diff --git "a/checkpoint-2060640/trainer_state.json" "b/checkpoint-2060640/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2060640/trainer_state.json" @@ -0,0 +1,24385 @@ +{ + "best_metric": 3.9931588172912598, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/rel-cl2/lstm/1/checkpoints/checkpoint-2060640", + "epoch": 0.025000606015738065, + "eval_steps": 10, + "global_step": 2060640, + "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": 10.8195, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 7.5561, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 7.0599, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 6.9972, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 6.9475, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 6.9188, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 6.7574, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994131474623009e-05, + "loss": 6.6474, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993292879871958e-05, + "loss": 6.5534, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992454285120906e-05, + "loss": 6.4733, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.991615690369854e-05, + "loss": 6.4162, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990777095618801e-05, + "loss": 6.3506, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989938500867749e-05, + "loss": 6.2788, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 6.2098, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 6.154, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 6.0923, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 6.0503, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 6.0096, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.963, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.9206, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.8923, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.982391148108281e-05, + "loss": 5.8495, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.981552553357229e-05, + "loss": 5.8265, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.980713958606178e-05, + "loss": 5.788, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.979875363855125e-05, + "loss": 5.7724, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.979036769104073e-05, + "loss": 5.7327, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.978198174353021e-05, + "loss": 5.7102, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773612174823426e-05, + "loss": 5.6808, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.97652262273129e-05, + "loss": 5.6655, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.975684027980238e-05, + "loss": 5.6388, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.974845433229186e-05, + "loss": 5.6265, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 5.6087, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 5.5848, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.9723329247367764e-05, + "loss": 5.5705, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.9714943299857244e-05, + "loss": 5.5555, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 5.5334, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 5.5301, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968980183612942e-05, + "loss": 5.4959, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.96814158886189e-05, + "loss": 5.4843, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967302994110837e-05, + "loss": 5.4547, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966467675120532e-05, + "loss": 5.4546, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.96562908036948e-05, + "loss": 5.4389, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964790485618428e-05, + "loss": 5.4366, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963951890867376e-05, + "loss": 5.409, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.963113296116324e-05, + "loss": 5.3987, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 5.3976, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 5.3891, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.9605991497435414e-05, + "loss": 5.3773, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.9597605549924894e-05, + "loss": 5.3578, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.9589219602414374e-05, + "loss": 5.3439, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958083365490385e-05, + "loss": 5.3611, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957244770739333e-05, + "loss": 5.3472, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956406175988281e-05, + "loss": 5.3271, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.955567581237229e-05, + "loss": 5.3072, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.954728986486177e-05, + "loss": 5.3151, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.9538920296154976e-05, + "loss": 5.294, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530534348644456e-05, + "loss": 5.3014, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522148401133936e-05, + "loss": 5.27, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951376245362342e-05, + "loss": 5.2815, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 5.266, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949702331620985e-05, + "loss": 5.2482, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948863736869932e-05, + "loss": 5.235, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.94802514211888e-05, + "loss": 5.2471, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947186547367828e-05, + "loss": 5.2046, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 5.2193, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945509357865724e-05, + "loss": 5.2267, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944670763114672e-05, + "loss": 5.2094, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.94383216836362e-05, + "loss": 5.2021, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 5.1768, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.942156616741889e-05, + "loss": 5.1731, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.941318021990837e-05, + "loss": 5.171, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404794272397856e-05, + "loss": 5.1818, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396408324887336e-05, + "loss": 5.1619, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388038756180545e-05, + "loss": 5.1702, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379652808670025e-05, + "loss": 5.1592, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371283239963234e-05, + "loss": 5.1568, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362897292452714e-05, + "loss": 5.1342, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.9354511344942194e-05, + "loss": 5.1321, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.9346125397431674e-05, + "loss": 5.1243, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.9337739449921154e-05, + "loss": 5.1194, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.9329353502410634e-05, + "loss": 5.1185, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.9320967554900114e-05, + "loss": 5.1013, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.9312581607389594e-05, + "loss": 5.1026, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930421203868281e-05, + "loss": 5.1017, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929582609117229e-05, + "loss": 5.0774, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.928744014366177e-05, + "loss": 5.0845, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927905419615125e-05, + "loss": 5.0835, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927066824864073e-05, + "loss": 5.0844, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.92622823011302e-05, + "loss": 5.0655, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925389635361968e-05, + "loss": 5.062, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924551040610916e-05, + "loss": 5.0485, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923712445859864e-05, + "loss": 5.0456, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922875488989185e-05, + "loss": 5.0451, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.922036894238133e-05, + "loss": 5.0429, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921198299487081e-05, + "loss": 5.0349, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920359704736029e-05, + "loss": 5.037, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919522747865351e-05, + "loss": 5.0276, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918684153114299e-05, + "loss": 5.0119, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.917845558363247e-05, + "loss": 5.0076, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.917006963612195e-05, + "loss": 5.0109, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.916168368861143e-05, + "loss": 5.0064, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.9153314119904636e-05, + "loss": 5.0103, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.9144928172394116e-05, + "loss": 4.9923, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.9136558603687325e-05, + "loss": 4.9852, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.9128172656176805e-05, + "loss": 4.9892, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.9119786708666285e-05, + "loss": 4.9695, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.9111400761155765e-05, + "loss": 4.975, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.9103014813645245e-05, + "loss": 4.9649, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.909462886613473e-05, + "loss": 4.9654, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908624291862421e-05, + "loss": 4.9521, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907785697111369e-05, + "loss": 4.9555, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.906947102360317e-05, + "loss": 4.9455, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906110145489638e-05, + "loss": 4.9481, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905271550738586e-05, + "loss": 4.9428, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904432955987534e-05, + "loss": 4.9335, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903594361236482e-05, + "loss": 4.9442, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.902757404365803e-05, + "loss": 4.9418, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.901918809614751e-05, + "loss": 4.9294, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.901080214863699e-05, + "loss": 4.9164, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.900241620112647e-05, + "loss": 4.9174, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.899403025361595e-05, + "loss": 4.9151, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985660684909166e-05, + "loss": 4.9168, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977274737398646e-05, + "loss": 4.9108, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968888789888125e-05, + "loss": 4.9012, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960502842377605e-05, + "loss": 4.9047, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952116894867085e-05, + "loss": 4.8905, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943730947356565e-05, + "loss": 4.8952, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.893534499984604e-05, + "loss": 4.8811, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.892695905233552e-05, + "loss": 4.8873, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.8918573104825e-05, + "loss": 4.876, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.8910203536118214e-05, + "loss": 4.8856, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890181758860769e-05, + "loss": 4.8846, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889343164109717e-05, + "loss": 4.882, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888504569358665e-05, + "loss": 4.8584, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.8876659746076134e-05, + "loss": 4.8639, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.8868273798565614e-05, + "loss": 4.862, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.8859887851055094e-05, + "loss": 4.8639, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.88515182823483e-05, + "loss": 4.852, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884313233483778e-05, + "loss": 4.8572, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883474638732726e-05, + "loss": 4.8458, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882636043981674e-05, + "loss": 4.861, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881797449230622e-05, + "loss": 4.8289, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.880960492359943e-05, + "loss": 4.8484, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880121897608891e-05, + "loss": 4.8358, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879283302857839e-05, + "loss": 4.8287, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878444708106787e-05, + "loss": 4.8282, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877607751236109e-05, + "loss": 4.813, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876769156485057e-05, + "loss": 4.8183, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875932199614378e-05, + "loss": 4.8269, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875093604863326e-05, + "loss": 4.8123, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.779831886291504, + "eval_runtime": 288.1178, + "eval_samples_per_second": 1324.427, + "eval_steps_per_second": 41.389, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.874255010112274e-05, + "loss": 4.8111, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.873416415361222e-05, + "loss": 4.8048, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.87257782061017e-05, + "loss": 4.8175, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.871739225859118e-05, + "loss": 4.8068, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.8709006311080657e-05, + "loss": 4.8127, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.8700636742373866e-05, + "loss": 4.7888, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.8692250794863346e-05, + "loss": 4.796, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.8683864847352826e-05, + "loss": 4.7801, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.8675478899842306e-05, + "loss": 4.7839, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.8667092952331785e-05, + "loss": 4.788, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.865870700482127e-05, + "loss": 4.7842, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.865033743611448e-05, + "loss": 4.7876, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.864196786740769e-05, + "loss": 4.7664, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.863358191989717e-05, + "loss": 4.7803, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.862519597238665e-05, + "loss": 4.7618, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.861682640367986e-05, + "loss": 4.7667, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.860844045616934e-05, + "loss": 4.7686, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860005450865882e-05, + "loss": 4.7593, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.85916685611483e-05, + "loss": 4.7627, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.858328261363778e-05, + "loss": 4.775, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.857489666612726e-05, + "loss": 4.7505, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.856651071861674e-05, + "loss": 4.7575, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.8558124771106226e-05, + "loss": 4.7503, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.85497388235957e-05, + "loss": 4.7591, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.854135287608518e-05, + "loss": 4.748, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.853296692857466e-05, + "loss": 4.7478, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.852458098106414e-05, + "loss": 4.7309, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.851619503355362e-05, + "loss": 4.7403, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.85078090860431e-05, + "loss": 4.7271, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.849942313853258e-05, + "loss": 4.738, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.849105356982579e-05, + "loss": 4.7333, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.848266762231527e-05, + "loss": 4.7318, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847428167480475e-05, + "loss": 4.7342, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846589572729423e-05, + "loss": 4.725, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.8457526158587444e-05, + "loss": 4.7303, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.8449140211076924e-05, + "loss": 4.7232, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.8440754263566404e-05, + "loss": 4.7129, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.8432368316055884e-05, + "loss": 4.7066, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.8423982368545363e-05, + "loss": 4.6953, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.8415596421034843e-05, + "loss": 4.7051, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840721047352432e-05, + "loss": 4.7039, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.839884090481753e-05, + "loss": 4.7105, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839045495730701e-05, + "loss": 4.6933, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.838206900979649e-05, + "loss": 4.6952, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.837368306228597e-05, + "loss": 4.6984, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.836529711477545e-05, + "loss": 4.6911, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.835691116726493e-05, + "loss": 4.6973, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.834852521975441e-05, + "loss": 4.6833, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834013927224389e-05, + "loss": 4.675, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.833176970353711e-05, + "loss": 4.7029, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.832338375602659e-05, + "loss": 4.6967, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.831499780851606e-05, + "loss": 4.6819, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.830661186100554e-05, + "loss": 4.678, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.829822591349502e-05, + "loss": 4.6853, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.828985634478824e-05, + "loss": 4.6695, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.828147039727771e-05, + "loss": 4.687, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.827308444976719e-05, + "loss": 4.6578, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.826469850225667e-05, + "loss": 4.682, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.825631255474615e-05, + "loss": 4.6739, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.824792660723563e-05, + "loss": 4.6568, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.823954065972511e-05, + "loss": 4.6549, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.82311547122146e-05, + "loss": 4.6691, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.8222801522311535e-05, + "loss": 4.6315, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.8214415574801015e-05, + "loss": 4.654, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.8206029627290495e-05, + "loss": 4.6645, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.8197643679779975e-05, + "loss": 4.656, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.8189274111073184e-05, + "loss": 4.6474, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.8180888163562664e-05, + "loss": 4.6334, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.8172502216052144e-05, + "loss": 4.639, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.8164116268541624e-05, + "loss": 4.6418, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.815574669983483e-05, + "loss": 4.6485, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.814736075232432e-05, + "loss": 4.6363, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.81389748048138e-05, + "loss": 4.6456, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.813058885730328e-05, + "loss": 4.649, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.812220290979276e-05, + "loss": 4.6462, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.811381696228224e-05, + "loss": 4.6283, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.810543101477172e-05, + "loss": 4.6338, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.80970450672612e-05, + "loss": 4.6326, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.808867549855441e-05, + "loss": 4.625, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808028955104389e-05, + "loss": 4.6308, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.807190360353337e-05, + "loss": 4.6205, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.806351765602285e-05, + "loss": 4.6291, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805514808731606e-05, + "loss": 4.6264, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804676213980554e-05, + "loss": 4.6066, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803837619229502e-05, + "loss": 4.6191, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.8029990244784504e-05, + "loss": 4.6188, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.8021604297273984e-05, + "loss": 4.6249, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.801323472856719e-05, + "loss": 4.6154, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.800484878105667e-05, + "loss": 4.6108, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.799646283354615e-05, + "loss": 4.6036, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.798807688603563e-05, + "loss": 4.5998, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.797970731732884e-05, + "loss": 4.604, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.797132136981832e-05, + "loss": 4.6104, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.79629354223078e-05, + "loss": 4.6054, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.795454947479728e-05, + "loss": 4.6106, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.794616352728676e-05, + "loss": 4.6005, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.793779395857997e-05, + "loss": 4.595, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.792940801106946e-05, + "loss": 4.5925, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.792102206355894e-05, + "loss": 4.5972, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.791263611604842e-05, + "loss": 4.6017, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.79042501685379e-05, + "loss": 4.6028, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.7895880599831107e-05, + "loss": 4.5901, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.7887494652320587e-05, + "loss": 4.5824, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.7879108704810067e-05, + "loss": 4.5922, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.7870722757299546e-05, + "loss": 4.577, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.786233680978902e-05, + "loss": 4.584, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.7853967241082236e-05, + "loss": 4.5802, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.7845581293571715e-05, + "loss": 4.5804, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.7837195346061195e-05, + "loss": 4.5706, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.7828809398550675e-05, + "loss": 4.5814, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.7820423451040155e-05, + "loss": 4.5675, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.781205388233337e-05, + "loss": 4.5722, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.7803667934822844e-05, + "loss": 4.5762, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.7795281987312324e-05, + "loss": 4.5642, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.7786896039801804e-05, + "loss": 4.5851, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.777852647109502e-05, + "loss": 4.5813, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.777014052358449e-05, + "loss": 4.5737, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.776175457607397e-05, + "loss": 4.5632, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.775336862856345e-05, + "loss": 4.5608, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.774499905985666e-05, + "loss": 4.5673, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.773661311234615e-05, + "loss": 4.5617, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.772822716483563e-05, + "loss": 4.5727, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.771984121732511e-05, + "loss": 4.5525, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.771145526981459e-05, + "loss": 4.5608, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.770306932230407e-05, + "loss": 4.5584, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.769468337479355e-05, + "loss": 4.5635, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.768629742728303e-05, + "loss": 4.546, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.767792785857624e-05, + "loss": 4.5561, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766954191106572e-05, + "loss": 4.5529, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.76611559635552e-05, + "loss": 4.555, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.765277001604468e-05, + "loss": 4.5589, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764438406853416e-05, + "loss": 4.5623, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.763599812102364e-05, + "loss": 4.5398, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762761217351312e-05, + "loss": 4.5484, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.76192262260026e-05, + "loss": 4.5526, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.7610856657295813e-05, + "loss": 4.5491, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.7602470709785293e-05, + "loss": 4.5443, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.75941011410785e-05, + "loss": 4.5479, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.758571519356798e-05, + "loss": 4.5424, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.757732924605746e-05, + "loss": 4.5595, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.756894329854694e-05, + "loss": 4.5306, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.756055735103642e-05, + "loss": 4.5488, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.75521714035259e-05, + "loss": 4.5361, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.7543785456015375e-05, + "loss": 4.5327, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.753541588730859e-05, + "loss": 4.5343, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.752702993979807e-05, + "loss": 4.5265, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.751864399228755e-05, + "loss": 4.5283, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.751025804477703e-05, + "loss": 4.534, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.750187209726651e-05, + "loss": 4.5274, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.494524002075195, + "eval_runtime": 288.449, + "eval_samples_per_second": 1322.906, + "eval_steps_per_second": 41.342, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.749348614975599e-05, + "loss": 4.5262, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748510020224547e-05, + "loss": 4.5186, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.747671425473495e-05, + "loss": 4.5382, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.746832830722443e-05, + "loss": 4.5264, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.745994235971391e-05, + "loss": 4.5361, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.745155641220339e-05, + "loss": 4.5141, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.744317046469287e-05, + "loss": 4.5224, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.743478451718235e-05, + "loss": 4.5078, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.742639856967183e-05, + "loss": 4.5174, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.741801262216131e-05, + "loss": 4.5193, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740962667465079e-05, + "loss": 4.5152, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.7401240727140264e-05, + "loss": 4.5262, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739287115843348e-05, + "loss": 4.5013, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.7384485210922966e-05, + "loss": 4.5182, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.7376099263412446e-05, + "loss": 4.5033, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736771331590192e-05, + "loss": 4.5029, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.73593273683914e-05, + "loss": 4.5036, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.735094142088088e-05, + "loss": 4.5115, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734255547337036e-05, + "loss": 4.5026, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733416952585984e-05, + "loss": 4.5215, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732578357834932e-05, + "loss": 4.5029, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.73173976308388e-05, + "loss": 4.5042, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.730901168332828e-05, + "loss": 4.503, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730062573581776e-05, + "loss": 4.5126, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.729225616711097e-05, + "loss": 4.4995, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.728387021960045e-05, + "loss": 4.503, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727548427208993e-05, + "loss": 4.4894, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.7267098324579415e-05, + "loss": 4.4941, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.725874513467635e-05, + "loss": 4.4833, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.725035918716583e-05, + "loss": 4.4986, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.724197323965531e-05, + "loss": 4.4974, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723358729214479e-05, + "loss": 4.4935, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.722520134463427e-05, + "loss": 4.5015, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.721681539712375e-05, + "loss": 4.4897, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720844582841696e-05, + "loss": 4.4901, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.720005988090644e-05, + "loss": 4.4915, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.719169031219965e-05, + "loss": 4.4862, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.718330436468914e-05, + "loss": 4.4764, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.717491841717862e-05, + "loss": 4.4676, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.71665324696681e-05, + "loss": 4.4776, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.715814652215758e-05, + "loss": 4.4798, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.714976057464706e-05, + "loss": 4.4838, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.714137462713654e-05, + "loss": 4.4753, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.713298867962602e-05, + "loss": 4.4687, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.71246027321155e-05, + "loss": 4.4825, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.711623316340871e-05, + "loss": 4.473, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.710784721589819e-05, + "loss": 4.4749, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.7099461268387667e-05, + "loss": 4.4669, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.7091075320877147e-05, + "loss": 4.4554, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.7082689373366627e-05, + "loss": 4.4871, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.7074319804659836e-05, + "loss": 4.4797, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.706593385714932e-05, + "loss": 4.4676, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.70575479096388e-05, + "loss": 4.4653, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704916196212828e-05, + "loss": 4.4741, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.7040776014617755e-05, + "loss": 4.4556, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703240644591097e-05, + "loss": 4.4764, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.702402049840045e-05, + "loss": 4.4508, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.7015634550889924e-05, + "loss": 4.469, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.7007248603379404e-05, + "loss": 4.4738, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.699887903467262e-05, + "loss": 4.4546, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.69904930871621e-05, + "loss": 4.4467, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.6982107139651573e-05, + "loss": 4.465, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.697372119214106e-05, + "loss": 4.4352, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696533524463054e-05, + "loss": 4.4534, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.695694929712002e-05, + "loss": 4.4594, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694857972841323e-05, + "loss": 4.4581, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694019378090271e-05, + "loss": 4.4516, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693180783339219e-05, + "loss": 4.4364, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692342188588167e-05, + "loss": 4.4406, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.691503593837115e-05, + "loss": 4.4428, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690666636966436e-05, + "loss": 4.4552, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.689828042215384e-05, + "loss": 4.4428, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.688989447464332e-05, + "loss": 4.4518, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.68815085271328e-05, + "loss": 4.458, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.687312257962228e-05, + "loss": 4.455, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.686473663211176e-05, + "loss": 4.4371, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.6856367063404974e-05, + "loss": 4.4433, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.6847981115894454e-05, + "loss": 4.4492, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.6839595168383934e-05, + "loss": 4.4361, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.683122559967714e-05, + "loss": 4.4411, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.682283965216662e-05, + "loss": 4.4373, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.68144537046561e-05, + "loss": 4.4382, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.680606775714558e-05, + "loss": 4.4438, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679769818843879e-05, + "loss": 4.4227, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678931224092827e-05, + "loss": 4.4412, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678092629341775e-05, + "loss": 4.4312, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.677254034590723e-05, + "loss": 4.4441, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.676415439839671e-05, + "loss": 4.4348, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.675576845088619e-05, + "loss": 4.4311, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674738250337568e-05, + "loss": 4.4247, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.673899655586516e-05, + "loss": 4.4232, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.673061060835464e-05, + "loss": 4.4229, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.672222466084412e-05, + "loss": 4.4311, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.671383871333359e-05, + "loss": 4.4378, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.670545276582307e-05, + "loss": 4.4318, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.669708319711629e-05, + "loss": 4.4237, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.6688713628409496e-05, + "loss": 4.4198, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.6680327680898976e-05, + "loss": 4.4215, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.6671941733388456e-05, + "loss": 4.4234, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.6663555785877936e-05, + "loss": 4.4318, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.6655169838367416e-05, + "loss": 4.4312, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.6646783890856896e-05, + "loss": 4.4199, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663841432215011e-05, + "loss": 4.4116, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.663002837463959e-05, + "loss": 4.4286, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.6621642427129065e-05, + "loss": 4.4094, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.6613256479618545e-05, + "loss": 4.4189, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.6604870532108025e-05, + "loss": 4.411, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.6596500963401234e-05, + "loss": 4.4159, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.6588115015890714e-05, + "loss": 4.4065, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.6579729068380194e-05, + "loss": 4.417, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.6571343120869674e-05, + "loss": 4.4063, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.6562957173359154e-05, + "loss": 4.4024, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.6554571225848634e-05, + "loss": 4.4189, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.6546185278338114e-05, + "loss": 4.3986, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.65377993308276e-05, + "loss": 4.4243, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.652941338331708e-05, + "loss": 4.4206, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.652104381461029e-05, + "loss": 4.4142, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.651265786709977e-05, + "loss": 4.4049, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650427191958925e-05, + "loss": 4.403, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.649588597207873e-05, + "loss": 4.4038, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648751640337194e-05, + "loss": 4.4043, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.647914683466515e-05, + "loss": 4.4138, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.647076088715463e-05, + "loss": 4.3966, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.646237493964411e-05, + "loss": 4.4073, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.645398899213359e-05, + "loss": 4.4052, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.644560304462307e-05, + "loss": 4.4055, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.6437217097112554e-05, + "loss": 4.3951, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.6428831149602034e-05, + "loss": 4.4013, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.6420445202091514e-05, + "loss": 4.401, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.6412059254580994e-05, + "loss": 4.403, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.6403673307070474e-05, + "loss": 4.4031, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.639528735955995e-05, + "loss": 4.4114, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.638690141204943e-05, + "loss": 4.3866, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.637853184334264e-05, + "loss": 4.3996, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.637014589583212e-05, + "loss": 4.4052, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.6361759948321596e-05, + "loss": 4.3959, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.6353374000811076e-05, + "loss": 4.3934, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.634500443210429e-05, + "loss": 4.4041, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.633663486339751e-05, + "loss": 4.3935, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.632824891588699e-05, + "loss": 4.4104, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.63198793471802e-05, + "loss": 4.3835, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.631149339966968e-05, + "loss": 4.397, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.630310745215916e-05, + "loss": 4.3932, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629472150464864e-05, + "loss": 4.3882, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.628633555713812e-05, + "loss": 4.3865, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.6277949609627597e-05, + "loss": 4.3833, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626956366211707e-05, + "loss": 4.3806, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626117771460655e-05, + "loss": 4.3906, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625279176709603e-05, + "loss": 4.3857, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 4.3582868576049805, + "eval_runtime": 293.5432, + "eval_samples_per_second": 1299.948, + "eval_steps_per_second": 40.624, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.6244422198389246e-05, + "loss": 4.3887, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.6236036250878726e-05, + "loss": 4.3754, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.6227650303368205e-05, + "loss": 4.3947, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.6219264355857685e-05, + "loss": 4.3826, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.6210878408347165e-05, + "loss": 4.3988, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.6202492460836645e-05, + "loss": 4.3769, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.6194106513326125e-05, + "loss": 4.3828, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.6185720565815605e-05, + "loss": 4.3684, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.6177350997108814e-05, + "loss": 4.3816, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.6168965049598294e-05, + "loss": 4.382, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.6160579102087774e-05, + "loss": 4.3795, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.6152193154577254e-05, + "loss": 4.3837, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.614382358587046e-05, + "loss": 4.3677, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.613545401716368e-05, + "loss": 4.3831, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.612706806965316e-05, + "loss": 4.3696, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.611868212214264e-05, + "loss": 4.3639, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.611029617463212e-05, + "loss": 4.3692, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.61019102271216e-05, + "loss": 4.3744, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.609354065841481e-05, + "loss": 4.3704, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.608515471090429e-05, + "loss": 4.3866, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.607676876339377e-05, + "loss": 4.3714, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.606838281588325e-05, + "loss": 4.3769, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.605999686837273e-05, + "loss": 4.3679, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.605161092086221e-05, + "loss": 4.3785, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.604322497335169e-05, + "loss": 4.368, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.603483902584117e-05, + "loss": 4.3728, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.602645307833065e-05, + "loss": 4.3629, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.601806713082013e-05, + "loss": 4.3584, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.6009697562113344e-05, + "loss": 4.3592, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.6001311614602824e-05, + "loss": 4.3679, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.5992925667092303e-05, + "loss": 4.37, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.5984539719581783e-05, + "loss": 4.3664, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.5976153772071257e-05, + "loss": 4.3754, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.59678005821682e-05, + "loss": 4.3645, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.595941463465768e-05, + "loss": 4.36, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.595102868714716e-05, + "loss": 4.3633, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.594264273963664e-05, + "loss": 4.3668, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.593425679212612e-05, + "loss": 4.3479, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.59258708446156e-05, + "loss": 4.3428, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.591748489710508e-05, + "loss": 4.3506, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.590909894959456e-05, + "loss": 4.3588, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.590071300208404e-05, + "loss": 4.3584, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.589232705457352e-05, + "loss": 4.3526, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.5883941107063e-05, + "loss": 4.3427, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.587557153835621e-05, + "loss": 4.3586, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.586718559084569e-05, + "loss": 4.3524, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.585879964333517e-05, + "loss": 4.3523, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.585041369582465e-05, + "loss": 4.3456, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.584202774831413e-05, + "loss": 4.3306, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.583364180080361e-05, + "loss": 4.3749, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.582527223209682e-05, + "loss": 4.3568, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.58168862845863e-05, + "loss": 4.3493, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.5808500337075786e-05, + "loss": 4.3493, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.5800114389565266e-05, + "loss": 4.3509, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.5791728442054746e-05, + "loss": 4.3403, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.5783358873347955e-05, + "loss": 4.3533, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.5774972925837435e-05, + "loss": 4.3367, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.5766586978326915e-05, + "loss": 4.3481, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.5758201030816395e-05, + "loss": 4.3593, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.5749815083305875e-05, + "loss": 4.338, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.5741429135795355e-05, + "loss": 4.3261, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.5733043188284835e-05, + "loss": 4.3532, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.5724657240774315e-05, + "loss": 4.3204, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.5716287672067524e-05, + "loss": 4.3331, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.570791810336074e-05, + "loss": 4.346, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.569953215585022e-05, + "loss": 4.3441, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.56911462083397e-05, + "loss": 4.3354, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.568276026082918e-05, + "loss": 4.3288, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.567437431331866e-05, + "loss": 4.3209, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.566598836580814e-05, + "loss": 4.3281, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.565760241829762e-05, + "loss": 4.3445, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.564921647078709e-05, + "loss": 4.3284, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.564084690208031e-05, + "loss": 4.3444, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.563246095456979e-05, + "loss": 4.3405, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.562407500705927e-05, + "loss": 4.3471, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.561568905954874e-05, + "loss": 4.3282, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.560731949084196e-05, + "loss": 4.3286, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.559893354333144e-05, + "loss": 4.3388, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.559054759582092e-05, + "loss": 4.324, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.558217802711413e-05, + "loss": 4.3378, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.557379207960361e-05, + "loss": 4.3254, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.556540613209309e-05, + "loss": 4.3274, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.5557020184582566e-05, + "loss": 4.3353, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.5548634237072046e-05, + "loss": 4.3179, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.5540248289561526e-05, + "loss": 4.3285, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.5531862342051006e-05, + "loss": 4.3276, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.5523476394540486e-05, + "loss": 4.3344, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.5515090447029966e-05, + "loss": 