch": 1.02, + "learning_rate": 2.0450197626645824e-05, + "loss": 3.8783, + "step": 1804800 + }, + { + "epoch": 1.02, + "learning_rate": 2.0441828057939037e-05, + "loss": 3.8921, + "step": 1805312 + }, + { + "epoch": 1.02, + "learning_rate": 2.0433442110428517e-05, + "loss": 3.9009, + "step": 1805824 + }, + { + "epoch": 1.02, + "learning_rate": 2.0425056162917997e-05, + "loss": 3.9001, + "step": 1806336 + }, + { + "epoch": 1.02, + "learning_rate": 2.0416670215407477e-05, + "loss": 3.8913, + "step": 1806848 + }, + { + "epoch": 1.02, + "learning_rate": 2.0408300646700686e-05, + "loss": 3.8868, + "step": 1807360 + }, + { + "epoch": 1.02, + "learning_rate": 2.0399914699190166e-05, + "loss": 3.8921, + "step": 1807872 + }, + { + "epoch": 1.02, + "learning_rate": 2.039154513048338e-05, + "loss": 3.8973, + "step": 1808384 + }, + { + "epoch": 1.02, + "learning_rate": 2.0383159182972858e-05, + "loss": 3.8718, + "step": 1808896 + }, + { + "epoch": 1.02, + "learning_rate": 2.0374773235462338e-05, + "loss": 3.8907, + "step": 1809408 + }, + { + "epoch": 1.02, + "learning_rate": 2.0366387287951818e-05, + "loss": 3.879, + "step": 1809920 + }, + { + "epoch": 1.02, + "learning_rate": 2.0358001340441298e-05, + "loss": 3.897, + "step": 1810432 + }, + { + "epoch": 1.02, + "learning_rate": 2.034963177173451e-05, + "loss": 3.8848, + "step": 1810944 + }, + { + "epoch": 1.02, + "learning_rate": 2.034124582422399e-05, + "loss": 3.893, + "step": 1811456 + }, + { + "epoch": 1.02, + "learning_rate": 2.033285987671347e-05, + "loss": 3.8876, + "step": 1811968 + }, + { + "epoch": 1.02, + "learning_rate": 2.032447392920295e-05, + "loss": 3.8975, + "step": 1812480 + }, + { + "epoch": 1.02, + "learning_rate": 2.031608798169243e-05, + "loss": 3.8899, + "step": 1812992 + }, + { + "epoch": 1.02, + "learning_rate": 2.0307702034181907e-05, + "loss": 3.8807, + "step": 1813504 + }, + { + "epoch": 1.02, + "learning_rate": 2.0299316086671387e-05, + "loss": 3.8954, + "step": 1814016 + }, + { + "epoch": 1.02, + "learning_rate": 2.0290930139160867e-05, + "loss": 3.9048, + "step": 1814528 + }, + { + "epoch": 1.02, + "learning_rate": 2.0282560570454083e-05, + "loss": 3.894, + "step": 1815040 + }, + { + "epoch": 1.02, + "learning_rate": 2.027417462294356e-05, + "loss": 3.8937, + "step": 1815552 + }, + { + "epoch": 1.02, + "learning_rate": 2.026578867543304e-05, + "loss": 3.8818, + "step": 1816064 + }, + { + "epoch": 1.02, + "learning_rate": 2.025740272792252e-05, + "loss": 3.8958, + "step": 1816576 + }, + { + "epoch": 1.02, + "learning_rate": 2.0249016780412e-05, + "loss": 3.8956, + "step": 1817088 + }, + { + "epoch": 1.02, + "learning_rate": 2.024063083290148e-05, + "loss": 3.8842, + "step": 1817600 + }, + { + "epoch": 1.02, + "learning_rate": 2.0232261264194692e-05, + "loss": 3.8865, + "step": 1818112 + }, + { + "epoch": 1.02, + "learning_rate": 2.022387531668417e-05, + "loss": 3.8909, + "step": 1818624 + }, + { + "epoch": 1.02, + "learning_rate": 2.021548936917365e-05, + "loss": 3.8937, + "step": 1819136 + }, + { + "epoch": 1.02, + "learning_rate": 2.020711980046686e-05, + "loss": 