4.3233, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.5506720878323175e-05, + "loss": 4.327, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.5498334930812655e-05, + "loss": 4.3156, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.548994898330214e-05, + "loss": 4.3153, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.548156303579162e-05, + "loss": 4.3196, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.54731770882811e-05, + "loss": 4.324, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.546479114077058e-05, + "loss": 4.3319, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.545642157206379e-05, + "loss": 4.3303, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.544803562455327e-05, + "loss": 4.3201, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.543964967704275e-05, + "loss": 4.3138, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.543126372953223e-05, + "loss": 4.3171, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.542289416082544e-05, + "loss": 4.3218, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.541450821331492e-05, + "loss": 4.3253, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.54061222658044e-05, + "loss": 4.3271, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.539773631829388e-05, + "loss": 4.317, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.538935037078336e-05, + "loss": 4.3099, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.538096442327284e-05, + "loss": 4.328, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.5372578475762326e-05, + "loss": 4.3029, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.5364192528251806e-05, + "loss": 4.3195, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.5355822959545015e-05, + "loss": 4.3065, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.5347437012034495e-05, + "loss": 4.3141, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.5339051064523975e-05, + "loss": 4.3064, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.5330665117013455e-05, + "loss": 4.314, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.532227916950293e-05, + "loss": 4.3067, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.5313909600796144e-05, + "loss": 4.302, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.5305523653285624e-05, + "loss": 4.3139, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.5297137705775104e-05, + "loss": 4.3027, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.528875175826458e-05, + "loss": 4.3223, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.5280365810754064e-05, + "loss": 4.3231, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.527199624204728e-05, + "loss": 4.3175, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.526361029453675e-05, + "loss": 4.3067, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.525522434702623e-05, + "loss": 4.3067, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.524683839951571e-05, + "loss": 4.3046, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.523845245200519e-05, + "loss": 4.3072, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.523006650449467e-05, + "loss": 4.3175, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.522168055698415e-05, + "loss": 4.2948, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.521329460947363e-05, + "loss": 4.3092, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.520492504076684e-05, + "loss": 4.3055, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.519655547206005e-05, + "loss": 4.312, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.518816952454953e-05, + "loss": 4.2991, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.517978357703902e-05, + "loss": 4.3067, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.517141400833223e-05, + "loss": 4.2991, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.516302806082171e-05, + "loss": 4.3151, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.5154642113311187e-05, + "loss": 4.3065, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.5146256165800667e-05, + "loss": 4.3162, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.5137870218290147e-05, + "loss": 4.2916, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.5129484270779626e-05, + "loss": 4.3078, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.5121098323269106e-05, + "loss": 4.3099, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.5112712375758586e-05, + "loss": 4.296, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.5104326428248066e-05, + "loss": 4.3028, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.5095940480737546e-05, + "loss": 4.3106, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.5087570912030755e-05, + "loss": 4.3006, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.5079184964520235e-05, + "loss": 4.3186, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.5070799017009715e-05, + "loss": 4.2898, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.5062413069499195e-05, + "loss": 4.3069, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.505404350079241e-05, + "loss": 4.2947, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.504565755328189e-05, + "loss": 4.2977, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.503727160577137e-05, + "loss": 4.2981, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.502888565826085e-05, + "loss": 4.2905, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.502049971075033e-05, + "loss": 4.288, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.501211376323981e-05, + "loss": 4.2969, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.500372781572929e-05, + "loss": 4.2964, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 4.2750773429870605, + "eval_runtime": 293.1439, + "eval_samples_per_second": 1301.719, + "eval_steps_per_second": 40.68, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.4995341868218764e-05, + "loss": 4.2958, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.4986955920708244e-05, + "loss": 4.2852, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.4978569973197724e-05, + "loss": 4.3043, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.4970184025687204e-05, + "loss": 4.293, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.4961798078176684e-05, + "loss": 4.3037, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.4953412130666164e-05, + "loss": 4.2926, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.494502618315565e-05, + "loss": 4.2921, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.493664023564513e-05, + "loss": 4.2802, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.492825428813461e-05, + "loss": 4.2896, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.491986834062409e-05, + "loss": 4.2923, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.491148239311357e-05, + "loss": 4.2916, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.490309644560305e-05, + "loss": 4.2929, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.489472687689626e-05, + "loss": 4.2806, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.488634092938574e-05, + "loss": 4.2963, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.487795498187522e-05, + "loss": 4.2803, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.486958541316843e-05, + "loss": 4.2775, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486119946565791e-05, + "loss": 4.281, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.485281351814739e-05, + "loss": 4.2898, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.484442757063687e-05, + "loss": 4.2827, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.483604162312635e-05, + "loss": 4.2987, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.482765567561583e-05, + "loss": 4.2862, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481926972810531e-05, + "loss": 4.2932, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481088378059479e-05, + "loss": 4.2809, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480249783308427e-05, + "loss": 4.2902, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479411188557375e-05, + "loss": 4.2834, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478572593806323e-05, + "loss": 4.288, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477733999055271e-05, + "loss": 4.2782, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476897042184592e-05, + "loss": 4.2767, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.47605844743354e-05, + "loss": 4.2726, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475219852682488e-05, + "loss": 4.2809, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474381257931436e-05, + "loss": 4.2861, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473542663180384e-05, + "loss": 4.2828, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472704068429332e-05, + "loss": 4.2886, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.471867111558653e-05, + "loss": 4.2777, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.471028516807601e-05, + "loss": 4.2777, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.470189922056549e-05, + "loss": 4.2856, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469351327305497e-05, + "loss": 4.2844, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468512732554445e-05, + "loss": 4.2607, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.467674137803393e-05, + "loss": 4.2671, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.466837180932714e-05, + "loss": 4.265, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.465998586181662e-05, + "loss": 4.2714, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.46515999143061e-05, + "loss": 4.2813, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464321396679558e-05, + "loss": 4.2696, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463484439808879e-05, + "loss": 4.2651, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.462645845057827e-05, + "loss": 4.2755, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461807250306775e-05, + "loss": 4.2689, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.460968655555724e-05, + "loss": 4.2737, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.460130060804672e-05, + "loss": 4.268, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.4592931039339926e-05, + "loss": 4.2446, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.4584545091829406e-05, + "loss": 4.2936, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.4576159144318886e-05, + "loss": 4.2772, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.4567773196808366e-05, + "loss": 4.2751, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.455938724929784e-05, + "loss": 4.2675, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.455100130178732e-05, + "loss": 4.2674, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.4542631733080535e-05, + "loss": 4.2608, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.4534262164373744e-05, + "loss": 4.2699, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.4525876216863224e-05, + "loss": 4.2617, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.4517490269352704e-05, + "loss": 4.2662, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.450910432184219e-05, + "loss": 4.2816, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.4500718374331664e-05, + "loss": 4.2594, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.4492332426821144e-05, + "loss": 4.2508, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.4483946479310624e-05, + "loss": 4.2747, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.4475560531800104e-05, + "loss": 4.2426, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446719096309331e-05, + "loss": 4.2581, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445880501558279e-05, + "loss": 4.2659, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445041906807227e-05, + "loss": 4.2655, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444203312056175e-05, + "loss": 4.2577, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.443366355185496e-05, + "loss": 4.2551, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.442527760434444e-05, + "loss": 4.2392, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441689165683393e-05, + "loss": 4.2539, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.440850570932341e-05, + "loss": 4.2646, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440011976181289e-05, + "loss": 4.255, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.439173381430237e-05, + "loss": 4.2615, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438334786679185e-05, + "loss": 4.2676, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437497829808506e-05, + "loss": 4.2746, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.436660872937827e-05, + "loss": 4.2516, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.4358222781867747e-05, + "loss": 4.2493, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.4349836834357227e-05, + "loss": 4.2652, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.4341450886846707e-05, + "loss": 4.2448, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.4333064939336186e-05, + "loss": 4.2649, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.4324678991825666e-05, + "loss": 4.25, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.4316293044315146e-05, + "loss": 4.2513, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.4307907096804626e-05, + "loss": 4.2634, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.429952114929411e-05, + "loss": 4.2422, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.429113520178359e-05, + "loss": 4.2523, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.428274925427307e-05, + "loss": 4.2503, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.427436330676255e-05, + "loss": 4.2621, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.426599373805576e-05, + "loss": 4.2458, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.425760779054524e-05, + "loss": 4.2544, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.424922184303472e-05, + "loss": 4.2432, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.42408358955242e-05, + "loss": 4.2444, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.423248270562114e-05, + "loss": 4.2422, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422409675811062e-05, + "loss": 4.2521, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.42157108106001e-05, + "loss": 4.2584, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.420732486308958e-05, + "loss": 4.2536, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.419893891557907e-05, + "loss": 4.2526, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.419055296806855e-05, + "loss": 4.2402, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.4182183399361756e-05, + "loss": 4.2437, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.4173797451851236e-05, + "loss": 4.2472, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.4165411504340716e-05, + "loss": 4.2536, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.4157025556830196e-05, + "loss": 4.254, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.4148672366927134e-05, + "loss": 4.2441, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.4140286419416614e-05, + "loss": 4.2397, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.4131900471906094e-05, + "loss": 4.2568, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.4123514524395574e-05, + "loss": 4.2326, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.4115128576885054e-05, + "loss": 4.247, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.4106742629374534e-05, + "loss": 4.238, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409835668186402e-05, + "loss": 4.2452, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.40899707343535e-05, + "loss": 4.2346, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.4081584786842974e-05, + "loss": 4.2447, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.4073198839332453e-05, + "loss": 4.2333, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.4064812891821933e-05, + "loss": 4.2345, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.4056426944311413e-05, + "loss": 4.243, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404804099680089e-05, + "loss": 4.2353, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.403965504929037e-05, + "loss": 4.2501, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.403126910177985e-05, + "loss": 4.254, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402289953307306e-05, + "loss": 4.2439, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.401451358556254e-05, + "loss": 4.2417, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400612763805202e-05, + "loss": 4.2321, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.39977416905415e-05, + "loss": 4.2376, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398935574303098e-05, + "loss": 4.2368, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.39809861743242e-05, + "loss": 4.2531, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.397260022681368e-05, + "loss": 4.2227, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396421427930316e-05, + "loss": 4.2415, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.395582833179264e-05, + "loss": 4.2369, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394745876308585e-05, + "loss": 4.2417, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.393907281557533e-05, + "loss": 4.2327, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.3930703246868536e-05, + "loss": 4.2389, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.3922317299358016e-05, + "loss": 4.2284, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.3913931351847496e-05, + "loss": 4.2459, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.3905545404336976e-05, + "loss": 4.2412, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.3897159456826456e-05, + "loss": 4.2438, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.3888773509315936e-05, + "loss": 4.2273, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.388038756180542e-05, + "loss": 4.2393, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.38720016142949e-05, + "loss": 4.2423, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.386361566678438e-05, + "loss": 4.2302, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.385522971927386e-05, + "loss": 4.2351, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.3846843771763336e-05, + "loss": 4.2437, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.3838457824252816e-05, + "loss": 4.231, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.3830071876742296e-05, + "loss": 4.2556, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.3821685929231775e-05, + "loss": 4.2251, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.3813299981721255e-05, + "loss": 4.2382, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.3804914034210735e-05, + "loss": 4.2279, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.3796544465503944e-05, + "loss": 4.2325, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378817489679716e-05, + "loss": 4.2333, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.377978894928664e-05, + "loss": 4.2245, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.3771419380579856e-05, + "loss": 4.2265, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.3763033433069336e-05, + "loss": 4.2206, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.375464748555881e-05, + "loss": 4.2348, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 4.217353343963623, + "eval_runtime": 294.6691, + "eval_samples_per_second": 1294.981, + "eval_steps_per_second": 40.469, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.374626153804829e-05, + "loss": 4.2351, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.373787559053777e-05, + "loss": 4.2208, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.372948964302725e-05, + "loss": 4.2363, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.372110369551673e-05, + "loss": 4.2326, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.371271774800621e-05, + "loss": 4.2341, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.370433180049569e-05, + "loss": 4.226, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.369594585298517e-05, + "loss": 4.227, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.368755990547465e-05, + "loss": 4.2156, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.367917395796413e-05, + "loss": 4.2251, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.3670804389257345e-05, + "loss": 4.228, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.3662418441746825e-05, + "loss": 4.2298, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.3654032494236305e-05, + "loss": 4.2242, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.3645662925529514e-05, + "loss": 4.2222, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.3637276978018994e-05, + "loss": 4.2263, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.3628891030508474e-05, + "loss": 4.2174, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.3620505082997954e-05, + "loss": 4.2101, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.3612119135487434e-05, + "loss": 4.2188, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.360374956678064e-05, + "loss": 4.2245, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.359536361927012e-05, + "loss": 4.2206, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.35869776717596e-05, + "loss": 4.2341, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.357859172424908e-05, + "loss": 4.2259, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.357020577673856e-05, + "loss": 4.2302, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.356181982922804e-05, + "loss": 4.218, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.355343388171752e-05, + "loss": 4.2259, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.3545047934207e-05, + "loss": 4.2199, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.353667836550022e-05, + "loss": 4.227, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.352830879679343e-05, + "loss": 4.2175, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.351992284928291e-05, + "loss": 4.2122, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.351153690177239e-05, + "loss": 4.211, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.350315095426187e-05, + "loss": 4.222, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.349476500675134e-05, + "loss": 4.2209, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.3486395438044556e-05, + "loss": 4.2222, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.3478009490534036e-05, + "loss": 4.225, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.3469623543023516e-05, + "loss": 4.2197, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.3461237595512996e-05, + "loss": 4.2161, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.3452851648002476e-05, + "loss": 4.2242, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.3444465700491956e-05, + "loss": 4.2207, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.3436079752981436e-05, + "loss": 4.2044, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.3427710184274645e-05, + "loss": 4.2058, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.3419324236764125e-05, + "loss": 4.2041, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.3410938289253605e-05, + "loss": 4.2059, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.3402552341743085e-05, + "loss": 4.2213, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.3394182773036294e-05, + "loss": 4.2101, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.3385796825525774e-05, + "loss": 4.2036, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.3377410878015254e-05, + "loss": 4.2159, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.3369024930504734e-05, + "loss": 4.208, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.3360638982994214e-05, + "loss": 4.2149, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.33522530354837e-05, + "loss": 4.2049, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.334386708797318e-05, + "loss": 4.1849, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.333548114046266e-05, + "loss": 4.2359, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.332711157175587e-05, + "loss": 4.2134, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.331874200304908e-05, + "loss": 4.2177, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.331035605553856e-05, + "loss": 4.2031, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.330197010802804e-05, + "loss": 4.2129, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.329358416051752e-05, + "loss": 4.2021, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.3285198213007e-05, + "loss": 4.2069, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.327681226549648e-05, + "loss": 4.2063, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.326842631798596e-05, + "loss": 4.2058, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.326005674927917e-05, + "loss": 4.2249, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.3251670801768654e-05, + "loss": 4.1977, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.3243301233061863e-05, + "loss": 4.1894, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.323491528555134e-05, + "loss": 4.2168, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.322652933804082e-05, + "loss": 4.1854, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.32181433905303e-05, + "loss": 4.1956, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.320975744301978e-05, + "loss": 4.2117, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.320137149550926e-05, + "loss": 4.2112, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.319298554799874e-05, + "loss": 4.195, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.318459960048822e-05, + "loss": 4.2029, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.317623003178143e-05, + "loss": 4.1802, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.316784408427091e-05, + "loss": 4.1993, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.315945813676039e-05, + "loss": 4.2054, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.315107218924987e-05, + "loss": 4.1953, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.314270262054309e-05, + "loss": 4.2062, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.313431667303257e-05, + "loss": 4.2077, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.312593072552205e-05, + "loss": 4.2196, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.311754477801153e-05, + "loss": 4.1921, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.3109158830501e-05, + "loss": 4.197, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.310077288299048e-05, + "loss": 4.2104, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.309238693547996e-05, + "loss": 4.1893, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.308400098796944e-05, + "loss": 4.2046, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.307561504045892e-05, + "loss": 4.1967, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.30672290929484e-05, + "loss": 4.1952, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.305885952424161e-05, + "loss": 4.2095, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.305047357673109e-05, + "loss": 4.1889, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.3042087629220577e-05, + "loss": 4.1922, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.3033701681710057e-05, + "loss": 4.2001, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.3025315734199536e-05, + "loss": 4.2043, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.3016929786689016e-05, + "loss": 4.191, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.3008543839178496e-05, + "loss": 4.2, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.3000157891667976e-05, + "loss": 4.1827, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.2991788322961185e-05, + "loss": 4.1934, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.2983418754254395e-05, + "loss": 4.1892, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.2975032806743874e-05, + "loss": 4.1968, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.2966646859233354e-05, + "loss": 4.209, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.2958260911722834e-05, + "loss": 4.1961, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.2949874964212314e-05, + "loss": 4.1971, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.294150539550553e-05, + "loss": 4.187, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.293311944799501e-05, + "loss": 4.19, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.292473350048449e-05, + "loss": 4.1928, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.291634755297397e-05, + "loss": 4.2012, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.290796160546345e-05, + "loss": 4.1966, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.289957565795293e-05, + "loss": 4.1976, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.289118971044241e-05, + "loss": 4.1873, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.288280376293189e-05, + "loss": 4.2008, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.28744341942251e-05, + "loss": 4.1791, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.286604824671458e-05, + "loss": 4.1943, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.285767867800779e-05, + "loss": 4.1794, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.284929273049727e-05, + "loss": 4.1966, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.284090678298675e-05, + "loss": 4.1835, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.283252083547623e-05, + "loss": 4.1888, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.2824151266769444e-05, + "loss": 4.1834, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.2815765319258924e-05, + "loss": 4.1824, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.2807379371748404e-05, + "loss": 4.1866, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.2798993424237884e-05, + "loss": 4.1842, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.2790607476727364e-05, + "loss": 4.1954, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.278222152921684e-05, + "loss": 4.2001, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.277383558170632e-05, + "loss": 4.1935, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.27654496341958e-05, + "loss": 4.1945, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.275706368668528e-05, + "loss": 4.1763, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.274867773917476e-05, + "loss": 4.1841, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.2740291791664237e-05, + "loss": 4.1874, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.2731905844153717e-05, + "loss": 4.1977, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.272353627544693e-05, + "loss": 4.1705, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.271515032793641e-05, + "loss": 4.1887, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.270676438042589e-05, + "loss": 4.1893, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.26983948117191e-05, + "loss": 4.1849, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.269000886420858e-05, + "loss": 4.1823, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.268162291669806e-05, + "loss": 4.1897, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.267323696918754e-05, + "loss": 4.1784, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.266485102167702e-05, + "loss": 4.1931, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.26564650741665e-05, + "loss": 4.1902, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.264809550545971e-05, + "loss": 4.1922, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.263970955794919e-05, + "loss": 4.1765, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.263132361043867e-05, + "loss": 4.1892, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.262293766292815e-05, + "loss": 4.1914, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.261455171541763e-05, + "loss": 4.1797, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.260616576790712e-05, + "loss": 4.1846, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.2597796199200326e-05, + "loss": 4.1905, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.2589426630493535e-05, + "loss": 4.1858, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.2581040682983015e-05, + "loss": 4.2009, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.2572671114276224e-05, + "loss": 4.178, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.2564285166765704e-05, + "loss": 4.1862, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.2555899219255184e-05, + "loss": 4.1804, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.2547513271744664e-05, + "loss": 4.1835, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.2539127324234144e-05, + "loss": 4.1771, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.2530741376723624e-05, + "loss": 4.1728, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.2522355429213104e-05, + "loss": 4.1814, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.2513969481702584e-05, + "loss": 4.1694, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.250558353419207e-05, + "loss": 4.1869, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 4.17576265335083, + "eval_runtime": 291.3672, + "eval_samples_per_second": 1309.657, + "eval_steps_per_second": 40.928, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.249719758668155e-05, + "loss": 4.1877, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.2488811639171024e-05, + "loss": 4.1711, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.2480425691660504e-05, + "loss": 4.1857, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.2472039744149984e-05, + "loss": 4.18, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.2463653796639464e-05, + "loss": 4.1882, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.2455267849128943e-05, + "loss": 4.1773, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.2446881901618423e-05, + "loss": 4.1795, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.24384959541079e-05, + "loss": 4.1674, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.243011000659738e-05, + "loss": 4.1771, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.242172405908686e-05, + "loss": 4.1802, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.241333811157634e-05, + "loss": 4.1802, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.240495216406582e-05, + "loss": 4.1757, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.239658259535903e-05, + "loss": 4.1744, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.238819664784852e-05, + "loss": 4.1768, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.2379810700338e-05, + "loss": 4.1746, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.237142475282748e-05, + "loss": 4.1608, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.236303880531696e-05, + "loss": 4.1717, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.235465285780644e-05, + "loss": 4.1765, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.234626691029591e-05, + "loss": 4.1743, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233788096278539e-05, + "loss": 4.1847, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.232949501527487e-05, + "loss": 4.1816, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232110906776435e-05, + "loss": 4.1841, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.231272312025383e-05, + "loss": 4.1666, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.230433717274331e-05, + "loss": 4.1787, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.229598398284026e-05, + "loss": 4.1754, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.228759803532974e-05, + "loss": 4.1786, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.227921208781922e-05, + "loss": 4.1684, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.22708261403087e-05, + "loss": 4.1692, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.226244019279818e-05, + "loss": 4.1661, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.2254054245287657e-05, + "loss": 4.1704, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.2245684676580866e-05, + "loss": 4.1714, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.2237298729070346e-05, + "loss": 4.1789, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.2228912781559826e-05, + "loss": 4.1795, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.2220526834049306e-05, + "loss": 4.1757, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.2212157265342515e-05, + "loss": 4.1699, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.2203771317831995e-05, + "loss": 4.1722, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.219540174912521e-05, + "loss": 4.1773, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.218701580161469e-05, + "loss": 4.1612, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.217862985410417e-05, + "loss": 4.1565, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.217024390659365e-05, + "loss": 4.1565, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.216185795908313e-05, + "loss": 4.1639, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.215347201157261e-05, + "loss": 4.1701, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.214508606406209e-05, + "loss": 4.1666, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.213670011655157e-05, + "loss": 4.1627, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.212831416904105e-05, + "loss": 4.1669, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.211992822153053e-05, + "loss": 4.165, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.211154227402001e-05, + "loss": 4.1681, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.210315632650949e-05, + "loss": 4.1597, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209477037899897e-05, + "loss": 4.1424, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208638443148845e-05, + "loss": 4.1858, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.207799848397792e-05, + "loss": 4.17, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.206961253646741e-05, + "loss": 4.1745, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.2061242967760626e-05, + "loss": 4.1618, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.20528570202501e-05, + "loss": 4.1659, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.204447107273958e-05, + "loss": 4.1618, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.203608512522906e-05, + "loss": 4.1619, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.202769917771854e-05, + "loss": 4.1652, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.201932960901175e-05, + "loss": 4.1595, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.201094366150123e-05, + "loss": 4.1808, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.200255771399071e-05, + "loss": 4.1569, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.1994188145283924e-05, + "loss": 4.1468, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.19858021977734e-05, + "loss": 4.1718, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.197741625026288e-05, + "loss": 4.1426, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.1969030302752363e-05, + "loss": 4.1453, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.1960644355241843e-05, + "loss": 4.1707, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.1952258407731323e-05, + "loss": 4.1662, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.19438724602208e-05, + "loss": 4.1493, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.193548651271028e-05, + "loss": 4.1625, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.192711694400349e-05, + "loss": 4.137, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.191873099649297e-05, + "loss": 4.1559, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.191034504898245e-05, + "loss": 4.1601, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.190195910147193e-05, + "loss": 4.155, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.189358953276514e-05, + "loss": 4.1625, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.188520358525462e-05, + "loss": 4.1623, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.18768176377441e-05, + "loss": 4.1737, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.186843169023358e-05, + "loss": 4.1514, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.18600621215268e-05, + "loss": 4.1538, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.185167617401628e-05, + "loss": 4.1641, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.184329022650576e-05, + "loss": 4.1487, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.183490427899524e-05, + "loss": 4.1605, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.1826551089092175e-05, + "loss": 4.1556, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.1818165141581655e-05, + "loss": 4.1518, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.1809779194071135e-05, + "loss": 4.1717, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.1801393246560615e-05, + "loss": 4.1442, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.1793007299050095e-05, + "loss": 4.1477, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.1784621351539575e-05, + "loss": 4.1588, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.1776235404029055e-05, + "loss": 4.1613, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.1767849456518535e-05, + "loss": 4.1514, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.175947988781175e-05, + "loss": 4.1579, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.175111031910496e-05, + "loss": 4.1396, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.174272437159444e-05, + "loss": 4.1488, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.173433842408392e-05, + "loss": 4.1485, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.17259524765734e-05, + "loss": 4.154, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.171756652906288e-05, + "loss": 4.1663, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170918058155236e-05, + "loss": 4.1526, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.170079463404184e-05, + "loss": 4.1557, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.169240868653132e-05, + "loss": 4.1477, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.16840227390208e-05, + "loss": 4.1466, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.167563679151028e-05, + "loss": 4.1489, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.166725084399975e-05, + "loss": 4.1606, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.165886489648923e-05, + "loss": 4.156, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.165049532778245e-05, + "loss": 4.1564, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.1642125759075664e-05, + "loss": 4.143, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.1633739811565144e-05, + "loss": 4.1564, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.1625353864054624e-05, + "loss": 4.1427, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.1616967916544104e-05, + "loss": 4.1521, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.160859834783731e-05, + "loss": 4.1375, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160021240032679e-05, + "loss": 4.1538, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.159182645281627e-05, + "loss": 4.1422, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.158344050530575e-05, + "loss": 4.1489, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.1575054557795226e-05, + "loss": 4.139, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.1566668610284706e-05, + "loss": 4.148, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155829904157792e-05, + "loss": 4.1429, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.15499130940674e-05, + "loss": 4.1403, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154152714655688e-05, + "loss": 4.1584, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153314119904636e-05, + "loss": 4.1587, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152475525153584e-05, + "loss": 4.1541, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151636930402532e-05, + "loss": 4.1491, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.15079833565148e-05, + "loss": 4.1393, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.149959740900428e-05, + "loss": 4.1439, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.149122784029749e-05, + "loss": 4.1479, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.148284189278697e-05, + "loss": 4.1516, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.147445594527645e-05, + "loss": 4.1333, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.146606999776593e-05, + "loss": 4.149, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.145768405025541e-05, + "loss": 4.1486, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.144931448154863e-05, + "loss": 4.1454, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.144092853403811e-05, + "loss": 4.1418, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.1432542586527587e-05, + "loss": 4.1462, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.1424156639017067e-05, + "loss": 4.1381, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.1415787070310276e-05, + "loss": 4.1563, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.1407401122799756e-05, + "loss": 4.1516, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.1399015175289236e-05, + "loss": 4.1502, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.1390629227778716e-05, + "loss": 4.1346, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.1382259659071925e-05, + "loss": 4.1536, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.1373873711561405e-05, + "loss": 4.1497, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.1365487764050885e-05, + "loss": 4.1393, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.1357118195344094e-05, + "loss": 4.1481, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.134874862663731e-05, + "loss": 4.148, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.134036267912679e-05, + "loss": 4.1444, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.133197673161627e-05, + "loss": 4.1619, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.132359078410575e-05, + "loss": 4.1375, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.131520483659523e-05, + "loss": 4.1472, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.130681888908471e-05, + "loss": 4.1446, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.129843294157419e-05, + "loss": 4.1437, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.129004699406367e-05, + "loss": 4.136, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128166104655315e-05, + "loss": 4.133, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.127327509904263e-05, + "loss": 4.1396, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.126488915153211e-05, + "loss": 4.1337, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125650320402159e-05, + "loss": 4.1461, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 4.14478063583374, + "eval_runtime": 294.6857, + "eval_samples_per_second": 1294.908, + "eval_steps_per_second": 40.467, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.1248150014118534e-05, + "loss": 4.1446, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.1239764066608014e-05, + "loss": 4.1332, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.1231378119097494e-05, + "loss": 4.1452, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.1222992171586974e-05, + "loss": 4.1421, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.1214606224076454e-05, + "loss": 4.1471, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.1206220276565934e-05, + "loss": 4.1392, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.1197834329055414e-05, + "loss": 4.1432, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.118944838154489e-05, + "loss": 4.1318, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.11810788128381e-05, + "loss": 4.1304, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.117270924413131e-05, + "loss": 4.1464, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.116432329662079e-05, + "loss": 4.1415, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.115593734911027e-05, + "loss": 4.1344, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.114756778040348e-05, + "loss": 4.1455, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.113918183289297e-05, + "loss": 4.1318, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.113079588538245e-05, + "loss": 4.1317, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.112240993787193e-05, + "loss": 4.1251, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.111402399036141e-05, + "loss": 4.1336, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.110563804285089e-05, + "loss": 4.1379, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.109725209534036e-05, + "loss": 4.1321, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.108886614782984e-05, + "loss": 4.1482, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.108048020031932e-05, + "loss": 