3.8903, + "step": 1819648 + }, + { + "epoch": 1.02, + "learning_rate": 2.019873385295634e-05, + "loss": 3.8732, + "step": 1820160 + }, + { + "epoch": 1.02, + "learning_rate": 2.019034790544582e-05, + "loss": 3.8949, + "step": 1820672 + }, + { + "epoch": 1.02, + "learning_rate": 2.0181961957935304e-05, + "loss": 3.882, + "step": 1821184 + }, + { + "epoch": 1.02, + "learning_rate": 2.0173576010424784e-05, + "loss": 3.902, + "step": 1821696 + }, + { + "epoch": 1.02, + "learning_rate": 2.0165190062914264e-05, + "loss": 3.8962, + "step": 1822208 + }, + { + "epoch": 1.02, + "learning_rate": 2.015680411540374e-05, + "loss": 3.8987, + "step": 1822720 + }, + { + "epoch": 1.02, + "learning_rate": 2.014841816789322e-05, + "loss": 3.8807, + "step": 1823232 + }, + { + "epoch": 1.02, + "learning_rate": 2.01400322203827e-05, + "loss": 3.9048, + "step": 1823744 + }, + { + "epoch": 1.02, + "learning_rate": 2.013164627287218e-05, + "loss": 3.8972, + "step": 1824256 + }, + { + "epoch": 1.02, + "learning_rate": 2.0123276704165393e-05, + "loss": 3.8956, + "step": 1824768 + }, + { + "epoch": 1.02, + "learning_rate": 2.0114890756654873e-05, + "loss": 3.8902, + "step": 1825280 + }, + { + "epoch": 1.02, + "learning_rate": 2.0106504809144353e-05, + "loss": 3.8941, + "step": 1825792 + }, + { + "epoch": 1.02, + "learning_rate": 2.0098118861633833e-05, + "loss": 3.8984, + "step": 1826304 + }, + { + "epoch": 1.02, + "learning_rate": 2.0089732914123313e-05, + "loss": 3.9069, + "step": 1826816 + }, + { + "epoch": 1.02, + "learning_rate": 2.0081363345416525e-05, + "loss": 3.8866, + "step": 1827328 + }, + { + "epoch": 1.02, + "learning_rate": 2.0072977397906005e-05, + "loss": 3.8955, + "step": 1827840 + }, + { + "epoch": 1.02, + "learning_rate": 2.0064591450395485e-05, + "loss": 3.9007, + "step": 1828352 + }, + { + "epoch": 1.02, + "learning_rate": 2.0056205502884965e-05, + "loss": 3.887, + "step": 1828864 + }, + { + "epoch": 1.02, + "learning_rate": 2.0047819555374445e-05, + "loss": 3.8874, + "step": 1829376 + }, + { + "epoch": 1.02, + "learning_rate": 2.003943360786392e-05, + "loss": 3.8973, + "step": 1829888 + }, + { + "epoch": 1.02, + "learning_rate": 2.00310476603534e-05, + "loss": 3.899, + "step": 1830400 + }, + { + "epoch": 1.02, + "learning_rate": 2.002266171284288e-05, + "loss": 3.8882, + "step": 1830912 + }, + { + "epoch": 1.02, + "learning_rate": 2.0014292144136094e-05, + "loss": 3.8934, + "step": 1831424 + }, + { + "epoch": 1.03, + "eval_loss": 3.9898858070373535, + "eval_runtime": 284.9169, + "eval_samples_per_second": 1339.306, + "eval_steps_per_second": 41.854, + "step": 1831680 + }, + { + "epoch": 0.0, + "learning_rate": 2.0005906196625574e-05, + "loss": 3.8836, + "step": 1831936 + }, + { + "epoch": 0.0, + "learning_rate": 1.9997520249115054e-05, + "loss": 3.8812, + "step": 1832448 + }, + { + "epoch": 0.0, + "learning_rate": 1.9989134301604534e-05, + "loss": 3.8929, + "step": 1832960 + }, + { + "epoch": 0.0, + "learning_rate": 1.9980748354094014e-05, + "loss": 3.8919, + "step": 1833472 + }, + { + "epoch": 0.0, + "learning_rate": 