4.1428, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.10720942528088e-05, + "loss": 4.1445, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.106370830529828e-05, + "loss": 4.132, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.105532235778776e-05, + "loss": 4.1363, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.104695278908097e-05, + "loss": 4.1452, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.103856684157045e-05, + "loss": 4.1374, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.1030197272863665e-05, + "loss": 4.1305, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.1021811325353145e-05, + "loss": 4.1346, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.1013425377842625e-05, + "loss": 4.1241, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.1005039430332105e-05, + "loss": 4.1335, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.0996653482821585e-05, + "loss": 4.1343, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.0988267535311065e-05, + "loss": 4.1413, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.0979881587800545e-05, + "loss": 4.1411, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.0971512019093754e-05, + "loss": 4.1401, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.0963126071583234e-05, + "loss": 4.1335, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.0954740124072714e-05, + "loss": 4.1329, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.0946354176562194e-05, + "loss": 4.1388, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.09379846078554e-05, + "loss": 4.1242, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.092959866034489e-05, + "loss": 4.1217, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.092121271283437e-05, + "loss": 4.1188, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.091282676532385e-05, + "loss": 4.1273, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.090444081781333e-05, + "loss": 4.1297, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.089605487030281e-05, + "loss": 4.1322, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.088766892279229e-05, + "loss": 4.1268, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.087928297528177e-05, + "loss": 4.1279, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.087089702777125e-05, + "loss": 4.1302, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.086251108026072e-05, + "loss": 4.1349, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.08541251327502e-05, + "loss": 4.1225, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.084575556404342e-05, + "loss": 4.1062, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.08373696165329e-05, + "loss": 4.1441, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.082898366902237e-05, + "loss": 4.1347, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.082059772151186e-05, + "loss": 4.1403, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.081221177400134e-05, + "loss": 4.1244, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.080382582649082e-05, + "loss": 4.1288, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.079545625778403e-05, + "loss": 4.1246, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.078707031027351e-05, + "loss": 4.1247, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.077868436276299e-05, + "loss": 4.1326, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.077029841525247e-05, + "loss": 4.117, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.076191246774195e-05, + "loss": 4.1466, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.075355927783889e-05, + "loss": 4.1258, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.074517333032837e-05, + "loss": 4.105, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.0736787382817845e-05, + "loss": 4.1362, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.0728401435307325e-05, + "loss": 4.112, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.072001548779681e-05, + "loss": 4.1093, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.071162954028629e-05, + "loss": 4.1355, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.070324359277577e-05, + "loss": 4.128, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.069485764526525e-05, + "loss": 4.115, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.068647169775473e-05, + "loss": 4.1249, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.067808575024421e-05, + "loss": 4.1047, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.066969980273369e-05, + "loss": 4.118, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.066131385522317e-05, + "loss": 4.1249, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.065294428651638e-05, + "loss": 4.1176, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.064455833900586e-05, + "loss": 4.1265, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.063617239149534e-05, + "loss": 4.1232, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.062778644398482e-05, + "loss": 4.138, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.06194004964743e-05, + "loss": 4.1163, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.061101454896378e-05, + "loss": 4.1201, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.060262860145326e-05, + "loss": 4.1279, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.059424265394274e-05, + "loss": 4.1145, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.0585873085235956e-05, + "loss": 4.1257, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.0577487137725436e-05, + "loss": 4.1205, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.056910119021491e-05, + "loss": 4.1129, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.056071524270439e-05, + "loss": 4.1341, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.055232929519387e-05, + "loss": 4.1084, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.0543959726487085e-05, + "loss": 4.1121, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.053557377897656e-05, + "loss": 4.124, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.052718783146604e-05, + "loss": 4.1229, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.051880188395552e-05, + "loss": 4.1149, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.0510448694052463e-05, + "loss": 4.1241, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.0502062746541943e-05, + "loss": 4.1037, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.049367679903143e-05, + "loss": 4.1108, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.048529085152091e-05, + "loss": 4.114, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.047690490401038e-05, + "loss": 4.1163, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.046851895649986e-05, + "loss": 4.1319, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.046013300898934e-05, + "loss": 4.119, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.045174706147882e-05, + "loss": 4.1228, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.044337749277203e-05, + "loss": 4.112, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.043500792406525e-05, + "loss": 4.1136, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.042662197655473e-05, + "loss": 4.1149, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.041823602904421e-05, + "loss": 4.1245, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.040985008153368e-05, + "loss": 4.1223, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.040146413402317e-05, + "loss": 4.1232, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.039307818651265e-05, + "loss": 4.113, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.038470861780586e-05, + "loss": 4.117, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.037633904909907e-05, + "loss": 4.1115, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.036795310158855e-05, + "loss": 4.1152, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.035956715407803e-05, + "loss": 4.1038, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.0351181206567506e-05, + "loss": 4.1212, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.0342795259056986e-05, + "loss": 4.1083, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.0334409311546466e-05, + "loss": 4.1142, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.0326023364035946e-05, + "loss": 4.1057, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.0317637416525426e-05, + "loss": 4.1124, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.0309251469014906e-05, + "loss": 4.1111, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.0300865521504386e-05, + "loss": 4.1085, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.0292479573993866e-05, + "loss": 4.1208, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.028409362648335e-05, + "loss": 4.1266, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.027572405777656e-05, + "loss": 4.1251, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.026733811026604e-05, + "loss": 4.1141, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.025895216275552e-05, + "loss": 4.105, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.025058259404873e-05, + "loss": 4.109, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.024219664653821e-05, + "loss": 4.1143, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.023381069902769e-05, + "loss": 4.117, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.022542475151717e-05, + "loss": 4.0999, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.021703880400665e-05, + "loss": 4.1167, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.020866923529986e-05, + "loss": 4.1165, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.020028328778934e-05, + "loss": 4.1088, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.019189734027882e-05, + "loss": 4.1084, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.0183527771572035e-05, + "loss": 4.1148, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.0175141824061515e-05, + "loss": 4.1057, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.0166755876550995e-05, + "loss": 4.1213, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.0158369929040475e-05, + "loss": 4.1133, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.0149983981529955e-05, + "loss": 4.12, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.0141598034019435e-05, + "loss": 4.102, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.0133212086508915e-05, + "loss": 4.1204, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.0124826138998395e-05, + "loss": 4.1174, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.011644019148787e-05, + "loss": 4.1076, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.010805424397735e-05, + "loss": 4.1149, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.0099684675270564e-05, + "loss": 4.1132, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.0091298727760044e-05, + "loss": 4.1143, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.0082912780249524e-05, + "loss": 4.1307, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.0074526832739004e-05, + "loss": 4.1025, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.0066140885228484e-05, + "loss": 4.1165, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.0057754937717964e-05, + "loss": 4.1122, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.0049368990207444e-05, + "loss": 4.1119, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.0040983042696924e-05, + "loss": 4.1041, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.003261347399013e-05, + "loss": 4.0998, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.002422752647961e-05, + "loss": 4.1098, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.001585795777282e-05, + "loss": 4.1006, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.00074720102623e-05, + "loss": 4.1147, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 4.119741916656494, + "eval_runtime": 295.1931, + "eval_samples_per_second": 1292.683, + "eval_steps_per_second": 40.397, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.999908606275178e-05, + "loss": 4.1065, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.999070011524126e-05, + "loss": 4.1047, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.998231416773074e-05, + "loss": 4.112, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.997392822022022e-05, + "loss": 4.1107, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.996554227270971e-05, + "loss": 4.1156, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.995715632519919e-05, + "loss": 4.1081, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.994877037768867e-05, + "loss": 4.1144, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.994038443017815e-05, + "loss": 4.0992, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.993199848266763e-05, + "loss": 4.099, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.992361253515711e-05, + "loss": 4.116, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.991522658764658e-05, + "loss": 4.109, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.990684064013606e-05, + "loss": 4.1025, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.989847107142928e-05, + "loss": 4.115, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.989008512391876e-05, + "loss": 4.0985, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.988169917640823e-05, + "loss": 4.103, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.987331322889771e-05, + "loss": 4.0881, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.986492728138719e-05, + "loss": 4.1038, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.985654133387668e-05, + "loss": 4.1096, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.984815538636616e-05, + "loss": 4.0968, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.983976943885564e-05, + "loss": 4.116, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.983138349134512e-05, + "loss": 4.1141, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.9822997543834597e-05, + "loss": 4.1105, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.9814611596324077e-05, + "loss": 4.1042, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.9806225648813557e-05, + "loss": 4.1066, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.9797856080106766e-05, + "loss": 4.1101, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.9789470132596246e-05, + "loss": 4.1053, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.9781084185085726e-05, + "loss": 4.096, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.9772714616378935e-05, + "loss": 4.1058, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.9764328668868415e-05, + "loss": 4.0938, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.9755942721357895e-05, + "loss": 4.1017, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.9747556773847374e-05, + "loss": 4.1015, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.973917082633686e-05, + "loss": 4.1066, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.973080125763007e-05, + "loss": 4.1113, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.972241531011955e-05, + "loss": 4.1132, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.971402936260903e-05, + "loss": 4.0965, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.970565979390224e-05, + "loss": 4.1042, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.969727384639172e-05, + "loss": 4.1102, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.96888878988812e-05, + "loss": 4.0916, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.968050195137068e-05, + "loss": 4.093, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967211600386016e-05, + "loss": 4.0922, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.966373005634964e-05, + "loss": 4.0909, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.965534410883912e-05, + "loss": 4.1006, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.96469581613286e-05, + "loss": 4.1019, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.963857221381808e-05, + "loss": 4.0933, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.963018626630756e-05, + "loss": 4.0953, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.962180031879704e-05, + "loss": 4.097, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.961341437128652e-05, + "loss": 4.1074, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.960504480257973e-05, + "loss": 4.0875, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.9596675233872944e-05, + "loss": 4.08, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958828928636242e-05, + "loss": 4.1094, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.95799033388519e-05, + "loss": 4.1031, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.957151739134138e-05, + "loss": 4.108, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.956313144383086e-05, + "loss": 4.0943, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.9554761875124066e-05, + "loss": 4.0969, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.9546375927613546e-05, + "loss": 4.0959, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.953800635890676e-05, + "loss": 4.0944, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.952962041139624e-05, + "loss": 4.1015, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.952123446388572e-05, + "loss": 4.0845, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.95128485163752e-05, + "loss": 4.1204, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.950446256886468e-05, + "loss": 4.091, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.949607662135416e-05, + "loss": 4.0762, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.948769067384364e-05, + "loss": 4.1063, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.947930472633312e-05, + "loss": 4.087, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.94709187788226e-05, + "loss": 4.0771, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.946253283131208e-05, + "loss": 4.1038, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.945414688380156e-05, + "loss": 4.0997, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.944576093629104e-05, + "loss": 4.0903, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.943739136758425e-05, + "loss": 4.0919, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.942900542007373e-05, + "loss": 4.0741, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.942061947256322e-05, + "loss": 4.0861, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.94122335250527e-05, + "loss": 4.0976, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.9403863956345906e-05, + "loss": 4.0905, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.9395478008835386e-05, + "loss": 4.0943, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.9387108440128595e-05, + "loss": 4.0916, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.9378722492618075e-05, + "loss": 4.1084, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.9370336545107555e-05, + "loss": 4.0897, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.9361950597597035e-05, + "loss": 4.0918, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.9353564650086515e-05, + "loss": 4.0946, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.9345178702575995e-05, + "loss": 4.0886, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.9336792755065475e-05, + "loss": 4.0975, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.9328406807554955e-05, + "loss": 4.0896, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.932003723884817e-05, + "loss": 4.0875, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.931165129133765e-05, + "loss": 4.1027, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.930326534382713e-05, + "loss": 4.079, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.929489577512034e-05, + "loss": 4.0844, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.928650982760982e-05, + "loss": 4.0909, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.92781238800993e-05, + "loss": 4.0941, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.926973793258878e-05, + "loss": 4.0831, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.926135198507825e-05, + "loss": 4.0965, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925296603756773e-05, + "loss": 4.0806, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.924458009005721e-05, + "loss": 4.0834, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923619414254669e-05, + "loss": 4.0809, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.922784095264364e-05, + "loss": 4.0859, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.9219471383936854e-05, + "loss": 4.1019, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.9211085436426334e-05, + "loss": 4.0876, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.9202699488915813e-05, + "loss": 4.0921, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.9194313541405293e-05, + "loss": 4.0838, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.918592759389477e-05, + "loss": 4.0835, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.917754164638425e-05, + "loss": 4.0864, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.9169155698873727e-05, + "loss": 4.0957, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.9160769751363206e-05, + "loss": 4.0937, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.9152383803852686e-05, + "loss": 4.0913, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.9143997856342166e-05, + "loss": 4.0912, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.9135611908831646e-05, + "loss": 4.0873, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.9127225961321126e-05, + "loss": 4.0851, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.911885639261434e-05, + "loss": 4.0859, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.911047044510382e-05, + "loss": 4.0751, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.91020844975933e-05, + "loss": 4.0911, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.909369855008278e-05, + "loss": 4.0809, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.908531260257226e-05, + "loss": 4.0834, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.907694303386547e-05, + "loss": 4.0807, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.906855708635495e-05, + "loss": 4.0781, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.906017113884443e-05, + "loss": 4.0847, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.905178519133391e-05, + "loss": 4.0793, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.904341562262712e-05, + "loss": 4.0959, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.90350296751166e-05, + "loss": 4.0958, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.9026660106409816e-05, + "loss": 4.0943, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.9018274158899296e-05, + "loss": 4.0855, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.9009904590192505e-05, + "loss": 4.0805, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.9001518642681985e-05, + "loss": 4.079, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.8993132695171465e-05, + "loss": 4.0876, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.8984746747660945e-05, + "loss": 4.0915, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.8976360800150425e-05, + "loss": 4.0741, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.8967974852639905e-05, + "loss": 4.0845, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.8959588905129385e-05, + "loss": 4.0881, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.8951219336422594e-05, + "loss": 4.0844, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.8942833388912074e-05, + "loss": 4.0793, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.8934447441401554e-05, + "loss": 4.0856, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.8926061493891034e-05, + "loss": 4.0762, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.8917675546380514e-05, + "loss": 4.0941, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.8909289598869994e-05, + "loss": 4.0846, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.890090365135948e-05, + "loss": 4.0962, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.889251770384896e-05, + "loss": 4.0769, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.888413175633844e-05, + "loss": 4.0879, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.887574580882791e-05, + "loss": 4.0925, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.886737624012113e-05, + "loss": 4.0814, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.885899029261061e-05, + "loss": 4.0849, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.885060434510009e-05, + "loss": 4.0867, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.884221839758956e-05, + "loss": 4.0832, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.883383245007904e-05, + "loss": 4.1008, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.882544650256852e-05, + "loss": 4.0796, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.8817060555058e-05, + "loss": 4.0891, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.880867460754748e-05, + "loss": 4.0861, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.88003050388407e-05, + "loss": 4.0833, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.879191909133018e-05, + "loss": 4.0766, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.878353314381966e-05, + "loss": 4.0749, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.877516357511287e-05, + "loss": 4.08, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.876677762760235e-05, + "loss": 4.0777, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.875839168009183e-05, + "loss": 4.0844, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 4.099898815155029, + "eval_runtime": 286.0052, + "eval_samples_per_second": 1334.21, + "eval_steps_per_second": 41.695, + "step": 686880 + }, + { + "epoch": 1.0, + "learning_rate": 3.875000573258131e-05, + "loss": 4.0793, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.874161978507079e-05, + "loss": 4.0783, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.873323383756027e-05, + "loss": 4.0808, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.872484789004975e-05, + "loss": 4.0872, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.871646194253923e-05, + "loss": 4.092, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.870807599502871e-05, + "loss": 4.0819, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.8699706426321916e-05, + "loss": 4.083, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.86913204788114e-05, + "loss": 4.0733, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.868293453130088e-05, + "loss": 4.0744, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.867454858379036e-05, + "loss": 4.0843, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.866617901508357e-05, + "loss": 4.0827, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.865779306757305e-05, + "loss": 4.0779, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.864943987766999e-05, + "loss": 4.0875, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.864105393015947e-05, + "loss": 4.0729, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.863266798264895e-05, + "loss": 4.0749, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.862428203513843e-05, + "loss": 4.0593, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.861589608762791e-05, + "loss": 4.0812, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.860751014011739e-05, + "loss": 4.0814, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.859912419260687e-05, + "loss": 4.0708, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.8590738245096356e-05, + "loss": 4.0884, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.8582368676389565e-05, + "loss": 4.0857, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.8573982728879045e-05, + "loss": 4.0865, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.8565596781368525e-05, + "loss": 4.0796, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.8557210833858005e-05, + "loss": 4.0802, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.8548824886347485e-05, + "loss": 4.0814, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.8540438938836965e-05, + "loss": 4.0832, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.8532052991326445e-05, + "loss": 4.0658, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.852366704381592e-05, + "loss": 4.0804, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.85152810963054e-05, + "loss": 4.0673, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.8506911527598614e-05, + "loss": 4.0764, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.849854195889182e-05, + "loss": 4.0779, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.849015601138131e-05, + "loss": 4.0833, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.848177006387079e-05, + "loss": 4.0767, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.847338411636027e-05, + "loss": 4.0888, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.846499816884975e-05, + "loss": 4.0721, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.845662860014296e-05, + "loss": 4.0776, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.844824265263244e-05, + "loss": 4.0824, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.843985670512192e-05, + "loss": 4.0621, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.843147075761139e-05, + "loss": 4.0662, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.842308481010087e-05, + "loss": 4.0706, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.841469886259035e-05, + "loss": 4.0652, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.840631291507983e-05, + "loss": 4.0737, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.839794334637305e-05, + "loss": 4.0811, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.838955739886253e-05, + "loss": 4.0672, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.838117145135201e-05, + "loss": 4.0732, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.837278550384149e-05, + "loss": 4.0705, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.836439955633097e-05, + "loss": 4.0775, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.835601360882045e-05, + "loss": 4.0632, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.834762766130993e-05, + "loss": 4.0565, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.833924171379941e-05, + "loss": 4.0833, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.8330872145092616e-05, + "loss": 4.078, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.8322486197582096e-05, + "loss": 4.0885, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.8314100250071576e-05, + "loss": 4.0657, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.8305714302561056e-05, + "loss": 4.0702, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.8297344733854265e-05, + "loss": 4.0718, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.828897516514748e-05, + "loss": 4.0668, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.828058921763696e-05, + "loss": 4.0815, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.827220327012644e-05, + "loss": 4.0546, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.826381732261592e-05, + "loss": 4.0959, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.82554313751054e-05, + "loss": 4.07, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.824704542759488e-05, + "loss": 4.0487, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.823865948008436e-05, + "loss": 4.0773, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.823027353257384e-05, + "loss": 4.0637, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.822188758506332e-05, + "loss": 4.0512, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.82135016375528e-05, + "loss": 4.0754, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.820511569004228e-05, + "loss": 4.0782, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.8196729742531754e-05, + "loss": 4.0615, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.8188343795021234e-05, + "loss": 4.0701, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.817999060511818e-05, + "loss": 4.048, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.8171604657607666e-05, + "loss": 4.063, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.8163218710097146e-05, + "loss": 4.0685, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.8154832762586626e-05, + "loss": 4.064, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.8146463193879835e-05, + "loss": 4.0759, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.8138077246369315e-05, + "loss": 4.062, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.8129691298858795e-05, + "loss": 4.0861, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.8121305351348275e-05, + "loss": 4.0655, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.8112919403837755e-05, + "loss": 4.0691, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.810453345632723e-05, + "loss": 4.0687, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.809614750881671e-05, + "loss": 4.0621, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.808776156130619e-05, + "loss": 4.0697, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.807937561379567e-05, + "loss": 4.0626, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.807098966628515e-05, + "loss": 4.0696, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.8062603718774634e-05, + "loss": 4.0726, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.8054217771264114e-05, + "loss": 4.0626, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.804584820255732e-05, + "loss": 4.0558, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.803747863385053e-05, + "loss": 4.066, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.802909268634001e-05, + "loss": 4.0727, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.802070673882949e-05, + "loss": 4.0582, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.801232079131897e-05, + "loss": 4.0673, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.800393484380845e-05, + "loss": 4.0543, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.799554889629793e-05, + "loss": 4.0614, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.798717932759114e-05, + "loss": 4.0591, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.797879338008062e-05, + "loss": 4.0631, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.79704074325701e-05, + "loss": 4.0759, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.796202148505959e-05, + "loss": 4.0648, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.795363553754907e-05, + "loss": 4.069, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.794526596884228e-05, + "loss": 4.0595, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.793688002133176e-05, + "loss": 4.059, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.792849407382124e-05, + "loss": 4.0625, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.792010812631072e-05, + "loss": 4.0707, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.79117221788002e-05, + "loss": 4.0704, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.790333623128968e-05, + "loss": 4.067, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.789495028377916e-05, + "loss": 4.065, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.788656433626864e-05, + "loss": 4.0606, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.7878194767561846e-05, + "loss": 4.0643, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.7869808820051326e-05, + "loss": 4.0611, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.7861422872540806e-05, + "loss": 4.0562, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.7853036925030286e-05, + "loss": 4.0648, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.78446673563235e-05, + "loss": 4.0572, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.783628140881298e-05, + "loss": 4.0591, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.782789546130246e-05, + "loss": 4.0551, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.781950951379194e-05, + "loss": 4.0535, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.781113994508515e-05, + "loss": 4.0611, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.780275399757463e-05, + "loss": 4.0538, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.779436805006411e-05, + "loss": 4.0689, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.778598210255359e-05, + "loss": 4.069, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.77776125338468e-05, + "loss": 4.0754, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.776922658633628e-05, + "loss": 4.0627, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.776084063882576e-05, + "loss": 4.0582, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.7752471070118975e-05, + "loss": 4.0529, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.7744085122608455e-05, + "loss": 4.0687, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.7735699175097935e-05, + "loss": 4.0651, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.7727313227587415e-05, + "loss": 4.048, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.771892728007689e-05, + "loss": 4.0606, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.771054133256637e-05, + "loss": 4.0626, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.770215538505585e-05, + "loss": 4.0616, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.769376943754533e-05, + "loss": 4.0568, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.768539986883854e-05, + "loss": 4.0607, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.767701392132802e-05, + "loss": 4.0522, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.76686279738175e-05, + "loss": 4.0723, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.766024202630698e-05, + "loss": 4.0616, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.765187245760019e-05, + "loss": 4.0699, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.764348651008967e-05, + "loss": 4.0527, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.763510056257915e-05, + "loss": 4.0665, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.762671461506863e-05, + "loss": 4.0693, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.761834504636184e-05, + "loss": 4.0549, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.760995909885132e-05, + "loss": 4.0639, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.76015731513408e-05, + "loss": 4.0618, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.759320358263401e-05, + "loss": 4.0657, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.758481763512349e-05, + "loss": 4.0739, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.757643168761297e-05, + "loss": 4.0595, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.756804574010245e-05, + "loss": 4.0626, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.755965979259193e-05, + "loss": 4.063, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.755127384508141e-05, + "loss": 4.061, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.7542904276374627e-05, + "loss": 4.0539, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.7534518328864107e-05, + "loss": 4.0523, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.7526132381353586e-05, + "loss": 4.0547, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.7517746433843066e-05, + "loss": 4.055, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.7509360486332546e-05, + "loss": 4.0589, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 4.083510875701904, + "eval_runtime": 283.4154, + "eval_samples_per_second": 1346.402, + "eval_steps_per_second": 42.076, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.7500974538822026e-05, + "loss": 4.059, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.7492588591311506e-05, + "loss": 4.0533, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.7484202643800986e-05, + "loss": 4.0576, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.7475816696290466e-05, + "loss": 4.0637, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.7467430748779946e-05, + "loss": 4.0705, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.7459044801269426e-05, + "loss": 4.0576, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.74506588537589e-05, + "loss": 4.0631, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.744227290624838e-05, + "loss": 4.0519, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.7433886958737866e-05, + "loss": 4.0487, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.7425501011227346e-05, + "loss": 4.0568, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.7417115063716826e-05, + "loss": 4.0647, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.7408729116206306e-05, + "loss": 4.0564, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.7400359547499515e-05, + "loss": 4.0634, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.7391973599988995e-05, + "loss": 4.0482, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.7383587652478475e-05, + "loss": 4.0552, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.7375201704967955e-05, + "loss": 4.0329, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.7366815757457435e-05, + "loss": 4.0593, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.7358429809946915e-05, + "loss": 4.0581, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.7350043862436395e-05, + "loss": 4.0472, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.7341657914925875e-05, + "loss": 4.0639, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.7333271967415355e-05, + "loss": 4.0652, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.7324886019904835e-05, + "loss": 4.0639, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.7316500072394315e-05, + "loss": 4.053, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.7308114124883794e-05, + "loss": 4.0578, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.729976093498074e-05, + "loss": 4.0586, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.729137498747022e-05, + "loss": 4.0619, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.72829890399597e-05, + "loss": 4.0421, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.727460309244918e-05, + "loss": 4.0555, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.726621714493866e-05, + "loss": 4.0482, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.725784757623187e-05, + "loss": 4.049, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.724946162872135e-05, + "loss": 4.0575, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.724107568121083e-05, + "loss": 4.0592, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.723268973370031e-05, + "loss": 4.0563, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.722430378618979e-05, + "loss": 4.0661, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.7215934217483e-05, + "loss": 4.0524, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.720756464877621e-05, + "loss": 4.0565, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.719917870126569e-05, + "loss": 4.0632, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.719079275375517e-05, + "loss": 4.0386, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.718240680624465e-05, + "loss": 4.0428, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.717402085873413e-05, + "loss": 4.0472, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.716565129002734e-05, + "loss": 4.0377, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.715726534251682e-05, + "loss": 4.0525, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.71488793950063e-05, + "loss": 4.0597, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.714049344749578e-05, + "loss": 4.0439, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.713212387878899e-05, + "loss": 4.0504, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.712373793127847e-05, + "loss": 4.0505, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.711535198376795e-05, + "loss": 4.0521, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.710696603625744e-05, + "loss": 4.0419, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.709858008874691e-05, + "loss": 4.0336, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.709019414123639e-05, + "loss": 4.0577, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.708180819372587e-05, + "loss": 4.0591, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.707342224621535e-05, + "loss": 4.0673, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.706503629870483e-05, + "loss": 4.0451, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.705665035119431e-05, + "loss": 4.046, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.704826440368379e-05, + "loss": 4.0506, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.703987845617327e-05, + "loss": 4.0455, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.703150888746648e-05, + "loss": 4.0605, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.702312293995596e-05, + "loss": 4.0312, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.7014753371249176e-05, + "loss": 4.0746, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.7006367423738655e-05, + "loss": 4.0509, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.6997981476228135e-05, + "loss": 4.0284, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.6989595528717615e-05, + "loss": 4.0537, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.6981209581207095e-05, + "loss": 4.0414, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.6972823633696575e-05, + "loss": 4.0296, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.6964437686186055e-05, + "loss": 4.0556, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.6956051738675535e-05, + "loss": 4.0552, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.6947665791165015e-05, + "loss": 4.04, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.6939296222458224e-05, + "loss": 4.0535, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.693092665375143e-05, + "loss": 4.0244, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.692254070624091e-05, + "loss": 4.0423, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.691415475873039e-05, + "loss": 4.0409, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.690576881121987e-05, + "loss": 4.0455, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.689738286370936e-05, + "loss": 4.0484, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.688899691619884e-05, + "loss": 4.042, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.688062734749205e-05, + "loss": 4.0664, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.687224139998153e-05, + "loss": 4.045, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.686385545247101e-05, + "loss": 4.0499, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.685546950496049e-05, + "loss": 4.0439, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.684708355744997e-05, + "loss": 4.0397, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.683869760993945e-05, + "loss": 4.0485, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.683031166242892e-05, + "loss": 4.0416, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.682194209372214e-05, + "loss": 4.0455, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.681355614621162e-05, + "loss": 4.0563, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.68051701987011e-05, + "loss": 4.0415, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.679678425119058e-05, + "loss": 4.0315, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.6788414682483794e-05, + "loss": 4.0426, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.6780028734973274e-05, + "loss": 4.0528, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.677164278746275e-05, + "loss": 4.0333, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.676325683995223e-05, + "loss": 4.0502, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.675488727124544e-05, + "loss": 4.0396, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.674650132373492e-05, + "loss": 4.0349, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.6738115376224396e-05, + "loss": 4.0381, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.6729729428713876e-05, + "loss": 4.038, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.6721343481203356e-05, + "loss": 4.0596, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.6712957533692836e-05, + "loss": 4.0416, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.6704587964986045e-05, + "loss": 4.0474, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.669620201747553e-05, + "loss": 4.0398, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.668781606996501e-05, + "loss": 4.0383, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.667943012245449e-05, + "loss": 4.0389, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.667104417494397e-05, + "loss": 4.0501, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.666265822743345e-05, + "loss": 4.0498, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.665428865872666e-05, + "loss": 4.046, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.664590271121614e-05, + "loss": 4.0458, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.663751676370562e-05, + "loss": 4.0356, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.66291308161951e-05, + "loss": 