1.9972362406583494e-05, + "loss": 3.9014, + "step": 1833984 + }, + { + "epoch": 0.0, + "learning_rate": 1.9963976459072974e-05, + "loss": 3.8895, + "step": 1834496 + }, + { + "epoch": 0.0, + "learning_rate": 1.9955590511562454e-05, + "loss": 3.8908, + "step": 1835008 + }, + { + "epoch": 0.0, + "learning_rate": 1.9947204564051934e-05, + "loss": 3.8866, + "step": 1835520 + }, + { + "epoch": 0.0, + "learning_rate": 1.9938818616541413e-05, + "loss": 3.8892, + "step": 1836032 + }, + { + "epoch": 0.0, + "learning_rate": 1.9930432669030893e-05, + "loss": 3.8903, + "step": 1836544 + }, + { + "epoch": 0.0, + "learning_rate": 1.9922046721520373e-05, + "loss": 3.895, + "step": 1837056 + }, + { + "epoch": 0.0, + "learning_rate": 1.9913660774009853e-05, + "loss": 3.8982, + "step": 1837568 + }, + { + "epoch": 0.0, + "learning_rate": 1.9905291205303066e-05, + "loss": 3.8915, + "step": 1838080 + }, + { + "epoch": 0.0, + "learning_rate": 1.9896905257792546e-05, + "loss": 3.8894, + "step": 1838592 + }, + { + "epoch": 0.0, + "learning_rate": 1.9888519310282026e-05, + "loss": 3.8879, + "step": 1839104 + }, + { + "epoch": 0.0, + "learning_rate": 1.9880133362771506e-05, + "loss": 3.8726, + "step": 1839616 + }, + { + "epoch": 0.0, + "learning_rate": 1.9871747415260982e-05, + "loss": 3.8857, + "step": 1840128 + }, + { + "epoch": 0.0, + "learning_rate": 1.9863361467750462e-05, + "loss": 3.8847, + "step": 1840640 + }, + { + "epoch": 0.0, + "learning_rate": 1.9854975520239942e-05, + "loss": 3.8892, + "step": 1841152 + }, + { + "epoch": 0.0, + "learning_rate": 1.9846589572729422e-05, + "loss": 3.894, + "step": 1841664 + }, + { + "epoch": 0.0, + "learning_rate": 1.9838203625218905e-05, + "loss": 3.9012, + "step": 1842176 + }, + { + "epoch": 0.0, + "learning_rate": 1.9829817677708385e-05, + "loss": 3.8949, + "step": 1842688 + }, + { + "epoch": 0.0, + "learning_rate": 1.9821431730197865e-05, + "loss": 3.8933, + "step": 1843200 + }, + { + "epoch": 0.0, + "learning_rate": 1.9813045782687342e-05, + "loss": 3.895, + "step": 1843712 + }, + { + "epoch": 0.0, + "learning_rate": 1.9804676213980554e-05, + "loss": 3.8842, + "step": 1844224 + }, + { + "epoch": 0.0, + "learning_rate": 1.9796290266470034e-05, + "loss": 3.8907, + "step": 1844736 + }, + { + "epoch": 0.0, + "learning_rate": 1.9787920697763247e-05, + "loss": 3.8927, + "step": 1845248 + }, + { + "epoch": 0.0, + "learning_rate": 1.9779534750252727e-05, + "loss": 3.8874, + "step": 1845760 + }, + { + "epoch": 0.0, + "learning_rate": 1.9771148802742207e-05, + "loss": 3.8858, + "step": 1846272 + }, + { + "epoch": 0.0, + "learning_rate": 1.9762762855231687e-05, + "loss": 3.8792, + "step": 1846784 + }, + { + "epoch": 0.01, + "learning_rate": 1.9754376907721163e-05, + "loss": 3.8907, + "step": 1847296 + }, + { + "epoch": 0.01, + "learning_rate": 1.9745990960210643e-05, + "loss": 3.899, + "step": 1847808 + }, + { + "epoch": 0.01, + "learning_rate": 1.9737605012700127e-05, + "loss": 3.8914, + "step": 1848320 + }, + { + "epoch": 0.01, + "learning_rate": 1.9729219065189607e-05, + "loss": 3.894, + "step": 1848832 + }, + { + "epoch": 0.01, + "learning_rate": 1.9720849496482816e-05, + "loss": 3.8837, + "step": 1849344 + }, + { + "epoch": 0.01, + "learning_rate": 1.9712479927776028e-05, + "loss": 3.8971, + "step": 1849856 + }, + { + "epoch": 0.01, + "learning_rate": 1.9704093980265508e-05, + "loss": 3.8914, + "step": 1850368 + }, + { + "epoch": 0.01, + "learning_rate": 1.9695708032754988e-05, + "loss": 3.8819, + "step": 1850880 + }, + { + "epoch": 0.01, + "learning_rate": 1.9687322085244468e-05, + "loss": 3.8835, + "step": 1851392 + }, + { + "epoch": 0.01, + "learning_rate": 1.9678936137733948e-05, + "loss": 3.8801, + "step": 1851904 + }, + { + "epoch": 0.01, + "learning_rate": 1.9670550190223428e-05, + "loss": 3.8844, + "step": 1852416 + }, + { + "epoch": 0.01, + "learning_rate": 1.9662164242712908e-05, + "loss": 3.9006, + "step": 1852928 + }, + { + "epoch": 0.01, + "learning_rate": 1.9653794674006117e-05, + "loss": 3.8887, + "step": 1853440 + }, + { + "epoch": 0.01, + "learning_rate": 1.9645408726495597e-05, + "loss": 3.8858, + "step": 1853952 + }, + { + "epoch": 0.01, + "learning_rate": 1.9637039157788813e-05, + "loss": 3.8975, + "step": 1854464 + }, + { + "epoch": 0.01, + "learning_rate": 1.962865321027829e-05, + "loss": 3.8872, + "step": 1854976 + }, + { + "epoch": 0.01, + "learning_rate": 1.9620283641571502e-05, + "loss": 3.8983, + "step": 1855488 + }, + { + "epoch": 0.01, + "learning_rate": 1.9611897694060982e-05, + "loss": 3.8869, + "step": 1856000 + }, + { + "epoch": 0.01, + "learning_rate": 1.960351174655046e-05, + "loss": 3.8655, + "step": 1856512 + }, + { + "epoch": 0.01, + "learning_rate": 1.9595125799039942e-05, + "loss": 3.9047, + "step": 1857024 + }, + { + "epoch": 0.01, + "learning_rate": 1.958673985152942e-05, + "loss": 3.8895, + "step": 1857536 + }, + { + "epoch": 0.01, + "learning_rate": 1.95783539040189e-05, + "loss": 3.8903, + "step": 1858048 + }, + { + "epoch": 0.01, + "learning_rate": 1.956996795650838e-05, + "loss": 3.8824, + "step": 1858560 + }, + { + "epoch": 0.01, + "learning_rate": 1.956158200899786e-05, + "loss": 3.8802, + "step": 1859072 + }, + { + "epoch": 0.01, + "learning_rate": 1.955319606148734e-05, + "loss": 3.8814, + "step": 1859584 + }, + { + "epoch": 0.01, + "learning_rate": 1.9544810113976818e-05, + "loss": 3.8858, + "step": 1860096 + }, + { + "epoch": 0.01, + "learning_rate": 1.9536424166466298e-05, + "loss": 3.8837, + "step": 1860608 + }, + { + "epoch": 0.01, + "learning_rate": 1.952803821895578e-05, + "loss": 3.883, + "step": 1861120 + }, + { + "epoch": 0.01, + "learning_rate": 1.9519668650248994e-05, + "loss": 3.8971, + "step": 1861632 + }, + { + "epoch": 0.01, + "learning_rate": 1.9511299081542203e-05, + "loss": 3.8825, + "step": 1862144 + }, + { + "epoch": 0.01, + "learning_rate": 1.9502913134031683e-05, + "loss": 3.8766, + "step": 1862656 + }, + { + "epoch": 0.01, + "learning_rate": 1.9494527186521163e-05, + "loss": 3.8932, + "step": 1863168 + }, + { + "epoch": 0.01, + "learning_rate": 1.9486141239010643e-05, + "loss": 3.8694, + "step": 1863680 + }, + { + "epoch": 0.01, + "learning_rate": 