4.047, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.662074486868458e-05, + "loss": 4.0389, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.661239167878152e-05, + "loss": 4.0347, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.6604005731271e-05, + "loss": 4.0396, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.6595619783760485e-05, + "loss": 4.0391, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.6587233836249965e-05, + "loss": 4.0394, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.6578847888739445e-05, + "loss": 4.032, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.6570461941228925e-05, + "loss": 4.0314, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.6562075993718405e-05, + "loss": 4.0409, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.6553690046207885e-05, + "loss": 4.0423, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.6545304098697365e-05, + "loss": 4.0443, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.6536918151186845e-05, + "loss": 4.049, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.6528532203676325e-05, + "loss": 4.0564, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.6520162634969534e-05, + "loss": 4.0396, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.6511776687459014e-05, + "loss": 4.0397, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.6503390739948494e-05, + "loss": 4.0321, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.6495004792437974e-05, + "loss": 4.045, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.648663522373118e-05, + "loss": 4.0438, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.647824927622067e-05, + "loss": 4.0329, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.646987970751388e-05, + "loss": 4.0342, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.646149376000336e-05, + "loss": 4.0465, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.645310781249284e-05, + "loss": 4.0424, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.644472186498232e-05, + "loss": 4.0328, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.643635229627553e-05, + "loss": 4.0377, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.642796634876501e-05, + "loss": 4.0368, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.641958040125449e-05, + "loss": 4.0469, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.641119445374397e-05, + "loss": 4.0441, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.640280850623345e-05, + "loss": 4.0492, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.639442255872293e-05, + "loss": 4.0339, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.638603661121241e-05, + "loss": 4.0457, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.637765066370189e-05, + "loss": 4.0484, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.636926471619137e-05, + "loss": 4.031, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.636087876868085e-05, + "loss": 4.0408, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.635249282117033e-05, + "loss": 4.0431, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.6344123252463536e-05, + "loss": 4.0477, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.6335737304953016e-05, + "loss": 4.0499, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.6327351357442496e-05, + "loss": 4.038, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.6318965409931976e-05, + "loss": 4.0421, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.6310579462421456e-05, + "loss": 4.0439, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.6302193514910936e-05, + "loss": 4.0379, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.6293807567400416e-05, + "loss": 4.0327, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.6285421619889896e-05, + "loss": 4.0336, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.6277052051183105e-05, + "loss": 4.0306, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.626866610367259e-05, + "loss": 4.0391, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.626028015616207e-05, + "loss": 4.0397, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 4.069751739501953, + "eval_runtime": 290.1959, + "eval_samples_per_second": 1314.943, + "eval_steps_per_second": 41.093, + "step": 839520 + }, + { + "epoch": 1.0, + "learning_rate": 3.625189420865155e-05, + "loss": 4.0365, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.624350826114103e-05, + "loss": 4.0351, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.623513869243424e-05, + "loss": 4.0383, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.622675274492372e-05, + "loss": 4.0417, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.62183667974132e-05, + "loss": 4.047, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.620998084990268e-05, + "loss": 4.039, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.620161128119589e-05, + "loss": 4.0431, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.619322533368537e-05, + "loss": 4.0346, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.618483938617485e-05, + "loss": 4.0272, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.617646981746806e-05, + "loss": 4.0357, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.616808386995754e-05, + "loss": 4.049, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.6159697922447025e-05, + "loss": 4.0313, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.6151328353740234e-05, + "loss": 4.0465, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.6142942406229714e-05, + "loss": 4.0262, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.6134556458719194e-05, + "loss": 4.0338, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.6126170511208674e-05, + "loss": 4.0166, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.6117784563698154e-05, + "loss": 4.0405, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.6109398616187634e-05, + "loss": 4.0367, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.6101012668677114e-05, + "loss": 4.0312, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.609262672116659e-05, + "loss": 4.0364, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.608424077365607e-05, + "loss": 4.0504, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.607585482614555e-05, + "loss": 4.042, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.606746887863503e-05, + "loss": 4.0381, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.605908293112451e-05, + "loss": 4.0347, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.605072974122146e-05, + "loss": 4.0436, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.604234379371094e-05, + "loss": 4.0378, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.603395784620042e-05, + "loss": 4.0272, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.602557189868989e-05, + "loss": 4.0341, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.601718595117937e-05, + "loss": 4.0285, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.600881638247259e-05, + "loss": 4.0272, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.600043043496206e-05, + "loss": 4.04, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.599204448745154e-05, + "loss": 4.033, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.598365853994102e-05, + "loss": 4.0427, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.59752725924305e-05, + "loss": 4.0437, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.596688664491998e-05, + "loss": 4.0313, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.59585170762132e-05, + "loss": 4.0378, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.595013112870268e-05, + "loss": 4.0406, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.594174518119216e-05, + "loss": 4.0228, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.5933359233681637e-05, + "loss": 4.0273, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.5924973286171117e-05, + "loss": 4.0215, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.5916587338660597e-05, + "loss": 4.0217, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.5908201391150076e-05, + "loss": 4.032, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.5899831822443286e-05, + "loss": 4.0416, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.5891445874932766e-05, + "loss": 4.0251, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.5883059927422245e-05, + "loss": 4.0269, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.5874673979911725e-05, + "loss": 4.0346, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.5866288032401205e-05, + "loss": 4.0326, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.5857918463694414e-05, + "loss": 4.0244, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.58495325161839e-05, + "loss": 4.0151, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.584114656867338e-05, + "loss": 4.0362, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.583276062116286e-05, + "loss": 4.0419, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.582437467365234e-05, + "loss": 4.0423, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.581598872614182e-05, + "loss": 4.0263, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.58076027786313e-05, + "loss": 4.027, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.579923320992451e-05, + "loss": 4.0299, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.579084726241399e-05, + "loss": 4.0239, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.578246131490347e-05, + "loss": 4.0433, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.577407536739295e-05, + "loss": 4.0147, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.576568941988242e-05, + "loss": 4.0513, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.57573034723719e-05, + "loss": 4.0316, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.574891752486138e-05, + "loss": 4.0116, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.57405479561546e-05, + "loss": 4.0308, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.573216200864408e-05, + "loss": 4.0233, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.572377606113356e-05, + "loss": 4.0129, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.571539011362304e-05, + "loss": 4.0313, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.570700416611252e-05, + "loss": 4.0355, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.5698618218602e-05, + "loss": 4.0225, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.569024864989521e-05, + "loss": 4.0344, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.568186270238469e-05, + "loss": 4.0056, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.567347675487417e-05, + "loss": 4.0241, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.566509080736365e-05, + "loss": 4.023, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.565670485985313e-05, + "loss": 4.0283, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.564833529114634e-05, + "loss": 4.0263, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.5639949343635823e-05, + "loss": 4.024, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.5631563396125303e-05, + "loss": 4.0444, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.562317744861478e-05, + "loss": 4.0289, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.561479150110426e-05, + "loss": 4.0283, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.560640555359374e-05, + "loss": 4.0264, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.559803598488695e-05, + "loss": 4.0218, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.558965003737643e-05, + "loss": 4.0319, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.558126408986591e-05, + "loss": 4.0234, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.557287814235539e-05, + "loss": 4.0232, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.556449219484487e-05, + "loss": 4.0352, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.555610624733435e-05, + "loss": 4.0264, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.554773667862756e-05, + "loss": 4.0095, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.553935073111704e-05, + "loss": 4.0254, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.553096478360652e-05, + "loss": 4.0317, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.552259521489974e-05, + "loss": 4.0165, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.551420926738922e-05, + "loss": 4.0273, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.55058233198787e-05, + "loss": 4.024, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.549743737236818e-05, + "loss": 4.0143, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.548905142485766e-05, + "loss": 4.0231, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.548066547734714e-05, + "loss": 4.0177, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.547227952983661e-05, + "loss": 4.0382, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.546389358232609e-05, + "loss": 4.0256, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.5455524013619306e-05, + "loss": 4.0304, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.5447138066108786e-05, + "loss": 4.0171, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.543875211859826e-05, + "loss": 4.0181, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.543036617108774e-05, + "loss": 4.0256, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.5421980223577226e-05, + "loss": 4.0302, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.5413594276066706e-05, + "loss": 4.0296, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.5405224707359915e-05, + "loss": 4.0269, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.5396838759849395e-05, + "loss": 4.0244, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.5388452812338875e-05, + "loss": 4.0155, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.5380066864828355e-05, + "loss": 4.0293, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.5371680917317835e-05, + "loss": 4.0197, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.5363311348611044e-05, + "loss": 4.0221, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.5354925401100524e-05, + "loss": 4.0192, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.5346539453590004e-05, + "loss": 4.0198, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.5338153506079483e-05, + "loss": 4.0213, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.5329767558568963e-05, + "loss": 4.0114, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.532139798986218e-05, + "loss": 4.0121, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.531301204235166e-05, + "loss": 4.0244, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.530464247364487e-05, + "loss": 4.0222, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.529625652613435e-05, + "loss": 4.0236, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.528787057862383e-05, + "loss": 4.0294, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.527948463111331e-05, + "loss": 4.0381, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.527109868360279e-05, + "loss": 4.0208, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.526271273609227e-05, + "loss": 4.0171, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.525432678858175e-05, + "loss": 4.0183, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.524594084107123e-05, + "loss": 4.0243, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.523755489356071e-05, + "loss": 4.0244, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.522916894605019e-05, + "loss": 4.0176, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.522078299853967e-05, + "loss": 4.0169, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.521239705102915e-05, + "loss": 4.0268, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.5204027482322364e-05, + "loss": 4.0184, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.5195641534811844e-05, + "loss": 4.0191, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.5187255587301324e-05, + "loss": 4.0253, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.51788696397908e-05, + "loss": 4.0201, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.517050007108401e-05, + "loss": 4.0223, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.516211412357349e-05, + "loss": 4.029, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.515372817606297e-05, + "loss": 4.0295, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.5145342228552446e-05, + "loss": 4.0179, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.5136956281041926e-05, + "loss": 4.0279, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.5128570333531406e-05, + "loss": 4.031, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.5120184386020886e-05, + "loss": 4.0169, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.51118148173141e-05, + "loss": 4.0211, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.510344524860731e-05, + "loss": 4.0256, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.50950593010968e-05, + "loss": 4.031, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.508667335358627e-05, + "loss": 4.0335, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.507828740607575e-05, + "loss": 4.0251, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.506990145856523e-05, + "loss": 4.0212, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.506151551105471e-05, + "loss": 4.0256, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.505312956354419e-05, + "loss": 4.0244, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.504474361603367e-05, + "loss": 4.0127, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.503637404732688e-05, + "loss": 4.0211, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.502798809981636e-05, + "loss": 4.0084, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.501960215230584e-05, + "loss": 4.0197, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.501123258359905e-05, + "loss": 4.0201, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 4.058034420013428, + "eval_runtime": 291.6524, + "eval_samples_per_second": 1308.376, + "eval_steps_per_second": 40.888, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.5002846636088535e-05, + "loss": 4.0278, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.4994460688578015e-05, + "loss": 4.0125, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.4986074741067495e-05, + "loss": 4.0176, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.4977688793556975e-05, + "loss": 4.0322, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.4969302846046455e-05, + "loss": 4.0252, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.4960916898535935e-05, + "loss": 4.0267, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.4952530951025415e-05, + "loss": 4.0241, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.4944145003514895e-05, + "loss": 4.0166, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.4935775434808104e-05, + "loss": 4.0086, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.4927389487297584e-05, + "loss": 4.0251, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.4919003539787064e-05, + "loss": 4.0219, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.4910617592276544e-05, + "loss": 4.0211, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.490224802356975e-05, + "loss": 4.0274, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.489386207605923e-05, + "loss": 4.0081, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.488547612854872e-05, + "loss": 4.0177, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.48770901810382e-05, + "loss": 3.9988, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.486870423352768e-05, + "loss": 4.0251, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.486031828601716e-05, + "loss": 4.016, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.485193233850663e-05, + "loss": 4.0185, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.484354639099611e-05, + "loss": 4.0223, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.483516044348559e-05, + "loss": 4.0296, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.482679087477881e-05, + "loss": 4.0246, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.481840492726828e-05, + "loss": 4.0178, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.481001897975776e-05, + "loss": 4.0169, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.480163303224724e-05, + "loss": 4.0303, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.479324708473672e-05, + "loss": 4.0203, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.47848611372262e-05, + "loss": 4.0093, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.477649156851942e-05, + "loss": 4.0201, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.47681056210089e-05, + "loss": 4.0074, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.475971967349838e-05, + "loss": 4.0155, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.475133372598786e-05, + "loss": 4.0234, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.474294777847734e-05, + "loss": 4.0154, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.473456183096682e-05, + "loss": 4.0228, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.47261758834563e-05, + "loss": 4.0277, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.471778993594578e-05, + "loss": 4.0162, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.4709420367238986e-05, + "loss": 4.0227, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.4701034419728466e-05, + "loss": 4.0245, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.4692648472217946e-05, + "loss": 4.0044, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.4684262524707426e-05, + "loss": 4.0126, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.4675876577196906e-05, + "loss": 4.0035, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.4667490629686386e-05, + "loss": 4.0071, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.46591210609796e-05, + "loss": 4.0166, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.465073511346908e-05, + "loss": 4.0221, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.464234916595856e-05, + "loss": 4.0071, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.463396321844804e-05, + "loss": 4.0129, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.462557727093752e-05, + "loss": 4.0142, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.4617191323426995e-05, + "loss": 4.0192, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.4608805375916475e-05, + "loss": 4.0083, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.4600419428405955e-05, + "loss": 3.9969, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.459204985969917e-05, + "loss": 4.0161, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.4583663912188644e-05, + "loss": 4.0305, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.4575277964678124e-05, + "loss": 4.0267, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.456690839597134e-05, + "loss": 4.0059, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.455852244846082e-05, + "loss": 4.0124, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.45501365009503e-05, + "loss": 4.0145, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.4541783311047244e-05, + "loss": 4.0012, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.4533397363536724e-05, + "loss": 4.0317, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.4525011416026204e-05, + "loss": 3.9953, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.4516625468515684e-05, + "loss": 4.0341, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.4508239521005164e-05, + "loss": 4.0135, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.4499853573494644e-05, + "loss": 3.9987, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.449146762598412e-05, + "loss": 4.0133, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.44830816784736e-05, + "loss": 4.0098, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.447469573096308e-05, + "loss": 3.9943, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.446630978345256e-05, + "loss": 4.0153, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.445794021474577e-05, + "loss": 4.02, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.444955426723525e-05, + "loss": 4.0069, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.444116831972473e-05, + "loss": 4.0151, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.443278237221421e-05, + "loss": 3.9902, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.442439642470369e-05, + "loss": 4.0081, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.441601047719317e-05, + "loss": 4.0046, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.440762452968265e-05, + "loss": 4.0143, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.439923858217213e-05, + "loss": 4.0069, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.439085263466161e-05, + "loss": 4.01, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.438246668715109e-05, + "loss": 4.0256, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.43740971184443e-05, + "loss": 4.0128, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.436571117093378e-05, + "loss": 4.0109, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.435732522342326e-05, + "loss": 4.0096, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.434893927591274e-05, + "loss": 4.0075, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.434055332840223e-05, + "loss": 4.0151, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.433218375969544e-05, + "loss": 4.0057, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.432379781218492e-05, + "loss": 4.0132, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.43154118646744e-05, + "loss": 4.0145, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.430702591716388e-05, + "loss": 4.0143, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.429863996965336e-05, + "loss": 3.9905, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.429025402214283e-05, + "loss": 4.0122, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.428186807463231e-05, + "loss": 4.0122, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.427348212712179e-05, + "loss": 4.0023, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.4265128937218735e-05, + "loss": 4.011, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.4256742989708215e-05, + "loss": 4.0061, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.4248357042197695e-05, + "loss": 4.0014, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.423998747349091e-05, + "loss": 4.0034, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.423160152598039e-05, + "loss": 4.0055, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.422321557846987e-05, + "loss": 4.0173, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.421482963095935e-05, + "loss": 4.0097, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.420644368344883e-05, + "loss": 4.0136, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.4198057735938304e-05, + "loss": 4.0036, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.4189671788427784e-05, + "loss": 4.0037, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.4181285840917264e-05, + "loss": 4.0074, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.4172899893406744e-05, + "loss": 4.0157, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.4164513945896224e-05, + "loss": 4.0123, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.4156127998385704e-05, + "loss": 4.0114, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.4147742050875184e-05, + "loss": 4.0105, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.41393724821684e-05, + "loss": 4.0007, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.413098653465788e-05, + "loss": 4.0126, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.412260058714736e-05, + "loss": 4.0061, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.411423101844057e-05, + "loss": 4.007, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.410584507093005e-05, + "loss": 4.0018, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.409745912341953e-05, + "loss": 4.0046, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.408907317590901e-05, + "loss": 4.0043, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.408068722839849e-05, + "loss": 4.0002, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.407230128088797e-05, + "loss": 3.9934, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.406391533337745e-05, + "loss": 4.0073, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.405552938586693e-05, + "loss": 4.0133, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.404715981716014e-05, + "loss": 4.0022, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.403877386964962e-05, + "loss": 4.0135, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.40303879221391e-05, + "loss": 4.0227, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.4022001974628584e-05, + "loss": 4.0048, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.4013616027118064e-05, + "loss": 4.0022, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.4005230079607544e-05, + "loss": 4.0035, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.399684413209702e-05, + "loss": 4.0068, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.398847456339023e-05, + "loss": 4.0066, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.398008861587971e-05, + "loss": 4.0025, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.397170266836919e-05, + "loss": 4.0039, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.3963316720858666e-05, + "loss": 4.011, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.3954930773348146e-05, + "loss": 4.0033, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.3946544825837626e-05, + "loss": 4.0088, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.3938158878327106e-05, + "loss": 4.0052, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.392978930962032e-05, + "loss": 4.004, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.39214033621098e-05, + "loss": 4.0008, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.391301741459928e-05, + "loss": 4.0169, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.390463146708876e-05, + "loss": 4.0112, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.389624551957824e-05, + "loss": 4.0023, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.388785957206772e-05, + "loss": 4.0079, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.38794736245572e-05, + "loss": 4.0171, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.387108767704668e-05, + "loss": 3.9982, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.386270172953616e-05, + "loss": 4.0085, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.385433216082937e-05, + "loss": 4.0096, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.384594621331885e-05, + "loss": 4.0162, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.383756026580833e-05, + "loss": 4.0144, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.382917431829781e-05, + "loss": 4.0116, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.382080474959102e-05, + "loss": 4.005, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.3812418802080507e-05, + "loss": 4.0175, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.3804032854569986e-05, + "loss": 4.0046, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.3795646907059466e-05, + "loss": 3.9957, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.3787260959548946e-05, + "loss": 4.0057, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.3778907769645885e-05, + "loss": 3.9948, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.3770521822135365e-05, + "loss": 4.0065, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.3762135874624845e-05, + "loss": 4.002, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 4.048644065856934, + "eval_runtime": 294.6646, + "eval_samples_per_second": 1295.001, + "eval_steps_per_second": 40.47, + "step": 992160 + }, + { + "epoch": 1.0, + "learning_rate": 3.3753749927114324e-05, + "loss": 4.0052, + "step": 992256 + }, + { + "epoch": 1.0, + "learning_rate": 3.3745363979603804e-05, + "loss": 3.9988, + "step": 992768 + }, + { + "epoch": 1.0, + "learning_rate": 3.3736978032093284e-05, + "loss": 4.0037, + "step": 993280 + }, + { + "epoch": 1.0, + "learning_rate": 3.3728608463386493e-05, + "loss": 4.016, + "step": 993792 + }, + { + "epoch": 1.0, + "learning_rate": 3.3720222515875973e-05, + "loss": 4.0084, + "step": 994304 + }, + { + "epoch": 1.0, + "learning_rate": 3.371183656836546e-05, + "loss": 4.0148, + "step": 994816 + }, + { + "epoch": 1.0, + "learning_rate": 3.370345062085494e-05, + "loss": 4.0044, + "step": 995328 + }, + { + "epoch": 1.0, + "learning_rate": 3.369506467334442e-05, + "loss": 4.0023, + "step": 995840 + }, + { + "epoch": 1.0, + "learning_rate": 3.36866787258339e-05, + "loss": 3.99, + "step": 996352 + }, + { + "epoch": 1.0, + "learning_rate": 3.367830915712711e-05, + "loss": 4.0097, + "step": 996864 + }, + { + "epoch": 1.0, + "learning_rate": 3.366992320961659e-05, + "loss": 4.0061, + "step": 997376 + }, + { + "epoch": 1.0, + "learning_rate": 3.366153726210607e-05, + "loss": 4.0055, + "step": 997888 + }, + { + "epoch": 1.0, + "learning_rate": 3.365316769339928e-05, + "loss": 4.017, + "step": 998400 + }, + { + "epoch": 1.0, + "learning_rate": 3.364478174588876e-05, + "loss": 3.9886, + "step": 998912 + }, + { + "epoch": 1.0, + "learning_rate": 3.363639579837824e-05, + "loss": 3.9987, + "step": 999424 + }, + { + "epoch": 1.0, + "learning_rate": 3.362800985086772e-05, + "loss": 3.9907, + "step": 999936 + }, + { + "epoch": 1.0, + "learning_rate": 3.36196239033572e-05, + "loss": 4.0036, + "step": 1000448 + }, + { + "epoch": 1.0, + "learning_rate": 3.361123795584668e-05, + "loss": 4.0045, + "step": 1000960 + }, + { + "epoch": 1.0, + "learning_rate": 3.360285200833616e-05, + "loss": 3.9987, + "step": 1001472 + }, + { + "epoch": 1.0, + "learning_rate": 3.359446606082564e-05, + "loss": 4.0101, + "step": 1001984 + }, + { + "epoch": 1.0, + "learning_rate": 3.358608011331512e-05, + "loss": 4.0119, + "step": 1002496 + }, + { + "epoch": 1.0, + "learning_rate": 3.35776941658046e-05, + "loss": 4.0085, + "step": 1003008 + }, + { + "epoch": 1.0, + "learning_rate": 3.356930821829408e-05, + "loss": 4.005, + "step": 1003520 + }, + { + "epoch": 1.0, + "learning_rate": 3.356092227078356e-05, + "loss": 4.0019, + "step": 1004032 + }, + { + "epoch": 1.0, + "learning_rate": 3.355255270207677e-05, + "loss": 4.0157, + "step": 1004544 + }, + { + "epoch": 1.0, + "learning_rate": 3.3544183133369976e-05, + "loss": 4.0034, + "step": 1005056 + }, + { + "epoch": 1.0, + "learning_rate": 3.3535797185859456e-05, + "loss": 3.9948, + "step": 1005568 + }, + { + "epoch": 1.0, + "learning_rate": 3.352742761715267e-05, + "loss": 4.0048, + "step": 1006080 + }, + { + "epoch": 1.0, + "learning_rate": 3.351904166964215e-05, + "loss": 3.9916, + "step": 1006592 + }, + { + "epoch": 1.0, + "learning_rate": 3.351065572213163e-05, + "loss": 3.9998, + "step": 1007104 + }, + { + "epoch": 1.01, + "learning_rate": 3.350226977462111e-05, + "loss": 4.0027, + "step": 1007616 + }, + { + "epoch": 1.01, + "learning_rate": 3.349388382711059e-05, + "loss": 4.0012, + "step": 1008128 + }, + { + "epoch": 1.01, + "learning_rate": 3.348549787960007e-05, + "loss": 4.0101, + "step": 1008640 + }, + { + "epoch": 1.01, + "learning_rate": 3.347711193208955e-05, + "loss": 4.012, + "step": 1009152 + }, + { + "epoch": 1.01, + "learning_rate": 3.346872598457903e-05, + "loss": 4.001, + "step": 1009664 + }, + { + "epoch": 1.01, + "learning_rate": 3.346037279467597e-05, + "loss": 4.0082, + "step": 1010176 + }, + { + "epoch": 1.01, + "learning_rate": 3.345198684716545e-05, + "loss": 4.0095, + "step": 1010688 + }, + { + "epoch": 1.01, + "learning_rate": 3.344360089965493e-05, + "loss": 3.9911, + "step": 1011200 + }, + { + "epoch": 1.01, + "learning_rate": 3.343521495214441e-05, + "loss": 3.9979, + "step": 1011712 + }, + { + "epoch": 1.01, + "learning_rate": 3.342682900463389e-05, + "loss": 3.9864, + "step": 1012224 + }, + { + "epoch": 1.01, + "learning_rate": 3.341844305712337e-05, + "loss": 3.9946, + "step": 1012736 + }, + { + "epoch": 1.01, + "learning_rate": 3.341005710961285e-05, + "loss": 3.9967, + "step": 1013248 + }, + { + "epoch": 1.01, + "learning_rate": 3.340167116210233e-05, + "loss": 4.0143, + "step": 1013760 + }, + { + "epoch": 1.01, + "learning_rate": 3.3393285214591816e-05, + "loss": 3.99, + "step": 1014272 + }, + { + "epoch": 1.01, + "learning_rate": 3.3384899267081296e-05, + "loss": 3.9963, + "step": 1014784 + }, + { + "epoch": 1.01, + "learning_rate": 3.3376513319570776e-05, + "loss": 4.0005, + "step": 1015296 + }, + { + "epoch": 1.01, + "learning_rate": 3.3368127372060256e-05, + "loss": 4.0016, + "step": 1015808 + }, + { + "epoch": 1.01, + "learning_rate": 3.3359757803353465e-05, + "loss": 3.9957, + "step": 1016320 + }, + { + "epoch": 1.01, + "learning_rate": 3.3351371855842945e-05, + "loss": 3.985, + "step": 1016832 + }, + { + "epoch": 1.01, + "learning_rate": 3.3343002287136154e-05, + "loss": 4.0027, + "step": 1017344 + }, + { + "epoch": 1.01, + "learning_rate": 3.3334616339625634e-05, + "loss": 4.0122, + "step": 1017856 + }, + { + "epoch": 1.01, + "learning_rate": 3.3326230392115114e-05, + "loss": 4.0072, + "step": 1018368 + }, + { + "epoch": 1.01, + "learning_rate": 3.3317844444604594e-05, + "loss": 3.9959, + "step": 1018880 + }, + { + "epoch": 1.01, + "learning_rate": 3.33094748758978e-05, + "loss": 3.9925, + "step": 1019392 + }, + { + "epoch": 1.01, + "learning_rate": 3.330108892838728e-05, + "loss": 4.0032, + "step": 1019904 + }, + { + "epoch": 1.01, + "learning_rate": 3.329270298087677e-05, + "loss": 3.9877, + "step": 1020416 + }, + { + "epoch": 1.01, + "learning_rate": 3.328431703336625e-05, + "loss": 4.0143, + "step": 1020928 + }, + { + "epoch": 1.01, + "learning_rate": 3.327594746465946e-05, + "loss": 3.9845, + "step": 1021440 + }, + { + "epoch": 1.01, + "learning_rate": 3.326756151714894e-05, + "loss": 4.018, + "step": 1021952 + }, + { + "epoch": 1.01, + "learning_rate": 3.325917556963842e-05, + "loss": 4.0033, + "step": 1022464 + }, + { + "epoch": 1.01, + "learning_rate": 3.32507896221279e-05, + "loss": 3.9816, + "step": 1022976 + }, + { + "epoch": 1.01, + "learning_rate": 3.324240367461738e-05, + "loss": 3.997, + "step": 1023488 + }, + { + "epoch": 1.01, + "learning_rate": 3.323401772710686e-05, + "loss": 3.9979, + "step": 1024000 + }, + { + "epoch": 1.01, + "learning_rate": 3.322564815840007e-05, + "loss": 3.9817, + "step": 1024512 + }, + { + "epoch": 1.01, + "learning_rate": 3.321726221088955e-05, + "loss": 3.9924, + "step": 1025024 + }, + { + "epoch": 1.01, + "learning_rate": 3.320887626337903e-05, + "loss": 4.0098, + "step": 1025536 + }, + { + "epoch": 1.01, + "learning_rate": 3.320049031586851e-05, + "loss": 3.9931, + "step": 1026048 + }, + { + "epoch": 1.01, + "learning_rate": 3.319210436835799e-05, + "loss": 3.9961, + "step": 1026560 + }, + { + "epoch": 1.01, + "learning_rate": 3.318371842084747e-05, + "loss": 3.9798, + "step": 1027072 + }, + { + "epoch": 1.01, + "learning_rate": 3.317534885214068e-05, + "loss": 3.9943, + "step": 1027584 + }, + { + "epoch": 1.01, + "learning_rate": 3.316696290463016e-05, + "loss": 3.9893, + "step": 1028096 + }, + { + "epoch": 1.01, + "learning_rate": 3.3158576957119636e-05, + "loss": 3.9998, + "step": 1028608 + }, + { + "epoch": 1.01, + "learning_rate": 3.3150191009609116e-05, + "loss": 3.9931, + "step": 1029120 + }, + { + "epoch": 1.01, + "learning_rate": 3.3141805062098596e-05, + "loss": 3.9965, + "step": 1029632 + }, + { + "epoch": 1.01, + "learning_rate": 3.3133435493391805e-05, + "loss": 4.0083, + "step": 1030144 + }, + { + "epoch": 1.01, + "learning_rate": 3.3125049545881285e-05, + "loss": 3.9983, + "step": 1030656 + }, + { + "epoch": 1.01, + "learning_rate": 3.3116663598370765e-05, + "loss": 3.997, + "step": 1031168 + }, + { + "epoch": 1.01, + "learning_rate": 3.3108277650860245e-05, + "loss": 3.9986, + "step": 1031680 + }, + { + "epoch": 1.01, + "learning_rate": 3.3099891703349725e-05, + "loss": 3.996, + "step": 1032192 + }, + { + "epoch": 1.01, + "learning_rate": 3.3091505755839205e-05, + "loss": 3.9996, + "step": 1032704 + }, + { + "epoch": 1.01, + "learning_rate": 3.308311980832869e-05, + "loss": 3.9899, + "step": 1033216 + }, + { + "epoch": 1.01, + "learning_rate": 3.307473386081817e-05, + "loss": 3.9966, + "step": 1033728 + }, + { + "epoch": 1.01, + "learning_rate": 3.306636429211138e-05, + "loss": 4.0041, + "step": 1034240 + }, + { + "epoch": 1.01, + "learning_rate": 3.305799472340459e-05, + "loss": 3.998, + "step": 1034752 + }, + { + "epoch": 1.01, + "learning_rate": 3.304960877589407e-05, + "loss": 3.9807, + "step": 1035264 + }, + { + "epoch": 1.01, + "learning_rate": 3.304122282838355e-05, + "loss": 3.9961, + "step": 1035776 + }, + { + "epoch": 1.01, + "learning_rate": 3.303283688087303e-05, + "loss": 3.9933, + "step": 1036288 + }, + { + "epoch": 1.01, + "learning_rate": 3.302446731216624e-05, + "loss": 3.9942, + "step": 1036800 + }, + { + "epoch": 1.01, + "learning_rate": 3.301608136465572e-05, + "loss": 3.9918, + "step": 1037312 + }, + { + "epoch": 1.01, + "learning_rate": 3.30076954171452e-05, + "loss": 3.9989, + "step": 1037824 + }, + { + "epoch": 1.02, + "learning_rate": 3.299930946963468e-05, + "loss": 3.9829, + "step": 1038336 + }, + { + "epoch": 1.02, + "learning_rate": 3.2990939900927895e-05, + "loss": 3.9908, + "step": 1038848 + }, + { + "epoch": 1.02, + "learning_rate": 3.2982553953417375e-05, + "loss": 3.9867, + "step": 1039360 + }, + { + "epoch": 1.02, + "learning_rate": 3.2974168005906855e-05, + "loss": 4.0057, + "step": 1039872 + }, + { + "epoch": 1.02, + "learning_rate": 3.2965782058396335e-05, + "loss": 3.9923, + "step": 1040384 + }, + { + "epoch": 1.02, + "learning_rate": 3.2957396110885815e-05, + "loss": 4.0037, + "step": 1040896 + }, + { + "epoch": 1.02, + "learning_rate": 3.2949010163375295e-05, + "loss": 3.9852, + "step": 1041408 + }, + { + "epoch": 1.02, + "learning_rate": 3.2940624215864775e-05, + "loss": 3.9912, + "step": 1041920 + }, + { + "epoch": 1.02, + "learning_rate": 3.2932254647157984e-05, + "loss": 3.9929, + "step": 1042432 + }, + { + "epoch": 1.02, + "learning_rate": 3.2923868699647464e-05, + "loss": 4.0, + "step": 1042944 + }, + { + "epoch": 1.02, + "learning_rate": 3.2915482752136944e-05, + "loss": 3.9999, + "step": 1043456 + }, + { + "epoch": 1.02, + "learning_rate": 3.2907096804626423e-05, + "loss": 3.9971, + "step": 1043968 + }, + { + "epoch": 1.02, + "learning_rate": 3.2898710857115903e-05, + "loss": 3.994, + "step": 1044480 + }, + { + "epoch": 1.02, + "learning_rate": 3.2890324909605383e-05, + "loss": 3.9881, + "step": 1044992 + }, + { + "epoch": 1.02, + "learning_rate": 3.288193896209486e-05, + "loss": 4.0009, + "step": 1045504 + }, + { + "epoch": 1.02, + "learning_rate": 3.287356939338808e-05, + "loss": 3.9873, + "step": 1046016 + }, + { + "epoch": 1.02, + "learning_rate": 3.286518344587756e-05, + "loss": 3.9907, + "step": 1046528 + }, + { + "epoch": 1.02, + "learning_rate": 3.285681387717077e-05, + "loss": 3.9912, + "step": 1047040 + }, + { + "epoch": 1.02, + "learning_rate": 3.284842792966025e-05, + "loss": 3.9889, + "step": 1047552 + }, + { + "epoch": 1.02, + "learning_rate": 3.284004198214973e-05, + "loss": 3.9902, + "step": 1048064 + }, + { + "epoch": 1.02, + "learning_rate": 3.283165603463921e-05, + "loss": 3.9914, + "step": 1048576 + }, + { + "epoch": 1.02, + "learning_rate": 3.282327008712869e-05, + "loss": 3.9791, + "step": 1049088 + }, + { + "epoch": 1.02, + "learning_rate": 3.281488413961817e-05, + "loss": 3.9933, + "step": 1049600 + }, + { + "epoch": 1.02, + "learning_rate": 3.280651457091138e-05, + "loss": 3.9977, + "step": 1050112 + }, + { + "epoch": 1.02, + "learning_rate": 3.279812862340086e-05, + "loss": 3.9883, + "step": 1050624 + }, + { + "epoch": 1.02, + "learning_rate": 3.278974267589034e-05, + "loss": 4.0013, + "step": 1051136 + }, + { + "epoch": 1.02, + "learning_rate": 3.278135672837982e-05, + "loss": 4.008, + "step": 1051648 + }, + { + "epoch": 1.02, + "learning_rate": 3.277298715967303e-05, + "loss": 3.9926, + "step": 1052160 + }, + { + "epoch": 1.02, + "learning_rate": 3.276460121216251e-05, + "loss": 3.9896, + "step": 1052672 + }, + { + "epoch": 1.02, + "learning_rate": 3.275621526465199e-05, + "loss": 3.987, + "step": 1053184 + }, + { + "epoch": 1.02, + "learning_rate": 3.2747829317141466e-05, + "loss": 3.9925, + "step": 1053696 + }, + { + "epoch": 1.02, + "learning_rate": 3.2739443369630946e-05, + "loss": 3.9913, + "step": 1054208 + }, + { + "epoch": 1.02, + "learning_rate": 3.2731057422120426e-05, + "loss": 3.9901, + "step": 1054720 + }, + { + "epoch": 1.02, + "learning_rate": 3.2722671474609906e-05, + "loss": 3.9877, + "step": 1055232 + }, + { + "epoch": 1.02, + "learning_rate": 3.2714285527099386e-05, + "loss": 3.9994, + "step": 1055744 + }, + { + "epoch": 1.02, + "learning_rate": 3.2705915958392595e-05, + "loss": 3.9922, + "step": 1056256 + }, + { + "epoch": 1.02, + "learning_rate": 3.2697530010882075e-05, + "loss": 3.9888, + "step": 1056768 + }, + { + "epoch": 1.02, + "learning_rate": 3.2689144063371555e-05, + "loss": 3.9919, + "step": 1057280 + }, + { + "epoch": 1.02, + "learning_rate": 3.2680758115861035e-05, + "loss": 3.9918, + "step": 1057792 + }, + { + "epoch": 1.02, + "learning_rate": 3.2672372168350515e-05, + "loss": 3.9857, + "step": 1058304 + }, + { + "epoch": 1.02, + "learning_rate": 3.266398622084e-05, + "loss": 4.004, + "step": 1058816 + }, + { + "epoch": 1.02, + "learning_rate": 3.265561665213321e-05, + "loss": 4.0004, + "step": 1059328 + }, + { + "epoch": 1.02, + "learning_rate": 3.264723070462269e-05, + "loss": 3.992, + "step": 1059840 + }, + { + "epoch": 1.02, + "learning_rate": 3.263884475711217e-05, + "loss": 3.9935, + "step": 1060352 + }, + { + "epoch": 1.02, + "learning_rate": 3.263045880960165e-05, + "loss": 3.9992, + "step": 1060864 + }, + { + "epoch": 1.02, + "learning_rate": 3.262207286209113e-05, + "loss": 3.9904, + "step": 1061376 + }, + { + "epoch": 1.02, + "learning_rate": 3.261368691458061e-05, + "loss": 3.994, + "step": 1061888 + }, + { + "epoch": 1.02, + "learning_rate": 3.260530096707009e-05, + "loss": 3.9936, + "step": 1062400 + }, + { + "epoch": 1.02, + "learning_rate": 3.25969313983633e-05, + "loss": 4.0076, + "step": 1062912 + }, + { + "epoch": 1.02, + "learning_rate": 3.258854545085278e-05, + "loss": 3.9936, + "step": 1063424 + }, + { + "epoch": 1.02, + "learning_rate": 3.258015950334226e-05, + "loss": 3.9999, + "step": 1063936 + }, + { + "epoch": 1.02, + "learning_rate": 3.257177355583174e-05, + "loss": 3.9896, + "step": 1064448 + }, + { + "epoch": 1.02, + "learning_rate": 3.256338760832122e-05, + "loss": 4.0025, + "step": 1064960 + }, + { + "epoch": 1.02, + "learning_rate": 3.25550016608107e-05, + "loss": 3.9905, + "step": 1065472 + }, + { + "epoch": 1.02, + "learning_rate": 3.2546615713300186e-05, + "loss": 3.9822, + "step": 1065984 + }, + { + "epoch": 1.02, + "learning_rate": 3.253822976578966e-05, + "loss": 3.9928, + "step": 1066496 + }, + { + "epoch": 1.02, + "learning_rate": 3.2529860197082875e-05, + "loss": 3.9805, + "step": 1067008 + }, + { + "epoch": 1.02, + "learning_rate": 3.2521474249572355e-05, + "loss": 3.9938, + "step": 1067520 + }, + { + "epoch": 1.02, + "learning_rate": 3.2513104680865564e-05, + "loss": 3.9871, + "step": 1068032 + }, + { + "epoch": 1.03, + "eval_loss": 4.0411176681518555, + "eval_runtime": 286.0545, + "eval_samples_per_second": 1333.98, + "eval_steps_per_second": 41.688, + "step": 1068480 + }, + { + "epoch": 0.0, + "learning_rate": 3.2504718733355044e-05, + "loss": 3.9871, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.2496332785844524e-05, + "loss": 3.988, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.2487946838334004e-05, + "loss": 3.9874, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.247956089082348e-05, + "loss": 4.0032, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.247117494331296e-05, + "loss": 3.9943, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.246278899580244e-05, + "loss": 4.0021, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.2454403048291924e-05, + "loss": 3.9902, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.2446017100781404e-05, + "loss": 3.9868, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.2437631153270884e-05, + "loss": 3.9815, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.2429245205760364e-05, + "loss": 3.9931, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.2420859258249843e-05, + "loss": 3.9918, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.2412473310739323e-05, + "loss": 3.9928, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.240410374203253e-05, + "loss": 4.0051, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.239571779452201e-05, + "loss": 3.9783, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.238733184701149e-05, + "loss": 3.9809, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.237894589950097e-05, + "loss": 3.9789, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.237055995199045e-05, + "loss": 3.9862, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.236217400447993e-05, + "loss": 