1.9477755291500123e-05, + "loss": 3.8786, + "step": 1864192 + }, + { + "epoch": 0.01, + "learning_rate": 1.9469369343989603e-05, + "loss": 3.8938, + "step": 1864704 + }, + { + "epoch": 0.01, + "learning_rate": 1.9460983396479083e-05, + "loss": 3.8881, + "step": 1865216 + }, + { + "epoch": 0.01, + "learning_rate": 1.9452597448968563e-05, + "loss": 3.8771, + "step": 1865728 + }, + { + "epoch": 0.01, + "learning_rate": 1.9444227880261772e-05, + "loss": 3.8809, + "step": 1866240 + }, + { + "epoch": 0.01, + "learning_rate": 1.9435841932751252e-05, + "loss": 3.8709, + "step": 1866752 + }, + { + "epoch": 0.01, + "learning_rate": 1.9427455985240735e-05, + "loss": 3.8865, + "step": 1867264 + }, + { + "epoch": 0.01, + "learning_rate": 1.9419070037730215e-05, + "loss": 3.894, + "step": 1867776 + }, + { + "epoch": 0.01, + "learning_rate": 1.9410700469023424e-05, + "loss": 3.8865, + "step": 1868288 + }, + { + "epoch": 0.01, + "learning_rate": 1.9402314521512904e-05, + "loss": 3.8876, + "step": 1868800 + }, + { + "epoch": 0.01, + "learning_rate": 1.9393944952806113e-05, + "loss": 3.8969, + "step": 1869312 + }, + { + "epoch": 0.01, + "learning_rate": 1.9385559005295596e-05, + "loss": 3.9003, + "step": 1869824 + }, + { + "epoch": 0.01, + "learning_rate": 1.9377173057785076e-05, + "loss": 3.8733, + "step": 1870336 + }, + { + "epoch": 0.01, + "learning_rate": 1.9368787110274556e-05, + "loss": 3.8938, + "step": 1870848 + }, + { + "epoch": 0.01, + "learning_rate": 1.9360401162764036e-05, + "loss": 3.8882, + "step": 1871360 + }, + { + "epoch": 0.01, + "learning_rate": 1.9352015215253516e-05, + "loss": 3.8729, + "step": 1871872 + }, + { + "epoch": 0.01, + "learning_rate": 1.9343629267742996e-05, + "loss": 3.8921, + "step": 1872384 + }, + { + "epoch": 0.01, + "learning_rate": 1.9335243320232473e-05, + "loss": 3.8863, + "step": 1872896 + }, + { + "epoch": 0.01, + "learning_rate": 1.9326857372721953e-05, + "loss": 3.8984, + "step": 1873408 + }, + { + "epoch": 0.01, + "learning_rate": 1.931848780401517e-05, + "loss": 3.8917, + "step": 1873920 + }, + { + "epoch": 0.01, + "learning_rate": 1.931010185650465e-05, + "loss": 3.8738, + "step": 1874432 + }, + { + "epoch": 0.01, + "learning_rate": 1.9301715908994125e-05, + "loss": 3.8794, + "step": 1874944 + }, + { + "epoch": 0.01, + "learning_rate": 1.9293329961483605e-05, + "loss": 3.8903, + "step": 1875456 + }, + { + "epoch": 0.01, + "learning_rate": 1.9284944013973085e-05, + "loss": 3.8845, + "step": 1875968 + }, + { + "epoch": 0.01, + "learning_rate": 1.9276574445266298e-05, + "loss": 3.8944, + "step": 1876480 + }, + { + "epoch": 0.01, + "learning_rate": 1.9268188497755778e-05, + "loss": 3.8899, + "step": 1876992 + }, + { + "epoch": 0.02, + "learning_rate": 1.9259802550245257e-05, + "loss": 3.8857, + "step": 1877504 + }, + { + "epoch": 0.02, + "learning_rate": 1.9251416602734737e-05, + "loss": 3.8867, + "step": 1878016 + }, + { + "epoch": 0.02, + "learning_rate": 1.9243030655224217e-05, + "loss": 3.8801, + "step": 1878528 + }, + { + "epoch": 0.02, + "learning_rate": 1.9234644707713697e-05, + "loss": 3.8788, + "step": 