3.9908, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.235378805696941e-05, + "loss": 3.988, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.234540210945889e-05, + "loss": 3.9914, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.233701616194837e-05, + "loss": 4.0008, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.232863021443785e-05, + "loss": 3.9908, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.232024426692733e-05, + "loss": 3.9945, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.231185831941681e-05, + "loss": 3.986, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.230348875071002e-05, + "loss": 4.0029, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.22951028031995e-05, + "loss": 3.9899, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.228671685568898e-05, + "loss": 3.9858, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.227833090817846e-05, + "loss": 3.9864, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.226996133947167e-05, + "loss": 3.9801, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.226157539196115e-05, + "loss": 3.988, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.225318944445063e-05, + "loss": 3.9887, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.224481987574384e-05, + "loss": 3.9893, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.2236433928233326e-05, + "loss": 3.9959, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.2228047980722806e-05, + "loss": 3.9985, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.2219662033212286e-05, + "loss": 3.9874, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.2211292464505495e-05, + "loss": 3.9957, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.2202906516994975e-05, + "loss": 3.9925, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.2194520569484455e-05, + "loss": 3.9798, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.2186134621973935e-05, + "loss": 3.9851, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.2177748674463415e-05, + "loss": 3.9713, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.2169379105756624e-05, + "loss": 3.9867, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.2160993158246104e-05, + "loss": 3.9838, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.2152607210735584e-05, + "loss": 3.9972, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.2144221263225064e-05, + "loss": 3.9765, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.2135835315714544e-05, + "loss": 3.9832, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.212746574700776e-05, + "loss": 3.9896, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.211907979949724e-05, + "loss": 3.9875, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.211069385198672e-05, + "loss": 3.9874, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.21023079044762e-05, + "loss": 3.9665, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.209392195696568e-05, + "loss": 3.9878, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.208553600945516e-05, + "loss": 3.9995, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.207715006194464e-05, + "loss": 3.9955, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.206878049323785e-05, + "loss": 3.9814, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.206039454572733e-05, + "loss": 3.9789, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.205200859821681e-05, + "loss": 3.9904, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.204362265070629e-05, + "loss": 3.9745, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.203523670319577e-05, + "loss": 3.9997, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.202685075568525e-05, + "loss": 3.9697, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.201846480817473e-05, + "loss": 4.0072, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.201007886066421e-05, + "loss": 3.9895, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.2001709291957424e-05, + "loss": 3.9671, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.1993323344446904e-05, + "loss": 3.9807, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.198493739693638e-05, + "loss": 3.988, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.197656782822959e-05, + "loss": 3.9668, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.196818188071907e-05, + "loss": 3.9758, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.195979593320855e-05, + "loss": 3.9988, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.1951409985698026e-05, + "loss": 3.9841, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.1943024038187506e-05, + "loss": 3.9815, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.1934638090676986e-05, + "loss": 3.9637, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.1926252143166466e-05, + "loss": 3.9811, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.191788257445968e-05, + "loss": 3.9749, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.190949662694916e-05, + "loss": 3.9921, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.190111067943864e-05, + "loss": 3.9753, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.189272473192812e-05, + "loss": 3.986, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.18843387844176e-05, + "loss": 3.992, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.187596921571081e-05, + "loss": 3.9882, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.186758326820029e-05, + "loss": 3.9817, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.185919732068977e-05, + "loss": 3.9824, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.185081137317925e-05, + "loss": 3.986, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.184242542566873e-05, + "loss": 3.986, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.183403947815821e-05, + "loss": 3.9789, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.182565353064769e-05, + "loss": 3.981, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.18172839619409e-05, + "loss": 3.9878, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.180889801443038e-05, + "loss": 3.9866, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.1800512066919866e-05, + "loss": 3.9673, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.1792126119409346e-05, + "loss": 3.9836, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.1783740171898826e-05, + "loss": 3.9813, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.1775354224388306e-05, + "loss": 3.9813, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.1766968276877786e-05, + "loss": 3.9814, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.1758598708170995e-05, + "loss": 3.9849, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.1750212760660475e-05, + "loss": 3.973, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.1741826813149955e-05, + "loss": 3.9734, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.1733440865639435e-05, + "loss": 3.9754, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.1725054918128915e-05, + "loss": 3.9908, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.171666897061839e-05, + "loss": 3.9809, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.1708299401911604e-05, + "loss": 3.9888, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.1699913454401084e-05, + "loss": 3.9777, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.1691527506890564e-05, + "loss": 3.9797, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.1683141559380044e-05, + "loss": 3.9763, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.1674755611869524e-05, + "loss": 3.99, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.1666369664359004e-05, + "loss": 3.9822, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.1657983716848484e-05, + "loss": 3.9851, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.1649597769337964e-05, + "loss": 3.9812, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.1641211821827444e-05, + "loss": 3.9731, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.163284225312065e-05, + "loss": 3.9926, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.162447268441386e-05, + "loss": 3.9694, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.161608673690334e-05, + "loss": 3.9772, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.160770078939282e-05, + "loss": 3.9825, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.15993148418823e-05, + "loss": 3.9721, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.159094527317552e-05, + "loss": 3.976, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.1582559325665e-05, + "loss": 3.9792, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.157417337815448e-05, + "loss": 3.9673, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.156578743064396e-05, + "loss": 3.9829, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.155740148313344e-05, + "loss": 3.9807, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.154901553562292e-05, + "loss": 3.9804, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.1540645966916126e-05, + "loss": 3.9894, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.1532260019405606e-05, + "loss": 3.9956, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.1523874071895086e-05, + "loss": 3.9827, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.1515488124384566e-05, + "loss": 3.9771, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.1507102176874046e-05, + "loss": 3.9746, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.1498716229363526e-05, + "loss": 3.9793, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.1490330281853006e-05, + "loss": 3.9766, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.1481944334342486e-05, + "loss": 3.9802, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.147355838683197e-05, + "loss": 3.9707, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.146517243932145e-05, + "loss": 3.9871, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.145680287061466e-05, + "loss": 3.977, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.144841692310414e-05, + "loss": 3.9807, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.144003097559362e-05, + "loss": 3.9785, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.143166140688683e-05, + "loss": 3.9765, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.142327545937631e-05, + "loss": 3.9731, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.141488951186579e-05, + "loss": 3.9907, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.140650356435527e-05, + "loss": 3.9864, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.139811761684475e-05, + "loss": 3.9843, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.138974804813796e-05, + "loss": 3.9746, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.138136210062744e-05, + "loss": 3.9849, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.137297615311692e-05, + "loss": 3.9797, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.13645902056064e-05, + "loss": 3.9815, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.1356220636899616e-05, + "loss": 3.9846, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.1347834689389095e-05, + "loss": 3.9901, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.1339448741878575e-05, + "loss": 3.9825, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.133106279436805e-05, + "loss": 3.9892, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.132267684685753e-05, + "loss": 3.9799, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.131429089934701e-05, + "loss": 3.9866, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.130590495183649e-05, + "loss": 3.9758, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.129751900432597e-05, + "loss": 3.9743, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.128914943561918e-05, + "loss": 3.9798, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.128076348810866e-05, + "loss": 3.9656, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.1272377540598144e-05, + "loss": 3.9791, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.126400797189135e-05, + "loss": 3.9785, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 4.034204006195068, + "eval_runtime": 291.2505, + "eval_samples_per_second": 1310.181, + "eval_steps_per_second": 40.944, + "step": 1144800 + }, + { + "epoch": 1.0, + "learning_rate": 3.125562202438083e-05, + "loss": 3.9767, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.124723607687031e-05, + "loss": 3.976, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.123885012935979e-05, + "loss": 3.9756, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.123046418184927e-05, + "loss": 3.9892, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.122207823433875e-05, + "loss": 3.9824, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.121369228682823e-05, + "loss": 3.9915, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.120530633931771e-05, + "loss": 3.9759, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.119693677061092e-05, + "loss": 3.9769, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.11885508231004e-05, + "loss": 3.9678, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.118016487558988e-05, + "loss": 3.9844, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.117177892807936e-05, + "loss": 3.9789, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.116340935937258e-05, + "loss": 3.9809, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.115503979066579e-05, + "loss": 3.9843, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.1146670221958996e-05, + "loss": 3.9729, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.1138284274448476e-05, + "loss": 3.9729, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.1129898326937956e-05, + "loss": 3.9692, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.1121512379427436e-05, + "loss": 3.9676, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.1113126431916916e-05, + "loss": 3.9767, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.1104740484406396e-05, + "loss": 3.9772, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.1096354536895876e-05, + "loss": 3.9789, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.1087968589385356e-05, + "loss": 3.99, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.1079599020678565e-05, + "loss": 3.9785, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.107121307316805e-05, + "loss": 3.9814, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.106282712565753e-05, + "loss": 3.976, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.105444117814701e-05, + "loss": 3.9882, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.104605523063649e-05, + "loss": 3.9732, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.103766928312597e-05, + "loss": 3.9748, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.102929971441918e-05, + "loss": 3.9719, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.102091376690866e-05, + "loss": 3.9723, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.101252781939814e-05, + "loss": 3.9755, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.100414187188762e-05, + "loss": 3.9743, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.09957559243771e-05, + "loss": 3.9811, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.098736997686658e-05, + "loss": 3.9845, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.0978984029356053e-05, + "loss": 3.9802, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.097061446064927e-05, + "loss": 3.9781, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.0962244891942485e-05, + "loss": 3.9824, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.0953858944431965e-05, + "loss": 3.9813, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.0945472996921445e-05, + "loss": 3.9656, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.0937087049410925e-05, + "loss": 3.9765, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.0928701101900405e-05, + "loss": 3.959, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.0920315154389885e-05, + "loss": 3.9719, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.091192920687936e-05, + "loss": 3.968, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.090354325936884e-05, + "loss": 3.9861, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.089515731185832e-05, + "loss": 3.9695, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.08867713643478e-05, + "loss": 3.9683, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.087838541683728e-05, + "loss": 3.9745, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.086999946932676e-05, + "loss": 3.9773, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.08616462794237e-05, + "loss": 3.9729, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.085326033191318e-05, + "loss": 3.956, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.084487438440266e-05, + "loss": 3.9715, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.083648843689214e-05, + "loss": 3.9883, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.082810248938162e-05, + "loss": 3.9816, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.08197165418711e-05, + "loss": 3.9725, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.081133059436058e-05, + "loss": 3.9676, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.080294464685006e-05, + "loss": 3.9809, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.079455869933954e-05, + "loss": 3.9612, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.078618913063275e-05, + "loss": 3.9877, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.077780318312223e-05, + "loss": 3.9565, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.076941723561171e-05, + "loss": 3.9876, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.076103128810119e-05, + "loss": 3.9816, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.075264534059067e-05, + "loss": 3.9576, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.074425939308015e-05, + "loss": 3.97, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.073587344556964e-05, + "loss": 3.9779, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.072750387686285e-05, + "loss": 3.9505, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.071911792935233e-05, + "loss": 3.9668, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.071073198184181e-05, + "loss": 3.9837, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.070234603433129e-05, + "loss": 3.9718, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.069396008682077e-05, + "loss": 3.9691, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.0685590518113976e-05, + "loss": 3.9563, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.0677204570603456e-05, + "loss": 3.9684, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.0668818623092936e-05, + "loss": 3.9605, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.0660432675582416e-05, + "loss": 3.9795, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.0652063106875625e-05, + "loss": 3.9636, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.0643677159365105e-05, + "loss": 3.9758, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.063529121185459e-05, + "loss": 3.979, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.062690526434407e-05, + "loss": 3.9752, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.0618519316833545e-05, + "loss": 3.9695, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.061014974812676e-05, + "loss": 3.9713, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.060176380061624e-05, + "loss": 3.9756, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.059337785310572e-05, + "loss": 3.9747, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.0584991905595194e-05, + "loss": 3.9695, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.0576605958084674e-05, + "loss": 3.9689, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.0568220010574154e-05, + "loss": 3.975, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.0559834063063634e-05, + "loss": 3.9751, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.0551448115553114e-05, + "loss": 3.9564, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.0543062168042594e-05, + "loss": 3.9698, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.053469259933581e-05, + "loss": 3.968, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.052630665182529e-05, + "loss": 3.9694, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.051792070431477e-05, + "loss": 3.9716, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.050955113560798e-05, + "loss": 3.9708, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.050116518809746e-05, + "loss": 3.964, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.049277924058694e-05, + "loss": 3.9583, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.048439329307642e-05, + "loss": 3.9639, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.04760073455659e-05, + "loss": 3.9779, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.046762139805538e-05, + "loss": 3.9691, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.045925182934859e-05, + "loss": 3.9779, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.045086588183807e-05, + "loss": 3.9649, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.044247993432755e-05, + "loss": 3.9657, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.043411036562076e-05, + "loss": 3.963, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.042572441811024e-05, + "loss": 3.9804, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.041733847059972e-05, + "loss": 3.9689, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.04089525230892e-05, + "loss": 3.9768, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.0400566575578683e-05, + "loss": 3.9668, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.0392180628068163e-05, + "loss": 3.9615, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.0383811059361372e-05, + "loss": 3.9795, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.0375425111850852e-05, + "loss": 3.9616, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.0367039164340332e-05, + "loss": 3.9639, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.0358653216829812e-05, + "loss": 3.9696, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.0350267269319292e-05, + "loss": 3.9673, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.0341881321808775e-05, + "loss": 3.9609, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.0333495374298255e-05, + "loss": 3.9658, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.032510942678773e-05, + "loss": 3.9561, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.031672347927721e-05, + "loss": 3.9693, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.030833753176669e-05, + "loss": 3.9691, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.029995158425617e-05, + "loss": 3.9676, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.029156563674565e-05, + "loss": 3.974, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.028319606803886e-05, + "loss": 3.9857, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.027481012052834e-05, + "loss": 3.971, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.026642417301782e-05, + "loss": 3.9653, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.02580382255073e-05, + "loss": 3.9591, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.0249668656800513e-05, + "loss": 3.967, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.0241282709289993e-05, + "loss": 3.9648, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.0232896761779473e-05, + "loss": 3.9672, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.0224510814268953e-05, + "loss": 3.9621, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.0216124866758433e-05, + "loss": 3.9761, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.0207738919247913e-05, + "loss": 3.9675, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.0199352971737393e-05, + "loss": 3.9701, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.0190967024226873e-05, + "loss": 3.964, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.0182597455520085e-05, + "loss": 3.9656, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.0174227886813294e-05, + "loss": 3.96, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.0165841939302774e-05, + "loss": 3.9774, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.0157455991792254e-05, + "loss": 3.9796, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.0149070044281734e-05, + "loss": 3.9738, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.0140684096771214e-05, + "loss": 3.9626, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.0132298149260698e-05, + "loss": 3.9688, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.0123912201750177e-05, + "loss": 3.9712, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.0115542633043387e-05, + "loss": 3.9689, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.0107156685532867e-05, + "loss": 3.9725, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.0098770738022347e-05, + "loss": 3.9785, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.009040116931556e-05, + "loss": 3.9692, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.008201522180504e-05, + "loss": 3.9805, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.007362927429452e-05, + "loss": 3.9623, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.0065243326784e-05, + "loss": 3.9747, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.0056873758077208e-05, + "loss": 3.9686, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.0048487810566688e-05, + "loss": 3.9586, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.0040101863056168e-05, + "loss": 3.9718, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.003171591554565e-05, + "loss": 3.9586, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.002332996803513e-05, + "loss": 3.9634, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.001494402052461e-05, + "loss": 3.969, + "step": 1220608 + }, + { + "epoch": 1.03, + "learning_rate": 3.000655807301409e-05, + "loss": 3.9657, + "step": 1221120 + }, + { + "epoch": 1.03, + "eval_loss": 4.028191089630127, + "eval_runtime": 292.8413, + "eval_samples_per_second": 1303.064, + "eval_steps_per_second": 40.722, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 2.9998172125503564e-05, + "loss": 3.9641, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.9989786177993044e-05, + "loss": 3.9657, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.9981400230482528e-05, + "loss": 3.9755, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.9973014282972008e-05, + "loss": 3.9712, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.9964628335461487e-05, + "loss": 3.98, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.9956242387950967e-05, + "loss": 3.9631, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.9947856440440447e-05, + "loss": 3.9607, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.9939470492929927e-05, + "loss": 3.9617, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.9931084545419407e-05, + "loss": 3.9707, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.9922698597908887e-05, + "loss": 3.9673, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.9914312650398367e-05, + "loss": 3.9702, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.9905926702887847e-05, + "loss": 3.9706, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.989755713418106e-05, + "loss": 3.9599, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.988917118667054e-05, + "loss": 3.9642, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.988080161796375e-05, + "loss": 3.9564, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.987241567045323e-05, + "loss": 3.9562, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.986402972294271e-05, + "loss": 3.9661, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.9855643775432192e-05, + "loss": 3.9661, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.9847257827921672e-05, + "loss": 3.9672, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.9838871880411152e-05, + "loss": 3.9824, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.9830485932900625e-05, + "loss": 3.965, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.9822099985390105e-05, + "loss": 3.9713, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.9813714037879585e-05, + "loss": 3.9648, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.9805328090369068e-05, + "loss": 3.9766, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.9796942142858548e-05, + "loss": 3.966, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.9788556195348028e-05, + "loss": 3.9655, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.9780186626641237e-05, + "loss": 3.9584, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.9771800679130717e-05, + "loss": 3.9646, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.9763414731620197e-05, + "loss": 3.9598, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.9755028784109677e-05, + "loss": 3.9657, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.974664283659916e-05, + "loss": 3.9678, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.973825688908864e-05, + "loss": 3.9686, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.972987094157812e-05, + "loss": 3.9706, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.972150137287133e-05, + "loss": 3.9686, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.971313180416454e-05, + "loss": 3.9667, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.9704745856654022e-05, + "loss": 3.9738, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.9696359909143502e-05, + "loss": 3.9573, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.9687973961632982e-05, + "loss": 3.9626, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.9679588014122462e-05, + "loss": 3.9493, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.9671202066611942e-05, + "loss": 3.9584, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.9662816119101422e-05, + "loss": 3.9579, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.96544301715909e-05, + "loss": 3.9702, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.964604422408038e-05, + "loss": 3.9595, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.963765827656986e-05, + "loss": 3.9575, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.9629272329059345e-05, + "loss": 3.9667, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.9620886381548818e-05, + "loss": 3.9671, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.9612500434038298e-05, + "loss": 3.9591, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.9604114486527778e-05, + "loss": 3.9521, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.9595728539017258e-05, + "loss": 3.9559, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.9587342591506738e-05, + "loss": 3.9769, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.9578989401603686e-05, + "loss": 3.9734, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.9570603454093166e-05, + "loss": 3.9573, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.956221750658264e-05, + "loss": 3.9586, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.955383155907212e-05, + "loss": 3.9683, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.95454456115616e-05, + "loss": 3.9508, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.9537076042854815e-05, + "loss": 3.972, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.9528690095344292e-05, + "loss": 3.9488, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.9520304147833772e-05, + "loss": 3.9793, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.9511918200323252e-05, + "loss": 3.9671, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.9503532252812732e-05, + "loss": 3.9523, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.949514630530221e-05, + "loss": 3.9528, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.948676035779169e-05, + "loss": 3.97, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.947837441028117e-05, + "loss": 3.9384, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.9469988462770655e-05, + "loss": 3.9557, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.9461602515260135e-05, + "loss": 3.9693, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.9453216567749615e-05, + "loss": 3.962, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.9444830620239095e-05, + "loss": 3.9586, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.9436477430336033e-05, + "loss": 3.9453, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.9428091482825516e-05, + "loss": 3.9539, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.9419705535314996e-05, + "loss": 3.9498, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.9411319587804476e-05, + "loss": 3.9723, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.9402933640293956e-05, + "loss": 3.9521, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.9394547692783436e-05, + "loss": 3.9642, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.9386161745272916e-05, + "loss": 3.9651, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.9377792176566125e-05, + "loss": 3.97, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.936940622905561e-05, + "loss": 3.9547, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.936102028154509e-05, + "loss": 3.9606, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.935263433403457e-05, + "loss": 3.9642, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.934424838652405e-05, + "loss": 3.964, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.933586243901353e-05, + "loss": 3.9573, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.9327476491503e-05, + "loss": 3.9568, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.9319090543992485e-05, + "loss": 3.9636, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.93107209752857e-05, + "loss": 3.962, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.9302335027775174e-05, + "loss": 3.9498, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.929396545906839e-05, + "loss": 3.9544, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.928557951155787e-05, + "loss": 3.959, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.927719356404735e-05, + "loss": 3.9641, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.9268807616536826e-05, + "loss": 3.9565, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.9260421669026306e-05, + "loss": 3.9597, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.9252035721515786e-05, + "loss": 3.9546, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.9243649774005266e-05, + "loss": 3.9489, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.9235263826494746e-05, + "loss": 3.9524, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.9226894257787955e-05, + "loss": 3.9636, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.921850831027744e-05, + "loss": 3.9573, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.9210138741570648e-05, + "loss": 3.9688, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.9201769172863864e-05, + "loss": 3.9629, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.9193383225353344e-05, + "loss": 3.9509, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.9184997277842823e-05, + "loss": 3.953, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.91766113303323e-05, + "loss": 3.9657, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.916822538282178e-05, + "loss": 3.9634, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.915983943531126e-05, + "loss": 3.9647, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.915145348780074e-05, + "loss": 3.9548, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.914306754029022e-05, + "loss": 3.953, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.91346815927797e-05, + "loss": 3.9703, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.912631202407291e-05, + "loss": 3.9484, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.9117926076562392e-05, + "loss": 3.9572, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.9109540129051872e-05, + "loss": 3.9579, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.9101154181541352e-05, + "loss": 3.9586, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.9092768234030832e-05, + "loss": 3.9486, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.9084382286520312e-05, + "loss": 3.9541, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.9075996339009792e-05, + "loss": 3.948, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.9067610391499272e-05, + "loss": 3.9578, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.9059224443988752e-05, + "loss": 3.9555, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.9050854875281964e-05, + "loss": 3.9551, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.9042468927771444e-05, + "loss": 3.9651, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.9034082980260924e-05, + "loss": 3.9753, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.9025713411554133e-05, + "loss": 3.9613, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.9017327464043613e-05, + "loss": 3.9532, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.9008941516533093e-05, + "loss": 3.9516, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.9000555569022573e-05, + "loss": 3.9527, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.8992169621512057e-05, + "loss": 3.9583, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.8983783674001537e-05, + "loss": 3.9577, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.897539772649101e-05, + "loss": 3.9488, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.896701177898049e-05, + "loss": 3.9617, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.8958642210273706e-05, + "loss": 3.9583, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.8950256262763186e-05, + "loss": 3.9572, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.8941870315252662e-05, + "loss": 3.9535, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.8933484367742142e-05, + "loss": 3.9559, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.8925098420231622e-05, + "loss": 3.9507, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.8916745230328567e-05, + "loss": 3.9673, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.8908359282818047e-05, + "loss": 3.9675, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.8899973335307527e-05, + "loss": 3.9648, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.889158738779701e-05, + "loss": 3.9488, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.8883201440286483e-05, + "loss": 3.963, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.8874815492775963e-05, + "loss": 3.9588, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.8866429545265443e-05, + "loss": 3.9597, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.885805997655866e-05, + "loss": 3.9564, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.8849674029048136e-05, + "loss": 3.9678, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.8841304460341352e-05, + "loss": 3.9574, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.883291851283083e-05, + "loss": 3.9755, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.8824532565320305e-05, + "loss": 3.9502, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.8816146617809785e-05, + "loss": 3.9695, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.8807760670299265e-05, + "loss": 3.9552, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.8799374722788748e-05, + "loss": 3.9517, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.8790988775278228e-05, + "loss": 3.9585, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.8782602827767708e-05, + "loss": 3.9493, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.8774216880257188e-05, + "loss": 3.9541, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.8765847311550397e-05, + "loss": 3.9585, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.8757461364039877e-05, + "loss": 3.9505, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 4.022686004638672, + "eval_runtime": 294.2769, + "eval_samples_per_second": 1296.707, + "eval_steps_per_second": 40.523, + "step": 1297440 + }, + { + "epoch": 1.0, + "learning_rate": 2.8749075416529357e-05, + "loss": 3.957, + "step": 1297920 + }, + { + "epoch": 1.0, + "learning_rate": 2.874068946901884e-05, + "loss": 3.9538, + "step": 1298432 + }, + { + "epoch": 1.0, + "learning_rate": 2.873230352150832e-05, + "loss": 3.9669, + "step": 1298944 + }, + { + "epoch": 1.0, + "learning_rate": 2.87239175739978e-05, + "loss": 3.9606, + "step": 1299456 + }, + { + "epoch": 1.0, + "learning_rate": 2.871553162648728e-05, + "loss": 3.9706, + "step": 1299968 + }, + { + "epoch": 1.0, + "learning_rate": 2.870714567897676e-05, + "loss": 3.9521, + "step": 1300480 + }, + { + "epoch": 1.0, + "learning_rate": 2.869877611026997e-05, + "loss": 3.9548, + "step": 1300992 + }, + { + "epoch": 1.0, + "learning_rate": 2.869039016275945e-05, + "loss": 3.9484, + "step": 1301504 + }, + { + "epoch": 1.0, + "learning_rate": 2.8682004215248933e-05, + "loss": 3.9608, + "step": 1302016 + }, + { + "epoch": 1.0, + "learning_rate": 2.8673618267738412e-05, + "loss": 3.9556, + "step": 1302528 + }, + { + "epoch": 1.0, + "learning_rate": 2.866524869903162e-05, + "loss": 3.9563, + "step": 1303040 + }, + { + "epoch": 1.0, + "learning_rate": 2.86568627515211e-05, + "loss": 3.9631, + "step": 1303552 + }, + { + "epoch": 1.0, + "learning_rate": 2.864849318281431e-05, + "loss": 3.946, + "step": 1304064 + }, + { + "epoch": 1.0, + "learning_rate": 2.8640107235303794e-05, + "loss": 3.958, + "step": 1304576 + }, + { + "epoch": 1.0, + "learning_rate": 2.8631721287793274e-05, + "loss": 3.9476, + "step": 1305088 + }, + { + "epoch": 1.0, + "learning_rate": 2.8623335340282754e-05, + "loss": 3.9483, + "step": 1305600 + }, + { + "epoch": 1.0, + "learning_rate": 2.8614965771575963e-05, + "loss": 3.9541, + "step": 1306112 + }, + { + "epoch": 1.0, + "learning_rate": 2.8606579824065443e-05, + "loss": 3.9522, + "step": 1306624 + }, + { + "epoch": 1.0, + "learning_rate": 2.8598193876554923e-05, + "loss": 3.9567, + "step": 1307136 + }, + { + "epoch": 1.0, + "learning_rate": 2.8589807929044403e-05, + "loss": 3.9758, + "step": 1307648 + }, + { + "epoch": 1.0, + "learning_rate": 2.8581421981533886e-05, + "loss": 3.9526, + "step": 1308160 + }, + { + "epoch": 1.0, + "learning_rate": 2.8573036034023366e-05, + "loss": 3.9566, + "step": 1308672 + }, + { + "epoch": 1.0, + "learning_rate": 2.8564666465316575e-05, + "loss": 3.9583, + "step": 1309184 + }, + { + "epoch": 1.0, + "learning_rate": 2.8556280517806055e-05, + "loss": 3.9622, + "step": 1309696 + }, + { + "epoch": 1.0, + "learning_rate": 2.8547894570295535e-05, + "loss": 3.959, + "step": 1310208 + }, + { + "epoch": 1.0, + "learning_rate": 2.8539508622785015e-05, + "loss": 3.959, + "step": 1310720 + }, + { + "epoch": 1.0, + "learning_rate": 2.8531122675274495e-05, + "loss": 3.9454, + "step": 1311232 + }, + { + "epoch": 1.0, + "learning_rate": 2.852273672776397e-05, + "loss": 3.9551, + "step": 1311744 + }, + { + "epoch": 1.0, + "learning_rate": 2.851435078025345e-05, + "loss": 3.9453, + "step": 1312256 + }, + { + "epoch": 1.01, + "learning_rate": 2.850596483274293e-05, + "loss": 3.9579, + "step": 1312768 + }, + { + "epoch": 1.01, + "learning_rate": 2.849759526403614e-05, + "loss": 3.9536, + "step": 1313280 + }, + { + "epoch": 1.01, + "learning_rate": 2.8489225695329357e-05, + "loss": 3.959, + "step": 1313792 + }, + { + "epoch": 1.01, + "learning_rate": 2.848083974781884e-05, + "loss": 3.9651, + "step": 1314304 + }, + { + "epoch": 1.01, + "learning_rate": 2.847245380030832e-05, + "loss": 3.9552, + "step": 1314816 + }, + { + "epoch": 1.01, + "learning_rate": 2.846408423160153e-05, + "loss": 3.9607, + "step": 1315328 + }, + { + "epoch": 1.01, + "learning_rate": 2.845569828409101e-05, + "loss": 3.958, + "step": 1315840 + }, + { + "epoch": 1.01, + "learning_rate": 2.844731233658049e-05, + "loss": 3.9509, + "step": 1316352 + }, + { + "epoch": 1.01, + "learning_rate": 2.843892638906997e-05, + "loss": 3.9497, + "step": 1316864 + }, + { + "epoch": 1.01, + "learning_rate": 2.8430540441559445e-05, + "loss": 3.9396, + "step": 1317376 + }, + { + "epoch": 1.01, + "learning_rate": 2.8422154494048925e-05, + "loss": 3.948, + "step": 1317888 + }, + { + "epoch": 1.01, + "learning_rate": 2.8413768546538405e-05, + "loss": 3.9505, + "step": 1318400 + }, + { + "epoch": 1.01, + "learning_rate": 2.8405382599027885e-05, + "loss": 3.9619, + "step": 1318912 + }, + { + "epoch": 1.01, + "learning_rate": 2.8396996651517365e-05, + "loss": 3.9486, + "step": 1319424 + }, + { + "epoch": 1.01, + "learning_rate": 2.8388610704006845e-05, + "loss": 3.9486, + "step": 1319936 + }, + { + "epoch": 1.01, + "learning_rate": 2.8380241135300058e-05, + "loss": 3.9554, + "step": 1320448 + }, + { + "epoch": 1.01, + "learning_rate": 2.8371855187789538e-05, + "loss": 3.9503, + "step": 1320960 + }, + { + "epoch": 1.01, + "learning_rate": 2.8363469240279018e-05, + "loss": 3.9538, + "step": 1321472 + }, + { + "epoch": 1.01, + "learning_rate": 2.8355099671572227e-05, + "loss": 3.9418, + "step": 1321984 + }, + { + "epoch": 1.01, + "learning_rate": 2.8346713724061707e-05, + "loss": 3.9414, + "step": 1322496 + }, + { + "epoch": 1.01, + "learning_rate": 2.8338327776551187e-05, + "loss": 3.9671, + "step": 1323008 + }, + { + "epoch": 1.01, + "learning_rate": 2.8329941829040666e-05, + "loss": 3.965, + "step": 1323520 + }, + { + "epoch": 1.01, + "learning_rate": 2.832155588153015e-05, + "loss": 3.9459, + "step": 1324032 + }, + { + "epoch": 1.01, + "learning_rate": 2.831316993401963e-05, + "loss": 3.952, + "step": 1324544 + }, + { + "epoch": 1.01, + "learning_rate": 2.830478398650911e-05, + "loss": 3.9578, + "step": 1325056 + }, + { + "epoch": 1.01, + "learning_rate": 2.829639803899859e-05, + "loss": 3.9415, + "step": 1325568 + }, + { + "epoch": 1.01, + "learning_rate": 2.82880284702918e-05, + "loss": 3.9623, + "step": 1326080 + }, + { + "epoch": 1.01, + "learning_rate": 2.827964252278128e-05, + "loss": 3.9374, + "step": 1326592 + }, + { + "epoch": 1.01, + "learning_rate": 2.827125657527076e-05, + "loss": 3.9673, + "step": 1327104 + }, + { + "epoch": 1.01, + "learning_rate": 2.8262870627760242e-05, + "loss": 3.9586, + "step": 1327616 + }, + { + "epoch": 1.01, + "learning_rate": 2.8254484680249722e-05, + "loss": 3.9445, + "step": 1328128 + }, + { + "epoch": 1.01, + "learning_rate": 2.824611511154293e-05, + "loss": 3.945, + "step": 1328640 + }, + { + "epoch": 1.01, + "learning_rate": 2.823772916403241e-05, + "loss": 3.9585, + "step": 1329152 + }, + { + "epoch": 1.01, + "learning_rate": 2.822934321652189e-05, + "loss": 3.9259, + "step": 1329664 + }, + { + "epoch": 1.01, + "learning_rate": 2.822095726901137e-05, + "loss": 3.9465, + "step": 1330176 + }, + { + "epoch": 1.01, + "learning_rate": 2.821257132150085e-05, + "loss": 3.9591, + "step": 1330688 + }, + { + "epoch": 1.01, + "learning_rate": 2.8204185373990328e-05, + "loss": 3.9557, + "step": 1331200 + }, + { + "epoch": 1.01, + "learning_rate": 2.8195799426479807e-05, + "loss": 3.9465, + "step": 1331712 + }, + { + "epoch": 1.01, + "learning_rate": 2.8187413478969287e-05, + "loss": 3.9353, + "step": 1332224 + }, + { + "epoch": 1.01, + "learning_rate": 2.8179027531458767e-05, + "loss": 3.9433, + "step": 1332736 + }, + { + "epoch": 1.01, + "learning_rate": 2.817065796275198e-05, + "loss": 3.9426, + "step": 1333248 + }, + { + "epoch": 1.01, + "learning_rate": 2.816227201524146e-05, + "loss": 3.9538, + "step": 1333760 + }, + { + "epoch": 1.01, + "learning_rate": 2.815388606773094e-05, + "loss": 3.9446, + "step": 1334272 + }, + { + "epoch": 1.01, + "learning_rate": 2.814550012022042e-05, + "loss": 3.9543, + "step": 1334784 + }, + { + "epoch": 1.01, + "learning_rate": 2.813713055151363e-05, + "loss": 3.9557, + "step": 1335296 + }, + { + "epoch": 1.01, + "learning_rate": 2.8128760982806845e-05, + "loss": 3.9604, + "step": 1335808 + }, + { + "epoch": 1.01, + "learning_rate": 2.8120375035296325e-05, + "loss": 3.9425, + "step": 1336320 + }, + { + "epoch": 1.01, + "learning_rate": 2.81119890877858e-05, + "loss": 3.9513, + "step": 1336832 + }, + { + "epoch": 1.01, + "learning_rate": 2.810360314027528e-05, + "loss": 3.9547, + "step": 1337344 + }, + { + "epoch": 1.01, + "learning_rate": 2.809521719276476e-05, + "loss": 3.9504, + "step": 1337856 + }, + { + "epoch": 1.01, + "learning_rate": 2.808683124525424e-05, + "loss": 3.9496, + "step": 1338368 + }, + { + "epoch": 1.01, + "learning_rate": 2.807844529774372e-05, + "loss": 3.9457, + "step": 1338880 + }, + { + "epoch": 1.01, + "learning_rate": 2.80700593502332e-05, + "loss": 3.9554, + "step": 1339392 + }, + { + "epoch": 1.01, + "learning_rate": 2.806167340272268e-05, + "loss": 3.9503, + "step": 1339904 + }, + { + "epoch": 1.01, + "learning_rate": 2.8053303834015893e-05, + "loss": 3.9365, + "step": 1340416 + }, + { + "epoch": 1.01, + "learning_rate": 2.8044917886505373e-05, + "loss": 3.9466, + "step": 1340928 + }, + { + "epoch": 1.01, + "learning_rate": 2.8036548317798582e-05, + "loss": 3.9472, + "step": 1341440 + }, + { + "epoch": 1.01, + "learning_rate": 2.8028162370288062e-05, + "loss": 3.9544, + "step": 1341952 + }, + { + "epoch": 1.01, + "learning_rate": 2.8019776422777542e-05, + "loss": 