1879040 + }, + { + "epoch": 0.02, + "learning_rate": 1.9226258760203177e-05, + "loss": 3.8936, + "step": 1879552 + }, + { + "epoch": 0.02, + "learning_rate": 1.921788919149639e-05, + "loss": 3.8864, + "step": 1880064 + }, + { + "epoch": 0.02, + "learning_rate": 1.920950324398587e-05, + "loss": 3.8942, + "step": 1880576 + }, + { + "epoch": 0.02, + "learning_rate": 1.920111729647535e-05, + "loss": 3.8725, + "step": 1881088 + }, + { + "epoch": 0.02, + "learning_rate": 1.9192731348964826e-05, + "loss": 3.8863, + "step": 1881600 + }, + { + "epoch": 0.02, + "learning_rate": 1.9184345401454306e-05, + "loss": 3.8956, + "step": 1882112 + }, + { + "epoch": 0.02, + "learning_rate": 1.9175959453943786e-05, + "loss": 3.8894, + "step": 1882624 + }, + { + "epoch": 0.02, + "learning_rate": 1.9167573506433266e-05, + "loss": 3.8852, + "step": 1883136 + }, + { + "epoch": 0.02, + "learning_rate": 1.9159187558922746e-05, + "loss": 3.8832, + "step": 1883648 + }, + { + "epoch": 0.02, + "learning_rate": 1.915080161141223e-05, + "loss": 3.8885, + "step": 1884160 + }, + { + "epoch": 0.02, + "learning_rate": 1.914243204270544e-05, + "loss": 3.8864, + "step": 1884672 + }, + { + "epoch": 0.02, + "learning_rate": 1.913404609519492e-05, + "loss": 3.8736, + "step": 1885184 + }, + { + "epoch": 0.02, + "learning_rate": 1.9125676526488128e-05, + "loss": 3.8814, + "step": 1885696 + }, + { + "epoch": 0.02, + "learning_rate": 1.9117290578977608e-05, + "loss": 3.8751, + "step": 1886208 + }, + { + "epoch": 0.02, + "learning_rate": 1.910890463146709e-05, + "loss": 3.8939, + "step": 1886720 + }, + { + "epoch": 0.02, + "learning_rate": 1.91005350627603e-05, + "loss": 3.8775, + "step": 1887232 + }, + { + "epoch": 0.02, + "learning_rate": 1.909214911524978e-05, + "loss": 3.8857, + "step": 1887744 + }, + { + "epoch": 0.02, + "learning_rate": 1.908376316773926e-05, + "loss": 3.8788, + "step": 1888256 + }, + { + "epoch": 0.02, + "learning_rate": 1.907537722022874e-05, + "loss": 3.8959, + "step": 1888768 + }, + { + "epoch": 0.02, + "learning_rate": 1.906699127271822e-05, + "loss": 3.8825, + "step": 1889280 + }, + { + "epoch": 0.02, + "learning_rate": 1.90586053252077e-05, + "loss": 3.8739, + "step": 1889792 + }, + { + "epoch": 0.02, + "learning_rate": 1.9050219377697183e-05, + "loss": 3.8906, + "step": 1890304 + }, + { + "epoch": 0.02, + "learning_rate": 1.904183343018666e-05, + "loss": 3.8974, + "step": 1890816 + }, + { + "epoch": 0.02, + "learning_rate": 1.903344748267614e-05, + "loss": 3.89, + "step": 1891328 + }, + { + "epoch": 0.02, + "learning_rate": 1.9025077913969352e-05, + "loss": 3.8871, + "step": 1891840 + }, + { + "epoch": 0.02, + "learning_rate": 1.9016691966458832e-05, + "loss": 3.8751, + "step": 1892352 + }, + { + "epoch": 0.02, + "learning_rate": 1.900830601894831e-05, + "loss": 3.8881, + "step": 1892864 + }, + { + "epoch": 0.02, + "learning_rate": 1.8999920071437792e-05, + "loss": 3.8904, + "step": 1893376 + }, + { + "epoch": 0.02, + "learning_rate": 1.8991534123927272e-05, + "loss": 3.88, + "step": 1893888 + }, + { + "epoch": 0.02, + "learning_rate": 