3.9498, + "step": 1342464 + }, + { + "epoch": 1.01, + "learning_rate": 2.8011390475267026e-05, + "loss": 3.9457, + "step": 1342976 + }, + { + "epoch": 1.02, + "learning_rate": 2.8003004527756506e-05, + "loss": 3.9441, + "step": 1343488 + }, + { + "epoch": 1.02, + "learning_rate": 2.7994634959049715e-05, + "loss": 3.9378, + "step": 1344000 + }, + { + "epoch": 1.02, + "learning_rate": 2.7986249011539195e-05, + "loss": 3.9398, + "step": 1344512 + }, + { + "epoch": 1.02, + "learning_rate": 2.7977863064028675e-05, + "loss": 3.9534, + "step": 1345024 + }, + { + "epoch": 1.02, + "learning_rate": 2.7969477116518155e-05, + "loss": 3.9495, + "step": 1345536 + }, + { + "epoch": 1.02, + "learning_rate": 2.7961107547811367e-05, + "loss": 3.9566, + "step": 1346048 + }, + { + "epoch": 1.02, + "learning_rate": 2.7952721600300847e-05, + "loss": 3.9516, + "step": 1346560 + }, + { + "epoch": 1.02, + "learning_rate": 2.7944335652790327e-05, + "loss": 3.9444, + "step": 1347072 + }, + { + "epoch": 1.02, + "learning_rate": 2.7935949705279807e-05, + "loss": 3.9453, + "step": 1347584 + }, + { + "epoch": 1.02, + "learning_rate": 2.7927563757769287e-05, + "loss": 3.9513, + "step": 1348096 + }, + { + "epoch": 1.02, + "learning_rate": 2.7919177810258767e-05, + "loss": 3.9578, + "step": 1348608 + }, + { + "epoch": 1.02, + "learning_rate": 2.7910791862748247e-05, + "loss": 3.9553, + "step": 1349120 + }, + { + "epoch": 1.02, + "learning_rate": 2.7902405915237727e-05, + "loss": 3.9456, + "step": 1349632 + }, + { + "epoch": 1.02, + "learning_rate": 2.789401996772721e-05, + "loss": 3.9415, + "step": 1350144 + }, + { + "epoch": 1.02, + "learning_rate": 2.788563402021669e-05, + "loss": 3.9584, + "step": 1350656 + }, + { + "epoch": 1.02, + "learning_rate": 2.7877248072706163e-05, + "loss": 3.9384, + "step": 1351168 + }, + { + "epoch": 1.02, + "learning_rate": 2.786887850399938e-05, + "loss": 3.9478, + "step": 1351680 + }, + { + "epoch": 1.02, + "learning_rate": 2.7860508935292588e-05, + "loss": 3.9474, + "step": 1352192 + }, + { + "epoch": 1.02, + "learning_rate": 2.785212298778207e-05, + "loss": 3.948, + "step": 1352704 + }, + { + "epoch": 1.02, + "learning_rate": 2.784373704027155e-05, + "loss": 3.9376, + "step": 1353216 + }, + { + "epoch": 1.02, + "learning_rate": 2.783535109276103e-05, + "loss": 3.9483, + "step": 1353728 + }, + { + "epoch": 1.02, + "learning_rate": 2.782696514525051e-05, + "loss": 3.9359, + "step": 1354240 + }, + { + "epoch": 1.02, + "learning_rate": 2.781859557654372e-05, + "loss": 3.9449, + "step": 1354752 + }, + { + "epoch": 1.02, + "learning_rate": 2.78102096290332e-05, + "loss": 3.9474, + "step": 1355264 + }, + { + "epoch": 1.02, + "learning_rate": 2.780182368152268e-05, + "loss": 3.9428, + "step": 1355776 + }, + { + "epoch": 1.02, + "learning_rate": 2.779343773401216e-05, + "loss": 3.9617, + "step": 1356288 + }, + { + "epoch": 1.02, + "learning_rate": 2.7785051786501637e-05, + "loss": 3.9633, + "step": 1356800 + }, + { + "epoch": 1.02, + "learning_rate": 2.7776698596598582e-05, + "loss": 3.9526, + "step": 1357312 + }, + { + "epoch": 1.02, + "learning_rate": 2.7768329027891795e-05, + "loss": 3.9436, + "step": 1357824 + }, + { + "epoch": 1.02, + "learning_rate": 2.7759943080381274e-05, + "loss": 3.94, + "step": 1358336 + }, + { + "epoch": 1.02, + "learning_rate": 2.7751557132870754e-05, + "loss": 3.9472, + "step": 1358848 + }, + { + "epoch": 1.02, + "learning_rate": 2.7743171185360234e-05, + "loss": 3.9435, + "step": 1359360 + }, + { + "epoch": 1.02, + "learning_rate": 2.7734785237849714e-05, + "loss": 3.9548, + "step": 1359872 + }, + { + "epoch": 1.02, + "learning_rate": 2.7726399290339194e-05, + "loss": 3.9361, + "step": 1360384 + }, + { + "epoch": 1.02, + "learning_rate": 2.7718013342828674e-05, + "loss": 3.9478, + "step": 1360896 + }, + { + "epoch": 1.02, + "learning_rate": 2.7709627395318154e-05, + "loss": 3.9495, + "step": 1361408 + }, + { + "epoch": 1.02, + "learning_rate": 2.7701241447807634e-05, + "loss": 3.9515, + "step": 1361920 + }, + { + "epoch": 1.02, + "learning_rate": 2.769285550029711e-05, + "loss": 3.9389, + "step": 1362432 + }, + { + "epoch": 1.02, + "learning_rate": 2.768446955278659e-05, + "loss": 3.9459, + "step": 1362944 + }, + { + "epoch": 1.02, + "learning_rate": 2.767608360527607e-05, + "loss": 3.9473, + "step": 1363456 + }, + { + "epoch": 1.02, + "learning_rate": 2.766769765776555e-05, + "loss": 3.9518, + "step": 1363968 + }, + { + "epoch": 1.02, + "learning_rate": 2.765931171025503e-05, + "loss": 3.9566, + "step": 1364480 + }, + { + "epoch": 1.02, + "learning_rate": 2.765092576274451e-05, + "loss": 3.956, + "step": 1364992 + }, + { + "epoch": 1.02, + "learning_rate": 2.764253981523399e-05, + "loss": 3.9382, + "step": 1365504 + }, + { + "epoch": 1.02, + "learning_rate": 2.7634170246527203e-05, + "loss": 3.9525, + "step": 1366016 + }, + { + "epoch": 1.02, + "learning_rate": 2.7625784299016683e-05, + "loss": 3.9515, + "step": 1366528 + }, + { + "epoch": 1.02, + "learning_rate": 2.7617414730309892e-05, + "loss": 3.9472, + "step": 1367040 + }, + { + "epoch": 1.02, + "learning_rate": 2.7609028782799372e-05, + "loss": 3.9504, + "step": 1367552 + }, + { + "epoch": 1.02, + "learning_rate": 2.7600642835288852e-05, + "loss": 3.9559, + "step": 1368064 + }, + { + "epoch": 1.02, + "learning_rate": 2.7592256887778335e-05, + "loss": 3.9482, + "step": 1368576 + }, + { + "epoch": 1.02, + "learning_rate": 2.7583870940267815e-05, + "loss": 3.9649, + "step": 1369088 + }, + { + "epoch": 1.02, + "learning_rate": 2.7575484992757295e-05, + "loss": 3.942, + "step": 1369600 + }, + { + "epoch": 1.02, + "learning_rate": 2.7567099045246775e-05, + "loss": 3.9555, + "step": 1370112 + }, + { + "epoch": 1.02, + "learning_rate": 2.7558713097736255e-05, + "loss": 3.9483, + "step": 1370624 + }, + { + "epoch": 1.02, + "learning_rate": 2.7550343529029464e-05, + "loss": 3.9424, + "step": 1371136 + }, + { + "epoch": 1.02, + "learning_rate": 2.7541957581518944e-05, + "loss": 3.9466, + "step": 1371648 + }, + { + "epoch": 1.02, + "learning_rate": 2.7533588012812157e-05, + "loss": 3.9429, + "step": 1372160 + }, + { + "epoch": 1.02, + "learning_rate": 2.7525202065301637e-05, + "loss": 3.945, + "step": 1372672 + }, + { + "epoch": 1.02, + "learning_rate": 2.7516816117791117e-05, + "loss": 3.9448, + "step": 1373184 + }, + { + "epoch": 1.02, + "learning_rate": 2.7508446549084326e-05, + "loss": 3.9411, + "step": 1373696 + }, + { + "epoch": 1.03, + "eval_loss": 4.0179524421691895, + "eval_runtime": 295.0017, + "eval_samples_per_second": 1293.521, + "eval_steps_per_second": 40.423, + "step": 1373760 + }, + { + "epoch": 0.0, + "learning_rate": 2.7500060601573806e-05, + "loss": 3.9461, + "step": 1374208 + }, + { + "epoch": 0.0, + "learning_rate": 2.749167465406329e-05, + "loss": 3.9418, + "step": 1374720 + }, + { + "epoch": 0.0, + "learning_rate": 2.748328870655277e-05, + "loss": 3.9574, + "step": 1375232 + }, + { + "epoch": 0.0, + "learning_rate": 2.747490275904225e-05, + "loss": 3.9492, + "step": 1375744 + }, + { + "epoch": 0.0, + "learning_rate": 2.746651681153173e-05, + "loss": 3.9646, + "step": 1376256 + }, + { + "epoch": 0.0, + "learning_rate": 2.745813086402121e-05, + "loss": 3.9409, + "step": 1376768 + }, + { + "epoch": 0.0, + "learning_rate": 2.744974491651069e-05, + "loss": 3.9462, + "step": 1377280 + }, + { + "epoch": 0.0, + "learning_rate": 2.744135896900017e-05, + "loss": 3.9351, + "step": 1377792 + }, + { + "epoch": 0.0, + "learning_rate": 2.743297302148965e-05, + "loss": 3.9519, + "step": 1378304 + }, + { + "epoch": 0.0, + "learning_rate": 2.7424587073979125e-05, + "loss": 3.9473, + "step": 1378816 + }, + { + "epoch": 0.0, + "learning_rate": 2.7416201126468605e-05, + "loss": 3.9458, + "step": 1379328 + }, + { + "epoch": 0.0, + "learning_rate": 2.7407815178958085e-05, + "loss": 3.956, + "step": 1379840 + }, + { + "epoch": 0.0, + "learning_rate": 2.739946198905503e-05, + "loss": 3.9347, + "step": 1380352 + }, + { + "epoch": 0.0, + "learning_rate": 2.739107604154451e-05, + "loss": 3.9489, + "step": 1380864 + }, + { + "epoch": 0.0, + "learning_rate": 2.738269009403399e-05, + "loss": 3.9366, + "step": 1381376 + }, + { + "epoch": 0.0, + "learning_rate": 2.7374304146523473e-05, + "loss": 3.9394, + "step": 1381888 + }, + { + "epoch": 0.0, + "learning_rate": 2.7365918199012947e-05, + "loss": 3.9384, + "step": 1382400 + }, + { + "epoch": 0.0, + "learning_rate": 2.7357532251502426e-05, + "loss": 3.9492, + "step": 1382912 + }, + { + "epoch": 0.0, + "learning_rate": 2.7349146303991906e-05, + "loss": 3.9455, + "step": 1383424 + }, + { + "epoch": 0.0, + "learning_rate": 2.7340760356481386e-05, + "loss": 3.9647, + "step": 1383936 + }, + { + "epoch": 0.0, + "learning_rate": 2.7332374408970866e-05, + "loss": 3.9449, + "step": 1384448 + }, + { + "epoch": 0.0, + "learning_rate": 2.732398846146035e-05, + "loss": 3.9475, + "step": 1384960 + }, + { + "epoch": 0.0, + "learning_rate": 2.731560251394983e-05, + "loss": 3.9461, + "step": 1385472 + }, + { + "epoch": 0.0, + "learning_rate": 2.730721656643931e-05, + "loss": 3.9536, + "step": 1385984 + }, + { + "epoch": 0.0, + "learning_rate": 2.729883061892879e-05, + "loss": 3.9448, + "step": 1386496 + }, + { + "epoch": 0.0, + "learning_rate": 2.729044467141827e-05, + "loss": 3.9499, + "step": 1387008 + }, + { + "epoch": 0.0, + "learning_rate": 2.728205872390775e-05, + "loss": 3.9377, + "step": 1387520 + }, + { + "epoch": 0.0, + "learning_rate": 2.727367277639723e-05, + "loss": 3.9427, + "step": 1388032 + }, + { + "epoch": 0.0, + "learning_rate": 2.726530320769044e-05, + "loss": 3.9335, + "step": 1388544 + }, + { + "epoch": 0.01, + "learning_rate": 2.7256917260179922e-05, + "loss": 3.9489, + "step": 1389056 + }, + { + "epoch": 0.01, + "learning_rate": 2.7248531312669402e-05, + "loss": 3.9493, + "step": 1389568 + }, + { + "epoch": 0.01, + "learning_rate": 2.7240145365158882e-05, + "loss": 3.9487, + "step": 1390080 + }, + { + "epoch": 0.01, + "learning_rate": 2.723177579645209e-05, + "loss": 3.9554, + "step": 1390592 + }, + { + "epoch": 0.01, + "learning_rate": 2.722338984894157e-05, + "loss": 3.9458, + "step": 1391104 + }, + { + "epoch": 0.01, + "learning_rate": 2.7215020280234783e-05, + "loss": 3.947, + "step": 1391616 + }, + { + "epoch": 0.01, + "learning_rate": 2.7206634332724263e-05, + "loss": 3.9508, + "step": 1392128 + }, + { + "epoch": 0.01, + "learning_rate": 2.7198264764017472e-05, + "loss": 3.9423, + "step": 1392640 + }, + { + "epoch": 0.01, + "learning_rate": 2.7189878816506952e-05, + "loss": 3.9389, + "step": 1393152 + }, + { + "epoch": 0.01, + "learning_rate": 2.7181492868996432e-05, + "loss": 3.93, + "step": 1393664 + }, + { + "epoch": 0.01, + "learning_rate": 2.7173106921485912e-05, + "loss": 3.9396, + "step": 1394176 + }, + { + "epoch": 0.01, + "learning_rate": 2.7164720973975392e-05, + "loss": 3.9418, + "step": 1394688 + }, + { + "epoch": 0.01, + "learning_rate": 2.7156335026464876e-05, + "loss": 3.9499, + "step": 1395200 + }, + { + "epoch": 0.01, + "learning_rate": 2.7147949078954356e-05, + "loss": 3.9428, + "step": 1395712 + }, + { + "epoch": 0.01, + "learning_rate": 2.7139563131443835e-05, + "loss": 3.9338, + "step": 1396224 + }, + { + "epoch": 0.01, + "learning_rate": 2.713117718393331e-05, + "loss": 3.9508, + "step": 1396736 + }, + { + "epoch": 0.01, + "learning_rate": 2.712279123642279e-05, + "loss": 3.9442, + "step": 1397248 + }, + { + "epoch": 0.01, + "learning_rate": 2.7114421667716004e-05, + "loss": 3.9407, + "step": 1397760 + }, + { + "epoch": 0.01, + "learning_rate": 2.7106035720205484e-05, + "loss": 3.9365, + "step": 1398272 + }, + { + "epoch": 0.01, + "learning_rate": 2.709764977269496e-05, + "loss": 3.9295, + "step": 1398784 + }, + { + "epoch": 0.01, + "learning_rate": 2.708926382518444e-05, + "loss": 3.9598, + "step": 1399296 + }, + { + "epoch": 0.01, + "learning_rate": 2.708087787767392e-05, + "loss": 3.9545, + "step": 1399808 + }, + { + "epoch": 0.01, + "learning_rate": 2.70724919301634e-05, + "loss": 3.9371, + "step": 1400320 + }, + { + "epoch": 0.01, + "learning_rate": 2.706410598265288e-05, + "loss": 3.9404, + "step": 1400832 + }, + { + "epoch": 0.01, + "learning_rate": 2.705572003514236e-05, + "loss": 3.9496, + "step": 1401344 + }, + { + "epoch": 0.01, + "learning_rate": 2.7047350466435573e-05, + "loss": 3.9318, + "step": 1401856 + }, + { + "epoch": 0.01, + "learning_rate": 2.7038980897728782e-05, + "loss": 3.9525, + "step": 1402368 + }, + { + "epoch": 0.01, + "learning_rate": 2.7030594950218262e-05, + "loss": 3.9291, + "step": 1402880 + }, + { + "epoch": 0.01, + "learning_rate": 2.7022209002707742e-05, + "loss": 3.9531, + "step": 1403392 + }, + { + "epoch": 0.01, + "learning_rate": 2.7013823055197222e-05, + "loss": 3.9534, + "step": 1403904 + }, + { + "epoch": 0.01, + "learning_rate": 2.7005437107686706e-05, + "loss": 3.9367, + "step": 1404416 + }, + { + "epoch": 0.01, + "learning_rate": 2.6997051160176186e-05, + "loss": 3.9302, + "step": 1404928 + }, + { + "epoch": 0.01, + "learning_rate": 2.6988665212665665e-05, + "loss": 3.9497, + "step": 1405440 + }, + { + "epoch": 0.01, + "learning_rate": 2.6980279265155145e-05, + "loss": 3.9222, + "step": 1405952 + }, + { + "epoch": 0.01, + "learning_rate": 2.6971893317644625e-05, + "loss": 3.9386, + "step": 1406464 + }, + { + "epoch": 0.01, + "learning_rate": 2.6963507370134105e-05, + "loss": 3.9475, + "step": 1406976 + }, + { + "epoch": 0.01, + "learning_rate": 2.6955137801427314e-05, + "loss": 3.9478, + "step": 1407488 + }, + { + "epoch": 0.01, + "learning_rate": 2.6946751853916798e-05, + "loss": 3.9405, + "step": 1408000 + }, + { + "epoch": 0.01, + "learning_rate": 2.6938365906406278e-05, + "loss": 3.9277, + "step": 1408512 + }, + { + "epoch": 0.01, + "learning_rate": 2.6929979958895758e-05, + "loss": 3.9318, + "step": 1409024 + }, + { + "epoch": 0.01, + "learning_rate": 2.6921594011385238e-05, + "loss": 3.9326, + "step": 1409536 + }, + { + "epoch": 0.01, + "learning_rate": 2.6913208063874718e-05, + "loss": 3.9453, + "step": 1410048 + }, + { + "epoch": 0.01, + "learning_rate": 2.6904822116364198e-05, + "loss": 3.9357, + "step": 1410560 + }, + { + "epoch": 0.01, + "learning_rate": 2.6896436168853674e-05, + "loss": 3.9453, + "step": 1411072 + }, + { + "epoch": 0.01, + "learning_rate": 2.688806660014689e-05, + "loss": 3.9492, + "step": 1411584 + }, + { + "epoch": 0.01, + "learning_rate": 2.68796970314401e-05, + "loss": 3.9514, + "step": 1412096 + }, + { + "epoch": 0.01, + "learning_rate": 2.687131108392958e-05, + "loss": 3.9328, + "step": 1412608 + }, + { + "epoch": 0.01, + "learning_rate": 2.686292513641906e-05, + "loss": 3.9402, + "step": 1413120 + }, + { + "epoch": 0.01, + "learning_rate": 2.685453918890854e-05, + "loss": 3.9485, + "step": 1413632 + }, + { + "epoch": 0.01, + "learning_rate": 2.684615324139802e-05, + "loss": 3.9376, + "step": 1414144 + }, + { + "epoch": 0.01, + "learning_rate": 2.6837767293887495e-05, + "loss": 3.9415, + "step": 1414656 + }, + { + "epoch": 0.01, + "learning_rate": 2.6829381346376975e-05, + "loss": 3.9394, + "step": 1415168 + }, + { + "epoch": 0.01, + "learning_rate": 2.6820995398866455e-05, + "loss": 3.9424, + "step": 1415680 + }, + { + "epoch": 0.01, + "learning_rate": 2.6812609451355935e-05, + "loss": 3.943, + "step": 1416192 + }, + { + "epoch": 0.01, + "learning_rate": 2.6804239882649144e-05, + "loss": 3.9274, + "step": 1416704 + }, + { + "epoch": 0.01, + "learning_rate": 2.6795853935138628e-05, + "loss": 3.9408, + "step": 1417216 + }, + { + "epoch": 0.01, + "learning_rate": 2.6787467987628108e-05, + "loss": 3.9355, + "step": 1417728 + }, + { + "epoch": 0.01, + "learning_rate": 2.6779082040117588e-05, + "loss": 3.9452, + "step": 1418240 + }, + { + "epoch": 0.01, + "learning_rate": 2.6770728850214533e-05, + "loss": 3.9389, + "step": 1418752 + }, + { + "epoch": 0.01, + "learning_rate": 2.6762342902704013e-05, + "loss": 3.9378, + "step": 1419264 + }, + { + "epoch": 0.02, + "learning_rate": 2.6753956955193493e-05, + "loss": 3.9354, + "step": 1419776 + }, + { + "epoch": 0.02, + "learning_rate": 2.674557100768297e-05, + "loss": 3.9304, + "step": 1420288 + }, + { + "epoch": 0.02, + "learning_rate": 2.6737201438976185e-05, + "loss": 3.9277, + "step": 1420800 + }, + { + "epoch": 0.02, + "learning_rate": 2.6728815491465665e-05, + "loss": 3.9416, + "step": 1421312 + }, + { + "epoch": 0.02, + "learning_rate": 2.6720429543955145e-05, + "loss": 3.9513, + "step": 1421824 + }, + { + "epoch": 0.02, + "learning_rate": 2.6712043596444618e-05, + "loss": 3.9446, + "step": 1422336 + }, + { + "epoch": 0.02, + "learning_rate": 2.6703657648934098e-05, + "loss": 3.9399, + "step": 1422848 + }, + { + "epoch": 0.02, + "learning_rate": 2.669527170142358e-05, + "loss": 3.9344, + "step": 1423360 + }, + { + "epoch": 0.02, + "learning_rate": 2.668688575391306e-05, + "loss": 3.9382, + "step": 1423872 + }, + { + "epoch": 0.02, + "learning_rate": 2.667849980640254e-05, + "loss": 3.9398, + "step": 1424384 + }, + { + "epoch": 0.02, + "learning_rate": 2.667011385889202e-05, + "loss": 3.947, + "step": 1424896 + }, + { + "epoch": 0.02, + "learning_rate": 2.666174429018523e-05, + "loss": 3.9439, + "step": 1425408 + }, + { + "epoch": 0.02, + "learning_rate": 2.665335834267471e-05, + "loss": 3.9374, + "step": 1425920 + }, + { + "epoch": 0.02, + "learning_rate": 2.664497239516419e-05, + "loss": 3.9298, + "step": 1426432 + }, + { + "epoch": 0.02, + "learning_rate": 2.663658644765367e-05, + "loss": 3.9498, + "step": 1426944 + }, + { + "epoch": 0.02, + "learning_rate": 2.6628216878946883e-05, + "loss": 3.9286, + "step": 1427456 + }, + { + "epoch": 0.02, + "learning_rate": 2.6619830931436363e-05, + "loss": 3.9409, + "step": 1427968 + }, + { + "epoch": 0.02, + "learning_rate": 2.6611444983925843e-05, + "loss": 3.9326, + "step": 1428480 + }, + { + "epoch": 0.02, + "learning_rate": 2.6603059036415323e-05, + "loss": 3.9406, + "step": 1428992 + }, + { + "epoch": 0.02, + "learning_rate": 2.6594689467708532e-05, + "loss": 3.9304, + "step": 1429504 + }, + { + "epoch": 0.02, + "learning_rate": 2.6586303520198015e-05, + "loss": 3.941, + "step": 1430016 + }, + { + "epoch": 0.02, + "learning_rate": 2.6577917572687495e-05, + "loss": 3.93, + "step": 1430528 + }, + { + "epoch": 0.02, + "learning_rate": 2.6569531625176975e-05, + "loss": 3.9316, + "step": 1431040 + }, + { + "epoch": 0.02, + "learning_rate": 2.6561162056470184e-05, + "loss": 3.9435, + "step": 1431552 + }, + { + "epoch": 0.02, + "learning_rate": 2.6552776108959664e-05, + "loss": 3.9309, + "step": 1432064 + }, + { + "epoch": 0.02, + "learning_rate": 2.6544390161449144e-05, + "loss": 3.9522, + "step": 1432576 + }, + { + "epoch": 0.02, + "learning_rate": 2.6536004213938624e-05, + "loss": 3.9525, + "step": 1433088 + }, + { + "epoch": 0.02, + "learning_rate": 2.6527651024035566e-05, + "loss": 3.9448, + "step": 1433600 + }, + { + "epoch": 0.02, + "learning_rate": 2.6519265076525046e-05, + "loss": 3.9343, + "step": 1434112 + }, + { + "epoch": 0.02, + "learning_rate": 2.6510879129014525e-05, + "loss": 3.9323, + "step": 1434624 + }, + { + "epoch": 0.02, + "learning_rate": 2.6502493181504005e-05, + "loss": 3.9354, + "step": 1435136 + }, + { + "epoch": 0.02, + "learning_rate": 2.6494107233993485e-05, + "loss": 3.9357, + "step": 1435648 + }, + { + "epoch": 0.02, + "learning_rate": 2.648572128648297e-05, + "loss": 3.9456, + "step": 1436160 + }, + { + "epoch": 0.02, + "learning_rate": 2.647733533897245e-05, + "loss": 3.9281, + "step": 1436672 + }, + { + "epoch": 0.02, + "learning_rate": 2.646894939146193e-05, + "loss": 3.9392, + "step": 1437184 + }, + { + "epoch": 0.02, + "learning_rate": 2.646056344395141e-05, + "loss": 3.9433, + "step": 1437696 + }, + { + "epoch": 0.02, + "learning_rate": 2.645217749644089e-05, + "loss": 3.941, + "step": 1438208 + }, + { + "epoch": 0.02, + "learning_rate": 2.644379154893037e-05, + "loss": 3.9335, + "step": 1438720 + }, + { + "epoch": 0.02, + "learning_rate": 2.643540560141985e-05, + "loss": 3.9345, + "step": 1439232 + }, + { + "epoch": 0.02, + "learning_rate": 2.642703603271306e-05, + "loss": 3.9382, + "step": 1439744 + }, + { + "epoch": 0.02, + "learning_rate": 2.641866646400627e-05, + "loss": 3.9419, + "step": 1440256 + }, + { + "epoch": 0.02, + "learning_rate": 2.641028051649575e-05, + "loss": 3.9437, + "step": 1440768 + }, + { + "epoch": 0.02, + "learning_rate": 2.640189456898523e-05, + "loss": 3.9512, + "step": 1441280 + }, + { + "epoch": 0.02, + "learning_rate": 2.639350862147471e-05, + "loss": 3.9296, + "step": 1441792 + }, + { + "epoch": 0.02, + "learning_rate": 2.638512267396419e-05, + "loss": 3.9449, + "step": 1442304 + }, + { + "epoch": 0.02, + "learning_rate": 2.637673672645367e-05, + "loss": 3.9444, + "step": 1442816 + }, + { + "epoch": 0.02, + "learning_rate": 2.6368350778943153e-05, + "loss": 3.9375, + "step": 1443328 + }, + { + "epoch": 0.02, + "learning_rate": 2.6359964831432626e-05, + "loss": 3.939, + "step": 1443840 + }, + { + "epoch": 0.02, + "learning_rate": 2.6351578883922106e-05, + "loss": 3.9488, + "step": 1444352 + }, + { + "epoch": 0.02, + "learning_rate": 2.6343209315215322e-05, + "loss": 3.9397, + "step": 1444864 + }, + { + "epoch": 0.02, + "learning_rate": 2.6334823367704802e-05, + "loss": 3.9562, + "step": 1445376 + }, + { + "epoch": 0.02, + "learning_rate": 2.632643742019428e-05, + "loss": 3.9324, + "step": 1445888 + }, + { + "epoch": 0.02, + "learning_rate": 2.631805147268376e-05, + "loss": 3.9426, + "step": 1446400 + }, + { + "epoch": 0.02, + "learning_rate": 2.630966552517324e-05, + "loss": 3.9392, + "step": 1446912 + }, + { + "epoch": 0.02, + "learning_rate": 2.6301295956466448e-05, + "loss": 3.9359, + "step": 1447424 + }, + { + "epoch": 0.02, + "learning_rate": 2.6292910008955928e-05, + "loss": 3.9365, + "step": 1447936 + }, + { + "epoch": 0.02, + "learning_rate": 2.6284524061445408e-05, + "loss": 3.9347, + "step": 1448448 + }, + { + "epoch": 0.02, + "learning_rate": 2.627613811393489e-05, + "loss": 3.933, + "step": 1448960 + }, + { + "epoch": 0.02, + "learning_rate": 2.6267784924031836e-05, + "loss": 3.9372, + "step": 1449472 + }, + { + "epoch": 0.02, + "learning_rate": 2.6259398976521316e-05, + "loss": 3.9354, + "step": 1449984 + }, + { + "epoch": 0.03, + "eval_loss": 4.013299465179443, + "eval_runtime": 295.3219, + "eval_samples_per_second": 1292.119, + "eval_steps_per_second": 40.38, + "step": 1450080 + }, + { + "epoch": 1.0, + "learning_rate": 2.6251013029010796e-05, + "loss": 3.9386, + "step": 1450496 + }, + { + "epoch": 1.0, + "learning_rate": 2.6242643460304005e-05, + "loss": 3.9333, + "step": 1451008 + }, + { + "epoch": 1.0, + "learning_rate": 2.6234257512793485e-05, + "loss": 3.9461, + "step": 1451520 + }, + { + "epoch": 1.0, + "learning_rate": 2.6225871565282968e-05, + "loss": 3.9392, + "step": 1452032 + }, + { + "epoch": 1.0, + "learning_rate": 2.6217485617772448e-05, + "loss": 3.9573, + "step": 1452544 + }, + { + "epoch": 1.0, + "learning_rate": 2.620909967026192e-05, + "loss": 3.9345, + "step": 1453056 + }, + { + "epoch": 1.0, + "learning_rate": 2.62007137227514e-05, + "loss": 3.9382, + "step": 1453568 + }, + { + "epoch": 1.0, + "learning_rate": 2.619232777524088e-05, + "loss": 3.9267, + "step": 1454080 + }, + { + "epoch": 1.0, + "learning_rate": 2.618394182773036e-05, + "loss": 3.9397, + "step": 1454592 + }, + { + "epoch": 1.0, + "learning_rate": 2.6175555880219845e-05, + "loss": 3.9416, + "step": 1455104 + }, + { + "epoch": 1.0, + "learning_rate": 2.6167169932709325e-05, + "loss": 3.9356, + "step": 1455616 + }, + { + "epoch": 1.0, + "learning_rate": 2.6158783985198805e-05, + "loss": 3.9421, + "step": 1456128 + }, + { + "epoch": 1.0, + "learning_rate": 2.6150414416492014e-05, + "loss": 3.931, + "step": 1456640 + }, + { + "epoch": 1.0, + "learning_rate": 2.6142028468981494e-05, + "loss": 3.9404, + "step": 1457152 + }, + { + "epoch": 1.0, + "learning_rate": 2.6133642521470974e-05, + "loss": 3.9299, + "step": 1457664 + }, + { + "epoch": 1.0, + "learning_rate": 2.6125256573960454e-05, + "loss": 3.9285, + "step": 1458176 + }, + { + "epoch": 1.0, + "learning_rate": 2.6116870626449937e-05, + "loss": 3.9298, + "step": 1458688 + }, + { + "epoch": 1.0, + "learning_rate": 2.6108484678939417e-05, + "loss": 3.9358, + "step": 1459200 + }, + { + "epoch": 1.0, + "learning_rate": 2.6100098731428897e-05, + "loss": 3.9379, + "step": 1459712 + }, + { + "epoch": 1.0, + "learning_rate": 2.6091712783918377e-05, + "loss": 3.954, + "step": 1460224 + }, + { + "epoch": 1.0, + "learning_rate": 2.6083343215211586e-05, + "loss": 3.9378, + "step": 1460736 + }, + { + "epoch": 1.0, + "learning_rate": 2.6074973646504798e-05, + "loss": 3.9438, + "step": 1461248 + }, + { + "epoch": 1.0, + "learning_rate": 2.6066587698994278e-05, + "loss": 3.9355, + "step": 1461760 + }, + { + "epoch": 1.0, + "learning_rate": 2.6058201751483758e-05, + "loss": 3.9425, + "step": 1462272 + }, + { + "epoch": 1.0, + "learning_rate": 2.6049815803973238e-05, + "loss": 3.9387, + "step": 1462784 + }, + { + "epoch": 1.0, + "learning_rate": 2.6041429856462718e-05, + "loss": 3.9415, + "step": 1463296 + }, + { + "epoch": 1.0, + "learning_rate": 2.6033060287755927e-05, + "loss": 3.9316, + "step": 1463808 + }, + { + "epoch": 1.0, + "learning_rate": 2.6024674340245407e-05, + "loss": 3.9288, + "step": 1464320 + }, + { + "epoch": 1.0, + "learning_rate": 2.6016288392734887e-05, + "loss": 3.93, + "step": 1464832 + }, + { + "epoch": 1.01, + "learning_rate": 2.600790244522437e-05, + "loss": 3.939, + "step": 1465344 + }, + { + "epoch": 1.01, + "learning_rate": 2.599951649771385e-05, + "loss": 3.9409, + "step": 1465856 + }, + { + "epoch": 1.01, + "learning_rate": 2.599114692900706e-05, + "loss": 3.9396, + "step": 1466368 + }, + { + "epoch": 1.01, + "learning_rate": 2.598276098149654e-05, + "loss": 3.9486, + "step": 1466880 + }, + { + "epoch": 1.01, + "learning_rate": 2.597437503398602e-05, + "loss": 3.9394, + "step": 1467392 + }, + { + "epoch": 1.01, + "learning_rate": 2.5966005465279232e-05, + "loss": 3.9348, + "step": 1467904 + }, + { + "epoch": 1.01, + "learning_rate": 2.5957619517768712e-05, + "loss": 3.9398, + "step": 1468416 + }, + { + "epoch": 1.01, + "learning_rate": 2.5949233570258192e-05, + "loss": 3.9398, + "step": 1468928 + }, + { + "epoch": 1.01, + "learning_rate": 2.5940847622747672e-05, + "loss": 3.9279, + "step": 1469440 + }, + { + "epoch": 1.01, + "learning_rate": 2.5932461675237152e-05, + "loss": 3.9215, + "step": 1469952 + }, + { + "epoch": 1.01, + "learning_rate": 2.5924075727726632e-05, + "loss": 3.9274, + "step": 1470464 + }, + { + "epoch": 1.01, + "learning_rate": 2.591568978021611e-05, + "loss": 3.9374, + "step": 1470976 + }, + { + "epoch": 1.01, + "learning_rate": 2.5907303832705588e-05, + "loss": 3.9396, + "step": 1471488 + }, + { + "epoch": 1.01, + "learning_rate": 2.5898917885195068e-05, + "loss": 3.9362, + "step": 1472000 + }, + { + "epoch": 1.01, + "learning_rate": 2.5890531937684548e-05, + "loss": 3.9231, + "step": 1472512 + }, + { + "epoch": 1.01, + "learning_rate": 2.5882162368977757e-05, + "loss": 3.9406, + "step": 1473024 + }, + { + "epoch": 1.01, + "learning_rate": 2.5873776421467237e-05, + "loss": 3.9352, + "step": 1473536 + }, + { + "epoch": 1.01, + "learning_rate": 2.5865390473956717e-05, + "loss": 3.9327, + "step": 1474048 + }, + { + "epoch": 1.01, + "learning_rate": 2.58570045264462e-05, + "loss": 3.9271, + "step": 1474560 + }, + { + "epoch": 1.01, + "learning_rate": 2.584861857893568e-05, + "loss": 3.9144, + "step": 1475072 + }, + { + "epoch": 1.01, + "learning_rate": 2.584023263142516e-05, + "loss": 3.9565, + "step": 1475584 + }, + { + "epoch": 1.01, + "learning_rate": 2.583184668391464e-05, + "loss": 3.9426, + "step": 1476096 + }, + { + "epoch": 1.01, + "learning_rate": 2.582346073640412e-05, + "loss": 3.9319, + "step": 1476608 + }, + { + "epoch": 1.01, + "learning_rate": 2.581509116769733e-05, + "loss": 3.9356, + "step": 1477120 + }, + { + "epoch": 1.01, + "learning_rate": 2.5806721598990542e-05, + "loss": 3.9361, + "step": 1477632 + }, + { + "epoch": 1.01, + "learning_rate": 2.5798335651480022e-05, + "loss": 3.926, + "step": 1478144 + }, + { + "epoch": 1.01, + "learning_rate": 2.5789949703969502e-05, + "loss": 3.941, + "step": 1478656 + }, + { + "epoch": 1.01, + "learning_rate": 2.5781563756458982e-05, + "loss": 3.9235, + "step": 1479168 + }, + { + "epoch": 1.01, + "learning_rate": 2.5773177808948462e-05, + "loss": 3.94, + "step": 1479680 + }, + { + "epoch": 1.01, + "learning_rate": 2.576479186143794e-05, + "loss": 3.9485, + "step": 1480192 + }, + { + "epoch": 1.01, + "learning_rate": 2.575640591392742e-05, + "loss": 3.9294, + "step": 1480704 + }, + { + "epoch": 1.01, + "learning_rate": 2.57480199664169e-05, + "loss": 3.9191, + "step": 1481216 + }, + { + "epoch": 1.01, + "learning_rate": 2.5739634018906385e-05, + "loss": 3.9465, + "step": 1481728 + }, + { + "epoch": 1.01, + "learning_rate": 2.5731264450199594e-05, + "loss": 3.9133, + "step": 1482240 + }, + { + "epoch": 1.01, + "learning_rate": 2.5722878502689074e-05, + "loss": 3.9249, + "step": 1482752 + }, + { + "epoch": 1.01, + "learning_rate": 2.5714492555178554e-05, + "loss": 3.9418, + "step": 1483264 + }, + { + "epoch": 1.01, + "learning_rate": 2.5706106607668034e-05, + "loss": 3.9374, + "step": 1483776 + }, + { + "epoch": 1.01, + "learning_rate": 2.5697737038961246e-05, + "loss": 3.9308, + "step": 1484288 + }, + { + "epoch": 1.01, + "learning_rate": 2.5689351091450726e-05, + "loss": 3.9243, + "step": 1484800 + }, + { + "epoch": 1.01, + "learning_rate": 2.5680965143940206e-05, + "loss": 3.9158, + "step": 1485312 + }, + { + "epoch": 1.01, + "learning_rate": 2.5672579196429686e-05, + "loss": 3.9245, + "step": 1485824 + }, + { + "epoch": 1.01, + "learning_rate": 2.5664209627722895e-05, + "loss": 3.9399, + "step": 1486336 + }, + { + "epoch": 1.01, + "learning_rate": 2.5655823680212375e-05, + "loss": 3.9243, + "step": 1486848 + }, + { + "epoch": 1.01, + "learning_rate": 2.5647437732701855e-05, + "loss": 3.9407, + "step": 1487360 + }, + { + "epoch": 1.01, + "learning_rate": 2.563905178519134e-05, + "loss": 3.9357, + "step": 1487872 + }, + { + "epoch": 1.01, + "learning_rate": 2.563066583768082e-05, + "loss": 3.9469, + "step": 1488384 + }, + { + "epoch": 1.01, + "learning_rate": 2.5622296268974028e-05, + "loss": 3.9278, + "step": 1488896 + }, + { + "epoch": 1.01, + "learning_rate": 2.5613926700267237e-05, + "loss": 3.9279, + "step": 1489408 + }, + { + "epoch": 1.01, + "learning_rate": 2.5605540752756717e-05, + "loss": 3.9405, + "step": 1489920 + }, + { + "epoch": 1.01, + "learning_rate": 2.55971548052462e-05, + "loss": 3.9272, + "step": 1490432 + }, + { + "epoch": 1.01, + "learning_rate": 2.558876885773568e-05, + "loss": 3.9383, + "step": 1490944 + }, + { + "epoch": 1.01, + "learning_rate": 2.558038291022516e-05, + "loss": 3.9299, + "step": 1491456 + }, + { + "epoch": 1.01, + "learning_rate": 2.557199696271464e-05, + "loss": 3.9321, + "step": 1491968 + }, + { + "epoch": 1.01, + "learning_rate": 2.556362739400785e-05, + "loss": 3.9362, + "step": 1492480 + }, + { + "epoch": 1.01, + "learning_rate": 2.555524144649733e-05, + "loss": 3.9204, + "step": 1492992 + }, + { + "epoch": 1.01, + "learning_rate": 2.554685549898681e-05, + "loss": 3.9306, + "step": 1493504 + }, + { + "epoch": 1.01, + "learning_rate": 2.5538469551476292e-05, + "loss": 3.9304, + "step": 1494016 + }, + { + "epoch": 1.01, + "learning_rate": 2.55300999827695e-05, + "loss": 3.9357, + "step": 1494528 + }, + { + "epoch": 1.01, + "learning_rate": 2.552171403525898e-05, + "loss": 3.9298, + "step": 1495040 + }, + { + "epoch": 1.01, + "learning_rate": 2.551332808774846e-05, + "loss": 3.9303, + "step": 1495552 + }, + { + "epoch": 1.02, + "learning_rate": 2.550494214023794e-05, + "loss": 3.925, + "step": 1496064 + }, + { + "epoch": 1.02, + "learning_rate": 2.5496572571531154e-05, + "loss": 3.9228, + "step": 1496576 + }, + { + "epoch": 1.02, + "learning_rate": 2.5488186624020634e-05, + "loss": 3.9239, + "step": 1497088 + }, + { + "epoch": 1.02, + "learning_rate": 2.5479800676510114e-05, + "loss": 3.9311, + "step": 1497600 + }, + { + "epoch": 1.02, + "learning_rate": 2.5471414728999594e-05, + "loss": 3.9422, + "step": 1498112 + }, + { + "epoch": 1.02, + "learning_rate": 2.5463028781489067e-05, + "loss": 3.9383, + "step": 1498624 + }, + { + "epoch": 1.02, + "learning_rate": 2.5454642833978547e-05, + "loss": 3.9329, + "step": 1499136 + }, + { + "epoch": 1.02, + "learning_rate": 2.5446273265271763e-05, + "loss": 3.9233, + "step": 1499648 + }, + { + "epoch": 1.02, + "learning_rate": 2.5437887317761243e-05, + "loss": 3.9289, + "step": 1500160 + }, + { + "epoch": 1.02, + "learning_rate": 2.542950137025072e-05, + "loss": 3.9336, + "step": 1500672 + }, + { + "epoch": 1.02, + "learning_rate": 2.54211154227402e-05, + "loss": 3.9391, + "step": 1501184 + }, + { + "epoch": 1.02, + "learning_rate": 2.541272947522968e-05, + "loss": 3.9365, + "step": 1501696 + }, + { + "epoch": 1.02, + "learning_rate": 2.540434352771916e-05, + "loss": 3.9302, + "step": 1502208 + }, + { + "epoch": 1.02, + "learning_rate": 2.539595758020864e-05, + "loss": 3.9228, + "step": 1502720 + }, + { + "epoch": 1.02, + "learning_rate": 2.538757163269812e-05, + "loss": 3.9455, + "step": 1503232 + }, + { + "epoch": 1.02, + "learning_rate": 2.537920206399133e-05, + "loss": 3.9141, + "step": 1503744 + }, + { + "epoch": 1.02, + "learning_rate": 2.537083249528454e-05, + "loss": 3.9352, + "step": 1504256 + }, + { + "epoch": 1.02, + "learning_rate": 2.536244654777402e-05, + "loss": 3.9251, + "step": 1504768 + }, + { + "epoch": 1.02, + "learning_rate": 2.53540606002635e-05, + "loss": 3.9324, + "step": 1505280 + }, + { + "epoch": 1.02, + "learning_rate": 2.5345674652752984e-05, + "loss": 3.9215, + "step": 1505792 + }, + { + "epoch": 1.02, + "learning_rate": 2.5337288705242464e-05, + "loss": 3.9321, + "step": 1506304 + }, + { + "epoch": 1.02, + "learning_rate": 2.5328902757731944e-05, + "loss": 3.9233, + "step": 1506816 + }, + { + "epoch": 1.02, + "learning_rate": 2.5320533189025153e-05, + "loss": 3.9233, + "step": 1507328 + }, + { + "epoch": 1.02, + "learning_rate": 2.5312147241514633e-05, + "loss": 3.9315, + "step": 1507840 + }, + { + "epoch": 1.02, + "learning_rate": 2.5303761294004113e-05, + "loss": 3.9239, + "step": 1508352 + }, + { + "epoch": 1.02, + "learning_rate": 2.5295375346493593e-05, + "loss": 3.9426, + "step": 1508864 + }, + { + "epoch": 1.02, + "learning_rate": 2.5286989398983073e-05, + "loss": 3.9447, + "step": 1509376 + }, + { + "epoch": 1.02, + "learning_rate": 2.5278603451472556e-05, + "loss": 3.9379, + "step": 1509888 + }, + { + "epoch": 1.02, + "learning_rate": 2.5270217503962036e-05, + "loss": 3.9267, + "step": 1510400 + }, + { + "epoch": 1.02, + "learning_rate": 2.5261831556451516e-05, + "loss": 3.9267, + "step": 1510912 + }, + { + "epoch": 1.02, + "learning_rate": 2.5253445608940996e-05, + "loss": 3.9244, + "step": 1511424 + }, + { + "epoch": 1.02, + "learning_rate": 2.5245076040234205e-05, + "loss": 3.9256, + "step": 1511936 + }, + { + "epoch": 1.02, + "learning_rate": 2.5236706471527417e-05, + "loss": 3.9379, + "step": 1512448 + }, + { + "epoch": 1.02, + "learning_rate": 2.5228320524016897e-05, + "loss": 3.9151, + "step": 1512960 + }, + { + "epoch": 1.02, + "learning_rate": 2.5219934576506377e-05, + "loss": 3.934, + "step": 1513472 + }, + { + "epoch": 1.02, + "learning_rate": 2.5211548628995857e-05, + "loss": 3.9313, + "step": 1513984 + }, + { + "epoch": 1.02, + "learning_rate": 2.5203162681485337e-05, + "loss": 3.9351, + "step": 1514496 + }, + { + "epoch": 1.02, + "learning_rate": 2.5194793112778546e-05, + "loss": 3.9239, + "step": 1515008 + }, + { + "epoch": 1.02, + "learning_rate": 2.5186407165268026e-05, + "loss": 3.9287, + "step": 1515520 + }, + { + "epoch": 1.02, + "learning_rate": 2.517802121775751e-05, + "loss": 3.9257, + "step": 1516032 + }, + { + "epoch": 1.02, + "learning_rate": 2.516963527024699e-05, + "loss": 3.9408, + "step": 1516544 + }, + { + "epoch": 1.02, + "learning_rate": 2.516124932273647e-05, + "loss": 3.9343, + "step": 1517056 + }, + { + "epoch": 1.02, + "learning_rate": 2.515286337522595e-05, + "loss": 3.9428, + "step": 1517568 + }, + { + "epoch": 1.02, + "learning_rate": 2.514449380651916e-05, + "loss": 3.9186, + "step": 1518080 + }, + { + "epoch": 1.02, + "learning_rate": 2.513610785900864e-05, + "loss": 3.9375, + "step": 1518592 + }, + { + "epoch": 1.02, + "learning_rate": 2.512772191149812e-05, + "loss": 3.9376, + "step": 1519104 + }, + { + "epoch": 1.02, + "learning_rate": 2.511935234279133e-05, + "loss": 3.9229, + "step": 1519616 + }, + { + "epoch": 1.02, + "learning_rate": 2.511096639528081e-05, + "loss": 3.932, + "step": 1520128 + }, + { + "epoch": 1.02, + "learning_rate": 2.510258044777029e-05, + "loss": 3.9419, + "step": 1520640 + }, + { + "epoch": 1.02, + "learning_rate": 2.509419450025977e-05, + "loss": 3.934, + "step": 1521152 + }, + { + "epoch": 1.02, + "learning_rate": 2.508580855274925e-05, + "loss": 3.9488, + "step": 1521664 + }, + { + "epoch": 1.02, + "learning_rate": 2.5077422605238727e-05, + "loss": 3.9245, + "step": 1522176 + }, + { + "epoch": 1.02, + "learning_rate": 2.5069036657728207e-05, + "loss": 3.9389, + "step": 1522688 + }, + { + "epoch": 1.02, + "learning_rate": 2.5060650710217687e-05, + "loss": 3.9279, + "step": 1523200 + }, + { + "epoch": 1.02, + "learning_rate": 2.5052264762707167e-05, + "loss": 3.9299, + "step": 1523712 + }, + { + "epoch": 1.02, + "learning_rate": 2.5043878815196647e-05, + "loss": 3.9284, + "step": 1524224 + }, + { + "epoch": 1.02, + "learning_rate": 2.5035492867686127e-05, + "loss": 3.9283, + "step": 1524736 + }, + { + "epoch": 1.02, + "learning_rate": 2.5027106920175607e-05, + "loss": 3.9237, + "step": 1525248 + }, + { + "epoch": 1.02, + "learning_rate": 2.501875373027255e-05, + "loss": 3.9262, + "step": 1525760 + }, + { + "epoch": 1.02, + "learning_rate": 2.501036778276203e-05, + "loss": 3.927, + "step": 1526272 + }, + { + "epoch": 1.03, + "eval_loss": 4.009834289550781, + "eval_runtime": 293.7762, + "eval_samples_per_second": 1298.917, + "eval_steps_per_second": 40.592, + "step": 1526400 + }, + { + "epoch": 0.0, + "learning_rate": 2.500198183525151e-05, + "loss": 3.9292, + "step": 1526784 + }, + { + "epoch": 0.0, + "learning_rate": 2.4993595887740992e-05, + "loss": 3.9251, + "step": 1527296 + }, + { + "epoch": 0.0, + "learning_rate": 2.498520994023047e-05, + "loss": 3.9401, + "step": 1527808 + }, + { + "epoch": 0.0, + "learning_rate": 2.497682399271995e-05, + "loss": 3.9309, + "step": 1528320 + }, + { + "epoch": 0.0, + "learning_rate": 2.4968438045209432e-05, + "loss": 3.946, + "step": 1528832 + }, + { + "epoch": 0.0, + "learning_rate": 2.4960052097698912e-05, + "loss": 3.9313, + "step": 1529344 + }, + { + "epoch": 0.0, + "learning_rate": 2.4951666150188392e-05, + "loss": 3.9276, + "step": 1529856 + }, + { + "epoch": 0.0, + "learning_rate": 2.494328020267787e-05, + "loss": 3.9205, + "step": 1530368 + }, + { + "epoch": 0.0, + "learning_rate": 2.4934894255167348e-05, + "loss": 3.9304, + "step": 1530880 + }, + { + "epoch": 0.0, + "learning_rate": 2.4926508307656828e-05, + "loss": 3.9329, + "step": 1531392 + }, + { + "epoch": 0.0, + "learning_rate": 2.4918122360146308e-05, + "loss": 3.9297, + "step": 1531904 + }, + { + "epoch": 0.0, + "learning_rate": 2.4909736412635788e-05, + "loss": 3.932, + "step": 1532416 + }, + { + "epoch": 0.0, + "learning_rate": 2.4901366843929e-05, + "loss": 3.924, + "step": 1532928 + }, + { + "epoch": 0.0, + "learning_rate": 2.489298089641848e-05, + "loss": 3.9347, + "step": 1533440 + }, + { + "epoch": 0.0, + "learning_rate": 2.488459494890796e-05, + "loss": 3.9207, + "step": 1533952 + }, + { + "epoch": 0.0, + "learning_rate": 2.487620900139744e-05, + "loss": 3.9195, + "step": 1534464 + }, + { + "epoch": 0.0, + "learning_rate": 2.486782305388692e-05, + "loss": 3.9226, + "step": 1534976 + }, + { + "epoch": 0.0, + "learning_rate": 2.48594371063764e-05, + "loss": 3.9316, + "step": 1535488 + }, + { + "epoch": 0.0, + "learning_rate": 2.4851067537669613e-05, + "loss": 3.9289, + "step": 1536000 + }, + { + "epoch": 0.0, + "learning_rate": 2.4842681590159093e-05, + "loss": 3.9447, + "step": 1536512 + }, + { + "epoch": 0.0, + "learning_rate": 2.4834295642648573e-05, + "loss": 3.9314, + "step": 1537024 + }, + { + "epoch": 0.0, + "learning_rate": 2.4825909695138053e-05, + "loss": 3.9395, + "step": 1537536 + }, + { + "epoch": 0.0, + "learning_rate": 2.481752374762753e-05, + "loss": 3.925, + "step": 1538048 + }, + { + "epoch": 0.0, + "learning_rate": 2.480913780011701e-05, + "loss": 3.9316, + "step": 1538560 + }, + { + "epoch": 0.0, + "learning_rate": 2.480075185260649e-05, + "loss": 3.9301, + "step": 1539072 + }, + { + "epoch": 0.0, + "learning_rate": 2.4792365905095973e-05, + "loss": 3.9354, + "step": 1539584 + }, + { + "epoch": 0.0, + "learning_rate": 2.4783979957585452e-05, + "loss": 3.9252, + "step": 1540096 + }, + { + "epoch": 0.0, + "learning_rate": 2.4775594010074932e-05, + "loss": 3.9257, + "step": 1540608 + }, + { + "epoch": 0.0, + "learning_rate": 2.4767208062564412e-05, + "loss": 3.9213, + "step": 1541120 + }, + { + "epoch": 0.0, + "learning_rate": 2.475883849385762e-05, + "loss": 3.9279, + "step": 1541632 + }, + { + "epoch": 0.01, + "learning_rate": 2.4750468925150834e-05, + "loss": 3.9348, + "step": 1542144 + }, + { + "epoch": 0.01, + "learning_rate": 2.4742082977640314e-05, + "loss": 3.9329, + "step": 1542656 + }, + { + "epoch": 0.01, + "learning_rate": 2.4733697030129794e-05, + "loss": 3.9376, + "step": 1543168 + }, + { + "epoch": 0.01, + "learning_rate": 2.4725311082619274e-05, + "loss": 3.9292, + "step": 1543680 + }, + { + "epoch": 0.01, + "learning_rate": 2.4716925135108754e-05, + "loss": 3.9281, + "step": 1544192 + }, + { + "epoch": 0.01, + "learning_rate": 2.4708555566401963e-05, + "loss": 3.9376, + "step": 1544704 + }, + { + "epoch": 0.01, + "learning_rate": 2.4700169618891443e-05, + "loss": 3.9339, + "step": 1545216 + }, + { + "epoch": 0.01, + "learning_rate": 2.4691783671380926e-05, + "loss": 3.9155, + "step": 1545728 + }, + { + "epoch": 0.01, + "learning_rate": 2.4683397723870406e-05, + "loss": 3.9182, + "step": 1546240 + }, + { + "epoch": 0.01, + "learning_rate": 2.4675028155163615e-05, + "loss": 3.9182, + "step": 1546752 + }, + { + "epoch": 0.01, + "learning_rate": 2.4666642207653095e-05, + "loss": 3.9247, + "step": 1547264 + }, + { + "epoch": 0.01, + "learning_rate": 2.4658272638946304e-05, + "loss": 3.9346, + "step": 1547776 + }, + { + "epoch": 0.01, + "learning_rate": 2.4649886691435788e-05, + "loss": 3.9241, + "step": 1548288 + }, + { + "epoch": 0.01, + "learning_rate": 2.4641500743925268e-05, + "loss": 3.9212, + "step": 1548800 + }, + { + "epoch": 0.01, + "learning_rate": 2.4633114796414748e-05, + "loss": 3.9292, + "step": 1549312 + }, + { + "epoch": 0.01, + "learning_rate": 2.4624728848904228e-05, + "loss": 3.9253, + "step": 1549824 + }, + { + "epoch": 0.01, + "learning_rate": 2.4616342901393707e-05, + "loss": 3.9278, + "step": 1550336 + }, + { + "epoch": 0.01, + "learning_rate": 2.4607956953883184e-05, + "loss": 3.922, + "step": 1550848 + }, + { + "epoch": 0.01, + "learning_rate": 2.4599571006372664e-05, + "loss": 3.9019, + "step": 1551360 + }, + { + "epoch": 0.01, + "learning_rate": 2.4591185058862144e-05, + "loss": 3.9503, + "step": 1551872 + }, + { + "epoch": 0.01, + "learning_rate": 2.4582799111351627e-05, + "loss": 3.9333, + "step": 1552384 + }, + { + "epoch": 0.01, + "learning_rate": 2.4574413163841107e-05, + "loss": 3.9314, + "step": 1552896 + }, + { + "epoch": 0.01, + "learning_rate": 2.4566027216330587e-05, + "loss": 3.9266, + "step": 1553408 + }, + { + "epoch": 0.01, + "learning_rate": 2.4557657647623796e-05, + "loss": 3.9256, + "step": 1553920 + }, + { + "epoch": 0.01, + "learning_rate": 2.4549271700113276e-05, + "loss": 3.9193, + "step": 1554432 + }, + { + "epoch": 0.01, + "learning_rate": 2.454090213140649e-05, + "loss": 3.9298, + "step": 1554944 + }, + { + "epoch": 0.01, + "learning_rate": 2.453251618389597e-05, + "loss": 3.9199, + "step": 1555456 + }, + { + "epoch": 0.01, + "learning_rate": 2.452413023638545e-05, + "loss": 3.9286, + "step": 1555968 + }, + { + "epoch": 0.01, + "learning_rate": 2.451574428887493e-05, + "loss": 3.9402, + "step": 1556480 + }, + { + "epoch": 0.01, + "learning_rate": 2.450735834136441e-05, + "loss": 3.9207, + "step": 1556992 + }, + { + "epoch": 0.01, + "learning_rate": 2.449897239385389e-05, + "loss": 3.9137, + "step": 1557504 + }, + { + "epoch": 0.01, + "learning_rate": 2.4490586446343365e-05, + "loss": 3.9356, + "step": 1558016 + }, + { + "epoch": 0.01, + "learning_rate": 2.448220049883285e-05, + "loss": 3.9061, + "step": 1558528 + }, + { + "epoch": 0.01, + "learning_rate": 2.447381455132233e-05, + "loss": 3.9193, + "step": 1559040 + }, + { + "epoch": 0.01, + "learning_rate": 2.446542860381181e-05, + "loss": 3.9289, + "step": 1559552 + }, + { + "epoch": 0.01, + "learning_rate": 2.445707541390875e-05, + "loss": 3.9293, + "step": 1560064 + }, + { + "epoch": 0.01, + "learning_rate": 2.444868946639823e-05, + "loss": 3.9228, + "step": 1560576 + }, + { + "epoch": 0.01, + "learning_rate": 2.444030351888771e-05, + "loss": 3.9195, + "step": 1561088 + }, + { + "epoch": 0.01, + "learning_rate": 2.443191757137719e-05, + "loss": 3.9066, + "step": 1561600 + }, + { + "epoch": 0.01, + "learning_rate": 2.442353162386667e-05, + "loss": 3.9184, + "step": 1562112 + }, + { + "epoch": 0.01, + "learning_rate": 2.4415162055159882e-05, + "loss": 3.9305, + "step": 1562624 + }, + { + "epoch": 0.01, + "learning_rate": 2.4406776107649362e-05, + "loss": 3.9186, + "step": 1563136 + }, + { + "epoch": 0.01, + "learning_rate": 2.439840653894257e-05, + "loss": 3.9276, + "step": 1563648 + }, + { + "epoch": 0.01, + "learning_rate": 2.439002059143205e-05, + "loss": 3.9296, + "step": 1564160 + }, + { + "epoch": 0.01, + "learning_rate": 2.4381634643921535e-05, + "loss": 3.9411, + "step": 1564672 + }, + { + "epoch": 0.01, + "learning_rate": 2.4373248696411015e-05, + "loss": 3.9203, + "step": 1565184 + }, + { + "epoch": 0.01, + "learning_rate": 2.436486274890049e-05, + "loss": 3.918, + "step": 1565696 + }, + { + "epoch": 0.01, + "learning_rate": 2.435647680138997e-05, + "loss": 3.9326, + "step": 1566208 + }, + { + "epoch": 0.01, + "learning_rate": 2.434809085387945e-05, + "loss": 3.9174, + "step": 1566720 + }, + { + "epoch": 0.01, + "learning_rate": 2.433970490636893e-05, + "loss": 3.9348, + "step": 1567232 + }, + { + "epoch": 0.01, + "learning_rate": 2.433131895885841e-05, + "loss": 3.9222, + "step": 1567744 + }, + { + "epoch": 0.01, + "learning_rate": 2.432293301134789e-05, + "loss": 3.9238, + "step": 1568256 + }, + { + "epoch": 0.01, + "learning_rate": 2.431454706383737e-05, + "loss": 3.9303, + "step": 1568768 + }, + { + "epoch": 0.01, + "learning_rate": 2.430616111632685e-05, + "loss": 3.9133, + "step": 1569280 + }, + { + "epoch": 0.01, + "learning_rate": 2.429777516881633e-05, + "loss": 3.9225, + "step": 1569792 + }, + { + "epoch": 0.01, + "learning_rate": 2.4289405600109543e-05, + "loss": 3.9204, + "step": 1570304 + }, + { + "epoch": 0.01, + "learning_rate": 2.428101965259902e-05, + "loss": 3.9286, + "step": 1570816 + }, + { + "epoch": 0.01, + "learning_rate": 2.4272633705088503e-05, + "loss": 3.9173, + "step": 1571328 + }, + { + "epoch": 0.01, + "learning_rate": 2.4264247757577983e-05, + "loss": 3.9252, + "step": 1571840 + }, + { + "epoch": 0.02, + "learning_rate": 2.4255878188871196e-05, + "loss": 3.917, + "step": 1572352 + }, + { + "epoch": 0.02, + "learning_rate": 2.4247492241360672e-05, + "loss": 3.9177, + "step": 1572864 + }, + { + "epoch": 0.02, + "learning_rate": 2.4239106293850152e-05, + "loss": 3.9117, + "step": 1573376 + }, + { + "epoch": 0.02, + "learning_rate": 2.4230736725143365e-05, + "loss": 3.9261, + "step": 1573888 + }, + { + "epoch": 0.02, + "learning_rate": 2.4222350777632845e-05, + "loss": 3.9357, + "step": 1574400 + }, + { + "epoch": 0.02, + "learning_rate": 2.4213964830122325e-05, + "loss": 3.926, + "step": 1574912 + }, + { + "epoch": 0.02, + "learning_rate": 2.4205578882611804e-05, + "loss": 3.9301, + "step": 1575424 + }, + { + "epoch": 0.02, + "learning_rate": 2.4197192935101284e-05, + "loss": 3.9153, + "step": 1575936 + }, + { + "epoch": 0.02, + "learning_rate": 2.4188806987590764e-05, + "loss": 3.9198, + "step": 1576448 + }, + { + "epoch": 0.02, + "learning_rate": 2.4180437418883974e-05, + "loss": 3.9243, + "step": 1576960 + }, + { + "epoch": 0.02, + "learning_rate": 2.4172051471373457e-05, + "loss": 3.9315, + "step": 1577472 + }, + { + "epoch": 0.02, + "learning_rate": 2.4163665523862937e-05, + "loss": 3.9281, + "step": 1577984 + }, + { + "epoch": 0.02, + "learning_rate": 2.4155295955156146e-05, + "loss": 3.9216, + "step": 1578496 + }, + { + "epoch": 0.02, + "learning_rate": 2.4146910007645626e-05, + "loss": 3.9194, + "step": 1579008 + }, + { + "epoch": 0.02, + "learning_rate": 2.4138524060135106e-05, + "loss": 3.9372, + "step": 1579520 + }, + { + "epoch": 0.02, + "learning_rate": 2.4130138112624586e-05, + "loss": 3.9097, + "step": 1580032 + }, + { + "epoch": 0.02, + "learning_rate": 2.4121752165114066e-05, + "loss": 3.9257, + "step": 1580544 + }, + { + "epoch": 0.02, + "learning_rate": 2.411336621760355e-05, + "loss": 3.9163, + "step": 1581056 + }, + { + "epoch": 0.02, + "learning_rate": 2.4104980270093026e-05, + "loss": 3.9262, + "step": 1581568 + }, + { + "epoch": 0.02, + "learning_rate": 2.4096594322582506e-05, + "loss": 3.9147, + "step": 1582080 + }, + { + "epoch": 0.02, + "learning_rate": 2.4088208375071986e-05, + "loss": 3.9239, + "step": 1582592 + }, + { + "epoch": 0.02, + "learning_rate": 2.4079822427561466e-05, + "loss": 3.9151, + "step": 1583104 + }, + { + "epoch": 0.02, + "learning_rate": 2.4071452858854675e-05, + "loss": 3.9181, + "step": 1583616 + }, + { + "epoch": 0.02, + "learning_rate": 2.4063066911344158e-05, + "loss": 3.9233, + "step": 1584128 + }, + { + "epoch": 0.02, + "learning_rate": 2.4054680963833638e-05, + "loss": 3.9182, + "step": 1584640 + }, + { + "epoch": 0.02, + "learning_rate": 2.4046295016323118e-05, + "loss": 3.9313, + "step": 1585152 + }, + { + "epoch": 0.02, + "learning_rate": 2.4037909068812598e-05, + "loss": 3.9374, + "step": 1585664 + }, + { + "epoch": 0.02, + "learning_rate": 2.4029523121302078e-05, + "loss": 3.9266, + "step": 1586176 + }, + { + "epoch": 0.02, + "learning_rate": 2.4021137173791554e-05, + "loss": 3.9245, + "step": 1586688 + }, + { + "epoch": 0.02, + "learning_rate": 2.4012751226281034e-05, + "loss": 3.914, + "step": 1587200 + }, + { + "epoch": 0.02, + "learning_rate": 2.400438165757425e-05, + "loss": 3.9191, + "step": 1587712 + }, + { + "epoch": 0.02, + "learning_rate": 2.399599571006373e-05, + "loss": 3.92, + "step": 1588224 + }, + { + "epoch": 0.02, + "learning_rate": 2.3987609762553207e-05, + "loss": 3.9348, + "step": 1588736 + }, + { + "epoch": 0.02, + "learning_rate": 2.3979223815042687e-05, + "loss": 3.9055, + "step": 1589248 + }, + { + "epoch": 0.02, + "learning_rate": 2.39708542463359e-05, + "loss": 3.9244, + "step": 1589760 + }, + { + "epoch": 0.02, + "learning_rate": 2.396246829882538e-05, + "loss": 3.9213, + "step": 1590272 + }, + { + "epoch": 0.02, + "learning_rate": 2.395408235131486e-05, + "loss": 3.9276, + "step": 1590784 + }, + { + "epoch": 0.02, + "learning_rate": 2.394569640380434e-05, + "loss": 3.9195, + "step": 1591296 + }, + { + "epoch": 0.02, + "learning_rate": 2.393732683509755e-05, + "loss": 3.9206, + "step": 1591808 + }, + { + "epoch": 0.02, + "learning_rate": 2.3928940887587028e-05, + "loss": 3.9149, + "step": 1592320 + }, + { + "epoch": 0.02, + "learning_rate": 2.3920554940076508e-05, + "loss": 3.9323, + "step": 1592832 + }, + { + "epoch": 0.02, + "learning_rate": 2.3912168992565988e-05, + "loss": 3.9284, + "step": 1593344 + }, + { + "epoch": 0.02, + "learning_rate": 2.3903799423859204e-05, + "loss": 3.9322, + "step": 1593856 + }, + { + "epoch": 0.02, + "learning_rate": 2.389541347634868e-05, + "loss": 3.9139, + "step": 1594368 + }, + { + "epoch": 0.02, + "learning_rate": 2.388702752883816e-05, + "loss": 3.9298, + "step": 1594880 + }, + { + "epoch": 0.02, + "learning_rate": 2.387864158132764e-05, + "loss": 3.9297, + "step": 1595392 + }, + { + "epoch": 0.02, + "learning_rate": 2.387025563381712e-05, + "loss": 3.9199, + "step": 1595904 + }, + { + "epoch": 0.02, + "learning_rate": 2.38618696863066e-05, + "loss": 3.9253, + "step": 1596416 + }, + { + "epoch": 0.02, + "learning_rate": 2.385348373879608e-05, + "loss": 3.9312, + "step": 1596928 + }, + { + "epoch": 0.02, + "learning_rate": 2.3845114170089293e-05, + "loss": 3.9234, + "step": 1597440 + }, + { + "epoch": 0.02, + "learning_rate": 2.3836728222578773e-05, + "loss": 3.9459, + "step": 1597952 + }, + { + "epoch": 0.02, + "learning_rate": 2.3828342275068253e-05, + "loss": 3.9162, + "step": 1598464 + }, + { + "epoch": 0.02, + "learning_rate": 2.3819956327557733e-05, + "loss": 3.9279, + "step": 1598976 + }, + { + "epoch": 0.02, + "learning_rate": 2.381157038004721e-05, + "loss": 3.9193, + "step": 1599488 + }, + { + "epoch": 0.02, + "learning_rate": 2.380318443253669e-05, + "loss": 3.9232, + "step": 1600000 + }, + { + "epoch": 0.02, + "learning_rate": 2.3794798485026172e-05, + "loss": 3.9238, + "step": 1600512 + }, + { + "epoch": 0.02, + "learning_rate": 2.3786428916319385e-05, + "loss": 3.9188, + "step": 1601024 + }, + { + "epoch": 0.02, + "learning_rate": 2.377804296880886e-05, + "loss": 3.9206, + "step": 1601536 + }, + { + "epoch": 0.02, + "learning_rate": 2.376965702129834e-05, + "loss": 3.9117, + "step": 1602048 + }, + { + "epoch": 0.02, + "learning_rate": 2.376127107378782e-05, + "loss": 3.9227, + "step": 1602560 + }, + { + "epoch": 0.03, + "eval_loss": 4.006990909576416, + "eval_runtime": 296.3428, + "eval_samples_per_second": 1287.668, + "eval_steps_per_second": 40.241, + "step": 1602720 + }, + { + "epoch": 0.0, + "learning_rate": 2.37528851262773e-05, + "loss": 3.9251, + "step": 1603072 + }, + { + "epoch": 0.0, + "learning_rate": 2.374449917876678e-05, + "loss": 3.9168, + "step": 1603584 + }, + { + "epoch": 0.0, + "learning_rate": 2.373611323125626e-05, + "loss": 3.9311, + "step": 1604096 + }, + { + "epoch": 0.0, + "learning_rate": 2.3727727283745745e-05, + "loss": 3.9271, + "step": 1604608 + }, + { + "epoch": 0.0, + "learning_rate": 2.371934133623522e-05, + "loss": 3.9335, + "step": 1605120 + }, + { + "epoch": 0.0, + "learning_rate": 2.37109553887247e-05, + "loss": 3.922, + "step": 1605632 + }, + { + "epoch": 0.0, + "learning_rate": 2.370256944121418e-05, + "loss": 3.9239, + "step": 1606144 + }, + { + "epoch": 0.0, + "learning_rate": 2.369418349370366e-05, + "loss": 3.9117, + "step": 1606656 + }, + { + "epoch": 0.0, + "learning_rate": 2.3685813924996873e-05, + "loss": 3.9222, + "step": 1607168 + }, + { + "epoch": 0.0, + "learning_rate": 2.3677427977486353e-05, + "loss": 3.9251, + "step": 1607680 + }, + { + "epoch": 0.0, + "learning_rate": 2.3669042029975833e-05, + "loss": 3.927, + "step": 1608192 + }, + { + "epoch": 0.0, + "learning_rate": 2.3660656082465313e-05, + "loss": 3.921, + "step": 1608704 + }, + { + "epoch": 0.0, + "learning_rate": 2.3652270134954793e-05, + "loss": 3.9219, + "step": 1609216 + }, + { + "epoch": 0.0, + "learning_rate": 2.3643884187444273e-05, + "loss": 3.9211, + "step": 1609728 + }, + { + "epoch": 0.0, + "learning_rate": 2.363549823993375e-05, + "loss": 3.9168, + "step": 1610240 + }, + { + "epoch": 0.0, + "learning_rate": 2.362711229242323e-05, + "loss": 3.9091, + "step": 1610752 + }, + { + "epoch": 0.0, + "learning_rate": 2.3618726344912713e-05, + "loss": 3.9164, + "step": 1611264 + }, + { + "epoch": 0.0, + "learning_rate": 2.3610340397402193e-05, + "loss": 3.9234, + "step": 1611776 + }, + { + "epoch": 0.0, + "learning_rate": 2.3601954449891673e-05, + "loss": 3.9209, + "step": 1612288 + }, + { + "epoch": 0.0, + "learning_rate": 2.3593568502381153e-05, + "loss": 3.9361, + "step": 1612800 + }, + { + "epoch": 0.0, + "learning_rate": 2.3585182554870633e-05, + "loss": 3.9258, + "step": 1613312 + }, + { + "epoch": 0.0, + "learning_rate": 2.357679660736011e-05, + "loss": 3.9326, + "step": 1613824 + }, + { + "epoch": 0.0, + "learning_rate": 2.356841065984959e-05, + "loss": 3.92, + "step": 1614336 + }, + { + "epoch": 0.0, + "learning_rate": 2.356002471233907e-05, + "loss": 3.9232, + "step": 1614848 + }, + { + "epoch": 0.0, + "learning_rate": 2.3551655143632282e-05, + "loss": 3.9216, + "step": 1615360 + }, + { + "epoch": 0.0, + "learning_rate": 2.3543269196121762e-05, + "loss": 3.9318, + "step": 1615872 + }, + { + "epoch": 0.0, + "learning_rate": 2.3534899627414974e-05, + "loss": 3.9179, + "step": 1616384 + }, + { + "epoch": 0.0, + "learning_rate": 2.3526513679904454e-05, + "loss": 3.9164, + "step": 1616896 + }, + { + "epoch": 0.0, + "learning_rate": 2.351812773239393e-05, + "loss": 3.9132, + "step": 1617408 + }, + { + "epoch": 0.0, + "learning_rate": 2.3509741784883414e-05, + "loss": 3.9233, + "step": 1617920 + }, + { + "epoch": 0.01, + "learning_rate": 2.3501355837372894e-05, + "loss": 3.924, + "step": 1618432 + }, + { + "epoch": 0.01, + "learning_rate": 2.3492986268666103e-05, + "loss": 3.9272, + "step": 1618944 + }, + { + "epoch": 0.01, + "learning_rate": 2.3484600321155583e-05, + "loss": 3.9281, + "step": 1619456 + }, + { + "epoch": 0.01, + "learning_rate": 2.3476230752448796e-05, + "loss": 3.9227, + "step": 1619968 + }, + { + "epoch": 0.01, + "learning_rate": 2.3467844804938276e-05, + "loss": 3.9215, + "step": 1620480 + }, + { + "epoch": 0.01, + "learning_rate": 2.3459475236231488e-05, + "loss": 3.93, + "step": 1620992 + }, + { + "epoch": 0.01, + "learning_rate": 2.3451089288720968e-05, + "loss": 3.9254, + "step": 1621504 + }, + { + "epoch": 0.01, + "learning_rate": 2.3442703341210448e-05, + "loss": 3.9112, + "step": 1622016 + }, + { + "epoch": 0.01, + "learning_rate": 2.3434317393699928e-05, + "loss": 3.9109, + "step": 1622528 + }, + { + "epoch": 0.01, + "learning_rate": 2.3425931446189405e-05, + "loss": 3.9093, + "step": 1623040 + }, + { + "epoch": 0.01, + "learning_rate": 2.3417545498678885e-05, + "loss": 3.913, + "step": 1623552 + }, + { + "epoch": 0.01, + "learning_rate": 2.3409159551168368e-05, + "loss": 3.9301, + "step": 1624064 + }, + { + "epoch": 0.01, + "learning_rate": 2.3400773603657848e-05, + "loss": 3.9195, + "step": 1624576 + }, + { + "epoch": 0.01, + "learning_rate": 2.3392387656147328e-05, + "loss": 3.913, + "step": 1625088 + }, + { + "epoch": 0.01, + "learning_rate": 2.3384001708636808e-05, + "loss": 3.9228, + "step": 1625600 + }, + { + "epoch": 0.01, + "learning_rate": 2.3375615761126284e-05, + "loss": 3.917, + "step": 1626112 + }, + { + "epoch": 0.01, + "learning_rate": 2.3367229813615764e-05, + "loss": 3.9216, + "step": 1626624 + }, + { + "epoch": 0.01, + "learning_rate": 2.3358843866105244e-05, + "loss": 3.9123, + "step": 1627136 + }, + { + "epoch": 0.01, + "learning_rate": 2.335047429739846e-05, + "loss": 3.8948, + "step": 1627648 + }, + { + "epoch": 0.01, + "learning_rate": 2.3342088349887937e-05, + "loss": 3.9435, + "step": 1628160 + }, + { + "epoch": 0.01, + "learning_rate": 2.3333702402377417e-05, + "loss": 3.9246, + "step": 1628672 + }, + { + "epoch": 0.01, + "learning_rate": 2.3325316454866897e-05, + "loss": 3.9262, + "step": 1629184 + }, + { + "epoch": 0.01, + "learning_rate": 2.3316930507356377e-05, + "loss": 3.9142, + "step": 1629696 + }, + { + "epoch": 0.01, + "learning_rate": 2.3308544559845856e-05, + "loss": 3.9226, + "step": 1630208 + }, + { + "epoch": 0.01, + "learning_rate": 2.3300158612335336e-05, + "loss": 3.9118, + "step": 1630720 + }, + { + "epoch": 0.01, + "learning_rate": 2.329180542243228e-05, + "loss": 3.9194, + "step": 1631232 + }, + { + "epoch": 0.01, + "learning_rate": 2.3283419474921758e-05, + "loss": 3.9182, + "step": 1631744 + }, + { + "epoch": 0.01, + "learning_rate": 2.3275033527411238e-05, + "loss": 3.9209, + "step": 1632256 + }, + { + "epoch": 0.01, + "learning_rate": 2.3266647579900718e-05, + "loss": 3.936, + "step": 1632768 + }, + { + "epoch": 0.01, + "learning_rate": 2.3258261632390198e-05, + "loss": 3.9114, + "step": 1633280 + }, + { + "epoch": 0.01, + "learning_rate": 2.3249875684879678e-05, + "loss": 3.9041, + "step": 1633792 + }, + { + "epoch": 0.01, + "learning_rate": 2.324148973736916e-05, + "loss": 3.9309, + "step": 1634304 + }, + { + "epoch": 0.01, + "learning_rate": 2.323310378985864e-05, + "loss": 3.9001, + "step": 1634816 + }, + { + "epoch": 0.01, + "learning_rate": 2.3224717842348118e-05, + "loss": 3.9076, + "step": 1635328 + }, + { + "epoch": 0.01, + "learning_rate": 2.3216331894837598e-05, + "loss": 3.9258, + "step": 1635840 + }, + { + "epoch": 0.01, + "learning_rate": 2.3207945947327078e-05, + "loss": 3.9249, + "step": 1636352 + }, + { + "epoch": 0.01, + "learning_rate": 2.3199559999816558e-05, + "loss": 3.9115, + "step": 1636864 + }, + { + "epoch": 0.01, + "learning_rate": 2.319119043110977e-05, + "loss": 3.9173, + "step": 1637376 + }, + { + "epoch": 0.01, + "learning_rate": 2.318280448359925e-05, + "loss": 3.897, + "step": 1637888 + }, + { + "epoch": 0.01, + "learning_rate": 2.317441853608873e-05, + "loss": 3.9138, + "step": 1638400 + }, + { + "epoch": 0.01, + "learning_rate": 2.316603258857821e-05, + "loss": 3.9214, + "step": 1638912 + }, + { + "epoch": 0.01, + "learning_rate": 2.315766301987142e-05, + "loss": 3.9096, + "step": 1639424 + }, + { + "epoch": 0.01, + "learning_rate": 2.3149309829968364e-05, + "loss": 3.9218, + "step": 1639936 + }, + { + "epoch": 0.01, + "learning_rate": 2.3140923882457844e-05, + "loss": 3.9207, + "step": 1640448 + }, + { + "epoch": 0.01, + "learning_rate": 2.3132537934947324e-05, + "loss": 3.9345, + "step": 1640960 + }, + { + "epoch": 0.01, + "learning_rate": 2.3124168366240533e-05, + "loss": 3.9105, + "step": 1641472 + }, + { + "epoch": 0.01, + "learning_rate": 2.3115782418730013e-05, + "loss": 3.9152, + "step": 1641984 + }, + { + "epoch": 0.01, + "learning_rate": 2.3107396471219493e-05, + "loss": 3.9252, + "step": 1642496 + }, + { + "epoch": 0.01, + "learning_rate": 2.3099010523708976e-05, + "loss": 3.9101, + "step": 1643008 + }, + { + "epoch": 0.01, + "learning_rate": 2.3090624576198456e-05, + "loss": 3.9227, + "step": 1643520 + }, + { + "epoch": 0.01, + "learning_rate": 2.3082238628687936e-05, + "loss": 3.9192, + "step": 1644032 + }, + { + "epoch": 0.01, + "learning_rate": 2.3073852681177413e-05, + "loss": 3.9148, + "step": 1644544 + }, + { + "epoch": 0.01, + "learning_rate": 2.3065466733666893e-05, + "loss": 3.9254, + "step": 1645056 + }, + { + "epoch": 0.01, + "learning_rate": 2.3057080786156373e-05, + "loss": 3.9071, + "step": 1645568 + }, + { + "epoch": 0.01, + "learning_rate": 2.3048694838645853e-05, + "loss": 3.9097, + "step": 1646080 + }, + { + "epoch": 0.01, + "learning_rate": 2.3040308891135336e-05, + "loss": 3.9164, + "step": 1646592 + }, + { + "epoch": 0.01, + "learning_rate": 2.3031922943624816e-05, + "loss": 3.9219, + "step": 1647104 + }, + { + "epoch": 0.01, + "learning_rate": 2.3023536996114296e-05, + "loss": 3.9128, + "step": 1647616 + }, + { + "epoch": 0.01, + "learning_rate": 2.3015151048603772e-05, + "loss": 3.9183, + "step": 1648128 + }, + { + "epoch": 0.02, + "learning_rate": 2.3006765101093252e-05, + "loss": 3.9063, + "step": 1648640 + }, + { + "epoch": 0.02, + "learning_rate": 2.2998379153582732e-05, + "loss": 3.9156, + "step": 1649152 + }, + { + "epoch": 0.02, + "learning_rate": 2.2990009584875945e-05, + "loss": 3.9071, + "step": 1649664 + }, + { + "epoch": 0.02, + "learning_rate": 2.2981623637365425e-05, + "loss": 3.9161, + "step": 1650176 + }, + { + "epoch": 0.02, + "learning_rate": 2.2973237689854905e-05, + "loss": 3.9311, + "step": 1650688 + }, + { + "epoch": 0.02, + "learning_rate": 2.2964868121148117e-05, + "loss": 3.9163, + "step": 1651200 + }, + { + "epoch": 0.02, + "learning_rate": 2.2956482173637594e-05, + "loss": 3.922, + "step": 1651712 + }, + { + "epoch": 0.02, + "learning_rate": 2.2948096226127074e-05, + "loss": 3.9101, + "step": 1652224 + }, + { + "epoch": 0.02, + "learning_rate": 2.2939710278616554e-05, + "loss": 3.9135, + "step": 1652736 + }, + { + "epoch": 0.02, + "learning_rate": 2.2931324331106037e-05, + "loss": 3.9157, + "step": 1653248 + }, + { + "epoch": 0.02, + "learning_rate": 2.2922938383595517e-05, + "loss": 3.9258, + "step": 1653760 + }, + { + "epoch": 0.02, + "learning_rate": 2.2914552436084997e-05, + "loss": 3.9178, + "step": 1654272 + }, + { + "epoch": 0.02, + "learning_rate": 2.2906166488574477e-05, + "loss": 3.9195, + "step": 1654784 + }, + { + "epoch": 0.02, + "learning_rate": 2.2897780541063954e-05, + "loss": 3.9106, + "step": 1655296 + }, + { + "epoch": 0.02, + "learning_rate": 2.2889410972357166e-05, + "loss": 3.9261, + "step": 1655808 + }, + { + "epoch": 0.02, + "learning_rate": 2.2881025024846646e-05, + "loss": 3.905, + "step": 1656320 + }, + { + "epoch": 0.02, + "learning_rate": 2.287265545613986e-05, + "loss": 3.9196, + "step": 1656832 + }, + { + "epoch": 0.02, + "learning_rate": 2.286426950862934e-05, + "loss": 3.9061, + "step": 1657344 + }, + { + "epoch": 0.02, + "learning_rate": 2.285588356111882e-05, + "loss": 3.9223, + "step": 1657856 + }, + { + "epoch": 0.02, + "learning_rate": 2.28474976136083e-05, + "loss": 3.9101, + "step": 1658368 + }, + { + "epoch": 0.02, + "learning_rate": 2.2839111666097775e-05, + "loss": 3.9149, + "step": 1658880 + }, + { + "epoch": 0.02, + "learning_rate": 2.2830725718587255e-05, + "loss": 3.9109, + "step": 1659392 + }, + { + "epoch": 0.02, + "learning_rate": 2.282235614988047e-05, + "loss": 3.9108, + "step": 1659904 + }, + { + "epoch": 0.02, + "learning_rate": 2.281397020236995e-05, + "loss": 3.9136, + "step": 1660416 + }, + { + "epoch": 0.02, + "learning_rate": 2.2805584254859427e-05, + "loss": 3.914, + "step": 1660928 + }, + { + "epoch": 0.02, + "learning_rate": 2.2797198307348907e-05, + "loss": 3.9218, + "step": 1661440 + }, + { + "epoch": 0.02, + "learning_rate": 2.2788812359838387e-05, + "loss": 3.9285, + "step": 1661952 + }, + { + "epoch": 0.02, + "learning_rate": 2.2780426412327867e-05, + "loss": 3.9211, + "step": 1662464 + }, + { + "epoch": 0.02, + "learning_rate": 2.2772040464817347e-05, + "loss": 3.9199, + "step": 1662976 + }, + { + "epoch": 0.02, + "learning_rate": 2.276365451730683e-05, + "loss": 3.9048, + "step": 1663488 + }, + { + "epoch": 0.02, + "learning_rate": 2.2755268569796307e-05, + "loss": 3.9105, + "step": 1664000 + }, + { + "epoch": 0.02, + "learning_rate": 2.2746882622285787e-05, + "loss": 3.9143, + "step": 1664512 + }, + { + "epoch": 0.02, + "learning_rate": 2.2738513053579e-05, + "loss": 3.9257, + "step": 1665024 + }, + { + "epoch": 0.02, + "learning_rate": 2.273012710606848e-05, + "loss": 3.8991, + "step": 1665536 + }, + { + "epoch": 0.02, + "learning_rate": 2.2721773916165424e-05, + "loss": 3.9203, + "step": 1666048 + }, + { + "epoch": 0.02, + "learning_rate": 2.27133879686549e-05, + "loss": 3.9182, + "step": 1666560 + }, + { + "epoch": 0.02, + "learning_rate": 2.270500202114438e-05, + "loss": 3.9165, + "step": 1667072 + }, + { + "epoch": 0.02, + "learning_rate": 2.269661607363386e-05, + "loss": 3.9135, + "step": 1667584 + }, + { + "epoch": 0.02, + "learning_rate": 2.268823012612334e-05, + "loss": 3.9182, + "step": 1668096 + }, + { + "epoch": 0.02, + "learning_rate": 2.267984417861282e-05, + "loss": 3.9089, + "step": 1668608 + }, + { + "epoch": 0.02, + "learning_rate": 2.26714582311023e-05, + "loss": 3.9253, + "step": 1669120 + }, + { + "epoch": 0.02, + "learning_rate": 2.266307228359178e-05, + "loss": 3.9212, + "step": 1669632 + }, + { + "epoch": 0.02, + "learning_rate": 2.265468633608126e-05, + "loss": 3.9253, + "step": 1670144 + }, + { + "epoch": 0.02, + "learning_rate": 2.264630038857074e-05, + "loss": 3.9064, + "step": 1670656 + }, + { + "epoch": 0.02, + "learning_rate": 2.2637930819863953e-05, + "loss": 3.9236, + "step": 1671168 + }, + { + "epoch": 0.02, + "learning_rate": 2.262954487235343e-05, + "loss": 3.9237, + "step": 1671680 + }, + { + "epoch": 0.02, + "learning_rate": 2.262115892484291e-05, + "loss": 3.9125, + "step": 1672192 + }, + { + "epoch": 0.02, + "learning_rate": 2.2612772977332393e-05, + "loss": 3.9184, + "step": 1672704 + }, + { + "epoch": 0.02, + "learning_rate": 2.2604387029821873e-05, + "loss": 3.9229, + "step": 1673216 + }, + { + "epoch": 0.02, + "learning_rate": 2.2596001082311353e-05, + "loss": 3.9201, + "step": 1673728 + }, + { + "epoch": 0.02, + "learning_rate": 2.2587631513604562e-05, + "loss": 3.9332, + "step": 1674240 + }, + { + "epoch": 0.02, + "learning_rate": 2.2579245566094042e-05, + "loss": 3.9151, + "step": 1674752 + }, + { + "epoch": 0.02, + "learning_rate": 2.2570859618583522e-05, + "loss": 3.9197, + "step": 1675264 + }, + { + "epoch": 0.02, + "learning_rate": 2.2562473671073002e-05, + "loss": 3.9136, + "step": 1675776 + }, + { + "epoch": 0.02, + "learning_rate": 2.2554087723562485e-05, + "loss": 3.9181, + "step": 1676288 + }, + { + "epoch": 0.02, + "learning_rate": 2.2545701776051962e-05, + "loss": 3.9124, + "step": 1676800 + }, + { + "epoch": 0.02, + "learning_rate": 2.253731582854144e-05, + "loss": 3.9118, + "step": 1677312 + }, + { + "epoch": 0.02, + "learning_rate": 2.252892988103092e-05, + "loss": 3.9161, + "step": 1677824 + }, + { + "epoch": 0.02, + "learning_rate": 2.2520576691127863e-05, + "loss": 3.9042, + "step": 1678336 + }, + { + "epoch": 0.02, + "learning_rate": 2.2512190743617347e-05, + "loss": 3.9201, + "step": 1678848 + }, + { + "epoch": 0.03, + "eval_loss": 4.004070281982422, + "eval_runtime": 292.0611, + "eval_samples_per_second": 1306.545, + "eval_steps_per_second": 40.83, + "step": 1679040 + }, + { + "epoch": 1.0, + "learning_rate": 2.2503804796106827e-05, + "loss": 3.9189, + "step": 1679360 + }, + { + "epoch": 1.0, + "learning_rate": 2.2495418848596307e-05, + "loss": 3.9116, + "step": 1679872 + }, + { + "epoch": 1.0, + "learning_rate": 2.2487032901085786e-05, + "loss": 3.9211, + "step": 1680384 + }, + { + "epoch": 1.0, + "learning_rate": 2.2478646953575263e-05, + "loss": 3.9195, + "step": 1680896 + }, + { + "epoch": 1.0, + "learning_rate": 2.2470261006064743e-05, + "loss": 3.9281, + "step": 1681408 + }, + { + "epoch": 1.0, + "learning_rate": 2.2461875058554223e-05, + "loss": 3.9162, + "step": 1681920 + }, + { + "epoch": 1.0, + "learning_rate": 2.2453505489847435e-05, + "loss": 3.9173, + "step": 1682432 + }, + { + "epoch": 1.0, + "learning_rate": 2.2445119542336915e-05, + "loss": 3.9065, + "step": 1682944 + }, + { + "epoch": 1.0, + "learning_rate": 2.2436733594826395e-05, + "loss": 3.9154, + "step": 1683456 + }, + { + "epoch": 1.0, + "learning_rate": 2.2428364026119608e-05, + "loss": 3.9186, + "step": 1683968 + }, + { + "epoch": 1.0, + "learning_rate": 2.2419978078609084e-05, + "loss": 3.9164, + "step": 1684480 + }, + { + "epoch": 1.0, + "learning_rate": 2.2411592131098564e-05, + "loss": 3.9139, + "step": 1684992 + }, + { + "epoch": 1.0, + "learning_rate": 2.240322256239178e-05, + "loss": 3.9133, + "step": 1685504 + }, + { + "epoch": 1.0, + "learning_rate": 2.239483661488126e-05, + "loss": 3.9142, + "step": 1686016 + }, + { + "epoch": 1.0, + "learning_rate": 2.2386450667370737e-05, + "loss": 3.9124, + "step": 1686528 + }, + { + "epoch": 1.0, + "learning_rate": 2.2378064719860217e-05, + "loss": 3.9034, + "step": 1687040 + }, + { + "epoch": 1.0, + "learning_rate": 2.2369678772349697e-05, + "loss": 3.9096, + "step": 1687552 + }, + { + "epoch": 1.0, + "learning_rate": 2.2361292824839177e-05, + "loss": 3.9135, + "step": 1688064 + }, + { + "epoch": 1.0, + "learning_rate": 2.2352906877328657e-05, + "loss": 3.9163, + "step": 1688576 + }, + { + "epoch": 1.0, + "learning_rate": 2.234452092981814e-05, + "loss": 3.9262, + "step": 1689088 + }, + { + "epoch": 1.0, + "learning_rate": 2.2336134982307616e-05, + "loss": 3.9228, + "step": 1689600 + }, + { + "epoch": 1.0, + "learning_rate": 2.2327749034797096e-05, + "loss": 3.9264, + "step": 1690112 + }, + { + "epoch": 1.0, + "learning_rate": 2.231937946609031e-05, + "loss": 3.9084, + "step": 1690624 + }, + { + "epoch": 1.0, + "learning_rate": 2.231099351857979e-05, + "loss": 3.9179, + "step": 1691136 + }, + { + "epoch": 1.0, + "learning_rate": 2.230260757106927e-05, + "loss": 3.9129, + "step": 1691648 + }, + { + "epoch": 1.0, + "learning_rate": 2.229422162355875e-05, + "loss": 3.9224, + "step": 1692160 + }, + { + "epoch": 1.0, + "learning_rate": 2.228583567604823e-05, + "loss": 3.9108, + "step": 1692672 + }, + { + "epoch": 1.0, + "learning_rate": 2.227744972853771e-05, + "loss": 3.913, + "step": 1693184 + }, + { + "epoch": 1.0, + "learning_rate": 2.226906378102719e-05, + "loss": 3.9101, + "step": 1693696 + }, + { + "epoch": 1.0, + "learning_rate": 2.226067783351667e-05, + "loss": 3.9129, + "step": 1694208 + }, + { + "epoch": 1.01, + "learning_rate": 2.2252308264809878e-05, + "loss": 3.9136, + "step": 1694720 + }, + { + "epoch": 1.01, + "learning_rate": 2.224392231729936e-05, + "loss": 3.9249, + "step": 1695232 + }, + { + "epoch": 1.01, + "learning_rate": 2.223555274859257e-05, + "loss": 3.9211, + "step": 1695744 + }, + { + "epoch": 1.01, + "learning_rate": 2.2227183179885783e-05, + "loss": 3.9204, + "step": 1696256 + }, + { + "epoch": 1.01, + "learning_rate": 2.2218797232375263e-05, + "loss": 3.9139, + "step": 1696768 + }, + { + "epoch": 1.01, + "learning_rate": 2.221042766366847e-05, + "loss": 3.9194, + "step": 1697280 + }, + { + "epoch": 1.01, + "learning_rate": 2.2202041716157955e-05, + "loss": 3.92, + "step": 1697792 + }, + { + "epoch": 1.01, + "learning_rate": 2.2193655768647435e-05, + "loss": 3.9064, + "step": 1698304 + }, + { + "epoch": 1.01, + "learning_rate": 2.218526982113691e-05, + "loss": 3.9015, + "step": 1698816 + }, + { + "epoch": 1.01, + "learning_rate": 2.217688387362639e-05, + "loss": 3.9016, + "step": 1699328 + }, + { + "epoch": 1.01, + "learning_rate": 2.216849792611587e-05, + "loss": 3.9097, + "step": 1699840 + }, + { + "epoch": 1.01, + "learning_rate": 2.216011197860535e-05, + "loss": 3.9158, + "step": 1700352 + }, + { + "epoch": 1.01, + "learning_rate": 2.215172603109483e-05, + "loss": 3.9138, + "step": 1700864 + }, + { + "epoch": 1.01, + "learning_rate": 2.214334008358431e-05, + "loss": 3.908, + "step": 1701376 + }, + { + "epoch": 1.01, + "learning_rate": 2.2134970514877524e-05, + "loss": 3.9156, + "step": 1701888 + }, + { + "epoch": 1.01, + "learning_rate": 2.2126584567367004e-05, + "loss": 3.9135, + "step": 1702400 + }, + { + "epoch": 1.01, + "learning_rate": 2.2118198619856484e-05, + "loss": 3.9149, + "step": 1702912 + }, + { + "epoch": 1.01, + "learning_rate": 2.2109812672345964e-05, + "loss": 3.9072, + "step": 1703424 + }, + { + "epoch": 1.01, + "learning_rate": 2.2101426724835444e-05, + "loss": 3.8901, + "step": 1703936 + }, + { + "epoch": 1.01, + "learning_rate": 2.2093040777324924e-05, + "loss": 3.9328, + "step": 1704448 + }, + { + "epoch": 1.01, + "learning_rate": 2.2084654829814404e-05, + "loss": 3.9158, + "step": 1704960 + }, + { + "epoch": 1.01, + "learning_rate": 2.2076268882303884e-05, + "loss": 3.9223, + "step": 1705472 + }, + { + "epoch": 1.01, + "learning_rate": 2.2067882934793363e-05, + "loss": 3.9105, + "step": 1705984 + }, + { + "epoch": 1.01, + "learning_rate": 2.2059496987282843e-05, + "loss": 3.9134, + "step": 1706496 + }, + { + "epoch": 1.01, + "learning_rate": 2.2051111039772323e-05, + "loss": 3.9065, + "step": 1707008 + }, + { + "epoch": 1.01, + "learning_rate": 2.2042741471065532e-05, + "loss": 3.9107, + "step": 1707520 + }, + { + "epoch": 1.01, + "learning_rate": 2.2034355523555016e-05, + "loss": 3.9125, + "step": 1708032 + }, + { + "epoch": 1.01, + "learning_rate": 2.2025969576044496e-05, + "loss": 3.9094, + "step": 1708544 + }, + { + "epoch": 1.01, + "learning_rate": 2.2017583628533976e-05, + "loss": 3.9295, + "step": 1709056 + }, + { + "epoch": 1.01, + "learning_rate": 2.2009197681023452e-05, + "loss": 3.9084, + "step": 1709568 + }, + { + "epoch": 1.01, + "learning_rate": 2.2000811733512932e-05, + "loss": 3.8986, + "step": 1710080 + }, + { + "epoch": 1.01, + "learning_rate": 2.1992425786002412e-05, + "loss": 3.9221, + "step": 1710592 + }, + { + "epoch": 1.01, + "learning_rate": 2.1984039838491892e-05, + "loss": 3.8944, + "step": 1711104 + }, + { + "epoch": 1.01, + "learning_rate": 2.1975670269785105e-05, + "loss": 3.8963, + "step": 1711616 + }, + { + "epoch": 1.01, + "learning_rate": 2.1967300701078317e-05, + "loss": 3.9222, + "step": 1712128 + }, + { + "epoch": 1.01, + "learning_rate": 2.1958914753567797e-05, + "loss": 3.9169, + "step": 1712640 + }, + { + "epoch": 1.01, + "learning_rate": 2.1950528806057274e-05, + "loss": 3.9044, + "step": 1713152 + }, + { + "epoch": 1.01, + "learning_rate": 2.1942159237350486e-05, + "loss": 3.9131, + "step": 1713664 + }, + { + "epoch": 1.01, + "learning_rate": 2.193377328983997e-05, + "loss": 3.8911, + "step": 1714176 + }, + { + "epoch": 1.01, + "learning_rate": 2.192538734232945e-05, + "loss": 3.9077, + "step": 1714688 + }, + { + "epoch": 1.01, + "learning_rate": 2.1917001394818926e-05, + "loss": 3.9097, + "step": 1715200 + }, + { + "epoch": 1.01, + "learning_rate": 2.1908615447308406e-05, + "loss": 3.9064, + "step": 1715712 + }, + { + "epoch": 1.01, + "learning_rate": 2.1900229499797886e-05, + "loss": 3.9131, + "step": 1716224 + }, + { + "epoch": 1.01, + "learning_rate": 2.1891843552287366e-05, + "loss": 3.9142, + "step": 1716736 + }, + { + "epoch": 1.01, + "learning_rate": 2.1883457604776846e-05, + "loss": 3.9267, + "step": 1717248 + }, + { + "epoch": 1.01, + "learning_rate": 2.1875071657266326e-05, + "loss": 3.9063, + "step": 1717760 + }, + { + "epoch": 1.01, + "learning_rate": 2.186668570975581e-05, + "loss": 3.9088, + "step": 1718272 + }, + { + "epoch": 1.01, + "learning_rate": 2.1858299762245286e-05, + "loss": 3.9161, + "step": 1718784 + }, + { + "epoch": 1.01, + "learning_rate": 2.1849913814734766e-05, + "loss": 3.9039, + "step": 1719296 + }, + { + "epoch": 1.01, + "learning_rate": 2.1841544246027978e-05, + "loss": 3.9147, + "step": 1719808 + }, + { + "epoch": 1.01, + "learning_rate": 2.1833158298517455e-05, + "loss": 3.912, + "step": 1720320 + }, + { + "epoch": 1.01, + "learning_rate": 2.1824772351006935e-05, + "loss": 3.9073, + "step": 1720832 + }, + { + "epoch": 1.01, + "learning_rate": 2.1816386403496418e-05, + "loss": 3.9239, + "step": 1721344 + }, + { + "epoch": 1.01, + "learning_rate": 2.180801683478963e-05, + "loss": 3.8967, + "step": 1721856 + }, + { + "epoch": 1.01, + "learning_rate": 2.1799630887279107e-05, + "loss": 3.9023, + "step": 1722368 + }, + { + "epoch": 1.01, + "learning_rate": 2.1791244939768587e-05, + "loss": 3.913, + "step": 1722880 + }, + { + "epoch": 1.01, + "learning_rate": 2.1782858992258067e-05, + "loss": 3.9146, + "step": 1723392 + }, + { + "epoch": 1.01, + "learning_rate": 2.177448942355128e-05, + "loss": 3.9088, + "step": 1723904 + }, + { + "epoch": 1.01, + "learning_rate": 2.176610347604076e-05, + "loss": 3.9107, + "step": 1724416 + }, + { + "epoch": 1.02, + "learning_rate": 2.1757733907333972e-05, + "loss": 3.897, + "step": 1724928 + }, + { + "epoch": 1.02, + "learning_rate": 2.1749347959823452e-05, + "loss": 3.9074, + "step": 1725440 + }, + { + "epoch": 1.02, + "learning_rate": 2.174096201231293e-05, + "loss": 3.9021, + "step": 1725952 + }, + { + "epoch": 1.02, + "learning_rate": 2.173257606480241e-05, + "loss": 3.9107, + "step": 1726464 + }, + { + "epoch": 1.02, + "learning_rate": 2.172419011729189e-05, + "loss": 3.923, + "step": 1726976 + }, + { + "epoch": 1.02, + "learning_rate": 2.1715820548585104e-05, + "loss": 3.9094, + "step": 1727488 + }, + { + "epoch": 1.02, + "learning_rate": 2.170743460107458e-05, + "loss": 3.9147, + "step": 1728000 + }, + { + "epoch": 1.02, + "learning_rate": 2.1699065032367793e-05, + "loss": 3.903, + "step": 1728512 + }, + { + "epoch": 1.02, + "learning_rate": 2.1690679084857273e-05, + "loss": 3.9061, + "step": 1729024 + }, + { + "epoch": 1.02, + "learning_rate": 2.168229313734675e-05, + "loss": 3.9062, + "step": 1729536 + }, + { + "epoch": 1.02, + "learning_rate": 2.1673907189836233e-05, + "loss": 3.9207, + "step": 1730048 + }, + { + "epoch": 1.02, + "learning_rate": 2.1665521242325713e-05, + "loss": 3.9125, + "step": 1730560 + }, + { + "epoch": 1.02, + "learning_rate": 2.1657135294815193e-05, + "loss": 3.9148, + "step": 1731072 + }, + { + "epoch": 1.02, + "learning_rate": 2.1648749347304673e-05, + "loss": 3.9022, + "step": 1731584 + }, + { + "epoch": 1.02, + "learning_rate": 2.1640363399794153e-05, + "loss": 3.9179, + "step": 1732096 + }, + { + "epoch": 1.02, + "learning_rate": 2.1631993831087362e-05, + "loss": 3.9016, + "step": 1732608 + }, + { + "epoch": 1.02, + "learning_rate": 2.1623607883576842e-05, + "loss": 3.9115, + "step": 1733120 + }, + { + "epoch": 1.02, + "learning_rate": 2.1615221936066325e-05, + "loss": 3.8972, + "step": 1733632 + }, + { + "epoch": 1.02, + "learning_rate": 2.1606835988555805e-05, + "loss": 3.913, + "step": 1734144 + }, + { + "epoch": 1.02, + "learning_rate": 2.1598450041045285e-05, + "loss": 3.9041, + "step": 1734656 + }, + { + "epoch": 1.02, + "learning_rate": 2.1590064093534762e-05, + "loss": 3.9095, + "step": 1735168 + }, + { + "epoch": 1.02, + "learning_rate": 2.1581678146024242e-05, + "loss": 3.8997, + "step": 1735680 + }, + { + "epoch": 1.02, + "learning_rate": 2.1573292198513722e-05, + "loss": 3.9099, + "step": 1736192 + }, + { + "epoch": 1.02, + "learning_rate": 2.1564922629806934e-05, + "loss": 3.9038, + "step": 1736704 + }, + { + "epoch": 1.02, + "learning_rate": 2.1556536682296414e-05, + "loss": 3.9058, + "step": 1737216 + }, + { + "epoch": 1.02, + "learning_rate": 2.1548150734785894e-05, + "loss": 3.9206, + "step": 1737728 + }, + { + "epoch": 1.02, + "learning_rate": 2.1539764787275374e-05, + "loss": 3.9209, + "step": 1738240 + }, + { + "epoch": 1.02, + "learning_rate": 2.1531395218568583e-05, + "loss": 3.9147, + "step": 1738752 + }, + { + "epoch": 1.02, + "learning_rate": 2.1523009271058063e-05, + "loss": 3.9126, + "step": 1739264 + }, + { + "epoch": 1.02, + "learning_rate": 2.1514623323547543e-05, + "loss": 3.9019, + "step": 1739776 + }, + { + "epoch": 1.02, + "learning_rate": 2.1506237376037026e-05, + "loss": 3.9035, + "step": 1740288 + }, + { + "epoch": 1.02, + "learning_rate": 2.1497851428526506e-05, + "loss": 3.9103, + "step": 1740800 + }, + { + "epoch": 1.02, + "learning_rate": 2.1489481859819715e-05, + "loss": 3.9135, + "step": 1741312 + }, + { + "epoch": 1.02, + "learning_rate": 2.1481095912309195e-05, + "loss": 3.8946, + "step": 1741824 + }, + { + "epoch": 1.02, + "learning_rate": 2.1472709964798675e-05, + "loss": 3.9132, + "step": 1742336 + }, + { + "epoch": 1.02, + "learning_rate": 2.1464324017288155e-05, + "loss": 3.9136, + "step": 1742848 + }, + { + "epoch": 1.02, + "learning_rate": 2.1455938069777635e-05, + "loss": 3.9093, + "step": 1743360 + }, + { + "epoch": 1.02, + "learning_rate": 2.1447552122267115e-05, + "loss": 3.9063, + "step": 1743872 + }, + { + "epoch": 1.02, + "learning_rate": 2.1439166174756595e-05, + "loss": 3.9078, + "step": 1744384 + }, + { + "epoch": 1.02, + "learning_rate": 2.1430780227246075e-05, + "loss": 3.9009, + "step": 1744896 + }, + { + "epoch": 1.02, + "learning_rate": 2.1422394279735555e-05, + "loss": 3.9207, + "step": 1745408 + }, + { + "epoch": 1.02, + "learning_rate": 2.1414024711028764e-05, + "loss": 3.9154, + "step": 1745920 + }, + { + "epoch": 1.02, + "learning_rate": 2.140565514232198e-05, + "loss": 3.915, + "step": 1746432 + }, + { + "epoch": 1.02, + "learning_rate": 2.139726919481146e-05, + "loss": 3.9001, + "step": 1746944 + }, + { + "epoch": 1.02, + "learning_rate": 2.138888324730094e-05, + "loss": 3.9182, + "step": 1747456 + }, + { + "epoch": 1.02, + "learning_rate": 2.1380497299790417e-05, + "loss": 3.9161, + "step": 1747968 + }, + { + "epoch": 1.02, + "learning_rate": 2.1372111352279897e-05, + "loss": 3.9061, + "step": 1748480 + }, + { + "epoch": 1.02, + "learning_rate": 2.1363725404769376e-05, + "loss": 3.9152, + "step": 1748992 + }, + { + "epoch": 1.02, + "learning_rate": 2.1355339457258856e-05, + "loss": 3.9136, + "step": 1749504 + }, + { + "epoch": 1.02, + "learning_rate": 2.1346953509748336e-05, + "loss": 3.9133, + "step": 1750016 + }, + { + "epoch": 1.02, + "learning_rate": 2.133858394104155e-05, + "loss": 3.9277, + "step": 1750528 + }, + { + "epoch": 1.02, + "learning_rate": 2.133019799353103e-05, + "loss": 3.9055, + "step": 1751040 + }, + { + "epoch": 1.02, + "learning_rate": 2.132181204602051e-05, + "loss": 3.9136, + "step": 1751552 + }, + { + "epoch": 1.02, + "learning_rate": 2.131342609850999e-05, + "loss": 3.9115, + "step": 1752064 + }, + { + "epoch": 1.02, + "learning_rate": 2.130504015099947e-05, + "loss": 3.9119, + "step": 1752576 + }, + { + "epoch": 1.02, + "learning_rate": 2.129665420348895e-05, + "loss": 3.9033, + "step": 1753088 + }, + { + "epoch": 1.02, + "learning_rate": 2.128828463478216e-05, + "loss": 3.9034, + "step": 1753600 + }, + { + "epoch": 1.02, + "learning_rate": 2.127991506607537e-05, + "loss": 3.9081, + "step": 1754112 + }, + { + "epoch": 1.02, + "learning_rate": 2.127152911856485e-05, + "loss": 3.9008, + "step": 1754624 + }, + { + "epoch": 1.02, + "learning_rate": 2.126314317105433e-05, + "loss": 3.9119, + "step": 1755136 + }, + { + "epoch": 1.03, + "eval_loss": 4.001281261444092, + "eval_runtime": 291.7896, + "eval_samples_per_second": 1307.761, + "eval_steps_per_second": 40.868, + "step": 1755360 + }, + { + "epoch": 0.0, + "learning_rate": 2.125475722354381e-05, + "loss": 3.9151, + "step": 1755648 + }, + { + "epoch": 0.0, + "learning_rate": 2.124637127603329e-05, + "loss": 3.9042, + "step": 1756160 + }, + { + "epoch": 0.0, + "learning_rate": 2.123798532852277e-05, + "loss": 3.9137, + "step": 1756672 + }, + { + "epoch": 0.0, + "learning_rate": 2.122959938101225e-05, + "loss": 3.9142, + "step": 1757184 + }, + { + "epoch": 0.0, + "learning_rate": 2.122121343350173e-05, + "loss": 3.9213, + "step": 1757696 + }, + { + "epoch": 0.0, + "learning_rate": 2.121282748599121e-05, + "loss": 3.9077, + "step": 1758208 + }, + { + "epoch": 0.0, + "learning_rate": 2.120444153848069e-05, + "loss": 3.9144, + "step": 1758720 + }, + { + "epoch": 0.0, + "learning_rate": 2.119605559097017e-05, + "loss": 3.9037, + "step": 1759232 + }, + { + "epoch": 0.0, + "learning_rate": 2.118766964345965e-05, + "loss": 3.9011, + "step": 1759744 + }, + { + "epoch": 0.0, + "learning_rate": 2.117928369594913e-05, + "loss": 3.917, + "step": 1760256 + }, + { + "epoch": 0.0, + "learning_rate": 2.117089774843861e-05, + "loss": 3.9093, + "step": 1760768 + }, + { + "epoch": 0.0, + "learning_rate": 2.116251180092809e-05, + "loss": 3.9052, + "step": 1761280 + }, + { + "epoch": 0.0, + "learning_rate": 2.1154142232221302e-05, + "loss": 3.9156, + "step": 1761792 + }, + { + "epoch": 0.0, + "learning_rate": 2.114575628471078e-05, + "loss": 3.9024, + "step": 1762304 + }, + { + "epoch": 0.0, + "learning_rate": 2.113737033720026e-05, + "loss": 3.9025, + "step": 1762816 + }, + { + "epoch": 0.0, + "learning_rate": 2.1128984389689742e-05, + "loss": 3.8963, + "step": 1763328 + }, + { + "epoch": 0.0, + "learning_rate": 2.1120598442179222e-05, + "loss": 3.9028, + "step": 1763840 + }, + { + "epoch": 0.0, + "learning_rate": 2.1112212494668702e-05, + "loss": 3.9107, + "step": 1764352 + }, + { + "epoch": 0.0, + "learning_rate": 2.1103826547158182e-05, + "loss": 3.9033, + "step": 1764864 + }, + { + "epoch": 0.0, + "learning_rate": 2.109544059964766e-05, + "loss": 3.923, + "step": 1765376 + }, + { + "epoch": 0.0, + "learning_rate": 2.108705465213714e-05, + "loss": 3.9163, + "step": 1765888 + }, + { + "epoch": 0.0, + "learning_rate": 2.107868508343035e-05, + "loss": 3.9174, + "step": 1766400 + }, + { + "epoch": 0.0, + "learning_rate": 2.1070299135919834e-05, + "loss": 3.905, + "step": 1766912 + }, + { + "epoch": 0.0, + "learning_rate": 2.106191318840931e-05, + "loss": 3.9057, + "step": 1767424 + }, + { + "epoch": 0.0, + "learning_rate": 2.105352724089879e-05, + "loss": 3.9156, + "step": 1767936 + }, + { + "epoch": 0.0, + "learning_rate": 2.104514129338827e-05, + "loss": 3.9143, + "step": 1768448 + }, + { + "epoch": 0.0, + "learning_rate": 2.103677172468148e-05, + "loss": 3.9044, + "step": 1768960 + }, + { + "epoch": 0.0, + "learning_rate": 2.1028402155974696e-05, + "loss": 3.9075, + "step": 1769472 + }, + { + "epoch": 0.0, + "learning_rate": 2.1020016208464176e-05, + "loss": 3.899, + "step": 1769984 + }, + { + "epoch": 0.0, + "learning_rate": 2.1011630260953656e-05, + "loss": 3.9077, + "step": 1770496 + }, + { + "epoch": 0.01, + "learning_rate": 2.1003244313443132e-05, + "loss": 3.9084, + "step": 1771008 + }, + { + "epoch": 0.01, + "learning_rate": 2.0994858365932612e-05, + "loss": 3.9172, + "step": 1771520 + }, + { + "epoch": 0.01, + "learning_rate": 2.0986472418422092e-05, + "loss": 3.9134, + "step": 1772032 + }, + { + "epoch": 0.01, + "learning_rate": 2.0978086470911572e-05, + "loss": 3.9135, + "step": 1772544 + }, + { + "epoch": 0.01, + "learning_rate": 2.0969700523401052e-05, + "loss": 3.9084, + "step": 1773056 + }, + { + "epoch": 0.01, + "learning_rate": 2.0961330954694264e-05, + "loss": 3.91, + "step": 1773568 + }, + { + "epoch": 0.01, + "learning_rate": 2.0952961385987477e-05, + "loss": 3.9131, + "step": 1774080 + }, + { + "epoch": 0.01, + "learning_rate": 2.0944575438476953e-05, + "loss": 3.9001, + "step": 1774592 + }, + { + "epoch": 0.01, + "learning_rate": 2.0936189490966433e-05, + "loss": 3.898, + "step": 1775104 + }, + { + "epoch": 0.01, + "learning_rate": 2.0927803543455913e-05, + "loss": 3.8942, + "step": 1775616 + }, + { + "epoch": 0.01, + "learning_rate": 2.0919417595945397e-05, + "loss": 3.9025, + "step": 1776128 + }, + { + "epoch": 0.01, + "learning_rate": 2.0911031648434877e-05, + "loss": 3.9048, + "step": 1776640 + }, + { + "epoch": 0.01, + "learning_rate": 2.0902645700924357e-05, + "loss": 3.911, + "step": 1777152 + }, + { + "epoch": 0.01, + "learning_rate": 2.0894259753413837e-05, + "loss": 3.9053, + "step": 1777664 + }, + { + "epoch": 0.01, + "learning_rate": 2.0885873805903313e-05, + "loss": 3.9051, + "step": 1778176 + }, + { + "epoch": 0.01, + "learning_rate": 2.0877487858392793e-05, + "loss": 3.9063, + "step": 1778688 + }, + { + "epoch": 0.01, + "learning_rate": 2.0869101910882273e-05, + "loss": 3.9115, + "step": 1779200 + }, + { + "epoch": 0.01, + "learning_rate": 2.0860715963371753e-05, + "loss": 3.8994, + "step": 1779712 + }, + { + "epoch": 0.01, + "learning_rate": 2.0852346394664966e-05, + "loss": 3.8844, + "step": 1780224 + }, + { + "epoch": 0.01, + "learning_rate": 2.0843960447154445e-05, + "loss": 3.9208, + "step": 1780736 + }, + { + "epoch": 0.01, + "learning_rate": 2.0835590878447658e-05, + "loss": 3.912, + "step": 1781248 + }, + { + "epoch": 0.01, + "learning_rate": 2.0827204930937135e-05, + "loss": 3.917, + "step": 1781760 + }, + { + "epoch": 0.01, + "learning_rate": 2.0818818983426618e-05, + "loss": 3.9044, + "step": 1782272 + }, + { + "epoch": 0.01, + "learning_rate": 2.0810433035916098e-05, + "loss": 3.9071, + "step": 1782784 + }, + { + "epoch": 0.01, + "learning_rate": 2.0802047088405578e-05, + "loss": 3.9016, + "step": 1783296 + }, + { + "epoch": 0.01, + "learning_rate": 2.0793661140895058e-05, + "loss": 3.9022, + "step": 1783808 + }, + { + "epoch": 0.01, + "learning_rate": 2.0785275193384538e-05, + "loss": 3.9099, + "step": 1784320 + }, + { + "epoch": 0.01, + "learning_rate": 2.0776889245874018e-05, + "loss": 3.8981, + "step": 1784832 + }, + { + "epoch": 0.01, + "learning_rate": 2.0768519677167227e-05, + "loss": 3.9256, + "step": 1785344 + }, + { + "epoch": 0.01, + "learning_rate": 2.0760133729656707e-05, + "loss": 3.9064, + "step": 1785856 + }, + { + "epoch": 0.01, + "learning_rate": 2.075174778214619e-05, + "loss": 3.887, + "step": 1786368 + }, + { + "epoch": 0.01, + "learning_rate": 2.074336183463567e-05, + "loss": 3.9163, + "step": 1786880 + }, + { + "epoch": 0.01, + "learning_rate": 2.0734975887125147e-05, + "loss": 3.8893, + "step": 1787392 + }, + { + "epoch": 0.01, + "learning_rate": 2.072660631841836e-05, + "loss": 3.8891, + "step": 1787904 + }, + { + "epoch": 0.01, + "learning_rate": 2.0718236749711568e-05, + "loss": 3.916, + "step": 1788416 + }, + { + "epoch": 0.01, + "learning_rate": 2.070985080220105e-05, + "loss": 3.9071, + "step": 1788928 + }, + { + "epoch": 0.01, + "learning_rate": 2.070146485469053e-05, + "loss": 3.8965, + "step": 1789440 + }, + { + "epoch": 0.01, + "learning_rate": 2.069307890718001e-05, + "loss": 3.9047, + "step": 1789952 + }, + { + "epoch": 0.01, + "learning_rate": 2.068469295966949e-05, + "loss": 3.8875, + "step": 1790464 + }, + { + "epoch": 0.01, + "learning_rate": 2.06763233909627e-05, + "loss": 3.8995, + "step": 1790976 + }, + { + "epoch": 0.01, + "learning_rate": 2.066793744345218e-05, + "loss": 3.9057, + "step": 1791488 + }, + { + "epoch": 0.01, + "learning_rate": 2.065955149594166e-05, + "loss": 3.8971, + "step": 1792000 + }, + { + "epoch": 0.01, + "learning_rate": 2.0651165548431144e-05, + "loss": 3.9068, + "step": 1792512 + }, + { + "epoch": 0.01, + "learning_rate": 2.064277960092062e-05, + "loss": 3.9049, + "step": 1793024 + }, + { + "epoch": 0.01, + "learning_rate": 2.06343936534101e-05, + "loss": 3.9187, + "step": 1793536 + }, + { + "epoch": 0.01, + "learning_rate": 2.062600770589958e-05, + "loss": 3.8996, + "step": 1794048 + }, + { + "epoch": 0.01, + "learning_rate": 2.061762175838906e-05, + "loss": 3.9054, + "step": 1794560 + }, + { + "epoch": 0.01, + "learning_rate": 2.060923581087854e-05, + "loss": 3.907, + "step": 1795072 + }, + { + "epoch": 0.01, + "learning_rate": 2.0600882620975485e-05, + "loss": 3.8977, + "step": 1795584 + }, + { + "epoch": 0.01, + "learning_rate": 2.0592496673464965e-05, + "loss": 3.9102, + "step": 1796096 + }, + { + "epoch": 0.01, + "learning_rate": 2.058411072595444e-05, + "loss": 3.9064, + "step": 1796608 + }, + { + "epoch": 0.01, + "learning_rate": 2.057572477844392e-05, + "loss": 3.8967, + "step": 1797120 + }, + { + "epoch": 0.01, + "learning_rate": 2.05673388309334e-05, + "loss": 3.9182, + "step": 1797632 + }, + { + "epoch": 0.01, + "learning_rate": 2.0558969262226614e-05, + "loss": 3.8909, + "step": 1798144 + }, + { + "epoch": 0.01, + "learning_rate": 2.0550583314716094e-05, + "loss": 3.8952, + "step": 1798656 + }, + { + "epoch": 0.01, + "learning_rate": 2.0542197367205574e-05, + "loss": 3.9081, + "step": 1799168 + }, + { + "epoch": 0.01, + "learning_rate": 2.0533811419695054e-05, + "loss": 3.9057, + "step": 1799680 + }, + { + "epoch": 0.01, + "learning_rate": 2.0525425472184534e-05, + "loss": 3.9004, + "step": 1800192 + }, + { + "epoch": 0.01, + "learning_rate": 2.0517055903477743e-05, + "loss": 3.909, + "step": 1800704 + }, + { + "epoch": 0.02, + "learning_rate": 2.0508669955967226e-05, + "loss": 3.8908, + "step": 1801216 + }, + { + "epoch": 0.02, + "learning_rate": 2.0500284008456706e-05, + "loss": 3.8983, + "step": 1801728 + }, + { + "epoch": 0.02, + "learning_rate": 2.0491898060946186e-05, + "loss": 3.8991, + "step": 1802240 + }, + { + "epoch": 0.02, + "learning_rate": 2.0483512113435666e-05, + "loss": 3.8995, + "step": 1802752 + }, + { + "epoch": 0.02, + "learning_rate": 2.0475126165925146e-05, + "loss": 3.9165, + "step": 1803264 + }, + { + "epoch": 0.02, + "learning_rate": 2.0466756597218355e-05, + "loss": 3.9025, + "step": 1803776 + }, + { + "epoch": 0.02, + "learning_rate": 2.0458370649707835e-05, + "loss": 3.9105, + "step": 1804288 + }, + { + "epoch": 0.02, + "learning_rate": 2.0449984702197315e-05, + "loss": 3.8965, + "step": 1804800 + }, + { + "epoch": 0.02, + "learning_rate": 2.0441598754686795e-05, + "loss": 3.9018, + "step": 1805312 + }, + { + "epoch": 0.02, + "learning_rate": 2.0433212807176275e-05, + "loss": 3.9015, + "step": 1805824 + }, + { + "epoch": 0.02, + "learning_rate": 2.0424826859665755e-05, + "loss": 3.9106, + "step": 1806336 + }, + { + "epoch": 0.02, + "learning_rate": 2.0416457290958967e-05, + "loss": 3.906, + "step": 1806848 + }, + { + "epoch": 0.02, + "learning_rate": 2.0408071343448444e-05, + "loss": 3.9098, + "step": 1807360 + }, + { + "epoch": 0.02, + "learning_rate": 2.0399685395937927e-05, + "loss": 3.899, + "step": 1807872 + }, + { + "epoch": 0.02, + "learning_rate": 2.0391299448427407e-05, + "loss": 3.9054, + "step": 1808384 + }, + { + "epoch": 0.02, + "learning_rate": 2.0382913500916887e-05, + "loss": 3.9016, + "step": 1808896 + }, + { + "epoch": 0.02, + "learning_rate": 2.0374527553406367e-05, + "loss": 3.9017, + "step": 1809408 + }, + { + "epoch": 0.02, + "learning_rate": 2.0366157984699576e-05, + "loss": 3.8924, + "step": 1809920 + }, + { + "epoch": 0.02, + "learning_rate": 2.0357772037189056e-05, + "loss": 3.9094, + "step": 1810432 + }, + { + "epoch": 0.02, + "learning_rate": 2.0349386089678536e-05, + "loss": 3.8953, + "step": 1810944 + }, + { + "epoch": 0.02, + "learning_rate": 2.034100014216802e-05, + "loss": 3.901, + "step": 1811456 + }, + { + "epoch": 0.02, + "learning_rate": 2.03326141946575e-05, + "loss": 3.8926, + "step": 1811968 + }, + { + "epoch": 0.02, + "learning_rate": 2.0324228247146976e-05, + "loss": 3.9019, + "step": 1812480 + }, + { + "epoch": 0.02, + "learning_rate": 2.0315842299636456e-05, + "loss": 3.8981, + "step": 1812992 + }, + { + "epoch": 0.02, + "learning_rate": 2.0307456352125936e-05, + "loss": 3.8989, + "step": 1813504 + }, + { + "epoch": 0.02, + "learning_rate": 2.029910316222288e-05, + "loss": 3.9086, + "step": 1814016 + }, + { + "epoch": 0.02, + "learning_rate": 2.029071721471236e-05, + "loss": 3.9163, + "step": 1814528 + }, + { + "epoch": 0.02, + "learning_rate": 2.028233126720184e-05, + "loss": 3.9142, + "step": 1815040 + }, + { + "epoch": 0.02, + "learning_rate": 2.027394531969132e-05, + "loss": 3.902, + "step": 1815552 + }, + { + "epoch": 0.02, + "learning_rate": 2.02655593721808e-05, + "loss": 3.8944, + "step": 1816064 + }, + { + "epoch": 0.02, + "learning_rate": 2.025718980347401e-05, + "loss": 3.897, + "step": 1816576 + }, + { + "epoch": 0.02, + "learning_rate": 2.024880385596349e-05, + "loss": 3.9031, + "step": 1817088 + }, + { + "epoch": 0.02, + "learning_rate": 2.0240417908452973e-05, + "loss": 3.9061, + "step": 1817600 + }, + { + "epoch": 0.02, + "learning_rate": 2.023203196094245e-05, + "loss": 3.8896, + "step": 1818112 + }, + { + "epoch": 0.02, + "learning_rate": 2.0223662392235662e-05, + "loss": 3.9061, + "step": 1818624 + }, + { + "epoch": 0.02, + "learning_rate": 2.0215276444725142e-05, + "loss": 3.909, + "step": 1819136 + }, + { + "epoch": 0.02, + "learning_rate": 2.0206890497214622e-05, + "loss": 3.8997, + "step": 1819648 + }, + { + "epoch": 0.02, + "learning_rate": 2.01985045497041e-05, + "loss": 3.899, + "step": 1820160 + }, + { + "epoch": 0.02, + "learning_rate": 2.0190118602193582e-05, + "loss": 3.904, + "step": 1820672 + }, + { + "epoch": 0.02, + "learning_rate": 2.0181732654683062e-05, + "loss": 3.8969, + "step": 1821184 + }, + { + "epoch": 0.02, + "learning_rate": 2.0173346707172542e-05, + "loss": 3.9103, + "step": 1821696 + }, + { + "epoch": 0.02, + "learning_rate": 2.016497713846575e-05, + "loss": 3.906, + "step": 1822208 + }, + { + "epoch": 0.02, + "learning_rate": 2.015659119095523e-05, + "loss": 3.9122, + "step": 1822720 + }, + { + "epoch": 0.02, + "learning_rate": 2.014820524344471e-05, + "loss": 3.8939, + "step": 1823232 + }, + { + "epoch": 0.02, + "learning_rate": 2.013981929593419e-05, + "loss": 3.911, + "step": 1823744 + }, + { + "epoch": 0.02, + "learning_rate": 2.0131433348423674e-05, + "loss": 3.9098, + "step": 1824256 + }, + { + "epoch": 0.02, + "learning_rate": 2.0123047400913154e-05, + "loss": 3.9008, + "step": 1824768 + }, + { + "epoch": 0.02, + "learning_rate": 2.011466145340263e-05, + "loss": 3.9052, + "step": 1825280 + }, + { + "epoch": 0.02, + "learning_rate": 2.010627550589211e-05, + "loss": 3.9045, + "step": 1825792 + }, + { + "epoch": 0.02, + "learning_rate": 2.0097905937185323e-05, + "loss": 3.9078, + "step": 1826304 + }, + { + "epoch": 0.02, + "learning_rate": 2.0089519989674803e-05, + "loss": 3.9225, + "step": 1826816 + }, + { + "epoch": 0.02, + "learning_rate": 2.0081150420968016e-05, + "loss": 3.8963, + "step": 1827328 + }, + { + "epoch": 0.02, + "learning_rate": 2.0072764473457496e-05, + "loss": 3.9103, + "step": 1827840 + }, + { + "epoch": 0.02, + "learning_rate": 2.0064378525946976e-05, + "loss": 3.9058, + "step": 1828352 + }, + { + "epoch": 0.02, + "learning_rate": 2.0055992578436456e-05, + "loss": 3.9044, + "step": 1828864 + }, + { + "epoch": 0.02, + "learning_rate": 2.0047606630925932e-05, + "loss": 3.8987, + "step": 1829376 + }, + { + "epoch": 0.02, + "learning_rate": 2.0039220683415412e-05, + "loss": 3.8944, + "step": 1829888 + }, + { + "epoch": 0.02, + "learning_rate": 2.0030851114708628e-05, + "loss": 3.9036, + "step": 1830400 + }, + { + "epoch": 0.02, + "learning_rate": 2.0022465167198105e-05, + "loss": 3.894, + "step": 1830912 + }, + { + "epoch": 0.02, + "learning_rate": 2.0014079219687585e-05, + "loss": 3.9052, + "step": 1831424 + }, + { + "epoch": 0.03, + "eval_loss": 3.998615026473999, + "eval_runtime": 293.0898, + "eval_samples_per_second": 1301.959, + "eval_steps_per_second": 40.687, + "step": 1831680 + }, + { + "epoch": 0.0, + "learning_rate": 2.0005693272177065e-05, + "loss": 3.9013, + "step": 1831936 + }, + { + "epoch": 0.0, + "learning_rate": 1.9997307324666544e-05, + "loss": 3.8998, + "step": 1832448 + }, + { + "epoch": 0.0, + "learning_rate": 1.9988921377156024e-05, + "loss": 3.9066, + "step": 1832960 + }, + { + "epoch": 0.0, + "learning_rate": 1.9980535429645504e-05, + "loss": 3.9071, + "step": 1833472 + }, + { + "epoch": 0.0, + "learning_rate": 1.9972149482134984e-05, + "loss": 3.9131, + "step": 1833984 + }, + { + "epoch": 0.0, + "learning_rate": 1.9963763534624464e-05, + "loss": 3.9026, + "step": 1834496 + }, + { + "epoch": 0.0, + "learning_rate": 1.9955377587113944e-05, + "loss": 3.9105, + "step": 1835008 + }, + { + "epoch": 0.0, + "learning_rate": 1.9946991639603424e-05, + "loss": 3.8957, + "step": 1835520 + }, + { + "epoch": 0.0, + "learning_rate": 1.9938605692092904e-05, + "loss": 3.8973, + "step": 1836032 + }, + { + "epoch": 0.0, + "learning_rate": 1.9930219744582384e-05, + "loss": 3.9112, + "step": 1836544 + }, + { + "epoch": 0.0, + "learning_rate": 1.9921833797071864e-05, + "loss": 3.9037, + "step": 1837056 + }, + { + "epoch": 0.0, + "learning_rate": 1.9913447849561344e-05, + "loss": 3.8976, + "step": 1837568 + }, + { + "epoch": 0.0, + "learning_rate": 1.9905078280854557e-05, + "loss": 3.911, + "step": 1838080 + }, + { + "epoch": 0.0, + "learning_rate": 1.9896692333344036e-05, + "loss": 3.8946, + "step": 1838592 + }, + { + "epoch": 0.0, + "learning_rate": 1.9888322764637246e-05, + "loss": 3.8981, + "step": 1839104 + }, + { + "epoch": 0.0, + "learning_rate": 1.9879936817126726e-05, + "loss": 3.8854, + "step": 1839616 + }, + { + "epoch": 0.0, + "learning_rate": 1.9871550869616205e-05, + "loss": 3.9008, + "step": 1840128 + }, + { + "epoch": 0.0, + "learning_rate": 1.9863164922105685e-05, + "loss": 3.9068, + "step": 1840640 + }, + { + "epoch": 0.0, + "learning_rate": 1.985477897459517e-05, + "loss": 3.895, + "step": 1841152 + }, + { + "epoch": 0.0, + "learning_rate": 1.9846393027084645e-05, + "loss": 3.915, + "step": 1841664 + }, + { + "epoch": 0.0, + "learning_rate": 1.9838007079574125e-05, + "loss": 3.91, + "step": 1842176 + }, + { + "epoch": 0.0, + "learning_rate": 1.9829621132063605e-05, + "loss": 3.9107, + "step": 1842688 + }, + { + "epoch": 0.0, + "learning_rate": 1.9821235184553085e-05, + "loss": 3.9029, + "step": 1843200 + }, + { + "epoch": 0.0, + "learning_rate": 1.9812849237042565e-05, + "loss": 3.904, + "step": 1843712 + }, + { + "epoch": 0.0, + "learning_rate": 1.9804463289532045e-05, + "loss": 3.9061, + "step": 1844224 + }, + { + "epoch": 0.0, + "learning_rate": 1.9796077342021525e-05, + "loss": 3.9048, + "step": 1844736 + }, + { + "epoch": 0.0, + "learning_rate": 1.9787691394511005e-05, + "loss": 3.8959, + "step": 1845248 + }, + { + "epoch": 0.0, + "learning_rate": 1.9779305447000485e-05, + "loss": 3.9029, + "step": 1845760 + }, + { + "epoch": 0.0, + "learning_rate": 1.9770919499489965e-05, + "loss": 3.8943, + "step": 1846272 + }, + { + "epoch": 0.0, + "learning_rate": 1.9762549930783174e-05, + "loss": 3.9011, + "step": 1846784 + }, + { + "epoch": 0.01, + "learning_rate": 1.9754163983272654e-05, + "loss": 3.9013, + "step": 1847296 + }, + { + "epoch": 0.01, + "learning_rate": 1.9745778035762137e-05, + "loss": 3.9071, + "step": 1847808 + }, + { + "epoch": 0.01, + "learning_rate": 1.9737392088251617e-05, + "loss": 3.9107, + "step": 1848320 + }, + { + "epoch": 0.01, + "learning_rate": 1.9729022519544826e-05, + "loss": 3.9116, + "step": 1848832 + }, + { + "epoch": 0.01, + "learning_rate": 1.9720636572034306e-05, + "loss": 3.8971, + "step": 1849344 + }, + { + "epoch": 0.01, + "learning_rate": 1.971226700332752e-05, + "loss": 3.9067, + "step": 1849856 + }, + { + "epoch": 0.01, + "learning_rate": 1.9703881055817e-05, + "loss": 3.9079, + "step": 1850368 + }, + { + "epoch": 0.01, + "learning_rate": 1.969549510830648e-05, + "loss": 3.891, + "step": 1850880 + }, + { + "epoch": 0.01, + "learning_rate": 1.968710916079596e-05, + "loss": 3.8956, + "step": 1851392 + }, + { + "epoch": 0.01, + "learning_rate": 1.967872321328544e-05, + "loss": 3.8905, + "step": 1851904 + }, + { + "epoch": 0.01, + "learning_rate": 1.967033726577492e-05, + "loss": 3.8925, + "step": 1852416 + }, + { + "epoch": 0.01, + "learning_rate": 1.96619513182644e-05, + "loss": 3.9005, + "step": 1852928 + }, + { + "epoch": 0.01, + "learning_rate": 1.965356537075388e-05, + "loss": 3.9047, + "step": 1853440 + }, + { + "epoch": 0.01, + "learning_rate": 1.9645179423243355e-05, + "loss": 3.8972, + "step": 1853952 + }, + { + "epoch": 0.01, + "learning_rate": 1.963679347573284e-05, + "loss": 3.896, + "step": 1854464 + }, + { + "epoch": 0.01, + "learning_rate": 1.962840752822232e-05, + "loss": 3.8993, + "step": 1854976 + }, + { + "epoch": 0.01, + "learning_rate": 1.96200215807118e-05, + "loss": 3.9097, + "step": 1855488 + }, + { + "epoch": 0.01, + "learning_rate": 1.9611635633201278e-05, + "loss": 3.8916, + "step": 1856000 + }, + { + "epoch": 0.01, + "learning_rate": 1.9603249685690758e-05, + "loss": 3.8808, + "step": 1856512 + }, + { + "epoch": 0.01, + "learning_rate": 1.9594880116983967e-05, + "loss": 3.9123, + "step": 1857024 + }, + { + "epoch": 0.01, + "learning_rate": 1.9586494169473447e-05, + "loss": 3.9045, + "step": 1857536 + }, + { + "epoch": 0.01, + "learning_rate": 1.957810822196293e-05, + "loss": 3.9102, + "step": 1858048 + }, + { + "epoch": 0.01, + "learning_rate": 1.956972227445241e-05, + "loss": 3.8981, + "step": 1858560 + }, + { + "epoch": 0.01, + "learning_rate": 1.9561336326941887e-05, + "loss": 3.8969, + "step": 1859072 + }, + { + "epoch": 0.01, + "learning_rate": 1.9552950379431367e-05, + "loss": 3.8978, + "step": 1859584 + }, + { + "epoch": 0.01, + "learning_rate": 1.954458081072458e-05, + "loss": 3.8977, + "step": 1860096 + }, + { + "epoch": 0.01, + "learning_rate": 1.953619486321406e-05, + "loss": 3.9063, + "step": 1860608 + }, + { + "epoch": 0.01, + "learning_rate": 1.9527825294507272e-05, + "loss": 3.8894, + "step": 1861120 + }, + { + "epoch": 0.01, + "learning_rate": 1.9519439346996752e-05, + "loss": 3.9221, + "step": 1861632 + }, + { + "epoch": 0.01, + "learning_rate": 1.9511053399486232e-05, + "loss": 3.8955, + "step": 1862144 + }, + { + "epoch": 0.01, + "learning_rate": 1.9502667451975712e-05, + "loss": 3.8804, + "step": 1862656 + }, + { + "epoch": 0.01, + "learning_rate": 1.949428150446519e-05, + "loss": 3.9116, + "step": 1863168 + }, + { + "epoch": 0.01, + "learning_rate": 1.948589555695467e-05, + "loss": 3.8913, + "step": 1863680 + }, + { + "epoch": 0.01, + "learning_rate": 1.947750960944415e-05, + "loss": 3.8804, + "step": 1864192 + }, + { + "epoch": 0.01, + "learning_rate": 1.9469123661933632e-05, + "loss": 3.9063, + "step": 1864704 + }, + { + "epoch": 0.01, + "learning_rate": 1.946073771442311e-05, + "loss": 3.9041, + "step": 1865216 + }, + { + "epoch": 0.01, + "learning_rate": 1.945235176691259e-05, + "loss": 3.8959, + "step": 1865728 + }, + { + "epoch": 0.01, + "learning_rate": 1.9443965819402068e-05, + "loss": 3.8957, + "step": 1866240 + }, + { + "epoch": 0.01, + "learning_rate": 1.9435579871891548e-05, + "loss": 3.8799, + "step": 1866752 + }, + { + "epoch": 0.01, + "learning_rate": 1.942721030318476e-05, + "loss": 3.8925, + "step": 1867264 + }, + { + "epoch": 0.01, + "learning_rate": 1.941882435567424e-05, + "loss": 3.9024, + "step": 1867776 + }, + { + "epoch": 0.01, + "learning_rate": 1.9410454786967453e-05, + "loss": 3.8943, + "step": 1868288 + }, + { + "epoch": 0.01, + "learning_rate": 1.9402068839456933e-05, + "loss": 3.899, + "step": 1868800 + }, + { + "epoch": 0.01, + "learning_rate": 1.9393682891946413e-05, + "loss": 3.8973, + "step": 1869312 + }, + { + "epoch": 0.01, + "learning_rate": 1.938529694443589e-05, + "loss": 3.9134, + "step": 1869824 + }, + { + "epoch": 0.01, + "learning_rate": 1.937691099692537e-05, + "loss": 3.8972, + "step": 1870336 + }, + { + "epoch": 0.01, + "learning_rate": 1.9368525049414853e-05, + "loss": 3.8992, + "step": 1870848 + }, + { + "epoch": 0.01, + "learning_rate": 1.9360139101904333e-05, + "loss": 3.9009, + "step": 1871360 + }, + { + "epoch": 0.01, + "learning_rate": 1.9351753154393813e-05, + "loss": 3.8943, + "step": 1871872 + }, + { + "epoch": 0.01, + "learning_rate": 1.9343383585687022e-05, + "loss": 3.9045, + "step": 1872384 + }, + { + "epoch": 0.01, + "learning_rate": 1.9334997638176502e-05, + "loss": 3.8984, + "step": 1872896 + }, + { + "epoch": 0.01, + "learning_rate": 1.9326611690665982e-05, + "loss": 3.8967, + "step": 1873408 + }, + { + "epoch": 0.01, + "learning_rate": 1.9318225743155462e-05, + "loss": 3.9083, + "step": 1873920 + }, + { + "epoch": 0.01, + "learning_rate": 1.9309856174448674e-05, + "loss": 3.8862, + "step": 1874432 + }, + { + "epoch": 0.01, + "learning_rate": 1.9301486605741887e-05, + "loss": 3.8922, + "step": 1874944 + }, + { + "epoch": 0.01, + "learning_rate": 1.9293100658231363e-05, + "loss": 3.8997, + "step": 1875456 + }, + { + "epoch": 0.01, + "learning_rate": 1.9284714710720843e-05, + "loss": 3.9006, + "step": 1875968 + }, + { + "epoch": 0.01, + "learning_rate": 1.9276328763210323e-05, + "loss": 3.8914, + "step": 1876480 + }, + { + "epoch": 0.01, + "learning_rate": 1.9267942815699807e-05, + "loss": 3.9034, + "step": 1876992 + }, + { + "epoch": 0.02, + "learning_rate": 1.9259556868189286e-05, + "loss": 3.8893, + "step": 1877504 + }, + { + "epoch": 0.02, + "learning_rate": 1.9251187299482496e-05, + "loss": 3.8915, + "step": 1878016 + }, + { + "epoch": 0.02, + "learning_rate": 1.9242801351971976e-05, + "loss": 3.8891, + "step": 1878528 + }, + { + "epoch": 0.02, + "learning_rate": 1.9234415404461455e-05, + "loss": 3.8941, + "step": 1879040 + }, + { + "epoch": 0.02, + "learning_rate": 1.9226029456950935e-05, + "loss": 3.9128, + "step": 1879552 + }, + { + "epoch": 0.02, + "learning_rate": 1.9217643509440415e-05, + "loss": 3.898, + "step": 1880064 + }, + { + "epoch": 0.02, + "learning_rate": 1.9209257561929895e-05, + "loss": 3.902, + "step": 1880576 + }, + { + "epoch": 0.02, + "learning_rate": 1.9200887993223108e-05, + "loss": 3.8937, + "step": 1881088 + }, + { + "epoch": 0.02, + "learning_rate": 1.9192502045712588e-05, + "loss": 3.8928, + "step": 1881600 + }, + { + "epoch": 0.02, + "learning_rate": 1.9184116098202068e-05, + "loss": 3.8956, + "step": 1882112 + }, + { + "epoch": 0.02, + "learning_rate": 1.9175730150691544e-05, + "loss": 3.9057, + "step": 1882624 + }, + { + "epoch": 0.02, + "learning_rate": 1.9167344203181024e-05, + "loss": 3.9006, + "step": 1883136 + }, + { + "epoch": 0.02, + "learning_rate": 1.9158958255670508e-05, + "loss": 3.8983, + "step": 1883648 + }, + { + "epoch": 0.02, + "learning_rate": 1.9150572308159988e-05, + "loss": 3.9004, + "step": 1884160 + }, + { + "epoch": 0.02, + "learning_rate": 1.9142202739453197e-05, + "loss": 3.8984, + "step": 1884672 + }, + { + "epoch": 0.02, + "learning_rate": 1.9133816791942677e-05, + "loss": 3.8956, + "step": 1885184 + }, + { + "epoch": 0.02, + "learning_rate": 1.9125430844432157e-05, + "loss": 3.8951, + "step": 1885696 + }, + { + "epoch": 0.02, + "learning_rate": 1.9117044896921637e-05, + "loss": 3.8875, + "step": 1886208 + }, + { + "epoch": 0.02, + "learning_rate": 1.910867532821485e-05, + "loss": 3.9012, + "step": 1886720 + }, + { + "epoch": 0.02, + "learning_rate": 1.910028938070433e-05, + "loss": 3.8915, + "step": 1887232 + }, + { + "epoch": 0.02, + "learning_rate": 1.909190343319381e-05, + "loss": 3.8925, + "step": 1887744 + }, + { + "epoch": 0.02, + "learning_rate": 1.908351748568329e-05, + "loss": 3.8914, + "step": 1888256 + }, + { + "epoch": 0.02, + "learning_rate": 1.907513153817277e-05, + "loss": 3.8914, + "step": 1888768 + }, + { + "epoch": 0.02, + "learning_rate": 1.9066761969465978e-05, + "loss": 3.8951, + "step": 1889280 + }, + { + "epoch": 0.02, + "learning_rate": 1.905837602195546e-05, + "loss": 3.8923, + "step": 1889792 + }, + { + "epoch": 0.02, + "learning_rate": 1.905000645324867e-05, + "loss": 3.907, + "step": 1890304 + }, + { + "epoch": 0.02, + "learning_rate": 1.904162050573815e-05, + "loss": 3.9077, + "step": 1890816 + }, + { + "epoch": 0.02, + "learning_rate": 1.903323455822763e-05, + "loss": 3.9066, + "step": 1891328 + }, + { + "epoch": 0.02, + "learning_rate": 1.902484861071711e-05, + "loss": 3.897, + "step": 1891840 + }, + { + "epoch": 0.02, + "learning_rate": 1.901646266320659e-05, + "loss": 3.8934, + "step": 1892352 + }, + { + "epoch": 0.02, + "learning_rate": 1.900807671569607e-05, + "loss": 3.8914, + "step": 1892864 + }, + { + "epoch": 0.02, + "learning_rate": 1.8999690768185554e-05, + "loss": 3.8994, + "step": 1893376 + }, + { + "epoch": 0.02, + "learning_rate": 1.899130482067503e-05, + "loss": 3.9032, + "step": 1893888 + }, + { + "epoch": 0.02, + "learning_rate": 1.8982935251968243e-05, + "loss": 3.8864, + "step": 1894400 + }, + { + "epoch": 0.02, + "learning_rate": 1.8974549304457723e-05, + "loss": 3.8967, + "step": 1894912 + }, + { + "epoch": 0.02, + "learning_rate": 1.89661633569472e-05, + "loss": 3.9022, + "step": 1895424 + }, + { + "epoch": 0.02, + "learning_rate": 1.895777740943668e-05, + "loss": 3.8966, + "step": 1895936 + }, + { + "epoch": 0.02, + "learning_rate": 1.8949391461926162e-05, + "loss": 3.8936, + "step": 1896448 + }, + { + "epoch": 0.02, + "learning_rate": 1.8941005514415642e-05, + "loss": 3.8986, + "step": 1896960 + }, + { + "epoch": 0.02, + "learning_rate": 1.8932619566905122e-05, + "loss": 3.8895, + "step": 1897472 + }, + { + "epoch": 0.02, + "learning_rate": 1.892424999819833e-05, + "loss": 3.9077, + "step": 1897984 + }, + { + "epoch": 0.02, + "learning_rate": 1.891586405068781e-05, + "loss": 3.898, + "step": 1898496 + }, + { + "epoch": 0.02, + "learning_rate": 1.890747810317729e-05, + "loss": 3.9103, + "step": 1899008 + }, + { + "epoch": 0.02, + "learning_rate": 1.889909215566677e-05, + "loss": 3.8887, + "step": 1899520 + }, + { + "epoch": 0.02, + "learning_rate": 1.8890706208156255e-05, + "loss": 3.9007, + "step": 1900032 + }, + { + "epoch": 0.02, + "learning_rate": 1.8882320260645735e-05, + "loss": 3.9075, + "step": 1900544 + }, + { + "epoch": 0.02, + "learning_rate": 1.887393431313521e-05, + "loss": 3.8949, + "step": 1901056 + }, + { + "epoch": 0.02, + "learning_rate": 1.886554836562469e-05, + "loss": 3.8973, + "step": 1901568 + }, + { + "epoch": 0.02, + "learning_rate": 1.8857178796917904e-05, + "loss": 3.8991, + "step": 1902080 + }, + { + "epoch": 0.02, + "learning_rate": 1.884879284940738e-05, + "loss": 3.8994, + "step": 1902592 + }, + { + "epoch": 0.02, + "learning_rate": 1.8840406901896863e-05, + "loss": 3.9153, + "step": 1903104 + }, + { + "epoch": 0.02, + "learning_rate": 1.8832020954386343e-05, + "loss": 3.8947, + "step": 1903616 + }, + { + "epoch": 0.02, + "learning_rate": 1.8823651385679556e-05, + "loss": 3.9031, + "step": 1904128 + }, + { + "epoch": 0.02, + "learning_rate": 1.8815265438169032e-05, + "loss": 3.9014, + "step": 1904640 + }, + { + "epoch": 0.02, + "learning_rate": 1.8806895869462245e-05, + "loss": 3.8968, + "step": 1905152 + }, + { + "epoch": 0.02, + "learning_rate": 1.8798509921951725e-05, + "loss": 3.8911, + "step": 1905664 + }, + { + "epoch": 0.02, + "learning_rate": 1.8790123974441205e-05, + "loss": 3.8912, + "step": 1906176 + }, + { + "epoch": 0.02, + "learning_rate": 1.8781738026930685e-05, + "loss": 3.8959, + "step": 1906688 + }, + { + "epoch": 0.02, + "learning_rate": 1.8773368458223897e-05, + "loss": 3.8926, + "step": 1907200 + }, + { + "epoch": 0.02, + "learning_rate": 1.8764982510713377e-05, + "loss": 3.898, + "step": 1907712 + }, + { + "epoch": 0.03, + "eval_loss": 3.9966838359832764, + "eval_runtime": 293.1458, + "eval_samples_per_second": 1301.711, + "eval_steps_per_second": 40.679, + "step": 1908000 + }, + { + "epoch": 1.0, + "learning_rate": 1.8756596563202854e-05, + "loss": 3.8957, + "step": 1908224 + }, + { + "epoch": 1.0, + "learning_rate": 1.8748210615692334e-05, + "loss": 3.8943, + "step": 1908736 + }, + { + "epoch": 1.0, + "learning_rate": 1.8739824668181817e-05, + "loss": 3.8988, + "step": 1909248 + }, + { + "epoch": 1.0, + "learning_rate": 1.8731438720671297e-05, + "loss": 3.9061, + "step": 1909760 + }, + { + "epoch": 1.0, + "learning_rate": 1.8723052773160777e-05, + "loss": 3.9108, + "step": 1910272 + }, + { + "epoch": 1.0, + "learning_rate": 1.8714666825650257e-05, + "loss": 3.8977, + "step": 1910784 + }, + { + "epoch": 1.0, + "learning_rate": 1.8706297256943466e-05, + "loss": 3.9003, + "step": 1911296 + }, + { + "epoch": 1.0, + "learning_rate": 1.8697911309432946e-05, + "loss": 3.8917, + "step": 1911808 + }, + { + "epoch": 1.0, + "learning_rate": 1.8689525361922426e-05, + "loss": 3.8914, + "step": 1912320 + }, + { + "epoch": 1.0, + "learning_rate": 1.868113941441191e-05, + "loss": 3.9027, + "step": 1912832 + }, + { + "epoch": 1.0, + "learning_rate": 1.867276984570512e-05, + "loss": 3.9002, + "step": 1913344 + }, + { + "epoch": 1.0, + "learning_rate": 1.86643838981946e-05, + "loss": 3.894, + "step": 1913856 + }, + { + "epoch": 1.0, + "learning_rate": 1.8656014329487808e-05, + "loss": 3.9032, + "step": 1914368 + }, + { + "epoch": 1.0, + "learning_rate": 1.8647628381977287e-05, + "loss": 3.8884, + "step": 1914880 + }, + { + "epoch": 1.0, + "learning_rate": 1.863924243446677e-05, + "loss": 3.8915, + "step": 1915392 + }, + { + "epoch": 1.0, + "learning_rate": 1.863085648695625e-05, + "loss": 3.8791, + "step": 1915904 + }, + { + "epoch": 1.0, + "learning_rate": 1.862248691824946e-05, + "loss": 3.9002, + "step": 1916416 + }, + { + "epoch": 1.0, + "learning_rate": 1.861410097073894e-05, + "loss": 3.9012, + "step": 1916928 + }, + { + "epoch": 1.0, + "learning_rate": 1.860571502322842e-05, + "loss": 3.8892, + "step": 1917440 + }, + { + "epoch": 1.0, + "learning_rate": 1.85973290757179e-05, + "loss": 3.9051, + "step": 1917952 + }, + { + "epoch": 1.0, + "learning_rate": 1.858894312820738e-05, + "loss": 3.9042, + "step": 1918464 + }, + { + "epoch": 1.0, + "learning_rate": 1.858055718069686e-05, + "loss": 3.9053, + "step": 1918976 + }, + { + "epoch": 1.0, + "learning_rate": 1.857217123318634e-05, + "loss": 3.8986, + "step": 1919488 + }, + { + "epoch": 1.0, + "learning_rate": 1.856378528567582e-05, + "loss": 3.8978, + "step": 1920000 + }, + { + "epoch": 1.0, + "learning_rate": 1.85553993381653e-05, + "loss": 3.8982, + "step": 1920512 + }, + { + "epoch": 1.0, + "learning_rate": 1.854702976945851e-05, + "loss": 3.9047, + "step": 1921024 + }, + { + "epoch": 1.0, + "learning_rate": 1.853864382194799e-05, + "loss": 3.8861, + "step": 1921536 + }, + { + "epoch": 1.0, + "learning_rate": 1.8530257874437472e-05, + "loss": 3.899, + "step": 1922048 + }, + { + "epoch": 1.0, + "learning_rate": 1.8521888305730684e-05, + "loss": 3.8894, + "step": 1922560 + }, + { + "epoch": 1.0, + "learning_rate": 1.851350235822016e-05, + "loss": 3.896, + "step": 1923072 + }, + { + "epoch": 1.01, + "learning_rate": 1.850511641070964e-05, + "loss": 3.8982, + "step": 1923584 + }, + { + "epoch": 1.01, + "learning_rate": 1.849673046319912e-05, + "loss": 3.9058, + "step": 1924096 + }, + { + "epoch": 1.01, + "learning_rate": 1.84883445156886e-05, + "loss": 3.8962, + "step": 1924608 + }, + { + "epoch": 1.01, + "learning_rate": 1.847995856817808e-05, + "loss": 3.9116, + "step": 1925120 + }, + { + "epoch": 1.01, + "learning_rate": 1.8471572620667564e-05, + "loss": 3.8942, + "step": 1925632 + }, + { + "epoch": 1.01, + "learning_rate": 1.8463203051960773e-05, + "loss": 3.9007, + "step": 1926144 + }, + { + "epoch": 1.01, + "learning_rate": 1.8454833483253982e-05, + "loss": 3.9036, + "step": 1926656 + }, + { + "epoch": 1.01, + "learning_rate": 1.8446447535743462e-05, + "loss": 3.8833, + "step": 1927168 + }, + { + "epoch": 1.01, + "learning_rate": 1.8438061588232942e-05, + "loss": 3.8897, + "step": 1927680 + }, + { + "epoch": 1.01, + "learning_rate": 1.8429675640722426e-05, + "loss": 3.8891, + "step": 1928192 + }, + { + "epoch": 1.01, + "learning_rate": 1.8421289693211906e-05, + "loss": 3.8867, + "step": 1928704 + }, + { + "epoch": 1.01, + "learning_rate": 1.8412903745701385e-05, + "loss": 3.8955, + "step": 1929216 + }, + { + "epoch": 1.01, + "learning_rate": 1.8404517798190865e-05, + "loss": 3.9025, + "step": 1929728 + }, + { + "epoch": 1.01, + "learning_rate": 1.8396131850680342e-05, + "loss": 3.8896, + "step": 1930240 + }, + { + "epoch": 1.01, + "learning_rate": 1.8387745903169822e-05, + "loss": 3.8927, + "step": 1930752 + }, + { + "epoch": 1.01, + "learning_rate": 1.8379359955659302e-05, + "loss": 3.8928, + "step": 1931264 + }, + { + "epoch": 1.01, + "learning_rate": 1.8370974008148782e-05, + "loss": 3.899, + "step": 1931776 + }, + { + "epoch": 1.01, + "learning_rate": 1.8362588060638265e-05, + "loss": 3.8848, + "step": 1932288 + }, + { + "epoch": 1.01, + "learning_rate": 1.8354218491931474e-05, + "loss": 3.8785, + "step": 1932800 + }, + { + "epoch": 1.01, + "learning_rate": 1.8345832544420954e-05, + "loss": 3.9055, + "step": 1933312 + }, + { + "epoch": 1.01, + "learning_rate": 1.8337446596910434e-05, + "loss": 3.8992, + "step": 1933824 + }, + { + "epoch": 1.01, + "learning_rate": 1.8329060649399914e-05, + "loss": 3.9094, + "step": 1934336 + }, + { + "epoch": 1.01, + "learning_rate": 1.8320691080693127e-05, + "loss": 3.8884, + "step": 1934848 + }, + { + "epoch": 1.01, + "learning_rate": 1.8312305133182607e-05, + "loss": 3.8918, + "step": 1935360 + }, + { + "epoch": 1.01, + "learning_rate": 1.8303919185672087e-05, + "loss": 3.8927, + "step": 1935872 + }, + { + "epoch": 1.01, + "learning_rate": 1.8295549616965296e-05, + "loss": 3.8912, + "step": 1936384 + }, + { + "epoch": 1.01, + "learning_rate": 1.8287163669454776e-05, + "loss": 3.9051, + "step": 1936896 + }, + { + "epoch": 1.01, + "learning_rate": 1.8278777721944256e-05, + "loss": 3.878, + "step": 1937408 + }, + { + "epoch": 1.01, + "learning_rate": 1.8270391774433736e-05, + "loss": 3.9196, + "step": 1937920 + }, + { + "epoch": 1.01, + "learning_rate": 1.826200582692322e-05, + "loss": 3.8948, + "step": 1938432 + }, + { + "epoch": 1.01, + "learning_rate": 1.8253619879412695e-05, + "loss": 3.8735, + "step": 1938944 + }, + { + "epoch": 1.01, + "learning_rate": 1.8245250310705908e-05, + "loss": 3.9017, + "step": 1939456 + }, + { + "epoch": 1.01, + "learning_rate": 1.8236864363195388e-05, + "loss": 3.8895, + "step": 1939968 + }, + { + "epoch": 1.01, + "learning_rate": 1.8228478415684868e-05, + "loss": 3.8753, + "step": 1940480 + }, + { + "epoch": 1.01, + "learning_rate": 1.8220092468174348e-05, + "loss": 3.8999, + "step": 1940992 + }, + { + "epoch": 1.01, + "learning_rate": 1.8211706520663828e-05, + "loss": 3.9005, + "step": 1941504 + }, + { + "epoch": 1.01, + "learning_rate": 1.8203320573153308e-05, + "loss": 3.8869, + "step": 1942016 + }, + { + "epoch": 1.01, + "learning_rate": 1.8194934625642788e-05, + "loss": 3.8949, + "step": 1942528 + }, + { + "epoch": 1.01, + "learning_rate": 1.8186565056935997e-05, + "loss": 3.8739, + "step": 1943040 + }, + { + "epoch": 1.01, + "learning_rate": 1.8178179109425477e-05, + "loss": 3.8872, + "step": 1943552 + }, + { + "epoch": 1.01, + "learning_rate": 1.8169793161914957e-05, + "loss": 3.8958, + "step": 1944064 + }, + { + "epoch": 1.01, + "learning_rate": 1.816142359320817e-05, + "loss": 3.8886, + "step": 1944576 + }, + { + "epoch": 1.01, + "learning_rate": 1.815303764569765e-05, + "loss": 3.8996, + "step": 1945088 + }, + { + "epoch": 1.01, + "learning_rate": 1.814465169818713e-05, + "loss": 3.8867, + "step": 1945600 + }, + { + "epoch": 1.01, + "learning_rate": 1.813626575067661e-05, + "loss": 3.9095, + "step": 1946112 + }, + { + "epoch": 1.01, + "learning_rate": 1.812787980316609e-05, + "loss": 3.8904, + "step": 1946624 + }, + { + "epoch": 1.01, + "learning_rate": 1.811949385565557e-05, + "loss": 3.8956, + "step": 1947136 + }, + { + "epoch": 1.01, + "learning_rate": 1.811110790814505e-05, + "loss": 3.8934, + "step": 1947648 + }, + { + "epoch": 1.01, + "learning_rate": 1.810272196063453e-05, + "loss": 3.8894, + "step": 1948160 + }, + { + "epoch": 1.01, + "learning_rate": 1.809433601312401e-05, + "loss": 3.897, + "step": 1948672 + }, + { + "epoch": 1.01, + "learning_rate": 1.808596644441722e-05, + "loss": 3.8903, + "step": 1949184 + }, + { + "epoch": 1.01, + "learning_rate": 1.8077580496906698e-05, + "loss": 3.8972, + "step": 1949696 + }, + { + "epoch": 1.01, + "learning_rate": 1.8069194549396178e-05, + "loss": 3.899, + "step": 1950208 + }, + { + "epoch": 1.01, + "learning_rate": 1.8060824980689394e-05, + "loss": 3.8886, + "step": 1950720 + }, + { + "epoch": 1.01, + "learning_rate": 1.8052439033178874e-05, + "loss": 3.8808, + "step": 1951232 + }, + { + "epoch": 1.01, + "learning_rate": 1.804405308566835e-05, + "loss": 3.8911, + "step": 1951744 + }, + { + "epoch": 1.01, + "learning_rate": 1.803566713815783e-05, + "loss": 3.8981, + "step": 1952256 + }, + { + "epoch": 1.01, + "learning_rate": 1.802728119064731e-05, + "loss": 3.886, + "step": 1952768 + }, + { + "epoch": 1.01, + "learning_rate": 1.801889524313679e-05, + "loss": 3.8945, + "step": 1953280 + }, + { + "epoch": 1.02, + "learning_rate": 1.801050929562627e-05, + "loss": 3.8843, + "step": 1953792 + }, + { + "epoch": 1.02, + "learning_rate": 1.800212334811575e-05, + "loss": 3.888, + "step": 1954304 + }, + { + "epoch": 1.02, + "learning_rate": 1.7993737400605233e-05, + "loss": 3.8846, + "step": 1954816 + }, + { + "epoch": 1.02, + "learning_rate": 1.7985367831898442e-05, + "loss": 3.889, + "step": 1955328 + }, + { + "epoch": 1.02, + "learning_rate": 1.7976981884387922e-05, + "loss": 3.9044, + "step": 1955840 + }, + { + "epoch": 1.02, + "learning_rate": 1.7968595936877402e-05, + "loss": 3.8929, + "step": 1956352 + }, + { + "epoch": 1.02, + "learning_rate": 1.796020998936688e-05, + "loss": 3.8978, + "step": 1956864 + }, + { + "epoch": 1.02, + "learning_rate": 1.7951840420660095e-05, + "loss": 3.8892, + "step": 1957376 + }, + { + "epoch": 1.02, + "learning_rate": 1.7943454473149575e-05, + "loss": 3.8885, + "step": 1957888 + }, + { + "epoch": 1.02, + "learning_rate": 1.7935068525639055e-05, + "loss": 3.8904, + "step": 1958400 + }, + { + "epoch": 1.02, + "learning_rate": 1.792668257812853e-05, + "loss": 3.8987, + "step": 1958912 + }, + { + "epoch": 1.02, + "learning_rate": 1.791829663061801e-05, + "loss": 3.8974, + "step": 1959424 + }, + { + "epoch": 1.02, + "learning_rate": 1.790991068310749e-05, + "loss": 3.8977, + "step": 1959936 + }, + { + "epoch": 1.02, + "learning_rate": 1.790152473559697e-05, + "loss": 3.8943, + "step": 1960448 + }, + { + "epoch": 1.02, + "learning_rate": 1.789313878808645e-05, + "loss": 3.8898, + "step": 1960960 + }, + { + "epoch": 1.02, + "learning_rate": 1.7884752840575934e-05, + "loss": 3.8951, + "step": 1961472 + }, + { + "epoch": 1.02, + "learning_rate": 1.7876399650672876e-05, + "loss": 3.8887, + "step": 1961984 + }, + { + "epoch": 1.02, + "learning_rate": 1.7868013703162353e-05, + "loss": 3.8852, + "step": 1962496 + }, + { + "epoch": 1.02, + "learning_rate": 1.7859627755651833e-05, + "loss": 3.8953, + "step": 1963008 + }, + { + "epoch": 1.02, + "learning_rate": 1.7851241808141313e-05, + "loss": 3.8872, + "step": 1963520 + }, + { + "epoch": 1.02, + "learning_rate": 1.7842855860630796e-05, + "loss": 3.8863, + "step": 1964032 + }, + { + "epoch": 1.02, + "learning_rate": 1.7834469913120276e-05, + "loss": 3.8849, + "step": 1964544 + }, + { + "epoch": 1.02, + "learning_rate": 1.7826100344413485e-05, + "loss": 3.8844, + "step": 1965056 + }, + { + "epoch": 1.02, + "learning_rate": 1.7817714396902965e-05, + "loss": 3.893, + "step": 1965568 + }, + { + "epoch": 1.02, + "learning_rate": 1.7809328449392445e-05, + "loss": 3.8868, + "step": 1966080 + }, + { + "epoch": 1.02, + "learning_rate": 1.7800942501881925e-05, + "loss": 3.8991, + "step": 1966592 + }, + { + "epoch": 1.02, + "learning_rate": 1.7792556554371405e-05, + "loss": 3.8998, + "step": 1967104 + }, + { + "epoch": 1.02, + "learning_rate": 1.7784186985664617e-05, + "loss": 3.9051, + "step": 1967616 + }, + { + "epoch": 1.02, + "learning_rate": 1.7775801038154097e-05, + "loss": 3.8915, + "step": 1968128 + }, + { + "epoch": 1.02, + "learning_rate": 1.7767431469447306e-05, + "loss": 3.8908, + "step": 1968640 + }, + { + "epoch": 1.02, + "learning_rate": 1.7759045521936786e-05, + "loss": 3.8826, + "step": 1969152 + }, + { + "epoch": 1.02, + "learning_rate": 1.7750659574426266e-05, + "loss": 3.8987, + "step": 1969664 + }, + { + "epoch": 1.02, + "learning_rate": 1.774227362691575e-05, + "loss": 3.896, + "step": 1970176 + }, + { + "epoch": 1.02, + "learning_rate": 1.773388767940523e-05, + "loss": 3.8793, + "step": 1970688 + }, + { + "epoch": 1.02, + "learning_rate": 1.772551811069844e-05, + "loss": 3.8898, + "step": 1971200 + }, + { + "epoch": 1.02, + "learning_rate": 1.771713216318792e-05, + "loss": 3.894, + "step": 1971712 + }, + { + "epoch": 1.02, + "learning_rate": 1.77087462156774e-05, + "loss": 3.896, + "step": 1972224 + }, + { + "epoch": 1.02, + "learning_rate": 1.770037664697061e-05, + "loss": 3.8884, + "step": 1972736 + }, + { + "epoch": 1.02, + "learning_rate": 1.769199069946009e-05, + "loss": 3.8893, + "step": 1973248 + }, + { + "epoch": 1.02, + "learning_rate": 1.768360475194957e-05, + "loss": 3.8842, + "step": 1973760 + }, + { + "epoch": 1.02, + "learning_rate": 1.767521880443905e-05, + "loss": 3.9025, + "step": 1974272 + }, + { + "epoch": 1.02, + "learning_rate": 1.766683285692853e-05, + "loss": 3.8917, + "step": 1974784 + }, + { + "epoch": 1.02, + "learning_rate": 1.7658446909418007e-05, + "loss": 3.9043, + "step": 1975296 + }, + { + "epoch": 1.02, + "learning_rate": 1.7650060961907487e-05, + "loss": 3.884, + "step": 1975808 + }, + { + "epoch": 1.02, + "learning_rate": 1.7641675014396967e-05, + "loss": 3.8988, + "step": 1976320 + }, + { + "epoch": 1.02, + "learning_rate": 1.763328906688645e-05, + "loss": 3.9028, + "step": 1976832 + }, + { + "epoch": 1.02, + "learning_rate": 1.762490311937593e-05, + "loss": 3.8873, + "step": 1977344 + }, + { + "epoch": 1.02, + "learning_rate": 1.761651717186541e-05, + "loss": 3.8956, + "step": 1977856 + }, + { + "epoch": 1.02, + "learning_rate": 1.760813122435489e-05, + "loss": 3.8942, + "step": 1978368 + }, + { + "epoch": 1.02, + "learning_rate": 1.7599745276844367e-05, + "loss": 3.9003, + "step": 1978880 + }, + { + "epoch": 1.02, + "learning_rate": 1.7591359329333847e-05, + "loss": 3.9079, + "step": 1979392 + }, + { + "epoch": 1.02, + "learning_rate": 1.7582973381823327e-05, + "loss": 3.8952, + "step": 1979904 + }, + { + "epoch": 1.02, + "learning_rate": 1.757458743431281e-05, + "loss": 3.8959, + "step": 1980416 + }, + { + "epoch": 1.02, + "learning_rate": 1.756620148680229e-05, + "loss": 3.8976, + "step": 1980928 + }, + { + "epoch": 1.02, + "learning_rate": 1.75578319180955e-05, + "loss": 3.8928, + "step": 1981440 + }, + { + "epoch": 1.02, + "learning_rate": 1.754944597058498e-05, + "loss": 3.8878, + "step": 1981952 + }, + { + "epoch": 1.02, + "learning_rate": 1.754106002307446e-05, + "loss": 3.8869, + "step": 1982464 + }, + { + "epoch": 1.02, + "learning_rate": 1.753267407556394e-05, + "loss": 3.8889, + "step": 1982976 + }, + { + "epoch": 1.02, + "learning_rate": 1.7524304506857152e-05, + "loss": 3.8891, + "step": 1983488 + }, + { + "epoch": 1.02, + "learning_rate": 1.751591855934663e-05, + "loss": 3.8925, + "step": 1984000 + }, + { + "epoch": 1.03, + "eval_loss": 3.9946038722991943, + "eval_runtime": 301.4588, + "eval_samples_per_second": 1265.815, + "eval_steps_per_second": 39.558, + "step": 1984320 + }, + { + "epoch": 0.0, + "learning_rate": 1.750753261183611e-05, + "loss": 3.8923, + "step": 1984512 + }, + { + "epoch": 0.0, + "learning_rate": 1.749914666432559e-05, + "loss": 3.8873, + "step": 1985024 + }, + { + "epoch": 0.0, + "learning_rate": 1.749076071681507e-05, + "loss": 3.8927, + "step": 1985536 + }, + { + "epoch": 0.0, + "learning_rate": 1.7482374769304548e-05, + "loss": 3.8992, + "step": 1986048 + }, + { + "epoch": 0.0, + "learning_rate": 1.7473988821794028e-05, + "loss": 3.9066, + "step": 1986560 + }, + { + "epoch": 0.0, + "learning_rate": 1.746560287428351e-05, + "loss": 3.8932, + "step": 1987072 + }, + { + "epoch": 0.0, + "learning_rate": 1.745721692677299e-05, + "loss": 3.8966, + "step": 1987584 + }, + { + "epoch": 0.0, + "learning_rate": 1.744883097926247e-05, + "loss": 3.8874, + "step": 1988096 + }, + { + "epoch": 0.0, + "learning_rate": 1.744044503175195e-05, + "loss": 3.8858, + "step": 1988608 + }, + { + "epoch": 0.0, + "learning_rate": 1.7432059084241428e-05, + "loss": 3.8947, + "step": 1989120 + }, + { + "epoch": 0.0, + "learning_rate": 1.7423673136730908e-05, + "loss": 3.8993, + "step": 1989632 + }, + { + "epoch": 0.0, + "learning_rate": 1.7415287189220388e-05, + "loss": 3.8901, + "step": 1990144 + }, + { + "epoch": 0.0, + "learning_rate": 1.7406917620513604e-05, + "loss": 3.8974, + "step": 1990656 + }, + { + "epoch": 0.0, + "learning_rate": 1.739853167300308e-05, + "loss": 3.8833, + "step": 1991168 + }, + { + "epoch": 0.0, + "learning_rate": 1.739014572549256e-05, + "loss": 3.8898, + "step": 1991680 + }, + { + "epoch": 0.0, + "learning_rate": 1.738175977798204e-05, + "loss": 3.8712, + "step": 1992192 + }, + { + "epoch": 0.0, + "learning_rate": 1.737337383047152e-05, + "loss": 3.8957, + "step": 1992704 + }, + { + "epoch": 0.0, + "learning_rate": 1.736500426176473e-05, + "loss": 3.895, + "step": 1993216 + }, + { + "epoch": 0.0, + "learning_rate": 1.7356618314254213e-05, + "loss": 3.8844, + "step": 1993728 + }, + { + "epoch": 0.0, + "learning_rate": 1.7348232366743692e-05, + "loss": 3.8993, + "step": 1994240 + }, + { + "epoch": 0.0, + "learning_rate": 1.7339846419233172e-05, + "loss": 3.903, + "step": 1994752 + }, + { + "epoch": 0.0, + "learning_rate": 1.7331460471722652e-05, + "loss": 3.9025, + "step": 1995264 + }, + { + "epoch": 0.0, + "learning_rate": 1.7323074524212132e-05, + "loss": 3.8911, + "step": 1995776 + }, + { + "epoch": 0.0, + "learning_rate": 1.731468857670161e-05, + "loss": 3.8942, + "step": 1996288 + }, + { + "epoch": 0.0, + "learning_rate": 1.730630262919109e-05, + "loss": 3.8956, + "step": 1996800 + }, + { + "epoch": 0.0, + "learning_rate": 1.729791668168057e-05, + "loss": 3.8998, + "step": 1997312 + }, + { + "epoch": 0.0, + "learning_rate": 1.7289530734170052e-05, + "loss": 3.8805, + "step": 1997824 + }, + { + "epoch": 0.0, + "learning_rate": 1.7281144786659532e-05, + "loss": 3.8909, + "step": 1998336 + }, + { + "epoch": 0.0, + "learning_rate": 1.727277521795274e-05, + "loss": 3.889, + "step": 1998848 + }, + { + "epoch": 0.0, + "learning_rate": 1.726438927044222e-05, + "loss": 3.8874, + "step": 1999360 + }, + { + "epoch": 0.01, + "learning_rate": 1.72560033229317e-05, + "loss": 3.8935, + "step": 1999872 + }, + { + "epoch": 0.01, + "learning_rate": 1.724761737542118e-05, + "loss": 3.8997, + "step": 2000384 + }, + { + "epoch": 0.01, + "learning_rate": 1.7239264185518126e-05, + "loss": 3.8947, + "step": 2000896 + }, + { + "epoch": 0.01, + "learning_rate": 1.7230878238007606e-05, + "loss": 3.9027, + "step": 2001408 + }, + { + "epoch": 0.01, + "learning_rate": 1.7222492290497083e-05, + "loss": 3.8893, + "step": 2001920 + }, + { + "epoch": 0.01, + "learning_rate": 1.7214122721790295e-05, + "loss": 3.8966, + "step": 2002432 + }, + { + "epoch": 0.01, + "learning_rate": 1.7205736774279775e-05, + "loss": 3.9013, + "step": 2002944 + }, + { + "epoch": 0.01, + "learning_rate": 1.719735082676926e-05, + "loss": 3.8778, + "step": 2003456 + }, + { + "epoch": 0.01, + "learning_rate": 1.7188964879258735e-05, + "loss": 3.8826, + "step": 2003968 + }, + { + "epoch": 0.01, + "learning_rate": 1.7180578931748215e-05, + "loss": 3.885, + "step": 2004480 + }, + { + "epoch": 0.01, + "learning_rate": 1.7172192984237695e-05, + "loss": 3.8775, + "step": 2004992 + }, + { + "epoch": 0.01, + "learning_rate": 1.7163807036727175e-05, + "loss": 3.8898, + "step": 2005504 + }, + { + "epoch": 0.01, + "learning_rate": 1.7155421089216655e-05, + "loss": 3.8999, + "step": 2006016 + }, + { + "epoch": 0.01, + "learning_rate": 1.7147035141706135e-05, + "loss": 3.8853, + "step": 2006528 + }, + { + "epoch": 0.01, + "learning_rate": 1.7138649194195615e-05, + "loss": 3.8876, + "step": 2007040 + }, + { + "epoch": 0.01, + "learning_rate": 1.7130263246685095e-05, + "loss": 3.8919, + "step": 2007552 + }, + { + "epoch": 0.01, + "learning_rate": 1.7121877299174575e-05, + "loss": 3.8941, + "step": 2008064 + }, + { + "epoch": 0.01, + "learning_rate": 1.7113507730467787e-05, + "loss": 3.8802, + "step": 2008576 + }, + { + "epoch": 0.01, + "learning_rate": 1.7105121782957264e-05, + "loss": 3.872, + "step": 2009088 + }, + { + "epoch": 0.01, + "learning_rate": 1.7096735835446744e-05, + "loss": 3.897, + "step": 2009600 + }, + { + "epoch": 0.01, + "learning_rate": 1.7088349887936227e-05, + "loss": 3.8967, + "step": 2010112 + }, + { + "epoch": 0.01, + "learning_rate": 1.7079963940425707e-05, + "loss": 3.9063, + "step": 2010624 + }, + { + "epoch": 0.01, + "learning_rate": 1.7071577992915187e-05, + "loss": 3.8828, + "step": 2011136 + }, + { + "epoch": 0.01, + "learning_rate": 1.7063192045404667e-05, + "loss": 3.885, + "step": 2011648 + }, + { + "epoch": 0.01, + "learning_rate": 1.7054806097894147e-05, + "loss": 3.8886, + "step": 2012160 + }, + { + "epoch": 0.01, + "learning_rate": 1.704646928679482e-05, + "loss": 3.8851, + "step": 2012672 + }, + { + "epoch": 0.01, + "learning_rate": 1.70380833392843e-05, + "loss": 3.9, + "step": 2013184 + }, + { + "epoch": 0.01, + "learning_rate": 1.702969739177378e-05, + "loss": 3.8709, + "step": 2013696 + }, + { + "epoch": 0.01, + "learning_rate": 1.702131144426326e-05, + "loss": 3.9151, + "step": 2014208 + }, + { + "epoch": 0.01, + "learning_rate": 1.7012925496752737e-05, + "loss": 3.8936, + "step": 2014720 + }, + { + "epoch": 0.01, + "learning_rate": 1.7004539549242217e-05, + "loss": 3.8706, + "step": 2015232 + }, + { + "epoch": 0.01, + "learning_rate": 1.6996153601731697e-05, + "loss": 3.8934, + "step": 2015744 + }, + { + "epoch": 0.01, + "learning_rate": 1.6987767654221177e-05, + "loss": 3.8842, + "step": 2016256 + }, + { + "epoch": 0.01, + "learning_rate": 1.697938170671066e-05, + "loss": 3.8714, + "step": 2016768 + }, + { + "epoch": 0.01, + "learning_rate": 1.697099575920014e-05, + "loss": 3.8966, + "step": 2017280 + }, + { + "epoch": 0.01, + "learning_rate": 1.696262619049335e-05, + "loss": 3.8959, + "step": 2017792 + }, + { + "epoch": 0.01, + "learning_rate": 1.695424024298283e-05, + "loss": 3.8813, + "step": 2018304 + }, + { + "epoch": 0.01, + "learning_rate": 1.694585429547231e-05, + "loss": 3.8938, + "step": 2018816 + }, + { + "epoch": 0.01, + "learning_rate": 1.693746834796179e-05, + "loss": 3.8677, + "step": 2019328 + }, + { + "epoch": 0.01, + "learning_rate": 1.6929098779255002e-05, + "loss": 3.883, + "step": 2019840 + }, + { + "epoch": 0.01, + "learning_rate": 1.6920712831744482e-05, + "loss": 3.8839, + "step": 2020352 + }, + { + "epoch": 0.01, + "learning_rate": 1.6912326884233962e-05, + "loss": 3.8869, + "step": 2020864 + }, + { + "epoch": 0.01, + "learning_rate": 1.6903940936723442e-05, + "loss": 3.892, + "step": 2021376 + }, + { + "epoch": 0.01, + "learning_rate": 1.689555498921292e-05, + "loss": 3.8851, + "step": 2021888 + }, + { + "epoch": 0.01, + "learning_rate": 1.68871690417024e-05, + "loss": 3.9069, + "step": 2022400 + }, + { + "epoch": 0.01, + "learning_rate": 1.6878783094191882e-05, + "loss": 3.8861, + "step": 2022912 + }, + { + "epoch": 0.01, + "learning_rate": 1.687039714668136e-05, + "loss": 3.8935, + "step": 2023424 + }, + { + "epoch": 0.01, + "learning_rate": 1.686202757797457e-05, + "loss": 3.8864, + "step": 2023936 + }, + { + "epoch": 0.01, + "learning_rate": 1.685364163046405e-05, + "loss": 3.8838, + "step": 2024448 + }, + { + "epoch": 0.01, + "learning_rate": 1.684525568295353e-05, + "loss": 3.8939, + "step": 2024960 + }, + { + "epoch": 0.01, + "learning_rate": 1.6836886114246743e-05, + "loss": 3.8866, + "step": 2025472 + }, + { + "epoch": 0.01, + "learning_rate": 1.6828500166736223e-05, + "loss": 3.8906, + "step": 2025984 + }, + { + "epoch": 0.01, + "learning_rate": 1.6820114219225703e-05, + "loss": 3.8972, + "step": 2026496 + }, + { + "epoch": 0.01, + "learning_rate": 1.6811728271715183e-05, + "loss": 3.8844, + "step": 2027008 + }, + { + "epoch": 0.01, + "learning_rate": 1.6803342324204663e-05, + "loss": 3.8743, + "step": 2027520 + }, + { + "epoch": 0.01, + "learning_rate": 1.6794956376694143e-05, + "loss": 3.8849, + "step": 2028032 + }, + { + "epoch": 0.01, + "learning_rate": 1.6786586807987352e-05, + "loss": 3.8966, + "step": 2028544 + }, + { + "epoch": 0.01, + "learning_rate": 1.6778200860476835e-05, + "loss": 3.877, + "step": 2029056 + }, + { + "epoch": 0.01, + "learning_rate": 1.6769814912966315e-05, + "loss": 3.8941, + "step": 2029568 + }, + { + "epoch": 0.01, + "learning_rate": 1.6761428965455795e-05, + "loss": 3.8849, + "step": 2030080 + }, + { + "epoch": 0.02, + "learning_rate": 1.6753043017945275e-05, + "loss": 3.8787, + "step": 2030592 + }, + { + "epoch": 0.02, + "learning_rate": 1.6744673449238484e-05, + "loss": 3.8805, + "step": 2031104 + }, + { + "epoch": 0.02, + "learning_rate": 1.6736287501727964e-05, + "loss": 3.8839, + "step": 2031616 + }, + { + "epoch": 0.02, + "learning_rate": 1.6727901554217444e-05, + "loss": 3.9027, + "step": 2032128 + }, + { + "epoch": 0.02, + "learning_rate": 1.6719515606706924e-05, + "loss": 3.8855, + "step": 2032640 + }, + { + "epoch": 0.02, + "learning_rate": 1.6711129659196404e-05, + "loss": 3.8923, + "step": 2033152 + }, + { + "epoch": 0.02, + "learning_rate": 1.6702743711685884e-05, + "loss": 3.8838, + "step": 2033664 + }, + { + "epoch": 0.02, + "learning_rate": 1.6694357764175364e-05, + "loss": 3.8811, + "step": 2034176 + }, + { + "epoch": 0.02, + "learning_rate": 1.6685971816664844e-05, + "loss": 3.8837, + "step": 2034688 + }, + { + "epoch": 0.02, + "learning_rate": 1.6677585869154324e-05, + "loss": 3.8954, + "step": 2035200 + }, + { + "epoch": 0.02, + "learning_rate": 1.6669216300447536e-05, + "loss": 3.8949, + "step": 2035712 + }, + { + "epoch": 0.02, + "learning_rate": 1.6660830352937016e-05, + "loss": 3.8909, + "step": 2036224 + }, + { + "epoch": 0.02, + "learning_rate": 1.6652444405426496e-05, + "loss": 3.8907, + "step": 2036736 + }, + { + "epoch": 0.02, + "learning_rate": 1.6644074836719705e-05, + "loss": 3.8818, + "step": 2037248 + }, + { + "epoch": 0.02, + "learning_rate": 1.6635688889209185e-05, + "loss": 3.8915, + "step": 2037760 + }, + { + "epoch": 0.02, + "learning_rate": 1.6627302941698665e-05, + "loss": 3.8858, + "step": 2038272 + }, + { + "epoch": 0.02, + "learning_rate": 1.6618916994188145e-05, + "loss": 3.8815, + "step": 2038784 + }, + { + "epoch": 0.02, + "learning_rate": 1.661053104667763e-05, + "loss": 3.887, + "step": 2039296 + }, + { + "epoch": 0.02, + "learning_rate": 1.6602145099167105e-05, + "loss": 3.8841, + "step": 2039808 + }, + { + "epoch": 0.02, + "learning_rate": 1.6593759151656585e-05, + "loss": 3.884, + "step": 2040320 + }, + { + "epoch": 0.02, + "learning_rate": 1.6585373204146065e-05, + "loss": 3.8808, + "step": 2040832 + }, + { + "epoch": 0.02, + "learning_rate": 1.6577020014243007e-05, + "loss": 3.8786, + "step": 2041344 + }, + { + "epoch": 0.02, + "learning_rate": 1.656863406673249e-05, + "loss": 3.8862, + "step": 2041856 + }, + { + "epoch": 0.02, + "learning_rate": 1.656024811922197e-05, + "loss": 3.8879, + "step": 2042368 + }, + { + "epoch": 0.02, + "learning_rate": 1.655186217171145e-05, + "loss": 3.8896, + "step": 2042880 + }, + { + "epoch": 0.02, + "learning_rate": 1.654347622420093e-05, + "loss": 3.8958, + "step": 2043392 + }, + { + "epoch": 0.02, + "learning_rate": 1.6535090276690407e-05, + "loss": 3.9015, + "step": 2043904 + }, + { + "epoch": 0.02, + "learning_rate": 1.6526704329179887e-05, + "loss": 3.8858, + "step": 2044416 + }, + { + "epoch": 0.02, + "learning_rate": 1.6518318381669366e-05, + "loss": 3.8866, + "step": 2044928 + }, + { + "epoch": 0.02, + "learning_rate": 1.650994881296258e-05, + "loss": 3.8785, + "step": 2045440 + }, + { + "epoch": 0.02, + "learning_rate": 1.650156286545206e-05, + "loss": 3.8907, + "step": 2045952 + }, + { + "epoch": 0.02, + "learning_rate": 1.649317691794154e-05, + "loss": 3.889, + "step": 2046464 + }, + { + "epoch": 0.02, + "learning_rate": 1.648479097043102e-05, + "loss": 3.8783, + "step": 2046976 + }, + { + "epoch": 0.02, + "learning_rate": 1.6476421401724228e-05, + "loss": 3.8819, + "step": 2047488 + }, + { + "epoch": 0.02, + "learning_rate": 1.6468035454213708e-05, + "loss": 3.8927, + "step": 2048000 + }, + { + "epoch": 0.02, + "learning_rate": 1.645964950670319e-05, + "loss": 3.8912, + "step": 2048512 + }, + { + "epoch": 0.02, + "learning_rate": 1.645126355919267e-05, + "loss": 3.8815, + "step": 2049024 + }, + { + "epoch": 0.02, + "learning_rate": 1.644287761168215e-05, + "loss": 3.8845, + "step": 2049536 + }, + { + "epoch": 0.02, + "learning_rate": 1.643450804297536e-05, + "loss": 3.8836, + "step": 2050048 + }, + { + "epoch": 0.02, + "learning_rate": 1.642612209546484e-05, + "loss": 3.8932, + "step": 2050560 + }, + { + "epoch": 0.02, + "learning_rate": 1.6417752526758053e-05, + "loss": 3.8907, + "step": 2051072 + }, + { + "epoch": 0.02, + "learning_rate": 1.6409366579247533e-05, + "loss": 3.8992, + "step": 2051584 + }, + { + "epoch": 0.02, + "learning_rate": 1.6400980631737013e-05, + "loss": 3.8804, + "step": 2052096 + }, + { + "epoch": 0.02, + "learning_rate": 1.6392611063030225e-05, + "loss": 3.8941, + "step": 2052608 + }, + { + "epoch": 0.02, + "learning_rate": 1.63842251155197e-05, + "loss": 3.8959, + "step": 2053120 + }, + { + "epoch": 0.02, + "learning_rate": 1.637583916800918e-05, + "loss": 3.88, + "step": 2053632 + }, + { + "epoch": 0.02, + "learning_rate": 1.636745322049866e-05, + "loss": 3.8881, + "step": 2054144 + }, + { + "epoch": 0.02, + "learning_rate": 1.6359067272988145e-05, + "loss": 3.8914, + "step": 2054656 + }, + { + "epoch": 0.02, + "learning_rate": 1.6350681325477625e-05, + "loss": 3.8978, + "step": 2055168 + }, + { + "epoch": 0.02, + "learning_rate": 1.6342295377967105e-05, + "loss": 3.8989, + "step": 2055680 + }, + { + "epoch": 0.02, + "learning_rate": 1.633390943045658e-05, + "loss": 3.8872, + "step": 2056192 + }, + { + "epoch": 0.02, + "learning_rate": 1.632552348294606e-05, + "loss": 3.8922, + "step": 2056704 + }, + { + "epoch": 0.02, + "learning_rate": 1.631713753543554e-05, + "loss": 3.8933, + "step": 2057216 + }, + { + "epoch": 0.02, + "learning_rate": 1.630875158792502e-05, + "loss": 3.8873, + "step": 2057728 + }, + { + "epoch": 0.02, + "learning_rate": 1.63003656404145e-05, + "loss": 3.8838, + "step": 2058240 + }, + { + "epoch": 0.02, + "learning_rate": 1.6292012450511446e-05, + "loss": 3.8814, + "step": 2058752 + }, + { + "epoch": 0.02, + "learning_rate": 1.6283626503000926e-05, + "loss": 3.8804, + "step": 2059264 + }, + { + "epoch": 0.02, + "learning_rate": 1.6275240555490406e-05, + "loss": 3.8872, + "step": 2059776 + }, + { + "epoch": 0.02, + "learning_rate": 1.6266854607979883e-05, + "loss": 3.8861, + "step": 2060288 + }, + { + "epoch": 0.03, + "eval_loss": 3.9931588172912598, + "eval_runtime": 293.1849, + "eval_samples_per_second": 1301.537, + "eval_steps_per_second": 40.674, + "step": 2060640 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 8.353164134722234e+17, + "trial_name": null, + "trial_params": null +}