1.8983148176416752e-05, + "loss": 3.8798, + "step": 1894400 + }, + { + "epoch": 0.02, + "learning_rate": 1.8974762228906232e-05, + "loss": 3.8879, + "step": 1894912 + }, + { + "epoch": 0.02, + "learning_rate": 1.896639266019944e-05, + "loss": 3.891, + "step": 1895424 + }, + { + "epoch": 0.02, + "learning_rate": 1.895800671268892e-05, + "loss": 3.8858, + "step": 1895936 + }, + { + "epoch": 0.02, + "learning_rate": 1.89496207651784e-05, + "loss": 3.8689, + "step": 1896448 + }, + { + "epoch": 0.02, + "learning_rate": 1.8941234817667884e-05, + "loss": 3.8885, + "step": 1896960 + }, + { + "epoch": 0.02, + "learning_rate": 1.8932865248961093e-05, + "loss": 3.8766, + "step": 1897472 + }, + { + "epoch": 0.02, + "learning_rate": 1.8924479301450573e-05, + "loss": 3.8946, + "step": 1897984 + }, + { + "epoch": 0.02, + "learning_rate": 1.8916093353940053e-05, + "loss": 3.89, + "step": 1898496 + }, + { + "epoch": 0.02, + "learning_rate": 1.8907707406429533e-05, + "loss": 3.8925, + "step": 1899008 + }, + { + "epoch": 0.02, + "learning_rate": 1.8899337837722746e-05, + "loss": 3.8746, + "step": 1899520 + }, + { + "epoch": 0.02, + "learning_rate": 1.8890951890212226e-05, + "loss": 3.898, + "step": 1900032 + }, + { + "epoch": 0.02, + "learning_rate": 1.8882565942701706e-05, + "loss": 3.8895, + "step": 1900544 + }, + { + "epoch": 0.02, + "learning_rate": 1.8874179995191186e-05, + "loss": 3.8935, + "step": 1901056 + }, + { + "epoch": 0.02, + "learning_rate": 1.8865794047680662e-05, + "loss": 3.8849, + "step": 1901568 + }, + { + "epoch": 0.02, + "learning_rate": 1.8857408100170142e-05, + "loss": 3.8844, + "step": 1902080 + }, + { + "epoch": 0.02, + "learning_rate": 1.8849038531463355e-05, + "loss": 3.8924, + "step": 1902592 + }, + { + "epoch": 0.02, + "learning_rate": 1.8840652583952838e-05, + "loss": 3.9053, + "step": 1903104 + }, + { + "epoch": 0.02, + "learning_rate": 1.8832266636442314e-05, + "loss": 3.8785, + "step": 1903616 + }, + { + "epoch": 0.02, + "learning_rate": 1.8823880688931794e-05, + "loss": 3.8902, + "step": 1904128 + }, + { + "epoch": 0.02, + "learning_rate": 1.8815494741421274e-05, + "loss": 3.894, + "step": 1904640 + }, + { + "epoch": 0.02, + "learning_rate": 1.8807108793910754e-05, + "loss": 3.8788, + "step": 1905152 + }, + { + "epoch": 0.02, + "learning_rate": 1.8798739225203967e-05, + "loss": 3.8836, + "step": 1905664 + }, + { + "epoch": 0.02, + "learning_rate": 1.8790353277693447e-05, + "loss": 3.8903, + "step": 1906176 + }, + { + "epoch": 0.02, + "learning_rate": 1.8781967330182927e-05, + "loss": 3.8946, + "step": 1906688 + }, + { + "epoch": 0.02, + "learning_rate": 1.8773581382672407e-05, + "loss": 3.8865, + "step": 1907200 + }, + { + "epoch": 0.02, + "learning_rate": 1.8765211813965616e-05, + "loss": 3.8865, + "step": 1907712 + }, + { + "epoch": 0.03, + "eval_loss": 3.987415313720703, + "eval_runtime": 295.0653, + "eval_samples_per_second": 1293.243, + "eval_steps_per_second": 40.415, + "step": 1908000 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 7.862622317221027e+17, + "trial_name": null, + "trial_params": null +}